diff options
44 files changed, 397 insertions, 326 deletions
@@ -1031,7 +1031,7 @@ LDFLAGS_vmlinux += $(call ld-option, -X,) endif ifeq ($(CONFIG_RELR),y) -LDFLAGS_vmlinux += --pack-dyn-relocs=relr +LDFLAGS_vmlinux += --pack-dyn-relocs=relr --use-android-relr-tags endif # We never want expected sections to be placed heuristically by the diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h index 8a078fc662ac..477703578caa 100644 --- a/arch/arm64/include/asm/alternative-macros.h +++ b/arch/arm64/include/asm/alternative-macros.h @@ -197,11 +197,6 @@ alternative_endif #define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...) \ alternative_insn insn1, insn2, cap, IS_ENABLED(cfg) -.macro user_alt, label, oldinstr, newinstr, cond -9999: alternative_insn "\oldinstr", "\newinstr", \cond - _asm_extable 9999b, \label -.endm - #endif /* __ASSEMBLY__ */ /* diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 934b9be582d2..4ad22c3135db 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -124,7 +124,8 @@ static inline u32 gic_read_rpr(void) #define gic_read_lpir(c) readq_relaxed(c) #define gic_write_lpir(v, c) writeq_relaxed(v, c) -#define gic_flush_dcache_to_poc(a,l) __flush_dcache_area((a), (l)) +#define gic_flush_dcache_to_poc(a,l) \ + dcache_clean_inval_poc((unsigned long)(a), (unsigned long)(a)+(l)) #define gits_read_baser(c) readq_relaxed(c) #define gits_write_baser(v, c) writeq_relaxed(v, c) diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 8418c1bd8f04..89faca0e740d 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -130,15 +130,27 @@ alternative_endif .endm /* - * Emit an entry into the exception table + * Create an exception table entry for `insn`, which will branch to `fixup` + * when an unhandled fault is taken. */ - .macro _asm_extable, from, to + .macro _asm_extable, insn, fixup .pushsection __ex_table, "a" .align 3 - .long (\from - .), (\to - .) + .long (\insn - .), (\fixup - .) .popsection .endm +/* + * Create an exception table entry for `insn` if `fixup` is provided. Otherwise + * do nothing. + */ + .macro _cond_extable, insn, fixup + .ifnc \fixup, + _asm_extable \insn, \fixup + .endif + .endm + + #define USER(l, x...) \ 9999: x; \ _asm_extable 9999b, l @@ -232,17 +244,25 @@ lr .req x30 // link register * @dst: destination register */ #if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__) - .macro this_cpu_offset, dst + .macro get_this_cpu_offset, dst mrs \dst, tpidr_el2 .endm #else - .macro this_cpu_offset, dst + .macro get_this_cpu_offset, dst alternative_if_not ARM64_HAS_VIRT_HOST_EXTN mrs \dst, tpidr_el1 alternative_else mrs \dst, tpidr_el2 alternative_endif .endm + + .macro set_this_cpu_offset, src +alternative_if_not ARM64_HAS_VIRT_HOST_EXTN + msr tpidr_el1, \src +alternative_else + msr tpidr_el2, \src +alternative_endif + .endm #endif /* @@ -253,7 +273,7 @@ alternative_endif .macro adr_this_cpu, dst, sym, tmp adrp \tmp, \sym add \dst, \tmp, #:lo12:\sym - this_cpu_offset \tmp + get_this_cpu_offset \tmp add \dst, \dst, \tmp .endm @@ -264,7 +284,7 @@ alternative_endif */ .macro ldr_this_cpu dst, sym, tmp adr_l \dst, \sym - this_cpu_offset \tmp + get_this_cpu_offset \tmp ldr \dst, [\dst, \tmp] .endm @@ -375,51 +395,53 @@ alternative_cb_end bfi \tcr, \tmp0, \pos, #3 .endm + .macro __dcache_op_workaround_clean_cache, op, addr +alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE + dc \op, \addr +alternative_else + dc civac, \addr +alternative_endif + .endm + /* * Macro to perform a data cache maintenance for the interval - * [kaddr, kaddr + size) + * [start, end) * * op: operation passed to dc instruction * domain: domain used in dsb instruciton - * kaddr: starting virtual address of the region - * size: size of the region - * Corrupts: kaddr, size, tmp1, tmp2 + * start: starting virtual address of the region + * end: end virtual address of the region + * fixup: optional label to branch to on user fault + * Corrupts: start, end, tmp1, tmp2 */ - .macro __dcache_op_workaround_clean_cache, op, kaddr -alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE - dc \op, \kaddr -alternative_else - dc civac, \kaddr -alternative_endif - .endm - - .macro dcache_by_line_op op, domain, kaddr, size, tmp1, tmp2 + .macro dcache_by_line_op op, domain, start, end, tmp1, tmp2, fixup dcache_line_size \tmp1, \tmp2 - add \size, \kaddr, \size sub \tmp2, \tmp1, #1 - bic \kaddr, \kaddr, \tmp2 -9998: + bic \start, \start, \tmp2 +.Ldcache_op\@: .ifc \op, cvau - __dcache_op_workaround_clean_cache \op, \kaddr + __dcache_op_workaround_clean_cache \op, \start .else .ifc \op, cvac - __dcache_op_workaround_clean_cache \op, \kaddr + __dcache_op_workaround_clean_cache \op, \start .else .ifc \op, cvap - sys 3, c7, c12, 1, \kaddr // dc cvap + sys 3, c7, c12, 1, \start // dc cvap .else .ifc \op, cvadp - sys 3, c7, c13, 1, \kaddr // dc cvadp + sys 3, c7, c13, 1, \start // dc cvadp .else - dc \op, \kaddr + dc \op, \start .endif .endif .endif .endif - add \kaddr, \kaddr, \tmp1 - cmp \kaddr, \size - b.lo 9998b + add \start, \start, \tmp1 + cmp \start, \end + b.lo .Ldcache_op\@ dsb \domain + + _cond_extable .Ldcache_op\@, \fixup .endm /* @@ -427,20 +449,22 @@ alternative_endif * [start, end) * * start, end: virtual addresses describing the region - * label: A label to branch to on user fault. + * fixup: optional label to branch to on user fault * Corrupts: tmp1, tmp2 */ - .macro invalidate_icache_by_line start, end, tmp1, tmp2, label + .macro invalidate_icache_by_line start, end, tmp1, tmp2, fixup icache_line_size \tmp1, \tmp2 sub \tmp2, \tmp1, #1 bic \tmp2, \start, \tmp2 -9997: -USER(\label, ic ivau, \tmp2) // invalidate I line PoU +.Licache_op\@: + ic ivau, \tmp2 // invalidate I line PoU add \tmp2, \tmp2, \tmp1 cmp \tmp2, \end - b.lo 9997b + b.lo .Licache_op\@ dsb ish isb + + _cond_extable .Licache_op\@, \fixup .endm /* @@ -745,7 +769,7 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU cbz \tmp, \lbl #endif adr_l \tmp, irq_stat + IRQ_CPUSTAT_SOFTIRQ_PENDING - this_cpu_offset \tmp2 + get_this_cpu_offset \tmp2 ldr w\tmp, [\tmp, \tmp2] cbnz w\tmp, \lbl // yield on pending softirq in task context .Lnoyield_\@: diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 52e5c1623224..543c997eb3b7 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -30,45 +30,58 @@ * the implementation assumes non-aliasing VIPT D-cache and (aliasing) * VIPT I-cache. * - * flush_icache_range(start, end) + * All functions below apply to the interval [start, end) + * - start - virtual start address (inclusive) + * - end - virtual end address (exclusive) * - * Ensure coherency between the I-cache and the D-cache in the - * region described by start, end. - * - start - virtual start address - * - end - virtual end address + * caches_clean_inval_pou(start, end) * - * invalidate_icache_range(start, end) + * Ensure coherency between the I-cache and the D-cache region to + * the Point of Unification. * - * Invalidate the I-cache in the region described by start, end. - * - start - virtual start address - * - end - virtual end address + * caches_clean_inval_user_pou(start, end) * - * __flush_cache_user_range(start, end) + * Ensure coherency between the I-cache and the D-cache region to + * the Point of Unification. + * Use only if the region might access user memory. * - * Ensure coherency between the I-cache and the D-cache in the - * region described by start, end. - * - start - virtual start address - * - end - virtual end address + * icache_inval_pou(start, end) * - * __flush_dcache_area(kaddr, size) + * Invalidate I-cache region to the Point of Unification. * - * Ensure that the data held in page is written back. - * - kaddr - page address - * - size - region size + * dcache_clean_inval_poc(start, end) + * + * Clean and invalidate D-cache region to the Point of Coherency. + * + * dcache_inval_poc(start, end) + * + * Invalidate D-cache region to the Point of Coherency. + * + * dcache_clean_poc(start, end) + * + * Clean D-cache region to the Point of Coherency. + * + * dcache_clean_pop(start, end) + * + * Clean D-cache region to the Point of Persistence. + * + * dcache_clean_pou(start, end) + * + * Clean D-cache region to the Point of Unification. */ -extern void __flush_icache_range(unsigned long start, unsigned long end); -extern int invalidate_icache_range(unsigned long start, unsigned long end); -extern void __flush_dcache_area(void *addr, size_t len); -extern void __inval_dcache_area(void *addr, size_t len); -extern void __clean_dcache_area_poc(void *addr, size_t len); -extern void __clean_dcache_area_pop(void *addr, size_t len); -extern void __clean_dcache_area_pou(void *addr, size_t len); -extern long __flush_cache_user_range(unsigned long start, unsigned long end); -extern void sync_icache_aliases(void *kaddr, unsigned long len); +extern void caches_clean_inval_pou(unsigned long start, unsigned long end); +extern void icache_inval_pou(unsigned long start, unsigned long end); +extern void dcache_clean_inval_poc(unsigned long start, unsigned long end); +extern void dcache_inval_poc(unsigned long start, unsigned long end); +extern void dcache_clean_poc(unsigned long start, unsigned long end); +extern void dcache_clean_pop(unsigned long start, unsigned long end); +extern void dcache_clean_pou(unsigned long start, unsigned long end); +extern long caches_clean_inval_user_pou(unsigned long start, unsigned long end); +extern void sync_icache_aliases(unsigned long start, unsigned long end); static inline void flush_icache_range(unsigned long start, unsigned long end) { - __flush_icache_range(start, end); + caches_clean_inval_pou(start, end); /* * IPI all online CPUs so that they undergo a context synchronization @@ -122,7 +135,7 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *, #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); -static __always_inline void __flush_icache_all(void) +static __always_inline void icache_inval_all_pou(void) { if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC)) return; diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 3578aba9c608..1bed37eb013a 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -137,7 +137,7 @@ void efi_virtmap_unload(void); static inline void efi_capsule_flush_cache_range(void *addr, int size) { - __flush_dcache_area(addr, size); + dcache_clean_inval_poc((unsigned long)addr, (unsigned long)addr + size); } #endif /* _ASM_EFI_H */ diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 25ed956f9af1..f4cbfa9025a8 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -180,7 +180,8 @@ static inline void *__kvm_vector_slot2addr(void *base, struct kvm; -#define kvm_flush_dcache_to_poc(a,l) __flush_dcache_area((a), (l)) +#define kvm_flush_dcache_to_poc(a,l) \ + dcache_clean_inval_poc((unsigned long)(a), (unsigned long)(a)+(l)) static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) { @@ -208,12 +209,12 @@ static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn, { if (icache_is_aliasing()) { /* any kind of VIPT cache */ - __flush_icache_all(); + icache_inval_all_pou(); } else if (is_kernel_in_hyp_mode() || !icache_is_vpipt()) { /* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */ void *va = page_address(pfn_to_page(pfn)); - invalidate_icache_range((unsigned long)va, + icache_inval_pou((unsigned long)va, (unsigned long)va + size); } } diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 9df3feeee890..7a094aafec20 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -329,13 +329,13 @@ long get_tagged_addr_ctrl(struct task_struct *task); * of header definitions for the use of task_stack_page. */ -#define current_top_of_stack() \ -({ \ - struct stack_info _info; \ - BUG_ON(!on_accessible_stack(current, current_stack_pointer, &_info)); \ - _info.high; \ +#define current_top_of_stack() \ +({ \ + struct stack_info _info; \ + BUG_ON(!on_accessible_stack(current, current_stack_pointer, 1, &_info)); \ + _info.high; \ }) -#define on_thread_stack() (on_task_stack(current, current_stack_pointer, NULL)) +#define on_thread_stack() (on_task_stack(current, current_stack_pointer, 1, NULL)) #endif /* __ASSEMBLY__ */ #endif /* __ASM_PROCESSOR_H */ diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h index eaa2cd92e4c1..8297bccf0784 100644 --- a/arch/arm64/include/asm/scs.h +++ b/arch/arm64/include/asm/scs.h @@ -9,18 +9,18 @@ #ifdef CONFIG_SHADOW_CALL_STACK scs_sp .req x18 - .macro scs_load tsk, tmp + .macro scs_load tsk ldr scs_sp, [\tsk, #TSK_TI_SCS_SP] .endm - .macro scs_save tsk, tmp + .macro scs_save tsk str scs_sp, [\tsk, #TSK_TI_SCS_SP] .endm #else - .macro scs_load tsk, tmp + .macro scs_load tsk .endm - .macro scs_save tsk, tmp + .macro scs_save tsk .endm #endif /* CONFIG_SHADOW_CALL_STACK */ diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h index 63e0b92a5fbb..8bc30a5c4569 100644 --- a/arch/arm64/include/asm/sdei.h +++ b/arch/arm64/include/asm/sdei.h @@ -42,8 +42,9 @@ unsigned long sdei_arch_get_entry_point(int conduit); struct stack_info; -bool _on_sdei_stack(unsigned long sp, struct stack_info *info); -static inline bool on_sdei_stack(unsigned long sp, +bool _on_sdei_stack(unsigned long sp, unsigned long size, + struct stack_info *info); +static inline bool on_sdei_stack(unsigned long sp, unsigned long size, struct stack_info *info) { if (!IS_ENABLED(CONFIG_VMAP_STACK)) @@ -51,7 +52,7 @@ static inline bool on_sdei_stack(unsigned long sp, if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE)) return false; if (in_nmi()) - return _on_sdei_stack(sp, info); + return _on_sdei_stack(sp, size, info); return false; } diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index 0e357757c0cc..fc55f5a57a06 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -73,12 +73,10 @@ asmlinkage void secondary_start_kernel(void); /* * Initial data for bringing up a secondary CPU. - * @stack - sp for the secondary CPU * @status - Result passed back from the secondary CPU to * indicate failure. */ struct secondary_data { - void *stack; struct task_struct *task; long status; }; diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index 4b33ca620679..1801399204d7 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -69,14 +69,14 @@ extern void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk, DECLARE_PER_CPU(unsigned long *, irq_stack_ptr); -static inline bool on_stack(unsigned long sp, unsigned long low, - unsigned long high, enum stack_type type, - struct stack_info *info) +static inline bool on_stack(unsigned long sp, unsigned long size, + unsigned long low, unsigned long high, + enum stack_type type, struct stack_info *info) { if (!low) return false; - if (sp < low || sp >= high) + if (sp < low || sp + size < sp || sp + size > high) return false; if (info) { @@ -87,38 +87,38 @@ static inline bool on_stack(unsigned long sp, unsigned long low, return true; } -static inline bool on_irq_stack(unsigned long sp, +static inline bool on_irq_stack(unsigned long sp, unsigned long size, struct stack_info *info) { unsigned long low = (unsigned long)raw_cpu_read(irq_stack_ptr); unsigned long high = low + IRQ_STACK_SIZE; - return on_stack(sp, low, high, STACK_TYPE_IRQ, info); + return on_stack(sp, size, low, high, STACK_TYPE_IRQ, info); } static inline bool on_task_stack(const struct task_struct *tsk, - unsigned long sp, + unsigned long sp, unsigned long size, struct stack_info *info) { unsigned long low = (unsigned long)task_stack_page(tsk); unsigned long high = low + THREAD_SIZE; - return on_stack(sp, low, high, STACK_TYPE_TASK, info); + return on_stack(sp, size, low, high, STACK_TYPE_TASK, info); } #ifdef CONFIG_VMAP_STACK DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack); -static inline bool on_overflow_stack(unsigned long sp, +static inline bool on_overflow_stack(unsigned long sp, unsigned long size, struct stack_info *info) { unsigned long low = (unsigned long)raw_cpu_ptr(overflow_stack); unsigned long high = low + OVERFLOW_STACK_SIZE; - return on_stack(sp, low, high, STACK_TYPE_OVERFLOW, info); + return on_stack(sp, size, low, high, STACK_TYPE_OVERFLOW, info); } #else -static inline bool on_overflow_stack(unsigned long sp, +static inline bool on_overflow_stack(unsigned long sp, unsigned long size, struct stack_info *info) { return false; } #endif @@ -128,21 +128,21 @@ static inline bool on_overflow_stack(unsigned long sp, * context. */ static inline bool on_accessible_stack(const struct task_struct *tsk, - unsigned long sp, + unsigned long sp, unsigned long size, struct stack_info *info) { if (info) info->type = STACK_TYPE_UNKNOWN; - if (on_task_stack(tsk, sp, info)) + if (on_task_stack(tsk, sp, size, info)) return true; if (tsk != current || preemptible()) return false; - if (on_irq_stack(sp, info)) + if (on_irq_stack(sp, size, info)) return true; - if (on_overflow_stack(sp, info)) + if (on_overflow_stack(sp, size, info)) return true; - if (on_sdei_stack(sp, info)) + if (on_sdei_stack(sp, size, info)) return true; return false; diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index c906d20c7b52..3fb79b76e9d9 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -181,7 +181,7 @@ static void __nocfi __apply_alternatives(struct alt_region *region, bool is_modu */ if (!is_module) { dsb(ish); - __flush_icache_all(); + icache_inval_all_pou(); isb(); /* Ignore ARM64_CB bit from feature mask */ diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 0cb34ccb6e73..bd0fc23d8719 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -27,6 +27,7 @@ int main(void) { DEFINE(TSK_ACTIVE_MM, offsetof(struct task_struct, active_mm)); + DEFINE(TSK_CPU, offsetof(struct task_struct, cpu)); BLANK(); DEFINE(TSK_TI_FLAGS, offsetof(struct task_struct, thread_info.flags)); DEFINE(TSK_TI_PREEMPT, offsetof(struct task_struct, thread_info.preempt_count)); @@ -99,7 +100,6 @@ int main(void) DEFINE(SOFTIRQ_SHIFT, SOFTIRQ_SHIFT); DEFINE(IRQ_CPUSTAT_SOFTIRQ_PENDING, offsetof(irq_cpustat_t, __softirq_pending)); BLANK(); - DEFINE(CPU_BOOT_STACK, offsetof(struct secondary_data, stack)); DEFINE(CPU_BOOT_TASK, offsetof(struct secondary_data, task)); BLANK(); DEFINE(FTR_OVR_VAL_OFFSET, offsetof(struct arm64_ftr_override, val)); diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S index 0073b24b5d25..61a87fa1c305 100644 --- a/arch/arm64/kernel/efi-entry.S +++ b/arch/arm64/kernel/efi-entry.S @@ -28,7 +28,8 @@ SYM_CODE_START(efi_enter_kernel) * stale icache entries from before relocation. */ ldr w1, =kernel_size - bl __clean_dcache_area_poc + add x1, x0, x1 + bl dcache_clean_poc ic ialluis /* @@ -36,8 +37,8 @@ SYM_CODE_START(efi_enter_kernel) * so that we can safely disable the MMU and caches. */ adr x0, 0f - ldr w1, 3f - bl __clean_dcache_area_poc + adr x1, 3f + bl dcache_clean_poc 0: /* Turn off Dcache and MMU */ mrs x0, CurrentEL @@ -64,5 +65,5 @@ SYM_CODE_START(efi_enter_kernel) mov x2, xzr mov x3, xzr br x19 +3: SYM_CODE_END(efi_enter_kernel) -3: .long . - 0b diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 3513984a88bd..3153f1448cdb 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -275,7 +275,7 @@ alternative_else_nop_endif mte_set_kernel_gcr x22, x23 - scs_load tsk, x20 + scs_load tsk .else add x21, sp, #PT_REGS_SIZE get_current_task tsk @@ -285,7 +285,7 @@ alternative_else_nop_endif stp lr, x21, [sp, #S_LR] /* - * For exceptions from EL0, create a terminal frame record. + * For exceptions from EL0, create a final frame record. * For exceptions from EL1, create a synthetic frame record so the * interrupted code shows up in the backtrace. */ @@ -375,7 +375,7 @@ alternative_if ARM64_WORKAROUND_845719 alternative_else_nop_endif #endif 3: - scs_save tsk, x0 + scs_save tsk #ifdef CONFIG_ARM64_PTR_AUTH alternative_if ARM64_HAS_ADDRESS_AUTH @@ -979,8 +979,8 @@ SYM_FUNC_START(cpu_switch_to) mov sp, x9 msr sp_el0, x1 ptrauth_keys_install_kernel x1, x8, x9, x10 - scs_save x0, x8 - scs_load x1, x8 + scs_save x0 + scs_load x1 ret SYM_FUNC_END(cpu_switch_to) NOKPROBE(cpu_switch_to) diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 96873dfa67fd..a6ccd6557d19 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -16,6 +16,7 @@ #include <asm/asm_pointer_auth.h> #include <asm/assembler.h> #include <asm/boot.h> +#include <asm/bug.h> #include <asm/ptrace.h> #include <asm/asm-offsets.h> #include <asm/cache.h> @@ -117,8 +118,8 @@ SYM_CODE_START_LOCAL(preserve_boot_args) dmb sy // needed before dc ivac with // MMU off - mov x1, #0x20 // 4 x 8 bytes - b __inval_dcache_area // tail call + add x1, x0, #0x20 // 4 x 8 bytes + b dcache_inval_poc // tail call SYM_CODE_END(preserve_boot_args) /* @@ -268,8 +269,7 @@ SYM_FUNC_START_LOCAL(__create_page_tables) */ adrp x0, init_pg_dir adrp x1, init_pg_end - sub x1, x1, x0 - bl __inval_dcache_area + bl dcache_inval_poc /* * Clear the init page tables. @@ -382,39 +382,57 @@ SYM_FUNC_START_LOCAL(__create_page_tables) adrp x0, idmap_pg_dir adrp x1, idmap_pg_end - sub x1, x1, x0 - bl __inval_dcache_area + bl dcache_inval_poc adrp x0, init_pg_dir adrp x1, init_pg_end - sub x1, x1, x0 - bl __inval_dcache_area + bl dcache_inval_poc ret x28 SYM_FUNC_END(__create_page_tables) + /* + * Initialize CPU registers with task-specific and cpu-specific context. + * + * Create a final frame record at task_pt_regs(current)->stackframe, so + * that the unwinder can identify the final frame record of any task by + * its location in the task stack. We reserve the entire pt_regs space + * for consistency with user tasks and kthreads. + */ + .macro init_cpu_task tsk, tmp1, tmp2 + msr sp_el0, \tsk + + ldr \tmp1, [\tsk, #TSK_STACK] + add sp, \tmp1, #THREAD_SIZE + sub sp, sp, #PT_REGS_SIZE + + stp xzr, xzr, [sp, #S_STACKFRAME] + add x29, sp, #S_STACKFRAME + + scs_load \tsk + + adr_l \tmp1, __per_cpu_offset + ldr w\tmp2, [\tsk, #TSK_CPU] + ldr \tmp1, [\tmp1, \tmp2, lsl #3] + set_this_cpu_offset \tmp1 + .endm + /* * The following fragment of code is executed with the MMU enabled. * * x0 = __PHYS_OFFSET */ SYM_FUNC_START_LOCAL(__primary_switched) - adrp x4, init_thread_union - add sp, x4, #THREAD_SIZE - adr_l x5, init_task - msr sp_el0, x5 // Save thread_info + adr_l x4, init_task + init_cpu_task x4, x5, x6 adr_l x8, vectors // load VBAR_EL1 with virtual msr vbar_el1, x8 // vector table address isb - stp xzr, x30, [sp, #-16]! + stp x29, x30, [sp, #-16]! mov x29, sp -#ifdef CONFIG_SHADOW_CALL_STACK - adr_l scs_sp, init_shadow_call_stack // Set shadow call stack -#endif - str_l x21, __fdt_pointer, x5 // Save FDT pointer ldr_l x4, kimage_vaddr // Save the offset between @@ -446,10 +464,9 @@ SYM_FUNC_START_LOCAL(__primary_switched) 0: #endif bl switch_to_vhe // Prefer VHE if possible - add sp, sp, #16 - mov x29, #0 - mov x30, #0 - b start_kernel + ldp x29, x30, [sp], #16 + bl start_kernel + ASM_BUG() SYM_FUNC_END(__primary_switched) .pushsection ".rodata", "a" @@ -632,21 +649,17 @@ SYM_FUNC_START_LOCAL(__secondary_switched) isb adr_l x0, secondary_data - ldr x1, [x0, #CPU_BOOT_STACK] // get secondary_data.stack - cbz x1, __secondary_too_slow - mov sp, x1 ldr x2, [x0, #CPU_BOOT_TASK] cbz x2, __secondary_too_slow - msr sp_el0, x2 - scs_load x2, x3 - mov x29, #0 - mov x30, #0 + + init_cpu_task x2, x1, x3 #ifdef CONFIG_ARM64_PTR_AUTH ptrauth_keys_init_cpu x2, x3, x4, x5 #endif - b secondary_start_kernel + bl secondary_start_kernel + ASM_BUG() SYM_FUNC_END(__secondary_switched) SYM_FUNC_START_LOCAL(__secondary_too_slow) diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S index 8ccca660034e..81c0186a5e32 100644 --- a/arch/arm64/kernel/hibernate-asm.S +++ b/arch/arm64/kernel/hibernate-asm.S @@ -45,7 +45,7 @@ * Because this code has to be copied to a 'safe' page, it can't call out to * other functions by PC-relative address. Also remember that it may be * mid-way through over-writing other functions. For this reason it contains - * code from flush_icache_range() and uses the copy_page() macro. + * code from caches_clean_inval_pou() and uses the copy_page() macro. * * This 'safe' page is mapped via ttbr0, and executed from there. This function * switches to a copy of the linear map in ttbr1, performs the restore, then @@ -87,11 +87,12 @@ SYM_CODE_START(swsusp_arch_suspend_exit) copy_page x0, x1, x2, x3, x4, x5, x6, x7, x8, x9 add x1, x10, #PAGE_SIZE - /* Clean the copied page to PoU - based on flush_icache_range() */ + /* Clean the copied page to PoU - based on caches_clean_inval_pou() */ raw_dcache_line_size x2, x3 sub x3, x2, #1 bic x4, x10, x3 -2: dc cvau, x4 /* clean D line / unified line */ +2: /* clean D line / unified line */ +alternative_insn "dc cvau, x4", "dc civac, x4", ARM64_WORKAROUND_CLEAN_CACHE add x4, x4, x2 cmp x4, x1 b.lo 2b diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index b1cef371df2b..46a0b4d6e251 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -210,7 +210,7 @@ static int create_safe_exec_page(void *src_start, size_t length, return -ENOMEM; memcpy(page, src_start, length); - __flush_icache_range((unsigned long)page, (unsigned long)page + length); + caches_clean_inval_pou((unsigned long)page, (unsigned long)page + length); rc = trans_pgd_idmap_page(&trans_info, &trans_ttbr0, &t0sz, page); if (rc) return rc; @@ -240,8 +240,6 @@ static int create_safe_exec_page(void *src_start, size_t length, return 0; } -#define dcache_clean_range(start, end) __flush_dcache_area(start, (end - start)) - #ifdef CONFIG_ARM64_MTE static DEFINE_XARRAY(mte_pages); @@ -383,13 +381,18 @@ int swsusp_arch_suspend(void) ret = swsusp_save(); } else { /* Clean kernel core startup/idle code to PoC*/ - dcache_clean_range(__mmuoff_data_start, __mmuoff_data_end); - dcache_clean_range(__idmap_text_start, __idmap_text_end); + dcache_clean_inval_poc((unsigned long)__mmuoff_data_start, + (unsigned long)__mmuoff_data_end); + dcache_clean_inval_poc((unsigned long)__idmap_text_start, + (unsigned long)__idmap_text_end); /* Clean kvm setup code to PoC? */ if (el2_reset_needed()) { - dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end); - dcache_clean_range(__hyp_text_start, __hyp_text_end); + dcache_clean_inval_poc( + (unsigned long)__hyp_idmap_text_start, + (unsigned long)__hyp_idmap_text_end); + dcache_clean_inval_poc((unsigned long)__hyp_text_start, + (unsigned long)__hyp_text_end); } swsusp_mte_restore_tags(); @@ -474,7 +477,8 @@ int swsusp_arch_resume(void) * The hibernate exit text contains a set of el2 vectors, that will * be executed at el2 with the mmu off in order to reload hyp-stub. */ - __flush_dcache_area(hibernate_exit, exit_size); + dcache_clean_inval_poc((unsigned long)hibernate_exit, + (unsigned long)hibernate_exit + exit_size); /* * KASLR will cause the el2 vectors to be in a different location in diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c index e628c8ce1ffe..53a381a7f65d 100644 --- a/arch/arm64/kernel/idreg-override.c +++ b/arch/arm64/kernel/idreg-override.c @@ -237,7 +237,8 @@ asmlinkage void __init init_feature_override(void) for (i = 0; i < ARRAY_SIZE(regs); i++) { if (regs[i]->override) - __flush_dcache_area(regs[i]->override, + dcache_clean_inval_poc((unsigned long)regs[i]->override, + (unsigned