Re: [PATCH] locking/static_key: Fix false positive warnings on concurrent dec/inc

[Peter Zijlstra <peterz@infradead.org>]

On Mon, Mar 18, 2019 at 02:58:14PM -0700, Jakub Kicinski wrote:
> Even though the atomic_dec_and_mutex_lock() in
> __static_key_slow_dec_cpuslocked() can never see a negative
> value in key->enabled the subsequent sanity check is re-reading
> key->enabled, which may have been set to -1 in the meantime by
> static_key_slow_inc_cpuslocked().

A little extra detail might not hurt, or a diagram or something.

> Instead of using -1 as a "enable in progress" constant use
> -0xffff, this way we can still treat smaller negative values
> as errors.

Those offset games always hurt my brain, but see below.

> Fixes: 4c5ea0a9cd02 ("locking/static_key: Fix concurrent static_key_slow_inc()")
> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
> ---
>  kernel/jump_label.c | 21 ++++++++++-----------
>  1 file changed, 10 insertions(+), 11 deletions(-)
> 
> diff --git a/kernel/jump_label.c b/kernel/jump_label.c
> index bad96b476eb6..4a227e70a8f3 100644
> --- a/kernel/jump_label.c
> +++ b/kernel/jump_label.c
> @@ -89,7 +89,7 @@ static void jump_label_update(struct static_key *key);
>  int static_key_count(struct static_key *key)
>  {
>  	/*
> -	 * -1 means the first static_key_slow_inc() is in progress.
> +	 * -0xffff means the first static_key_slow_inc() is in progress.
>  	 *  static_key_enabled() must return true, so return 1 here.
>  	 */
>  	int n = atomic_read(&key->enabled);
> @@ -125,7 +125,10 @@ void static_key_slow_inc_cpuslocked(struct static_key *key)
>  
>  	jump_label_lock();
>  	if (atomic_read(&key->enabled) == 0) {
> -		atomic_set(&key->enabled, -1);
> +		/* Use a large enough negative number so we can still
> +		 * catch underflow bugs in static_key_slow_dec().
> +		 */

Broken comment style.

> +		atomic_set(&key->enabled, -0xffff);
>  		jump_label_update(key);
>  		/*
>  		 * Ensure that if the above cmpxchg loop observes our positive
> @@ -158,7 +161,7 @@ void static_key_enable_cpuslocked(struct static_key *key)
>  
>  	jump_label_lock();
>  	if (atomic_read(&key->enabled) == 0) {
> -		atomic_set(&key->enabled, -1);
> +		atomic_set(&key->enabled, -0xffff);
>  		jump_label_update(key);
>  		/*
>  		 * See static_key_slow_inc().
> @@ -208,15 +211,11 @@ static void __static_key_slow_dec_cpuslocked(struct static_key *key,
>  {
>  	lockdep_assert_cpus_held();
>  
> -	/*
> -	 * The negative count check is valid even when a negative
> -	 * key->enabled is in use by static_key_slow_inc(); a
> -	 * __static_key_slow_dec() before the first static_key_slow_inc()
> -	 * returns is unbalanced, because all other static_key_slow_inc()
> -	 * instances block while the update is in progress.
> -	 */
>  	if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
> -		WARN(atomic_read(&key->enabled) < 0,
> +		int v;
> +
> +		v = atomic_read(&key->enabled);
> +		WARN(v < 0 && v != -0xffff,
>  		     "jump label: negative count!\n");
>  		return;
>  	}

> Alternatively we could implement atomic_dec_and_mutex_lock_return().

I think I like that better, something like:

---
 kernel/jump_label.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index bad96b476eb6..a799b1ac6b2f 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -206,6 +206,8 @@ static void __static_key_slow_dec_cpuslocked(struct static_key *key,
 					   unsigned long rate_limit,
 					   struct delayed_work *work)
 {
+	int val;
+
 	lockdep_assert_cpus_held();
 
 	/*
@@ -215,17 +217,20 @@ static void __static_key_slow_dec_cpuslocked(struct static_key *key,
 	 * returns is unbalanced, because all other static_key_slow_inc()
 	 * instances block while the update is in progress.
 	 */
-	if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
-		WARN(atomic_read(&key->enabled) < 0,
-		     "jump label: negative count!\n");
+	val = atomic_fetch_add_unless(&key->enabled, -1, 1);
+	if (val != 1) {
+		WARN(val < 0, "jump label: negative count!\n");
 		return;
 	}
 
-	if (rate_limit) {
-		atomic_inc(&key->enabled);
-		schedule_delayed_work(work, rate_limit);
-	} else {
-		jump_label_update(key);
+	jump_label_lock();
+	if (atomic_dec_and_test(&key->enabled)) {
+		if (rate_limit) {
+			atomic_inc(&key->enabled);
+			schedule_delayed_work(work, rate_limit);
+		} else {
+			jump_label_update(key);
+		}
 	}
 	jump_label_unlock();
 }