powerpc/paravirt: Use is_kvm_guest() in vcpu_is_preempted()

If its a shared LPAR but not a KVM guest, then see if the vCPU is
related to the calling vCPU. On PowerVM, only cores can be preempted.
So if one vCPU is a non-preempted state, we can decipher that all
other vCPUs sharing the same core are in non-preempted state.

Performance results:

  $ perf stat -r 5 -a perf bench sched pipe -l 10000000 (lesser time is better)

  powerpc/next
       35,107,951.20 msec cpu-clock                 #  255.898 CPUs utilized            ( +-  0.31% )
          23,655,348      context-switches          #    0.674 K/sec                    ( +-  3.72% )
              14,465      cpu-migrations            #    0.000 K/sec                    ( +-  5.37% )
              82,463      page-faults               #    0.002 K/sec                    ( +-  8.40% )
   1,127,182,328,206      cycles                    #    0.032 GHz                      ( +-  1.60% )  (66.67%)
      78,587,300,622      stalled-cycles-frontend   #    6.97% frontend cycles idle     ( +-  0.08% )  (50.01%)
     654,124,218,432      stalled-cycles-backend    #   58.03% backend cycles idle      ( +-  1.74% )  (50.01%)
     834,013,059,242      instructions              #    0.74  insn per cycle
                                                    #    0.78  stalled cycles per insn  ( +-  0.73% )  (66.67%)
     132,911,454,387      branches                  #    3.786 M/sec                    ( +-  0.59% )  (50.00%)
       2,890,882,143      branch-misses             #    2.18% of all branches          ( +-  0.46% )  (50.00%)

             137.195 +- 0.419 seconds time elapsed  ( +-  0.31% )

  powerpc/next + patchset
       29,981,702.64 msec cpu-clock                 #  255.881 CPUs utilized            ( +-  1.30% )
          40,162,456      context-switches          #    0.001 M/sec                    ( +-  0.01% )
               1,110      cpu-migrations            #    0.000 K/sec                    ( +-  5.20% )
              62,616      page-faults               #    0.002 K/sec                    ( +-  3.93% )
   1,430,030,626,037      cycles                    #    0.048 GHz                      ( +-  1.41% )  (66.67%)
      83,202,707,288      stalled-cycles-frontend   #    5.82% frontend cycles idle     ( +-  0.75% )  (50.01%)
     744,556,088,520      stalled-cycles-backend    #   52.07% backend cycles idle      ( +-  1.39% )  (50.01%)
     940,138,418,674      instructions              #    0.66  insn per cycle
                                                    #    0.79  stalled cycles per insn  ( +-  0.51% )  (66.67%)
     146,452,852,283      branches                  #    4.885 M/sec                    ( +-  0.80% )  (50.00%)
       3,237,743,996      branch-misses             #    2.21% of all branches          ( +-  1.18% )  (50.01%)

              117.17 +- 1.52 seconds time elapsed  ( +-  1.30% )

This is around 14.6% improvement in performance.

Signed-off-by: Srikar Dronamraju <[email protected]>
Acked-by: Waiman Long <[email protected]>
[mpe: Fold in performance results from cover letter]
Signed-off-by: Michael Ellerman <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: srikard

arch/powerpc/include/asm/paravirt.h

@@ -10,6 +10,9 @@
 #endif
 
 #ifdef CONFIG_PPC_SPLPAR
+#include <asm/kvm_guest.h>
+#include <asm/cputhreads.h>
+
 DECLARE_STATIC_KEY_FALSE(shared_processor);
 
 static inline bool is_shared_processor(void)
@@ -74,6 +77,21 @@ static inline bool vcpu_is_preempted(int cpu)
 {
 	if (!is_shared_processor())
 		return false;
+
+#ifdef CONFIG_PPC_SPLPAR
+	if (!is_kvm_guest()) {
+		int first_cpu = cpu_first_thread_sibling(smp_processor_id());
+
+		/*
+		 * Preemption can only happen at core granularity. This CPU
+		 * is not preempted if one of the CPU of this core is not
+		 * preempted.
+		 */
+		if (cpu_first_thread_sibling(cpu) == first_cpu)
+			return false;
+	}
+#endif
+
 	if (yield_count_of(cpu) & 1)
 		return true;
 	return false;