Merge branch 'core/rcu' into sched/core, to pick up dependency

We are going to rely on the loosening of RCU callback semantics,
introduced by this commit:

  806f04e9fd: ("rcu: Allow for smp_call_function() running callbacks from idle")

Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/compiler.h

@@ -120,12 +120,65 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 /* Annotate a C jump table to allow objtool to follow the code flow */
 #define __annotate_jump_table __section(.rodata..c_jump_table)
 
+#ifdef CONFIG_DEBUG_ENTRY
+/* Begin/end of an instrumentation safe region */
+#define instrumentation_begin() ({					\
+	asm volatile("%c0:\n\t"						\
+		     ".pushsection .discard.instr_begin\n\t"		\
+		     ".long %c0b - .\n\t"				\
+		     ".popsection\n\t" : : "i" (__COUNTER__));		\
+})
+
+/*
+ * Because instrumentation_{begin,end}() can nest, objtool validation considers
+ * _begin() a +1 and _end() a -1 and computes a sum over the instructions.
+ * When the value is greater than 0, we consider instrumentation allowed.
+ *
+ * There is a problem with code like:
+ *
+ * noinstr void foo()
+ * {
+ *	instrumentation_begin();
+ *	...
+ *	if (cond) {
+ *		instrumentation_begin();
+ *		...
+ *		instrumentation_end();
+ *	}
+ *	bar();
+ *	instrumentation_end();
+ * }
+ *
+ * If instrumentation_end() would be an empty label, like all the other
+ * annotations, the inner _end(), which is at the end of a conditional block,
+ * would land on the instruction after the block.
+ *
+ * If we then consider the sum of the !cond path, we'll see that the call to
+ * bar() is with a 0-value, even though, we meant it to happen with a positive
+ * value.
+ *
+ * To avoid this, have _end() be a NOP instruction, this ensures it will be
+ * part of the condition block and does not escape.
+ */
+#define instrumentation_end() ({					\
+	asm volatile("%c0: nop\n\t"					\
+		     ".pushsection .discard.instr_end\n\t"		\
+		     ".long %c0b - .\n\t"				\
+		     ".popsection\n\t" : : "i" (__COUNTER__));		\
+})
+#endif /* CONFIG_DEBUG_ENTRY */
+
 #else
 #define annotate_reachable()
 #define annotate_unreachable()
 #define __annotate_jump_table
 #endif
 
+#ifndef instrumentation_begin
+#define instrumentation_begin()		do { } while(0)
+#define instrumentation_end()		do { } while(0)
+#endif
+
 #ifndef ASM_UNREACHABLE
 # define ASM_UNREACHABLE
 #endif

include/linux/compiler_types.h

@@ -118,6 +118,10 @@ struct ftrace_likely_data {
 #define notrace			__attribute__((__no_instrument_function__))
 #endif
 
+/* Section for code which can't be instrumented at all */
+#define noinstr								\
+	noinline notrace __attribute((__section__(".noinstr.text")))
+
 /*
  * it doesn't make sense on ARM (currently the only user of __naked)
  * to trace naked functions because then mcount is called without

include/linux/ftrace_irq.h

@@ -2,15 +2,6 @@
 #ifndef _LINUX_FTRACE_IRQ_H
 #define _LINUX_FTRACE_IRQ_H
 
-
-#ifdef CONFIG_FTRACE_NMI_ENTER
-extern void arch_ftrace_nmi_enter(void);
-extern void arch_ftrace_nmi_exit(void);
-#else
-static inline void arch_ftrace_nmi_enter(void) { }
-static inline void arch_ftrace_nmi_exit(void) { }
-#endif
-
 #ifdef CONFIG_HWLAT_TRACER
 extern bool trace_hwlat_callback_enabled;
 extern void trace_hwlat_callback(bool enter);
@@ -22,12 +13,10 @@ static inline void ftrace_nmi_enter(void)
 	if (trace_hwlat_callback_enabled)
 		trace_hwlat_callback(true);
 #endif
-	arch_ftrace_nmi_enter();
 }
 
 static inline void ftrace_nmi_exit(void)
 {
-	arch_ftrace_nmi_exit();
 #ifdef CONFIG_HWLAT_TRACER
 	if (trace_hwlat_callback_enabled)
 		trace_hwlat_callback(false);

include/linux/hardirq.h

@@ -65,14 +65,26 @@ extern void irq_exit(void);
 #define arch_nmi_exit()		do { } while (0)
 #endif
 
