sched: fix locking for insert_vcpu() in credit1 and RTDS

The insert_vcpu() hook is handled with inconsistent locking.
In fact, schedule_cpu_switch() calls the hook with runqueue
lock held, while sched_move_domain() relies on the hook
implementations to take the lock themselves (and, since that
is not done in Credit1 and RTDS, such operation is not safe
in those cases).

This is fixed as follows:
 - take the lock in the hook implementations, in specific
   schedulers' code;
 - avoid calling insert_vcpu(), for the idle vCPU, in
   schedule_cpu_switch(). In fact, idle vCPUs are set to run
   immediately, and the various schedulers won't insert them
   in their runqueues anyway, even when explicitly asked to.

While there, still in schedule_cpu_switch(), locking with
_irq() is enough (there's no need to do *_irqsave()).

Signed-off-by: Dario Faggioli <dario.faggioli@citrix.com>
Reviewed-by: Meng Xu <mengxu@cis.upenn.edu>
Reviewed-by: George Dunlap <george.dunlap@citrix.com>
master commit: ae2f41e3d7e7798537b7ea6dbb9a0c6aeb1179e3
master date: 2015-11-24 14:48:34 +0100

diff --git a/xen/common/sched_credit.c b/xen/common/sched_credit.c
index 81f351089a726a8eacdfe12bd14326c1cd8dbc1d..f08075d0571735c3a6096648caf6c3549c917a84 100644 (file)
--- a/xen/common/sched_credit.c
+++ b/xen/common/sched_credit.c
@@ -910,9 +910,15 @@ static void
 csched_vcpu_insert(const struct scheduler *ops, struct vcpu *vc)
 {
     struct csched_vcpu *svc = vc->sched_priv;
+    spinlock_t *lock;
+    unsigned long flags;
+
+    lock = vcpu_schedule_lock_irqsave(vc, &flags);
 
     if ( !__vcpu_on_runq(svc) && vcpu_runnable(vc) && !vc->is_running )
         __runq_insert(vc->processor, svc);
+
+    vcpu_schedule_unlock_irqrestore(lock, flags, vc);
 }
 
 static void

diff --git a/xen/common/schedule.c b/xen/common/schedule.c
index 79768c59d8b1cae233164a14530adb0025ecb7f9..f2a7427769ac886e0bc4ab58364f9019c9300343 100644 (file)
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
@@ -1418,7 +1418,6 @@ void __init scheduler_init(void)
 
 int schedule_cpu_switch(unsigned int cpu, struct cpupool *c)
 {
-    unsigned long flags;
     struct vcpu *idle;
     spinlock_t *lock;
     void *ppriv, *ppriv_old, *vpriv, *vpriv_old;
@@ -1439,7 +1438,7 @@ int schedule_cpu_switch(unsigned int cpu, struct cpupool *c)
         return -ENOMEM;
     }
 
-    lock = pcpu_schedule_lock_irqsave(cpu, &flags);
+    lock = pcpu_schedule_lock_irq(cpu);
 
     SCHED_OP(old_ops, tick_suspend, cpu);
     vpriv_old = idle->sched_priv;
@@ -1448,9 +1447,8 @@ int schedule_cpu_switch(unsigned int cpu, struct cpupool *c)
     ppriv_old = per_cpu(schedule_data, cpu).sched_priv;
     per_cpu(schedule_data, cpu).sched_priv = ppriv;
     SCHED_OP(new_ops, tick_resume, cpu);
-    SCHED_OP(new_ops, insert_vcpu, idle);
 
-    pcpu_schedule_unlock_irqrestore(lock, flags, cpu);
+    pcpu_schedule_unlock_irq(lock, cpu);
 
     SCHED_OP(old_ops, free_vdata, vpriv_old);
     SCHED_OP(old_ops, free_pdata, ppriv_old, cpu);