[Xen-changelog] [xen master] sched: fix race between sched_move_domain() and vcpu_wake()

[patchbot@xxxxxxx]

commit ef55257bc81204e34691f1c2aa9e01f2d0768bdd
Author:     David Vrabel <david.vrabel@xxxxxxxxxx>
AuthorDate: Mon Oct 14 08:58:31 2013 +0200
Commit:     Jan Beulich <jbeulich@xxxxxxxx>
CommitDate: Mon Oct 14 08:58:31 2013 +0200

    sched: fix race between sched_move_domain() and vcpu_wake()
    
    From: David Vrabel <david.vrabel@xxxxxxxxxx>
    
    sched_move_domain() changes v->processor for all the domain's VCPUs.
    If another domain, softirq etc. triggers a simultaneous call to
    vcpu_wake() (e.g., by setting an event channel as pending), then
    vcpu_wake() may lock one schedule lock and try to unlock another.
    
    vcpu_schedule_lock() attempts to handle this but only does so for the
    window between reading the schedule_lock from the per-CPU data and the
    spin_lock() call.  This does not help with sched_move_domain()
    changing v->processor between the calls to vcpu_schedule_lock() and
    vcpu_schedule_unlock().
    
    Fix the race by taking the schedule_lock for v->processor in
    sched_move_domain().
    
    Signed-off-by: David Vrabel <david.vrabel@xxxxxxxxxx>
    Acked-by: Juergen Gross <juergen.gross@xxxxxxxxxxxxxx>
    
    Use vcpu_schedule_lock_irq() (which now returns the lock) to properly
    retry the locking should the to be used lock have changed in the course
    of acquiring it (issue pointed out by George Dunlap).
    
    Add a comment explaining the state after the v->processor adjustment.
    
    Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
    Reviewed-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
    Acked-by: Keir Fraser <keir@xxxxxxx>
---
 xen/common/schedule.c |   11 +++++++++++
 1 files changed, 11 insertions(+), 0 deletions(-)

diff --git a/xen/common/schedule.c b/xen/common/schedule.c
index 95472ba..af3abc2 100644
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
@@ -276,6 +276,8 @@ int sched_move_domain(struct domain *d, struct cpupool *c)
     new_p = cpumask_first(c->cpu_valid);
     for_each_vcpu ( d, v )
     {
+        spinlock_t *lock;
+
         vcpudata = v->sched_priv;
 
         migrate_timer(&v->periodic_timer, new_p);
@@ -283,7 +285,16 @@ int sched_move_domain(struct domain *d, struct cpupool *c)
         migrate_timer(&v->poll_timer, new_p);
 
         cpumask_setall(v->cpu_affinity);
+
+        lock = vcpu_schedule_lock_irq(v);
         v->processor = new_p;
+        /*
+         * With v->processor modified we must not
+         * - make any further changes assuming we hold the scheduler lock,
+         * - use vcpu_schedule_unlock_irq().
+         */
+        spin_unlock_irq(lock);
+
         v->sched_priv = vcpu_priv[v->vcpu_id];
         evtchn_move_pirqs(v);
 
--
generated by git-patchbot for /home/xen/git/xen.git#master

_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxx
http://lists.xensource.com/xen-changelog