rcu: Add grace-period, quiescent-state, and call_rcu trace events

Add trace events to record grace-period start and end, quiescent states,
CPUs noticing grace-period start and end, grace-period initialization,
call_rcu() invocation, tasks blocking in RCU read-side critical sections,
tasks exiting those same critical sections, force_quiescent_state()
detection of dyntick-idle and offline CPUs, CPUs entering and leaving
dyntick-idle mode (except from NMIs), CPUs coming online and going
offline, and CPUs being kicked for staying in dyntick-idle mode for too
long (as in many weeks, even on 32-bit systems).

Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

rcu: Add the rcu flavor to callback trace events

The earlier trace events for registering RCU callbacks and for invoking
them did not include the RCU flavor (rcu_bh, rcu_preempt, or rcu_sched).
This commit adds the RCU flavor to those trace events.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

1 files changed, 331 insertions, 14 deletions

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index ac52aba00a3e..669fbd62ec25 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -24,7 +24,7 @@ TRACE_EVENT(rcu_utilization,
         TP_ARGS(s),
 
         TP_STRUCT__entry(
-                __field(char *, s)
+                __field(char *, s)
         ),
 
         TP_fast_assign(
@@ -34,6 +34,297 @@ TRACE_EVENT(rcu_utilization,
         TP_printk("%s", __entry->s)
 );
 
