[PATCH tip/core/rcu 0/23] v3 patches queued for 2.6.35

[PATCH tip/core/rcu 0/23] v3 patches queued for 2.6.35

[Paul E. McKenney]

Hello!

RFC preview of RCU patches queued for 2.6.35, take 3, now ready for
-tip inclusion.  Take 2 is at http://lkml.org/lkml/2010/4/15/324.
Changes to old patches noted in "[]", new patches flagged with "New".

 1.	substitute set_need_resched for sending resched IPIs
 	This reduces OS jitter.

 2.	make dead code really dead.
 3.	move some code from macro to function
 	Cleanups from Lai Jiangshan.

 4.	ignore offline CPUs in last non dyntick idle CPU check
 	Fix to my CONFIG_RCU_FAST_NO_HZ code to handle offline and
	non-existent CPUs, also from Lai Jiangshan.

 5.	fix bogus CONFIG_PROVE_LOCKING in comments to reality
 6.	fix now bogus rcu_scheduler_active comments
 	Comment fixups.

 7.	shrink rcutiny by making synchronize_rcu_bh be inline
 	Shrink TINY_RCU some more.

 8.	rename rcutiny rcu_ctrlblk to rcu_sched_ctrlblk
 	First step towards TINY_PREEMPTIBLE_RCU.

 9.	refactor RCU's context switch handling
 	Reduce the number of needless softirqs.

10.	slim down rcutiny by removing rcu_scheduler_active and friends
	More shrinkage for TINY_RCU

11.	enable CPU_STALL_VERBOSE by default.  It will have been in one
	release, so time to enable it.

12.	disable CPU stall warnings upon panic

13.	print boot-time console messages if RCU configs out of ordinary

14.	improve RCU CPU stall-warning messages

15.	permit discontiguous cpu_possible_mask CPU numbering

16.	v2: reduce the number of spurious RCU_SOFTIRQ invocations
	[Original from Lai Jiangshan]

17.	New: improve the RCU CPU-stall-warning documentation

18.	New: debugobjects transition check
19.	New: introduce rcu_head_init_on_stack
20.	New: remove all non-on-stack rcu_head initializations
21.	New: remove rcu_head initializers
22.	New: Add debug RCU head objects
	Debug-objects-based rcu_head checking from Mathieu Desnoyers

23.	New: make SRCU usable in modules
	[From Lai Jiangshan]

							Thanx, Paul

 b/Documentation/RCU/stallwarn.txt             |   94 ++++++++++++----
 b/Documentation/RCU/trace.txt                 |   35 +++---
 b/arch/powerpc/mm/pgtable.c                   |    1 
 b/block/cfq-iosched.c                         |    1 
 b/block/genhd.c                               |    1 
 b/drivers/staging/batman-adv/hard-interface.c |    1 
 b/fs/file.c                                   |    3 
 b/fs/fs-writeback.c                           |   31 ++++-
 b/fs/partitions/check.c                       |    1 
 b/include/linux/debugobjects.h                |   11 +
 b/include/linux/init_task.h                   |    1 
 b/include/linux/rcupdate.h                    |   15 +-
 b/include/linux/rcutiny.h                     |   12 +-
 b/include/linux/rcutree.h                     |    2 
 b/include/linux/srcu.h                        |    4 
 b/kernel/rcupdate.c                           |   19 ---
 b/kernel/rcutiny.c                            |    9 -
 b/kernel/rcutiny_plugin.h                     |   39 ++++++
 b/kernel/rcutorture.c                         |    2 
 b/kernel/rcutree.c                            |   10 +
 b/kernel/rcutree.h                            |    1 
 b/kernel/rcutree_plugin.h                     |    2 
 b/kernel/rcutree_trace.c                      |    4 
 b/kernel/sched.c                              |    2 
 b/kernel/softirq.c                            |    2 
 b/lib/Kconfig.debug                           |    2 
 b/lib/debugobjects.c                          |   59 +++++++++-
 b/mm/backing-dev.c                            |    1 
 b/mm/slob.c                                   |    1 
 b/security/selinux/avc.c                      |    1 
 b/security/selinux/netnode.c                  |    2 
 include/linux/rcupdate.h                      |   75 ++++++++++---
 include/linux/rcutiny.h                       |   17 ++
 include/linux/rcutree.h                       |    4 
 include/linux/srcu.h                          |    2 
 kernel/rcupdate.c                             |  149 ++++++++++++++++++++++++++
 kernel/rcutiny.c                              |   28 +++-
 kernel/rcutree.c                              |  127 +++++++++++++++-------
 kernel/rcutree.h                              |    1 
 kernel/rcutree_plugin.h                       |   55 ++++++++-
 lib/Kconfig.debug                             |    6 +
 41 files changed, 669 insertions(+), 164 deletions(-)

[PATCH tip/core/rcu 01/23] rcu: substitute set_need_resched for sending resched IPIs

[Paul E. McKenney]

This patch adds a check to __rcu_pending() that does a local
set_need_resched() if the current CPU is holding up the current grace
period and if force_quiescent_state() will be called soon.  The goal is
to reduce the probability that force_quiescent_state() will need to do
smp_send_reschedule(), which sends an IPI and is therefore more expensive
on most architectures.

Signed-off-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
---
 kernel/rcutree.c |   10 ++++++++++
 1 files changed, 10 insertions(+), 0 deletions(-)

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 3ec8160..e54c123 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1499,6 +1499,16 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
 	if (rdp->qs_pending) {
+
+		/*
+		 * If force_quiescent_state() coming soon and this CPU
+		 * needs a quiescent state, and this is either RCU-sched
+		 * or RCU-bh, force a local reschedule.
+		 */
+		if (!rdp->preemptable &&
+		    ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs) - 1,
+				 jiffies))
+			set_need_resched();
 		rdp->n_rp_qs_pending++;
 		return 1;
 	}
-- 
1.7.0

[PATCH tip/core/rcu 02/23] rcu: make dead code really dead

[Paul E. McKenney]

From: Lai Jiangshan <laijs@cn.fujitsu.com>

cleanup: make dead code really dead

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcutree.c |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index e54c123..6042fb8 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1236,11 +1236,11 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 		break; /* grace period idle or initializing, ignore. */
 
 	case RCU_SAVE_DYNTICK:
-
-		raw_spin_unlock(&rnp->lock);  /* irqs remain disabled */
 		if (RCU_SIGNAL_INIT != RCU_SAVE_DYNTICK)
 			break; /* So gcc recognizes the dead code. */
 
+		raw_spin_unlock(&rnp->lock);  /* irqs remain disabled */
+
 		/* Record dyntick-idle state. */
 		force_qs_rnp(rsp, dyntick_save_progress_counter);
 		raw_spin_lock(&rnp->lock);  /* irqs already disabled */
-- 
1.7.0

[PATCH tip/core/rcu 03/23] rcu: move some code from macro to function

[Paul E. McKenney]

From: Lai Jiangshan <laijs@cn.fujitsu.com>

Shrink the RCU_INIT_FLAVOR() macro by moving all but the initialization
of the ->rda[] array to rcu_init_one().  The call to rcu_init_one()
can then be moved to the end of the RCU_INIT_FLAVOR() macro, which is
required because rcu_boot_init_percpu_data(), which is now called from
rcu_init_one(), depends on the initialization of the ->rda[] array.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcutree.c |   18 +++++++++---------
 1 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 6042fb8..86bb949 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1859,6 +1859,14 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 			INIT_LIST_HEAD(&rnp->blocked_tasks[3]);
 		}
 	}
+
+	rnp = rsp->level[NUM_RCU_LVLS - 1];
+	for_each_possible_cpu(i) {
+		if (i > rnp->grphi)
+			rnp++;
+		rsp->rda[i]->mynode = rnp;
+		rcu_boot_init_percpu_data(i, rsp);
+	}
 }
 
 /*
@@ -1869,19 +1877,11 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 #define RCU_INIT_FLAVOR(rsp, rcu_data) \
 do { \
 	int i; \
-	int j; \
-	struct rcu_node *rnp; \
 	\
-	rcu_init_one(rsp); \
-	rnp = (rsp)->level[NUM_RCU_LVLS - 1]; \
-	j = 0; \
 	for_each_possible_cpu(i) { \
-		if (i > rnp[j].grphi) \
-			j++; \
-		per_cpu(rcu_data, i).mynode = &rnp[j]; \
 		(rsp)->rda[i] = &per_cpu(rcu_data, i); \
-		rcu_boot_init_percpu_data(i, rsp); \
 	} \
+	rcu_init_one(rsp); \
 } while (0)
 
 void __init rcu_init(void)
-- 
1.7.0

[PATCH tip/core/rcu 04/23] rcu: ignore offline CPUs in last non-dyntick-idle CPU check

[Paul E. McKenney]

From: Lai Jiangshan <laijs@cn.fujitsu.com>

Offline CPUs are not in nohz_cpu_mask, but can be ignored when checking
for the last non-dyntick-idle CPU.  This patch therefore only checks
online CPUs for not being dyntick idle, allowing fast entry into
full-system dyntick-idle state even when there are some offline CPUs.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcutree_plugin.h |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 79b53bd..687c4e9 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -1016,7 +1016,7 @@ int rcu_needs_cpu(int cpu)
 
 	/* Don't bother unless we are the last non-dyntick-idle CPU. */
 	for_each_cpu_not(thatcpu, nohz_cpu_mask)
-		if (thatcpu != cpu) {
+		if (cpu_online(thatcpu) && thatcpu != cpu) {
 			per_cpu(rcu_dyntick_drain, cpu) = 0;
 			per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
 			return rcu_needs_cpu_quick_check(cpu);
-- 
1.7.0

[PATCH tip/core/rcu 05/23] rcu: Fix bogus CONFIG_PROVE_LOCKING in comments to reflect reality.

