diff options
Diffstat (limited to 'arch/x86/kernel/unwind_orc.c')
| -rw-r--r-- | arch/x86/kernel/unwind_orc.c | 323 |
1 files changed, 233 insertions, 90 deletions
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 26038eacf74a..977ee75e047c 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -1,3 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/objtool.h> #include <linux/module.h> #include <linux/sort.h> #include <asm/ptrace.h> @@ -5,21 +7,73 @@ #include <asm/unwind.h> #include <asm/orc_types.h> #include <asm/orc_lookup.h> +#include <asm/orc_header.h> + +ORC_HEADER; #define orc_warn(fmt, ...) \ - printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__) + printk_deferred_once(KERN_WARNING "WARNING: " fmt, ##__VA_ARGS__) + +#define orc_warn_current(args...) \ +({ \ + static bool dumped_before; \ + if (state->task == current && !state->error) { \ + orc_warn(args); \ + if (unwind_debug && !dumped_before) { \ + dumped_before = true; \ + unwind_dump(state); \ + } \ + } \ +}) extern int __start_orc_unwind_ip[]; extern int __stop_orc_unwind_ip[]; extern struct orc_entry __start_orc_unwind[]; extern struct orc_entry __stop_orc_unwind[]; -static DEFINE_MUTEX(sort_mutex); -int *cur_orc_ip_table = __start_orc_unwind_ip; -struct orc_entry *cur_orc_table = __start_orc_unwind; +static bool orc_init __ro_after_init; +static bool unwind_debug __ro_after_init; +static unsigned int lookup_num_blocks __ro_after_init; + +static int __init unwind_debug_cmdline(char *str) +{ + unwind_debug = true; + + return 0; +} +early_param("unwind_debug", unwind_debug_cmdline); + +static void unwind_dump(struct unwind_state *state) +{ + static bool dumped_before; + unsigned long word, *sp; + struct stack_info stack_info = {0}; + unsigned long visit_mask = 0; + + if (dumped_before) + return; -unsigned int lookup_num_blocks; -bool orc_init; + dumped_before = true; + + printk_deferred("unwind stack type:%d next_sp:%p mask:0x%lx graph_idx:%d\n", + state->stack_info.type, state->stack_info.next_sp, + state->stack_mask, state->graph_idx); + + for (sp = __builtin_frame_address(0); sp; + sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { + if (get_stack_info(sp, state->task, &stack_info, &visit_mask)) + break; + + for (; sp < stack_info.end; sp++) { + + word = READ_ONCE_NOCHECK(*sp); + + printk_deferred("%0*lx: %0*lx (%pB)\n", BITS_PER_LONG/4, + (unsigned long)sp, BITS_PER_LONG/4, + word, (void *)word); + } + } +} static inline unsigned long orc_ip(const int *ip) { @@ -31,7 +85,7 @@ static struct orc_entry *__orc_find(int *ip_table, struct orc_entry *u_table, { int *first = ip_table; int *last = ip_table + num_entries - 1; - int *mid = first, *found = first; + int *mid, *found = first; if (!num_entries) return NULL; @@ -81,30 +135,35 @@ static struct orc_entry *orc_find(unsigned long ip); * But they are copies of the ftrace entries that are static and * defined in ftrace_*.S, which do have orc entries. * - * If the undwinder comes across a ftrace trampoline, then find the + * If the unwinder comes across a ftrace trampoline, then find the * ftrace function that was used to create it, and use that ftrace - * function's orc entrie, as the placement of the return code in + * function's orc entry, as the placement of the return code in * the stack will be identical. */ static struct orc_entry *orc_ftrace_find(unsigned long ip) { struct ftrace_ops *ops; - unsigned long caller; + unsigned long tramp_addr, offset; ops = ftrace_ops_trampoline(ip); if (!ops) return NULL; + /* Set tramp_addr to the start of the code copied by the trampoline */ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) - caller = (unsigned long)ftrace_regs_call; + tramp_addr = (unsigned long)ftrace_regs_caller; else - caller = (unsigned long)ftrace_call; + tramp_addr = (unsigned long)ftrace_caller; + + /* Now place tramp_addr to the location within the trampoline ip is at */ + offset = ip - ops->trampoline; + tramp_addr += offset; /* Prevent unlikely recursion */ - if (ip == caller) + if (ip == tramp_addr) return NULL; - return orc_find(caller); + return orc_find(tramp_addr); } #else static struct orc_entry *orc_ftrace_find(unsigned long ip) @@ -113,12 +172,35 @@ static struct orc_entry *orc_ftrace_find(unsigned long ip) } #endif +/* + * If we crash with IP==0, the last successfully executed instruction + * was