+/*
+ * NMI vs Tracing
+ * --------------
+ *
+ * We must not land in a tracer until (or after) we've changed preempt_count
+ * such that in_nmi() becomes true. To that effect all NMI C entry points must
+ * be marked 'notrace' and call nmi_enter() as soon as possible.
+ */
+
+/*
+ * nmi_enter() can nest up to 15 times; see NMI_BITS.
+ */
 #define nmi_enter()						\
 	do {							\
 		arch_nmi_enter();				\
 		printk_nmi_enter();				\
 		lockdep_off();					\
 		ftrace_nmi_enter();				\
-		BUG_ON(in_nmi());				\
-		preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		BUG_ON(in_nmi() == NMI_MASK);			\
+		__preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET);	\
 		rcu_nmi_enter();				\
 		lockdep_hardirq_enter();			\
 	} while (0)
@@ -82,7 +94,7 @@ extern void irq_exit(void);
 		lockdep_hardirq_exit();				\
 		rcu_nmi_exit();					\
 		BUG_ON(!in_nmi());				\
-		preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		__preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET);	\
 		ftrace_nmi_exit();				\
 		lockdep_on();					\
 		printk_nmi_exit();				\

include/linux/lockdep.h

@@ -308,8 +308,27 @@ extern void lockdep_set_selftest_task(struct task_struct *task);
 
 extern void lockdep_init_task(struct task_struct *task);
 
-extern void lockdep_off(void);
-extern void lockdep_on(void);
+/*
+ * Split the recrursion counter in two to readily detect 'off' vs recursion.
+ */
+#define LOCKDEP_RECURSION_BITS	16
+#define LOCKDEP_OFF		(1U << LOCKDEP_RECURSION_BITS)
+#define LOCKDEP_RECURSION_MASK	(LOCKDEP_OFF - 1)
+
+/*
+ * lockdep_{off,on}() are macros to avoid tracing and kprobes; not inlines due
+ * to header dependencies.
+ */
+
+#define lockdep_off()					\
+do {							\
+	current->lockdep_recursion += LOCKDEP_OFF;	\
+} while (0)
+
+#define lockdep_on()					\
+do {							\
+	current->lockdep_recursion -= LOCKDEP_OFF;	\
+} while (0)
 
 extern void lockdep_register_key(struct lock_class_key *key);
 extern void lockdep_unregister_key(struct lock_class_key *key);

include/linux/preempt.h

@@ -26,13 +26,13 @@
  *         PREEMPT_MASK:	0x000000ff
  *         SOFTIRQ_MASK:	0x0000ff00
  *         HARDIRQ_MASK:	0x000f0000
- *             NMI_MASK:	0x00100000
+ *             NMI_MASK:	0x00f00000
  * PREEMPT_NEED_RESCHED:	0x80000000
  */
 #define PREEMPT_BITS	8
 #define SOFTIRQ_BITS	8
 #define HARDIRQ_BITS	4
-#define NMI_BITS	1
+#define NMI_BITS	4
 
 #define PREEMPT_SHIFT	0
 #define SOFTIRQ_SHIFT	(PREEMPT_SHIFT + PREEMPT_BITS)

include/linux/rculist.h

@@ -371,7 +371,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
  * @member:	the name of the list_head within the struct.
- * @cond...:	optional lockdep expression if called from non-RCU protection.
+ * @cond:	optional lockdep expression if called from non-RCU protection.
  *
  * This list-traversal primitive may safely run concurrently with
  * the _rcu list-mutation primitives such as list_add_rcu()
@@ -646,7 +646,7 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n,
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
  * @member:	the name of the hlist_node within the struct.
- * @cond...:	optional lockdep expression if called from non-RCU protection.
+ * @cond:	optional lockdep expression if called from non-RCU protection.
  *
  * This list-traversal primitive may safely run concurrently with
  * the _rcu list-mutation primitives such as hlist_add_head_rcu()

include/linux/rcupdate.h

@@ -37,6 +37,7 @@
 /* Exported common interfaces */
 void call_rcu(struct rcu_head *head, rcu_callback_t func);
 void rcu_barrier_tasks(void);
+void rcu_barrier_tasks_rude(void);
 void synchronize_rcu(void);
 