+#ifdef CONFIG_RCU_TRACE
+
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
+
+/*
+ * Tracepoint for grace-period events: starting and ending a grace
+ * period ("start" and "end", respectively), a CPU noting the start
+ * of a new grace period or the end of an old grace period ("cpustart"
+ * and "cpuend", respectively), a CPU passing through a quiescent
+ * state ("cpuqs"), a CPU coming online or going offline ("cpuonl"
+ * and "cpuofl", respectively), and a CPU being kicked for being too
+ * long in dyntick-idle mode ("kick").
+ */
+TRACE_EVENT(rcu_grace_period,
+
+        TP_PROTO(char *rcuname, unsigned long gpnum, char *gpevent),
+
+        TP_ARGS(rcuname, gpnum, gpevent),
+
+        TP_STRUCT__entry(
+                __field(char *, rcuname)
+                __field(unsigned long, gpnum)
+                __field(char *, gpevent)
+        ),
+
+        TP_fast_assign(
+                __entry->rcuname = rcuname;
+                __entry->gpnum = gpnum;
+                __entry->gpevent = gpevent;
+        ),
+
+        TP_printk("%s %lu %s",
+                  __entry->rcuname, __entry->gpnum, __entry->gpevent)
+);
+
+/*
+ * Tracepoint for grace-period-initialization events.  These are
+ * distinguished by the type of RCU, the new grace-period number, the
+ * rcu_node structure level, the starting and ending CPU covered by the
+ * rcu_node structure, and the mask of CPUs that will be waited for.
+ * All but the type of RCU are extracted from the rcu_node structure.
+ */
+TRACE_EVENT(rcu_grace_period_init,
+
+        TP_PROTO(char *rcuname, unsigned long gpnum, u8 level,
+                 int grplo, int grphi, unsigned long qsmask),
+
+        TP_ARGS(rcuname, gpnum, level, grplo, grphi, qsmask),
+
+        TP_STRUCT__entry(
+                __field(char *, rcuname)
+                __field(unsigned long, gpnum)
+                __field(u8, level)
+                __field(int, grplo)
+                __field(int, grphi)
+                __field(unsigned long, qsmask)
+        ),
+
+        TP_fast_assign(
+                __entry->rcuname = rcuname;
+                __entry->gpnum = gpnum;
+                __entry->level = level;
+                __entry->grplo = grplo;
+                __entry->grphi = grphi;
+                __entry->qsmask = qsmask;
+        ),
+
+        TP_printk("%s %lu %u %d %d %lx",
+                  __entry->rcuname, __entry->gpnum, __entry->level,
+                  __entry->grplo, __entry->grphi, __entry->qsmask)
+);
+
+/*
+ * Tracepoint for tasks blocking within preemptible-RCU read-side
+ * critical sections.  Track the type of RCU (which one day might
+ * include SRCU), the grace-period number that the task is blocking
+ * (the current or the next), and the task's PID.
+ */
+TRACE_EVENT(rcu_preempt_task,
+
+        TP_PROTO(char *rcuname, int pid, unsigned long gpnum),
+
+        TP_ARGS(rcuname, pid, gpnum),
+
+        TP_STRUCT__entry(
+                __field(char *, rcuname)
+                __field(unsigned long, gpnum)
+                __field(int, pid)
+        ),
+
+        TP_fast_assign(
+                __entry->rcuname = rcuname;
+                __entry->gpnum = gpnum;
+                __entry->pid = pid;
+        ),
+
+        TP_printk("%s %lu %d",
+                  __entry->rcuname, __entry->gpnum, __entry->pid)
+);
+
+/*
+ * Tracepoint for tasks that blocked within a given preemptible-RCU
+ * read-side critical section exiting that critical section.  Track the
+ * type of RCU (which one day might include SRCU) and the task's PID.
+ */
+TRACE_EVENT(rcu_unlock_preempted_task,
+
+        TP_PROTO(char *rcuname, unsigned long gpnum, int pid),
+
+        TP_ARGS(rcuname, gpnum, pid),
+
+        TP_STRUCT__entry(
+                __field(char *, rcuname)
+                __field(unsigned long, gpnum)
+                __field(int, pid)
+        ),
+
+        TP_fast_assign(
+                __entry->rcuname = rcuname;
+                __entry->gpnum = gpnum;
+                __entry->pid = pid;
+        ),
+
+        TP_printk("%s %lu %d", __entry->rcuname, __entry->gpnum, __entry->pid)
+);
+
+/*
+ * Tracepoint for quiescent-state-reporting events.  These are
+ * distinguished by the type of RCU, the grace-period number, the
+ * mask of quiescent lower-level entities, the rcu_node structure level,
+ * the starting and ending CPU covered by the rcu_node structure, and
+ * whether there are any blocked tasks blocking the current grace period.
+ * All but the type of RCU are extracted from the rcu_node structure.
+ */
+TRACE_EVENT(rcu_quiescent_state_report,
+
+        TP_PROTO(char *rcuname, unsigned long gpnum,
+                 unsigned long mask, unsigned long qsmask,
+                 u8 level, int grplo, int grphi, int gp_tasks),
+
+        TP_ARGS(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks),
+
+        TP_STRUCT__entry(
+                __field(char *, rcuname)
+                __field(unsigned long, gpnum)
+                __field(unsigned long, mask)
+                __field(unsigned long, qsmask)
+                __field(u8, level)
+                __field(int, grplo)
+                __field(int, grphi)
+                __field(u8, gp_tasks)
+        ),
+
+        TP_fast_assign(
+                __entry->rcuname = rcuname;
+                __entry->gpnum = gpnum;
+                __entry->mask = mask;
+                __entry->qsmask = qsmask;
+                __entry->level = level;
+                __entry->grplo = grplo;
+                __entry->grphi = grphi;
+                __entry->gp_tasks = gp_tasks;
+        ),
+
+        TP_printk("%s %lu %lx>%lx %u %d %d %u",
+                  __entry->rcuname, __entry->gpnum,
+                  __entry->mask, __entry->qsmask, __entry->level,
+                  __entry->grplo, __entry->grphi, __entry->gp_tasks)
+);
+
+/*
+ * Tracepoint for quiescent states detected by force_quiescent_state().
+ * These trace events include the type of RCU, the grace-period number
+ * that was blocked by the CPU, the CPU itself, and the type of quiescent
+ * state, which can be "dti" for dyntick-idle mode, "ofl" for CPU offline,
+ * or "kick" when kicking a CPU that has b