[Paul E. McKenney]

It is CONFIG_DEBUG_LOCK_ALLOC rather than CONFIG_PROVE_LOCKING, so fix it.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h |   15 ++++++++-------
 include/linux/srcu.h     |    4 ++--
 2 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 07db2fe..40854c6 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -106,8 +106,8 @@ extern int debug_lockdep_rcu_enabled(void);
 /**
  * rcu_read_lock_held - might we be in RCU read-side critical section?
  *
- * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in
- * an RCU read-side critical section.  In absence of CONFIG_PROVE_LOCKING,
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU
+ * read-side critical section.  In absence of CONFIG_DEBUG_LOCK_ALLOC,
  * this assumes we are in an RCU read-side critical section unless it can
  * prove otherwise.
  *
@@ -129,11 +129,12 @@ extern int rcu_read_lock_bh_held(void);
 /**
  * rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section?
  *
- * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in an
- * RCU-sched read-side critical section.  In absence of CONFIG_PROVE_LOCKING,
- * this assumes we are in an RCU-sched read-side critical section unless it
- * can prove otherwise.  Note that disabling of preemption (including
- * disabling irqs) counts as an RCU-sched read-side critical section.
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an
+ * RCU-sched read-side critical section.  In absence of
+ * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
+ * critical section unless it can prove otherwise.  Note that disabling
+ * of preemption (including disabling irqs) counts as an RCU-sched
+ * read-side critical section.
  *
  * Check rcu_scheduler_active to prevent false positives during boot.
  */
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 4d5ecb2..9c01f10 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -84,8 +84,8 @@ long srcu_batches_completed(struct srcu_struct *sp);
 /**
  * srcu_read_lock_held - might we be in SRCU read-side critical section?
  *
- * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in
- * an SRCU read-side critical section.  In absence of CONFIG_PROVE_LOCKING,
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU
+ * read-side critical section.  In absence of CONFIG_DEBUG_LOCK_ALLOC,
  * this assumes we are in an SRCU read-side critical section unless it can
  * prove otherwise.
  */
-- 
1.7.0

[PATCH tip/core/rcu 06/23] rcu: fix now-bogus rcu_scheduler_active comments.

[Paul E. McKenney]

The rcu_scheduler_active check has been wrapped into the new
debug_lockdep_rcu_enabled() function, so update the comments to
reflect this new reality.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h |    6 ++++--
 1 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 40854c6..07c8591 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -111,7 +111,8 @@ extern int debug_lockdep_rcu_enabled(void);
  * this assumes we are in an RCU read-side critical section unless it can
  * prove otherwise.
  *
- * Check rcu_scheduler_active to prevent false positives during boot.
+ * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
+ * and while lockdep is disabled.
  */
 static inline int rcu_read_lock_held(void)
 {
@@ -136,7 +137,8 @@ extern int rcu_read_lock_bh_held(void);
  * of preemption (including disabling irqs) counts as an RCU-sched
  * read-side critical section.
  *
- * Check rcu_scheduler_active to prevent false positives during boot.
+ * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
+ * and while lockdep is disabled.
  */
 #ifdef CONFIG_PREEMPT
 static inline int rcu_read_lock_sched_held(void)
-- 
1.7.0

[PATCH tip/core/rcu 07/23] rcu: shrink rcutiny by making synchronize_rcu_bh() be inline

[Paul E. McKenney]

Because synchronize_rcu_bh() is identical to synchronize_sched(),
make the former a static inline invoking the latter, saving the
overhead of an EXPORT_SYMBOL_GPL() and the duplicate code.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h |    2 --
 include/linux/rcutiny.h  |   12 +++++++++++-
 include/linux/rcutree.h  |    2 ++
 kernel/rcutiny.c         |    9 ++-------
 4 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 07c8591..08a04b1 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -56,8 +56,6 @@ struct rcu_head {
 };
 
 /* Exported common interfaces */
-extern void synchronize_rcu_bh(void);
-extern void synchronize_sched(void);
 extern void rcu_barrier(void);
 extern void rcu_barrier_bh(void);
 extern void rcu_barrier_sched(void);
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index a519587..bbeb55b 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -74,7 +74,17 @@ static inline void rcu_sched_force_quiescent_state(void)
 {
 }
 
-#define synchronize_rcu synchronize_sched
+extern void synchronize_sched(void);
+
+static inline void synchronize_rcu(void)
+{
+	synchronize_sched();
+}
+
+static inline void synchronize_rcu_bh(void)
+{
+	synchronize_sched();
+}
 
 static inline void synchronize_rcu_expedited(void)
 {
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 42cc3a0..7484fe6 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -86,6 +86,8 @@ static inline void __rcu_read_unlock_bh(void)
 
 extern void call_rcu_sched(struct rcu_head *head,
 			   void (*func)(struct rcu_head *rcu));
+extern void synchronize_rcu_bh(void);
+extern void synchronize_sched(void);
 extern void synchronize_rcu_expedited(void);
 
 static inline void synchronize_rcu_bh_expedited(void)
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 9f6d9ff..272c6d2 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -187,7 +187,8 @@ static void rcu_process_callbacks(struct softirq_action *unused)
  *
  * Cool, huh?  (Due to Josh Triplett.)
  *
- * But we want to make this a static inline later.
+ * But we want to make this a static inline later.  The cond_resched()
+ * currently makes this problematic.
  */
 void synchronize_sched(void)
 {
@@ -195,12 +196,6 @@ void synchronize_sched(void)
 }
 EXPORT_SYMBOL_GPL(synchronize_sched);
 
-void synchronize_rcu_bh(void)
-{
-	synchronize_sched();
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
-
 /*
  * Helper function for call_rcu() and call_rcu_bh().
  */
-- 
1.7.0

[PATCH tip/core/rcu 08/23] rcu: rename rcutiny rcu_ctrlblk to rcu_sched_ctrlblk

[Paul E. McKenney]

Make naming line up in preparation for CONFIG_TINY_PREEMPT_RCU.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcutiny.c |   13 +++++++------
 1 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 272c6d2..d9f8a62 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -44,9 +44,9 @@ struct rcu_ctrlblk {
 };
 
 /* Definition for rcupdate control block. */
-static struct rcu_ctrlblk rcu_ctrlblk = {
-	.donetail	= &rcu_ctrlblk.rcucblist,
-	.curtail	= &rcu_ctrlblk.rcucblist,
+static struct rcu_ctrlblk rcu_sched_ctrlblk = {
+	.donetail	= &rcu_sched_ctrlblk.rcucblist,
+	.curtail	= &rcu_sched_ctrlblk.rcucblist,
 };
 
 static struct rcu_ctrlblk rcu_bh_ctrlblk = {
@@ -108,7 +108,8 @@ static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
  */
 void rcu_sched_qs(int cpu)
 {
-	if (rcu_qsctr_help(&rcu_ctrlblk) + rcu_qsctr_help(&rcu_bh_ctrlblk))
+	if (rcu_qsctr_help(&rcu_sched_ctrlblk) +
+	    rcu_qsctr_help(&rcu_bh_ctrlblk))
 		raise_softirq(RCU_SOFTIRQ);
 }
 
@@ -173,7 +174,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
  */
 static void rcu_process_callbacks(struct softirq_action *unused)
 {
-	__rcu_process_callbacks(&rcu_ctrlblk);
+	__rcu_process_callbacks(&rcu_sched_ctrlblk);
 	__rcu_process_callbacks(&rcu_bh_ctrlblk);
 }
 
@@ -221,7 +222,7 @@ static void __call_rcu(struct rcu_head *head,
  */
 void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 {
-	__call_rcu(head, func, &rcu_ctrlblk);
+	__call_rcu(head, func, &rcu_sched_ctrlblk);
 }
 EXPORT_SYMBOL_GPL(call_rcu);
 
-- 
1.7.0

[PATCH tip/core/rcu 09/23] rcu: refactor RCU's context-switch handling

[Paul E. McKenney]

The addition of preemptible RCU to treercu resulted in a bit of
confusion and inefficiency surrounding the handling of context switches
for RCU-sched and for RCU-preempt.  For RCU-sched, a context switch
is a quiescent state, pure and simple, just like it always has been.
For RCU-preempt, a context switch is in no way a quiescent state, but
special handling is required when a task blocks in an RCU read-side
critical section.

However, the callout from the scheduler and the outer loop in ksoftirqd
still calls something named rcu_sched_qs(), whose name is no longer
accurate.  Furthermore, when rcu_check_callbacks() notes an RCU-sched
quiescent state, it ends up unnecessarily (though harmlessly, aside
from the performance hit) enqueuing the current task if it happens to
be running in an RCU-preempt read-side critical section.  This not only
increases the maximum latency of scheduler_tick(), it also needlessly
increases the overhead of the next outermost rcu_read_unlock() invocation.

This patch addresses this situation by separating the notion of RCU's
context-switch handling from that of RCU-sched's quiescent states.
The context-switch handling is covered by rcu_note_context_switch() in
general and by rcu_preempt_note_context_switch() for preemptible RCU.
This permits rcu_sched_qs() to handle quiescent states and only quiescent
states.  It also reduces the maximum latency of scheduler_tick(), though
probably by much less than a microsecond.  Finally, it means that tasks
within preemptible-RCU read-side critical sections avoid incurring the
overhead of queuing unless there really is a context switch.

Suggested-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcutiny.h |    4 ++++
 include/linux/rcutree.h |    1 +
 kernel/rcutree.c        |   17 ++++++++++++-----
 kernel/rcutree_plugin.h |   11 +++++++----
 kernel/sched.c          |    2 +-
 kernel/softirq.c        |    2 +-
 6 files changed, 26 insertions(+), 11 deletions(-)

diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index bbeb55b..ff22b97 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -29,6 +29,10 @@
 
 void rcu_sched_qs(int cpu);
 void rcu_bh_qs(int cpu);
+static inline void rcu_note_context_switch(int cpu)
+{
+	rcu_sched_qs(cpu);
+}
 
 #define __rcu_read_lock()	preempt_disable()
 #define __rcu_read_unlock()	preempt_enable()
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 7484fe6..b9f7460 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -34,6 +34,7 @@ struct notifier_block;
 
 extern void rcu_sched_qs(int cpu);
 extern void rcu_bh_qs(int cpu);
+extern void rcu_note_context_switch(int cpu);
 extern int rcu_needs_cpu(int cpu);
 extern int rcu_expedited_torture_stats(char *page);
 
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 86bb949..e336313 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -97,25 +97,32 @@ static int rcu_gp_in_progress(struct rcu_state *rsp)
  */
 void rcu_sched_qs(int cpu)
 {
-	struct rcu_data *rdp;
+	struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu);
 
-	rdp = &per_cpu(rcu_sched_data, cpu);
 	rdp->passed_quiesc_completed = rdp->gpnum - 1;
 	barrier();
 	rdp->passed_quiesc = 1;
-	rcu_preempt_note_context_switch(cpu);
 }
 
 void rcu_bh_qs(int cpu)
 {
-	struct rcu_data *rdp;
+	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
 
-	rdp = &per_cpu(rcu_bh_data, cpu);
 	rdp->passed_quiesc_completed = rdp->gpnum - 1;
 	barrier();
 	rdp->passed_quiesc = 1;
 }
 