long)regs[i]->override + sizeof(*regs[i]->override)); } } diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index bcf3c2755370..c96a9a0043bf 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -35,7 +35,7 @@ __efistub_strnlen = __pi_strnlen; __efistub_strcmp = __pi_strcmp; __efistub_strncmp = __pi_strncmp; __efistub_strrchr = __pi_strrchr; -__efistub___clean_dcache_area_poc = __pi___clean_dcache_area_poc; +__efistub_dcache_clean_poc = __pi_dcache_clean_poc; #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) __efistub___memcpy = __pi_memcpy; diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 6c0de2f60ea9..51cb8dc98d00 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -198,7 +198,7 @@ int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn) ret = aarch64_insn_write(tp, insn); if (ret == 0) - __flush_icache_range((uintptr_t)tp, + caches_clean_inval_pou((uintptr_t)tp, (uintptr_t)tp + AARCH64_INSN_SIZE); return ret; diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 341342b207f6..cfa2cfde3019 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -72,7 +72,9 @@ u64 __init kaslr_early_init(void) * we end up running with module randomization disabled. */ module_alloc_base = (u64)_etext - MODULES_VSIZE; - __flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base)); + dcache_clean_inval_poc((unsigned long)&module_alloc_base, + (unsigned long)&module_alloc_base + + sizeof(module_alloc_base)); /* * Try to map the FDT early. If this fails, we simply bail, @@ -170,8 +172,12 @@ u64 __init kaslr_early_init(void) module_alloc_base += (module_range * (seed & ((1 << 21) - 1))) >> 21; module_alloc_base &= PAGE_MASK; - __flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base)); - __flush_dcache_area(&memstart_offset_seed, sizeof(memstart_offset_seed)); + dcache_clean_inval_poc((unsigned long)&module_alloc_base, + (unsigned long)&module_alloc_base + + sizeof(module_alloc_base)); + dcache_clean_inval_poc((unsigned long)&memstart_offset_seed, + (unsigned long)&memstart_offset_seed + + sizeof(memstart_offset_seed)); return offset; } diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index 90a335c74442..03ceabe4d912 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -68,10 +68,16 @@ int machine_kexec_post_load(struct kimage *kimage) kimage->arch.kern_reloc = __pa(reloc_code); kexec_image_info(kimage); - /* Flush the reloc_code in preparation for its execution. */ - __flush_dcache_area(reloc_code, arm64_relocate_new_kernel_size); - flush_icache_range((uintptr_t)reloc_code, (uintptr_t)reloc_code + - arm64_relocate_new_kernel_size); + /* + * For execution with the MMU off, reloc_code needs to be cleaned to the + * PoC and invalidated from the I-cache. + */ + dcache_clean_inval_poc((unsigned long)reloc_code, + (unsigned long)reloc_code + + arm64_relocate_new_kernel_size); + icache_inval_pou((uintptr_t)reloc_code, + (uintptr_t)reloc_code + + arm64_relocate_new_kernel_size); return 0; } @@ -102,16 +108,18 @@ static void kexec_list_flush(struct kimage *kimage) for (entry = &kimage->head; ; entry++) { unsigned int flag; - void *addr; + unsigned long addr; /* flush the list entries. */ - __flush_dcache_area(entry, sizeof(kimage_entry_t)); + dcache_clean_inval_poc((unsigned long)entry, + (unsigned long)entry + + sizeof(kimage_entry_t)); flag = *entry & IND_FLAGS; if (flag == IND_DONE) break; - addr = phys_to_virt(*entry & PAGE_MASK); + addr = (unsigned long)phys_to_virt(*entry & PAGE_MASK); switch (flag) { case IND_INDIRECTION: @@ -120,7 +128,7 @@ static void kexec_list_flush(struct kimage *kimage) break; case IND_SOURCE: /* flush the source pages. */ - __flush_dcache_area(addr, PAGE_SIZE); + dcache_clean_inval_poc(addr, addr + PAGE_SIZE); break; case IND_DESTINATION: break; @@ -147,8 +155,10 @@ static void kexec_segment_flush(const struct kimage *kimage) kimage->segment[i].memsz, kimage->segment[i].memsz / PAGE_SIZE); - __flush_dcache_area(phys_to_virt(kimage->segment[i].mem), - kimage->segment[i].memsz); + dcache_clean_inval_poc( + (unsigned long)phys_to_virt(kimage->segment[i].mem), + (unsigned long)phys_to_virt(kimage->segment[i].mem) + + kimage->segment[i].memsz); } } diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c index 88ff471b0bce..4a72c2727309 100644 --- a/arch/arm64/kernel/perf_callchain.c +++ b/arch/arm64/kernel/perf_callchain.c @@ -116,7 +116,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, tail = (struct frame_tail __user *)regs->regs[29]; while (entry->nr < entry->max_stack && - tail && !((unsigned long)tail & 0xf)) + tail && !((unsigned long)tail & 0x7)) tail = user_backtrace(tail, entry); } else { #ifdef CONFIG_COMPAT diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c index 2c247634552b..9be668f3f034 100644 --- a/arch/arm64/kernel/probes/uprobes.c +++ b/arch/arm64/kernel/probes/uprobes.c @@ -21,7 +21,7 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, memcpy(dst, src, len); /* flush caches (dcache/icache) */ - sync_icache_aliases(dst, len); + sync_icache_aliases((unsigned long)dst, (unsigned long)dst + len); kunmap_atomic(xol_page_kaddr); } diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index b4bb67f17a2c..8928fba54e4b 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -435,6 +435,11 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, } p->thread.cpu_context.pc = (unsigned long)ret_from_fork; p->thread.cpu_context.sp = (unsigned long)childregs; + /* + * For the benefit of the unwinder, set up childregs->stackframe + * as the final frame for the new task. + */ + p->thread.cpu_context.fp = (unsigned long)childregs->stackframe; ptrace_hw_copy_thread(p); diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index eb2f73939b7b..499b6b2f9757 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -122,7 +122,7 @@ static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) { return ((addr & ~(THREAD_SIZE - 1)) == (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))) || - on_irq_stack(addr, NULL); + on_irq_stack(addr, sizeof(unsigned long), NULL); } /** diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index 2c7ca449dd51..c524f96f97c4 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -162,31 +162,33 @@ static int init_sdei_scs(void) return err; } -static bool on_sdei_normal_stack(unsigned long sp, struct stack_info *info) +static bool on_sdei_normal_stack(unsigned long sp, unsigned long size, + struct stack_info *info) { unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr); unsigned long high = low + SDEI_STACK_SIZE; - return on_stack(sp, low, high, STACK_TYPE_SDEI_NORMAL, info); + return on_stack(sp, size, low, high, STACK_TYPE_SDEI_NORMAL, info); } -static bool on_sdei_critical_stack(unsigned long sp, struct stack_info *info) +static bool