 #ifdef CONFIG_PREEMPT_RCU
@@ -129,25 +130,57 @@ static inline void rcu_init_nohz(void) { }
  * Note a quasi-voluntary context switch for RCU-tasks's benefit.
  * This is a macro rather than an inline function to avoid #include hell.
  */
-#ifdef CONFIG_TASKS_RCU
-#define rcu_tasks_qs(t) \
-	do { \
-		if (READ_ONCE((t)->rcu_tasks_holdout)) \
-			WRITE_ONCE((t)->rcu_tasks_holdout, false); \
+#ifdef CONFIG_TASKS_RCU_GENERIC
+
+# ifdef CONFIG_TASKS_RCU
+# define rcu_tasks_classic_qs(t, preempt)				\
+	do {								\
+		if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout))	\
+			WRITE_ONCE((t)->rcu_tasks_holdout, false);	\
 	} while (0)
-#define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t)
 void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func);
 void synchronize_rcu_tasks(void);
+# else
+# define rcu_tasks_classic_qs(t, preempt) do { } while (0)
+# define call_rcu_tasks call_rcu
+# define synchronize_rcu_tasks synchronize_rcu
+# endif
+
+# ifdef CONFIG_TASKS_RCU_TRACE
+# define rcu_tasks_trace_qs(t)						\
+	do {								\
+		if (!likely(READ_ONCE((t)->trc_reader_checked)) &&	\
+		    !unlikely(READ_ONCE((t)->trc_reader_nesting))) {	\
+			smp_store_release(&(t)->trc_reader_checked, true); \
+			smp_mb(); /* Readers partitioned by store. */	\
+		}							\
+	} while (0)
+# else
+# define rcu_tasks_trace_qs(t) do { } while (0)
+# endif
+
+#define rcu_tasks_qs(t, preempt)					\
+do {									\
+	rcu_tasks_classic_qs((t), (preempt));				\
+	rcu_tasks_trace_qs((t));					\
+} while (0)
+
+# ifdef CONFIG_TASKS_RUDE_RCU
+void call_rcu_tasks_rude(struct rcu_head *head, rcu_callback_t func);
+void synchronize_rcu_tasks_rude(void);
+# endif
+
+#define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false)
 void exit_tasks_rcu_start(void);
 void exit_tasks_rcu_finish(void);
-#else /* #ifdef CONFIG_TASKS_RCU */
-#define rcu_tasks_qs(t)	do { } while (0)
+#else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
+#define rcu_tasks_qs(t, preempt) do { } while (0)
 #define rcu_note_voluntary_context_switch(t) do { } while (0)
 #define call_rcu_tasks call_rcu
 #define synchronize_rcu_tasks synchronize_rcu
 static inline void exit_tasks_rcu_start(void) { }
 static inline void exit_tasks_rcu_finish(void) { }
-#endif /* #else #ifdef CONFIG_TASKS_RCU */
+#endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
 
 /**
  * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU
@@ -158,7 +191,7 @@ static inline void exit_tasks_rcu_finish(void) { }
  */
 #define cond_resched_tasks_rcu_qs() \
 do { \
-	rcu_tasks_qs(current); \
+	rcu_tasks_qs(current, false); \
 	cond_resched(); \
 } while (0)
 

