rcu: add grace-period age and more kthread state to tracing

This commit adds the age in jiffies of the current grace period along
with the duration in jiffies of the longest grace period since boot
to the rcu/rcugp debugfs file.  It also adds an additional "O" state
to kthread tracing to differentiate between the kthread waiting due to
having nothing to do on the one hand and waiting due to being on the
wrong CPU on the other hand.

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

diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 40b530dd0fc7b977aaf69b857c5ce5178ddbcf76..fd4bffb6e8c92057ad8a7c739775d10148102ccd 100644 (file)
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -159,8 +159,8 @@ o   "qs" gives an indication of the state of the callback queue
        the corresponding character is replaced by ".".
 
 o      "kt" is the per-CPU kernel-thread state.  The digit preceding
-       the slash is zero if there is no work pending and 1 otherwise.
-       The character after the slash is as follows:
+       the first slash is zero if there is no work pending and 1
+       otherwise.  The character between the slashes is as follows:
 
        "S"     The kernel thread is stopped, in other words, all
                CPUs corresponding to this rcu_node structure are
@@ -171,10 +171,18 @@ o "kt" is the per-CPU kernel-thread state.  The digit preceding
        "W"     The kernel thread is waiting because there is no work
                for it to do.
 
+       "O"     The kernel thread is waiting because it has been
+               forced off of its designated CPU or because its
+               ->cpus_allowed mask permits it to run on other than
+               its designated CPU.
+
        "Y"     The kernel thread is yielding to avoid hogging CPU.
 
        "?"     Unknown value, indicates a bug.
 
+       The number after the final slash is the CPU that the kthread
+       is actually running on.
+
 o      "b" is the batch limit for this CPU.  If more than this number
        of RCU callbacks is ready to invoke, then the remainder will
        be deferred.

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index bb84deca3319bc114845cfbf88518f89bd1556d9..27b6d8de82f6ddfdfa40b56f8dab343e0eef5835 100644 (file)
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -92,6 +92,7 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active);
  */
 static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
 DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
+DEFINE_PER_CPU(int, rcu_cpu_kthread_cpu);
 static DEFINE_PER_CPU(wait_queue_head_t, rcu_cpu_wq);
 DEFINE_PER_CPU(char, rcu_cpu_has_work);
 static char rcu_kthreads_spawnable;
@@ -888,6 +889,8 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
        __releases(rcu_get_root(rsp)->lock)
 {
+       unsigned long gp_duration;
+
        WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
 
        /*
@@ -895,6 +898,9 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
         * is seen before the assignment to rsp->completed.
         */
        smp_mb(); /* See above block comment. */
+       gp_duration = jiffies - rsp->gp_start;
+       if (gp_duration > rsp->gp_max)
+               rsp->gp_max = gp_duration;
        rsp->completed = rsp->gpnum;
        rsp->signaled = RCU_GP_IDLE;
        rcu_start_gp(rsp, flags);  /* releases root node's rnp->lock. */
@@ -1583,12 +1589,15 @@ static int rcu_cpu_kthread_should_stop(int cpu)
               smp_processor_id() != cpu) {
                if (kthread_should_stop())
                        return 1;
+               per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
+               per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id();
                local_bh_enable();
                schedule_timeout_uninterruptible(1);
                if (!cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)))
                        set_cpus_allowed_ptr(current, cpumask_of(cpu));
                local_bh_disable();
        }
+       per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
        return 0;
 }
 
@@ -1656,6 +1665,7 @@ static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
        if (IS_ERR(t))
                return PTR_ERR(t);
        kthread_bind(t, cpu);
+       per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
        WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL);
        per_cpu(rcu_cpu_kthread_task, cpu) = t;
        wake_up_process(t);

diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 67341dbebd95961af287a81cc95005292b66bd65..37502a27a0724fd0c96f789d888f12218fc21d76 100644 (file)
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -93,8 +93,9 @@ struct rcu_dynticks {
 #define RCU_KTHREAD_STOPPED  0
 #define RCU_KTHREAD_RUNNING  1
 #define RCU_KTHREAD_WAITING  2
-#define RCU_KTHREAD_YIELDING 3
-#define RCU_KTHREAD_MAX      3
+#define RCU_KTHREAD_OFFCPU   3
+#define RCU_KTHREAD_YIELDING 4
+#define RCU_KTHREAD_MAX      4
 
