Merge tag 'sched-rt-2022-10-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull preempt RT updates from Thomas Gleixner:
 "Introduce preempt_[dis|enable_nested() and use it to clean up various
  places which have open coded PREEMPT_RT conditionals.

  On PREEMPT_RT enabled kernels, spinlocks and rwlocks are neither
  disabling preemption nor interrupts. Though there are a few places
  which depend on the implicit preemption/interrupt disable of those
  locks, e.g. seqcount write sections, per CPU statistics updates etc.

  PREEMPT_RT added open coded CONFIG_PREEMPT_RT conditionals to
  disable/enable preemption in the related code parts all over the
  place. That's hard to read and does not really explain why this is
  necessary.

  Linus suggested to use helper functions (preempt_disable_nested() and
  preempt_enable_nested()) and use those in the affected places. On !RT
  enabled kernels these functions are NOPs, but contain a lockdep assert
  to validate that preemption is actually disabled to catch call sites
  which do not have preemption disabled.

  Clean up the affected code paths in mm, dentry and lib"

* tag 'sched-rt-2022-10-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  u64_stats: Streamline the implementation
  flex_proportions: Disable preemption entering the write section.
  mm/compaction: Get rid of RT ifdeffery
  mm/memcontrol: Replace the PREEMPT_RT conditionals
  mm/debug: Provide VM_WARN_ON_IRQS_ENABLED()
  mm/vmstat: Use preempt_[dis|en]able_nested()
  dentry: Use preempt_[dis|en]able_nested()
  preempt: Provide preempt_[dis|en]able_nested()

4 files changed, 25 insertions, 42 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 0331f1461f81..3897e924e40f 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -579,6 +579,12 @@ config COMPACTION
 	  it and then we would be really interested to hear about that at
 	  linux-mm@kvack.org.
 
+config COMPACT_UNEVICTABLE_DEFAULT
+	int
+	depends on COMPACTION
+	default 0 if PREEMPT_RT
+	default 1
+
 #
 # support for free page reporting
 config PAGE_REPORTING
diff --git a/mm/compaction.c b/mm/compaction.c
index 640fa76228dd..10561cb1aaad 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1727,11 +1727,7 @@ typedef enum {
  * Allow userspace to control policy on scanning the unevictable LRU for
  * compactable pages.
  */
-#ifdef CONFIG_PREEMPT_RT
-int sysctl_compact_unevictable_allowed __read_mostly = 0;
-#else
-int sysctl_compact_unevictable_allowed __read_mostly = 1;
-#endif
+int sysctl_compact_unevictable_allowed __read_mostly = CONFIG_COMPACT_UNEVICTABLE_DEFAULT;
 
 static inline void
 update_fast_start_pfn(struct compact_control *cc, unsigned long pfn)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9d054e3767ce..cf405510cd17 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -597,25 +597,18 @@ static u64 flush_next_time;
  */
 static void memcg_stats_lock(void)
 {
-#ifdef CONFIG_PREEMPT_RT
-      preempt_disable();
-#else
-      VM_BUG_ON(!irqs_disabled());
-#endif
+	preempt_disable_nested();
+	VM_WARN_ON_IRQS_ENABLED();
 }
 
 static void __memcg_stats_lock(void)
 {
-#ifdef CONFIG_PREEMPT_RT
-      preempt_disable();
-#endif
+	preempt_disable_nested();
 }
 
 static void memcg_stats_unlock(void)
 {
-#ifdef CONFIG_PREEMPT_RT
-      preempt_enable();
-#endif
+	preempt_enable_nested();
 }
 
 static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
@@ -715,7 +708,7 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	 * interrupt context while other caller need to have disabled interrupt.
 	 */
 	__memcg_stats_lock();
-	if (IS_ENABLED(CONFIG_DEBUG_VM) && !IS_ENABLED(CONFIG_PREEMPT_RT)) {
+	if (IS_ENABLED(CONFIG_DEBUG_VM)) {
 		switch (idx) {
 		case NR_ANON_MAPPED:
 		case NR_FILE_MAPPED:
@@ -725,7 +718,7 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			WARN_ON_ONCE(!in_task());
 			break;
 		default:
-			WARN_ON_ONCE(!irqs_disabled());
+			VM_WARN_ON_IRQS_ENABLED();
 		}
 	}
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index da264a040c55..30686e6b4145 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -355,8 +355,7 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
 	 * CPU migrations and preemption potentially corrupts a counter so
 	 * disable preemption.
 	 */
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		preempt_disable();
+	preempt_disable_nested();
 
 	x = delta + __this_cpu_read(*p);
 
@@ -368,8 +367,7 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
 	}
 	__this_cpu_write(*p, x);
 
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		preempt_enable();
+	preempt_enable_nested();
 }
 EXPORT_SYMBOL(__mod_zone_page_state);
 
@@ -393,8 +391,7 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
 	}
 
 	/* See __mod_node_page_state */
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		preempt_disable();
+	preempt_disable_nested();
 
 	x = delta + __this_cpu_read(*p);
 
@@ -406,8 +403,7 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
 	}
 	__this_cpu_write(*p, x);
 
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		preempt_enable();
+	preempt_enable_nested();
 }
 EXPORT_SYMBOL(__mod_node_page_state);
 
@@ -441,8 +437,7 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
 	s8 v, t;
 
 	/* See __mod_node_page_state */
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		preempt_disable();
+	preempt_disable_nested();
 
 	v = __this_cpu_inc_return(*p);
 	t = __this_cpu_read(pcp->stat_threshold);
@@ -453,8 +448,7 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
 		__this_cpu_write(*p, -overstep);
 	}
 
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		preempt_enable();
+	preempt_enable_nested();
 }
 
 void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
@@ -466,8 +460,7 @@ void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
 	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
 
 	/* See __mod_node_page_state */
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		preempt_disable();
+	preempt_disable_nested();
 
 	v = __this_cpu_inc_return(*p);
 	t = __this_cpu_read(pcp->stat_threshold);
@@ -478,8 +471,7 @@ void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
 		__this_cpu_write(*p, -overstep);
 	}
 
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		preempt_enable();
+	preempt_enable_nested();
 }
 
 void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
@@ -501,8 +493,7 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
 	s8 v, t;
 
 	/* See __mod_node_page_state */
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		preempt_disable();
+	preempt_disable_nested();
 
 	v = __this_cpu_dec_return(*p);
 	t = __this_cpu_read(pcp->stat_threshold);
@@ -513,8 +504,7 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
 		__this_cpu_write(*p, overstep);
 	}
 
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		preempt_enable();
+	preempt_enable_nested();
 }
 
 void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
@@ -526,8 +516,7 @@ void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
 	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
 
 	/* See __mod_node_page_state */
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		preempt_disable();
+	preempt_disable_nested();
 
 	v = __this_cpu_dec_return(*p);
 	t = __this_cpu_read(pcp->stat_threshold);
@@ -538,8 +527,7 @@ void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
 		__this_cpu_write(*p, overstep);
 	}
 
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		preempt_enable();
+	preempt_enable_nested();
 }
 
 void __dec_zone_page_state(struct page *page, enum zone_stat_item item)