[PATCH tip/core/rcu 0/6] v2 RCU fixes for 3.11

[PATCH tip/core/rcu 0/6] v2 RCU fixes for 3.11

[Paul E. McKenney]

1-2.	Convert remaining printk() calls to pr_*().

3.	Remove "Experimental" flags from old RCU Kconfig options.

4.	Automatically tune defaults for delays between attempts to
	force quiescent states.

5.	Merge adjacent identical #ifdefs.

6.	Apply Dave Jones's NOCB Kconfig help feedback.

Changes since v2:

o	Adaptive-ticks-CPU-kick patch dropped from this series and
	added to Frederic Weisbecker's adaptive-ticks patchset.

o	Patch to avoid allocating bootmem from rcu_init() was applied
	to 3.10 due to the number of people running into the corresponding
	splat.

o	Changed force-quiescent-state delay computation to use impulse
	functions, as suggested by Josh Triplett.

o	Added Dave Jones's NOCB Kconfig help patch.

							Thanx, Paul

 b/init/Kconfig            |   36 +++++++++++++++++++++---------
 b/kernel/rcupdate.c       |    3 --
 b/kernel/rcutree.c        |   24 +++++++++++++++-----
 b/kernel/rcutree.h        |   15 ++++++++----
 b/kernel/rcutree_plugin.h |   55 ++++++++++++++++++++++------------------------
 5 files changed, 82 insertions(+), 51 deletions(-)

[PATCH tip/core/rcu 1/6] rcu: Convert rcutree.c printk calls

[Paul E. McKenney]

From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

This commit converts printk() calls to the corresponding pr_*() calls.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
---
 kernel/rcutree.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 16ea679..302eadf 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -866,7 +866,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 	 * See Documentation/RCU/stallwarn.txt for info on how to debug
 	 * RCU CPU stall warnings.
 	 */
-	printk(KERN_ERR "INFO: %s detected stalls on CPUs/tasks:",
+	pr_err("INFO: %s detected stalls on CPUs/tasks:",
 	       rsp->name);
 	print_cpu_stall_info_begin();
 	rcu_for_each_leaf_node(rsp, rnp) {
@@ -899,7 +899,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 	       smp_processor_id(), (long)(jiffies - rsp->gp_start),
 	       rsp->gpnum, rsp->completed, totqlen);
 	if (ndetected == 0)
-		printk(KERN_ERR "INFO: Stall ended before state dump start\n");
+		pr_err("INFO: Stall ended before state dump start\n");
 	else if (!trigger_all_cpu_backtrace())
 		rcu_dump_cpu_stacks(rsp);
 
@@ -922,7 +922,7 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	 * See Documentation/RCU/stallwarn.txt for info on how to debug
 	 * RCU CPU stall warnings.
 	 */
-	printk(KERN_ERR "INFO: %s self-detected stall on CPU", rsp->name);
+	pr_err("INFO: %s self-detected stall on CPU", rsp->name);
 	print_cpu_stall_info_begin();
 	print_cpu_stall_info(rsp, smp_processor_id());
 	print_cpu_stall_info_end();
-- 
1.8.1.5

[PATCH tip/core/rcu 2/6] rcu: Convert rcutree_plugin.h printk calls

[Paul E. McKenney]

From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

This commit converts printk() calls to the corresponding pr_*() calls.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
---
 kernel/rcutree_plugin.h | 45 ++++++++++++++++++++++-----------------------
 1 file changed, 22 insertions(+), 23 deletions(-)

diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 3db5a37..207844e 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -53,38 +53,37 @@ static char __initdata nocb_buf[NR_CPUS * 5];
 static void __init rcu_bootup_announce_oddness(void)
 {
 #ifdef CONFIG_RCU_TRACE
-	printk(KERN_INFO "\tRCU debugfs-based tracing is enabled.\n");
+	pr_info("\tRCU debugfs-based tracing is enabled.\n");
 #endif
 #if (defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) || (!defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32)
-	printk(KERN_INFO "\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
+	pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
 	       CONFIG_RCU_FANOUT);
 #endif
 #ifdef CONFIG_RCU_FANOUT_EXACT
-	printk(KERN_INFO "\tHierarchical RCU autobalancing is disabled.\n");
+	pr_info("\tHierarchical RCU autobalancing is disabled.\n");
 #endif
 #ifdef CONFIG_RCU_FAST_NO_HZ
-	printk(KERN_INFO
-	       "\tRCU dyntick-idle grace-period acceleration is enabled.\n");
+	pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n");
 #endif
 #ifdef CONFIG_PROVE_RCU
-	printk(KERN_INFO "\tRCU lockdep checking is enabled.\n");
+	pr_info("\tRCU lockdep checking is enabled.\n");
 #endif
 #ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE
-	printk(KERN_INFO "\tRCU torture testing starts during boot.\n");
+	pr_info("\tRCU torture testing starts during boot.\n");
 #endif
 #if defined(CONFIG_TREE_PREEMPT_RCU) && !defined(CONFIG_RCU_CPU_STALL_VERBOSE)
-	printk(KERN_INFO "\tDump stacks of tasks blocking RCU-preempt GP.\n");
+	pr_info("\tDump stacks of tasks blocking RCU-preempt GP.\n");
 #endif
 #if defined(CONFIG_RCU_CPU_STALL_INFO)
-	printk(KERN_INFO "\tAdditional per-CPU info printed with stalls.\n");
+	pr_info("\tAdditional per-CPU info printed with stalls.\n");
 #endif
 #if NUM_RCU_LVL_4 != 0
-	printk(KERN_INFO "\tFour-level hierarchy is enabled.\n");
+	pr_info("\tFour-level hierarchy is enabled.\n");
 #endif
 	if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF)
-		printk(KERN_INFO "\tExperimental boot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
+		pr_info("\tExperimental boot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
 	if (nr_cpu_ids != NR_CPUS)
-		printk(KERN_INFO "\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
+		pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
 #ifdef CONFIG_RCU_NOCB_CPU
 #ifndef CONFIG_RCU_NOCB_CPU_NONE
 	if (!have_rcu_nocb_mask) {
@@ -123,7 +122,7 @@ static int rcu_preempted_readers_exp(struct rcu_node *rnp);
  */
 static void __init rcu_bootup_announce(void)
 {
-	printk(KERN_INFO "Preemptible hierarchical RCU implementation.\n");
+	pr_info("Preemptible hierarchical RCU implementation.\n");
 	rcu_bootup_announce_oddness();
 }
 
@@ -490,13 +489,13 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp)
 
 static void rcu_print_task_stall_begin(struct rcu_node *rnp)
 {
-	printk(KERN_ERR "\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",
+	pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",
 	       rnp->level, rnp->grplo, rnp->grphi);
 }
 
 static void rcu_print_task_stall_end(void)
 {
-	printk(KERN_CONT "\n");
+	pr_cont("\n");
 }
 
 #else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */
@@ -526,7 +525,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp)
 	t = list_entry(rnp->gp_tasks,
 		       struct task_struct, rcu_node_entry);
 	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
-		printk(KERN_CONT " P%d", t->pid);
+		pr_cont(" P%d", t->pid);
 		ndetected++;
 	}
 	rcu_print_task_stall_end();
@@ -942,7 +941,7 @@ static struct rcu_state *rcu_state = &rcu_sched_state;
  */
 static void __init rcu_bootup_announce(void)
 {
-	printk(KERN_INFO "Hierarchical RCU implementation.\n");
+	pr_info("Hierarchical RCU implementation.\n");
 	rcu_bootup_announce_oddness();
 }
 
@@ -1883,7 +1882,7 @@ static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
 /* Initiate the stall-info list. */
 static void print_cpu_stall_info_begin(void)
 {
-	printk(KERN_CONT "\n");
+	pr_cont("\n");
 }
 