+/*
+ * Note a context switch.  This is a quiescent state for RCU-sched,
+ * and requires special handling for preemptible RCU.
+ */
+void rcu_note_context_switch(int cpu)
+{
+	rcu_sched_qs(cpu);
+	rcu_preempt_note_context_switch(cpu);
+}
+
 #ifdef CONFIG_NO_HZ
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 	.dynticks_nesting = 1,
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 687c4e9..f9bc83a 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -75,13 +75,19 @@ EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
  * that this just means that the task currently running on the CPU is
  * not in a quiescent state.  There might be any number of tasks blocked
  * while in an RCU read-side critical section.
+ *
+ * Unlike the other rcu_*_qs() functions, callers to this function
+ * must disable irqs in order to protect the assignment to
+ * ->rcu_read_unlock_special.
  */
 static void rcu_preempt_qs(int cpu)
 {
 	struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
+
 	rdp->passed_quiesc_completed = rdp->gpnum - 1;
 	barrier();
 	rdp->passed_quiesc = 1;
+	current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
 }
 
 /*
@@ -144,9 +150,8 @@ static void rcu_preempt_note_context_switch(int cpu)
 	 * grace period, then the fact that the task has been enqueued
 	 * means that we continue to block the current grace period.
 	 */
-	rcu_preempt_qs(cpu);
 	local_irq_save(flags);
-	t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+	rcu_preempt_qs(cpu);
 	local_irq_restore(flags);
 }
 
@@ -236,7 +241,6 @@ static void rcu_read_unlock_special(struct task_struct *t)
 	 */
 	special = t->rcu_read_unlock_special;
 	if (special & RCU_READ_UNLOCK_NEED_QS) {
-		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
 		rcu_preempt_qs(smp_processor_id());
 	}
 
@@ -473,7 +477,6 @@ static void rcu_preempt_check_callbacks(int cpu)
 	struct task_struct *t = current;
 
 	if (t->rcu_read_lock_nesting == 0) {
-		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
 		rcu_preempt_qs(cpu);
 		return;
 	}
diff --git a/kernel/sched.c b/kernel/sched.c
index 6af210a..f8ca2c0 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3696,7 +3696,7 @@ need_resched:
 	preempt_disable();
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
-	rcu_sched_qs(cpu);
+	rcu_note_context_switch(cpu);
 	prev = rq->curr;
 	switch_count = &prev->nivcsw;
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 7c1a67e..0db913a 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -716,7 +716,7 @@ static int run_ksoftirqd(void * __bind_cpu)
 			preempt_enable_no_resched();
 			cond_resched();
 			preempt_disable();
-			rcu_sched_qs((long)__bind_cpu);
+			rcu_note_context_switch((long)__bind_cpu);
 		}
 		preempt_enable();
 		set_current_state(TASK_INTERRUPTIBLE);
-- 
1.7.0

[PATCH tip/core/rcu 10/23] rcu: slim down rcutiny by removing rcu_scheduler_active and friends

[Paul E. McKenney]

TINY_RCU does not need rcu_scheduler_active unless CONFIG_DEBUG_LOCK_ALLOC.
So conditionally compile rcu_scheduler_active in order to slim down
rcutiny a bit more.  Also gets rid of an EXPORT_SYMBOL_GPL, which is
responsible for most of the slimming.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h |    4 +---
 include/linux/rcutiny.h  |   13 +++++++++++++
 include/linux/rcutree.h  |    3 +++
 kernel/rcupdate.c        |   19 -------------------
 kernel/rcutiny.c         |    7 +++++++
 kernel/rcutiny_plugin.h  |   39 +++++++++++++++++++++++++++++++++++++++
 kernel/rcutree.c         |   19 +++++++++++++++++++
 7 files changed, 82 insertions(+), 22 deletions(-)
 create mode 100644 kernel/rcutiny_plugin.h

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 08a04b1..6e6f851 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -64,8 +64,6 @@ extern int sched_expedited_torture_stats(char *page);
 
 /* Internal to kernel */
 extern void rcu_init(void);
-extern int rcu_scheduler_active;
-extern void rcu_scheduler_starting(void);
 
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
 #include <linux/rcutree.h>
@@ -178,7 +176,7 @@ static inline int rcu_read_lock_bh_held(void)
 #ifdef CONFIG_PREEMPT
 static inline int rcu_read_lock_sched_held(void)
 {
-	return !rcu_scheduler_active || preempt_count() != 0 || irqs_disabled();
+	return preempt_count() != 0 || irqs_disabled();
 }
 #else /* #ifdef CONFIG_PREEMPT */
 static inline int rcu_read_lock_sched_held(void)
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index ff22b97..14e5a76 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -128,4 +128,17 @@ static inline int rcu_preempt_depth(void)
 	return 0;
 }
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+extern int rcu_scheduler_active __read_mostly;
+extern void rcu_scheduler_starting(void);
+
+#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+static inline void rcu_scheduler_starting(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
 #endif /* __LINUX_RCUTINY_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index b9f7460..4828205 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -123,4 +123,7 @@ static inline int rcu_blocking_is_gp(void)
 	return num_online_cpus() == 1;
 }
 
+extern void rcu_scheduler_starting(void);
+extern int rcu_scheduler_active __read_mostly;
+
 #endif /* __LINUX_RCUTREE_H */
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 03a7ea1..689281e 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -44,7 +44,6 @@
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
-#include <linux/kernel_stat.h>
 #include <linux/hardirq.h>
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -64,9 +63,6 @@ struct lockdep_map rcu_sched_lock_map =
 EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
 #endif
 
-int rcu_scheduler_active __read_mostly;
-EXPORT_SYMBOL_GPL(rcu_scheduler_active);
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 int debug_lockdep_rcu_enabled(void)
@@ -97,21 +93,6 @@ EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 /*
- * This function is invoked towards the end of the scheduler's initialization
- * process.  Before this is called, the idle task might contain
- * RCU read-side critical sections (during which time, this idle
- * task is booting the system).  After this function is called, the
- * idle tasks are prohibited from containing RCU read-side critical
- * sections.
- */
-void rcu_scheduler_starting(void)
-{
-	WARN_ON(num_online_cpus() != 1);
-	WARN_ON(nr_context_switches() > 0);
-	rcu_scheduler_active = 1;
-}
-
-/*
  * Awaken the corresponding synchronize_rcu() instance now that a
  * grace period has elapsed.
  */
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index d9f8a62..b1804ff 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -54,6 +54,11 @@ static struct rcu_ctrlblk rcu_bh_ctrlblk = {
 	.curtail	= &rcu_bh_ctrlblk.rcucblist,
 };
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+int rcu_scheduler_active __read_mostly;
+EXPORT_SYMBOL_GPL(rcu_scheduler_active);
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
 #ifdef CONFIG_NO_HZ
 
 static long rcu_dynticks_nesting = 1;
@@ -276,3 +281,5 @@ void __init rcu_init(void)
 {
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 }
+
+#include "rcutiny_plugin.h"
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
new file mode 100644
index 0000000..d223a92
--- /dev/null
+++ b/kernel/rcutiny_plugin.h
@@ -0,0 +1,39 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion (tree-based version)
+ * Internal non-public definitions that provide either classic
+ * or preemptable semantics.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright IBM Corporation, 2009
+ *
+ * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ */
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+#include <linux/kernel_stat.h>
+
+/*
+ * During boot, we forgive RCU lockdep issues.  After this function is
+ * invoked, we start taking RCU lockdep issues seriously.
+ */
+void rcu_scheduler_starting(void)
+{
+	WARN_ON(nr_context_switches() > 0);
+	rcu_scheduler_active = 1;
+}
+
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index e336313..3623f8e 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -46,6 +46,7 @@
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/time.h>
+#include <linux/kernel_stat.h>
 
 #include "rcutree.h"
 
@@ -80,6 +81,9 @@ DEFINE_PER_CPU(struct rcu_data, rcu_sched_data);
 struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state);
 DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
 
+int rcu_scheduler_active __read_mostly;
+EXPORT_SYMBOL_GPL(rcu_scheduler_active);
+
 /*
  * Return true if an RCU grace period is in progress.  The ACCESS_ONCE()s
  * permit this function to be invoked without holding the root rcu_node
@@ -1784,6 +1788,21 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 }
 
 /*
+ * This function is invoked towards the end of the scheduler's initialization
+ * process.  Before this is called, the idle task might contain
+ * RCU read-side critical sections (during which time, this idle
+ * task is booting the system).  After this function is called, the
+ * idle tasks are prohibited from containing RCU read-side critical
+ * sections.  This function also enables RCU lockdep checking.
+ */
+void rcu_scheduler_starting(void)
+{
+	WARN_ON(num_online_cpus() != 1);
+	WARN_ON(nr_context_switches() > 0);
+	rcu_scheduler_active = 1;
+}
+
+/*
  * Compute the per-level fanout, either using the exact fanout specified
  * or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT.
  */
-- 
1.7.0

[PATCH tip/core/rcu 11/23] rcu: enable CPU_STALL_VERBOSE by default

[Paul E. McKenney]

The CPU_STALL_VERBOSE kernel configuration parameter was added to
2.6.34 to identify any preempted/blocked tasks that were preventing
the current grace period from completing when running preemptible
RCU.  As is conventional for new configurations parameters, this
defaulted disabled.  It is now time to enable it by default.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 lib/Kconfig.debug |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 935248b..40d7be7 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -793,7 +793,7 @@ config RCU_CPU_STALL_DETECTOR
 config RCU_CPU_STALL_VERBOSE
 	bool "Print additional per-task information for RCU_CPU_STALL_DETECTOR"
 	depends on RCU_CPU_STALL_DETECTOR && TREE_PREEMPT_RCU
-	default n
+	default y
 	help
 	  This option causes RCU to printk detailed per-task information
 	  for any tasks that are stalling the current RCU grace period.
-- 
1.7.0

[PATCH tip/core/rcu 12/23] rcu: disable CPU stall warnings upon panic

[Paul E. McKenney]

The current RCU CPU stall warnings remain enabled even after a panic
occurs, which some people have found to be a bit counterproductive.
This patch therefore uses a notifier to disable stall warnings once a
panic occurs.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcutree.c |   24 ++++++++++++++++++++++++
 1 files changed, 24 insertions(+), 0 deletions(-)

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 3623f8e..595fb83 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -449,6 +449,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 
+int rcu_cpu_stall_panicking __read_mostly;
+
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
 	rsp->gp_start = jiffies;
@@ -526,6 +528,8 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 	long delta;
 	struct rcu_node *rnp;
 
+	if (rcu_cpu_stall_panicking)
+		return;
 	delta = jiffies - rsp->jiffies_stall;
 	rnp = rdp->mynode;
 	if ((rnp->qsmask & rdp->grpmask) && delta >= 0) {
@@ -540,6 +544,21 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 	}
 }
 
+static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
+{
+	rcu_cpu_stall_panicking = 1;
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block rcu_panic_block = {
+	.notifier_call = rcu_panic,
+};
+
+static void __init check_cpu_stall_init(void)
+{
+	atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
+}
+
 #else /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
@@ -550,6 +569,10 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 {
 }
 
+static void __init check_cpu_stall_init(void)
+{
+}
+
 #endif /* #else #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 /*
@@ -1934,6 +1957,7 @@ void __init rcu_init(void)
 	cpu_notifier(rcu_cpu_notify, 0);
 	for_each_online_cpu(cpu)
 		rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
+	check_cpu_stall_init();
 }
 
 #include "rcutree_plugin.h"
-- 
1.7.0

[PATCH tip/core/rcu 13/23] rcu: print boot-time console messages if RCU configs out of ordinary

[Paul E. McKenney]

Print boot-time messages if tracing is enabled, if fanout is set
to non-default values, if exact fanout is specified, if accelerated
dyntick-idle grace periods have been enabled, if RCU-lockdep is enabled,
if rcutorture has been boot-time enabled, if the CPU stall detector has
been disabled, or if four-level hierarchy has been enabled.

