Merge tag 'core-debugobjects-2023-05-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull debugobjects fixes from Thomas Gleixner:
"Two fixes for debugobjects:
- Prevent the allocation path from waking up kswapd.
That's a long standing issue due to the GFP_ATOMIC allocation flag.
As debug objects can be invoked from pretty much any context waking
kswapd can end up in arbitrary lock chains versus the waitqueue
lock
- Correct the explicit lockdep wait-type violation in
debug_object_fill_pool()"
* tag 'core-debugobjects-2023-05-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
debugobjects: Don't wake up kswapd from fill_pool()
debugobjects,locking: Annotate debug_object_fill_pool() wait type violation
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index b32256e..74bd269 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -344,6 +344,16 @@
#define lockdep_repin_lock(l,c) lock_repin_lock(&(l)->dep_map, (c))
#define lockdep_unpin_lock(l,c) lock_unpin_lock(&(l)->dep_map, (c))
+/*
+ * Must use lock_map_aquire_try() with override maps to avoid
+ * lockdep thinking they participate in the block chain.
+ */
+#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \
+ struct lockdep_map _name = { \
+ .name = #_name "-wait-type-override", \
+ .wait_type_inner = _wait_type, \
+ .lock_type = LD_LOCK_WAIT_OVERRIDE, }
+
#else /* !CONFIG_LOCKDEP */
static inline void lockdep_init_task(struct task_struct *task)
@@ -432,6 +442,9 @@
#define lockdep_repin_lock(l, c) do { (void)(l); (void)(c); } while (0)
#define lockdep_unpin_lock(l, c) do { (void)(l); (void)(c); } while (0)
+#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \
+ struct lockdep_map __maybe_unused _name = {}
+
#endif /* !LOCKDEP */
enum xhlock_context_t {
@@ -556,6 +569,7 @@
#define rwsem_release(l, i) lock_release(l, i)
#define lock_map_acquire(l) lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_)
+#define lock_map_acquire_try(l) lock_acquire_exclusive(l, 0, 1, NULL, _THIS_IP_)
#define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_)
#define lock_map_acquire_tryread(l) lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_)
#define lock_map_release(l) lock_release(l, _THIS_IP_)
diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h
index d224308..59f4fb1 100644
--- a/include/linux/lockdep_types.h
+++ b/include/linux/lockdep_types.h
@@ -33,6 +33,7 @@
enum lockdep_lock_type {
LD_LOCK_NORMAL = 0, /* normal, catch all */
LD_LOCK_PERCPU, /* percpu */
+ LD_LOCK_WAIT_OVERRIDE, /* annotation */
LD_LOCK_MAX,
};
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index dcd1d5b..4dfd2f3 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -2263,6 +2263,9 @@
static inline bool usage_skip(struct lock_list *entry, void *mask)
{
+ if (entry->class->lock_type == LD_LOCK_NORMAL)
+ return false;
+
/*
* Skip local_lock() for irq inversion detection.
*
@@ -2289,14 +2292,16 @@
* As a result, we will skip local_lock(), when we search for irq
* inversion bugs.
*/
- if (entry->class->lock_type == LD_LOCK_PERCPU) {
- if (DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG))
- return false;
+ if (entry->class->lock_type == LD_LOCK_PERCPU &&
+ DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG))
+ return false;
- return true;
- }
+ /*
+ * Skip WAIT_OVERRIDE for irq inversion detection -- it's not actually
+ * a lock and only used to override the wait_type.
+ */
- return false;
+ return true;
}
/*
@@ -4768,7 +4773,8 @@
for (; depth < curr->lockdep_depth; depth++) {
struct held_lock *prev = curr->held_locks + depth;
- u8 prev_inner = hlock_class(prev)->wait_type_inner;
+ struct lock_class *class = hlock_class(prev);
+ u8 prev_inner = class->wait_type_inner;
if (prev_inner) {
/*
@@ -4778,6 +4784,14 @@
* Also due to trylocks.
*/
curr_inner = min(curr_inner, prev_inner);
+
+ /*
+ * Allow override for annotations -- this is typically
+ * only valid/needed for code that only exists when
+ * CONFIG_PREEMPT_RT=n.
+ */
+ if (unlikely(class->lock_type == LD_LOCK_WAIT_OVERRIDE))
+ curr_inner = prev_inner;
}
}
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 003edc5..984985c 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -126,7 +126,7 @@
static void fill_pool(void)
{
- gfp_t gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN;
+ gfp_t gfp = __GFP_HIGH | __GFP_NOWARN;
struct debug_obj *obj;
unsigned long flags;
@@ -591,10 +591,21 @@
{
/*
* On RT enabled kernels the pool refill must happen in preemptible
- * context:
+ * context -- 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) || preemptible())
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) {
+ /*
+ * Annotate away the spinlock_t inside raw_spinlock_t warning
+ * by temporarily raising the wait-type to WAIT_SLEEP, matching
+ * the preemptible() condition above.
+ */
+ static DEFINE_WAIT_OVERRIDE_MAP(fill_pool_map, LD_WAIT_SLEEP);
+ lock_map_acquire_try(&fill_pool_map);
fill_pool();
+ lock_map_release(&fill_pool_map);
+ }
}
static void
