Revert "rcu: Move PREEMPT_RCU preemption to switch_to() invocation"

This reverts commit 616c310e83b872024271c915c1b9ab505b9efad9.
(Move PREEMPT_RCU preemption to switch_to() invocation).
Testing by Sasha Levin <levinsasha928@gmail.com> showed that this
can result in deadlock due to invoking the scheduler when one of
the runqueue locks is held.  Because this commit was simply a
performance optimization, revert it.

Reported-by: Sasha Levin <levinsasha928@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Sasha Levin <levinsasha928@gmail.com>

8 files changed, 19 insertions, 16 deletions

diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index 88e466b159dc..43b39d61b538 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -705,7 +705,6 @@ static void stack_proc(void *arg)
         struct task_struct *from = current, *to = arg;
 
         to->thread.saved_task = from;
-        rcu_switch_from(from);
         switch_to(from, to, from);
 }
 
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 26d1a47591f1..9cac722b169c 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -184,7 +184,6 @@ static inline int rcu_preempt_depth(void)
 /* Internal to kernel */
 extern void rcu_sched_qs(int cpu);
 extern void rcu_bh_qs(int cpu);
-extern void rcu_preempt_note_context_switch(void);
 extern void rcu_check_callbacks(int cpu, int user);
 struct notifier_block;
 extern void rcu_idle_enter(void);
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 854dc4c5c271..4e56a9c69a35 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -87,6 +87,10 @@ static inline void kfree_call_rcu(struct rcu_head *head,
 
 #ifdef CONFIG_TINY_RCU
 
+static inline void rcu_preempt_note_context_switch(void)
+{
+}
+
 static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
 {
         *delta_jiffies = ULONG_MAX;
@@ -95,6 +99,7 @@ static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
 
 #else /* #ifdef CONFIG_TINY_RCU */
 
+void rcu_preempt_note_context_switch(void);
 int rcu_preempt_needs_cpu(void);
 
 static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
@@ -108,6 +113,7 @@ static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
 static inline void rcu_note_context_switch(int cpu)
 {
         rcu_sched_qs(cpu);
+        rcu_preempt_note_context_switch();
 }
 
 /*
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4059c0f33f07..06a4c5f4f55c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1871,22 +1871,12 @@ static inline void rcu_copy_process(struct task_struct *p)
         INIT_LIST_HEAD(&p->rcu_node_entry);
 }
 
-static inline void rcu_switch_from(struct task_struct *prev)
-{
-        if (prev->rcu_read_lock_nesting != 0)
-                rcu_preempt_note_context_switch();
-}
-
 #else
 
 static inline void rcu_copy_process(struct task_struct *p)
 {
 }
 
-static inline void rcu_switch_from(struct task_struct *prev)
-{
-}
-
 #endif
 
 #ifdef CONFIG_SMP
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 38ecdda3f55f..4b97bba7396e 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -201,6 +201,7 @@ void rcu_note_context_switch(int cpu)
 {
         trace_rcu_utilization("Start context switch");
         rcu_sched_qs(cpu);
+        rcu_preempt_note_context_switch(cpu);
         trace_rcu_utilization("End context switch");
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index ea056495783e..19b61ac1079f 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -444,6 +444,7 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work);
 /* Forward declarations for rcutree_plugin.h */
 static void rcu_bootup_announce(void);
 long rcu_batches_completed(void);
+static void rcu_preempt_note_context_switch(int cpu);
 static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 5271a020887e..3e4899459f3d 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -153,7 +153,7 @@ static void rcu_preempt_qs(int cpu)
  *
  * Caller must disable preemption.
  */
-void rcu_preempt_note_context_switch(void)
+static void rcu_preempt_note_context_switch(int cpu)
 {
         struct task_struct *t = current;
         unsigned long flags;
@@ -164,7 +164,7 @@ void rcu_preempt_note_context_switch(void)
             (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
 
                 /* Possibly blocking in an RCU read-side critical section. */
-                rdp = __this_cpu_ptr(rcu_preempt_state.rda);
+                rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
                 rnp = rdp->mynode;
                 raw_spin_lock_irqsave(&rnp->lock, flags);
                 t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
@@ -228,7 +228,7 @@ void rcu_preempt_note_context_switch(void)
          * means that we continue to block the current grace period.
          */
         local_irq_save(flags);
-        rcu_preempt_qs(smp_processor_id());
+        rcu_preempt_qs(cpu);
         local_irq_restore(flags);
 }
 
@@ -1002,6 +1002,14 @@ void rcu_force_quiescent_state(void)
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
 /*
+ * Because preemptible RCU does not exist, we never have to check for
+ * CPUs being in quiescent states.
+ */
+static void rcu_preempt_note_context_switch(int cpu)
+{
+}
+
+/*
  * Because preemptible RCU does not exist, there are never any preempted
  * RCU readers.
  */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d5594a4268d4..eaead2df6aa8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2081,7 +2081,6 @@ context_switch(struct rq *rq, struct task_struct *prev,
 #endif
 
         /* Here we just switch the register state and the stack. */
-        rcu_switch_from(prev);
         switch_to(prev, next, prev);
 
         barrier();