locking/lockdep: Rework FS_RECLAIM annotation

A while ago someone, and I cannot find the email just now, asked if we
could not implement the RECLAIM_FS inversion stuff with a 'fake' lock
like we use for other things like workqueues etc. I think this should
be possible which allows reducing the 'irq' states and will reduce the
amount of __bfs() lookups we do.

Removing the 1 IRQ state results in 4 less __bfs() walks per
dependency, improving lockdep performance. And by moving this
annotation out of the lockdep code it becomes easier for the mm people
to extend.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Byungchul Park <byungchul.park@lge.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Nikolay Borisov <nborisov@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: akpm@linux-foundation.org
Cc: boqun.feng@gmail.com
Cc: iamjoonsoo.kim@lge.com
Cc: kernel-team@lge.com
Cc: kirill@shutemov.name
Cc: npiggin@gmail.com
Cc: walken@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

drivers/gpu/drm/i915/i915_debugfs.c

@@ -28,6 +28,7 @@
 
 #include <linux/debugfs.h>
 #include <linux/sort.h>
+#include <linux/sched/mm.h>
 #include "intel_drv.h"
 
 static inline struct drm_i915_private *node_to_i915(struct drm_info_node *node)
@@ -4331,7 +4332,7 @@ i915_drop_caches_set(void *data, u64 val)
 		mutex_unlock(&dev->struct_mutex);
 	}
 
-	lockdep_set_current_reclaim_state(GFP_KERNEL);
+	fs_reclaim_acquire(GFP_KERNEL);
 	if (val & DROP_BOUND)
 		i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_BOUND);
 
@@ -4340,7 +4341,7 @@ i915_drop_caches_set(void *data, u64 val)
 
 	if (val & DROP_SHRINK_ALL)
 		i915_gem_shrink_all(dev_priv);
-	lockdep_clear_current_reclaim_state();
+	fs_reclaim_release(GFP_KERNEL);
 
 	if (val & DROP_FREED) {
 		synchronize_rcu();

include/linux/lockdep.h

@@ -29,7 +29,7 @@ extern int lock_stat;
  * We'd rather not expose kernel/lockdep_states.h this wide, but we do need
  * the total number of states... :-(
  */
-#define XXX_LOCK_USAGE_STATES		(1+3*4)
+#define XXX_LOCK_USAGE_STATES		(1+2*4)
 
 /*
  * NR_LOCKDEP_CACHING_CLASSES ... Number of classes
@@ -363,10 +363,6 @@ static inline void lock_set_subclass(struct lockdep_map *lock,
 
 extern void lock_downgrade(struct lockdep_map *lock, unsigned long ip);
 
-extern void lockdep_set_current_reclaim_state(gfp_t gfp_mask);
-extern void lockdep_clear_current_reclaim_state(void);
-extern void lockdep_trace_alloc(gfp_t mask);
-
 struct pin_cookie { unsigned int val; };
 
 #define NIL_COOKIE (struct pin_cookie){ .val = 0U, }
@@ -375,7 +371,7 @@ extern struct pin_cookie lock_pin_lock(struct lockdep_map *lock);
 extern void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie);
 extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie);
 
-# define INIT_LOCKDEP				.lockdep_recursion = 0, .lockdep_reclaim_gfp = 0,
+# define INIT_LOCKDEP				.lockdep_recursion = 0,
 
 #define lockdep_depth(tsk)	(debug_locks ? (tsk)->lockdep_depth : 0)
 
@@ -416,9 +412,6 @@ static inline void lockdep_on(void)
 # define lock_downgrade(l, i)			do { } while (0)
 # define lock_set_class(l, n, k, s, i)		do { } while (0)
 # define lock_set_subclass(l, s, i)		do { } while (0)
-# define lockdep_set_current_reclaim_state(g)	do { } while (0)
-# define lockdep_clear_current_reclaim_state()	do { } while (0)
-# define lockdep_trace_alloc(g)			do { } while (0)
 # define lockdep_info()				do { } while (0)
 # define lockdep_init_map(lock, name, key, sub) \
 		do { (void)(name); (void)(key); } while (0)

include/linux/sched.h

@@ -846,7 +846,6 @@ struct task_struct {
 	int				lockdep_depth;
 	unsigned int			lockdep_recursion;
 	struct held_lock		held_locks[MAX_LOCK_DEPTH];
-	gfp_t				lockdep_reclaim_gfp;
 #endif
 
