[PATCH AUTOSEL 4.14 03/14] kprobes: Fix potential deadlock in kprobe_optimizer()

[Sasha Levin]

From: Andrea Righi <andrea.righi@xxxxxxxxxxxxx>

[ Upstream commit f1c6ece23729257fb46562ff9224cf5f61b818da ]

lockdep reports the following deadlock scenario:

 WARNING: possible circular locking dependency detected

 kworker/1:1/48 is trying to acquire lock:
 000000008d7a62b2 (text_mutex){+.+.}, at: kprobe_optimizer+0x163/0x290

 but task is already holding lock:
 00000000850b5e2d (module_mutex){+.+.}, at: kprobe_optimizer+0x31/0x290

 which lock already depends on the new lock.

 the existing dependency chain (in reverse order) is:

 -> #1 (module_mutex){+.+.}:
        __mutex_lock+0xac/0x9f0
        mutex_lock_nested+0x1b/0x20
        set_all_modules_text_rw+0x22/0x90
        ftrace_arch_code_modify_prepare+0x1c/0x20
        ftrace_run_update_code+0xe/0x30
        ftrace_startup_enable+0x2e/0x50
        ftrace_startup+0xa7/0x100
        register_ftrace_function+0x27/0x70
        arm_kprobe+0xb3/0x130
        enable_kprobe+0x83/0xa0
        enable_trace_kprobe.part.0+0x2e/0x80
        kprobe_register+0x6f/0xc0
        perf_trace_event_init+0x16b/0x270
        perf_kprobe_init+0xa7/0xe0
        perf_kprobe_event_init+0x3e/0x70
        perf_try_init_event+0x4a/0x140
        perf_event_alloc+0x93a/0xde0
        __do_sys_perf_event_open+0x19f/0xf30
        __x64_sys_perf_event_open+0x20/0x30
        do_syscall_64+0x65/0x1d0
        entry_SYSCALL_64_after_hwframe+0x49/0xbe

 -> #0 (text_mutex){+.+.}:
        __lock_acquire+0xfcb/0x1b60
        lock_acquire+0xca/0x1d0
        __mutex_lock+0xac/0x9f0
        mutex_lock_nested+0x1b/0x20
        kprobe_optimizer+0x163/0x290
        process_one_work+0x22b/0x560
        worker_thread+0x50/0x3c0
        kthread+0x112/0x150
        ret_from_fork+0x3a/0x50

 other info that might help us debug this:

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock(module_mutex);
                                lock(text_mutex);
                                lock(module_mutex);
   lock(text_mutex);

  *** DEADLOCK ***

As a reproducer I've been using bcc's funccount.py
(https://github.com/iovisor/bcc/blob/master/tools/funccount.py),
for example:

 # ./funccount.py '*interrupt*'

That immediately triggers the lockdep splat.

Fix by acquiring text_mutex before module_mutex in kprobe_optimizer().

Signed-off-by: Andrea Righi <andrea.righi@xxxxxxxxxxxxx>
Acked-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@xxxxxxxxx>
Cc: David S. Miller <davem@xxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Naveen N. Rao <naveen.n.rao@xxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Fixes: d5b844a2cf50 ("ftrace/x86: Remove possible deadlock between register_kprobe() and ftrace_run_update_code()")
Link: http://lkml.kernel.org/r/20190812184302.GA7010@xps-13
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
 kernel/kprobes.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ec11bb986a8b4..c43bc2bc5b2ca 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -483,6 +483,7 @@ static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
  */
 static void do_optimize_kprobes(void)
 {
+	lockdep_assert_held(&text_mutex);
 	/*
 	 * The optimization/unoptimization refers online_cpus via
 	 * stop_machine() and cpu-hotplug modifies online_cpus.
@@ -500,9 +501,7 @@ static void do_optimize_kprobes(void)
 	    list_empty(&optimizing_list))
 		return;
 
-	mutex_lock(&text_mutex);
 	arch_optimize_kprobes(&optimizing_list);
-	mutex_unlock(&text_mutex);
 }
 
 /*
@@ -513,6 +512,7 @@ static void do_unoptimize_kprobes(void)
 {
 	struct optimized_kprobe *op, *tmp;
 
+	lockdep_assert_held(&text_mutex);
 	/* See comment in do_optimize_kprobes() */
 	lockdep_assert_cpus_held();
 
@@ -520,7 +520,6 @@ static void do_unoptimize_kprobes(void)
 	if (list_empty(&unoptimizing_list))
 		return;
 
-	mutex_lock(&text_mutex);
 	arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list);
 	/* Loop free_list for disarming */
 	list_for_each_entry_safe(op, tmp, &freeing_list, list) {
@@ -537,7 +536,6 @@ static void do_unoptimize_kprobes(void)
 		} else
 			list_del_init(&op->list);
 	}
-	mutex_unlock(&text_mutex);
 }
 
 /* Reclaim all kprobes on the free_list */
@@ -563,6 +561,7 @@ static void kprobe_optimizer(struct work_struct *work)
 {
 	mutex_lock(&kprobe_mutex);
 	cpus_read_lock();
+	mutex_lock(&text_mutex);
 	/* Lock modules while optimizing kprobes */
 	mutex_lock(&module_mutex);
 
@@ -590,6 +589,7 @@ static void kprobe_optimizer(struct work_struct *work)
 	do_free_cleaned_kprobes();
 
 	mutex_unlock(&module_mutex);
+	mutex_unlock(&text_mutex);
 	cpus_read_unlock();
 	mutex_unlock(&kprobe_mutex);
 
-- 
2.20.1