4 files changed, 51 insertions, 13 deletions

diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 495f5c051b03..9852e0d62d95 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -256,7 +256,7 @@ noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
 	exit_to_user_mode();
 }
 
-irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs)
+noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 {
 	irqentry_state_t ret = {
 		.exit_rcu = false,
@@ -333,7 +333,7 @@ void irqentry_exit_cond_resched(void)
 	}
 }
 
-void noinstr irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
+noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
 {
 	lockdep_assert_irqs_disabled();
 
diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c
index 15f67949d11e..732623c30359 100644
--- a/kernel/kcsan/core.c
+++ b/kernel/kcsan/core.c
@@ -397,8 +397,7 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type)
 	}
 
 	if (!kcsan_interrupt_watcher)
-		/* Use raw to avoid lockdep recursion via IRQ flags tracing. */
-		raw_local_irq_save(irq_flags);
+		local_irq_save(irq_flags);
 
 	watchpoint = insert_watchpoint((unsigned long)ptr, size, is_write);
 	if (watchpoint == NULL) {
@@ -539,7 +538,7 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type)
 	kcsan_counter_dec(KCSAN_COUNTER_USED_WATCHPOINTS);
 out_unlock:
 	if (!kcsan_interrupt_watcher)
-		raw_local_irq_restore(irq_flags);
+		local_irq_restore(irq_flags);
 out:
 	user_access_restore(ua_flags);
 }
diff --git a/kernel/kcsan/report.c b/kernel/kcsan/report.c
index ac5f8345bae9..6b2fb1a6d8cd 100644
--- a/kernel/kcsan/report.c
+++ b/kernel/kcsan/report.c
@@ -606,10 +606,11 @@ void kcsan_report(const volatile void *ptr, size_t size, int access_type,
 		goto out;
 
 	/*
-	 * With TRACE_IRQFLAGS, lockdep's IRQ trace state becomes corrupted if
-	 * we do not turn off lockdep here; this could happen due to recursion
-	 * into lockdep via KCSAN if we detect a race in utilities used by
-	 * lockdep.
+	 * Because we may generate reports when we're in scheduler code, the use
+	 * of printk() could deadlock. Until such time that all printing code
+	 * called in print_report() is scheduler-safe, accept the risk, and just
+	 * get our message out. As such, also disable lockdep to hide the
+	 * warning, and avoid disabling lockdep for the rest of the kernel.
 	 */
 	lockdep_off();
 
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 29a8de4c50b9..d595623c4b34 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -395,7 +395,7 @@ void lockdep_init_task(struct task_struct *task)
 
 static __always_inline void lockdep_recursion_finish(void)
 {
-	if (WARN_ON_ONCE(--current->lockdep_recursion))
+	if (WARN_ON_ONCE((--current->lockdep_recursion) & LOCKDEP_RECURSION_MASK))
 		current->lockdep_recursion = 0;
 }
 
@@ -3646,7 +3646,16 @@ static void __trace_hardirqs_on_caller(void)
  */
 void lockdep_hardirqs_on_prepare(unsigned long ip)
 {
-	if (unlikely(!debug_locks || current->lockdep_recursion))
+	if (unlikely(!debug_locks))
+		return;
+
+	/*
+	 * NMIs do not (and cannot) track lock dependencies, nothing to do.
+	 */
+	if (unlikely(in_nmi()))
+		return;
+
+	if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK))
 		return;
 
 	if (unlikely(current->hardirqs_enabled)) {
@@ -3692,7 +3701,27 @@ void noinstr lockdep_hardirqs_on(unsigned long ip)
 {
 	struct task_struct *curr = current;
 
-	if (unlikely(!debug_locks || curr->lockdep_recursion))
+	if (unlikely(!debug_locks))
+		return;
+
+	/*
+	 * NMIs can happen in the middle of local_irq_{en,dis}able() where the
+	 * tracking state and hardware state are out of sync.
+	 *
+	 * NMIs must save lockdep_hardirqs_enabled() to restore IRQ state from,
+	 * and not rely on hardware state like normal interrupts.
+	 */
+	if (unlikely(in_nmi())) {
+		/*
+		 * Skip:
+		 *  - recursion check, because NMI can hit lockdep;
+		 *  - hardware state check, because above;
+		 *  - chain_key check, see lockdep_hardirqs_on_prepare().
+		 */
+		goto skip_checks;
+	}
+
+	if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK))
 		return;
 
 	if (curr->hardirqs_enabled) {
@@ -3720,6 +3749,7 @@ void noinstr lockdep_hardirqs_on(unsigned long ip)
 	DEBUG_LOCKS_WARN_ON(current->hardirq_chain_key !=
 			    current->curr_chain_key);
 
+skip_checks:
 	/* we'll do an OFF -> ON transition: */
 	curr->hardirqs_enabled = 1;
 	curr->hardirq_enable_ip = ip;
@@ -3735,7 +3765,15 @@ void noinstr lockdep_hardirqs_off(unsigned long ip)
 {
 	struct task_struct *curr = current;
 
-	if (unlikely(!debug_locks || curr->lockdep_recursion))
+	if (unlikely(!debug_locks))
+		return;
+
+	/*
+	 * Matching lockdep_hardirqs_on(), allow NMIs in the middle of lockdep;
+	 * they will restore the software state. This ensures the software
+	 * state is consistent inside NMIs as well.
+	 */
+	if (unlikely(!in_nmi() && (current->lockdep_recursion & LOCKDEP_RECURSION_MASK)))
 		return;
 
 	/*