include/linux/rcupdate_trace.h

@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Read-Copy Update mechanism for mutual exclusion, adapted for tracing.
+ *
+ * Copyright (C) 2020 Paul E. McKenney.
+ */
+
+#ifndef __LINUX_RCUPDATE_TRACE_H
+#define __LINUX_RCUPDATE_TRACE_H
+
+#include <linux/sched.h>
+#include <linux/rcupdate.h>
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+extern struct lockdep_map rcu_trace_lock_map;
+
+static inline int rcu_read_lock_trace_held(void)
+{
+	return lock_is_held(&rcu_trace_lock_map);
+}
+
+#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+static inline int rcu_read_lock_trace_held(void)
+{
+	return 1;
+}
+
+#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+#ifdef CONFIG_TASKS_TRACE_RCU
+
+void rcu_read_unlock_trace_special(struct task_struct *t, int nesting);
+
+/**
+ * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section
+ *
+ * When synchronize_rcu_trace() is invoked by one task, then that task
+ * is guaranteed to block until all other tasks exit their read-side
+ * critical sections.  Similarly, if call_rcu_trace() is invoked on one
+ * task while other tasks are within RCU read-side critical sections,
+ * invocation of the corresponding RCU callback is deferred until after
+ * the all the other tasks exit their critical sections.
+ *
+ * For more details, please see the documentation for rcu_read_lock().
+ */
+static inline void rcu_read_lock_trace(void)
+{
+	struct task_struct *t = current;
+
+	WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1);
+	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) &&
+	    t->trc_reader_special.b.need_mb)
+		smp_mb(); // Pairs with update-side barriers
+	rcu_lock_acquire(&rcu_trace_lock_map);
+}
+
+/**
+ * rcu_read_unlock_trace - mark end of RCU-trace read-side critical section
+ *
+ * Pairs with a preceding call to rcu_read_lock_trace(), and nesting is
+ * allowed.  Invoking a rcu_read_unlock_trace() when there is no matching
+ * rcu_read_lock_trace() is verboten, and will result in lockdep complaints.
+ *
+ * For more details, please see the documentation for rcu_read_unlock().
+ */
+static inline void rcu_read_unlock_trace(void)
+{
+	int nesting;
+	struct task_struct *t = current;
+
+	rcu_lock_release(&rcu_trace_lock_map);
+	nesting = READ_ONCE(t->trc_reader_nesting) - 1;
+	if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) {
+		WRITE_ONCE(t->trc_reader_nesting, nesting);
+		return;  // We assume shallow reader nesting.
+	}
+	rcu_read_unlock_trace_special(t, nesting);
+}
+
+void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func);
+void synchronize_rcu_tasks_trace(void);
+void rcu_barrier_tasks_trace(void);
+
+#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
+
+#endif /* __LINUX_RCUPDATE_TRACE_H */

include/linux/rcupdate_wait.h

@@ -31,4 +31,23 @@ do {									\
 
 #define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__)
 
+/**
+ * synchronize_rcu_mult - Wait concurrently for multiple grace periods
+ * @...: List of call_rcu() functions for different grace periods to wait on
+ *
+ * This macro waits concurrently for multiple types of RCU grace periods.
+ * For example, synchronize_rcu_mult(call_rcu, call_rcu_tasks) would wait
+ * on concurrent RCU and RCU-tasks grace periods.  Waiting on a given SRCU
+ * domain requires you to write a wrapper function for that SRCU domain's
+ * call_srcu() function, with this wrapper supplying the pointer to the
+ * corresponding srcu_struct.
+ *
+ * The first argument tells Tiny RCU's _wait_rcu_gp() not to
+ * bother waiting for RCU.  The reason for this is because anywhere
+ * synchronize_rcu_mult() can be called is automatically already a full
+ * grace period.
+ */
+#define synchronize_rcu_mult(...) \
+	_wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__)
+
 #endif /* _LINUX_SCHED_RCUPDATE_WAIT_H */

include/linux/rcutiny.h

@@ -49,7 +49,7 @@ static inline void rcu_softirq_qs(void)
 #define rcu_note_context_switch(preempt) \
 	do { \
 		rcu_qs(); \
-		rcu_tasks_qs(current); \
+		rcu_tasks_qs(current, (preempt)); \
 	} while (0)
 