This is all for TREE_RCU and TREE_PREEMPT_RCU.  TINY_RCU will be handled
separately, if at all.

Suggested-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcutree.c        |    6 ------
 kernel/rcutree_plugin.h |   44 ++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 42 insertions(+), 8 deletions(-)

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 595fb83..ec6196f 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1938,12 +1938,6 @@ void __init rcu_init(void)
 	int cpu;
 
 	rcu_bootup_announce();
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-	printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-#if NUM_RCU_LVL_4 != 0
-	printk(KERN_INFO "Experimental four-level hierarchy is enabled.\n");
-#endif /* #if NUM_RCU_LVL_4 != 0 */
 	RCU_INIT_FLAVOR(&rcu_sched_state, rcu_sched_data);
 	RCU_INIT_FLAVOR(&rcu_bh_state, rcu_bh_data);
 	__rcu_init_preempt();
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index f9bc83a..0ae2339 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -26,6 +26,45 @@
 
 #include <linux/delay.h>
 
+/*
+ * Check the RCU kernel configuration parameters and print informative
+ * messages about anything out of the ordinary.  If you like #ifdef, you
+ * will love this function.
+ */
+static void __init rcu_bootup_announce_oddness(void)
+{
+#ifdef CONFIG_RCU_TRACE
+	printk(KERN_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",
+	       CONFIG_RCU_FANOUT);
+#endif
+#ifdef CONFIG_RCU_FANOUT_EXACT
+	printk(KERN_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");
+#endif
+#ifdef CONFIG_PROVE_RCU
+	printk(KERN_INFO "\tRCU lockdep checking is enabled.\n");
+#endif
+#ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE
+	printk(KERN_INFO "\tRCU torture testing starts during boot.\n");
+#endif
+#ifndef CONFIG_RCU_CPU_STALL_DETECTOR
+	printk(KERN_INFO
+	       "\tRCU-based detection of stalled CPUs is disabled.\n");
+#endif
+#ifndef CONFIG_RCU_CPU_STALL_VERBOSE
+	printk(KERN_INFO "\tVerbose stalled-CPUs detection is disabled.\n");
+#endif
+#if NUM_RCU_LVL_4 != 0
+	printk(KERN_INFO "\tExperimental four-level hierarchy is enabled.\n");
+#endif
+}
+
 #ifdef CONFIG_TREE_PREEMPT_RCU
 
 struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
@@ -38,8 +77,8 @@ static int rcu_preempted_readers_exp(struct rcu_node *rnp);
  */
 static void __init rcu_bootup_announce(void)
 {
-	printk(KERN_INFO
-	       "Experimental preemptable hierarchical RCU implementation.\n");
+	printk(KERN_INFO "Preemptable hierarchical RCU implementation.\n");
+	rcu_bootup_announce_oddness();
 }
 
 /*
@@ -757,6 +796,7 @@ void exit_rcu(void)
 static void __init rcu_bootup_announce(void)
 {
 	printk(KERN_INFO "Hierarchical RCU implementation.\n");
+	rcu_bootup_announce_oddness();
 }
 
 /*
-- 
1.7.0

[PATCH tip/core/rcu 14/23] rcu: improve RCU CPU stall-warning messages

[Paul E. McKenney]

The existing RCU CPU stall-warning messages can be confusing, especially
in the case where one CPU detects a single other stalled CPU.  In addition,
the console messages did not say which flavor of RCU detected the stall,
which can make it difficult to work out exactly what is causing the stall.
This commit improves these messages.

Requested-by: Dhaval Giani <dhaval.giani@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcutree.c |   20 +++++++++++---------
 kernel/rcutree.h |    1 +
 2 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index ec6196f..f391886 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -54,8 +54,8 @@
 
 static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
 
-#define RCU_STATE_INITIALIZER(name) { \
-	.level = { &name.node[0] }, \
+#define RCU_STATE_INITIALIZER(structname) { \
+	.level = { &structname.node[0] }, \
 	.levelcnt = { \
 		NUM_RCU_LVL_0,  /* root of hierarchy. */ \
 		NUM_RCU_LVL_1, \
@@ -66,13 +66,14 @@ static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
 	.signaled = RCU_GP_IDLE, \
 	.gpnum = -300, \
 	.completed = -300, \
-	.onofflock = __RAW_SPIN_LOCK_UNLOCKED(&name.onofflock), \
+	.onofflock = __RAW_SPIN_LOCK_UNLOCKED(&structname.onofflock), \
 	.orphan_cbs_list = NULL, \
-	.orphan_cbs_tail = &name.orphan_cbs_list, \
+	.orphan_cbs_tail = &structname.orphan_cbs_list, \
 	.orphan_qlen = 0, \
-	.fqslock = __RAW_SPIN_LOCK_UNLOCKED(&name.fqslock), \
+	.fqslock = __RAW_SPIN_LOCK_UNLOCKED(&structname.fqslock), \
 	.n_force_qs = 0, \
 	.n_force_qs_ngp = 0, \
+	.name = #structname, \
 }
 
 struct rcu_state rcu_sched_state = RCU_STATE_INITIALIZER(rcu_sched_state);
@@ -483,7 +484,8 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 
 	/* OK, time to rat on our buddy... */
 
-	printk(KERN_ERR "INFO: RCU detected CPU stalls:");
+	printk(KERN_ERR "INFO: %s detected stalls on CPUs/tasks: {",
+	       rsp->name);
 	rcu_for_each_leaf_node(rsp, rnp) {
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		rcu_print_task_stall(rnp);
@@ -494,7 +496,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 			if (rnp->qsmask & (1UL << cpu))
 				printk(" %d", rnp->grplo + cpu);
 	}
-	printk(" (detected by %d, t=%ld jiffies)\n",
+	printk("} (detected by %d, t=%ld jiffies)\n",
 	       smp_processor_id(), (long)(jiffies - rsp->gp_start));
 	trigger_all_cpu_backtrace();
 
@@ -510,8 +512,8 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	unsigned long flags;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
-	printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu jiffies)\n",
-			smp_processor_id(), jiffies - rsp->gp_start);
+	printk(KERN_ERR "INFO: %s detected stall on CPU %d (t=%lu jiffies)\n",
+	       rsp->name, smp_processor_id(), jiffies - rsp->gp_start);
 	trigger_all_cpu_backtrace();
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 4a525a3..11f1711 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -326,6 +326,7 @@ struct rcu_state {
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+	char *name;				/* Name of structure. */
 };
 
 /* Return values for rcu_preempt_offline_tasks(). */
-- 
1.7.0

[PATCH tip/core/rcu 15/23] rcu: permit discontiguous cpu_possible_mask CPU numbering

[Paul E. McKenney]

TREE_RCU assumes that CPU numbering is contiguous, but some users need
large holes in the numbering to better map to hardware layout.  This patch
makes TREE_RCU (and TREE_PREEMPT_RCU) tolerate large holes in the CPU
numbering.  However, NR_CPUS must still be greater than the largest
CPU number.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcutree.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index f391886..c60fd74 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1913,7 +1913,7 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 
 	rnp = rsp->level[NUM_RCU_LVLS - 1];
 	for_each_possible_cpu(i) {
-		if (i > rnp->grphi)
+		while (i > rnp->grphi)
 			rnp++;
 		rsp->rda[i]->mynode = rnp;
 		rcu_boot_init_percpu_data(i, rsp);
-- 
1.7.0

[PATCH tip/core/rcu 16/23] rcu: v2: reduce the number of spurious RCU_SOFTIRQ invocations

[Paul E. McKenney]

Lai Jiangshan noted that up to 10% of the RCU_SOFTIRQ are spurious, and
traced this down to the fact that the current grace-period machinery
will uselessly raise RCU_SOFTIRQ when a given CPU needs to go through
a quiescent state, but has not yet done so.  In this situation, there
might well be nothing that RCU_SOFTIRQ can do, and the overhead can be
worth worrying about in the ksoftirqd case.  This patch therefore avoids
raising RCU_SOFTIRQ in this situation.

