x86/time: don't move TSC backwards in time_calibration_tsc_rendezvous()

While doing this for small amounts may be okay, the unconditional use
of CPU0's value here has been found to be a problem when the boot time
TSC of the BSP was behind that of all APs by more than a second. In
particular because of get_s_time_fixed() producing insane output when
the calculated delta is negative, we can't allow this to happen.

On the first iteration have all other CPUs sort out the highest TSC
value any one of them has read. On the second iteration, if that
maximum is higher than CPU0's, update its recorded value from that
taken in the first iteration. Use the resulting value on the last
iteration to write everyone's TSCs.

To account for the possible discontinuity, have
time_calibration_rendezvous_tail() record the newly written value, but
extrapolate local stime using the value read.

Reported-by: Claudemir Todo Bom <claudemir@todobom.com>
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
Release-Acked-by: Ian Jackson <iwj@xenproject.org>

diff --git a/xen/arch/x86/time.c b/xen/arch/x86/time.c
index a894f74b8843a25a90a68fccc8ab7761e9634eeb..6bc1fd11d6d1c3cebce0b535c4dd4dbf78e841a0 100644 (file)
--- a/xen/arch/x86/time.c
+++ b/xen/arch/x86/time.c
@@ -1658,17 +1658,17 @@ struct calibration_rendezvous {
     cpumask_t cpu_calibration_map;
     atomic_t semaphore;
     s_time_t master_stime;
-    u64 master_tsc_stamp;
+    uint64_t master_tsc_stamp, max_tsc_stamp;
 };
 
 static void
 time_calibration_rendezvous_tail(const struct calibration_rendezvous *r,
-                                 uint64_t tsc)
+                                 uint64_t old_tsc, uint64_t new_tsc)
 {
     struct cpu_time_stamp *c = &this_cpu(cpu_calibration);
 
-    c->local_tsc    = tsc;
-    c->local_stime  = get_s_time_fixed(c->local_tsc);
+    c->local_tsc    = new_tsc;
+    c->local_stime  = get_s_time_fixed(old_tsc ?: new_tsc);
     c->master_stime = r->master_stime;
 
     raise_softirq(TIME_CALIBRATE_SOFTIRQ);
@@ -1683,6 +1683,7 @@ static void time_calibration_tsc_rendezvous(void *_r)
     int i;
     struct calibration_rendezvous *r = _r;
     unsigned int total_cpus = cpumask_weight(&r->cpu_calibration_map);
+    uint64_t tsc = 0;
 
     /* Loop to get rid of cache effects on TSC skew. */
     for ( i = 4; i >= 0; i-- )
@@ -1692,8 +1693,15 @@ static void time_calibration_tsc_rendezvous(void *_r)
             while ( atomic_read(&r->semaphore) != (total_cpus - 1) )
                 cpu_relax();
 
-            if ( r->master_tsc_stamp == 0 )
-                r->master_tsc_stamp = rdtsc_ordered();
+            if ( tsc == 0 )
+                r->master_tsc_stamp = tsc = rdtsc_ordered();
+            else if ( r->master_tsc_stamp < r->max_tsc_stamp )
+                /*
+                 * We want to avoid moving the TSC backwards for any CPU.
+                 * Use the largest value observed anywhere on the first
+                 * iteration.
+                 */
+                r->master_tsc_stamp = r->max_tsc_stamp;
             else if ( i == 0 )
                 r->master_stime = read_platform_stime(NULL);
 
@@ -1712,6 +1720,15 @@ static void time_calibration_tsc_rendezvous(void *_r)
             while ( atomic_read(&r->semaphore) < total_cpus )
                 cpu_relax();
 
+            if ( tsc == 0 )
+            {
+                uint64_t cur = ACCESS_ONCE(r->max_tsc_stamp);
+
+                tsc = rdtsc_ordered();
+                while ( tsc > cur )
+                    cur = cmpxchg(&r->max_tsc_stamp, cur, tsc);
+            }
+
             if ( i == 0 )
                 write_tsc(r->master_tsc_stamp);
 
@@ -1719,9 +1736,12 @@ static void time_calibration_tsc_rendezvous(void *_r)
             while ( atomic_read(&r->semaphore) > total_cpus )
                 cpu_relax();
         }
+
+        /* Just in case a read above ended up reading zero. */
+        tsc += !tsc;
     }
 
-    time_calibration_rendezvous_tail(r, r->master_tsc_stamp);
+    time_calibration_rendezvous_tail(r, tsc, r->master_tsc_stamp);
 }
 
 /* Ordinary rendezvous function which does not modify TSC values. */
@@ -1746,7 +1766,7 @@ static void time_calibration_std_rendezvous(void *_r)
         smp_rmb(); /* receive signal /then/ read r->master_stime */
     }
 
-    time_calibration_rendezvous_tail(r, rdtsc_ordered());
+    time_calibration_rendezvous_tail(r, 0, rdtsc_ordered());
 }
 
 /*