Message-ID: <87h6oh2apx.fsf@all.your.base.are.belong.to.us>
Date:   Wed, 30 Aug 2023 10:30:50 +0200
From:   Björn Töpel <bjorn@...nel.org>
To:     Daniel Borkmann <daniel@...earbox.net>,
        Puranjay Mohan <puranjay12@...il.com>,
        paul.walmsley@...ive.com, palmer@...belt.com,
        aou@...s.berkeley.edu, pulehui@...wei.com,
        conor.dooley@...rochip.com, ast@...nel.org, andrii@...nel.org,
        martin.lau@...ux.dev, song@...nel.org, yhs@...com,
        kpsingh@...nel.org, bpf@...r.kernel.org,
        linux-riscv@...ts.infradead.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH bpf-next v3 0/3] bpf, riscv: use BPF prog pack allocator
 in BPF JIT

Daniel Borkmann <daniel@...earbox.net> writes:

> On 8/29/23 12:06 PM, Björn Töpel wrote:
>> Puranjay Mohan <puranjay12@...il.com> writes:
>> 
>>> Changes in v2 -> v3:
>>> 1. Fix maximum width of code in patches from 80 to 100. [All patches]
>>> 2. Add checks for ctx->ro_insns == NULL. [Patch 3]
>>> 3. Fix check for edge condition where amount of text to set > 2 * pagesize
>>>     [Patch 1 and 2]
>>> 4. Add reviewed-by in patches.
>>> 5. Adding results of selftest here:
>>>     Using the command: ./test_progs on qemu
>>>     Without the series: Summary: 336/3162 PASSED, 56 SKIPPED, 90 FAILED
>>>     With this series: Summary: 336/3162 PASSED, 56 SKIPPED, 90 FAILED
>>>
>>> Changes in v1 -> v2:
>>> 1. Implement a new function patch_text_set_nosync() to be used in bpf_arch_text_invalidate().
>>>     The implementation in v1 called patch_text_nosync() in a loop and it was bad as it would
>>>     call flush_icache_range() for every word making it really slow. This was found by running
>>>     the test_tag selftest which would take forever to complete.
>>>
>>> Here is some data to prove the V2 fixes the problem:
>>>
>>> Without this series:
>>> root@...selftester:~/src/kselftest/bpf# time ./test_tag
>>> test_tag: OK (40945 tests)
>>>
>>> real    7m47.562s
>>> user    0m24.145s
>>> sys     6m37.064s
>>>
>>> With this series applied:
>>> root@...selftester:~/src/selftest/bpf# time ./test_tag
>>> test_tag: OK (40945 tests)
>>>
>>> real    7m29.472s
>>> user    0m25.865s
>>> sys     6m18.401s
>>>
>>> BPF programs currently consume a page each on RISCV. For systems with many BPF
>>> programs, this adds significant pressure to instruction TLB. High iTLB pressure
>>> usually causes slow down for the whole system.
>>>
>>> Song Liu introduced the BPF prog pack allocator[1] to mitigate the above issue.
>>> It packs multiple BPF programs into a single huge page. It is currently only
>>> enabled for the x86_64 BPF JIT.
>>>
>>> I enabled this allocator on the ARM64 BPF JIT[2]. It is being reviewed now.
>>>
>>> This patch series enables the BPF prog pack allocator for the RISCV BPF JIT.
>>> This series needs a patch[3] from the ARM64 series to work.
>>>
>>> ======================================================
>>> Performance Analysis of prog pack allocator on RISCV64
>>> ======================================================
>>>
>>> Test setup:
>>> ===========
>>>
>>> Host machine: Debian GNU/Linux 11 (bullseye)
>>> Qemu Version: QEMU emulator version 8.0.3 (Debian 1:8.0.3+dfsg-1)
>>> u-boot-qemu Version: 2023.07+dfsg-1
>>> opensbi Version: 1.3-1
>>>
>>> To test the performance of the BPF prog pack allocator on RV, a stresser
>>> tool[4] linked below was built. This tool loads 8 BPF programs on the system and
>>> triggers 5 of them in an infinite loop by doing system calls.
>>>
>>> The runner script starts 20 instances of the above which loads 8*20=160 BPF
>>> programs on the system, 5*20=100 of which are being constantly triggered.
>>> The script is passed a command which would be run in the above environment.