on_sdei_critical_stack(unsigned long sp, unsigned long size, + struct stack_info *info) { unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr); unsigned long high = low + SDEI_STACK_SIZE; - return on_stack(sp, low, high, STACK_TYPE_SDEI_CRITICAL, info); + return on_stack(sp, size, low, high, STACK_TYPE_SDEI_CRITICAL, info); } -bool _on_sdei_stack(unsigned long sp, struct stack_info *info) +bool _on_sdei_stack(unsigned long sp, unsigned long size, struct stack_info *info) { if (!IS_ENABLED(CONFIG_VMAP_STACK)) return false; - if (on_sdei_critical_stack(sp, info)) + if (on_sdei_critical_stack(sp, size, info)) return true; - if (on_sdei_normal_stack(sp, info)) + if (on_sdei_normal_stack(sp, size, info)) return true; return false; diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 61845c0821d9..b7a35a03e9b9 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -87,12 +87,6 @@ void __init smp_setup_processor_id(void) u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK; set_cpu_logical_map(0, mpidr); - /* - * clear __my_cpu_offset on boot CPU to avoid hang caused by - * using percpu variable early, for example, lockdep will - * access percpu variable inside lock_release - */ - set_my_cpu_offset(0); pr_info("Booting Linux on physical CPU 0x%010lx [0x%08x]\n", (unsigned long)mpidr, read_cpuid_id()); } diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index dcd7041b2b07..2fe8fab886e2 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -120,9 +120,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) * page tables. */ secondary_data.task = idle; - secondary_data.stack = task_stack_page(idle) + THREAD_SIZE; update_cpu_boot_status(CPU_MMU_OFF); - __flush_dcache_area(&secondary_data, sizeof(secondary_data)); /* Now bring the CPU into our world */ ret = boot_secondary(cpu, idle); @@ -142,8 +140,6 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) pr_crit("CPU%u: failed to come online\n", cpu); secondary_data.task = NULL; - secondary_data.stack = NULL; - __flush_dcache_area(&secondary_data, sizeof(secondary_data)); status = READ_ONCE(secondary_data.status); if (status == CPU_MMU_OFF) status = READ_ONCE(__early_cpu_boot_status); @@ -202,10 +198,7 @@ asmlinkage notrace void secondary_start_kernel(void) u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK; struct mm_struct *mm = &init_mm; const struct cpu_operations *ops; - unsigned int cpu; - - cpu = task_cpu(current); - set_my_cpu_offset(per_cpu_offset(cpu)); + unsigned int cpu = smp_processor_id(); /* * All kernel threads share the same mm context; grab a @@ -452,6 +445,11 @@ void __init smp_cpus_done(unsigned int max_cpus) void __init smp_prepare_boot_cpu(void) { + /* + * The runtime per-cpu areas have been allocated by + * setup_per_cpu_areas(), and CPU0's boot time per-cpu area will be + * freed shortly, so we must move over to the runtime per-cpu area. + */ set_my_cpu_offset(per_cpu_offset(smp_processor_id())); cpuinfo_store_boot_cpu(); diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c index c45a83512805..7e1624ecab3c 100644 --- a/arch/arm64/kernel/smp_spin_table.c +++ b/arch/arm64/kernel/smp_spin_table.c @@ -36,7 +36,7 @@ static void write_pen_release(u64 val) unsigned long size = sizeof(secondary_holding_pen_release); secondary_holding_pen_release = val; - __flush_dcache_area(start, size); + dcache_clean_inval_poc((unsigned long)start, (unsigned long)start + size); } @@ -90,8 +90,9 @@ static int smp_spin_table_cpu_prepare(unsigned int cpu) * the boot protocol. */ writeq_relaxed(pa_holding_pen, release_addr); - __flush_dcache_area((__force void *)release_addr, - sizeof(*release_addr)); + dcache_clean_inval_poc((__force unsigned long)release_addr, + (__force unsigned long)release_addr + + sizeof(*release_addr)); /* * Send an event to wake up the secondary CPU. diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index de07147a7926..b189de5ca6cb 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -68,13 +68,17 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) unsigned long fp = frame->fp; struct stack_info info; - if (fp & 0xf) - return -EINVAL; - if (!tsk) tsk = current; - if (!on_accessible_stack(tsk, fp, &info)) + /* Final frame; nothing to unwind */ + if (fp == (unsigned long)task_pt_regs(tsk)->stackframe) + return -ENOENT; + + if (fp & 0x7) + return -EINVAL; + + if (!on_accessible_stack(tsk, fp, 16, &info)) return -EINVAL; if (test_bit(info.type, frame->stacks_done)) @@ -128,12 +132,6 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) frame->pc = ptrauth_strip_insn_pac(frame->pc); - /* - * This is a terminal record, so we have finished unwinding. - */ - if (!frame->fp && !frame->pc) - return -ENOENT; - return 0; } NOKPROBE_SYMBOL(unwind_frame); diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index 265fe3eb1069..db5159a3055f 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -41,7 +41,7 @@ __do_compat_cache_op(unsigned long start, unsigned long end) dsb(ish); } - ret = __flush_cache_user_range(start, start + chunk); + ret = caches_clean_inval_user_pou(start, start + chunk); if (ret) return ret; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 1cb39c0803a4..c1953f65ca0e 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1064,7 +1064,7 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) stage2_unmap_vm(vcpu->kvm); else - __flush_icache_all(); + icache_inval_all_pou(); } vcpu_reset_hcr(vcpu); diff --git a/arch/arm64/kvm/hyp/nvhe/cache.S b/arch/arm64/kvm/hyp/nvhe/cache.S index 36cef6915428..958734f4d6b0 100644 --- a/arch/arm64/kvm/hyp/nvhe/cache.S +++ b/arch/arm64/kvm/hyp/nvhe/cache.S @@ -7,7 +7,7 @@ #include <asm/assembler.h> #include <asm/alternative.h> -SYM_FUNC_START_PI(__flush_dcache_area) +SYM_FUNC_START_PI(dcache_clean_inval_poc) dcache_by_line_op civac, sy, x0, x1, x2, x3 ret -SYM_FUNC_END_PI(__flush_dcache_area) +SYM_FUNC_END_PI(dcache_clean_inval_poc) diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index 7488f53b0aa2..8143ebd4fb72 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -134,7 +134,8 @@ static void update_nvhe_init_params(void) for (i = 0; i < hyp_nr_cpus; i++) { params = per_cpu_ptr(&kvm_init_params, i); params->pgd_pa = __hyp_pa(pkvm_pgtable.pgd); - __flush_dcache_area(params, sizeof(*params)); + dcache_clean_inval_poc((unsigned long)params, + (unsigned long)params + sizeof(*params)); } } diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c index 83dc3b271bc5..38ed0f6f2703 100644 --- a/arch/arm64/kvm/hyp/nvhe/tlb.c +++ b/arch/arm64/kvm/hyp/nvhe/tlb.c @@ -104,7 +104,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, * you should be running with VHE enabled. */ if (icache_is_vpipt()) - __flush_icache_all(); + icache_inval_all_pou(); __tlb_switch_to_host(&cxt); } diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index