[PATCH rcu 0/6] Miscellaneous fixes for v5.17

[PATCH rcu 0/6] Miscellaneous fixes for v5.17

[Paul E. McKenney]

Hello!

This series contains miscellaneous fixes:

1.	Replace ________p1 and _________p1 with __UNIQUE_ID(rcu),
	courtesy of Chun-Hung Tseng.

2.	in_irq() cleanup, courtesy of Changbin Du.

3.	Improve tree_plugin.h comments and add code cleanups, courtesy
	of Zhouyi Zhou.

4.	Avoid running boost kthreads on isolated CPUs, courtesy of Zqiang.

5.	Avoid alloc_pages() when recording stack, courtesy of Jun Miao.

6.	Prevent redundant __srcu_read_unlock() wakeup.

						Thanx, Paul

------------------------------------------------------------------------

 b/include/linux/rcupdate.h |   50 +++++++++++++++++++++++++--------------------
 b/include/linux/rcutiny.h  |    2 -
 b/include/linux/srcu.h     |    3 +-
 b/kernel/rcu/srcutiny.c    |    2 -
 b/kernel/rcu/tree.c        |    2 -
 b/kernel/rcu/tree_plugin.h |    2 -
 kernel/rcu/tree.c          |    4 +--
 kernel/rcu/tree_plugin.h   |   14 ++++++------
 8 files changed, 43 insertions(+), 36 deletions(-)

[PATCH rcu 1/6] rcu: Replace ________p1 and _________p1 with __UNIQUE_ID(rcu)

[Paul E. McKenney]

From: Chun-Hung Tseng <henrybear327@gmail.com>

This commit replaces both ________p1 and _________p1 with __UNIQUE_ID(rcu),
and also adjusts the callers of the affected macros.

__UNIQUE_ID(rcu) will generate unique variable names during compilation,
which eliminates the need of ________p1 and _________p1 (both having 4
occurrences prior to the code change).  This also avoids the variable
name shadowing issue, or at least makes those wishing to cause shadowing
problems work much harder to do so.

The same idea is used for the min/max macros (commit 589a978 and commit
e9092d0).

Signed-off-by: Jim Huang <jserv@ccns.ncku.edu.tw>
Signed-off-by: Chun-Hung Tseng <henrybear327@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rcupdate.h | 50 ++++++++++++++++++++++------------------
 include/linux/srcu.h     |  3 ++-
 2 files changed, 30 insertions(+), 23 deletions(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 5e0beb5c5659a..88b42eb464068 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -364,6 +364,12 @@ static inline void rcu_preempt_sleep_check(void) { }
 #define rcu_check_sparse(p, space)
 #endif /* #else #ifdef __CHECKER__ */
 
+#define __unrcu_pointer(p, local)					\
+({									\
+	typeof(*p) *local = (typeof(*p) *__force)(p);			\
+	rcu_check_sparse(p, __rcu);					\
+	((typeof(*p) __force __kernel *)(local)); 			\
+})
 /**
  * unrcu_pointer - mark a pointer as not being RCU protected
  * @p: pointer needing to lose its __rcu property
@@ -371,39 +377,35 @@ static inline void rcu_preempt_sleep_check(void) { }
  * Converts @p from an __rcu pointer to a __kernel pointer.
  * This allows an __rcu pointer to be used with xchg() and friends.
  */
-#define unrcu_pointer(p)						\
-({									\
-	typeof(*p) *_________p1 = (typeof(*p) *__force)(p);		\
-	rcu_check_sparse(p, __rcu);					\
-	((typeof(*p) __force __kernel *)(_________p1)); 		\
-})
+#define unrcu_pointer(p) __unrcu_pointer(p, __UNIQUE_ID(rcu))
 