probably an indirect function call with a NULL function pointer, + * and we don't have unwind information for NULL. + * This hardcoded ORC entry for IP==0 allows us to unwind from a NULL function + * pointer into its parent and then continue normally from there. + */ +static struct orc_entry null_orc_entry = { + .sp_offset = sizeof(long), + .sp_reg = ORC_REG_SP, + .bp_reg = ORC_REG_UNDEFINED, + .type = ORC_TYPE_CALL +}; + +/* Fake frame pointer entry -- used as a fallback for generated code */ +static struct orc_entry orc_fp_entry = { + .type = ORC_TYPE_CALL, + .sp_reg = ORC_REG_BP, + .sp_offset = 16, + .bp_reg = ORC_REG_PREV_SP, + .bp_offset = -16, +}; + static struct orc_entry *orc_find(unsigned long ip) { static struct orc_entry *orc; - if (!orc_init) - return NULL; + if (ip == 0) + return &null_orc_entry; /* For non-init vmlinux addresses, use the fast lookup table: */ if (ip >= LOOKUP_START_IP && ip < LOOKUP_STOP_IP) { @@ -147,7 +229,7 @@ static struct orc_entry *orc_find(unsigned long ip) } /* vmlinux .init slow lookup: */ - if (init_kernel_text(ip)) + if (is_kernel_inittext(ip)) return __orc_find(__start_orc_unwind_ip, __start_orc_unwind, __stop_orc_unwind_ip - __start_orc_unwind_ip, ip); @@ -159,10 +241,15 @@ static struct orc_entry *orc_find(unsigned long ip) return orc_ftrace_find(ip); } +#ifdef CONFIG_MODULES + +static DEFINE_MUTEX(sort_mutex); +static int *cur_orc_ip_table = __start_orc_unwind_ip; +static struct orc_entry *cur_orc_table = __start_orc_unwind; + static void orc_sort_swap(void *_a, void *_b, int size) { struct orc_entry *orc_a, *orc_b; - struct orc_entry orc_tmp; int *a = _a, *b = _b, tmp; int delta = _b - _a; @@ -174,9 +261,7 @@ static void orc_sort_swap(void *_a, void *_b, int size) /* Swap the corresponding .orc_unwind entries: */ orc_a = cur_orc_table + (a - cur_orc_ip_table); orc_b = cur_orc_table + (b - cur_orc_ip_table); - orc_tmp = *orc_a; - *orc_a = *orc_b; - *orc_b = orc_tmp; + swap(*orc_a, *orc_b); } static int orc_sort_cmp(const void *_a, const void *_b) @@ -192,16 +277,15 @@ static int orc_sort_cmp(const void *_a, const void *_b) return -1; /* - * The "weak" section terminator entries need to always be on the left + * The "weak" section terminator entries need to always be first * to ensure the lookup code skips them in favor of real entries. * These terminator entries exist to handle any gaps created by * whitelisted .o files which didn't get objtool generation. */ orc_a = cur_orc_table + (a - cur_orc_ip_table); - return orc_a->sp_reg == ORC_REG_UNDEFINED && !orc_a->end ? -1 : 1; + return orc_a->type == ORC_TYPE_UNDEFINED ? -1 : 1; } -#ifdef CONFIG_MODULES void unwind_module_init(struct module *mod, void *_orc_ip, size_t orc_ip_size, void *_orc, size_t orc_size) { @@ -245,9 +329,11 @@ void __init unwind_init(void) return; } - /* Sort the .orc_unwind and .orc_unwind_ip tables: */ - sort(__start_orc_unwind_ip, num_entries, sizeof(int), orc_sort_cmp, - orc_sort_swap); + /* + * Note, the orc_unwind and orc_unwind_ip tables were already + * sorted at build time via the 'sorttable' tool. + * It's ready for binary search straight away, no need to sort it. + */ /* Initialize the fast lookup table: */ lookup_num_blocks = orc_lookup_end - orc_lookup; @@ -304,11 +390,11 @@ static bool stack_access_ok(struct unwind_state *state, unsigned long _addr, struct stack_info *info = &state->stack_info; void *addr = (void *)_addr; - if (!on_stack(info, addr, len) && - (get_stack_info(addr, state->task, info, &state->stack_mask))) - return false; + if (on_stack(info, addr, len)) + return true; - return true; + return !get_stack_info(addr, state->task, info, &state->stack_mask) && + on_stack(info, addr, len); } static bool deref_stack_reg(struct unwind_state *state, unsigned long addr, @@ -332,8 +418,8 @@ static bool deref_stack_regs(struct unwind_state *state, unsigned long addr, if (!stack_access_ok(state, addr, sizeof(struct pt_regs))) return false; - *ip = regs->ip; - *sp = regs->sp; + *ip = READ_ONCE_NOCHECK(regs->ip); + *sp = READ_ONCE_NOCHECK(regs->sp); return true; } @@ -345,14 +431,43 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr if (!stack_access_ok(state, addr, IRET_FRAME_SIZE)) return false; - *ip = regs->ip; - *sp = regs->sp; + *ip = READ_ONCE_NOCHECK(regs->ip); + *sp = READ_ONCE_NOCHECK(regs->sp); return true; } +/* + * If