[LINUX] Fix interaction between idle loop and RCU subsystem.

There is a problem with the current implementation of stop_hz_timer in
arch/i386/kernel/time-xen.c where the hz timer can be stopped on a CPU
which has RCU callbacks pending.

This patch backports a new RCU API created to fix this problem for the
s390 implementation of stop_hz_timer and also updates the time-xen.c
implementation of stop_hz_timer to call the new API.

Signed-off-by: Harry Butterworth <butterwo@uk.ibm.com>

diff --git a/linux-2.6-xen-sparse/arch/i386/kernel/time-xen.c b/linux-2.6-xen-sparse/arch/i386/kernel/time-xen.c
index 575596e3ee3dce27959625c9382ed6e7f7650859..fbc9f999efbc45624b954741281ce00cb9c84af7 100644 (file)
--- a/linux-2.6-xen-sparse/arch/i386/kernel/time-xen.c
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/time-xen.c
@@ -978,12 +978,19 @@ static void stop_hz_timer(void)
        unsigned int cpu = smp_processor_id();
        unsigned long j;
 
-       /* We must do this /before/ checking rcu_pending(). */
        cpu_set(cpu, nohz_cpu_mask);
+
+       /* See matching smp_mb in rcu_start_batch in rcupdate.c.  These mbs  */
+       /* ensure that if __rcu_pending (nested in rcu_needs_cpu) fetches a  */
+       /* value of rcp->cur that matches rdp->quiescbatch and allows us to  */
+       /* stop the hz timer then the cpumasks created for subsequent values */
+       /* of cur in rcu_start_batch are guaranteed to pick up the updated   */
+       /* nohz_cpu_mask and so will not depend on this cpu.                 */
+
        smp_mb();
 
        /* Leave ourselves in 'tick mode' if rcu or softirq pending. */
-       if (rcu_pending(cpu) || local_softirq_pending()) {
+       if (rcu_needs_cpu(cpu) || local_softirq_pending()) {
                cpu_clear(cpu, nohz_cpu_mask);
                j = jiffies + 1;
        } else {

diff --git a/patches/linux-2.6.16.13/rcu_needs_cpu.patch b/patches/linux-2.6.16.13/rcu_needs_cpu.patch
new file mode 100644 (file)
index 0000000..f2d60f7
--- /dev/null
+++ b/patches/linux-2.6.16.13/rcu_needs_cpu.patch
@@ -0,0 +1,33 @@
+--- ../pristine-linux-2.6.16.13/kernel/rcupdate.c      2006-05-02 22:38:44.000000000 +0100
++++ ./kernel/rcupdate.c        2006-06-09 20:27:45.000000000 +0100
+@@ -485,6 +485,20 @@ int rcu_pending(int cpu)
+               __rcu_pending(&rcu_bh_ctrlblk, &per_cpu(rcu_bh_data, cpu));
+ }
+ 
++/*
++ * Check to see if any future RCU-related work will need to be done
++ * by the current CPU, even if none need be done immediately, returning
++ * 1 if so.  This function is part of the RCU implementation; it is -not-
++ * an exported member of the RCU API.
++ */
++int rcu_needs_cpu(int cpu)
++{
++      struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
++      struct rcu_data *rdp_bh = &per_cpu(rcu_bh_data, cpu);
++
++      return (!!rdp->curlist || !!rdp_bh->curlist || rcu_pending(cpu));
++}
++
+ void rcu_check_callbacks(int cpu, int user)
+ {
+       if (user || 
+--- ../pristine-linux-2.6.16.13/include/linux/rcupdate.h       2006-05-02 22:38:44.000000000 +0100
++++ ./include/linux/rcupdate.h 2006-06-09 20:28:57.000000000 +0100
+@@ -134,6 +134,7 @@ static inline void rcu_bh_qsctr_inc(int 
+ }
+ 
+ extern int rcu_pending(int cpu);
++extern int rcu_needs_cpu(int cpu);
+ 
+ /**
+  * rcu_read_lock - mark the beginning of an RCU read-side critical section.