* Fix lockdep's detection of "USED" <- "IN-NMI" inversions, from Peter

Zijlstra.
 
 * Make percpu-rwsem operations on the semaphore's ->read_count IRQ-safe
   because it can be used in an IRQ context, from Hou Tao.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAl9nsLQACgkQEsHwGGHe
 VUo0+g/7B9JzDtRSgchT095VcD8w+YcZTyiJM58q9I9OZMxi1zdJZPyoQZ2xZjnG
 aczDJN5H6P6OcBm949EUCHhmDEDfoZpC7Y5FEHe9dJitPmC7rRilGJuz4Im8td3N
 DsLhpFe8KUSqRVyygjvjM393md8tw+m4Jq+syjWri4/1wj1Fs4jHdhKWgz6b2cup
 JXbfjgVOkHVOTloMHnmgdHOPvkh60/LoG8r/5gzLbD8Z/FTD3BSOCTgw+8L8EB+b
 yiWWuEcR5LDjy7sNY2xVhTB+nkHJXe4o+HVufZoAzd1j7FDLfDVSNaZHJVp2m7Gp
 W47xRrzIKIJl6DUp5E4TGi9aZvkO/h5kqSOZ4MhfaeEqw9DLW/KxbherJjzVY3bb
 Nt74N+N+WOq6riTVx5wJkDRmtT5RaeW1kKJUaSeGMl3fxCken5CKE1WyBbae0GiU
 kq3tCn4t0OKCWhuiixFNg6RxuXokjfzXDiHr9aUt3x5musc9P+5YUIdOMsaHwoAH
 0YrAZoRCPyE2ABUgKC8hoTc3Y+TIwji7c0B9S2GoHRTm1LZTRURlLOUQyJ4oU9Ez
 Vt5TILwre9lX9tTW7BlxlOCYkgRQn78vLBSOy1CEUTsORbdYnv/kCy5S5yHEILpT
 f3E345wzdd8zrXGQfX2jsVgNAx0F+81Fb9H9FMJSCFgjIya+SRM=
 =70QQ
 -----END PGP SIGNATURE-----

Merge tag 'locking_urgent_for_v5.9_rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking fixes from Borislav Petkov:
 "Two fixes from the locking/urgent pile:

   - Fix lockdep's detection of "USED" <- "IN-NMI" inversions (Peter
     Zijlstra)

   - Make percpu-rwsem operations on the semaphore's ->read_count
     IRQ-safe because it can be used in an IRQ context (Hou Tao)"

* tag 'locking_urgent_for_v5.9_rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  locking/percpu-rwsem: Use this_cpu_{inc,dec}() for read_count
  locking/lockdep: Fix "USED" <- "IN-NMI" inversions

include/linux/percpu-rwsem.h

@@ -60,7 +60,7 @@ static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
 	 * anything we did within this RCU-sched read-size critical section.
 	 */
 	if (likely(rcu_sync_is_idle(&sem->rss)))
-		__this_cpu_inc(*sem->read_count);
+		this_cpu_inc(*sem->read_count);
 	else
 		__percpu_down_read(sem, false); /* Unconditional memory barrier */
 	/*
@@ -79,7 +79,7 @@ static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 	 * Same as in percpu_down_read().
 	 */
 	if (likely(rcu_sync_is_idle(&sem->rss)))
-		__this_cpu_inc(*sem->read_count);
+		this_cpu_inc(*sem->read_count);
 	else
 		ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */
 	preempt_enable();
@@ -103,7 +103,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
 	 * Same as in percpu_down_read().
 	 */
 	if (likely(rcu_sync_is_idle(&sem->rss))) {
-		__this_cpu_dec(*sem->read_count);
+		this_cpu_dec(*sem->read_count);
 	} else {
 		/*
 		 * slowpath; reader will only ever wake a single blocked
@@ -115,7 +115,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
 		 * aggregate zero, as that is the only time it matters) they
 		 * will also see our critical section.
 		 */
-		__this_cpu_dec(*sem->read_count);
+		this_cpu_dec(*sem->read_count);
 		rcuwait_wake_up(&sem->writer);
 	}
 	preempt_enable();

