Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RCU updates from Ingo Molnar:
 "The main RCU changes in this development cycle were:

   - Miscellaneous fixes, including a change to call_rcu()'s rcu_head
     alignment check.

   - Security-motivated list consistency checks, which are disabled by
     default behind DEBUG_LIST.

   - Torture-test updates.

   - Documentation updates, yet again just simple changes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  torture: Prevent jitter from delaying build-only runs
  torture: Remove obsolete files from rcutorture .gitignore
  rcu: Don't kick unless grace period or request
  rcu: Make expedited grace periods recheck dyntick idle state
  torture: Trace long read-side delays
  rcu: RCU_TRACE enables event tracing as well as debugfs
  rcu: Remove obsolete comment from __call_rcu()
  rcu: Remove obsolete rcu_check_callbacks() header comment
  rcu: Tighten up __call_rcu() rcu_head alignment check
  Documentation/RCU: Fix minor typo
  documentation: Present updated RCU guarantee
  bug: Avoid Kconfig warning for BUG_ON_DATA_CORRUPTION
  lib/Kconfig.debug: Fix typo in select statement
  lkdtm: Add tests for struct list corruption
  bug: Provide toggle for BUG on data corruption
  list: Split list_del() debug checking into separate function
  rculist: Consolidate DEBUG_LIST for list_add_rcu()
  list: Split list_add() debug checking into separate function

4 files changed, 28 insertions, 13 deletions

diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index bf08fee53dc7..87c51225ceec 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -289,15 +289,24 @@ static int rcu_torture_read_lock(void) __acquires(RCU)
 
 static void rcu_read_delay(struct torture_random_state *rrsp)
 {
+	unsigned long started;
+	unsigned long completed;
 	const unsigned long shortdelay_us = 200;
 	const unsigned long longdelay_ms = 50;
+	unsigned long long ts;
 
 	/* We want a short delay sometimes to make a reader delay the grace
 	 * period, and we want a long delay occasionally to trigger
 	 * force_quiescent_state. */
 
-	if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms)))
+	if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
+		started = cur_ops->completed();
+		ts = rcu_trace_clock_local();
 		mdelay(longdelay_ms);
+		completed = cur_ops->completed();
+		do_trace_rcu_torture_read(cur_ops->name, NULL, ts,
+					  started, completed);
+	}
 	if (!(torture_random(rrsp) % (nrealreaders * 2 * shortdelay_us)))
 		udelay(shortdelay_us);
 #ifdef CONFIG_PREEMPT
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 69a5611a7e7c..96c52e43f7ca 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1304,7 +1304,8 @@ static void rcu_stall_kick_kthreads(struct rcu_state *rsp)
 	if (!rcu_kick_kthreads)
 		return;
 	j = READ_ONCE(rsp->jiffies_kick_kthreads);
-	if (time_after(jiffies, j) && rsp->gp_kthread) {
+	if (time_after(jiffies, j) && rsp->gp_kthread &&
+	    (rcu_gp_in_progress(rsp) || READ_ONCE(rsp->gp_flags))) {
 		WARN_ONCE(1, "Kicking %s grace-period kthread\n", rsp->name);
 		rcu_ftrace_dump(DUMP_ALL);
 		wake_up_process(rsp->gp_kthread);
@@ -2828,8 +2829,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
  * Also schedule RCU core processing.
  *
  * This function must be called from hardirq context.  It is normally
- * invoked from the scheduling-clock interrupt.  If rcu_pending returns
- * false, there is no point in invoking rcu_check_callbacks().
+ * invoked from the scheduling-clock interrupt.
  */
 void rcu_check_callbacks(int user)
 {
@@ -3121,7 +3121,9 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func,
 	unsigned long flags;
 	struct rcu_data *rdp;
 
-	WARN_ON_ONCE((unsigned long)head & 0x1); /* Misaligned rcu_head! */
+	/* Misaligned rcu_head! */
+	WARN_ON_ONCE((unsigned long)head & (sizeof(void *) - 1));
+
 	if (debug_rcu_head_queue(head)) {
 		/* Probable double call_rcu(), so leak the callback. */
 		WRITE_ONCE(head->func, rcu_leak_callback);
@@ -3130,13 +3132,6 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func,
 	}
 	head->func = func;
 	head->next = NULL;
-
-	/*
-	 * Opportunistically note grace-period endings and beginnings.
-	 * Note that we might see a beginning right after we see an
-	 * end, but never vice versa, since this CPU has to pass through
-	 * a quiescent state betweentimes.
-	 */
 	local_irq_save(flags);
 	rdp = this_cpu_ptr(rsp->rda);
 
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index e99a5234d9ed..fe98dd24adf8 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -404,6 +404,7 @@ struct rcu_data {
 	atomic_long_t exp_workdone1;	/* # done by others #1. */
 	atomic_long_t exp_workdone2;	/* # done by others #2. */
 	atomic_long_t exp_workdone3;	/* # done by others #3. */
+	int exp_dynticks_snap;		/* Double-check need for IPI. */
 
 	/* 7) Callback offloading. */
 #ifdef CONFIG_RCU_NOCB_CPU
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 24343eb87b58..d3053e99fdb6 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -358,8 +358,10 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 			struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
 
+			rdp->exp_dynticks_snap =
+				atomic_add_return(0, &rdtp->dynticks);
 			if (raw_smp_processor_id() == cpu ||
-			    !(atomic_add_return(0, &rdtp->dynticks) & 0x1) ||
+			    !(rdp->exp_dynticks_snap & 0x1) ||
 			    !(rnp->qsmaskinitnext & rdp->grpmask))
 				mask_ofl_test |= rdp->grpmask;
 		}
@@ -377,9 +379,17 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 		/* IPI the remaining CPUs for expedited quiescent state. */
 		for_each_leaf_node_possible_cpu(rnp, cpu) {
 			unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
+			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+			struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
 			if (!(mask_ofl_ipi & mask))
 				continue;
 retry_ipi:
+			if (atomic_add_return(0, &rdtp->dynticks) !=
+			    rdp->exp_dynticks_snap) {
+				mask_ofl_test |= mask;
+				continue;
+			}
 			ret = smp_call_function_single(cpu, func, rsp, 0);
 			if (!ret) {
 				mask_ofl_ipi &= ~mask;