Changes since v1 (http://lkml.org/lkml/2010/3/30/122 from Lai Jiangshan):

o	Omit the rcu_qs_pending() prechecks, as they aren't that
	much less expensive than the quiescent-state checks.

o	Merge with the set_need_resched() patch that reduces IPIs.

o	Add the new n_rp_report_qs field to the rcu_pending tracing output.

o	Update the tracing documentation accordingly.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 Documentation/RCU/trace.txt |   35 +++++++++++++++++++----------------
 kernel/rcutree.c            |   11 ++++++-----
 kernel/rcutree.h            |    1 +
 kernel/rcutree_trace.c      |    4 +++-
 4 files changed, 29 insertions(+), 22 deletions(-)

diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 8608fd8..efd8cc9 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -256,23 +256,23 @@ o	Each element of the form "1/1 0:127 ^0" represents one struct
 The output of "cat rcu/rcu_pending" looks as follows:
 
 rcu_sched:
-  0 np=255892 qsp=53936 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
-  1 np=261224 qsp=54638 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
-  2 np=237496 qsp=49664 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
-  3 np=236249 qsp=48766 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
-  4 np=221310 qsp=46850 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
-  5 np=237332 qsp=48449 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
-  6 np=219995 qsp=46718 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
-  7 np=249893 qsp=49390 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
+  0 np=255892 qsp=53936 rpq=85 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
+  1 np=261224 qsp=54638 rpq=33 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
+  2 np=237496 qsp=49664 rpq=23 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
+  3 np=236249 qsp=48766 rpq=98 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
+  4 np=221310 qsp=46850 rpq=7 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
+  5 np=237332 qsp=48449 rpq=9 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
+  6 np=219995 qsp=46718 rpq=12 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
+  7 np=249893 qsp=49390 rpq=42 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
 rcu_bh:
-  0 np=146741 qsp=1419 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
-  1 np=155792 qsp=12597 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
-  2 np=136629 qsp=18680 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
-  3 np=137723 qsp=2843 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
-  4 np=123110 qsp=12433 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
-  5 np=137456 qsp=4210 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
-  6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
-  7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
+  0 np=146741 qsp=1419 rpq=6 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
+  1 np=155792 qsp=12597 rpq=3 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
+  2 np=136629 qsp=18680 rpq=1 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
+  3 np=137723 qsp=2843 rpq=0 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
+  4 np=123110 qsp=12433 rpq=0 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
+  5 np=137456 qsp=4210 rpq=1 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
+  6 np=120834 qsp=9902 rpq=2 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
+  7 np=144888 qsp=26336 rpq=0 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
 
 As always, this is once again split into "rcu_sched" and "rcu_bh"
 portions, with CONFIG_TREE_PREEMPT_RCU kernels having an additional
@@ -284,6 +284,9 @@ o	"np" is the number of times that __rcu_pending() has been invoked
 o	"qsp" is the number of times that the RCU was waiting for a
 	quiescent state from this CPU.
 
+o	"rpq" is the number of times that the CPU had passed through
+	a quiescent state, but not yet reported it to RCU.
+
 o	"cbr" is the number of times that this CPU had RCU callbacks
 	that had passed through a grace period, and were thus ready
 	to be invoked.
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index c60fd74..ba69969 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1161,8 +1161,6 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
  */
 void rcu_check_callbacks(int cpu, int user)
 {
-	if (!rcu_pending(cpu))
-		return; /* if nothing for RCU to do. */
 	if (user ||
 	    (idle_cpu(cpu) && rcu_scheduler_active &&
 	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
@@ -1194,7 +1192,8 @@ void rcu_check_callbacks(int cpu, int user)
 		rcu_bh_qs(cpu);
 	}
 	rcu_preempt_check_callbacks(cpu);
-	raise_softirq(RCU_SOFTIRQ);
+	if (rcu_pending(cpu))
+		raise_softirq(RCU_SOFTIRQ);
 }
 
 #ifdef CONFIG_SMP
@@ -1534,18 +1533,20 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 	check_cpu_stall(rsp, rdp);
 
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
-	if (rdp->qs_pending) {
+	if (rdp->qs_pending && !rdp->passed_quiesc) {
 
 		/*
 		 * If force_quiescent_state() coming soon and this CPU
 		 * needs a quiescent state, and this is either RCU-sched
 		 * or RCU-bh, force a local reschedule.
 		 */
+		rdp->n_rp_qs_pending++;
 		if (!rdp->preemptable &&
 		    ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs) - 1,
 				 jiffies))
 			set_need_resched();
-		rdp->n_rp_qs_pending++;
+	} else if (rdp->qs_pending && rdp->passed_quiesc) {
+		rdp->n_rp_report_qs++;
 		return 1;
 	}
 
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 11f1711..14c040b 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -223,6 +223,7 @@ struct rcu_data {
 	/* 5) __rcu_pending() statistics. */
 	unsigned long n_rcu_pending;	/* rcu_pending() calls since boot. */
 	unsigned long n_rp_qs_pending;
+	unsigned long n_rp_report_qs;
 	unsigned long n_rp_cb_ready;
 	unsigned long n_rp_cpu_needs_gp;
 	unsigned long n_rp_gp_completed;
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index d45db2e..36c95b4 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -241,11 +241,13 @@ static const struct file_operations rcugp_fops = {
 static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp)
 {
 	seq_printf(m, "%3d%cnp=%ld "
-		   "qsp=%ld cbr=%ld cng=%ld gpc=%ld gps=%ld nf=%ld nn=%ld\n",
+		   "qsp=%ld rpq=%ld cbr=%ld cng=%ld "
+		   "gpc=%ld gps=%ld nf=%ld nn=%ld\n",
 		   rdp->cpu,
 		   cpu_is_offline(rdp->cpu) ? '!' : ' ',
 		   rdp->n_rcu_pending,
 		   rdp->n_rp_qs_pending,
+		   rdp->n_rp_report_qs,
 		   rdp->n_rp_cb_ready,
 		   rdp->n_rp_cpu_needs_gp,
 		   rdp->n_rp_gp_completed,
-- 
1.7.0

[PATCH tip/core/rcu 17/23] rcu: improve the RCU CPU-stall warning documentation

[Paul E. McKenney]

The existing Documentation/RCU/stallwarn.txt has proven unhelpful, so
rework it a bit.  In particular, show how to interpret the stall-warning
messages.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 Documentation/RCU/stallwarn.txt |   94 +++++++++++++++++++++++++++++---------
 1 files changed, 71 insertions(+), 23 deletions(-)

diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 1423d25..44c6dcc 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -3,35 +3,79 @@ Using RCU's CPU Stall Detector
 The CONFIG_RCU_CPU_STALL_DETECTOR kernel config parameter enables
 RCU's CPU stall detector, which detects conditions that unduly delay
 RCU grace periods.  The stall detector's idea of what constitutes
-"unduly delayed" is controlled by a pair of C preprocessor macros:
+"unduly delayed" is controlled by a set of C preprocessor macros:
 
 RCU_SECONDS_TILL_STALL_CHECK
 
 	This macro defines the period of time that RCU will wait from
 	the beginning of a grace period until it issues an RCU CPU
-	stall warning.	It is normally ten seconds.
+	stall warning.	This time period is normally ten seconds.
 
 RCU_SECONDS_TILL_STALL_RECHECK
 
 	This macro defines the period of time that RCU will wait after
-	issuing a stall warning until it issues another stall warning.
-	It is normally set to thirty seconds.
+	issuing a stall warning until it issues another stall warning
+	for the same stall.  This time period is normally set to thirty
+	seconds.
 
 RCU_STALL_RAT_DELAY
 
-	The CPU stall detector tries to make the offending CPU rat on itself,
-	as this often gives better-quality stack traces.  However, if
-	the offending CPU does not detect its own stall in the number
-	of jiffies specified by RCU_STALL_RAT_DELAY, then other CPUs will
-	complain.  This is normally set to two jiffies.
+	The CPU stall detector tries to make the offending CPU print its
+	own warnings, as this often gives better-quality stack traces.
+	However, if the offending CPU does not detect its own stall in
+	the number of jiffies specified by RCU_STALL_RAT_DELAY, then
+	some other CPU will complain.  This delay is normally set to
+	two jiffies.
 
-The following problems can result in an RCU CPU stall warning:
+When a CPU detects that it is stalling, it will print a message similar
+to the following:
+
+INFO: rcu_sched_state detected stall on CPU 5 (t=2500 jiffies)
+
+This message indicates that CPU 5 detected that it was causing a stall,
+and that the stall was affecting RCU-sched.  This message will normally be
+followed by a stack dump of the offending CPU.  On TREE_RCU kernel builds,
+RCU and RCU-sched are implemented by the same underlying mechanism,
+while on TREE_PREEMPT_RCU kernel builds, RCU is instead implemented
+by rcu_preempt_state.
+
+On the other hand, if the offending CPU fails to print out a stall-warning
+message quickly enough, some other CPU will print a message similar to
+the following:
+
+INFO: rcu_bh_state detected stalls on CPUs/tasks: { 3 5 } (detected by 2, 2502 jiffies)
+
+This message indicates that CPU 2 detected that CPUs 3 and 5 were both
+causing stalls, and that the stall was affecting RCU-bh.  This message
+will normally be followed by stack dumps for each CPU.  Please note that
+TREE_PREEMPT_RCU builds can be stalled by tasks as well as by CPUs,
+and that the tasks will be indicated by PID, for example, "P3421".
+It is even possible for a rcu_preempt_state stall to be caused by both
+CPUs -and- tasks, in which case the offending CPUs and tasks will all
+be called out in the list.
+
+Finally, if the grace period ends just as the stall warning starts
+printing, there will be a spurious stall-warning message:
+
+INFO: rcu_bh_state detected stalls on CPUs/tasks: { } (detected by 4, 2502 jiffies)
+
+This is rare, but does happen from time to time in real life.
+
+So your kernel printed an RCU CPU stall warning.  The next question is
+"What caused it?"  The following problems can result in RCU CPU stall
+warnings:
 
 o	A CPU looping in an RCU read-side critical section.
 	
-o	A CPU looping with interrupts disabled.
+o	A CPU looping with interrupts disabled.  This condition can
+	result in RCU-sched and RCU-bh stalls.
 
-o	A CPU looping with preemption disabled.
+o	A CPU looping with preemption disabled.  This condition can
+	result in RCU-sched stalls and, if ksoftirqd is in use, RCU-bh
+	stalls.
+
+o	A CPU looping with bottom halves disabled.  This condition can
+	result in RCU-sched and RCU-bh stalls.
 
 o	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
 	without invoking schedule().
@@ -39,20 +83,24 @@ o	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
 o	A bug in the RCU implementation.
 
 o	A hardware failure.  This is quite unlikely, but has occurred
-	at least once in a former life.  A CPU failed in a running system,
+	at least once in real life.  A CPU failed in a running system,
 	becoming unresponsive, but not causing an immediate crash.
 	This resulted in a series of RCU CPU stall warnings, eventually
 	leading the realization that the CPU had failed.
 
