[xen stable-4.13] sched: allow rcu work to happen when syncing cpus in core scheduling

[patchbot@xxxxxxx]

commit f2ad77ba78224a9cc21e14f57bb1d2210d561e0b
Author:     Juergen Gross <jgross@xxxxxxxx>
AuthorDate: Wed Jun 24 16:26:11 2020 +0200
Commit:     Jan Beulich <jbeulich@xxxxxxxx>
CommitDate: Wed Jun 24 16:26:11 2020 +0200

    sched: allow rcu work to happen when syncing cpus in core scheduling
    
    With RCU barriers moved from tasklets to normal RCU processing cpu
    offlining in core scheduling might deadlock due to cpu synchronization
    required by RCU processing and core scheduling concurrently.
    
    Fix that by bailing out from core scheduling synchronization in case
    of pending RCU work. Additionally the RCU softirq is now required to
    be of higher priority than the scheduling softirqs in order to do
    RCU processing before entering the scheduler again, as bailing out from
    the core scheduling synchronization requires to raise another softirq
    SCHED_SLAVE, which would bypass RCU processing again.
    
    Reported-by: Sergey Dyasli <sergey.dyasli@xxxxxxxxxx>
    Tested-by: Sergey Dyasli <sergey.dyasli@xxxxxxxxxx>
    Signed-off-by: Juergen Gross <jgross@xxxxxxxx>
    Acked-by: Dario Faggioli <dfaggioli@xxxxxxxx>
    master commit: 4e9c57c4edbabab1b66f965db0203100097944ff
    master date: 2020-05-15 16:04:00 +0200
---
 xen/common/schedule.c     | 13 ++++++++++---
 xen/include/xen/softirq.h |  2 +-
 2 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/xen/common/schedule.c b/xen/common/schedule.c
index 6d24a3a135..ccc20ce040 100644
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
@@ -2270,13 +2270,20 @@ static struct sched_unit 
*sched_wait_rendezvous_in(struct sched_unit *prev,
             v = unit2vcpu_cpu(prev, cpu);
         }
         /*
-         * Coming from idle might need to do tasklet work.
+         * Check for any work to be done which might need cpu synchronization.
+         * This is either pending RCU work, or tasklet work when coming from
+         * idle. It is mandatory that RCU softirqs are of higher priority
+         * than scheduling ones as otherwise a deadlock might occur.
          * In order to avoid deadlocks we can't do that here, but have to
-         * continue the idle loop.
+         * schedule the previous vcpu again, which will lead to the desired
+         * processing to be done.
          * Undo the rendezvous_in_cnt decrement and schedule another call of
          * sched_slave().
          */
-        if ( is_idle_unit(prev) && sched_tasklet_check_cpu(cpu) )
+        BUILD_BUG_ON(RCU_SOFTIRQ > SCHED_SLAVE_SOFTIRQ ||
+                     RCU_SOFTIRQ > SCHEDULE_SOFTIRQ);
+        if ( rcu_pending(cpu) ||
+             (is_idle_unit(prev) && sched_tasklet_check_cpu(cpu)) )
         {
             struct vcpu *vprev = current;
 
diff --git a/xen/include/xen/softirq.h b/xen/include/xen/softirq.h
index d7273b389b..d21b048b8c 100644
--- a/xen/include/xen/softirq.h
+++ b/xen/include/xen/softirq.h
@@ -4,10 +4,10 @@
 /* Low-latency softirqs come first in the following list. */
 enum {
     TIMER_SOFTIRQ = 0,
+    RCU_SOFTIRQ,
     SCHED_SLAVE_SOFTIRQ,
     SCHEDULE_SOFTIRQ,
     NEW_TLBFLUSH_CLOCK_PERIOD_SOFTIRQ,
-    RCU_SOFTIRQ,
     TASKLET_SOFTIRQ,
     NR_COMMON_SOFTIRQS
 };
--
generated by git-patchbot for /home/xen/git/xen.git#stable-4.13