Skip to content

Improve PMU support

Atish Patra qemu-devel qemu-riscv 12 versions – In review

Get series with b4
b4 am [email protected]

Versions newest first · linked by author and title

  1. v14 Latest5 patches 14 repliesIn review
  2. v136 patches 4 repliesApplied
  3. v126 patches 10 repliesSuperseded
Earlier versions · 9
VersionPostedPatchesRepliesStatus
v116 patches13 repliesSuperseded
v1012 patches21 repliesSuperseded
v912 patches6 repliesSuperseded
v812 patches4 repliesSuperseded
v712 patches10 repliesSuperseded
v612 patches6 repliesSuperseded
v5 posting 2/212 patches10 repliesSuperseded
v5 posting 1/20 of 12 patches0 repliesSuperseded
v411 patches15 repliesSuperseded

Changes in v14 from the cover letter

1. Added sanity check for the hashtable in pmu.c

Patches in v14 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/5target/riscv: Add sscofpmf extension supporttarget/riscv/cpu.c target/riscv/cpu.h target/riscv/cpu_bits.h +4 more+623 -110 replies
2/5target/riscv: Simplify counter predicate functiontarget/riscv/csr.c+9 -1010 replies
3/5target/riscv: Add few cache related PMU eventstarget/riscv/cpu_helper.c+25 -00 replies
4/5hw/riscv: virt: Add PMU DT node to the device treehw/riscv/virt.c target/riscv/pmu.c target/riscv/pmu.h+74 -012 replies
5/5target/riscv: Update the privilege field for sscofpmf CSRstarget/riscv/csr.c+60 -300 replies

Reviews trailers per patch

All 5 patches have a Reviewed-by or Acked-by.

PatchAlistair FrancisBin MengHeiko StuebnerWeiwei Li
1/5R-b T-b
2/5A-b R-b
3/5R-b T-b
4/5A-b
5/5R-b R-b

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes. Scroll the table sideways for all 4 reviewers.

Read the v14 thread

Cover letter [PATCH v14 0/5] Improve PMU support

The latest version of the SBI specification includes a Performance Monitoring Unit(PMU) extension[1] which allows the supervisor to start/stop/configure various PMU events. The Sscofpmf ('Ss' for Privileged arch and Supervisor-level extensions, and 'cofpmf' for Count OverFlow and Privilege Mode Filtering) extension[2] allows the perf like tool to handle overflow interrupts and filtering support.

This series implements remaining PMU infrastructure to support PMU in virt machine. The first seven patches from the original series have been merged already.

This will allow us to add any PMU events in future. Currently, this series enables the following omu events.
1. cycle count
2. instruction count
3. DTLB load/store miss
4. ITLB prefetch miss

The first two are computed using host ticks while last three are counted during cpu_tlb_fill. We can do both sampling and count from guest userspace. This series has been tested on both RV64 and RV32. Both Linux[3] and Opensbi[4] patches are required to get the perf working.

Here is an output of perf stat/report while running hackbench with latest OpenSBI & Linux kernel.

Perf stat:
==========
[root@fedora-riscv ~]# perf stat -e cycles -e instructions -e dTLB-load-misses -e dTLB-store-misses -e iTLB-load-misses \

Quoted 1 line

perf bench sched messaging -g 1 -l 10

# Running 'sched/messaging' benchmark:
# 20 sender and receiver processes per group
# 1 groups == 40 processes run

     Total time: 0.265 [sec]

Performance counter stats for 'perf bench sched messaging -g 1 -l 10':

     4,167,825,362      cycles                                                      
     4,166,609,256      instructions              #    1.00  insn per cycle         
         3,092,026      dTLB-load-misses                                            
           258,280      dTLB-store-misses                                           
         2,068,966      iTLB-load-misses                                            
       0.585791767 seconds time elapsed

       0.373802000 seconds user
       1.042359000 seconds sys

Perf record:
============
[root@fedora-riscv ~]# perf record -e cycles -e instructions \

