From: illusionist.neo@gmail.com (Shubham Bansal)
To: linux-arm-kernel@lists.infradead.org
Subject: arch: arm: bpf: Converting cBPF to eBPF for arm 32 bit
Date: Wed, 8 Feb 2017 12:59:29 +0530 [thread overview]
Message-ID: <CAHgaXd+cUbmQ20sPVVG88c7QAPMQzSw710tRA8BFTU5sCafuRw@mail.gmail.com> (raw)
In-Reply-To: <CAHgaXd+EKJ0FWaaPojsNJtgY_YpdQXu6eMEp97uOpTFAWs4qTQ@mail.gmail.com>
Anybody willing to take swing at my following comments ?
On Wed, Feb 1, 2017 at 6:31 PM, Shubham Bansal
<illusionist.neo@gmail.com> wrote:
> Hi Kees & Daniel,
>
> On Tue, Jan 31, 2017 at 09:44:56AM -0800, Kees Cook wrote:
>> >> > 1.) Currently, as eBPF uses 64 bit registers, I am mapping 64 bit eBPF
>> >> > registers with 32 bit arm registers which looks wrong to me. Do anybody
>> >> > have some idea about how to map eBPF->arm 32 bit registers ?
>> >>
>> >> I was going to say "look at the x86 32-bit implementation." ... But
>> >> there isn't one. :( I'm going to guess that there isn't a very good
>> >> answer here. I assume you'll have to build some kind of stack scratch
>> >> space to load/save.
>> >
>> >
>> > Now I see why nobody has implemented eBPF JIT for the 32 bit systems. I
>> > think its very difficult to implement it without any complications and
>> > errors.
>>
>> Yeah, that does seem to make it much more difficult.
> I was thinking of first implementing only instructions with 32 bit
> register operands. It will hugely decrease the surface area of eBPF
> instructions that I have to cover for the first patch.
>
> So, What I am thinking is something like this :
>
> - bpf_mov r0(64),r1(64) will be JITed like this :
> - ar1(32) <- r1(64). Convert/Mask 64 bit ebpf register(r1) value into 32
> bit and store it in arm register(ar1).
> - Do MOV ar0(32),ar1(32) as an ARM instruction.
> - ar0(32) -> r0(64). Zero Extend the ar0 32 bit register value
> and store it in 64 bit ebpf register r0.
>
> - Similarly, For all BPF_ALU class instructions.
> - For BPF_ADD, I will mask the addition result to 32 bit only.
> I am not sure, Overflow might be a problem.
> - For BPF_SUB, I will mask the subtraction result to 32 bit only.
> I am not sure, Underflow might be problem.
> - For BPF_MUL, similar to BPF_ADD. Overflow Problem ?
> - For BPF_DIV, 32 bit masking should be fine, I guess.
> - For BPF_OR, BPF_AND, BPF_XOR, BPF_LSH, BPF_RSH, BPF_MOD 32 bit
> masking should be fine.
> - For BPF_NEG and BPF_ARSH, might be a problem because of the sign bit.
> - For BPF_END, 32 bit masking should work fine.
> Let me know if any of the above point is wrong or need your suggestion.
>
> - Although, for ALU instructions, there is a big problem of register
> flag manipulations. Generally, architecture's ABI takes care of this
> part but as we are doing 64 bit Instructions emulation(kind of) on 32
> bit machine, it needs to be done manually. Does that sound correct ?
>
> - I am not JITing BPF_ALU64 class instructions as of now. As we have to
> take care of atomic instructions and race conditions with these
> instruction which looks complicated to me as of now. Will try to figure out
> this part and implement it later. Currently, I will just let it be
> interpreted by the ebpf interpreter.
>
> - For BPF_JMP class, I am assuming that, although eBPF is 64 bit ABI,
> the address pointers on 32 bit arch like arm will be of 32 bit only.
> So, for BPF_JMP, masking the 64 bit destination address to 32 bit
> should do the trick and no address will be corrupted in this way. Am I
> correct to assume this ?
> Also, I need to check for address getting out of the allowed memory
> range.