state->regs is non-NULL, and points to a full pt_regs, just get the reg + * value from state->regs. + * + * Otherwise, if state->regs just points to IRET regs, and the previous frame + * had full regs, it's safe to get the value from the previous regs. This can + * happen when early/late IRQ entry code gets interrupted by an NMI. + */ +static bool get_reg(struct unwind_state *state, unsigned int reg_off, + unsigned long *val) +{ + unsigned int reg = reg_off/8; + + if (!state->regs) + return false; + + if (state->full_regs) { + *val = READ_ONCE_NOCHECK(((unsigned long *)state->regs)[reg]); + return true; + } + + if (state->prev_regs) { + *val = READ_ONCE_NOCHECK(((unsigned long *)state->prev_regs)[reg]); + return true; + } + + return false; +} + bool unwind_next_frame(struct unwind_state *state) { - unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp; + unsigned long ip_p, sp, tmp, orig_ip = state->ip, prev_sp = state->sp; enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; bool indirect = false; @@ -361,7 +476,7 @@ bool unwind_next_frame(struct unwind_state *state) return false; /* Don't let modules unload while we're reading their ORC data. */ - preempt_disable(); + guard(rcu)(); /* End-of-stack check for user tasks: */ if (state->regs && user_mode(state->regs)) @@ -370,21 +485,32 @@ bool unwind_next_frame(struct unwind_state *state) /* * Find the orc_entry associated with the text address. * - * Decrement call return addresses by one so they work for sibling - * calls and calls to noreturn functions. + * For a call frame (as opposed to a signal frame), state->ip points to + * the instruction after the call. That instruction's stack layout + * could be different from the call instruction's layout, for example + * if the call was to a noreturn function. So get the ORC data for the + * call instruction itself. */ orc = orc_find(state->signal ? state->ip : state->ip - 1); - if (!orc) - goto err; - - /* End-of-stack check for kernel threads: */ - if (orc->sp_reg == ORC_REG_UNDEFINED) { - if (!orc->end) + if (!orc) { + /* + * As a fallback, try to assume this code uses a frame pointer. + * This is useful for generated code, like BPF, which ORC + * doesn't know about. This is just a guess, so the rest of + * the unwind is no longer considered reliable. + */ + orc = &orc_fp_entry; + state->error = true; + } else { + if (orc->type == ORC_TYPE_UNDEFINED) goto err; - goto the_end; + if (orc->type == ORC_TYPE_END_OF_STACK) + goto the_end; } + state->signal = orc->signal; + /* Find the previous frame's stack: */ switch (orc->sp_reg) { case ORC_REG_SP: @@ -396,7 +522,7 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_REG_SP_INDIRECT: - sp = state->sp + orc->sp_offset; + sp = state->sp; indirect = true; break; @@ -406,43 +532,39 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_REG_R10: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R10 at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, r10), &sp)) { + orc_warn_current("missing R10 value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->r10; break; case ORC_REG_R13: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R13 at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, r13), &sp)) { + orc_warn_current("missing R13 value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->r13; break; case ORC_REG_DI: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DI at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, di), &sp)) { + orc_warn_current("missing RDI value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->di; break; case ORC_REG_DX: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DX at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, dx), &sp)) { + orc_warn_current("missing DX value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->dx; break; default: - orc_warn("unknown SP base reg %d for ip %pB\n", + orc_warn("unknown SP base reg %d at %pB\n", orc->sp_reg, (void *)state->ip); goto err; } @@ -450,6 +572,9 @@ bool unwind_next_frame(struct unwind_state *state) if (indirect) { if (!deref_stack_reg(state, sp, &sp)) goto err; + + if (orc->sp_reg == ORC_REG_SP_INDIRECT) + sp += orc->sp_offset; } /* Find IP, SP and possibly regs: */ @@ -460,49 +585,63 @@ bool unwind_next_frame(struct unwind_state *state) if (!deref_stack_reg(state, ip_p, &state->ip)) goto