diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index f7e3cd50ece0..98f654d466e5 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1020,6 +1020,15 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) regs->flags &= ~X86_EFLAGS_IF; trace_hardirqs_off(); regs->ip = (unsigned long)(jp->entry); + + /* + * jprobes use jprobe_return() which skips the normal return + * path of the function, and this messes up the accounting of the + * function graph tracer to get messed up. + * + * Pause function graph tracing while performing the jprobe function. + */ + pause_graph_tracing(); return 1; } NOKPROBE_SYMBOL(setjmp_pre_handler); @@ -1048,24 +1057,25 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); u8 *addr = (u8 *) (regs->ip - 1); struct jprobe *jp = container_of(p, struct jprobe, kp); + void *saved_sp = kcb->jprobe_saved_sp; if ((addr > (u8 *) jprobe_return) && (addr < (u8 *) jprobe_return_end)) { - if (stack_addr(regs) != kcb->jprobe_saved_sp) { + if (stack_addr(regs) != saved_sp) { struct pt_regs *saved_regs = &kcb->jprobe_saved_regs; printk(KERN_ERR "current sp %p does not match saved sp %p\n", - stack_addr(regs), kcb->jprobe_saved_sp); + stack_addr(regs), saved_sp); printk(KERN_ERR "Saved registers for jprobe %p\n", jp); show_regs(saved_regs); printk(KERN_ERR "Current registers\n"); show_regs(regs); BUG(); } + /* It's OK to start function graph tracing again */ + unpause_graph_tracing(); *regs = kcb->jprobe_saved_regs; - memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp), - kcb->jprobes_stack, - MIN_STACK_SIZE(kcb->jprobe_saved_sp)); + memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp)); preempt_enable_no_resched(); return 1; } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 929a733d302e..224e768bdc73 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2497,12 +2497,14 @@ static void ftrace_run_update_code(int command) } static void ftrace_run_modify_code(struct ftrace_ops *ops, int command, - struct ftrace_hash *old_hash) + struct ftrace_ops_hash *old_hash) { ops->flags |= FTRACE_OPS_FL_MODIFYING; - ops->old_hash.filter_hash = old_hash; + ops->old_hash.filter_hash = old_hash->filter_hash; + ops->old_hash.notrace_hash = old_hash->notrace_hash; ftrace_run_update_code(command); ops->old_hash.filter_hash = NULL; + ops->old_hash.notrace_hash = NULL; ops->flags &= ~FTRACE_OPS_FL_MODIFYING; } @@ -3579,7 +3581,7 @@ static struct ftrace_ops trace_probe_ops __read_mostly = static int ftrace_probe_registered; -static void __enable_ftrace_function_probe(struct ftrace_hash *old_hash) +static void __enable_ftrace_function_probe(struct ftrace_ops_hash *old_hash) { int ret; int i; @@ -3637,6 +3639,7 @@ int register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, void *data) { + struct ftrace_ops_hash old_hash_ops; struct ftrace_func_probe *entry; struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash; struct ftrace_hash *old_hash = *orig_hash; @@ -3658,6 +3661,10 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, mutex_lock(&trace_probe_ops.func_hash->regex_lock); + old_hash_ops.filter_hash = old_hash; + /* Probes only have filters */ + old_hash_ops.notrace_hash = NULL; + hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash); if (!hash) { count = -ENOMEM; @@ -3718,7 +3725,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash); - __enable_ftrace_function_probe(old_hash); + __enable_ftrace_function_probe(&old_hash_ops); if (!ret) free_ftrace_hash_rcu(old_hash); @@ -4006,10 +4013,34 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) } static void ftrace_ops_update_code(struct ftrace_ops *ops, - struct ftrace_hash *old_hash) + struct ftrace_ops_hash *old_hash) { - if (ops->flags & FTRACE_OPS_FL_ENABLED && ftrace_enabled) + struct ftrace_ops *op; + + if (!ftrace_enabled) + return; + + if (ops->flags & FTRACE_OPS_FL_ENABLED) { ftrace_run_modify_code(ops, FTRACE_UPDATE_CALLS, old_hash); + return; + } + + /* + * If this is the shared global_ops filter, then we need to + * check if there is another ops that shares it, is enabled. + * If so, we still need to run the modify code. + */ + if (ops->func_hash != &global_ops.local_hash) + return; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + if (op->func_hash == &global_ops.local_hash && + op->flags & FTRACE_OPS_FL_ENABLED) { + ftrace_run_modify_code(op, FTRACE_UPDATE_CALLS, old_hash); + /* Only need to do this once */ + return; + } + } while_for_each_ftrace_op(op); } static int @@ -4017,6 +4048,7 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, unsigned long ip, int remove, int reset, int enable) { struct ftrace_hash **orig_hash; + struct ftrace_ops_hash old_hash_ops; struct ftrace_hash *old_hash; struct ftrace_hash *hash; int ret; @@ -4053,9 +4085,11 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, mutex_lock(&ftrace_lock); old_hash = *orig_hash; + old_hash_ops.filter_hash = ops->func_hash->filter_hash; + old_hash_ops.notrace_hash = ops->func_hash->notrace_hash; ret = ftrace_hash_move(ops, enable, orig_hash, hash); if (!ret) { - ftrace_ops_update_code(ops, old_hash); + ftrace_ops_update_code(ops, &old_hash_ops); free_ftrace_hash_rcu(old_hash); } mutex_unlock(&ftrace_lock); @@ -4267,6 +4301,7 @@ static void __init set_ftrace_early_filters(void) int ftrace_regex_release(struct inode *inode, struct file *file) { struct seq_file *m = (struct seq_file *)file->private_data; + struct ftrace_ops_hash old_hash_ops; struct ftrace_iterator *iter; struct ftrace_hash **orig_hash; struct ftrace_hash *old_hash; @@ -4300,10 +4335,12 @@ int ftrace_regex_release(struct inode *inode, struct file *file) mutex_lock(&ftrace_lock); old_hash = *orig_hash; + old_hash_ops.filter_hash = iter->ops->func_hash->filter_hash; + old_hash_ops.notrace_hash = iter->ops->func_hash->notrace_hash; ret = ftrace_hash_move(iter->ops, filter_hash, orig_hash, iter->hash); if (!ret) { - ftrace_ops_update_code(iter->ops, old_hash); + ftrace_ops_update_code(iter->ops, &old_hash_ops); free_ftrace_hash_rcu(old_hash); } mutex_unlock(&ftrace_lock); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2e767972e99c..4a9079b9f082 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6918,7 +6918,6 @@ void __init trace_init(void) tracepoint_printk = 0; } tracer_alloc_buffers(); - init_ftrace_syscalls(); trace_event_init(); } diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 366a78a3e61e..b03a0ea77b99 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2429,12 +2429,39 @@ static __init int event_trace_memsetup(void) return 0; } +static __init void +early_enable_events(struct trace_array *tr, bool disable_first) +{ + char *buf = bootup_event_buf; + char *token; + int ret; + + while (true) { + token = strsep(&buf, ","); + + if (!token) + break; + if (!*token) + continue; + + /* Restarting syscalls requires that we stop them first */ + if (disable_first) + ftrace_set_clr_event(tr, token, 0); + + ret = ftrace_set_clr_event(tr, token, 1); + if (ret) + pr_warn("Failed to enable trace event: %s\n", token); + + /* Put back the comma to allow this to be called again */ + if (buf) + *(buf - 1) = ','; + } +} + static __init int event_trace_enable(void) { struct trace_array *tr = top_trace_array(); struct ftrace_event_call **iter, *call; - char *buf = bootup_event_buf; - char *token; int ret; if (!tr) @@ -2456,18 +2483,7 @@ static __init int event_trace_enable(void) */ __trace_early_add_events(tr); - while (true) { - token = strsep(&buf, ","); - - if (!token) - break; - if (!*token) - continue; - - ret = ftrace_set_clr_event(tr, token, 1); - if (ret) - pr_warn("Failed to enable trace event: %s\n", token); - } + early_enable_events(tr, false); trace_printk_start_comm(); @@ -2478,6 +2494,31 @@ static __init int event_trace_enable(void) return 0; } +/* + * event_trace_enable() is called from trace_event_init() first to + * initialize events and perhaps start any events that are on the + * command line. Unfortunately, there are some events that will not + * start this early, like the system call tracepoints that need + * to set the TIF_SYSCALL_TRACEPOINT flag of pid 1. But event_trace_enable() + * is called before pid 1 starts, and this flag is never set, making + * the syscall tracepoint never get reached, but the event is enabled + * regardless (and not doing anything). + */ +static __init int event_trace_enable_again(void) +{ + struct trace_array *tr; + + tr = top_trace_array(); + if (!tr) + return -ENODEV; + + early_enable_events(tr, true); + + return 0; +} + +early_initcall(event_trace_enable_again); + static __init int event_trace_init(void) { struct trace_array *tr;