 #ifdef CONFIG_UBSAN

include/linux/sched/mm.h

@@ -167,6 +167,14 @@ static inline gfp_t current_gfp_context(gfp_t flags)
 	return flags;
 }
 
+#ifdef CONFIG_LOCKDEP
+extern void fs_reclaim_acquire(gfp_t gfp_mask);
+extern void fs_reclaim_release(gfp_t gfp_mask);
+#else
+static inline void fs_reclaim_acquire(gfp_t gfp_mask) { }
+static inline void fs_reclaim_release(gfp_t gfp_mask) { }
+#endif
+
 static inline unsigned int memalloc_noio_save(void)
 {
 	unsigned int flags = current->flags & PF_MEMALLOC_NOIO;

kernel/locking/lockdep.c

@@ -344,14 +344,12 @@ EXPORT_SYMBOL(lockdep_on);
 #if VERBOSE
 # define HARDIRQ_VERBOSE	1
 # define SOFTIRQ_VERBOSE	1
-# define RECLAIM_VERBOSE	1
 #else
 # define HARDIRQ_VERBOSE	0
 # define SOFTIRQ_VERBOSE	0
-# define RECLAIM_VERBOSE	0
 #endif
 
-#if VERBOSE || HARDIRQ_VERBOSE || SOFTIRQ_VERBOSE || RECLAIM_VERBOSE
+#if VERBOSE || HARDIRQ_VERBOSE || SOFTIRQ_VERBOSE
 /*
  * Quick filtering for interesting events:
  */
@@ -2567,14 +2565,6 @@ static int SOFTIRQ_verbose(struct lock_class *class)
 	return 0;
 }
 
-static int RECLAIM_FS_verbose(struct lock_class *class)
-{
-#if RECLAIM_VERBOSE
-	return class_filter(class);
-#endif
-	return 0;
-}
-
 #define STRICT_READ_CHECKS	1
 
 static int (*state_verbose_f[])(struct lock_class *class) = {
@@ -2870,57 +2860,6 @@ void trace_softirqs_off(unsigned long ip)
 		debug_atomic_inc(redundant_softirqs_off);
 }
 
-static void __lockdep_trace_alloc(gfp_t gfp_mask, unsigned long flags)
-{
-	struct task_struct *curr = current;
-
-	if (unlikely(!debug_locks))
-		return;
-
-	gfp_mask = current_gfp_context(gfp_mask);
-
-	/* no reclaim without waiting on it */
-	if (!(gfp_mask & __GFP_DIRECT_RECLAIM))
-		return;
-
-	/* this guy won't enter reclaim */
-	if ((curr->flags & PF_MEMALLOC) && !(gfp_mask & __GFP_NOMEMALLOC))
-		return;
-
-	/* We're only interested __GFP_FS allocations for now */
-	if (!(gfp_mask & __GFP_FS) || (curr->flags & PF_MEMALLOC_NOFS))
-		return;
-
-	/*
-	 * Oi! Can't be having __GFP_FS allocations with IRQs disabled.
-	 */
-	if (DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags)))
-		return;
-
-	/* Disable lockdep if explicitly requested */
-	if (gfp_mask & __GFP_NOLOCKDEP)
-		return;
-
-	mark_held_locks(curr, RECLAIM_FS);
-}
-
-static void check_flags(unsigned long flags);
-
-void lockdep_trace_alloc(gfp_t gfp_mask)
-{
-	unsigned long flags;
-
-	if (unlikely(current->lockdep_recursion))
-		return;
-
-	raw_local_irq_save(flags);
-	check_flags(flags);
-	current->lockdep_recursion = 1;
-	__lockdep_trace_alloc(gfp_mask, flags);
-	current->lockdep_recursion = 0;
-	raw_local_irq_restore(flags);
-}
-
 static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock)
 {
 	/*
@@ -2966,22 +2905,6 @@ static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock)
 		}
 	}
 
