lockdep: Teach lockdep about "USED" <- "IN-NMI" inversions

nmi_enter() does lockdep_off() and hence lockdep ignores everything.

And NMI context makes it impossible to do full IN-NMI tracking like we
do IN-HARDIRQ, that could result in graph_lock recursion.

However, since look_up_lock_class() is lockless, we can find the class
of a lock that has prior use and detect IN-NMI after USED, just not
USED after IN-NMI.

NOTE: By shifting the lockdep_off() recursion count to bit-16, we can
easily differentiate between actual recursion and off.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Link: https://lkml.kernel.org/r/20200221134215.090538203@infradead.org

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 47e3acb6b5c97305baa59aa5bbe614d20a5c0f2f..4c3b1ccc6c2d38f544a085f0aaee331c33021ea2 100644 (file)
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -393,15 +393,22 @@ void lockdep_init_task(struct task_struct *task)
        task->lockdep_recursion = 0;
 }
 
+/*
+ * Split the recrursion counter in two to readily detect 'off' vs recursion.
+ */
+#define LOCKDEP_RECURSION_BITS 16
+#define LOCKDEP_OFF            (1U << LOCKDEP_RECURSION_BITS)
+#define LOCKDEP_RECURSION_MASK (LOCKDEP_OFF - 1)
+
 void lockdep_off(void)
 {
-       current->lockdep_recursion++;
+       current->lockdep_recursion += LOCKDEP_OFF;
 }
 EXPORT_SYMBOL(lockdep_off);
 
 void lockdep_on(void)
 {
-       current->lockdep_recursion--;
+       current->lockdep_recursion -= LOCKDEP_OFF;
 }
 EXPORT_SYMBOL(lockdep_on);
 
@@ -597,6 +604,7 @@ static const char *usage_str[] =
 #include "lockdep_states.h"
 #undef LOCKDEP_STATE
        [LOCK_USED] = "INITIAL USE",
+       [LOCK_USAGE_STATES] = "IN-NMI",
 };
 #endif
 
@@ -809,6 +817,7 @@ static int count_matching_names(struct lock_class *new_class)
        return count + 1;
 }
 
+/* used from NMI context -- must be lockless */
 static inline struct lock_class *
 look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass)
 {
@@ -4720,6 +4729,36 @@ void lock_downgrade(struct lockdep_map *lock, unsigned long ip)
 }
 EXPORT_SYMBOL_GPL(lock_downgrade);
 
+/* NMI context !!! */
+static void verify_lock_unused(struct lockdep_map *lock, struct held_lock *hlock, int subclass)
+{
+#ifdef CONFIG_PROVE_LOCKING
+       struct lock_class *class = look_up_lock_class(lock, subclass);
+
+       /* if it doesn't have a class (yet), it certainly hasn't been used yet */
+       if (!class)
+               return;
+
+       if (!(class->usage_mask & LOCK_USED))
+               return;
+
+       hlock->class_idx = class - lock_classes;
+
+       print_usage_bug(current, hlock, LOCK_USED, LOCK_USAGE_STATES);
+#endif
+}
+
+static bool lockdep_nmi(void)
+{
+       if (current->lockdep_recursion & LOCKDEP_RECURSION_MASK)
+               return false;
+
+       if (!in_nmi())
+               return false;
+
+       return true;
+}
+
 /*
  * We are not always called with irqs disabled - do that here,
  * and also avoid lockdep recursion:
@@ -4730,8 +4769,25 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 {
        unsigned long flags;
 
-       if (unlikely(current->lockdep_recursion))
+       if (unlikely(current->lockdep_recursion)) {
+               /* XXX allow trylock from NMI ?!? */
+               if (lockdep_nmi() && !trylock) {
+                       struct held_lock hlock;
+
+                       hlock.acquire_ip = ip;
+                       hlock.instance = lock;
+                       hlock.nest_lock = nest_lock;
+                       hlock.irq_context = 2; // XXX
+                       hlock.trylock = trylock;
+                       hlock.read = read;
+                       hlock.check = check;
+                       hlock.hardirqs_off = true;
+                       hlock.references = 0;
+
+                       verify_lock_unused(lock, &hlock, subclass);
+               }
                return;
+       }
 
        raw_local_irq_save(flags);
        check_flags(flags);