From: Yonghong Song <yhs@fb.com>
To: Brendan Jackman <jackmanb@google.com>
Cc: <bpf@vger.kernel.org>, Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
KP Singh <kpsingh@chromium.org>,
Florent Revest <revest@chromium.org>,
<linux-kernel@vger.kernel.org>, Jann Horn <jannh@google.com>
Subject: Re: [PATCH bpf-next v3 09/14] bpf: Pull out a macro for interpreting atomic ALU operations
Date: Fri, 4 Dec 2020 07:20:18 -0800 [thread overview]
Message-ID: <4a39dd08-f0ca-595f-1f59-a6acb44f3176@fb.com> (raw)
In-Reply-To: <X8oBaf4c+EAd8LQE@google.com>
On 12/4/20 1:29 AM, Brendan Jackman wrote:
> On Thu, Dec 03, 2020 at 10:30:18PM -0800, Yonghong Song wrote:
>>
>>
>> On 12/3/20 8:02 AM, Brendan Jackman wrote:
>>> Since the atomic operations that are added in subsequent commits are
>>> all isomorphic with BPF_ADD, pull out a macro to avoid the
>>> interpreter becoming dominated by lines of atomic-related code.
>>>
>>> Note that this sacrificies interpreter performance (combining
>>> STX_ATOMIC_W and STX_ATOMIC_DW into single switch case means that we
>>> need an extra conditional branch to differentiate them) in favour of
>>> compact and (relatively!) simple C code.
>>>
>>> Change-Id: I8cae5b66e75f34393de6063b91c05a8006fdd9e6
>>> Signed-off-by: Brendan Jackman <jackmanb@google.com>
>>
>> Ack with a minor suggestion below.
>>
>> Acked-by: Yonghong Song <yhs@fb.com>
>>
>>> ---
>>> kernel/bpf/core.c | 79 +++++++++++++++++++++++------------------------
>>> 1 file changed, 38 insertions(+), 41 deletions(-)
>>>
>>> diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
>>> index 28f960bc2e30..498d3f067be7 100644
>>> --- a/kernel/bpf/core.c
>>> +++ b/kernel/bpf/core.c
>>> @@ -1618,55 +1618,52 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
>>> LDX_PROBE(DW, 8)
>>> #undef LDX_PROBE
>>> - STX_ATOMIC_W:
>>> - switch (IMM) {
>>> - case BPF_ADD:
>>> - /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */
>>> - atomic_add((u32) SRC, (atomic_t *)(unsigned long)
>>> - (DST + insn->off));
>>> - break;
>>> - case BPF_ADD | BPF_FETCH:
>>> - SRC = (u32) atomic_fetch_add(
>>> - (u32) SRC,
>>> - (atomic_t *)(unsigned long) (DST + insn->off));
>>> - break;
>>> - case BPF_XCHG:
>>> - SRC = (u32) atomic_xchg(
>>> - (atomic_t *)(unsigned long) (DST + insn->off),
>>> - (u32) SRC);
>>> - break;
>>> - case BPF_CMPXCHG:
>>> - BPF_R0 = (u32) atomic_cmpxchg(
>>> - (atomic_t *)(unsigned long) (DST + insn->off),
>>> - (u32) BPF_R0, (u32) SRC);
>>> +#define ATOMIC(BOP, KOP) \
>>
>> ATOMIC a little bit generic. Maybe ATOMIC_FETCH_BOP?
>
> Well it doesn't fetch in all cases and "BOP" is intended to
> differentiate from KOP i.e. BOP = BPF operation KOP = Kernel operation.
>
> Could go with ATOMIC_ALU_OP?
ATOMIC_ALU_OP sounds good.
>
>>> + case BOP: \
>>> + if (BPF_SIZE(insn->code) == BPF_W) \
>>> + atomic_##KOP((u32) SRC, (atomic_t *)(unsigned long) \
>>> + (DST + insn->off)); \
>>> + else \
>>> + atomic64_##KOP((u64) SRC, (atomic64_t *)(unsigned long) \
>>> + (DST + insn->off)); \
>>> + break; \
>>> + case BOP | BPF_FETCH: \
>>> + if (BPF_SIZE(insn->code) == BPF_W) \
>>> + SRC = (u32) atomic_fetch_##KOP( \
>>> + (u32) SRC, \
>>> + (atomic_t *)(unsigned long) (DST + insn->off)); \
>>> + else \
>>> + SRC = (u64) atomic64_fetch_##KOP( \
>>> + (u64) SRC, \
>>> + (atomic64_t *)(s64) (DST + insn->off)); \
>>> break;
>>> - default:
>>> - goto default_label;
>>> - }
>>> - CONT;
>>> STX_ATOMIC_DW:
>>> + STX_ATOMIC_W:
>>> switch (IMM) {
>>> - case BPF_ADD:
>>> - /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */
>>> - atomic64_add((u64) SRC, (atomic64_t *)(unsigned long)
>>> - (DST + insn->off));
>>> - break;
>>> - case BPF_ADD | BPF_FETCH:
>>> - SRC = (u64) atomic64_fetch_add(
>>> - (u64) SRC,
>>> - (atomic64_t *)(s64) (DST + insn->off));
>>> - break;
>>> + ATOMIC(BPF_ADD, add)
>>> +
>>> case BPF_XCHG:
>>> - SRC = (u64) atomic64_xchg(
>>> - (atomic64_t *)(u64) (DST + insn->off),
>>> - (u64) SRC);
>>> + if (BPF_SIZE(insn->code) == BPF_W)