 /*
  * Definition for node within the RCU grace-period-detection hierarchy.
@@ -383,6 +384,8 @@ struct rcu_state {
                                                /*  but in jiffies. */
        unsigned long jiffies_stall;            /* Time at which to check */
                                                /*  for CPU stalls. */
+       unsigned long gp_max;                   /* Maximum GP duration in */
+                                               /*  jiffies. */
        char *name;                             /* Name of structure. */
 };
 

diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index 3baa235786b568e0e6334be907a41fa10f9182ec..564b8fef2a7e3335412e668a8d9a95d6b875ccab 100644 (file)
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -47,13 +47,14 @@
 #include "rcutree.h"
 
 DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
+DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_cpu);
 DECLARE_PER_CPU(char, rcu_cpu_has_work);
 
 static char convert_kthread_status(unsigned int kthread_status)
 {
        if (kthread_status > RCU_KTHREAD_MAX)
                return '?';
-       return "SRWY"[kthread_status];
+       return "SRWOY"[kthread_status];
 }
 
 static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
@@ -74,7 +75,7 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
                   rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
        seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi);
-       seq_printf(m, " ql=%ld qs=%c%c%c%c kt=%d/%c b=%ld",
+       seq_printf(m, " ql=%ld qs=%c%c%c%c kt=%d/%c/%d b=%ld",
                   rdp->qlen,
                   ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] !=
                        rdp->nxttail[RCU_NEXT_TAIL]],
@@ -86,6 +87,7 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
                   per_cpu(rcu_cpu_has_work, rdp->cpu),
                   convert_kthread_status(per_cpu(rcu_cpu_kthread_status,
                                          rdp->cpu)),
+                  per_cpu(rcu_cpu_kthread_cpu, rdp->cpu),
                   rdp->blimit);
        seq_printf(m, " ci=%lu co=%lu ca=%lu\n",
                   rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted);
@@ -312,16 +314,35 @@ static const struct file_operations rcuhier_fops = {
        .release = single_release,
 };
 
+static void show_one_rcugp(struct seq_file *m, struct rcu_state *rsp)
+{
+       unsigned long flags;
+       unsigned long completed;
+       unsigned long gpnum;
+       unsigned long gpage;
+       unsigned long gpmax;
+       struct rcu_node *rnp = &rsp->node[0];
+
+       raw_spin_lock_irqsave(&rnp->lock, flags);
+       completed = rsp->completed;
+       gpnum = rsp->gpnum;
+       if (rsp->completed == rsp->gpnum)
+               gpage = 0;
+       else
+               gpage = jiffies - rsp->gp_start;
+       gpmax = rsp->gp_max;
+       raw_spin_unlock_irqrestore(&rnp->lock, flags);
+       seq_printf(m, "%s: completed=%ld  gpnum=%lu  age=%ld  max=%ld\n",
+                  rsp->name, completed, gpnum, gpage, gpmax);
+}
+
 static int show_rcugp(struct seq_file *m, void *unused)
 {
 #ifdef CONFIG_TREE_PREEMPT_RCU
-       seq_printf(m, "rcu_preempt: completed=%ld  gpnum=%lu\n",
-                  rcu_preempt_state.completed, rcu_preempt_state.gpnum);
+       show_one_rcugp(m, &rcu_preempt_state);
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-       seq_printf(m, "rcu_sched: completed=%ld  gpnum=%lu\n",
-                  rcu_sched_state.completed, rcu_sched_state.gpnum);
-       seq_printf(m, "rcu_bh: completed=%ld  gpnum=%lu\n",
-                  rcu_bh_state.completed, rcu_bh_state.gpnum);
+       show_one_rcugp(m, &rcu_sched_state);
+       show_one_rcugp(m, &rcu_bh_state);
        return 0;
 }