-#define __rcu_access_pointer(p, space) \
+#define __rcu_access_pointer(p, local, space) \
 ({ \
-	typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \
+	typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \
 	rcu_check_sparse(p, space); \
-	((typeof(*p) __force __kernel *)(_________p1)); \
+	((typeof(*p) __force __kernel *)(local)); \
 })
-#define __rcu_dereference_check(p, c, space) \
+#define __rcu_dereference_check(p, local, c, space) \
 ({ \
 	/* Dependency order vs. p above. */ \
-	typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \
+	typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \
 	RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \
 	rcu_check_sparse(p, space); \
-	((typeof(*p) __force __kernel *)(________p1)); \
+	((typeof(*p) __force __kernel *)(local)); \
 })
-#define __rcu_dereference_protected(p, c, space) \
+#define __rcu_dereference_protected(p, local, c, space) \
 ({ \
 	RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \
 	rcu_check_sparse(p, space); \
 	((typeof(*p) __force __kernel *)(p)); \
 })
-#define rcu_dereference_raw(p) \
+#define __rcu_dereference_raw(p, local) \
 ({ \
 	/* Dependency order vs. p above. */ \
-	typeof(p) ________p1 = READ_ONCE(p); \
-	((typeof(*p) __force __kernel *)(________p1)); \
+	typeof(p) local = READ_ONCE(p); \
+	((typeof(*p) __force __kernel *)(local)); \
 })
+#define rcu_dereference_raw(p) __rcu_dereference_raw(p, __UNIQUE_ID(rcu))
 
 /**
  * RCU_INITIALIZER() - statically initialize an RCU-protected global variable
@@ -490,7 +492,7 @@ do {									      \
  * when tearing down multi-linked structures after a grace period
  * has elapsed.
  */
-#define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu)
+#define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu)
 
 /**
  * rcu_dereference_check() - rcu_dereference with debug checking
@@ -526,7 +528,8 @@ do {									      \
  * annotated as __rcu.
  */
 #define rcu_dereference_check(p, c) \
-	__rcu_dereference_check((p), (c) || rcu_read_lock_held(), __rcu)
+	__rcu_dereference_check((p), __UNIQUE_ID(rcu), \
+				(c) || rcu_read_lock_held(), __rcu)
 
 /**
  * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking
@@ -541,7 +544,8 @@ do {									      \
  * rcu_read_lock() but also rcu_read_lock_bh() into account.
  */
 #define rcu_dereference_bh_check(p, c) \
-	__rcu_dereference_check((p), (c) || rcu_read_lock_bh_held(), __rcu)
+	__rcu_dereference_check((p), __UNIQUE_ID(rcu), \
+				(c) || rcu_read_lock_bh_held(), __rcu)
 
 /**
  * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking
@@ -556,7 +560,8 @@ do {									      \
  * only rcu_read_lock() but also rcu_read_lock_sched() into account.
  */
 #define rcu_dereference_sched_check(p, c) \
-	__rcu_dereference_check((p), (c) || rcu_read_lock_sched_held(), \
+	__rcu_dereference_check((p), __UNIQUE_ID(rcu), \
+				(c) || rcu_read_lock_sched_held(), \
 				__rcu)
 
 /*
@@ -566,7 +571,8 @@ do {									      \
  * The no-tracing version of rcu_dereference_raw() must not call
  * rcu_read_lock_held().
  */
-#define rcu_dereference_raw_check(p) __rcu_dereference_check((p), 1, __rcu)
+#define rcu_dereference_raw_check(p) \
+	__rcu_dereference_check((p), __UNIQUE_ID(rcu), 1, __rcu)
 
 /**
  * rcu_dereference_protected() - fetch RCU pointer when updates prevented
@@ -585,7 +591,7 @@ do {									      \
  * but very ugly failures.
  */
 #define rcu_dereference_protected(p, c) \
-	__rcu_dereference_protected((p), (c), __rcu)
+	__rcu_dereference_protected((p), __UNIQUE_ID(rcu), (c), __rcu)
 
 
 /**
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index e6011a9975af2..01226e4d960a0 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -117,7 +117,8 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp)
  * lockdep_is_held() calls.
  */
 #define srcu_dereference_check(p, ssp, c) \
-	__rcu_dereference_check((p), (c) || srcu_read_lock_held(ssp), __rcu)
+	__rcu_dereference_check((p), __UNIQUE_ID(rcu), \
+				(c) || srcu_read_lock_held(ssp), __rcu)
 
 /**
  * srcu_dereference - fetch SRCU-protected pointer for later dereferencing
-- 
2.31.1.189.g2e36527f23

[PATCH rcu 2/6] rcu: in_irq() cleanup

[Paul E. McKenney]

From: Changbin Du <changbin.du@gmail.com>

This commit replaces the obsolete and ambiguous macro in_irq() with its
shiny new in_hardirq() equivalent.

