[PATCH v9 74/74] cputlb: queue async flush jobs without the BQL

[Robert Foley]

From: "Emilio G. Cota" <address@hidden>

This yields sizable scalability improvements, as the below results show.

Host: Two Intel Xeon Silver 4114 10-core CPUs at 2.20 GHz

VM: Ubuntu 18.04 ppc64

                   Speedup vs a single thread for kernel build                  
                                                                               
  7 +-----------------------------------------------------------------------+  
    |         +          +         +         +         +          +         |  
    |                                    ###########       baseline ******* |  
    |                               #####           ####   cpu lock ####### |  
    |                             ##                    ####                |  
  6 |-+                         ##                          ##            +-|  
    |                         ##                              ####          |  
    |                       ##                                    ###       |  
    |                     ##        *****                            #      |  
    |                   ##      ****     ***                          #     |  
    |                 ##     ***            *                               |  
  5 |-+             ##    ***                ****                         +-|  
    |              #  ****                       **                         |  
    |             # **                             **                       |  
    |             #*                                 **                     |  
    |          #*                                          **               |  
    |         #*                                             *              |  
    |         #                                               ******        |  
    |        #                                                      **      |  
    |       #                                                         *     |  
  3 |-+     #                                                             +-|  
    |      #                                                                |  
    |      #                                                                |  
    |     #                                                                 |  
    |     #                                                                 |  
  2 |-+  #                                                                +-|  
    |    #                                                                  |  
    |   #                                                                   |  
    |   #                                                                   |  
    |  #                                                                    |  
    |  #      +          +         +         +         +          +         |  
  1 +-----------------------------------------------------------------------+  
    0         5          10        15        20        25         30        35  
                                   Guest vCPUs  
Pictures are also here:
https://drive.google.com/file/d/1ASg5XyP9hNfN9VysXC3qe5s9QSJlwFAt/view?usp=sharing

Some notes:
- baseline corresponds to the commit before this series
- cpu-lock is this series

Single-threaded performance is affected very lightly. Results
below for debian aarch64 bootup+test for the entire series
on an Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz host:

- Before:

 Performance counter stats for 'taskset -c 0 ../img/aarch64/die.sh' (10 runs):

       7269.033478      task-clock (msec)         #    0.998 CPUs utilized
      ( +-  0.06% )
    30,659,870,302      cycles                    #    4.218 GHz
      ( +-  0.06% )
    54,790,540,051      instructions              #    1.79  insns per cycle
      ( +-  0.05% )
     9,796,441,380      branches                  # 1347.695 M/sec
      ( +-  0.05% )
       165,132,201      branch-misses             #    1.69% of all branches
      ( +-  0.12% )

       7.287011656 seconds time elapsed
 ( +-  0.10% )

- After:

       7375.924053      task-clock (msec)         #    0.998 CPUs utilized
      ( +-  0.13% )
    31,107,548,846      cycles                    #    4.217 GHz
      ( +-  0.12% )
    55,355,668,947      instructions              #    1.78  insns per cycle
      ( +-  0.05% )
     9,929,917,664      branches                  # 1346.261 M/sec
      ( +-  0.04% )
       166,547,442      branch-misses             #    1.68% of all branches
      ( +-  0.09% )

       7.389068145 seconds time elapsed
 ( +-  0.13% )

That is, a 1.37% slowdown.

Reviewed-by: Alex Bennée <address@hidden>
Reviewed-by: Richard Henderson <address@hidden>
Tested-by: Alex Bennée <address@hidden>
Signed-off-by: Emilio G. Cota <address@hidden>
[Updated the speedup chart results for re-based series.]
Signed-off-by: Robert Foley <address@hidden>
---
 accel/tcg/cputlb.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index eb2cf9de5e..50bc76fb61 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -284,7 +284,7 @@ static void flush_all_helper(CPUState *src, run_on_cpu_func 
fn,
 
     CPU_FOREACH(cpu) {
         if (cpu != src) {
-            async_run_on_cpu(cpu, fn, d);
+            async_run_on_cpu_no_bql(cpu, fn, d);
         }
     }
 }
@@ -352,8 +352,8 @@ void tlb_flush_by_mmuidx(CPUState *cpu, uint16_t idxmap)
     tlb_debug("mmu_idx: 0x%" PRIx16 "\n", idxmap);
 
     if (cpu->created && !qemu_cpu_is_self(cpu)) {
-        async_run_on_cpu(cpu, tlb_flush_by_mmuidx_async_work,
-                         RUN_ON_CPU_HOST_INT(idxmap));
+        async_run_on_cpu_no_bql(cpu, tlb_flush_by_mmuidx_async_work,
+                                RUN_ON_CPU_HOST_INT(idxmap));
     } else {
         tlb_flush_by_mmuidx_async_work(cpu, RUN_ON_CPU_HOST_INT(idxmap));
     }
@@ -547,7 +547,7 @@ void tlb_flush_page_by_mmuidx(CPUState *cpu, target_ulong 
addr, uint16_t idxmap)
          * we can stuff idxmap into the low TARGET_PAGE_BITS, avoid
          * allocating memory for this operation.
          */
-        async_run_on_cpu(cpu, tlb_flush_page_by_mmuidx_async_1,
+        async_run_on_cpu_no_bql(cpu, tlb_flush_page_by_mmuidx_async_1,
                          RUN_ON_CPU_TARGET_PTR(addr | idxmap));
     } else {
         TLBFlushPageByMMUIdxData *d = g_new(TLBFlushPageByMMUIdxData, 1);
@@ -555,7 +555,7 @@ void tlb_flush_page_by_mmuidx(CPUState *cpu, target_ulong 
addr, uint16_t idxmap)
         /* Otherwise allocate a structure, freed by the worker.  */
         d->addr = addr;
         d->idxmap = idxmap;
-        async_run_on_cpu(cpu, tlb_flush_page_by_mmuidx_async_2,
+        async_run_on_cpu_no_bql(cpu, tlb_flush_page_by_mmuidx_async_2,
                          RUN_ON_CPU_HOST_PTR(d));
     }
 }
-- 
2.17.1