From: Andrii Nakryiko <andrii.nakryiko@gmail.com>
To: Alexei Starovoitov <ast@kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>,
Daniel Borkmann <daniel@iogearbox.net>,
Andrii Nakryiko <andriin@fb.com>,
Networking <netdev@vger.kernel.org>, bpf <bpf@vger.kernel.org>,
Kernel Team <kernel-team@fb.com>
Subject: Re: [PATCH v2 bpf-next 1/9] bpf: track spill/fill of constants
Date: Fri, 14 Jun 2019 09:29:56 -0700 [thread overview]
Message-ID: <CAEf4BzZ03j8DkBz0CN+-HbKcxWcHy+woHZKTjJDkq+SkFqD7RQ@mail.gmail.com> (raw)
In-Reply-To: <20190614072557.196239-2-ast@kernel.org>
On Fri, Jun 14, 2019 at 12:26 AM Alexei Starovoitov <ast@kernel.org> wrote:
>
> Compilers often spill induction variables into the stack,
> hence it is necessary for the verifier to track scalar values
> of the registers through stack slots.
>
> Also few bpf programs were incorrectly rejected in the past,
> since the verifier was not able to track such constants while
> they were used to compute offsets into packet headers.
>
> Tracking constants through the stack significantly decreases
> the chances of state pruning, since two different constants
> are considered to be different by state equivalency.
> End result that cilium tests suffer serious degradation in the number
> of states processed and corresponding verification time increase.
>
> before after
> bpf_lb-DLB_L3.o 1838 6441
> bpf_lb-DLB_L4.o 3218 5908
> bpf_lb-DUNKNOWN.o 1064 1064
> bpf_lxc-DDROP_ALL.o 26935 93790
> bpf_lxc-DUNKNOWN.o 34439 123886
> bpf_netdev.o 9721 31413
> bpf_overlay.o 6184 18561
> bpf_lxc_jit.o 39389 359445
>
> After further debugging turned out that cillium progs are
> getting hurt by clang due to the same constant tracking issue.
> Newer clang generates better code by spilling less to the stack.
> Instead it keeps more constants in the registers which
> hurts state pruning since the verifier already tracks constants
> in the registers:
> old clang new clang
> (no spill/fill tracking introduced by this patch)
> bpf_lb-DLB_L3.o 1838 1923
> bpf_lb-DLB_L4.o 3218 3077
> bpf_lb-DUNKNOWN.o 1064 1062
> bpf_lxc-DDROP_ALL.o 26935 166729
> bpf_lxc-DUNKNOWN.o 34439 174607
> bpf_netdev.o 9721 8407
> bpf_overlay.o 6184 5420
> bpf_lcx_jit.o 39389 39389
>
> The final table is depressing:
> old clang old clang new clang new clang
> const spill/fill const spill/fill
> bpf_lb-DLB_L3.o 1838 6441 1923 8128
> bpf_lb-DLB_L4.o 3218 5908 3077 6707
> bpf_lb-DUNKNOWN.o 1064 1064 1062 1062
> bpf_lxc-DDROP_ALL.o 26935 93790 166729 380712
> bpf_lxc-DUNKNOWN.o 34439 123886 174607 440652
> bpf_netdev.o 9721 31413 8407 31904
> bpf_overlay.o 6184 18561 5420 23569
> bpf_lxc_jit.o 39389 359445 39389 359445
>
> Tracking constants in the registers hurts state pruning already.
> Adding tracking of constants through stack hurts pruning even more.
> The later patch address this general constant tracking issue
> with coarse/precise logic.
>
> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
> ---
This looks good as well, thanks!
Acked-by: Andrii Nakryiko <andriin@fb.com>
> kernel/bpf/verifier.c | 90 +++++++++++++++++++++++++++++++------------
> 1 file changed, 65 insertions(+), 25 deletions(-)
>
next prev parent reply other threads:[~2019-06-14 16:30 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-14 7:25 [PATCH v2 bpf-next 0/9] bpf: bounded loops and other features Alexei Starovoitov
2019-06-14 7:25 ` [PATCH v2 bpf-next 1/9] bpf: track spill/fill of constants Alexei Starovoitov
2019-06-14 16:29 ` Andrii Nakryiko [this message]
2019-06-14 7:25 ` [PATCH v2 bpf-next 2/9] selftests/bpf: fix tests due to const spill/fill Alexei Starovoitov
2019-06-14 7:25 ` [PATCH v2 bpf-next 3/9] bpf: extend is_branch_taken to registers Alexei Starovoitov
2019-06-14 16:38 ` Andrii Nakryiko
2019-06-14 7:25 ` [PATCH v2 bpf-next 4/9] bpf: introduce bounded loops Alexei Starovoitov
2019-06-14 7:25 ` [PATCH v2 bpf-next 5/9] bpf: fix callees pruning callers Alexei Starovoitov
2019-06-14 7:25 ` [PATCH v2 bpf-next 6/9] selftests/bpf: fix tests Alexei Starovoitov
2019-06-14 7:25 ` [PATCH v2 bpf-next 7/9] selftests/bpf: add basic verifier tests for loops Alexei Starovoitov
2019-06-14 7:25 ` [PATCH v2 bpf-next 8/9] selftests/bpf: add realistic loop tests Alexei Starovoitov
2019-06-14 16:49 ` Andrii Nakryiko
2019-06-14 7:25 ` [PATCH v2 bpf-next 9/9] bpf: precise scalar_value tracking Alexei Starovoitov
2019-06-14 21:45 ` Andrii Nakryiko
2019-06-15 19:00 ` Alexei Starovoitov
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=CAEf4BzZ03j8DkBz0CN+-HbKcxWcHy+woHZKTjJDkq+SkFqD7RQ@mail.gmail.com \
--to=andrii.nakryiko@gmail.com \
--cc=andriin@fb.com \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=kernel-team@fb.com \
--cc=netdev@vger.kernel.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).