diff options
Diffstat (limited to 'arch/arm64/kernel/stacktrace.c')
| -rw-r--r-- | arch/arm64/kernel/stacktrace.c | 675 |
1 files changed, 528 insertions, 147 deletions
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index b83c8d911930..3ebcf8c53fb0 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -5,7 +5,9 @@ * Copyright (C) 2012 ARM Ltd. */ #include <linux/kernel.h> +#include <linux/efi.h> #include <linux/export.h> +#include <linux/filter.h> #include <linux/ftrace.h> #include <linux/kprobes.h> #include <linux/sched.h> @@ -13,47 +15,233 @@ #include <linux/sched/task_stack.h> #include <linux/stacktrace.h> +#include <asm/efi.h> #include <asm/irq.h> -#include <asm/pointer_auth.h> #include <asm/stack_pointer.h> #include <asm/stacktrace.h> +enum kunwind_source { + KUNWIND_SOURCE_UNKNOWN, + KUNWIND_SOURCE_FRAME, + KUNWIND_SOURCE_CALLER, + KUNWIND_SOURCE_TASK, + KUNWIND_SOURCE_REGS_PC, +}; + +union unwind_flags { + unsigned long all; + struct { + unsigned long fgraph : 1, + kretprobe : 1; + }; +}; + +/* + * Kernel unwind state + * + * @common: Common unwind state. + * @task: The task being unwound. + * @graph_idx: Used by ftrace_graph_ret_addr() for optimized stack unwinding. + * @kr_cur: When KRETPROBES is selected, holds the kretprobe instance + * associated with the most recently encountered replacement lr + * value. + */ +struct kunwind_state { + struct unwind_state common; + struct task_struct *task; + int graph_idx; +#ifdef CONFIG_KRETPROBES + struct llist_node *kr_cur; +#endif + enum kunwind_source source; + union unwind_flags flags; + struct pt_regs *regs; +}; + +static __always_inline void +kunwind_init(struct kunwind_state *state, + struct task_struct *task) +{ + unwind_init_common(&state->common); + state->task = task; + state->source = KUNWIND_SOURCE_UNKNOWN; + state->flags.all = 0; + state->regs = NULL; +} + +/* + * Start an unwind from a pt_regs. + * + * The unwind will begin at the PC within the regs. + * + * The regs must be on a stack currently owned by the calling task. + */ +static __always_inline void +kunwind_init_from_regs(struct kunwind_state *state, + struct pt_regs *regs) +{ + kunwind_init(state, current); + + state->regs = regs; + state->common.fp = regs->regs[29]; + state->common.pc = regs->pc; + state->source = KUNWIND_SOURCE_REGS_PC; +} + +/* + * Start an unwind from a caller. + * + * The unwind will begin at the caller of whichever function this is inlined + * into. + * + * The function which invokes this must be noinline. + */ +static __always_inline void +kunwind_init_from_caller(struct kunwind_state *state) +{ + kunwind_init(state, current); + + state->common.fp = (unsigned long)__builtin_frame_address(1); + state->common.pc = (unsigned long)__builtin_return_address(0); + state->source = KUNWIND_SOURCE_CALLER; +} + /* - * AArch64 PCS assigns the frame pointer to x29. + * Start an unwind from a blocked task. * - * A simple function prologue looks like this: - * sub sp, sp, #0x10 - * stp x29, x30, [sp] - * mov x29, sp + * The unwind will begin at the blocked tasks saved PC (i.e. the caller of + * cpu_switch_to()). * - * A simple function epilogue looks like this: - * mov sp, x29 - * ldp x29, x30, [sp] - * add sp, sp, #0x10 + * The caller should ensure the task is blocked in cpu_switch_to() for the + * duration of the unwind, or the unwind will be bogus. It is never valid to + * call this for the current task. */ +static __always_inline void +kunwind_init_from_task(struct kunwind_state *state, + struct task_struct *task) +{ + kunwind_init(state, task); + state->common.fp = thread_saved_fp(task); + state->common.pc = thread_saved_pc(task); + state->source = KUNWIND_SOURCE_TASK; +} -void start_backtrace(struct stackframe *frame, unsigned long fp, - unsigned long pc) +static __always_inline int +kunwind_recover_return_address(struct kunwind_state *state) { - frame->fp = fp; - frame->pc = pc; #ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame->graph = 0; -#endif + if (state->task->ret_stack && + (state->common.pc == (unsigned