-	/*
-	 * We reuse the irq context infrastructure more broadly as a general
-	 * context checking code. This tests GFP_FS recursion (a lock taken
-	 * during reclaim for a GFP_FS allocation is held over a GFP_FS
-	 * allocation).
-	 */
-	if (!hlock->trylock && (curr->lockdep_reclaim_gfp & __GFP_FS)) {
-		if (hlock->read) {
-			if (!mark_lock(curr, hlock, LOCK_USED_IN_RECLAIM_FS_READ))
-					return 0;
-		} else {
-			if (!mark_lock(curr, hlock, LOCK_USED_IN_RECLAIM_FS))
-					return 0;
-		}
-	}
-
 	return 1;
 }
 
@@ -3040,10 +2963,6 @@ static inline int separate_irq_context(struct task_struct *curr,
 	return 0;
 }
 
-void lockdep_trace_alloc(gfp_t gfp_mask)
-{
-}
-
 #endif /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */
 
 /*
@@ -3952,18 +3871,6 @@ void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie)
 }
 EXPORT_SYMBOL_GPL(lock_unpin_lock);
 
-void lockdep_set_current_reclaim_state(gfp_t gfp_mask)
-{
-	current->lockdep_reclaim_gfp = current_gfp_context(gfp_mask);
-}
-EXPORT_SYMBOL_GPL(lockdep_set_current_reclaim_state);
-
-void lockdep_clear_current_reclaim_state(void)
-{
-	current->lockdep_reclaim_gfp = 0;
-}
-EXPORT_SYMBOL_GPL(lockdep_clear_current_reclaim_state);
-
 #ifdef CONFIG_LOCK_STAT
 static int
 print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock,

kernel/locking/lockdep_states.h

@@ -6,4 +6,3 @@
  */
 LOCKDEP_STATE(HARDIRQ)
 LOCKDEP_STATE(SOFTIRQ)
-LOCKDEP_STATE(RECLAIM_FS)

mm/page_alloc.c

@@ -66,6 +66,7 @@
 #include <linux/kthread.h>
 #include <linux/memcontrol.h>
 #include <linux/ftrace.h>
+#include <linux/lockdep.h>
 
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -3490,6 +3491,47 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla
 }
 #endif /* CONFIG_COMPACTION */
 
+#ifdef CONFIG_LOCKDEP
+struct lockdep_map __fs_reclaim_map =
+	STATIC_LOCKDEP_MAP_INIT("fs_reclaim", &__fs_reclaim_map);
+
+static bool __need_fs_reclaim(gfp_t gfp_mask)
+{
+	gfp_mask = current_gfp_context(gfp_mask);
+
+	/* no reclaim without waiting on it */
+	if (!(gfp_mask & __GFP_DIRECT_RECLAIM))
+		return false;
+
+	/* this guy won't enter reclaim */
+	if ((current->flags & PF_MEMALLOC) && !(gfp_mask & __GFP_NOMEMALLOC))
+		return false;
+
+	/* We're only interested __GFP_FS allocations for now */
+	if (!(gfp_mask & __GFP_FS))
+		return false;
+
+	if (gfp_mask & __GFP_NOLOCKDEP)
+		return false;
+
+	return true;
+}
+
+void fs_reclaim_acquire(gfp_t gfp_mask)
+{
+	if (__need_fs_reclaim(gfp_mask))
+		lock_map_acquire(&__fs_reclaim_map);
+}
+EXPORT_SYMBOL_GPL(fs_reclaim_acquire);
+
+void fs_reclaim_release(gfp_t gfp_mask)
+{
+	if (__need_fs_reclaim(gfp_mask))
+		lock_map_release(&__fs_reclaim_map);
+}
+EXPORT_SYMBOL_GPL(fs_reclaim_release);
+#endif
+
 /* Perform direct synchronous page reclaim */
 static int
 __perform_reclaim(gfp_t gfp_mask, unsigned int order,
@@ -3504,7 +3546,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
 	/* We now go into synchronous reclaim */
 	cpuset_memory_pressure_bump();
 	noreclaim_flag = memalloc_noreclaim_save();
-	lockdep_set_current_reclaim_state(gfp_mask);
+	fs_reclaim_acquire(gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
 	current->reclaim_state = &reclaim_state;
 