err; - state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, - state->ip, (void *)ip_p); - + state->ip = unwind_recover_ret_addr(state, state->ip, + (unsigned long *)ip_p); state->sp = sp; state->regs = NULL; - state->signal = false; + state->prev_regs = NULL; break; case ORC_TYPE_REGS: if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) { - orc_warn("can't dereference registers at %p for ip %pB\n", - (void *)sp, (void *)orig_ip); + orc_warn_current("can't access registers at %pB\n", + (void *)orig_ip); goto err; } - + /* + * There is a small chance to interrupt at the entry of + * arch_rethook_trampoline() where the ORC info doesn't exist. + * That point is right after the RET to arch_rethook_trampoline() + * which was modified return address. + * At that point, the @addr_p of the unwind_recover_rethook() + * (this has to point the address of the stack entry storing + * the modified return address) must be "SP - (a stack entry)" + * because SP is incremented by the RET. + */ + state->ip = unwind_recover_rethook(state, state->ip, + (unsigned long *)(state->sp - sizeof(long))); state->regs = (struct pt_regs *)sp; + state->prev_regs = NULL; state->full_regs = true; - state->signal = true; break; - case ORC_TYPE_REGS_IRET: + case ORC_TYPE_REGS_PARTIAL: if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) { - orc_warn("can't dereference iret registers at %p for ip %pB\n", - (void *)sp, (void *)orig_ip); + orc_warn_current("can't access iret registers at %pB\n", + (void *)orig_ip); goto err; } + /* See ORC_TYPE_REGS case comment. */ + state->ip = unwind_recover_rethook(state, state->ip, + (unsigned long *)(state->sp - sizeof(long))); + if (state->full_regs) + state->prev_regs = state->regs; state->regs = (void *)sp - IRET_FRAME_OFFSET; state->full_regs = false; - state->signal = true; break; default: - orc_warn("unknown .orc_unwind entry type %d for ip %pB\n", + orc_warn("unknown .orc_unwind entry type %d at %pB\n", orc->type, (void *)orig_ip); - break; + goto err; } /* Find BP: */ switch (orc->bp_reg) { case ORC_REG_UNDEFINED: - if (state->regs && state->full_regs) - state->bp = state->regs->bp; + if (get_reg(state, offsetof(struct pt_regs, bp), &tmp)) + state->bp = tmp; break; case ORC_REG_PREV_SP: @@ -525,19 +664,17 @@ bool unwind_next_frame(struct unwind_state *state) if (state->stack_info.type == prev_type && on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) && state->sp <= prev_sp) { - orc_warn("stack going in the wrong direction? ip=%pB\n", - (void *)orig_ip); + orc_warn_current("stack going in the wrong direction? at %pB\n", + (void *)orig_ip); goto err; } - preempt_enable(); return true; err: state->error = true; the_end: - preempt_enable(); state->stack_info.type = STACK_TYPE_UNKNOWN; return false; } @@ -549,20 +686,23 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, memset(state, 0, sizeof(*state)); state->task = task; + if (!orc_init) + goto err; + /* * Refuse to unwind the stack of a task while it's executing on another * CPU. This check is racy, but that's ok: the unwinder has other * checks to prevent it from going off the rails. */ if (task_on_another_cpu(task)) - goto done; + goto err; if (regs) { if (user_mode(regs)) - goto done; + goto the_end; state->ip = regs->ip; - state->sp = kernel_stack_pointer(regs); + state->sp = regs->sp; state->bp = regs->bp; state->regs = regs; state->full_regs = true; @@ -578,9 +718,10 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, } else { struct inactive_task_frame *frame = (void *)task->thread.sp; - state->sp = task->thread.sp; + state->sp = task->thread.sp + sizeof(*frame); state->bp = READ_ONCE_NOCHECK(frame->bp); state->ip = READ_ONCE_NOCHECK(frame->ret_addr); + state->signal = (void *)state->ip == ret_from_fork_asm; } if (get_stack_info((unsigned long *)state->sp, state->task, @@ -592,6 +733,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, * generate some kind of backtrace if this happens. */ void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp); + state->error = true; if (get_stack_info(next_page, state->task, &state->stack_info, &state->stack_mask)) return; @@ -617,8 +759,9 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, return; -done: +err: + state->error = true; +the_end: state->stack_info.type = STACK_TYPE_UNKNOWN; - return; } EXPORT_SYMBOL_GPL(__unwind_start); |