-The RCU, RCU-sched, and RCU-bh implementations have CPU stall warning.
-SRCU does not do so directly, but its calls to synchronize_sched() will
-result in RCU-sched detecting any CPU stalls that might be occurring.
-
-To diagnose the cause of the stall, inspect the stack traces.  The offending
-function will usually be near the top of the stack.  If you have a series
-of stall warnings from a single extended stall, comparing the stack traces
-can often help determine where the stall is occurring, which will usually
-be in the function nearest the top of the stack that stays the same from
-trace to trace.
+The RCU, RCU-sched, and RCU-bh implementations have CPU stall
+warning.  SRCU does not have its own CPU stall warnings, but its
+calls to synchronize_sched() will result in RCU-sched detecting
+RCU-sched-related CPU stalls.  Please note that RCU only detects
+CPU stalls when there is a grace period in progress.  No grace period,
+no CPU stall warnings.
+
+To diagnose the cause of the stall, inspect the stack traces.
+The offending function will usually be near the top of the stack.
+If you have a series of stall warnings from a single extended stall,
+comparing the stack traces can often help determine where the stall
+is occurring, which will usually be in the function nearest the top of
+that portion of the stack which remains the same from trace to trace.
+If you can reliably trigger the stall, ftrace can be quite helpful.
 
 RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE.
-- 
1.7.0

[PATCH tip/core/rcu 18/23] Debugobjects transition check

[Paul E. McKenney]

From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>

Implement a basic state machine checker in the debugobjects.

This state machine checker detects races and inconsistencies within the "active"
life of a debugobject. The checker only keeps track of the current state; all
the state machine logic is kept at the object instance level.

The checker works by adding a supplementary "unsigned int astate" field to the
debug_obj structure. It keeps track of the current "active state" of the object.

The only constraints that are imposed on the states by the debugobjects system
is that:

- activation of an object sets the current active state to 0,
- deactivation of an object expects the current active state to be 0.

For the rest of the states, the state mapping is determined by the specific
object instance. Therefore, the logic keeping track of the state machine is
within the specialized instance, without any need to know about it at the
debugobject level.

The current object active state is changed by calling:

debug_object_active_state(addr, descr, expect, next)

where "expect" is the expected state and "next" is the next state to move to if
the expected state is found. A warning is generated if the expected is not
found.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: David S. Miller <davem@davemloft.net>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: akpm@linux-foundation.org
CC: mingo@elte.hu
CC: laijs@cn.fujitsu.com
CC: dipankar@in.ibm.com
CC: josh@joshtriplett.org
CC: dvhltc@us.ibm.com
CC: niv@us.ibm.com
CC: peterz@infradead.org
CC: rostedt@goodmis.org
CC: Valdis.Kletnieks@vt.edu
CC: dhowells@redhat.com
CC: eric.dumazet@gmail.com
CC: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/debugobjects.h |   11 ++++++++
 lib/debugobjects.c           |   59 +++++++++++++++++++++++++++++++++++++++--
 2 files changed, 67 insertions(+), 3 deletions(-)

diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h
index 8c243aa..597692f 100644
--- a/include/linux/debugobjects.h
+++ b/include/linux/debugobjects.h
@@ -20,12 +20,14 @@ struct debug_obj_descr;
  * struct debug_obj - representaion of an tracked object
  * @node:	hlist node to link the object into the tracker list
  * @state:	tracked object state
+ * @astate:	current active state
  * @object:	pointer to the real object
  * @descr:	pointer to an object type specific debug description structure
  */
 struct debug_obj {
 	struct hlist_node	node;
 	enum debug_obj_state	state;
+	unsigned int		astate;
 	void			*object;
 	struct debug_obj_descr	*descr;
 };
@@ -60,6 +62,15 @@ extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr);
 extern void debug_object_destroy   (void *addr, struct debug_obj_descr *descr);
 extern void debug_object_free      (void *addr, struct debug_obj_descr *descr);
 
+/*
+ * Active state:
+ * - Set at 0 upon initialization.
+ * - Must return to 0 before deactivation.
+ */
+extern void
+debug_object_active_state(void *addr, struct debug_obj_descr *descr,
+			  unsigned int expect, unsigned int next);
+
 extern void debug_objects_early_init(void);
 extern void debug_objects_mem_init(void);
 #else
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index b862b30..076464f 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -141,6 +141,7 @@ alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr)
 		obj->object = addr;
 		obj->descr  = descr;
 		obj->state  = ODEBUG_STATE_NONE;
+		obj->astate = 0;
 		hlist_del(&obj->node);
 
 		hlist_add_head(&obj->node, &b->list);
@@ -252,8 +253,10 @@ static void debug_print_object(struct debug_obj *obj, char *msg)
 
 	if (limit < 5 && obj->descr != descr_test) {
 		limit++;
-		WARN(1, KERN_ERR "ODEBUG: %s %s object type: %s\n", msg,
-		       obj_states[obj->state], obj->descr->name);
+		WARN(1, KERN_ERR "ODEBUG: %s %s (active state %u) "
+				 "object type: %s\n",
+			msg, obj_states[obj->state], obj->astate,
+			obj->descr->name);
 	}
 	debug_objects_warnings++;
 }
@@ -447,7 +450,10 @@ void debug_object_deactivate(void *addr, struct debug_obj_descr *descr)
 		case ODEBUG_STATE_INIT:
 		case ODEBUG_STATE_INACTIVE:
 		case ODEBUG_STATE_ACTIVE:
-			obj->state = ODEBUG_STATE_INACTIVE;
+			if (!obj->astate)
+				obj->state = ODEBUG_STATE_INACTIVE;
+			else
+				debug_print_object(obj, "deactivate");
 			break;
 
 		case ODEBUG_STATE_DESTROYED:
@@ -553,6 +559,53 @@ out_unlock:
 	raw_spin_unlock_irqrestore(&db->lock, flags);
 }
 
+/**
+ * debug_object_active_state - debug checks object usage state machine
+ * @addr:	address of the object
+ * @descr:	pointer to an object specific debug description structure
+ * @expect:	expected state
+ * @next:	state to move to if expected state is found
+ */
+void
+debug_object_active_state(void *addr, struct debug_obj_descr *descr,
+			  unsigned int expect, unsigned int next)
+{
+	struct debug_bucket *db;
+	struct debug_obj *obj;
+	unsigned long flags;
+
+	if (!debug_objects_enabled)
+		return;
+
+	db = get_bucket((unsigned long) addr);
+
+	raw_spin_lock_irqsave(&db->lock, flags);
+
+	obj = lookup_object(addr, db);
+	if (obj) {
+		switch (obj->state) {
+		case ODEBUG_STATE_ACTIVE:
+			if (obj->astate == expect)
+				obj->astate = next;
+			else
+				debug_print_object(obj, "active_state");
+			break;
+
+		default:
+			debug_print_object(obj, "active_state");
+			break;
+		}
+	} else {
+		struct debug_obj o = { .object = addr,
+				       .state = ODEBUG_STATE_NOTAVAILABLE,
+				       .descr = descr };
+
+		debug_print_object(&o, "active_state");
+	}
+
+	raw_spin_unlock_irqrestore(&db->lock, flags);
+}
+
 #ifdef CONFIG_DEBUG_OBJECTS_FREE
 static void __debug_check_no_obj_freed(const void *address, unsigned long size)
 {
-- 
1.7.0

[PATCH tip/core/rcu 19/23] rcu head introduce rcu head init on stack

[Paul E. McKenney]

From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>

PEM:
o     Would it be possible to make this bisectable as follows?

      a.      Insert a new patch after current patch 4/6 that
              defines destroy_rcu_head_on_stack(),
              init_rcu_head_on_stack(), and init_rcu_head() with
              their !CONFIG_DEBUG_OBJECTS_RCU_HEAD definitions.

This patch performs this transition.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: David S. Miller <davem@davemloft.net>
CC: akpm@linux-foundation.org
CC: mingo@elte.hu
CC: laijs@cn.fujitsu.com
CC: dipankar@in.ibm.com
CC: josh@joshtriplett.org
CC: dvhltc@us.ibm.com
CC: niv@us.ibm.com
CC: tglx@linutronix.de
CC: peterz@infradead.org
CC: rostedt@goodmis.org
CC: Valdis.Kletnieks@vt.edu
CC: dhowells@redhat.com
CC: eric.dumazet@gmail.com
CC: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h |    8 ++++++++
 1 files changed, 8 insertions(+), 0 deletions(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 6e6f851..c63372b 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -79,6 +79,14 @@ extern void rcu_init(void);
        (ptr)->next = NULL; (ptr)->func = NULL; \
 } while (0)
 
+static inline void init_rcu_head_on_stack(struct rcu_head *head)
+{
+}
+
+static inline void destroy_rcu_head_on_stack(struct rcu_head *head)
+{
+}
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 extern struct lockdep_map rcu_lock_map;
-- 
1.7.0

[PATCH tip/core/rcu 20/23] remove all rcu head initializations, except on_stack initializations

[Paul E. McKenney]

From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>

Remove all rcu head inits. We don't care about the RCU head state before passing
it to call_rcu() anyway. Only leave the "on_stack" variants so debugobjects can
keep track of objects on stack.

This patch applies to current -tip based on 2.6.34-rc2.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: David S. Miller <davem@davemloft.net>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: akpm@linux-foundation.org
CC: mingo@elte.hu
CC: laijs@cn.fujitsu.com
CC: dipankar@in.ibm.com
CC: josh@joshtriplett.org
CC: dvhltc@us.ibm.com
CC: niv@us.ibm.com
CC: tglx@linutronix.de
CC: peterz@infradead.org
CC: rostedt@goodmis.org
CC: Valdis.Kletnieks@vt.edu
CC: dhowells@redhat.com
CC: eric.dumazet@gmail.com
CC: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 arch/powerpc/mm/pgtable.c                   |    1 -
 block/cfq-iosched.c                         |    1 -
 block/genhd.c                               |    1 -
 drivers/staging/batman-adv/hard-interface.c |    1 -
 fs/file.c                                   |    3 --
 fs/fs-writeback.c                           |   31 ++++++++++++++++++++++----
 fs/partitions/check.c                       |    1 -
 include/linux/init_task.h                   |    1 -
 kernel/rcutiny.c                            |    6 +++++
 kernel/rcutorture.c                         |    2 +
 kernel/rcutree.c                            |    4 +++
 mm/backing-dev.c                            |    1 -
 mm/slob.c                                   |    1 -
 security/selinux/avc.c                      |    1 -
 security/selinux/netnode.c                  |    2 -
 15 files changed, 38 insertions(+), 19 deletions(-)

diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index ebc2f38..2c7e801 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -92,7 +92,6 @@ static void pte_free_rcu_callback(struct rcu_head *head)
 
 static void pte_free_submit(struct pte_freelist_batch *batch)
 {
-	INIT_RCU_HEAD(&batch->rcu);
 	call_rcu(&batch->rcu, pte_free_rcu_callback);
 }
 
