Merge branch 'for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/rcu

Pull RCU updates from Paul McKenney:

  1. Miscellaneous fixes.
  2. kfree_rcu() updates.
  3. Remove scheduler locking restriction
  4. RCU-tasks update, including addition of RCU Tasks Trace for
     BPF use and RCU Tasks Rude.  (This branch is on top of #3 due
     to overlap of changed code.)
  5. RCU CPU stall warning updates.
  6. Torture-test updates.

1 files changed, 34 insertions, 19 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 04278493bf15..9437b53cc603 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -356,28 +356,30 @@ struct util_est {
 } __attribute__((__aligned__(sizeof(u64))));
 
 /*
- * The load_avg/util_avg accumulates an infinite geometric series
- * (see __update_load_avg() in kernel/sched/fair.c).
+ * The load/runnable/util_avg accumulates an infinite geometric series
+ * (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c).
  *
  * [load_avg definition]
  *
  *   load_avg = runnable% * scale_load_down(load)
  *
- * where runnable% is the time ratio that a sched_entity is runnable.
- * For cfs_rq, it is the aggregated load_avg of all runnable and
- * blocked sched_entities.
+ * [runnable_avg definition]
+ *
+ *   runnable_avg = runnable% * SCHED_CAPACITY_SCALE
  *
  * [util_avg definition]
  *
  *   util_avg = running% * SCHED_CAPACITY_SCALE
  *
- * where running% is the time ratio that a sched_entity is running on
- * a CPU. For cfs_rq, it is the aggregated util_avg of all runnable
- * and blocked sched_entities.
+ * where runnable% is the time ratio that a sched_entity is runnable and
+ * running% the time ratio that a sched_entity is running.
+ *
+ * For cfs_rq, they are the aggregated values of all runnable and blocked
+ * sched_entities.
  *
- * load_avg and util_avg don't direcly factor frequency scaling and CPU
- * capacity scaling. The scaling is done through the rq_clock_pelt that
- * is used for computing those signals (see update_rq_clock_pelt())
+ * The load/runnable/util_avg doesn't direcly factor frequency scaling and CPU
+ * capacity scaling. The scaling is done through the rq_clock_pelt that is used
+ * for computing those signals (see update_rq_clock_pelt())
  *
  * N.B., the above ratios (runnable% and running%) themselves are in the
  * range of [0, 1]. To do fixed point arithmetics, we therefore scale them
@@ -401,11 +403,11 @@ struct util_est {
 struct sched_avg {
 	u64				last_update_time;
 	u64				load_sum;
-	u64				runnable_load_sum;
+	u64				runnable_sum;
 	u32				util_sum;
 	u32				period_contrib;
 	unsigned long			load_avg;
-	unsigned long			runnable_load_avg;
+	unsigned long			runnable_avg;
 	unsigned long			util_avg;
 	struct util_est			util_est;
 } ____cacheline_aligned;
@@ -449,7 +451,6 @@ struct sched_statistics {
 struct sched_entity {
 	/* For load-balancing: */
 	struct load_weight		load;
-	unsigned long			runnable_weight;
 	struct rb_node			run_node;
 	struct list_head		group_node;
 	unsigned int			on_rq;
@@ -470,6 +471,8 @@ struct sched_entity {
 	struct cfs_rq			*cfs_rq;
 	/* rq "owned" by this entity/group: */
 	struct cfs_rq			*my_q;
+	/* cached value of my_q->h_nr_running */
+	unsigned long			runnable_weight;
 #endif
 
 #ifdef CONFIG_SMP
@@ -610,7 +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. */
 };
@@ -721,6 +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;
@@ -782,9 +793,12 @@ struct task_struct {
 	unsigned			frozen:1;
 #endif
 #ifdef CONFIG_BLK_CGROUP
-	/* to be used once the psi infrastructure lands upstream. */
 	unsigned			use_memdelay:1;
 #endif
+#ifdef CONFIG_PSI
+	/* Stalled due to lack of memory */
+	unsigned			in_memstall:1;
+#endif
 
 	unsigned long			atomic_flags; /* Flags requiring atomic access. */
 
@@ -939,8 +953,8 @@ struct task_struct {
 	struct seccomp			seccomp;
 
 	/* Thread group tracking: */
-	u32				parent_exec_id;
-	u32				self_exec_id;
+	u64				parent_exec_id;
+	u64				self_exec_id;
 
 	/* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */
 	spinlock_t			alloc_lock;
@@ -970,6 +984,7 @@ struct task_struct {
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 	unsigned int			irq_events;
+	unsigned int			hardirq_threaded;
 	unsigned long			hardirq_enable_ip;
 	unsigned long			hardirq_disable_ip;
 	unsigned int			hardirq_enable_event;
@@ -982,6 +997,7 @@ struct task_struct {
 	unsigned int			softirq_enable_event;
 	int				softirqs_enabled;
 	int				softirq_context;
+	int				irq_config;
 #endif
 
 #ifdef CONFIG_LOCKDEP
@@ -1477,7 +1493,6 @@ extern struct pid *cad_pid;
 #define PF_KTHREAD		0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
 #define PF_SWAPWRITE		0x00800000	/* Allowed to write to swap */
-#define PF_MEMSTALL		0x01000000	/* Stalled due to lack of memory */
 #define PF_UMH			0x02000000	/* I'm an Usermodehelper process */
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */