Merge git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched

* git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched:
  softlockup: fix task state setting
  rcu: add support for dynamic ticks and preempt rcu

4 files changed, 231 insertions, 10 deletions

diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index 987cfb7ade89..c7c52096df48 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -23,6 +23,10 @@
  *              to Suparna Bhattacharya for pushing me completely away
  *              from atomic instructions on the read side.
  *
+ *  - Added handling of Dynamic Ticks
+ *      Copyright 2007 - Paul E. Mckenney <paulmck@us.ibm.com>
+ *                     - Steven Rostedt <srostedt@redhat.com>
+ *
  * Papers:  http://www.rdrop.com/users/paulmck/RCU
  *
  * Design Document: http://lwn.net/Articles/253651/
@@ -409,6 +413,212 @@ static void __rcu_advance_callbacks(struct rcu_data *rdp)
         }
 }
 
+#ifdef CONFIG_NO_HZ
+
+DEFINE_PER_CPU(long, dynticks_progress_counter) = 1;
+static DEFINE_PER_CPU(long, rcu_dyntick_snapshot);
+static DEFINE_PER_CPU(int, rcu_update_flag);
+
+/**
+ * rcu_irq_enter - Called from Hard irq handlers and NMI/SMI.
+ *
+ * If the CPU was idle with dynamic ticks active, this updates the
+ * dynticks_progress_counter to let the RCU handling know that the
+ * CPU is active.
+ */
+void rcu_irq_enter(void)
+{
+        int cpu = smp_processor_id();
+
+        if (per_cpu(rcu_update_flag, cpu))
+                per_cpu(rcu_update_flag, cpu)++;
+
+        /*
+         * Only update if we are coming from a stopped ticks mode
+         * (dynticks_progress_counter is even).
+         */
+        if (!in_interrupt() &&
+            (per_cpu(dynticks_progress_counter, cpu) & 0x1) == 0) {
+                /*
+                 * The following might seem like we could have a race
+                 * with NMI/SMIs. But this really isn't a problem.
+                 * Here we do a read/modify/write, and the race happens
+                 * when an NMI/SMI comes in after the read and before
+                 * the write. But NMI/SMIs will increment this counter
+                 * twice before returning, so the zero bit will not
+                 * be corrupted by the NMI/SMI which is the most important
+                 * part.
+                 *
+                 * The only thing is that we would bring back the counter
+                 * to a postion that it was in during the NMI/SMI.
+                 * But the zero bit would be set, so the rest of the
+                 * counter would again be ignored.
+                 *
+                 * On return from the IRQ, the counter may have the zero
+                 * bit be 0 and the counter the same as the return from
+                 * the NMI/SMI. If the state machine was so unlucky to
+                 * see that, it still doesn't matter, since all
+                 * RCU read-side critical sections on this CPU would
+                 * have already completed.
+                 */
+                per_cpu(dynticks_progress_counter, cpu)++;
+                /*
+                 * The following memory barrier ensures that any
+                 * rcu_read_lock() primitives in the irq handler
+                 * are seen by other CPUs to follow the above
+                 * increment to dynticks_progress_counter. This is
+                 * required in order for other CPUs to correctly
+                 * determine when it is safe to advance the RCU
+                 * grace-period state machine.
+                 */
+                smp_mb(); /* see above block comment. */
+                /*
+                 * Since we can't determine the dynamic tick mode from
+                 * the dynticks_progress_counter after this routine,
+                 * we use a second flag to acknowledge that we came
+                 * from an idle state with ticks stopped.
+                 */
+                per_cpu(rcu_update_flag, cpu)++;
+                /*
+                 * If we take an NMI/SMI now, they will also increment
+                 * the rcu_update_flag, and will not update the
+                 * dynticks_progress_counter on exit. That is for
+                 * this IRQ to do.
+                 */
+        }
+}
+
+/**
+ * rcu_irq_exit - Called from exiting Hard irq context.
+ *
+ * If the CPU was idle with dynamic ticks active, update the
+ * dynticks_progress_counter to put let the RCU handling be
+ * aware that the CPU is going back to idle with no ticks.
+ */
+void rcu_irq_exit(void)
+{
+        int cpu = smp_processor_id();
+
+        /*
+         * rcu_update_flag is set if we interrupted the CPU
+         * when it was idle with ticks stopped.
+         * Once this occurs, we keep track of interrupt nesting
+         * because a NMI/SMI could also come in, and we still
+         * only want the IRQ that started the increment of the
+         * dynticks_progress_counter to be the one that modifies
+         * it on exit.
+         */
+        if (per_cpu(rcu_update_flag, cpu)) {
+                if (--per_cpu(rcu_update_flag, cpu))
+                        return;
+
+                /* This must match the interrupt nesting */
+                WARN_ON(in_interrupt());
+
+                /*
+                 * If an NMI/SMI happens now we are still
+                 * protected by the dynticks_progress_counter being odd.
+                 */
+
+                /*
+                 * The following memory barrier ensures that any
+                 * rcu_read_unlock() primitives in the irq handler
+                 * are seen by other CPUs to preceed the following
+                 * increment to dynticks_progress_counter. This
+                 * is required in order for other CPUs to determine
+                 * when it is safe to advance the RCU grace-period
+                 * state machine.
+                 */
+                smp_mb(); /* see above block comment. */
+                per_cpu(dynticks_progress_counter, cpu)++;
+                WARN_ON(per_cpu(dynticks_progress_counter, cpu) & 0x1);
+        }
+}
+
+static void dyntick_save_progress_counter(int cpu)
+{
+        per_cpu(rcu_dyntick_snapshot, cpu) =
+                per_cpu(dynticks_progress_counter, cpu);
+}
+
+static inline int
+rcu_try_flip_waitack_needed(int cpu)
+{
+        long curr;
+        long snap;
+
+        curr = per_cpu(dynticks_progress_counter, cpu);
+        snap = per_cpu(rcu_dyntick_snapshot, cpu);
+        smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
+
+        /*
+         * If the CPU remained in dynticks mode for the entire time
+         * and didn't take any interrupts, NMIs, SMIs, or whatever,
+         * then it cannot be in the middle of an rcu_read_lock(), so
+         * the next rcu_read_lock() it executes must use the new value
+         * of the counter.  So we can safely pretend that this CPU
+         * already acknowledged the counter.
+         */
+
+        if ((curr == snap) && ((curr & 0x1) == 0))
+                return 0;
+
+        /*
+         * If the CPU passed through or entered a dynticks idle phase with
+         * no active irq handlers, then, as above, we can safely pretend
+         * that this CPU already acknowledged the counter.
+         */
+
+        if ((curr - snap) > 2 || (snap & 0x1) == 0)
+                return 0;
+
+        /* We need this CPU to explicitly acknowledge the counter flip. */
+
+        return 1;
+}
+
+static inline int
+rcu_try_flip_waitmb_needed(int cpu)
+{
+        long curr;
+        long snap;
+
+        curr = per_cpu(dynticks_progress_counter, cpu);
+        snap = per_cpu(rcu_dyntick_snapshot, cpu);
+        smp_mb(); /* force ordering with cpu entering/leaving dynticks. */