Signed-off-by: Changbin Du <changbin.du@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rcutiny.h  | 2 +-
 kernel/rcu/tree.c        | 2 +-
 kernel/rcu/tree_plugin.h | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 9be015305f9f9..858f4d429946d 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -85,7 +85,7 @@ static inline void rcu_irq_enter_irqson(void) { }
 static inline void rcu_irq_exit(void) { }
 static inline void rcu_irq_exit_check_preempt(void) { }
 #define rcu_is_idle_cpu(cpu) \
-	(is_idle_task(current) && !in_nmi() && !in_irq() && !in_serving_softirq())
+	(is_idle_task(current) && !in_nmi() && !in_hardirq() && !in_serving_softirq())
 static inline void exit_rcu(void) { }
 static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index ef8d36f580fc3..f0f19dc7f19ec 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1467,7 +1467,7 @@ static void rcu_gp_kthread_wake(void)
 {
 	struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);
 
-	if ((current == t && !in_irq() && !in_serving_softirq()) ||
+	if ((current == t && !in_hardirq() && !in_serving_softirq()) ||
 	    !READ_ONCE(rcu_state.gp_flags) || !t)
 		return;
 	WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 5199559fbbf0c..599084c4c21fd 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -642,7 +642,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
 			   (IS_ENABLED(CONFIG_RCU_BOOST) && irqs_were_disabled &&
 			    t->rcu_blocked_node);
 		// Need to defer quiescent state until everything is enabled.
-		if (use_softirq && (in_irq() || (expboost && !irqs_were_disabled))) {
+		if (use_softirq && (in_hardirq() || (expboost && !irqs_were_disabled))) {
 			// Using softirq, safe to awaken, and either the
 			// wakeup is free or there is either an expedited
 			// GP in flight or a potential need to deboost.
-- 
2.31.1.189.g2e36527f23

[PATCH rcu 3/6] rcu: Improve tree_plugin.h comments and add code cleanups

[Paul E. McKenney]

From: Zhouyi Zhou <zhouzhouyi@gmail.com>

This commit cleans up some comments and code in kernel/rcu/tree_plugin.h.

Signed-off-by: Zhouyi Zhou <zhouzhouyi@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 kernel/rcu/tree_plugin.h | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 599084c4c21fd..f44580276fbdc 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -16,7 +16,7 @@
 static bool rcu_rdp_is_offloaded(struct rcu_data *rdp)
 {
 	/*
-	 * In order to read the offloaded state of an rdp is a safe
+	 * In order to read the offloaded state of an rdp in a safe
 	 * and stable way and prevent from its value to be changed
 	 * under us, we must either hold the barrier mutex, the cpu
 	 * hotplug lock (read or write) or the nocb lock. Local
@@ -56,7 +56,7 @@ static void __init rcu_bootup_announce_oddness(void)
 	if (IS_ENABLED(CONFIG_PROVE_RCU))
 		pr_info("\tRCU lockdep checking is enabled.\n");
 	if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
-		pr_info("\tRCU strict (and thus non-scalable) grace periods enabled.\n");
+		pr_info("\tRCU strict (and thus non-scalable) grace periods are enabled.\n");
 	if (RCU_NUM_LVLS >= 4)
 		pr_info("\tFour(or more)-level hierarchy is enabled.\n");
 	if (RCU_FANOUT_LEAF != 16)
@@ -88,13 +88,13 @@ static void __init rcu_bootup_announce_oddness(void)
 	if (rcu_kick_kthreads)
 		pr_info("\tKick kthreads if too-long grace period.\n");
 	if (IS_ENABLED(CONFIG_DEBUG_OBJECTS_RCU_HEAD))
-		pr_info("\tRCU callback double-/use-after-free debug enabled.\n");
+		pr_info("\tRCU callback double-/use-after-free debug is enabled.\n");
 	if (gp_preinit_delay)
 		pr_info("\tRCU debug GP pre-init slowdown %d jiffies.\n", gp_preinit_delay);
 	if (gp_init_delay)
 		pr_info("\tRCU debug GP init slowdown %d jiffies.\n", gp_init_delay);
 	if (gp_cleanup_delay)
-		pr_info("\tRCU debug GP init slowdown %d jiffies.\n", gp_cleanup_delay);
+		pr_info("\tRCU debug GP cleanup slowdown %d jiffies.\n", gp_cleanup_delay);
 	if (!use_softirq)
 		pr_info("\tRCU_SOFTIRQ processing moved to rcuc kthreads.\n");
 	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG))
@@ -1153,7 +1153,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 /*
  * Create an RCU-boost kthread for the specified node if one does not
  * already exist.  We only create this kthread for preemptible RCU.
- * Returns zero if all is well, a negated errno otherwise.
  */
 static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
 {
@@ -1455,7 +1454,7 @@ static void rcu_cleanup_after_idle(void)
  * CPU unless the grace period has extended for too long.
  *
  * This code relies on the fact that all NO_HZ_FULL CPUs are also
- * CONFIG_RCU_NOCB_CPU CPUs.
+ * RCU_NOCB_CPU CPUs.
  */
 static bool rcu_nohz_full_cpu(void)
 {
-- 
2.31.1.189.g2e36527f23

