Merge tag 'kvm-s390-next-7.2-2' of https://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

* Fix S390_USER_OPEREXEC so it can now be enabled regardless of other
  unrelated capabilities

* Fix handling of the _PAGE_UNUSED pte bit that could lead to guest
  memory corruption in some scenarios

* A bunch of misc gmap fixes (locking, behaviour under memory pressure)

* Fix CMMA dirty tracking

1 files changed, 37 insertions, 9 deletions

diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index b18a682fe3da..6fb00e08a4e2 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -720,6 +720,41 @@ static inline bool debug_objects_is_pi_blocked_on(void)
 #endif
 }
 
+static inline bool can_fill_pool(void)
+{
+	/*
+	 * On !RT enabled kernels there are no restrictions and spinlock_t and
+	 * raw_spinlock_t are the same types.
+	 */
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		return true;
+
+	/*
+	 * On RT enabled kernels, the task must not be blocked on a lock as
+	 * that could corrupt the PI state when blocking on a lock in the
+	 * allocation path.
+	 */
+	if (debug_objects_is_pi_blocked_on())
+		return false;
+
+	/*
+	 * On RT enabled kernels the pool refill should happen in preemptible
+	 * context.
+	 */
+	if (preemptible())
+		return true;
+
+	/*
+	 * Though during system boot before scheduling is set up, preemption is
+	 * disabled and the pool can get exhausted. Before scheduling is active
+	 * a task cannot be blocked on a sleeping lock, but it might hold a lock
+	 * and if interrupted then hard interrupt context might run into a lock
+	 * inversion. So exclude hard interrupt context from allocations before
+	 * scheduling is active.
+	 */
+	return system_state < SYSTEM_SCHEDULING && !in_hardirq();
+}
+
 static void debug_objects_fill_pool(void)
 {
 	if (!static_branch_likely(&obj_cache_enabled))
@@ -734,18 +769,11 @@ static void debug_objects_fill_pool(void)
 	if (likely(!pool_should_refill(&pool_global)))
 		return;
 
-	/*
-	 * On RT enabled kernels the pool refill must happen in preemptible
-	 * context and not enqueued on an rt_mutex -- for !RT kernels we rely
-	 * on the fact that spinlock_t and raw_spinlock_t are basically the
-	 * same type and this lock-type inversion works just fine.
-	 */
-	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || system_state < SYSTEM_SCHEDULING ||
-	    (preemptible() && !debug_objects_is_pi_blocked_on())) {
+	if (can_fill_pool()) {
 		/*
 		 * Annotate away the spinlock_t inside raw_spinlock_t warning
 		 * by temporarily raising the wait-type to LD_WAIT_CONFIG, matching
-		 * the preemptible() condition above.
+		 * the preemptible() condition in can_fill_pool().
 		 */
 		static DEFINE_WAIT_OVERRIDE_MAP(fill_pool_map, LD_WAIT_CONFIG);
 		lock_map_acquire_try(&fill_pool_map);