c37c1dc4feaf..e9ad7fb28ee3 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -839,8 +839,11 @@ static int stage2_unmap_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, stage2_put_pte(ptep, mmu, addr, level, mm_ops); if (need_flush) { - __flush_dcache_area(kvm_pte_follow(pte, mm_ops), - kvm_granule_size(level)); + kvm_pte_t *pte_follow = kvm_pte_follow(pte, mm_ops); + + dcache_clean_inval_poc((unsigned long)pte_follow, + (unsigned long)pte_follow + + kvm_granule_size(level)); } if (childp) @@ -988,11 +991,15 @@ static int stage2_flush_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, struct kvm_pgtable *pgt = arg; struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops; kvm_pte_t pte = *ptep; + kvm_pte_t *pte_follow; if (!kvm_pte_valid(pte) || !stage2_pte_cacheable(pgt, pte)) return 0; - __flush_dcache_area(kvm_pte_follow(pte, mm_ops), kvm_granule_size(level)); + pte_follow = kvm_pte_follow(pte, mm_ops); + dcache_clean_inval_poc((unsigned long)pte_follow, + (unsigned long)pte_follow + + kvm_granule_size(level)); return 0; } diff --git a/arch/arm64/lib/uaccess_flushcache.c b/arch/arm64/lib/uaccess_flushcache.c index c83bb5a4aad2..baee22961bdb 100644 --- a/arch/arm64/lib/uaccess_flushcache.c +++ b/arch/arm64/lib/uaccess_flushcache.c @@ -15,7 +15,7 @@ void memcpy_flushcache(void *dst, const void *src, size_t cnt) * barrier to order the cache maintenance against the memcpy. */ memcpy(dst, src, cnt); - __clean_dcache_area_pop(dst, cnt); + dcache_clean_pop((unsigned long)dst, (unsigned long)dst + cnt); } EXPORT_SYMBOL_GPL(memcpy_flushcache); @@ -33,6 +33,6 @@ unsigned long __copy_user_flushcache(void *to, const void __user *from, rc = raw_copy_from_user(to, from, n); /* See above */ - __clean_dcache_area_pop(to, n - rc); + dcache_clean_pop((unsigned long)to, (unsigned long)to + n - rc); return rc; } diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index 2d881f34dd9d..5051b3c1a4f1 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -15,7 +15,7 @@ #include <asm/asm-uaccess.h> /* - * flush_icache_range(start,end) + * caches_clean_inval_pou_macro(start,end) [fixup] * * Ensure that the I and D caches are coherent within specified region. * This is typically used when code has been written to a memory region, @@ -23,12 +23,27 @@ * * - start - virtual start address of region * - end - virtual end address of region + * - fixup - optional label to branch to on user fault */ -SYM_FUNC_START(__flush_icache_range) - /* FALLTHROUGH */ +.macro caches_clean_inval_pou_macro, fixup +alternative_if ARM64_HAS_CACHE_IDC + dsb ishst + b .Ldc_skip_\@ +alternative_else_nop_endif + mov x2, x0 + mov x3, x1 + dcache_by_line_op cvau, ish, x2, x3, x4, x5, \fixup +.Ldc_skip_\@: +alternative_if ARM64_HAS_CACHE_DIC + isb + b .Lic_skip_\@ +alternative_else_nop_endif + invalidate_icache_by_line x0, x1, x2, x3, \fixup +.Lic_skip_\@: +.endm /* - * __flush_cache_user_range(start,end) + * caches_clean_inval_pou(start,end) * * Ensure that the I and D caches are coherent within specified region. * This is typically used when code has been written to a memory region, @@ -37,117 +52,103 @@ SYM_FUNC_START(__flush_icache_range) * - start - virtual start address of region * - end - virtual end address of region */ -SYM_FUNC_START(__flush_cache_user_range) +SYM_FUNC_START(caches_clean_inval_pou) + caches_clean_inval_pou_macro + ret +SYM_FUNC_END(caches_clean_inval_pou) + +/* + * caches_clean_inval_user_pou(start,end) + * + * Ensure that the I and D caches are coherent within specified region. + * This is typically used when code has been written to a memory region, + * and will be executed. + * + * - start - virtual start address of region + * - end - virtual end address of region + */ +SYM_FUNC_START(caches_clean_inval_user_pou) uaccess_ttbr0_enable x2, x3, x4 -alternative_if ARM64_HAS_CACHE_IDC - dsb ishst - b 7f -alternative_else_nop_endif - dcache_line_size x2, x3 - sub x3, x2, #1 - bic x4, x0, x3 -1: -user_alt 9f, "dc cvau, x4", "dc civac, x4", ARM64_WORKAROUND_CLEAN_CACHE - add x4, x4, x2 - cmp x4, x1 - b.lo 1b - dsb ish -7: -alternative_if ARM64_HAS_CACHE_DIC - isb - b 8f -alternative_else_nop_endif - invalidate_icache_by_line x0, x1, x2, x3, 9f -8: mov x0, #0 + caches_clean_inval_pou_macro 2f + mov x0, xzr 1: uaccess_ttbr0_disable x1, x2 ret -9: +2: mov x0, #-EFAULT b 1b -SYM_FUNC_END(__flush_icache_range) -SYM_FUNC_END(__flush_cache_user_range) +SYM_FUNC_END(caches_clean_inval_user_pou) /* - * invalidate_icache_range(start,end) + * icache_inval_pou(start,end) * * Ensure that the I cache is invalid within specified region. * * - start - virtual start address of region * - end - virtual end address of region */ -SYM_FUNC_START(invalidate_icache_range) +SYM_FUNC_START(icache_inval_pou) alternative_if ARM64_HAS_CACHE_DIC - mov x0, xzr isb ret alternative_else_nop_endif - uaccess_ttbr0_enable x2, x3, x4 - - invalidate_icache_by_line x0, x1, x2, x3, 2f - mov x0, xzr -1: - uaccess_ttbr0_disable x1, x2 + invalidate_icache_by_line x0, x1, x2, x3 ret -2: - mov x0, #-EFAULT - b 1b -SYM_FUNC_END(invalidate_icache_range) +SYM_FUNC_END(icache_inval_pou) /* - * __flush_dcache_area(kaddr, size) + * dcache_clean_inval_poc(start, end) * - * Ensure that any D-cache lines for the interval [kaddr, kaddr+size) + * Ensure that any D-cache lines for the interval [start, end) * are cleaned and invalidated to the PoC. * - * - kaddr - kernel address - * - size - size in question + * - start - virtual start address of region + * - end - virtual end address of region */ -SYM_FUNC_START_PI(__flush_dcache_area) +SYM_FUNC_START_PI(dcache_clean_inval_poc) dcache_by_line_op civac, sy, x0, x1, x2, x3 ret -SYM_FUNC_END_PI(__flush_dcache_area) +SYM_FUNC_END_PI(dcache_clean_inval_poc) /* - * __clean_dcache_area_pou(kaddr, size) + * dcache_clean_pou(start, end) * - * Ensure that any D-cache lines for the interval [kaddr, kaddr+size) + * Ensure that any D-cache lines for the interval [start, end) * are cleaned to the PoU. * - * - kaddr - kernel address - * - size - size in question + * - start - virtual start address of region + * - end - virtual end address of region */ -SYM_FUNC_START(__clean_dcache_area_pou) +SYM_FUNC_START(dcache_clean_pou) alternative_if ARM64_HAS_CACHE_IDC dsb ishst ret alternative_else_nop_endif dcache_by_line_op cvau, ish, x0, x1, x2, x3 ret -SYM_FUNC_END(__clean_dcache_area_pou) +SYM_FUNC_END(dcache_clean_pou) /* - * __inval_dcache_area(kaddr, size) + * dcache_inval_poc(start, end) * - * Ensure that any D-cache lines for the interval [kaddr, kaddr+size) + * Ensure that any D-cache lines for the interval [start, end) * are invalidated. Any partial lines at the ends of the interval are * also cleaned to PoC to prevent