long)return_to_handler)) { + unsigned long orig_pc; + orig_pc = ftrace_graph_ret_addr(state->task, &state->graph_idx, + state->common.pc, + (void *)state->common.fp); + if (state->common.pc == orig_pc) { + WARN_ON_ONCE(state->task == current); + return -EINVAL; + } + state->common.pc = orig_pc; + state->flags.fgraph = 1; + } +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ - /* - * Prime the first unwind. - * - * In unwind_frame() we'll check that the FP points to a valid stack, - * which can't be STACK_TYPE_UNKNOWN, and the first unwind will be - * treated as a transition to whichever stack that happens to be. The - * prev_fp value won't be used, but we set it to 0 such that it is - * definitely not an accessible stack address. - */ - bitmap_zero(frame->stacks_done, __NR_STACK_TYPES); - frame->prev_fp = 0; - frame->prev_type = STACK_TYPE_UNKNOWN; +#ifdef CONFIG_KRETPROBES + if (is_kretprobe_trampoline(state->common.pc)) { + unsigned long orig_pc; + orig_pc = kretprobe_find_ret_addr(state->task, + (void *)state->common.fp, + &state->kr_cur); + if (!orig_pc) + return -EINVAL; + state->common.pc = orig_pc; + state->flags.kretprobe = 1; + } +#endif /* CONFIG_KRETPROBES */ + + return 0; +} + +static __always_inline +int kunwind_next_regs_pc(struct kunwind_state *state) +{ + struct stack_info *info; + unsigned long fp = state->common.fp; + struct pt_regs *regs; + + regs = container_of((u64 *)fp, struct pt_regs, stackframe.record.fp); + + info = unwind_find_stack(&state->common, (unsigned long)regs, sizeof(*regs)); + if (!info) + return -EINVAL; + + unwind_consume_stack(&state->common, info, (unsigned long)regs, + sizeof(*regs)); + + state->regs = regs; + state->common.pc = regs->pc; + state->common.fp = regs->regs[29]; + state->regs = NULL; + state->source = KUNWIND_SOURCE_REGS_PC; + return 0; +} + +static __always_inline int +kunwind_next_frame_record_meta(struct kunwind_state *state) +{ + struct task_struct *tsk = state->task; + unsigned long fp = state->common.fp; + struct frame_record_meta *meta; + struct stack_info *info; + + info = unwind_find_stack(&state->common, fp, sizeof(*meta)); + if (!info) + return -EINVAL; + + meta = (struct frame_record_meta *)fp; + switch (READ_ONCE(meta->type)) { + case FRAME_META_TYPE_FINAL: + if (meta == &task_pt_regs(tsk)->stackframe) + return -ENOENT; + WARN_ON_ONCE(tsk == current); + return -EINVAL; + case FRAME_META_TYPE_PT_REGS: + return kunwind_next_regs_pc(state); + default: + WARN_ON_ONCE(tsk == current); + return -EINVAL; + } +} + +static __always_inline int +kunwind_next_frame_record(struct kunwind_state *state) +{ + unsigned long fp = state->common.fp; + struct frame_record *record; + struct stack_info *info; + unsigned long new_fp, new_pc; + + if (fp & 0x7) + return -EINVAL; + + info = unwind_find_stack(&state->common, fp, sizeof(*record)); + if (!info) + return -EINVAL; + + record = (struct frame_record *)fp; + new_fp = READ_ONCE(record->fp); + new_pc = READ_ONCE(record->lr); + + if (!new_fp && !new_pc) + return kunwind_next_frame_record_meta(state); + + unwind_consume_stack(&state->common, info, fp, sizeof(*record)); + + state->common.fp = new_fp; + state->common.pc = new_pc; + state->source = KUNWIND_SOURCE_FRAME; + + return 0; } /* @@ -63,112 +251,236 @@ void start_backtrace(struct stackframe *frame, unsigned long fp, * records (e.g. a cycle), determined based on the location and fp value of A * and the location (but not the fp value) of B. */ -int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) +static __always_inline int +kunwind_next(struct kunwind_state *state) { - unsigned long fp = frame->fp; - struct stack_info info; + int err; + + state->flags.all = 0; + + switch (state->source) { + case KUNWIND_SOURCE_FRAME: + case KUNWIND_SOURCE_CALLER: + case KUNWIND_SOURCE_TASK: + case KUNWIND_SOURCE_REGS_PC: + err = kunwind_next_frame_record(state); + break; + default: + err = -EINVAL; + } - if (!tsk) - tsk = current; + if (err) + return err; - /* Final frame; nothing to unwind */ - if (fp == (unsigned