>>> + SRC = (u32) atomic_xchg(
>>> + (atomic_t *)(unsigned long) (DST + insn->off),
>>> + (u32) SRC);
>>> + else
>>> + SRC = (u64) atomic64_xchg(
>>> + (atomic64_t *)(u64) (DST + insn->off),
>>> + (u64) SRC);
>>> break;
>>> case BPF_CMPXCHG:
>>> - BPF_R0 = (u64) atomic64_cmpxchg(
>>> - (atomic64_t *)(u64) (DST + insn->off),
>>> - (u64) BPF_R0, (u64) SRC);
>>> + if (BPF_SIZE(insn->code) == BPF_W)
>>> + BPF_R0 = (u32) atomic_cmpxchg(
>>> + (atomic_t *)(unsigned long) (DST + insn->off),
>>> + (u32) BPF_R0, (u32) SRC);
>>> + else
>>> + BPF_R0 = (u64) atomic64_cmpxchg(
>>> + (atomic64_t *)(u64) (DST + insn->off),
>>> + (u64) BPF_R0, (u64) SRC);
>>> break;
>>> +
>>> default:
>>> goto default_label;
>>> }
>>>
next prev parent reply other threads:[~2020-12-04 15:21 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-03 16:02 [PATCH bpf-next v3 00/14] Atomics for eBPF Brendan Jackman
2020-12-03 16:02 ` [PATCH bpf-next v3 01/14] bpf: x86: Factor out emission of ModR/M for *(reg + off) Brendan Jackman
2020-12-03 16:02 ` [PATCH bpf-next v3 02/14] bpf: x86: Factor out emission of REX byte Brendan Jackman
2020-12-03 16:02 ` [PATCH bpf-next v3 03/14] bpf: x86: Factor out function to emit NEG Brendan Jackman
2020-12-03 16:02 ` [PATCH bpf-next v3 04/14] bpf: x86: Factor out a lookup table for some ALU opcodes Brendan Jackman
2020-12-03 16:02 ` [PATCH bpf-next v3 05/14] bpf: Rename BPF_XADD and prepare to encode other atomics in .imm Brendan Jackman
2020-12-04 4:49 ` Yonghong Song
2020-12-03 16:02 ` [PATCH bpf-next v3 06/14] bpf: Move BPF_STX reserved field check into BPF_STX verifier code Brendan Jackman
2020-12-04 4:51 ` Yonghong Song
2020-12-03 16:02 ` [PATCH bpf-next v3 07/14] bpf: Add BPF_FETCH field / create atomic_fetch_add instruction Brendan Jackman
2020-12-04 5:02 ` Yonghong Song
2020-12-04 5:27 ` Yonghong Song
2020-12-04 9:12 ` Brendan Jackman
2020-12-03 16:02 ` [PATCH bpf-next v3 08/14] bpf: Add instructions for atomic_[cmp]xchg Brendan Jackman
2020-12-04 5:34 ` Yonghong Song
2020-12-04 9:26 ` Brendan Jackman
2020-12-03 16:02 ` [PATCH bpf-next v3 09/14] bpf: Pull out a macro for interpreting atomic ALU operations Brendan Jackman
2020-12-04 6:30 ` Yonghong Song
2020-12-04 9:29 ` Brendan Jackman
2020-12-04 15:20 ` Yonghong Song [this message]
2020-12-03 16:02 ` [PATCH bpf-next v3 10/14] bpf: Add bitwise atomic instructions Brendan Jackman
2020-12-04 6:42 ` Yonghong Song
2020-12-04 9:36 ` Brendan Jackman
2020-12-04 15:21 ` Yonghong Song
2020-12-07 11:28 ` Brendan Jackman
2020-12-07 15:58 ` Yonghong Song
2020-12-07 16:14 ` Brendan Jackman
2020-12-03 16:02 ` [PATCH bpf-next v3 11/14] tools build: Implement feature check for BPF atomics in Clang Brendan Jackman
2020-12-03 21:02 ` Andrii Nakryiko
2020-12-03 16:02 ` [PATCH bpf-next v3 12/14] bpf: Pull tools/build/feature biz into selftests Makefile Brendan Jackman
2020-12-03 21:01 ` Andrii Nakryiko
2020-12-04 9:41 ` Brendan Jackman
2020-12-04 19:00 ` Andrii Nakryiko
2020-12-07 11:00 ` Brendan Jackman
2020-12-08 2:19 ` Andrii Nakryiko
2020-12-08 17:04 ` Brendan Jackman
2020-12-08 18:31 ` Andrii Nakryiko
2020-12-03 16:02 ` [PATCH bpf-next v3 13/14] bpf: Add tests for new BPF atomic operations Brendan Jackman
2020-12-04 7:06 ` Yonghong Song
2020-12-04 9:45 ` Brendan Jackman
2020-12-04 15:28 ` Yonghong Song
2020-12-04 19:49 ` Andrii Nakryiko
2020-12-07 15:48 ` Brendan Jackman
2020-12-03 16:02 ` [PATCH bpf-next v3 14/14] bpf: Document new atomic instructions Brendan Jackman
2020-12-03 16:10 ` [PATCH bpf-next v3 00/14] Atomics for eBPF Brendan Jackman
2020-12-04 4:46 ` Yonghong Song
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4a39dd08-f0ca-595f-1f59-a6acb44f3176@fb.com \
--to=yhs@fb.com \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=jackmanb@google.com \
--cc=jannh@google.com \
--cc=kpsingh@chromium.org \
--cc=linux-kernel@vger.kernel.org \
--cc=revest@chromium.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).