>>>
>>> The script was run with following perf command:
>>> ./run.sh "perf stat -a \
>>>          -e iTLB-load-misses \
>>>          -e dTLB-load-misses  \
>>>          -e dTLB-store-misses \
>>>          -e instructions \
>>>          --timeout 60000"
>>>
>>> The output of the above command is discussed below before and after enabling the
>>> BPF prog pack allocator.
>>>
>>> The tests were run on qemu-system-riscv64 with 8 cpus, 16G memory. The rootfs
>>> was created using Bjorn's riscv-cross-builder[5] docker container linked below.
>>>
>>> Results
>>> =======
>>>
>>> Before enabling prog pack allocator:
>>> ------------------------------------
>>>
>>> Performance counter stats for 'system wide':
>>>
>>>             4939048      iTLB-load-misses
>>>             5468689      dTLB-load-misses
>>>              465234      dTLB-store-misses
>>>       1441082097998      instructions
>>>
>>>        60.045791200 seconds time elapsed
>>>
>>> After enabling prog pack allocator:
>>> -----------------------------------
>>>
>>> Performance counter stats for 'system wide':
>>>
>>>             3430035      iTLB-load-misses
>>>             5008745      dTLB-load-misses
>>>              409944      dTLB-store-misses
>>>       1441535637988      instructions
>>>
>>>        60.046296600 seconds time elapsed
>>>
>>> Improvements in metrics
>>> =======================
>>>
>>> It was expected that the iTLB-load-misses would decrease as now a single huge
>>> page is used to keep all the BPF programs compared to a single page for each
>>> program earlier.
>>>
>>> --------------------------------------------
>>> The improvement in iTLB-load-misses: -30.5 %
>>> --------------------------------------------
>>>
>>> I repeated this expriment more than 100 times in different setups and the
>>> improvement was always greater than 30%.
>>>
>>> This patch series is boot tested on the Starfive VisionFive 2 board[6].
>>> The performance analysis was not done on the board because it doesn't
>>> expose iTLB-load-misses, etc. The stresser program was run on the board to test
>>> the loading and unloading of BPF programs
>>>
>>> [1] https://lore.kernel.org/bpf/20220204185742.271030-1-song@kernel.org/
>>> [2] https://lore.kernel.org/all/20230626085811.3192402-1-puranjay12@gmail.com/
>>> [3] https://lore.kernel.org/all/20230626085811.3192402-2-puranjay12@gmail.com/
>>> [4] https://github.com/puranjaymohan/BPF-Allocator-Bench
>>> [5] https://github.com/bjoto/riscv-cross-builder
>>> [6] https://www.starfivetech.com/en/site/boards
>>>
>>> Puranjay Mohan (3):
>>>    riscv: extend patch_text_nosync() for multiple pages
>>>    riscv: implement a memset like function for text
>>>    bpf, riscv: use prog pack allocator in the BPF JIT
>> 
>> Thank you! For the series:
>> 
>> Acked-by: Björn Töpel <bjorn@...nel.org>
>> Tested-by: Björn Töpel <bjorn@...osinc.com>
>> 
>> @Alexei @Daniel This series depends on a core BPF patch from the Arm
>>                  series [3].
>> 
>> @Palmer LMK if you have any concerns taking the RISC-V text patching
>>          stuff via the BPF tree.
>
> Palmer, did the riscv PR already go to Linus?
>
> If not yet, perhaps you could ship this series along with your PR to Linus
> during this merge window given the big net PR (incl. bpf) was already merged
> yesterday. So from our side only fixes ship to Linus.
>
> Otherwise we could take it into bpf-next for the next dev cycle if there are
> no objections, let us know.

Daniel, I'll bring this up on the RISC-V patchwork sync meeting [1]
today.

[1] https://lore.kernel.org/linux-riscv/mhng-775d4068-6c1e-48a4-a1dc-b4a76ff26bb3@palmer-ri-x1c9a/

Powered by blists - more mailing lists