xen: Have schedulers revise initial placement

The generic domain creation logic in
xen/common/domctl.c:default_vcpu0_location() attempts to try to do
initial placement load-balancing by placing vcpu 0 on the least-busy
non-primary hyperthread available.  Unfortunately, the logic can end
up picking a pcpu that's not in the online mask.  When this is passed
to a scheduler such which assumes that the initial assignment is
valid, it causes a null pointer dereference looking up the runqueue.

Furthermore, this initial placement doesn't take into account hard or
soft affinity, or any scheduler-specific knowledge (such as historic
runqueue load, as in credit2).

To solve this, when inserting a vcpu, always call the per-scheduler
"pick" function to revise the initial placement.  This will
automatically take all knowledge the scheduler has into account.

csched2_cpu_pick ASSERTs that the vcpu's pcpu scheduler lock has been
taken.  Grab and release the lock to minimize time spend with irqs
disabled.

Signed-off-by: George Dunlap <george.dunlap@citrix.com>
Reviewed-by: Meng Xu <mengxu@cis.upenn.edu>
Reviwed-by: Dario Faggioli <dario.faggioli@citrix.com>
master commit: 9f358ddd69463fa8fb65cf67beb5f6f0d3350e32
master date: 2016-07-26 10:42:49 +0100

diff --git a/xen/common/sched_credit.c b/xen/common/sched_credit.c
index 8a20f08dd16bf12e95e7c6d03360c4e0d08eeae4..57d7558526c8a196a96f8501b1cb637a000dd488 100644 (file)
--- a/xen/common/sched_credit.c
+++ b/xen/common/sched_credit.c
@@ -893,6 +893,9 @@ csched_vcpu_insert(const struct scheduler *ops, struct vcpu *vc)
 
     BUG_ON( is_idle_vcpu(vc) );
 
+    /* This is safe because vc isn't yet being scheduled */
+    vc->processor = csched_cpu_pick(ops, vc);
+
     lock = vcpu_schedule_lock_irq(vc);
 
     if ( !__vcpu_on_runq(svc) && vcpu_runnable(vc) && !vc->is_running )

diff --git a/xen/common/sched_credit2.c b/xen/common/sched_credit2.c
index 2ab030476f9b86df9a16d48bbde199f18507b8c6..94c17e356807c58c756f89c18153412ff8c66cc2 100644 (file)
--- a/xen/common/sched_credit2.c
+++ b/xen/common/sched_credit2.c
@@ -269,6 +269,7 @@ struct csched2_dom {
     uint16_t nr_vcpus;
 };
 
+static int csched2_cpu_pick(const struct scheduler *ops, struct vcpu *vc);
 
 /*
  * Time-to-credit, credit-to-time.
@@ -870,9 +871,16 @@ csched2_vcpu_insert(const struct scheduler *ops, struct vcpu *vc)
     /* FIXME: Do we need the private lock here? */
     list_add_tail(&svc->sdom_elem, &svc->sdom->vcpu);
 
-    /* Add vcpu to runqueue of initial processor */
+    /* csched2_cpu_pick() expects the pcpu lock to be held */
+    lock = vcpu_schedule_lock_irq(vc);
+
+    vc->processor = csched2_cpu_pick(ops, vc);
+
+    spin_unlock_irq(lock);
+
     lock = vcpu_schedule_lock_irq(vc);
 
+    /* Add vcpu to runqueue of initial processor */
     runq_assign(ops, vc);
 
     vcpu_schedule_unlock_irq(lock, vc);

diff --git a/xen/common/sched_rt.c b/xen/common/sched_rt.c
index e50041c8ced245d5e2471d8e026eb07a7dca1374..c1256d8d3b4c46be2e0b471e2a39dbb526a0d53c 100644 (file)
--- a/xen/common/sched_rt.c
+++ b/xen/common/sched_rt.c
@@ -169,6 +169,8 @@ struct rt_dom {
     struct domain *dom;         /* pointer to upper domain */
 };
 
+static int rt_cpu_pick(const struct scheduler *ops, struct vcpu *vc);
+
 /*
  * Useful inline functions
  */
@@ -552,6 +554,9 @@ rt_vcpu_insert(const struct scheduler *ops, struct vcpu *vc)
 
     BUG_ON( is_idle_vcpu(vc) );
 
+    /* This is safe because vc isn't yet being scheduled */
+    vc->processor = rt_cpu_pick(ops, vc);
+
     lock = vcpu_schedule_lock_irq(vc);
 
     now = NOW();