long)task_pt_regs(tsk)->stackframe) - return -ENOENT; + state->common.pc = ptrauth_strip_kernel_insn_pac(state->common.pc); - if (fp & 0x7) - return -EINVAL; + return kunwind_recover_return_address(state); +} - if (!on_accessible_stack(tsk, fp, 16, &info)) - return -EINVAL; +typedef bool (*kunwind_consume_fn)(const struct kunwind_state *state, void *cookie); - if (test_bit(info.type, frame->stacks_done)) - return -EINVAL; +static __always_inline int +do_kunwind(struct kunwind_state *state, kunwind_consume_fn consume_state, + void *cookie) +{ + int ret; - /* - * As stacks grow downward, any valid record on the same stack must be - * at a strictly higher address than the prior record. - * - * Stacks can nest in several valid orders, e.g. - * - * TASK -> IRQ -> OVERFLOW -> SDEI_NORMAL - * TASK -> SDEI_NORMAL -> SDEI_CRITICAL -> OVERFLOW - * - * ... but the nesting itself is strict. Once we transition from one - * stack to another, it's never valid to unwind back to that first - * stack. - */ - if (info.type == frame->prev_type) { - if (fp <= frame->prev_fp) + ret = kunwind_recover_return_address(state); + if (ret) + return ret; + + while (1) { + if (!consume_state(state, cookie)) + return -EINVAL; + ret = kunwind_next(state); + if (ret == -ENOENT) + return 0; + if (ret < 0) + return ret; + } +} + +/* + * Per-cpu stacks are only accessible when unwinding the current task in a + * non-preemptible context. + */ +#define STACKINFO_CPU(name) \ + ({ \ + ((task == current) && !preemptible()) \ + ? stackinfo_get_##name() \ + : stackinfo_get_unknown(); \ + }) + +/* + * SDEI stacks are only accessible when unwinding the current task in an NMI + * context. + */ +#define STACKINFO_SDEI(name) \ + ({ \ + ((task == current) && in_nmi()) \ + ? stackinfo_get_sdei_##name() \ + : stackinfo_get_unknown(); \ + }) + +#define STACKINFO_EFI \ + ({ \ + ((task == current) && current_in_efi()) \ + ? stackinfo_get_efi() \ + : stackinfo_get_unknown(); \ + }) + +static __always_inline int +kunwind_stack_walk(kunwind_consume_fn consume_state, + void *cookie, struct task_struct *task, + struct pt_regs *regs) +{ + struct stack_info stacks[] = { + stackinfo_get_task(task), + STACKINFO_CPU(irq), + STACKINFO_CPU(overflow), +#if defined(CONFIG_ARM_SDE_INTERFACE) + STACKINFO_SDEI(normal), + STACKINFO_SDEI(critical), +#endif +#ifdef CONFIG_EFI + STACKINFO_EFI, +#endif + }; + struct kunwind_state state = { + .common = { + .stacks = stacks, + .nr_stacks = ARRAY_SIZE(stacks), + }, + }; + + if (regs) { + if (task != current) return -EINVAL; + kunwind_init_from_regs(&state, regs); + } else if (task == current) { + kunwind_init_from_caller(&state); } else { - set_bit(frame->prev_type, frame->stacks_done); + kunwind_init_from_task(&state, task); } + return do_kunwind(&state, consume_state, cookie); +} + +struct kunwind_consume_entry_data { + stack_trace_consume_fn consume_entry; + void *cookie; +}; + +static __always_inline bool +arch_kunwind_consume_entry(const struct kunwind_state *state, void *cookie) +{ + struct kunwind_consume_entry_data *data = cookie; + return data->consume_entry(data->cookie, state->common.pc); +} + +noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, + void *cookie, struct task_struct *task, + struct pt_regs *regs) +{ + struct kunwind_consume_entry_data data = { + .consume_entry = consume_entry, + .cookie = cookie, + }; + + kunwind_stack_walk(arch_kunwind_consume_entry, &data, task, regs); +} + +static __always_inline bool +arch_reliable_kunwind_consume_entry(const struct kunwind_state *state, void *cookie) +{ /* - * Record this frame record's values and location. The prev_fp and - * prev_type are only meaningful to the next unwind_frame() invocation. + * At an exception boundary we can reliably consume the saved PC. We do + * not know whether the LR was live when the exception was taken, and + * so we cannot perform the next unwind step reliably. + * + * All that matters is whether the *entire* unwind is reliable, so give + * up as soon as we hit an exception boundary. */ - frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp)); - frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8)); - frame->prev_fp = fp; - frame->prev_type = info.type; + if (state->source == KUNWIND_SOURCE_REGS_PC) + return false; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - if (tsk->ret_stack && - (ptrauth_strip_insn_pac(frame->pc) == (unsigned long)return_to_handler)) { - struct ftrace_ret_stack *ret_stack; - /* - * This is a case where function graph tracer has - * modified a return address (LR) in a stack frame - * to hook a function return. - * So replace it to an original value. - */ - ret_stack = ftrace_graph_get_ret_stack(tsk, frame->graph++); - if (WARN_ON_ONCE(!ret_stack)) - return -EINVAL; - frame->pc = ret_stack->ret; - } -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + return arch_kunwind_consume_entry(state, cookie); +} + +noinline noinstr int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, + void *cookie, + struct task_struct *task) +{ + struct kunwind_consume_entry_data data = { + .consume_entry = consume_entry, + .cookie = cookie, + }; - frame->pc = ptrauth_strip_insn_pac(frame->pc); + return kunwind_stack_walk(arch_reliable_kunwind_consume_entry, &data, + task, NULL); +} - return 0; +struct bpf_unwind_consume_entry_data { + bool (*consume_entry)(void *cookie, u64 ip, u64 sp, u64 fp); + void *cookie; +}; + +static bool +arch_bpf_unwind_consume_entry(const struct kunwind_state *state, void *cookie) +{ + struct bpf_unwind_consume_entry_data *data = cookie; + + return data->consume_entry(data->cookie, state->common.pc, 0, + state->common.fp); } -NOKPROBE_SYMBOL(unwind_frame); -void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame, - bool (*fn)(void *, unsigned long), void *data) +noinline noinstr void arch_bpf_stack_walk(bool (*consume_entry)(void *cookie, u64 ip, u64 sp, + u64 fp), void *cookie) { - while (1) { - int ret; + struct bpf_unwind_consume_entry_data data = { + .consume_entry = consume_entry, + .cookie = cookie, + }; - if (!fn(data, frame->pc)) - break; - ret = unwind_frame(tsk, frame); - if (ret < 0) - break; + kunwind_stack_walk(arch_bpf_unwind_consume_entry, &data, current, NULL); +} + +static const char *state_source_string(const struct kunwind_state *state) +{ + switch (state->source) { + case KUNWIND_SOURCE_FRAME: return NULL; + case KUNWIND_SOURCE_CALLER: return "C"; + case KUNWIND_SOURCE_TASK: return "T"; + case KUNWIND_SOURCE_REGS_PC: return "P"; + default: return "U"; } } -NOKPROBE_SYMBOL(walk_stackframe); -static void dump_backtrace_entry(unsigned long where, const char *loglvl) +static bool dump_backtrace_entry(const struct kunwind_state *state, void *arg) { - printk("%s %pSb\n", loglvl, (void *)where); + const char *source = state_source_string(state); + union unwind_flags flags = state->flags; + bool has_info = source || flags.all; + char *loglvl = arg; + + printk("%s %pSb%s%s%s%s%s\n", loglvl, + (void *)state->common.pc, + has_info ? " (" : "", + source ? source : "", + flags.fgraph ? "F" : "", + flags.kretprobe ? "K" : "", + has_info ? ")" : ""); + + return true; } void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk, const char *loglvl) { - struct stackframe frame; - int skip = 0; - pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); - if (regs) { - if (user_mode(regs)) - return; - skip = 1; - } + if (regs && user_mode(regs)) + return; if (!tsk) tsk = current; @@ -176,36 +488,8 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk, if (!try_get_task_stack(tsk)) return; - if (tsk == current) { - start_backtrace(&frame, - (unsigned long)__builtin_frame_address(0), - (unsigned long)dump_backtrace); - } else { - /* - * task blocked in __switch_to - */ - start_backtrace(&frame, - thread_saved_fp(tsk), - thread_saved_pc(tsk)); - } - printk("%sCall trace:\n", loglvl); - do { - /* skip until specified stack frame */ - if (!skip) { - dump_backtrace_entry(frame.pc, loglvl); - } else if (frame.fp == regs->regs[29]) { - skip = 0; - /* - * Mostly, this is the case where this