 static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt)
@@ -71,6 +71,7 @@ static inline void rcu_irq_enter(void) { }
 static inline void rcu_irq_exit_irqson(void) { }
 static inline void rcu_irq_enter_irqson(void) { }
 static inline void rcu_irq_exit(void) { }
+static inline void rcu_irq_exit_preempt(void) { }
 static inline void exit_rcu(void) { }
 static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
@@ -85,8 +86,10 @@ static inline void rcu_scheduler_starting(void) { }
 static inline void rcu_end_inkernel_boot(void) { }
 static inline bool rcu_inkernel_boot_has_ended(void) { return true; }
 static inline bool rcu_is_watching(void) { return true; }
+static inline bool __rcu_is_watching(void) { return true; }
 static inline void rcu_momentary_dyntick_idle(void) { }
 static inline void kfree_rcu_scheduler_running(void) { }
+static inline bool rcu_gp_might_be_stalled(void) { return false; }
 
 /* Avoid RCU read-side critical sections leaking across. */
 static inline void rcu_all_qs(void) { barrier(); }

include/linux/rcutree.h

@@ -39,6 +39,7 @@ void rcu_barrier(void);
 bool rcu_eqs_special_set(int cpu);
 void rcu_momentary_dyntick_idle(void);
 void kfree_rcu_scheduler_running(void);
+bool rcu_gp_might_be_stalled(void);
 unsigned long get_state_synchronize_rcu(void);
 void cond_synchronize_rcu(unsigned long oldstate);
 
@@ -46,6 +47,7 @@ void rcu_idle_enter(void);
 void rcu_idle_exit(void);
 void rcu_irq_enter(void);
 void rcu_irq_exit(void);
+void rcu_irq_exit_preempt(void);
 void rcu_irq_enter_irqson(void);
 void rcu_irq_exit_irqson(void);
 
@@ -56,6 +58,7 @@ extern int rcu_scheduler_active __read_mostly;
 void rcu_end_inkernel_boot(void);
 bool rcu_inkernel_boot_has_ended(void);
 bool rcu_is_watching(void);
+bool __rcu_is_watching(void);
 #ifndef CONFIG_PREEMPTION
 void rcu_all_qs(void);
 #endif

include/linux/sched.h

@@ -613,7 +613,7 @@ union rcu_special {
 		u8			blocked;
 		u8			need_qs;
 		u8			exp_hint; /* Hint for performance. */
-		u8			deferred_qs;
+		u8			need_mb; /* Readers need smp_mb(). */
 	} b; /* Bits. */
 	u32 s; /* Set of bits. */
 };
@@ -724,6 +724,14 @@ struct task_struct {
 	struct list_head		rcu_tasks_holdout_list;
 #endif /* #ifdef CONFIG_TASKS_RCU */
 
+#ifdef CONFIG_TASKS_TRACE_RCU
+	int				trc_reader_nesting;
+	int				trc_ipi_to_cpu;
+	union rcu_special		trc_reader_special;
+	bool				trc_reader_checked;
+	struct list_head		trc_holdout_list;
+#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
+
 	struct sched_info		sched_info;
 
 	struct list_head		tasks;
@@ -1289,6 +1297,12 @@ struct task_struct {
 	unsigned long			prev_lowest_stack;
 #endif
 
+#ifdef CONFIG_X86_MCE
+	u64				mce_addr;
+	u64				mce_status;
+	struct callback_head		mce_kill_me;
+#endif
+
 	/*
 	 * New fields for task_struct should be added above here, so that
 	 * they are included in the randomized portion of task_struct.

include/linux/torture.h

@@ -89,7 +89,7 @@ void _torture_stop_kthread(char *m, struct task_struct **tp);
 #ifdef CONFIG_PREEMPTION
 #define torture_preempt_schedule() preempt_schedule()
 #else
-#define torture_preempt_schedule()
+#define torture_preempt_schedule()	do { } while (0)
 #endif
 
 #endif /* __LINUX_TORTURE_H */

include/linux/wait.h

@@ -1149,4 +1149,6 @@ int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, i
 		(wait)->flags = 0;						\
 	} while (0)
 
+bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg);
+
 #endif /* _LINUX_WAIT_H */