linux-kernel - Re: [Linux-v4.6-rc1] ext4: WARNING: CPU: 2 PID: 2692 at kernel/locking/lockdep.c:2017 __lock

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Wed, 30 Mar 2016 11:36:59 +0200
From:	Peter Zijlstra <peterz@...radead.org>
To:	Ingo Molnar <mingo@...nel.org>
Cc:	Alfredo Alvarez Fernandez <alfredoalvarezfernandez@...il.com>,
	Linus Torvalds <torvalds@...ux-foundation.org>,
	Sedat Dilek <sedat.dilek@...il.com>,
	Theodore Ts'o <tytso@....edu>,
	linux-fsdevel <linux-fsdevel@...r.kernel.org>,
	LKML <linux-kernel@...r.kernel.org>
Subject: Re: [Linux-v4.6-rc1] ext4: WARNING: CPU: 2 PID: 2692 at
 kernel/locking/lockdep.c:2017 __lock_acquire+0x180e/0x2260

On Tue, Mar 29, 2016 at 10:47:02AM +0200, Ingo Molnar wrote:

> > You are right; this is lockdep running into a hash collision; which is a new 
> > DEBUG_LOCKDEP test. See 9e4e7554e755 ("locking/lockdep: Detect chain_key 
> > collisions").
> 
> I've Cc:-ed Alfredo Alvarez Fernandez who added that test.

OK, so while the code in check_no_collision() seems sensible, it relies
on borken bits.

The whole chain_hlocks and /proc/lockdep_chains stuff appears to have
been buggered from the start.

The below patch should fix this.

Furthermore, our hash function has definite room for improvement.

---
 include/linux/lockdep.h       |  8 +++++---
 kernel/locking/lockdep.c      | 30 ++++++++++++++++++++++++------
 kernel/locking/lockdep_proc.c |  2 ++
 3 files changed, 31 insertions(+), 9 deletions(-)

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index d026b190c530..2568c120513b 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -196,9 +196,11 @@ struct lock_list {
  * We record lock dependency chains, so that we can cache them:
  */
 struct lock_chain {
-	u8				irq_context;
-	u8				depth;
-	u16				base;
+	/* see BUILD_BUG_ON()s in lookup_chain_cache() */
+	unsigned int			irq_context :  2,
+					depth       :  6,
+					base	    : 24;
+	/* 4 byte hole */
 	struct hlist_node		entry;
 	u64				chain_key;
 };
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 53ab2f85d77e..91a4b7780afb 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -2099,15 +2099,37 @@ static inline int lookup_chain_cache(struct task_struct *curr,
 	chain->irq_context = hlock->irq_context;
 	i = get_first_held_lock(curr, hlock);
 	chain->depth = curr->lockdep_depth + 1 - i;
+
+	BUILD_BUG_ON((1UL << 24) <= ARRAY_SIZE(chain_hlocks));
+	BUILD_BUG_ON((1UL << 6)  <= ARRAY_SIZE(curr->held_locks));
+	BUILD_BUG_ON((1UL << 8*sizeof(chain_hlocks[0])) <= ARRAY_SIZE(lock_classes));
+
 	if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) {
 		chain->base = nr_chain_hlocks;
-		nr_chain_hlocks += chain->depth;
 		for (j = 0; j < chain->depth - 1; j++, i++) {
 			int lock_id = curr->held_locks[i].class_idx - 1;
 			chain_hlocks[chain->base + j] = lock_id;
 		}
 		chain_hlocks[chain->base + j] = class - lock_classes;
 	}
+
+	if (nr_chain_hlocks < MAX_LOCKDEP_CHAIN_HLOCKS)
+		nr_chain_hlocks += chain->depth;
+
+#ifdef CONFIG_DEBUG_LOCKDEP
+	/*
+	 * Important for check_no_collision().
+	 */
+	if (unlikely(nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)) {
+		if (debug_locks_off_graph_unlock())
+			return 0;
+
+		print_lockdep_off("BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!");
+		dump_stack();
+		return 0;
+	}
+#endif
+
 	hlist_add_head_rcu(&chain->entry, hash_head);
 	debug_atomic_inc(chain_lookup_misses);
 	inc_chains();
@@ -2860,11 +2882,6 @@ static int separate_irq_context(struct task_struct *curr,
 {
 	unsigned int depth = curr->lockdep_depth;
 
-	/*
-	 * Keep track of points where we cross into an interrupt context:
-	 */
-	hlock->irq_context = 2*(curr->hardirq_context ? 1 : 0) +
-				curr->softirq_context;
 	if (depth) {
 		struct held_lock *prev_hlock;
 
@@ -3164,6 +3181,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	hlock->acquire_ip = ip;
 	hlock->instance = lock;
 	hlock->nest_lock = nest_lock;
+	hlock->irq_context = 2*(!!curr->hardirq_context) + !!curr->softirq_context;
 	hlock->trylock = trylock;
 	hlock->read = read;
 	hlock->check = check;
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index dbb61a302548..a0f61effad25 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -141,6 +141,8 @@ static int lc_show(struct seq_file *m, void *v)
 	int i;
 
 	if (v == SEQ_START_TOKEN) {
+		if (nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)
+			seq_printf(m, "(buggered) ");
 		seq_printf(m, "all lock chains:\n");
 		return 0;
 	}