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

…ux/kernel/git/tip/tip

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

   - documentation updates

   - miscellaneous fixes

   - minor reorganization of code

   - torture-test updates"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (30 commits)
  rcu: Correctly handle sparse possible cpus
  rcu: sysctl: Panic on RCU Stall
  rcu: Fix a typo in a comment
  rcu: Make call_rcu_tasks() tolerate first call with irqs disabled
  rcu: Disable TASKS_RCU for usermode Linux
  rcu: No ordering for rcu_assign_pointer() of NULL
  rcutorture: Fix error return code in rcu_perf_init()
  torture: Inflict default jitter
  rcuperf: Don't treat gp_exp mis-setting as a WARN
  rcutorture: Drop "-soundhw pcspkr" from x86 boot arguments
  rcutorture: Don't specify the cpu type of QEMU on PPC
  rcutorture: Make -soundhw a x86 specific option
  rcutorture: Use vmlinux as the fallback kernel image
  rcutorture/doc: Create initrd using dracut
  torture: Stop onoff task if there is only one cpu
  torture: Add starvation events to error summary
  torture:  Break online and offline functions out of torture_onoff()
  torture: Forgive lengthy trace dumps and preemption
  torture: Remove CONFIG_RCU_TORTURE_TEST_RUNNABLE, simplify code
  torture: Simplify code, eliminate RCU_PERF_TEST_RUNNABLE
  ...

Documentation/RCU/Design/Requirements/Requirements.html

@@ -2391,6 +2391,41 @@ <h3><a name="Energy Efficiency">Energy Efficiency</a></h3>
 idle-loop code.
 Steven Rostedt supplied <tt>_rcuidle</tt> event tracing,
 which is used quite heavily in the idle loop.
+However, there are some restrictions on the code placed within
+<tt>RCU_NONIDLE()</tt>:
+
+<ol>
+<li>	Blocking is prohibited.
+	In practice, this is not a serious restriction given that idle
+	tasks are prohibited from blocking to begin with.
+<li>	Although nesting <tt>RCU_NONIDLE()</tt> is permited, they cannot
+	nest indefinitely deeply.
+	However, given that they can be nested on the order of a million
+	deep, even on 32-bit systems, this should not be a serious
+	restriction.
+	This nesting limit would probably be reached long after the
+	compiler OOMed or the stack overflowed.
+<li>	Any code path that enters <tt>RCU_NONIDLE()</tt> must sequence
+	out of that same <tt>RCU_NONIDLE()</tt>.
+	For example, the following is grossly illegal:
+
+	<blockquote>
+	<pre>
+ 1     RCU_NONIDLE({
+ 2       do_something();
+ 3       goto bad_idea;  /* BUG!!! */
+ 4       do_something_else();});
+ 5   bad_idea:
+	</pre>
+	</blockquote>
+
+	<p>
+	It is just as illegal to transfer control into the middle of
+	<tt>RCU_NONIDLE()</tt>'s argument.
+	Yes, in theory, you could transfer in as long as you also
+	transferred out, but in practice you could also expect to get sharply
+	worded review comments.
+</ol>
 
 <p>
 It is similarly socially unacceptable to interrupt an

Documentation/RCU/stallwarn.txt

@@ -49,7 +49,7 @@ rcupdate.rcu_task_stall_timeout
 	This boot/sysfs parameter controls the RCU-tasks stall warning
 	interval.  A value of zero or less suppresses RCU-tasks stall
 	warnings.  A positive value sets the stall-warning interval
-	in jiffies.  An RCU-tasks stall warning starts wtih the line:
+	in jiffies.  An RCU-tasks stall warning starts with the line:
 
 		INFO: rcu_tasks detected stalls on tasks:
 

Documentation/RCU/whatisRCU.txt

@@ -5,6 +5,9 @@ to start learning about RCU:
 2.	What is RCU? Part 2: Usage   http://lwn.net/Articles/263130/
 3.	RCU part 3: the RCU API      http://lwn.net/Articles/264090/
 4.	The RCU API, 2010 Edition    http://lwn.net/Articles/418853/
+	2010 Big API Table           http://lwn.net/Articles/419086/
+5.	The RCU API, 2014 Edition    http://lwn.net/Articles/609904/
+	2014 Big API Table           http://lwn.net/Articles/609973/
 
 
 What is RCU?