[PATCH rcu 4/6] rcu: Avoid running boost kthreads on isolated CPUs

[Paul E. McKenney]

From: Zqiang <qiang.zhang1211@gmail.com>

When the boost kthreads are created on systems with nohz_full CPUs,
the cpus_allowed_ptr is set to housekeeping_cpumask(HK_FLAG_KTHREAD).
However, when the rcu_boost_kthread_setaffinity() is called, the original
affinity will be changed and these kthreads can subsequently run on
nohz_full CPUs.  This commit makes rcu_boost_kthread_setaffinity()
restrict these boost kthreads to housekeeping CPUs.

Signed-off-by: Zqiang <qiang.zhang1211@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 kernel/rcu/tree_plugin.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index f44580276fbdc..87fc4609b7563 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1203,8 +1203,9 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 		if ((mask & leaf_node_cpu_bit(rnp, cpu)) &&
 		    cpu != outgoingcpu)
 			cpumask_set_cpu(cpu, cm);
+	cpumask_and(cm, cm, housekeeping_cpumask(HK_FLAG_RCU));
 	if (cpumask_weight(cm) == 0)
-		cpumask_setall(cm);
+		cpumask_copy(cm, housekeeping_cpumask(HK_FLAG_RCU));
 	set_cpus_allowed_ptr(t, cm);
 	free_cpumask_var(cm);
 }
-- 
2.31.1.189.g2e36527f23

[PATCH rcu 5/6] rcu: Avoid alloc_pages() when recording stack

[Paul E. McKenney]

From: Jun Miao <jun.miao@intel.com>

The default kasan_record_aux_stack() calls stack_depot_save() with GFP_NOWAIT,
which in turn can then call alloc_pages(GFP_NOWAIT, ...).  In general, however,
it is not even possible to use either GFP_ATOMIC nor GFP_NOWAIT in certain
non-preemptive contexts/RT kernel including raw_spin_locks (see gfp.h and ab00db216c9c7).
Fix it by instructing stackdepot to not expand stack storage via alloc_pages()
in case it runs out by using kasan_record_aux_stack_noalloc().