function is - * called in panic/abort. As exception handler's - * stack frame does not contain the corresponding pc - * at which an exception has taken place, use regs->pc - * instead. - */ - dump_backtrace_entry(regs->pc, loglvl); - } - } while (!unwind_frame(tsk, &frame)); + kunwind_stack_walk(dump_backtrace_entry, (void *)loglvl, tsk, regs); put_task_stack(tsk); } @@ -216,25 +500,122 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl) barrier(); } -#ifdef CONFIG_STACKTRACE +/* + * The struct defined for userspace stack frame in AARCH64 mode. + */ +struct frame_tail { + struct frame_tail __user *fp; + unsigned long lr; +} __attribute__((packed)); -noinline void arch_stack_walk(stack_trace_consume_fn consume_entry, - void *cookie, struct task_struct *task, - struct pt_regs *regs) +/* + * Get the return address for a single stackframe and return a pointer to the + * next frame tail. + */ +static struct frame_tail __user * +unwind_user_frame(struct frame_tail __user *tail, void *cookie, + stack_trace_consume_fn consume_entry) +{ + struct frame_tail buftail; + unsigned long err; + unsigned long lr; + + /* Also check accessibility of one struct frame_tail beyond */ + if (!access_ok(tail, sizeof(buftail))) + return NULL; + + pagefault_disable(); + err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail)); + pagefault_enable(); + + if (err) + return NULL; + + lr = ptrauth_strip_user_insn_pac(buftail.lr); + + if (!consume_entry(cookie, lr)) + return NULL; + + /* + * Frame pointers should strictly progress back up the stack + * (towards higher addresses). + */ + if (tail >= buftail.fp) + return NULL; + + return buftail.fp; +} + +#ifdef CONFIG_COMPAT +/* + * The registers we're interested in are at the end of the variable + * length saved register structure. The fp points at the end of this + * structure so the address of this struct is: + * (struct compat_frame_tail *)(xxx->fp)-1 + * + * This code has been adapted from the ARM OProfile support. + */ +struct compat_frame_tail { + compat_uptr_t fp; /* a (struct compat_frame_tail *) in compat mode */ + u32 sp; + u32 lr; +} __attribute__((packed)); + +static struct compat_frame_tail __user * +unwind_compat_user_frame(struct compat_frame_tail __user *tail, void *cookie, + stack_trace_consume_fn consume_entry) { - struct stackframe frame; + struct compat_frame_tail buftail; + unsigned long err; + + /* Also check accessibility of one struct frame_tail beyond */ + if (!access_ok(tail, sizeof(buftail))) + return NULL; + + pagefault_disable(); + err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail)); + pagefault_enable(); + + if (err) + return NULL; + + if (!consume_entry(cookie, buftail.lr)) + return NULL; - if (regs) - start_backtrace(&frame, regs->regs[29], regs->pc); - else if (task == current) - start_backtrace(&frame, - (unsigned long)__builtin_frame_address(1), - (unsigned long)__builtin_return_address(0)); - else - start_backtrace(&frame, thread_saved_fp(task), - thread_saved_pc(task)); + /* + * Frame pointers should strictly progress back up the stack + * (towards higher addresses). + */ + if (tail + 1 >= (struct compat_frame_tail __user *) + compat_ptr(buftail.fp)) + return NULL; - walk_stackframe(task, &frame, consume_entry, cookie); + return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1; } +#endif /* CONFIG_COMPAT */ + + +void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, + const struct pt_regs *regs) +{ + if (!consume_entry(cookie, regs->pc)) + return; + if (!compat_user_mode(regs)) { + /* AARCH64 mode */ + struct frame_tail __user *tail; + + tail = (struct frame_tail __user *)regs->regs[29]; + while (tail && !((unsigned long)tail & 0x7)) + tail = unwind_user_frame(tail, cookie, consume_entry); + } else { +#ifdef CONFIG_COMPAT + /* AARCH32 compat mode */ + struct compat_frame_tail __user *tail; + + tail = (struct compat_frame_tail __user *)regs->compat_fp - 1; + while (tail && !((unsigned long)tail & 0x3)) + tail = unwind_compat_user_frame(tail, cookie, consume_entry); #endif + } +} |