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 838834b..0b695dd 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -3741,7 +3741,6 @@ static void *cfq_init_queue(struct request_queue *q)
 	 * second, in order to have larger depth for async operations.
 	 */
 	cfqd->last_delayed_sync = jiffies - HZ;
-	INIT_RCU_HEAD(&cfqd->rcu);
 	return cfqd;
 }
 
diff --git a/block/genhd.c b/block/genhd.c
index d13ba76..27e85a2 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -987,7 +987,6 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno)
 	if (!new_ptbl)
 		return -ENOMEM;
 
-	INIT_RCU_HEAD(&new_ptbl->rcu_head);
 	new_ptbl->len = target;
 
 	for (i = 0; i < len; i++)
diff --git a/drivers/staging/batman-adv/hard-interface.c b/drivers/staging/batman-adv/hard-interface.c
index befd488..96ea0e5 100644
--- a/drivers/staging/batman-adv/hard-interface.c
+++ b/drivers/staging/batman-adv/hard-interface.c
@@ -301,7 +301,6 @@ int hardif_add_interface(char *dev, int if_num)
 	batman_if->if_num = if_num;
 	batman_if->dev = dev;
 	batman_if->if_active = IF_INACTIVE;
-	INIT_RCU_HEAD(&batman_if->rcu);
 
 	printk(KERN_INFO "batman-adv:Adding interface: %s\n", dev);
 	avail_ifs++;
diff --git a/fs/file.c b/fs/file.c
index 34bb7f7..cccaead 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -178,7 +178,6 @@ static struct fdtable * alloc_fdtable(unsigned int nr)
 	fdt->open_fds = (fd_set *)data;
 	data += nr / BITS_PER_BYTE;
 	fdt->close_on_exec = (fd_set *)data;
-	INIT_RCU_HEAD(&fdt->rcu);
 	fdt->next = NULL;
 
 	return fdt;
@@ -312,7 +311,6 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
 	new_fdt->close_on_exec = (fd_set *)&newf->close_on_exec_init;
 	new_fdt->open_fds = (fd_set *)&newf->open_fds_init;
 	new_fdt->fd = &newf->fd_array[0];
-	INIT_RCU_HEAD(&new_fdt->rcu);
 	new_fdt->next = NULL;
 
 	spin_lock(&oldf->file_lock);
@@ -430,7 +428,6 @@ struct files_struct init_files = {
 		.fd		= &init_files.fd_array[0],
 		.close_on_exec	= (fd_set *)&init_files.close_on_exec_init,
 		.open_fds	= (fd_set *)&init_files.open_fds_init,
-		.rcu		= RCU_HEAD_INIT,
 	},
 	.file_lock	= __SPIN_LOCK_UNLOCKED(init_task.file_lock),
 };
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 4b37f7c..ea38c65 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -75,12 +75,33 @@ static inline bool bdi_work_on_stack(struct bdi_work *work)
 	return test_bit(WS_ONSTACK_B, &work->state);
 }
 
-static inline void bdi_work_init(struct bdi_work *work,
-				 struct wb_writeback_args *args)
+static inline void __bdi_work_init(struct bdi_work *work,
+				   struct wb_writeback_args *args,
+				   int on_stack)
 {
-	INIT_RCU_HEAD(&work->rcu_head);
 	work->args = *args;
 	work->state = WS_USED;
+	if (on_stack) {
+		work->state |= WS_ONSTACK;
+		init_rcu_head_on_stack(&work->rcu_head);
+	}
+}
+
+static inline void bdi_work_init(struct bdi_work *work,
+				 struct wb_writeback_args *args)
+{
+	__bdi_work_init(work, args, false);
+}
+
+static inline void bdi_work_init_on_stack(struct bdi_work *work,
+					  struct wb_writeback_args *args)
+{
+	__bdi_work_init(work, args, true);
+}
+
+static inline void bdi_destroy_work_on_stack(struct bdi_work *work)
+{
+	destroy_rcu_head_on_stack(&work->rcu_head);
 }
 
 /**
@@ -233,11 +254,11 @@ static void bdi_sync_writeback(struct backing_dev_info *bdi,
 	};
 	struct bdi_work work;
 
-	bdi_work_init(&work, &args);
-	work.state |= WS_ONSTACK;
+	bdi_work_init_on_stack(&work, &args);
 
 	bdi_queue_work(bdi, &work);
 	bdi_wait_on_work_clear(&work);
+	bdi_destroy_work_on_stack(&work);
 }
 
 /**
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index e238ab2..7444e6f 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -456,7 +456,6 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	}
 
 	/* everything is up and running, commence */
-	INIT_RCU_HEAD(&p->rcu_head);
 	rcu_assign_pointer(ptbl->part[partno], p);
 
 	/* suppress uevent if the disk supresses it */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index b1ed1cd..7996fc2 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -49,7 +49,6 @@ extern struct group_info init_groups;
 		{ .first = &init_task.pids[PIDTYPE_PGID].node },	\
 		{ .first = &init_task.pids[PIDTYPE_SID].node },		\
 	},								\
-	.rcu		= RCU_HEAD_INIT,				\
 	.level		= 0,						\
 	.numbers	= { {						\
 		.nr		= 0,					\
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index b1804ff..38729d3 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -245,11 +245,13 @@ void rcu_barrier(void)
 {
 	struct rcu_synchronize rcu;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier);
 
@@ -257,11 +259,13 @@ void rcu_barrier_bh(void)
 {
 	struct rcu_synchronize rcu;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu_bh(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_bh);
 
@@ -269,11 +273,13 @@ void rcu_barrier_sched(void)
 {
 	struct rcu_synchronize rcu;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu_sched(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_sched);
 
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 58df55b..077defb 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -464,9 +464,11 @@ static void rcu_bh_torture_synchronize(void)
 {
 	struct rcu_bh_torture_synchronize rcu;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	call_rcu_bh(&rcu.head, rcu_bh_torture_wakeme_after_cb);
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 
 static struct rcu_torture_ops rcu_bh_ops = {
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index ba69969..d443734 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1484,11 +1484,13 @@ void synchronize_sched(void)
 	if (rcu_blocking_is_gp())
 		return;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu_sched(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(synchronize_sched);
 
@@ -1508,11 +1510,13 @@ void synchronize_rcu_bh(void)
 	if (rcu_blocking_is_gp())
 		return;
 
+	init_rcu_head_on_stack(&rcu.head);
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu_bh(&rcu.head, wakeme_after_rcu);
 	/* Wait for it. */
 	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
 
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f13e067..1bba4ae 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -656,7 +656,6 @@ int bdi_init(struct backing_dev_info *bdi)
 	bdi->max_ratio = 100;
 	bdi->max_prop_frac = PROP_FRAC_BASE;
 	spin_lock_init(&bdi->wb_lock);
-	INIT_RCU_HEAD(&bdi->rcu_head);
 	INIT_LIST_HEAD(&bdi->bdi_list);
 	INIT_LIST_HEAD(&bdi->wb_list);
 	INIT_LIST_HEAD(&bdi->work_list);
diff --git a/mm/slob.c b/mm/slob.c
index 837ebd6..6de238d 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -647,7 +647,6 @@ void kmem_cache_free(struct kmem_cache *c, void *b)
 	if (unlikely(c->flags & SLAB_DESTROY_BY_RCU)) {
 		struct slob_rcu *slob_rcu;
 		slob_rcu = b + (c->size - sizeof(struct slob_rcu));
-		INIT_RCU_HEAD(&slob_rcu->head);
 		slob_rcu->size = c->size;
 		call_rcu(&slob_rcu->head, kmem_rcu_free);
 	} else {
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index 989fef8..bf4e3bc 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -288,7 +288,6 @@ static struct avc_node *avc_alloc_node(void)
 	if (!node)
 		goto out;
 
-	INIT_RCU_HEAD(&node->rhead);
 	INIT_HLIST_NODE(&node->list);
 	avc_cache_stats_incr(allocations);
 
diff --git a/security/selinux/netnode.c b/security/selinux/netnode.c
index dc92792..65ebfe9 100644
--- a/security/selinux/netnode.c
+++ b/security/selinux/netnode.c
@@ -183,8 +183,6 @@ static void sel_netnode_insert(struct sel_netnode *node)
 		BUG();
 	}
 
-	INIT_RCU_HEAD(&node->rcu);
-
 	/* we need to impose a limit on the growth of the hash table so check
 	 * this bucket to make sure it is within the specified bounds */
 	list_add_rcu(&node->list, &sel_netnode_hash[idx].list);
-- 
1.7.0

[PATCH tip/core/rcu 21/23] rcu head remove init

[Paul E. McKenney]

From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>

RCU heads really don't need to be initialized. Their state before call_rcu()
really does not matter.

We need to keep init/destroy_rcu_head_on_stack() though, since we want
debugobjects to be able to keep track of these objects.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: David S. Miller <davem@davemloft.net>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: akpm@linux-foundation.org
CC: mingo@elte.hu
CC: laijs@cn.fujitsu.com
CC: dipankar@in.ibm.com
CC: josh@joshtriplett.org
CC: dvhltc@us.ibm.com
CC: niv@us.ibm.com
CC: tglx@linutronix.de
CC: peterz@infradead.org
CC: rostedt@goodmis.org
CC: Valdis.Kletnieks@vt.edu
CC: dhowells@redhat.com
CC: eric.dumazet@gmail.com
CC: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h |    6 ------
 1 files changed, 0 insertions(+), 6 deletions(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index c63372b..729cab8 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -73,12 +73,6 @@ extern void rcu_init(void);
 #error "Unknown RCU implementation specified to kernel configuration"
 #endif
 
-#define RCU_HEAD_INIT	{ .next = NULL, .func = NULL }
-#define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT
-#define INIT_RCU_HEAD(ptr) do { \
-       (ptr)->next = NULL; (ptr)->func = NULL; \
-} while (0)
-
 static inline void init_rcu_head_on_stack(struct rcu_head *head)
 {
 }
-- 
1.7.0

[PATCH tip/core/rcu 22/23] tree/tiny rcu: Add debug RCU head objects (v5)

[Paul E. McKenney]

From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>

Helps finding racy users of call_rcu(), which results in hangs because list
entries are overwritten and/or skipped.

Changelog since v4:
- Bissectability is now OK
- Now generate a WARN_ON_ONCE() for non-initialized rcu_head passed to
  call_rcu(). Statically initialized objects are detected with
  object_is_static().
- Rename rcu_head_init_on_stack to init_rcu_head_on_stack.
- Remove init_rcu_head() completely.

Changelog since v3:
- Include comments from Lai Jiangshan

This new patch version is based on the debugobjects with the newly introduced
"active state" tracker.