Documentation/sysctl/kernel.txt

@@ -58,6 +58,7 @@ show up in /proc/sys/kernel:
 - panic_on_stackoverflow
 - panic_on_unrecovered_nmi
 - panic_on_warn
+- panic_on_rcu_stall
 - perf_cpu_time_max_percent
 - perf_event_paranoid
 - perf_event_max_stack
@@ -618,6 +619,17 @@ a kernel rebuild when attempting to kdump at the location of a WARN().
 
 ==============================================================
 
+panic_on_rcu_stall:
+
+When set to 1, calls panic() after RCU stall detection messages. This
+is useful to define the root cause of RCU stalls using a vmcore.
+
+0: do not panic() when RCU stall takes place, default behavior.
+
+1: panic() after printing RCU stall messages.
+
+==============================================================
+
 perf_cpu_time_max_percent:
 
 Hints to the kernel how much CPU time it should be allowed to

include/linux/kernel.h

@@ -451,6 +451,7 @@ extern int panic_on_oops;
 extern int panic_on_unrecovered_nmi;
 extern int panic_on_io_nmi;
 extern int panic_on_warn;
+extern int sysctl_panic_on_rcu_stall;
 extern int sysctl_panic_on_stackoverflow;
 
 extern bool crash_kexec_post_notifiers;

include/linux/rcupdate.h

@@ -45,6 +45,7 @@
 #include <linux/bug.h>
 #include <linux/compiler.h>
 #include <linux/ktime.h>
+#include <linux/irqflags.h>
 
 #include <asm/barrier.h>
 
@@ -379,12 +380,13 @@ static inline void rcu_init_nohz(void)
  * in the inner idle loop.
  *
  * This macro provides the way out:  RCU_NONIDLE(do_something_with_RCU())
- * will tell RCU that it needs to pay attending, invoke its argument
- * (in this example, a call to the do_something_with_RCU() function),
+ * will tell RCU that it needs to pay attention, invoke its argument
+ * (in this example, calling the do_something_with_RCU() function),
  * and then tell RCU to go back to ignoring this CPU.  It is permissible
- * to nest RCU_NONIDLE() wrappers, but the nesting level is currently
- * quite limited.  If deeper nesting is required, it will be necessary
- * to adjust DYNTICK_TASK_NESTING_VALUE accordingly.
+ * to nest RCU_NONIDLE() wrappers, but not indefinitely (but the limit is
+ * on the order of a million or so, even on 32-bit systems).  It is
+ * not legal to block within RCU_NONIDLE(), nor is it permissible to
+ * transfer control either into or out of RCU_NONIDLE()'s statement.
  */
 #define RCU_NONIDLE(a) \
 	do { \
@@ -649,7 +651,16 @@ static inline void rcu_preempt_sleep_check(void)
  * please be careful when making changes to rcu_assign_pointer() and the
  * other macros that it invokes.
  */
-#define rcu_assign_pointer(p, v) smp_store_release(&p, RCU_INITIALIZER(v))
+#define rcu_assign_pointer(p, v)					      \
+({									      \
+	uintptr_t _r_a_p__v = (uintptr_t)(v);				      \
+									      \
+	if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL)	      \
+		WRITE_ONCE((p), (typeof(p))(_r_a_p__v));		      \
+	else								      \
+		smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \
+	_r_a_p__v;							      \
+})
 
 /**
  * rcu_access_pointer() - fetch RCU pointer with no dereferencing

include/linux/torture.h

@@ -50,6 +50,10 @@
 	do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s); } while (0)
 