kernel/locking/lockdep.c

@@ -3969,13 +3969,18 @@ static int separate_irq_context(struct task_struct *curr,
 static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			     enum lock_usage_bit new_bit)
 {
-	unsigned int new_mask = 1 << new_bit, ret = 1;
+	unsigned int old_mask, new_mask, ret = 1;
 
 	if (new_bit >= LOCK_USAGE_STATES) {
 		DEBUG_LOCKS_WARN_ON(1);
 		return 0;
 	}
 
+	if (new_bit == LOCK_USED && this->read)
+		new_bit = LOCK_USED_READ;
+
+	new_mask = 1 << new_bit;
+
 	/*
 	 * If already set then do not dirty the cacheline,
 	 * nor do any checks:
@@ -3988,13 +3993,22 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 	/*
 	 * Make sure we didn't race:
 	 */
-	if (unlikely(hlock_class(this)->usage_mask & new_mask)) {
+	if (unlikely(hlock_class(this)->usage_mask & new_mask))
-		graph_unlock();
+		goto unlock;
-		return 1;
-	}
 
+	old_mask = hlock_class(this)->usage_mask;
 	hlock_class(this)->usage_mask |= new_mask;
 
+	/*
+	 * Save one usage_traces[] entry and map both LOCK_USED and
+	 * LOCK_USED_READ onto the same entry.
+	 */
+	if (new_bit == LOCK_USED || new_bit == LOCK_USED_READ) {
+		if (old_mask & (LOCKF_USED | LOCKF_USED_READ))
+			goto unlock;
+		new_bit = LOCK_USED;
+	}
+
 	if (!(hlock_class(this)->usage_traces[new_bit] = save_trace()))
 		return 0;
 
@@ -4008,6 +4022,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			return 0;
 	}
 
+unlock:
 	graph_unlock();
 
 	/*
@@ -4942,12 +4957,20 @@ static void verify_lock_unused(struct lockdep_map *lock, struct held_lock *hlock
 {
 #ifdef CONFIG_PROVE_LOCKING
 	struct lock_class *class = look_up_lock_class(lock, subclass);
+	unsigned long mask = LOCKF_USED;
 
 	/* if it doesn't have a class (yet), it certainly hasn't been used yet */
 	if (!class)
 		return;
 
-	if (!(class->usage_mask & LOCK_USED))
+	/*
+	 * READ locks only conflict with USED, such that if we only ever use
+	 * READ locks, there is no deadlock possible -- RCU.
+	 */
+	if (!hlock->read)
+		mask |= LOCKF_USED_READ;
+
+	if (!(class->usage_mask & mask))
 		return;
 
 	hlock->class_idx = class - lock_classes;

kernel/locking/lockdep_internals.h

@@ -19,6 +19,7 @@ enum lock_usage_bit {
 #include "lockdep_states.h"
 #undef LOCKDEP_STATE
 	LOCK_USED,
+	LOCK_USED_READ,
 	LOCK_USAGE_STATES
 };
 
@@ -40,6 +41,7 @@ enum {
 #include "lockdep_states.h"
 #undef LOCKDEP_STATE
 	__LOCKF(USED)
+	__LOCKF(USED_READ)
 };
 
 #define LOCKDEP_STATE(__STATE)	LOCKF_ENABLED_##__STATE |

kernel/locking/percpu-rwsem.c

@@ -45,7 +45,7 @@ EXPORT_SYMBOL_GPL(percpu_free_rwsem);
 
 static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 {
-	__this_cpu_inc(*sem->read_count);
+	this_cpu_inc(*sem->read_count);
 
 	/*
 	 * Due to having preemption disabled the decrement happens on
@@ -71,7 +71,7 @@ static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 	if (likely(!atomic_read_acquire(&sem->block)))
 		return true;
 
-	__this_cpu_dec(*sem->read_count);
+	this_cpu_dec(*sem->read_count);
 
 	/* Prod writer to re-evaluate readers_active_check() */
 	rcuwait_wake_up(&sem->writer);