 /*
@@ -1914,7 +1913,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
 		ticks_value = rsp->gpnum - rdp->gpnum;
 	}
 	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
-	printk(KERN_ERR "\t%d: (%lu %s) idle=%03x/%llx/%d softirq=%u/%u %s\n",
+	pr_err("\t%d: (%lu %s) idle=%03x/%llx/%d softirq=%u/%u %s\n",
 	       cpu, ticks_value, ticks_title,
 	       atomic_read(&rdtp->dynticks) & 0xfff,
 	       rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting,
@@ -1925,7 +1924,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
 /* Terminate the stall-info list. */
 static void print_cpu_stall_info_end(void)
 {
-	printk(KERN_ERR "\t");
+	pr_err("\t");
 }
 
 /* Zero ->ticks_this_gp for all flavors of RCU. */
@@ -1948,17 +1947,17 @@ static void increment_cpu_stall_ticks(void)
 
 static void print_cpu_stall_info_begin(void)
 {
-	printk(KERN_CONT " {");
+	pr_cont(" {");
 }
 
 static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
 {
-	printk(KERN_CONT " %d", cpu);
+	pr_cont(" %d", cpu);
 }
 
 static void print_cpu_stall_info_end(void)
 {
-	printk(KERN_CONT "} ");
+	pr_cont("} ");
 }
 
 static void zero_cpu_stall_ticks(struct rcu_data *rdp)
-- 
1.8.1.5

[PATCH tip/core/rcu 3/6] rcu: Remove "Experimental" flags

[Paul E. McKenney]

From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

After a release or two, features are no longer experimental.  Therefore,
this commit removes the "Experimental" tag from them.

Reported-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
---
 init/Kconfig            |  2 +-
 kernel/rcutree_plugin.h | 10 +++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index 9d3a788..09ab5c2 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -655,7 +655,7 @@ config RCU_BOOST_DELAY
 	  Accept the default if unsure.
 
 config RCU_NOCB_CPU
-	bool "Offload RCU callback processing from boot-selected CPUs (EXPERIMENTAL"
+	bool "Offload RCU callback processing from boot-selected CPUs"
 	depends on TREE_RCU || TREE_PREEMPT_RCU
 	default n
 	help
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 207844e..6b3ccaa 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -81,7 +81,7 @@ static void __init rcu_bootup_announce_oddness(void)
 	pr_info("\tFour-level hierarchy is enabled.\n");
 #endif
 	if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF)
-		pr_info("\tExperimental boot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
+		pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
 	if (nr_cpu_ids != NR_CPUS)
 		pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
 #ifdef CONFIG_RCU_NOCB_CPU
@@ -91,19 +91,19 @@ static void __init rcu_bootup_announce_oddness(void)
 		have_rcu_nocb_mask = true;
 	}
 #ifdef CONFIG_RCU_NOCB_CPU_ZERO
-	pr_info("\tExperimental no-CBs CPU 0\n");
+	pr_info("\tOffload RCU callbacks from CPU 0\n");
 	cpumask_set_cpu(0, rcu_nocb_mask);
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */
 #ifdef CONFIG_RCU_NOCB_CPU_ALL
-	pr_info("\tExperimental no-CBs for all CPUs\n");
+	pr_info("\tOffload RCU callbacks from all CPUs\n");
 	cpumask_setall(rcu_nocb_mask);
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */
 #endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */
 	if (have_rcu_nocb_mask) {
 		cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask);
-		pr_info("\tExperimental no-CBs CPUs: %s.\n", nocb_buf);
+		pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf);
 		if (rcu_nocb_poll)
-			pr_info("\tExperimental polled no-CBs CPUs.\n");
+			pr_info("\tPoll for callbacks from no-CBs CPUs.\n");
 	}
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 }
-- 
1.8.1.5

[PATCH tip/core/rcu 4/6] rcu: Drive quiescent-state-forcing delay from HZ

[Paul E. McKenney]

From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

Systems with HZ=100 can have slow bootup times due to the default
three-jiffy delays between quiescent-state forcing attempts.  This
commit therefore auto-tunes the RCU_JIFFIES_TILL_FORCE_QS value based
on the value of HZ.  However, this would break very large systems that
require more time between quiescent-state forcing attempts.  This
commit therefore also ups the default delay by one jiffy for each
256 CPUs that might be on the system (based off of nr_cpu_ids at
runtime, -not- NR_CPUS at build time).