Non-initialized entries are all considered as "statically initialized". An
activation fixup (triggered by call_rcu()) takes care of performing the debug
object initialization without issuing any warning. Since we cannot increase the
size of struct rcu_head, I don't see much room to put an identifier for
statically initialized rcu_head structures. So for now, we have to live without
"activation without explicit init" detection. But the main purpose of this debug
option is to detect double-activations (double call_rcu() use of a rcu_head
before the callback is executed), which is correctly addressed here.

This also detects potential internal RCU callback corruption, which would cause
the callbacks to be executed twice.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: David S. Miller <davem@davemloft.net>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: akpm@linux-foundation.org
CC: mingo@elte.hu
CC: laijs@cn.fujitsu.com
CC: dipankar@in.ibm.com
CC: josh@joshtriplett.org
CC: dvhltc@us.ibm.com
CC: niv@us.ibm.com
CC: tglx@linutronix.de
CC: peterz@infradead.org
CC: rostedt@goodmis.org
CC: Valdis.Kletnieks@vt.edu
CC: dhowells@redhat.com
CC: eric.dumazet@gmail.com
CC: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>
---
 include/linux/rcupdate.h |   49 +++++++++++++++
 kernel/rcupdate.c        |  149 ++++++++++++++++++++++++++++++++++++++++++++++
 kernel/rcutiny.c         |    2 +
 kernel/rcutree.c         |    2 +
 lib/Kconfig.debug        |    6 ++
 5 files changed, 208 insertions(+), 0 deletions(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 729cab8..f2bc463 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -40,6 +40,7 @@
 #include <linux/seqlock.h>
 #include <linux/lockdep.h>
 #include <linux/completion.h>
+#include <linux/debugobjects.h>
 
 #ifdef CONFIG_RCU_TORTURE_TEST
 extern int rcutorture_runnable; /* for sysctl */
@@ -73,6 +74,16 @@ extern void rcu_init(void);
 #error "Unknown RCU implementation specified to kernel configuration"
 #endif
 
+/*
+ * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic
+ * initialization and destruction of rcu_head on the stack. rcu_head structures
+ * allocated dynamically in the heap or defined statically don't need any
+ * initialization.
+ */
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+extern void init_rcu_head_on_stack(struct rcu_head *head);
+extern void destroy_rcu_head_on_stack(struct rcu_head *head);
+#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 static inline void init_rcu_head_on_stack(struct rcu_head *head)
 {
 }
@@ -80,6 +91,7 @@ static inline void init_rcu_head_on_stack(struct rcu_head *head)
 static inline void destroy_rcu_head_on_stack(struct rcu_head *head)
 {
 }
+#endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
@@ -502,4 +514,41 @@ extern void call_rcu(struct rcu_head *head,
 extern void call_rcu_bh(struct rcu_head *head,
 			void (*func)(struct rcu_head *head));
 
+/*
+ * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
+ * by call_rcu() and rcu callback execution, and are therefore not part of the
+ * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors.
+ */
+
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+# define STATE_RCU_HEAD_READY	0
+# define STATE_RCU_HEAD_QUEUED	1
+
+extern struct debug_obj_descr rcuhead_debug_descr;
+
+static inline void debug_rcu_head_queue(struct rcu_head *head)
+{
+	debug_object_activate(head, &rcuhead_debug_descr);
+	debug_object_active_state(head, &rcuhead_debug_descr,
+				  STATE_RCU_HEAD_READY,
+				  STATE_RCU_HEAD_QUEUED);
+}
+
+static inline void debug_rcu_head_unqueue(struct rcu_head *head)
+{
+	debug_object_active_state(head, &rcuhead_debug_descr,
+				  STATE_RCU_HEAD_QUEUED,
+				  STATE_RCU_HEAD_READY);
+	debug_object_deactivate(head, &rcuhead_debug_descr);
+}
+#else	/* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+static inline void debug_rcu_head_queue(struct rcu_head *head)
+{
+}
+
+static inline void debug_rcu_head_unqueue(struct rcu_head *head)
+{
+}
+#endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 689281e..7780427 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -103,3 +103,152 @@ void wakeme_after_rcu(struct rcu_head  *head)
 	rcu = container_of(head, struct rcu_synchronize, head);
 	complete(&rcu->completion);
 }
+
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+static inline void debug_init_rcu_head(struct rcu_head *head)
+{
+	debug_object_init(head, &rcuhead_debug_descr);
+}
+
+static inline void debug_rcu_head_free(struct rcu_head *head)
+{
+	debug_object_free(head, &rcuhead_debug_descr);
+}
+
+/*
+ * fixup_init is called when:
+ * - an active object is initialized
+ */
+static int rcuhead_fixup_init(void *addr, enum debug_obj_state state)
+{
+	struct rcu_head *head = addr;
+
+	switch (state) {
+	case ODEBUG_STATE_ACTIVE:
+		/*
+		 * Ensure that queued callbacks are all executed.
+		 * If we detect that we are nested in a RCU read-side critical
+		 * section, we should simply fail, otherwise we would deadlock.
+		 */
+#ifndef CONFIG_PREEMPT
+		WARN_ON(1);
+		return 0;
+#else
+		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
+		    irqs_disabled()) {
+			WARN_ON(1);
+			return 0;
+		}
+		rcu_barrier();
+		rcu_barrier_sched();
+		rcu_barrier_bh();
+		debug_object_init(head, &rcuhead_debug_descr);
+		return 1;
+#endif
+	default:
+		return 0;
+	}
+}
+
+/*
+ * fixup_activate is called when:
+ * - an active object is activated
+ * - an unknown object is activated (might be a statically initialized object)
+ * Activation is performed internally by call_rcu().
+ */
+static int rcuhead_fixup_activate(void *addr, enum debug_obj_state state)
+{
+	struct rcu_head *head = addr;
+
+	switch (state) {
+
+	case ODEBUG_STATE_NOTAVAILABLE:
+		/*
+		 * This is not really a fixup. We just make sure that it is
+		 * tracked in the object tracker.
+		 */
+		debug_object_init(head, &rcuhead_debug_descr);
+		debug_object_activate(head, &rcuhead_debug_descr);
+		return 0;
+
+	case ODEBUG_STATE_ACTIVE:
+		/*
+		 * Ensure that queued callbacks are all executed.
+		 * If we detect that we are nested in a RCU read-side critical
+		 * section, we should simply fail, otherwise we would deadlock.
+		 */
+#ifndef CONFIG_PREEMPT
+		WARN_ON(1);
+		return 0;
+#else
+		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
+		    irqs_disabled()) {
+			WARN_ON(1);
+			return 0;
+		}
+		rcu_barrier();
+		rcu_barrier_sched();
+		rcu_barrier_bh();
+		debug_object_activate(head, &rcuhead_debug_descr);
+		return 1;
+#endif
+	default:
+		return 0;
+	}
+}
+
+/*
+ * fixup_free is called when:
+ * - an active object is freed
+ */
+static int rcuhead_fixup_free(void *addr, enum debug_obj_state state)
+{
+	struct rcu_head *head = addr;
+
+	switch (state) {
+	case ODEBUG_STATE_ACTIVE:
+		/*
+		 * Ensure that queued callbacks are all executed.
+		 * If we detect that we are nested in a RCU read-side critical
+		 * section, we should simply fail, otherwise we would deadlock.
+		 */
+#ifndef CONFIG_PREEMPT
+		WARN_ON(1);
+		return 0;
+#else
+		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
+		    irqs_disabled()) {
+			WARN_ON(1);
+			return 0;
+		}
+		rcu_barrier();
+		rcu_barrier_sched();
+		rcu_barrier_bh();
+		debug_object_free(head, &rcuhead_debug_descr);
+		return 1;
+#endif
+	default:
+		return 0;
+	}
+}
+
+void init_rcu_head_on_stack(struct rcu_head *head)
+{
+	debug_object_init_on_stack(head, &rcuhead_debug_descr);
+}
+EXPORT_SYMBOL_GPL(init_rcu_head_on_stack);
+
+void destroy_rcu_head_on_stack(struct rcu_head *head)
+{
+	debug_object_free(head, &rcuhead_debug_descr);
+}
+EXPORT_SYMBOL_GPL(destroy_rcu_head_on_stack);
+
+struct debug_obj_descr rcuhead_debug_descr = {
+	.name = "rcu_head",
+	.fixup_init = rcuhead_fixup_init,
+	.fixup_activate = rcuhead_fixup_activate,
+	.fixup_free = rcuhead_fixup_free,
+};
+EXPORT_SYMBOL_GPL(rcuhead_debug_descr);
+#endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 38729d3..196ec02 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -169,6 +169,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 	while (list) {
 		next = list->next;
 		prefetch(next);
+		debug_rcu_head_unqueue(list);
 		list->func(list);
 		list = next;
 	}
@@ -211,6 +212,7 @@ static void __call_rcu(struct rcu_head *head,
 {
 	unsigned long flags;
 
+	debug_rcu_head_queue(head);
 	head->func = func;
 	head->next = NULL;
 
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index d443734..d5bc439 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1112,6 +1112,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 	while (list) {
 		next = list->next;
 		prefetch(next);
+		debug_rcu_head_unqueue(list);
 		list->func(list);
 		list = next;
 		if (++count >= rdp->blimit)
@@ -1388,6 +1389,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	unsigned long flags;
 	struct rcu_data *rdp;
 
+	debug_rcu_head_queue(head);
 	head->func = func;
 	head->next = NULL;
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 40d7be7..dd8e8d2 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -307,6 +307,12 @@ config DEBUG_OBJECTS_WORK
 	  work queue routines to track the life time of work objects and
 	  validate the work operations.
 
+config DEBUG_OBJECTS_RCU_HEAD
+	bool "Debug RCU callbacks objects"
+	depends on DEBUG_OBJECTS
+	help
+	  Enable this to turn on debugging of RCU list heads (call_rcu() usage).
+
 config DEBUG_OBJECTS_ENABLE_DEFAULT
 	int "debug_objects bootup default value (0-1)"
         range 0 1
-- 
1.7.0

[PATCH tip/core/rcu 23/23] rcu: make SRCU usable in modules

[Paul E. McKenney]

Add a #include for mutex.h to allow SRCU to be more easily used in
kernel modules.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/srcu.h |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 9c01f10..4d5d2f5 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -27,6 +27,8 @@
 #ifndef _LINUX_SRCU_H
 #define _LINUX_SRCU_H
 
+#include <linux/mutex.h>
+
 struct srcu_struct_array {
 	int c[2];
 };
-- 
1.7.0