Merge tag 'locking-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Thomas Gleixner:

 - Move futex code into kernel/futex/ and split up the kitchen sink into
   seperate files to make integration of sys_futex_waitv() simpler.

 - Add a new sys_futex_waitv() syscall which allows to wait on multiple
   futexes.

   The main use case is emulating Windows' WaitForMultipleObjects which
   allows Wine to improve the performance of Windows Games. Also native
   Linux games can benefit from this interface as this is a common wait
   pattern for this kind of applications.

 - Add context to ww_mutex_trylock() to provide a path for i915 to
   rework their eviction code step by step without making lockdep upset
   until the final steps of rework are completed. It's also useful for
   regulator and TTM to avoid dropping locks in the non contended path.

 - Lockdep and might_sleep() cleanups and improvements

 - A few improvements for the RT substitutions.

 - The usual small improvements and cleanups.

* tag 'locking-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits)
  locking: Remove spin_lock_flags() etc
  locking/rwsem: Fix comments about reader optimistic lock stealing conditions
  locking: Remove rcu_read_{,un}lock() for preempt_{dis,en}able()
  locking/rwsem: Disable preemption for spinning region
  docs: futex: Fix kernel-doc references
  futex: Fix PREEMPT_RT build
  futex2: Documentation: Document sys_futex_waitv() uAPI
  selftests: futex: Test sys_futex_waitv() wouldblock
  selftests: futex: Test sys_futex_waitv() timeout
  selftests: futex: Add sys_futex_waitv() test
  futex,arm: Wire up sys_futex_waitv()
  futex,x86: Wire up sys_futex_waitv()
  futex: Implement sys_futex_waitv()
  futex: Simplify double_lock_hb()
  futex: Split out wait/wake
  futex: Split out requeue
  futex: Rename mark_wake_futex()
  futex: Rename: match_futex()
  futex: Rename: hb_waiter_{inc,dec,pending}()
  futex: Split out PI futex
  ...

1 files changed, 43 insertions, 24 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 59bea523c84b..bc0e242e434c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9470,14 +9470,8 @@ void __init sched_init(void)
 }
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
-static inline int preempt_count_equals(int preempt_offset)
-{
-	int nested = preempt_count() + rcu_preempt_depth();
-
-	return (nested == preempt_offset);
-}
 
-void __might_sleep(const char *file, int line, int preempt_offset)
+void __might_sleep(const char *file, int line)
 {
 	unsigned int state = get_current_state();
 	/*
@@ -9491,11 +9485,32 @@ void __might_sleep(const char *file, int line, int preempt_offset)
 			(void *)current->task_state_change,
 			(void *)current->task_state_change);
 
-	___might_sleep(file, line, preempt_offset);
+	__might_resched(file, line, 0);
 }
 EXPORT_SYMBOL(__might_sleep);
 
-void ___might_sleep(const char *file, int line, int preempt_offset)
+static void print_preempt_disable_ip(int preempt_offset, unsigned long ip)
+{
+	if (!IS_ENABLED(CONFIG_DEBUG_PREEMPT))
+		return;
+
+	if (preempt_count() == preempt_offset)
+		return;
+
+	pr_err("Preemption disabled at:");
+	print_ip_sym(KERN_ERR, ip);
+}
+
+static inline bool resched_offsets_ok(unsigned int offsets)
+{
+	unsigned int nested = preempt_count();
+
+	nested += rcu_preempt_depth() << MIGHT_RESCHED_RCU_SHIFT;
+
+	return nested == offsets;
+}
+
+void __might_resched(const char *file, int line, unsigned int offsets)
 {
 	/* Ratelimiting timestamp: */
 	static unsigned long prev_jiffy;
@@ -9505,7 +9520,7 @@ void ___might_sleep(const char *file, int line, int preempt_offset)
 	/* WARN_ON_ONCE() by default, no rate limit required: */
 	rcu_sleep_check();
 
-	if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
+	if ((resched_offsets_ok(offsets) && !irqs_disabled() &&
 	     !is_idle_task(current) && !current->non_block_count) ||
 	    system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING ||
 	    oops_in_progress)
@@ -9518,29 +9533,33 @@ void ___might_sleep(const char *file, int line, int preempt_offset)
 	/* Save this before calling printk(), since that will clobber it: */
 	preempt_disable_ip = get_preempt_disable_ip(current);
 
-	printk(KERN_ERR
-		"BUG: sleeping function called from invalid context at %s:%d\n",
-			file, line);
-	printk(KERN_ERR
-		"in_atomic(): %d, irqs_disabled(): %d, non_block: %d, pid: %d, name: %s\n",
-			in_atomic(), irqs_disabled(), current->non_block_count,
-			current->pid, current->comm);
+	pr_err("BUG: sleeping function called from invalid context at %s:%d\n",
+	       file, line);
+	pr_err("in_atomic(): %d, irqs_disabled(): %d, non_block: %d, pid: %d, name: %s\n",
+	       in_atomic(), irqs_disabled(), current->non_block_count,
+	       current->pid, current->comm);
+	pr_err("preempt_count: %x, expected: %x\n", preempt_count(),
+	       offsets & MIGHT_RESCHED_PREEMPT_MASK);
+
+	if (IS_ENABLED(CONFIG_PREEMPT_RCU)) {
+		pr_err("RCU nest depth: %d, expected: %u\n",
+		       rcu_preempt_depth(), offsets >> MIGHT_RESCHED_RCU_SHIFT);
+	}
 
 	if (task_stack_end_corrupted(current))
-		printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
+		pr_emerg("Thread overran stack, or stack corrupted\n");
 
 	debug_show_held_locks(current);
 	if (irqs_disabled())
 		print_irqtrace_events(current);
-	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
-	    && !preempt_count_equals(preempt_offset)) {
-		pr_err("Preemption disabled at:");
-		print_ip_sym(KERN_ERR, preempt_disable_ip);
-	}
+
+	print_preempt_disable_ip(offsets & MIGHT_RESCHED_PREEMPT_MASK,
+				 preempt_disable_ip);
+
 	dump_stack();
 	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
 }
-EXPORT_SYMBOL(___might_sleep);
+EXPORT_SYMBOL(__might_resched);
 
 void __cant_sleep(const char *file, int line, int preempt_offset)
 {