Updated to collapse #ifdefs for RCU_JIFFIES_TILL_FORCE_QS into a
step-function definition as suggested by Josh Triplett.

Reported-by: Paul Mackerras <paulus@au1.ibm.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcutree.c | 18 ++++++++++++++++--
 kernel/rcutree.h | 15 ++++++++++-----
 2 files changed, 26 insertions(+), 7 deletions(-)

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 302eadf..33510a1 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -218,8 +218,8 @@ module_param(blimit, long, 0444);
 module_param(qhimark, long, 0444);
 module_param(qlowmark, long, 0444);
 
-static ulong jiffies_till_first_fqs = RCU_JIFFIES_TILL_FORCE_QS;
-static ulong jiffies_till_next_fqs = RCU_JIFFIES_TILL_FORCE_QS;
+static ulong jiffies_till_first_fqs = ULONG_MAX;
+static ulong jiffies_till_next_fqs = ULONG_MAX;
 
 module_param(jiffies_till_first_fqs, ulong, 0644);
 module_param(jiffies_till_next_fqs, ulong, 0644);
@@ -3252,11 +3252,25 @@ static void __init rcu_init_one(struct rcu_state *rsp,
  */
 static void __init rcu_init_geometry(void)
 {
+	ulong d;
 	int i;
 	int j;
 	int n = nr_cpu_ids;
 	int rcu_capacity[MAX_RCU_LVLS + 1];
 
+	/*
+	 * Initialize any unspecified boot parameters.
+	 * The default values of jiffies_till_first_fqs and
+	 * jiffies_till_next_fqs are set to the RCU_JIFFIES_TILL_FORCE_QS
+	 * value, which is a function of HZ, then adding one for each
+	 * RCU_JIFFIES_FQS_DIV CPUs that might be on the system.
+	 */
+	d = RCU_JIFFIES_TILL_FORCE_QS + nr_cpu_ids / RCU_JIFFIES_FQS_DIV;
+	if (jiffies_till_first_fqs == ULONG_MAX)
+		jiffies_till_first_fqs = d;
+	if (jiffies_till_next_fqs == ULONG_MAX)
+		jiffies_till_next_fqs = d;
+
 	/* If the compile-time values are accurate, just leave. */
 	if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
 	    nr_cpu_ids == NR_CPUS)
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index da77a8f..cc5b1b7 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -342,12 +342,17 @@ struct rcu_data {
 #define RCU_FORCE_QS		3	/* Need to force quiescent state. */
 #define RCU_SIGNAL_INIT		RCU_SAVE_DYNTICK
 
-#define RCU_JIFFIES_TILL_FORCE_QS	 3	/* for rsp->jiffies_force_qs */
+#define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500))
+					/* For jiffies_till_first_fqs and */
+					/*  and jiffies_till_next_fqs. */
 
-#define RCU_STALL_RAT_DELAY		2	/* Allow other CPUs time */
-						/*  to take at least one */
-						/*  scheduling clock irq */
-						/*  before ratting on them. */
+#define RCU_JIFFIES_FQS_DIV	256	/* Very large systems need more */
+					/*  delay between bouts of */
+					/*  quiescent-state forcing. */
+
+#define RCU_STALL_RAT_DELAY	2	/* Allow other CPUs time to take */
+					/*  at least one scheduling clock */
+					/*  irq before ratting on them. */
 
 #define rcu_wait(cond)							\
 do {									\
-- 
1.8.1.5

[PATCH tip/core/rcu 5/6] rcu: Merge adjacent identical ifdefs

[Paul E. McKenney]

From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

Two ifdefs in kernel/rcupdate.c now have identical conditions with
nothing between them, so the commit merges them into a single ifdef.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
---
 kernel/rcupdate.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 48ab703..faeea98 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -145,9 +145,6 @@ static struct lock_class_key rcu_sched_lock_key;
 struct lockdep_map rcu_sched_lock_map =
 	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);
 EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
-#endif
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 int debug_lockdep_rcu_enabled(void)
 {
-- 
1.8.1.5

[PATCH tip/core/rcu 6/6] rcu: Apply Dave Jones's NOCB Kconfig help feedback

[Paul E. McKenney]

From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

The Kconfig help text for the RCU_NOCB_CPU_NONE, RCU_NOCB_CPU_ZERO,
and RCU_NOCB_CPU_ALL Kconfig options was unclear, so this commit
adds a bit more detail.

Reported-by: Dave Jones <davej@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 init/Kconfig | 34 +++++++++++++++++++++++++---------
 1 file changed, 25 insertions(+), 9 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index 09ab5c2..289bb3f 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -681,9 +681,10 @@ choice
 	prompt "Build-forced no-CBs CPUs"
 	default RCU_NOCB_CPU_NONE
 	help
-	  This option allows no-CBs CPUs to be specified at build time.
-	  Additional no-CBs CPUs may be specified by the rcu_nocbs=
-	  boot parameter.
+	  This option allows no-CBs CPUs (whose RCU callbacks are invoked
+	  from kthreads rather than from softirq context) to be specified
+	  at build time.  Additional no-CBs CPUs may be specified by
+	  the rcu_nocbs= boot parameter.
 
 config RCU_NOCB_CPU_NONE
 	bool "No build_forced no-CBs CPUs"
@@ -691,25 +692,40 @@ config RCU_NOCB_CPU_NONE
 	help
 	  This option does not force any of the CPUs to be no-CBs CPUs.
 	  Only CPUs designated by the rcu_nocbs= boot parameter will be
-	  no-CBs CPUs.
+	  no-CBs CPUs, whose RCU callbacks will be invoked by per-CPU
+	  kthreads whose names begin with "rcuo".  All other CPUs will
+	  invoke their own RCU callbacks in softirq context.
+
+	  Select this option if you want to choose no-CBs CPUs at
+	  boot time, for example, to allow testing of different no-CBs
+	  configurations without having to rebuild the kernel each time.
 
 config RCU_NOCB_CPU_ZERO
 	bool "CPU 0 is a build_forced no-CBs CPU"
 	depends on RCU_NOCB_CPU && !NO_HZ_FULL
 	help
-	  This option forces CPU 0 to be a no-CBs CPU.  Additional CPUs
-	  may be designated as no-CBs CPUs using the rcu_nocbs= boot
-	  parameter will be no-CBs CPUs.
+	  This option forces CPU 0 to be a no-CBs CPU, so that its RCU
+	  callbacks are invoked by a per-CPU kthread whose name begins
+	  with "rcuo".	Additional CPUs may be designated as no-CBs
+	  CPUs using the rcu_nocbs= boot parameter will be no-CBs CPUs.
+	  All other CPUs will invoke their own RCU callbacks in softirq
+	  context.
 
 	  Select this if CPU 0 needs to be a no-CBs CPU for real-time
-	  or energy-efficiency reasons.
+	  or energy-efficiency reasons, but the real reason it exists
+	  is to ensure that randconfig testing covers mixed systems.
 
 config RCU_NOCB_CPU_ALL
 	bool "All CPUs are build_forced no-CBs CPUs"
 	depends on RCU_NOCB_CPU
 	help
 	  This option forces all CPUs to be no-CBs CPUs.  The rcu_nocbs=
-	  boot parameter will be ignored.
+	  boot parameter will be ignored.  All CPUs' RCU callbacks will
+	  be executed in the context of per-CPU rcuo kthreads created for
+	  this purpose.  Assuming that the kthreads whose names start with
+	  "rcuo" are bound to "housekeeping" CPUs, this reduces OS jitter
+	  on the remaining CPUs, but might decrease memory locality during
+	  RCU-callback invocation, thus potentially degrading throughput.
 
 	  Select this if all CPUs need to be no-CBs CPUs for real-time
 	  or energy-efficiency reasons.
-- 
1.8.1.5