 /* Definitions for online/offline exerciser. */
+bool torture_offline(int cpu, long *n_onl_attempts, long *n_onl_successes,
+		     unsigned long *sum_offl, int *min_onl, int *max_onl);
+bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
+		    unsigned long *sum_onl, int *min_onl, int *max_onl);
 int torture_onoff_init(long ooholdoff, long oointerval);
 void torture_onoff_stats(void);
 bool torture_onoff_failures(void);

init/Kconfig

@@ -517,6 +517,7 @@ config SRCU
 config TASKS_RCU
 	bool
 	default n
+	depends on !UML
 	select SRCU
 	help
 	  This option enables a task-based RCU implementation that uses

kernel/rcu/rcuperf.c

@@ -58,7 +58,7 @@ MODULE_AUTHOR("Paul E. McKenney <[email protected]>");
 #define VERBOSE_PERFOUT_ERRSTRING(s) \
 	do { if (verbose) pr_alert("%s" PERF_FLAG "!!! %s\n", perf_type, s); } while (0)
 
-torture_param(bool, gp_exp, true, "Use expedited GP wait primitives");
+torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
 torture_param(int, holdoff, 10, "Holdoff time before test start (s)");
 torture_param(int, nreaders, -1, "Number of RCU reader threads");
 torture_param(int, nwriters, -1, "Number of RCU updater threads");
@@ -96,12 +96,7 @@ static int rcu_perf_writer_state;
 #define MAX_MEAS 10000
 #define MIN_MEAS 100
 
-#if defined(MODULE) || defined(CONFIG_RCU_PERF_TEST_RUNNABLE)
-#define RCUPERF_RUNNABLE_INIT 1
-#else
-#define RCUPERF_RUNNABLE_INIT 0
-#endif
-static int perf_runnable = RCUPERF_RUNNABLE_INIT;
+static int perf_runnable = IS_ENABLED(MODULE);
 module_param(perf_runnable, int, 0444);
 MODULE_PARM_DESC(perf_runnable, "Start rcuperf at boot");
 
@@ -363,8 +358,6 @@ rcu_perf_writer(void *arg)
 	u64 *wdpp = writer_durations[me];
 
 	VERBOSE_PERFOUT_STRING("rcu_perf_writer task started");
-	WARN_ON(rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp);
-	WARN_ON(rcu_gp_is_normal() && gp_exp);
 	WARN_ON(!wdpp);
 	set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
 	sp.sched_priority = 1;
@@ -631,12 +624,24 @@ rcu_perf_init(void)
 		firsterr = -ENOMEM;
 		goto unwind;
 	}
+	if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp) {
+		VERBOSE_PERFOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!");
+		firsterr = -EINVAL;
+		goto unwind;
+	}
+	if (rcu_gp_is_normal() && gp_exp) {
+		VERBOSE_PERFOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!");
+		firsterr = -EINVAL;
+		goto unwind;
+	}
 	for (i = 0; i < nrealwriters; i++) {
 		writer_durations[i] =
 			kcalloc(MAX_MEAS, sizeof(*writer_durations[i]),
 				GFP_KERNEL);
-		if (!writer_durations[i])
+		if (!writer_durations[i]) {
+			firsterr = -ENOMEM;
 			goto unwind;
+		}
 		firsterr = torture_create_kthread(rcu_perf_writer, (void *)i,
 						  writer_tasks[i]);
 		if (firsterr)

kernel/rcu/rcutorture.c

@@ -182,12 +182,7 @@ static const char *rcu_torture_writer_state_getname(void)
 	return rcu_torture_writer_state_names[i];
 }
 
-#if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE)
-#define RCUTORTURE_RUNNABLE_INIT 1
-#else
-#define RCUTORTURE_RUNNABLE_INIT 0
-#endif
-static int torture_runnable = RCUTORTURE_RUNNABLE_INIT;
+static int torture_runnable = IS_ENABLED(MODULE);
 module_param(torture_runnable, int, 0444);
 MODULE_PARM_DESC(torture_runnable, "Start rcutorture at boot");
 
@@ -1476,7 +1471,7 @@ static int rcu_torture_barrier_cbs(void *arg)
 			break;
 		/*
 		 * The above smp_load_acquire() ensures barrier_phase load
-		 * is ordered before the folloiwng ->call().
+		 * is ordered before the following ->call().
 		 */
 		local_irq_disable(); /* Just to test no-irq call_rcu(). */
 		cur_ops->call(&rcu, rcu_torture_barrier_cbf);