[PATCH v3 0/3] Assorted fixes in RISC-V PMU driver

Samuel Holland samuel.holland at sifive.com
Wed Jun 26 06:31:01 PDT 2024


Hi Atish,

On 2024-06-26 2:23 AM, Atish Patra wrote:
> This series contains 3 fixes out of which the first one is a new fix
> for invalid event data reported in lkml[2]. The last two are v3 of Samuel's
> patch[1]. I added the RB/TB/Fixes tag and moved 1 unrelated change
> to its own patch. I also changed a error message in kvm vcpu_pmu from
> pr_err to pr_debug to avoid redundant failure error messages generated
> due to the boot time quering of events implemented in the patch[1]

Thanks for picking this up! The change in patch 2 isn't quite unrelated.
pmu_sbi_check_std_events() depends on pmu_sbi_stop_all() to ensure all counters
are free at the beginning of the function. Compare v1 of the patch where the
function contains an additional call to SBI_EXT_PMU_COUNTER_STOP. With the
current patch ordering, everything works out, so it all looks good to me.

Regards,
Samuel

> Here is the original cover letter for the patch[1]
> 
> Before this patch:
> $ perf list hw
> 
> List of pre-defined events (to be used in -e or -M):
> 
>   branch-instructions OR branches                    [Hardware event]
>   branch-misses                                      [Hardware event]
>   bus-cycles                                         [Hardware event]
>   cache-misses                                       [Hardware event]
>   cache-references                                   [Hardware event]
>   cpu-cycles OR cycles                               [Hardware event]
>   instructions                                       [Hardware event]
>   ref-cycles                                         [Hardware event]
>   stalled-cycles-backend OR idle-cycles-backend      [Hardware event]
>   stalled-cycles-frontend OR idle-cycles-frontend    [Hardware event]
> 
> $ perf stat -ddd true
> 
>  Performance counter stats for 'true':
> 
>               4.36 msec task-clock                       #    0.744 CPUs utilized
>                  1      context-switches                 #  229.325 /sec
>                  0      cpu-migrations                   #    0.000 /sec
>                 38      page-faults                      #    8.714 K/sec
>          4,375,694      cycles                           #    1.003 GHz                         (60.64%)
>            728,945      instructions                     #    0.17  insn per cycle
>             79,199      branches                         #   18.162 M/sec
>             17,709      branch-misses                    #   22.36% of all branches
>            181,734      L1-dcache-loads                  #   41.676 M/sec
>              5,547      L1-dcache-load-misses            #    3.05% of all L1-dcache accesses
>      <not counted>      LLC-loads                                                               (0.00%)
>      <not counted>      LLC-load-misses                                                         (0.00%)
>      <not counted>      L1-icache-loads                                                         (0.00%)
>      <not counted>      L1-icache-load-misses                                                   (0.00%)
>      <not counted>      dTLB-loads                                                              (0.00%)
>      <not counted>      dTLB-load-misses                                                        (0.00%)
>      <not counted>      iTLB-loads                                                              (0.00%)
>      <not counted>      iTLB-load-misses                                                        (0.00%)
>      <not counted>      L1-dcache-prefetches                                                    (0.00%)
>      <not counted>      L1-dcache-prefetch-misses                                               (0.00%)
> 
>        0.005860375 seconds time elapsed
> 
>        0.000000000 seconds user
>        0.010383000 seconds sys
> 
> After this patch:
> $ perf list hw
> 
> List of pre-defined events (to be used in -e or -M):
> 
>   branch-instructions OR branches                    [Hardware event]
>   branch-misses                                      [Hardware event]
>   cache-misses                                       [Hardware event]
>   cache-references                                   [Hardware event]
>   cpu-cycles OR cycles                               [Hardware event]
>   instructions                                       [Hardware event]
> 
> $ perf stat -ddd true
> 
>  Performance counter stats for 'true':
> 
>               5.16 msec task-clock                       #    0.848 CPUs utilized
>                  1      context-switches                 #  193.817 /sec
>                  0      cpu-migrations                   #    0.000 /sec
>                 37      page-faults                      #    7.171 K/sec
>          5,183,625      cycles                           #    1.005 GHz
>            961,696      instructions                     #    0.19  insn per cycle
>             85,853      branches                         #   16.640 M/sec
>             20,462      branch-misses                    #   23.83% of all branches
>            243,545      L1-dcache-loads                  #   47.203 M/sec
>              5,974      L1-dcache-load-misses            #    2.45% of all L1-dcache accesses
>    <not supported>      LLC-loads
>    <not supported>      LLC-load-misses
>    <not supported>      L1-icache-loads
>    <not supported>      L1-icache-load-misses
>    <not supported>      dTLB-loads
>             19,619      dTLB-load-misses
>    <not supported>      iTLB-loads
>              6,831      iTLB-load-misses
>    <not supported>      L1-dcache-prefetches
>    <not supported>      L1-dcache-prefetch-misses
> 
>        0.006085625 seconds time elapsed
> 
>        0.000000000 seconds user
>        0.013022000 seconds sys
> 
> Changes in v3:
>  - Added one more fix
>  - Separated an unrelated change to its own patch.
>  - Rebase and Added RB/TB/Fixes tag.
>  - Changed a error message in kvm code to avoid unnecessary failures
>    at guest booting.
> Changes in v2:
>  - Move the event checking to a workqueue to make it asynchronous
>  - Add more details to the commit message based on the v1 discussion
> 
> [1] https://lore.kernel.org/linux-riscv/20240418014652.1143466-1-samuel.holland@sifive.com/
> [2] https://lore.kernel.org/all/CC51D53B-846C-4D81-86FC-FBF969D0A0D6@pku.edu.cn/
> 
> Signed-off-by: Atish Patra <atishp at rivosinc.com>
> ---
> Atish Patra (1):
>       drivers/perf: riscv: Do not update the event data if uptodate
> 
> Samuel Holland (2):
>       drivers/perf: riscv: Reset the counter to hpmevent mapping while starting cpus
>       perf: RISC-V: Check standard event availability
> 
>  arch/riscv/kvm/vcpu_pmu.c    |  2 +-
>  drivers/perf/riscv_pmu.c     |  2 +-
>  drivers/perf/riscv_pmu_sbi.c | 44 +++++++++++++++++++++++++++++++++++++++++---
>  3 files changed, 43 insertions(+), 5 deletions(-)
> ---
> base-commit: 55027e689933ba2e64f3d245fb1ff185b3e7fc81
> change-id: 20240625-misc_perf_fixes-5c57f555d828
> --
> Regards,
> Atish patra
> 




More information about the linux-riscv mailing list