From 9b38cc704e844e41d9cf74e647bff1d249512cb3 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 12 May 2020 17:03:18 +0900 Subject: kretprobe: Prevent triggering kretprobe from within kprobe_flush_task Ziqian reported lockup when adding retprobe on _raw_spin_lock_irqsave. My test was also able to trigger lockdep output: ============================================ WARNING: possible recursive locking detected 5.6.0-rc6+ #6 Not tainted -------------------------------------------- sched-messaging/2767 is trying to acquire lock: ffffffff9a492798 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_hash_lock+0x52/0xa0 but task is already holding lock: ffffffff9a491a18 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_trampoline+0x0/0x50 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(kretprobe_table_locks[i].lock)); lock(&(kretprobe_table_locks[i].lock)); *** DEADLOCK *** May be due to missing lock nesting notation 1 lock held by sched-messaging/2767: #0: ffffffff9a491a18 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_trampoline+0x0/0x50 stack backtrace: CPU: 3 PID: 2767 Comm: sched-messaging Not tainted 5.6.0-rc6+ #6 Call Trace: dump_stack+0x96/0xe0 __lock_acquire.cold.57+0x173/0x2b7 ? native_queued_spin_lock_slowpath+0x42b/0x9e0 ? lockdep_hardirqs_on+0x590/0x590 ? __lock_acquire+0xf63/0x4030 lock_acquire+0x15a/0x3d0 ? kretprobe_hash_lock+0x52/0xa0 _raw_spin_lock_irqsave+0x36/0x70 ? kretprobe_hash_lock+0x52/0xa0 kretprobe_hash_lock+0x52/0xa0 trampoline_handler+0xf8/0x940 ? kprobe_fault_handler+0x380/0x380 ? find_held_lock+0x3a/0x1c0 kretprobe_trampoline+0x25/0x50 ? lock_acquired+0x392/0xbc0 ? _raw_spin_lock_irqsave+0x50/0x70 ? __get_valid_kprobe+0x1f0/0x1f0 ? _raw_spin_unlock_irqrestore+0x3b/0x40 ? finish_task_switch+0x4b9/0x6d0 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 The code within the kretprobe handler checks for probe reentrancy, so we won't trigger any _raw_spin_lock_irqsave probe in there. The problem is in outside kprobe_flush_task, where we call: kprobe_flush_task kretprobe_table_lock raw_spin_lock_irqsave _raw_spin_lock_irqsave where _raw_spin_lock_irqsave triggers the kretprobe and installs kretprobe_trampoline handler on _raw_spin_lock_irqsave return. The kretprobe_trampoline handler is then executed with already locked kretprobe_table_locks, and first thing it does is to lock kretprobe_table_locks ;-) the whole lockup path like: kprobe_flush_task kretprobe_table_lock raw_spin_lock_irqsave _raw_spin_lock_irqsave ---> probe triggered, kretprobe_trampoline installed ---> kretprobe_table_locks locked kretprobe_trampoline trampoline_handler kretprobe_hash_lock(current, &head, &flags); <--- deadlock Adding kprobe_busy_begin/end helpers that mark code with fake probe installed to prevent triggering of another kprobe within this code. Using these helpers in kprobe_flush_task, so the probe recursion protection check is hit and the probe is never set to prevent above lockup. Link: http://lkml.kernel.org/r/158927059835.27680.7011202830041561604.stgit@devnote2 Fixes: ef53d9c5e4da ("kprobes: improve kretprobe scalability with hashed locking") Cc: Ingo Molnar Cc: "Gustavo A . R . Silva" Cc: Anders Roxell Cc: "Naveen N . Rao" Cc: Anil S Keshavamurthy Cc: David Miller Cc: Ingo Molnar Cc: Peter Zijlstra Cc: stable@vger.kernel.org Reported-by: "Ziqian SUN (Zamir)" Acked-by: Masami Hiramatsu Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt (VMware) --- arch/x86/kernel/kprobes/core.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 3bafe1bd4dc7..8a5ec10e95dc 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -753,16 +753,11 @@ asm( NOKPROBE_SYMBOL(kretprobe_trampoline); STACK_FRAME_NON_STANDARD(kretprobe_trampoline); -static struct kprobe kretprobe_kprobe = { - .addr = (void *)kretprobe_trampoline, -}; - /* * Called from kretprobe_trampoline */ __used __visible void *trampoline_handler(struct pt_regs *regs) { - struct kprobe_ctlblk *kcb; struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; struct hlist_node *tmp; @@ -772,16 +767,12 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) void *frame_pointer; bool skipped = false; - preempt_disable(); - /* * Set a dummy kprobe for avoiding kretprobe recursion. * Since kretprobe never run in kprobe handler, kprobe must not * be running at this point. */ - kcb = get_kprobe_ctlblk(); - __this_cpu_write(current_kprobe, &kretprobe_kprobe); - kcb->kprobe_status = KPROBE_HIT_ACTIVE; + kprobe_busy_begin(); INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); @@ -857,7 +848,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) __this_cpu_write(current_kprobe, &ri->rp->kp); ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, &kretprobe_kprobe); + __this_cpu_write(current_kprobe, &kprobe_busy); } recycle_rp_inst(ri, &empty_rp); @@ -873,8 +864,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); - __this_cpu_write(current_kprobe, NULL); - preempt_enable(); + kprobe_busy_end(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); -- cgit v1.2.3