Quoted 2 lines

-e dTLB-load-misses -e dTLB-store-misses -e iTLB-load-misses -c 10000 \
perf bench sched messaging -g 1 -l 10

# Running 'sched/messaging' benchmark:
# 20 sender and receiver processes per group
# 1 groups == 40 processes run

     Total time: 1.397 [sec]

[ perf record: Woken up 10 times to write data ]
Check IO/CPU overload!
[ perf record: Captured and wrote 8.211 MB perf.data (214486 samples) ]

[root@fedora-riscv riscv]# perf report
Available samples

107K cycles                                                                    ◆
107K instructions                                                              ▒
250 dTLB-load-misses                                                           ▒
13 dTLB-store-misses                                                           ▒

172 iTLB-load-misses
..

Changes from v13->v14:
1. Added sanity check for the hashtable in pmu.c

Changes from v12->v13:
1. Rebased on top of the apply-next.
2. Addressed comments about space & comment block.

Changes from v11->v12:
1. Rebased on top of the apply-next.
2. Aligned the write function & .min_priv to the previous line.
3. Fixed the FDT generations for multi-socket scenario.
4. Dropped interrupt property from the DT.
5. Generate illegal instruction fault instead of virtual instruction fault for VS/VU access while mcounteren is not set.

Changes from v10->v11:
1. Rebased on top of the master where first 7 patches were already merged.
2. Removed unnecessary additional check in ctr predicate function.
3. Removed unnecessary priv version checks in mcountinhibit read/write.
4. Added Heiko's reviewed-by/tested-by tags.

Changes from v8->v9:
1. Added the write_done flags to the vmstate.
2. Fixed the hpmcounter read access from M-mode.

Changes from v7->v8:
1. Removeding ordering constraints for mhpmcounter & mhpmevent.

Changes from v6->v7:
1. Fixed all the compilation errors for the usermode.

Changes from v5->v6:
1. Fixed compilation issue with PATCH 1.
2. Addressed other comments.

Changes from v4->v5:
1. Rebased on top of the -next with following patches.
- isa extension
- priv 1.12 spec
2. Addressed all the comments on v4
3. Removed additional isa-ext DT node in favor of riscv,isa string update

Changes from v3->v4:
1. Removed the dummy events from pmu DT node.
2. Fixed pmu_avail_counters mask generation.
3. Added a patch to simplify the predicate function for counters.

Changes from v2->v3:
1. Addressed all the comments on PATCH1-4.
2. Split patch1 into two separate patches.
3. Added explicit comments to explain the event types in DT node.
4. Rebased on latest Qemu.

Changes from v1->v2:
1. Dropped the ACks from v1 as signficant changes happened after v1.
2. sscofpmf support.
3. A generic counter management framework.

[1] https://github.com/riscv-non-isa/riscv-sbi-doc/blob/master/riscv-sbi.adoc
[2] https://drive.google.com/file/d/171j4jFjIkKdj5LWcExphq4xG_2sihbfd/edit
[3] https://github.com/atishp04/qemu/tree/riscv_pmu_v14

Atish Patra (5):
target/riscv: Add sscofpmf extension support target/riscv: Simplify counter predicate function target/riscv: Add few cache related PMU events hw/riscv: virt: Add PMU DT node to the device tree target/riscv: Update the privilege field for sscofpmf CSRs

hw/riscv/virt.c           |  16 ++
target/riscv/cpu.c        |  12 ++
target/riscv/cpu.h        |  25 +++
target/riscv/cpu_bits.h   |  55 +++++
target/riscv/cpu_helper.c |  25 +++
target/riscv/csr.c        | 304 +++++++++++++++++----------
target/riscv/machine.c    |   1 +
target/riscv/pmu.c        | 425 +++++++++++++++++++++++++++++++++++++-
target/riscv/pmu.h        |   8 +
9 files changed, 760 insertions(+), 111 deletions(-)

--
2.25.1