@@ -3512,7 +3554,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
 								ac->nodemask);
 
 	current->reclaim_state = NULL;
-	lockdep_clear_current_reclaim_state();
+	fs_reclaim_release(gfp_mask);
 	memalloc_noreclaim_restore(noreclaim_flag);
 
 	cond_resched();
@@ -4041,7 +4083,8 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
 			*alloc_flags |= ALLOC_CPUSET;
 	}
 
-	lockdep_trace_alloc(gfp_mask);
+	fs_reclaim_acquire(gfp_mask);
+	fs_reclaim_release(gfp_mask);
 
 	might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
 

mm/slab.h

@@ -43,6 +43,7 @@ struct kmem_cache {
 #include <linux/kasan.h>
 #include <linux/kmemleak.h>
 #include <linux/random.h>
+#include <linux/sched/mm.h>
 
 /*
  * State of the slab allocator.
@@ -412,7 +413,10 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
 						     gfp_t flags)
 {
 	flags &= gfp_allowed_mask;
-	lockdep_trace_alloc(flags);
+
+	fs_reclaim_acquire(flags);
+	fs_reclaim_release(flags);
+
 	might_sleep_if(gfpflags_allow_blocking(flags));
 
 	if (should_failslab(s, flags))

mm/slob.c

@@ -432,7 +432,8 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 
 	gfp &= gfp_allowed_mask;
 
-	lockdep_trace_alloc(gfp);
+	fs_reclaim_acquire(gfp);
+	fs_reclaim_release(gfp);
 
 	if (size < PAGE_SIZE - align) {
 		if (!size)
@@ -538,7 +539,8 @@ static void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
 
 	flags &= gfp_allowed_mask;
 
-	lockdep_trace_alloc(flags);
+	fs_reclaim_acquire(flags);
+	fs_reclaim_release(flags);
 
 	if (c->size < PAGE_SIZE) {
 		b = slob_alloc(c->size, flags, c->align, node);

mm/vmscan.c

@@ -3525,8 +3525,6 @@ static int kswapd(void *p)
 	};
 	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 
-	lockdep_set_current_reclaim_state(GFP_KERNEL);
-
 	if (!cpumask_empty(cpumask))
 		set_cpus_allowed_ptr(tsk, cpumask);
 	current->reclaim_state = &reclaim_state;
@@ -3585,14 +3583,15 @@ static int kswapd(void *p)
 		 */
 		trace_mm_vmscan_kswapd_wake(pgdat->node_id, classzone_idx,
 						alloc_order);
+		fs_reclaim_acquire(GFP_KERNEL);
 		reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
+		fs_reclaim_release(GFP_KERNEL);
 		if (reclaim_order < alloc_order)
 			goto kswapd_try_sleep;
 	}
 
 	tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
 	current->reclaim_state = NULL;
-	lockdep_clear_current_reclaim_state();
 
 	return 0;
 }
@@ -3655,14 +3654,14 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 	unsigned int noreclaim_flag;
 
 	noreclaim_flag = memalloc_noreclaim_save();
-	lockdep_set_current_reclaim_state(sc.gfp_mask);
+	fs_reclaim_acquire(sc.gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
 	p->reclaim_state = NULL;
-	lockdep_clear_current_reclaim_state();
+	fs_reclaim_release(sc.gfp_mask);
 	memalloc_noreclaim_restore(noreclaim_flag);
 
 	return nr_reclaimed;
@@ -3847,7 +3846,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	 */
 	noreclaim_flag = memalloc_noreclaim_save();
 	p->flags |= PF_SWAPWRITE;
-	lockdep_set_current_reclaim_state(sc.gfp_mask);
+	fs_reclaim_acquire(sc.gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
@@ -3862,9 +3861,9 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	}
 
 	p->reclaim_state = NULL;
+	fs_reclaim_release(gfp_mask);
 	current->flags &= ~PF_SWAPWRITE;
 	memalloc_noreclaim_restore(noreclaim_flag);
-	lockdep_clear_current_reclaim_state();
 	return sc.nr_reclaimed >= nr_pages;
 }