Jianwei Hu reported:
BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:969
in_atomic(): 0, irqs_disabled(): 1, non_block: 0, pid: 15319, name: python3
INFO: lockdep is turned off.
irq event stamp: 0
  hardirqs last  enabled at (0): [<0000000000000000>] 0x0
  hardirqs last disabled at (0): [<ffffffff856c8b13>] copy_process+0xaf3/0x2590
  softirqs last  enabled at (0): [<ffffffff856c8b13>] copy_process+0xaf3/0x2590
  softirqs last disabled at (0): [<0000000000000000>] 0x0
  CPU: 6 PID: 15319 Comm: python3 Tainted: G        W  O 5.15-rc7-preempt-rt #1
  Hardware name: Supermicro SYS-E300-9A-8C/A2SDi-8C-HLN4F, BIOS 1.1b 12/17/2018
  Call Trace:
    show_stack+0x52/0x58
    dump_stack+0xa1/0xd6
    ___might_sleep.cold+0x11c/0x12d
    rt_spin_lock+0x3f/0xc0
    rmqueue+0x100/0x1460
    rmqueue+0x100/0x1460
    mark_usage+0x1a0/0x1a0
    ftrace_graph_ret_addr+0x2a/0xb0
    rmqueue_pcplist.constprop.0+0x6a0/0x6a0
     __kasan_check_read+0x11/0x20
     __zone_watermark_ok+0x114/0x270
     get_page_from_freelist+0x148/0x630
     is_module_text_address+0x32/0xa0
     __alloc_pages_nodemask+0x2f6/0x790
     __alloc_pages_slowpath.constprop.0+0x12d0/0x12d0
     create_prof_cpu_mask+0x30/0x30
     alloc_pages_current+0xb1/0x150
     stack_depot_save+0x39f/0x490
     kasan_save_stack+0x42/0x50
     kasan_save_stack+0x23/0x50
     kasan_record_aux_stack+0xa9/0xc0
     __call_rcu+0xff/0x9c0
     call_rcu+0xe/0x10
     put_object+0x53/0x70
     __delete_object+0x7b/0x90
     kmemleak_free+0x46/0x70
     slab_free_freelist_hook+0xb4/0x160
     kfree+0xe5/0x420
     kfree_const+0x17/0x30
     kobject_cleanup+0xaa/0x230
     kobject_put+0x76/0x90
     netdev_queue_update_kobjects+0x17d/0x1f0
     ... ...
     ksys_write+0xd9/0x180
     __x64_sys_write+0x42/0x50
     do_syscall_64+0x38/0x50
     entry_SYSCALL_64_after_hwframe+0x44/0xa9

Links: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/include/linux/kasan.h?id=7cb3007ce2da27ec02a1a3211941e7fe6875b642
Fixes: 84109ab58590 ("rcu: Record kvfree_call_rcu() call stack for KASAN")
Fixes: 26e760c9a7c8 ("rcu: kasan: record and print call_rcu() call stack")
Reported-by: Jianwei Hu <jianwei.hu@windriver.com>
Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Acked-by: Marco Elver <elver@google.com>
Tested-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Jun Miao <jun.miao@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 kernel/rcu/tree.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f0f19dc7f19ec..c8beea8dd3a05 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2982,7 +2982,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func)
 	head->func = func;
 	head->next = NULL;
 	local_irq_save(flags);
-	kasan_record_aux_stack(head);
+	kasan_record_aux_stack_noalloc(head);
 	rdp = this_cpu_ptr(&rcu_data);
 
 	/* Add the callback to our list. */
@@ -3547,7 +3547,7 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 		return;
 	}
 
-	kasan_record_aux_stack(ptr);
+	kasan_record_aux_stack_noalloc(ptr);
 	success = add_ptr_to_bulk_krc_lock(&krcp, &flags, ptr, !head);
 	if (!success) {
 		run_page_cache_worker(krcp);
-- 
2.31.1.189.g2e36527f23

[PATCH rcu 6/6] srcu: Prevent redundant __srcu_read_unlock() wakeup

[Paul E. McKenney]

Tiny SRCU readers can appear at task level, but also in interrupt and
softirq handlers.  Because Tiny SRCU is selected only in kernels built
with CONFIG_SMP=n and CONFIG_PREEMPTION=n, it is not possible for a grace
period to start while there is a non-task-level SRCU reader executing.
This means that it does not make sense for __srcu_read_unlock() to awaken
the Tiny SRCU grace period, because that can only happen when the grace
period is waiting for one value of ->srcu_idx and __srcu_read_unlock()
is ending the last reader for some other value of ->srcu_idx.  After all,
any such wakeup will be redundant.

Worse yet, in some cases, such wakeups generate lockdep splats:

	======================================================
	WARNING: possible circular locking dependency detected
	5.15.0-rc1+ #3758 Not tainted
	------------------------------------------------------
	rcu_torture_rea/53 is trying to acquire lock:
	ffffffff9514e6a8 (srcu_ctl.srcu_wq.lock){..-.}-{2:2}, at:
	xa/0x30

	but task is already holding lock:
	ffff95c642479d80 (&p->pi_lock){-.-.}-{2:2}, at:
	_extend+0x370/0x400

	which lock already depends on the new lock.

	the existing dependency chain (in reverse order) is:

	-> #1 (&p->pi_lock){-.-.}-{2:2}:
	       _raw_spin_lock_irqsave+0x2f/0x50
	       try_to_wake_up+0x50/0x580
	       swake_up_locked.part.7+0xe/0x30
	       swake_up_one+0x22/0x30
	       rcutorture_one_extend+0x1b6/0x400
	       rcu_torture_one_read+0x290/0x5d0
	       rcu_torture_timer+0x1a/0x70
	       call_timer_fn+0xa6/0x230
	       run_timer_softirq+0x493/0x4c0
	       __do_softirq+0xc0/0x371
	       irq_exit+0x73/0x90
	       sysvec_apic_timer_interrupt+0x63/0x80
	       asm_sysvec_apic_timer_interrupt+0x12/0x20
	       default_idle+0xb/0x10
	       default_idle_call+0x5e/0x170
	       do_idle+0x18a/0x1f0
	       cpu_startup_entry+0xa/0x10
	       start_kernel+0x678/0x69f
	       secondary_startup_64_no_verify+0xc2/0xcb

	-> #0 (srcu_ctl.srcu_wq.lock){..-.}-{2:2}:
	       __lock_acquire+0x130c/0x2440
	       lock_acquire+0xc2/0x270
	       _raw_spin_lock_irqsave+0x2f/0x50
	       swake_up_one+0xa/0x30
	       rcutorture_one_extend+0x387/0x400
	       rcu_torture_one_read+0x290/0x5d0
	       rcu_torture_reader+0xac/0x200
	       kthread+0x12d/0x150
	       ret_from_fork+0x22/0x30

	other info that might help us debug this:

	 Possible unsafe locking scenario:

	       CPU0                    CPU1
	       ----                    ----
	  lock(&p->pi_lock);
				       lock(srcu_ctl.srcu_wq.lock);
				       lock(&p->pi_lock);
	  lock(srcu_ctl.srcu_wq.lock);

	 *** DEADLOCK ***

	1 lock held by rcu_torture_rea/53:
	 #0: ffff95c642479d80 (&p->pi_lock){-.-.}-{2:2}, at:
	_extend+0x370/0x400

	stack backtrace:
	CPU: 0 PID: 53 Comm: rcu_torture_rea Not tainted 5.15.0-rc1+

	Hardware name: Red Hat KVM/RHEL-AV, BIOS
	e_el8.5.0+746+bbd5d70c 04/01/2014
	Call Trace:
	 check_noncircular+0xfe/0x110
	 ? find_held_lock+0x2d/0x90
	 __lock_acquire+0x130c/0x2440
	 lock_acquire+0xc2/0x270
	 ? swake_up_one+0xa/0x30
	 ? find_held_lock+0x72/0x90
	 _raw_spin_lock_irqsave+0x2f/0x50
	 ? swake_up_one+0xa/0x30
	 swake_up_one+0xa/0x30
	 rcutorture_one_extend+0x387/0x400
	 rcu_torture_one_read+0x290/0x5d0
	 rcu_torture_reader+0xac/0x200
	 ? rcutorture_oom_notify+0xf0/0xf0
	 ? __kthread_parkme+0x61/0x90
	 ? rcu_torture_one_read+0x5d0/0x5d0
	 kthread+0x12d/0x150
	 ? set_kthread_struct+0x40/0x40
	 ret_from_fork+0x22/0x30

This is a false positive because there is only one CPU, and both locks
are raw (non-preemptible) spinlocks.  However, it is worthwhile getting
rid of the redundant wakeup, which has the side effect of breaking
the theoretical deadlock cycle.  This commit therefore eliminates the
redundant wakeups.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 kernel/rcu/srcutiny.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index a0ba2ed49bc61..92c002d654828 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -99,7 +99,7 @@ void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
 	int newval = READ_ONCE(ssp->srcu_lock_nesting[idx]) - 1;
 
 	WRITE_ONCE(ssp->srcu_lock_nesting[idx], newval);
-	if (!newval && READ_ONCE(ssp->srcu_gp_waiting))
+	if (!newval && READ_ONCE(ssp->srcu_gp_waiting) && in_task())
 		swake_up_one(&ssp->srcu_wq);
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
-- 
2.31.1.189.g2e36527f23