data loss. * - * - kaddr - kernel address - * - size - size in question + * - start - kernel start address of region + * - end - kernel end address of region */ SYM_FUNC_START_LOCAL(__dma_inv_area) -SYM_FUNC_START_PI(__inval_dcache_area) +SYM_FUNC_START_PI(dcache_inval_poc) /* FALLTHROUGH */ /* - * __dma_inv_area(start, size) + * __dma_inv_area(start, end) * - start - virtual start address of region - * - size - size in question + * - end - virtual end address of region */ - add x1, x1, x0 dcache_line_size x2, x3 sub x3, x2, #1 tst x1, x3 // end cache line aligned? @@ -165,48 +166,48 @@ SYM_FUNC_START_PI(__inval_dcache_area) b.lo 2b dsb sy ret -SYM_FUNC_END_PI(__inval_dcache_area) +SYM_FUNC_END_PI(dcache_inval_poc) SYM_FUNC_END(__dma_inv_area) /* - * __clean_dcache_area_poc(kaddr, size) + * dcache_clean_poc(start, end) * - * Ensure that any D-cache lines for the interval [kaddr, kaddr+size) + * Ensure that any D-cache lines for the interval [start, end) * are cleaned to the PoC. * - * - kaddr - kernel address - * - size - size in question + * - start - virtual start address of region + * - end - virtual end address of region */ SYM_FUNC_START_LOCAL(__dma_clean_area) -SYM_FUNC_START_PI(__clean_dcache_area_poc) +SYM_FUNC_START_PI(dcache_clean_poc) /* FALLTHROUGH */ /* - * __dma_clean_area(start, size) + * __dma_clean_area(start, end) * - start - virtual start address of region - * - size - size in question + * - end - virtual end address of region */ dcache_by_line_op cvac, sy, x0, x1, x2, x3 ret -SYM_FUNC_END_PI(__clean_dcache_area_poc) +SYM_FUNC_END_PI(dcache_clean_poc) SYM_FUNC_END(__dma_clean_area) /* - * __clean_dcache_area_pop(kaddr, size) + * dcache_clean_pop(start, end) * - * Ensure that any D-cache lines for the interval [kaddr, kaddr+size) + * Ensure that any D-cache lines for the interval [start, end) * are cleaned to the PoP. * - * - kaddr - kernel address - * - size - size in question + * - start - virtual start address of region + * - end - virtual end address of region */ -SYM_FUNC_START_PI(__clean_dcache_area_pop) +SYM_FUNC_START_PI(dcache_clean_pop) alternative_if_not ARM64_HAS_DCPOP - b __clean_dcache_area_poc + b dcache_clean_poc alternative_else_nop_endif dcache_by_line_op cvap, sy, x0, x1, x2, x3 ret -SYM_FUNC_END_PI(__clean_dcache_area_pop) +SYM_FUNC_END_PI(dcache_clean_pop) /* * __dma_flush_area(start, size) @@ -217,6 +218,7 @@ SYM_FUNC_END_PI(__clean_dcache_area_pop) * - size - size in question */ SYM_FUNC_START_PI(__dma_flush_area) + add x1, x0, x1 dcache_by_line_op civac, sy, x0, x1, x2, x3 ret SYM_FUNC_END_PI(__dma_flush_area) @@ -228,6 +230,7 @@ SYM_FUNC_END_PI(__dma_flush_area) * - dir - DMA direction */ SYM_FUNC_START_PI(__dma_map_area) + add x1, x0, x1 cmp w2, #DMA_FROM_DEVICE b.eq __dma_inv_area b __dma_clean_area @@ -240,6 +243,7 @@ SYM_FUNC_END_PI(__dma_map_area) * - dir - DMA direction */ SYM_FUNC_START_PI(__dma_unmap_area) + add x1, x0, x1 cmp w2, #DMA_TO_DEVICE b.ne __dma_inv_area ret diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index 6d44c028d1c9..2aaf950b906c 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -14,28 +14,25 @@ #include <asm/cache.h> #include <asm/tlbflush.h> -void sync_icache_aliases(void *kaddr, unsigned long len) +void sync_icache_aliases(unsigned long start, unsigned long end) { - unsigned long addr = (unsigned long)kaddr; - if (icache_is_aliasing()) { - __clean_dcache_area_pou(kaddr, len); - __flush_icache_all(); + dcache_clean_pou(start, end); + icache_inval_all_pou(); } else { /* * Don't issue kick_all_cpus_sync() after I-cache invalidation * for user mappings. */ - __flush_icache_range(addr, addr + len); + caches_clean_inval_pou(start, end); } } -static void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, - unsigned long uaddr, void *kaddr, - unsigned long len) +static void flush_ptrace_access(struct vm_area_struct *vma, unsigned long start, + unsigned long end) { if (vma->vm_flags & VM_EXEC) - sync_icache_aliases(kaddr, len); + sync_icache_aliases(start, end); } /* @@ -48,7 +45,7 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long len) { memcpy(dst, src, len); - flush_ptrace_access(vma, page, uaddr, dst, len); + flush_ptrace_access(vma, (unsigned long)dst, (unsigned long)dst + len); } void __sync_icache_dcache(pte_t pte) @@ -56,7 +53,9 @@ void __sync_icache_dcache(pte_t pte) struct page *page = pte_page(pte); if (!test_bit(PG_dcache_clean, &page->flags)) { - sync_icache_aliases(page_address(page), page_size(page)); + sync_icache_aliases((unsigned long)page_address(page), + (unsigned long)page_address(page) + + page_size(page)); set_bit(PG_dcache_clean, &page->flags); } } @@ -77,20 +76,20 @@ EXPORT_SYMBOL(flush_dcache_page); /* * Additional functions defined in assembly. */ -EXPORT_SYMBOL(__flush_icache_range); +EXPORT_SYMBOL(caches_clean_inval_pou); #ifdef CONFIG_ARCH_HAS_PMEM_API void arch_wb_cache_pmem(void *addr, size_t size) { /* Ensure order against any prior non-cacheable writes */ dmb(osh); - __clean_dcache_area_pop(addr, size); + dcache_clean_pop((unsigned long)addr, (unsigned long)addr + size); } EXPORT_SYMBOL_GPL(arch_wb_cache_pmem); void arch_invalidate_pmem(void *addr, size_t size) { - __inval_dcache_area(addr, size); + dcache_inval_poc((unsigned long)addr, (unsigned long)addr + size); } EXPORT_SYMBOL_GPL(arch_invalidate_pmem); #endif diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 97d7bcd8d4f2..bc555cd5e6b1 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -83,11 +83,7 @@ SYM_FUNC_START(cpu_do_suspend) mrs x9, mdscr_el1 mrs x10, oslsr_el1 mrs x11, sctlr_el1 -alternative_if_not ARM64_HAS_VIRT_HOST_EXTN - mrs x12, tpidr_el1 -alternative_else - mrs x12, tpidr_el2 -alternative_endif + get_this_cpu_offset x12 mrs x13, sp_el0 stp x2, x3, [x0] stp x4, x5, [x0, #16] @@ -145,11 +141,7 @@ SYM_FUNC_START(cpu_do_resume) msr mdscr_el1, x10 msr sctlr_el1, x12 -alternative_if_not ARM64_HAS_VIRT_HOST_EXTN - msr tpidr_el1, x13 -alternative_else - msr tpidr_el2, x13 -alternative_endif + set_this_cpu_offset x13 msr sp_el0, x14 /* * Restore oslsr_el1 by writing oslar_el1 diff --git a/scripts/tools-support-relr.sh b/scripts/tools-support-relr.sh index 45e8aa360b45..cb55878bd5b8 100755 --- a/scripts/tools-support-relr.sh +++ b/scripts/tools-support-relr.sh @@ -7,7 +7,8 @@ trap "rm -f $tmp_file.o $tmp_file $tmp_file.bin" EXIT cat << "END" | $CC -c -x c - -o $tmp_file.o >/dev/null 2>&1 void *p = &p; END -$LD $tmp_file.o -shared -Bsymbolic --pack-dyn-relocs=relr -o $tmp_file +$LD $tmp_file.o -shared -Bsymbolic --pack-dyn-relocs=relr \ + --use-android-relr-tags -o $tmp_file # Despite printing an error message, GNU nm still exits with exit code 0 if it # sees a relr section. So we need to check that nothing is printed to stderr. |