>
> - For BPF_LD, BPF_LDX, BPF_ST and BPF_STX class instructions, I am
> assuming the same thing as above - All addresses and pointers are 32
> bit - which can be taken care just by maksing the eBPF register
> values. Does that sound correct ?
> Also, I need to check for the address overflow, address getting out
> of the allowed memory range and things like that.
>
>> > Do you have any code references for me to take a look? Otherwise, I think
>> > its not possible for me to implement it without using any reference.
>>
>> I don't know anything else, no.
>
> I think, I will give it a try. Otherwise, my last 1 month which I used
> to read about eBPF, eBPF linux code and arm32 ABI would be a complete
> waste.
>
>> >>
>> >>
>> >> > 2.) Also, is my current mapping good enough to make the JIT fast enough
>> >> > ?
>> >> > because as you might know, eBPF JIT mostly depends on 1-to-1 mapping of
>> >> > its instructions with native instructions.
>> >>
>> >> I don't know -- it might be tricky with needing to deal with 64-bit
>> >> registers. But if you can make it faster than the non-JIT, it should
>> >> be a win. :) Yay assembly.
>
> Well, As I mentioned above about my thinking towards the implementation,
> I am not sure it would be faster than non-JIT or even correct for that matter.
> It might be but I don't think I have enough knowledge to benchmark the
> implementation as of now.
>
>
> -Shubham Bansal
-Shubham
next prev parent reply other threads:[~2017-02-08 7:29 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-01-30 10:38 arch: arm: bpf: Converting cBPF to eBPF for arm 32 bit Shubham Bansal
2017-01-30 21:57 ` Kees Cook
[not found] ` <CAHgaXd+nj69n-Xf46N=4M-j-0hKHVrrLfsvRZCG=2CCAtVF6ZA@mail.gmail.com>
[not found] ` <CAGXu5j+NSLomuSgD40kys+pWc+J9aB6Bbk_gSP9Lp_ScimQn_w@mail.gmail.com>
2017-02-01 13:01 ` Shubham Bansal
[not found] ` <76621BFF-B30B-4417-AB2B-DB21CA6092D9@netronome.com>
2017-02-03 7:04 ` Shubham Bansal
2017-02-03 8:25 ` nick viljoen
2017-02-08 7:29 ` Shubham Bansal [this message]
2017-02-08 19:41 ` Kees Cook
2017-03-15 12:13 ` Shubham Bansal
2017-03-15 21:55 ` David Miller
2017-03-28 20:49 ` Shubham Bansal
2017-03-29 0:00 ` Daniel Borkmann
2017-03-30 14:04 ` Shubham Bansal
2017-04-06 11:05 ` Shubham Bansal
2017-04-06 12:51 ` Daniel Borkmann
2017-05-06 16:48 ` Shubham Bansal
2017-05-06 18:38 ` David Miller
2017-05-06 20:27 ` Shubham Bansal
2017-05-06 22:17 ` Shubham Bansal
2017-05-09 20:12 ` Shubham Bansal
2017-05-09 20:19 ` David Miller
2017-05-09 20:25 ` Daniel Borkmann
[not found] <CAHgaXdKsO2xoKYp7g91g+n+d_1KHSSByLjzBB-WjVXSjhB7qxw@mail.gmail.com>
[not found] ` <20170510.212952.1440495072777358778.davem@davemloft.net>
[not found] ` <CAHgaXdK8LEEUPm4jTRRzCnjwdWAauHmmB=caZsSFY8MmStH89Q@mail.gmail.com>
[not found] ` <20170510.215218.2185526627014393313.davem@davemloft.net>
[not found] ` <CAHgaXdKZ_v+iO7uqEDx7PA7D+xcp1FngGvJ1SRSsGXNQ-iWWDQ@mail.gmail.com>
2017-05-11 9:32 ` Shubham Bansal
2017-05-11 15:30 ` Kees Cook
2017-05-13 21:38 ` Shubham Bansal
2017-05-15 17:44 ` Kees Cook
2017-05-15 19:55 ` Daniel Borkmann
2017-05-20 20:01 ` Shubham Bansal
2017-05-22 13:01 ` Daniel Borkmann
2017-05-22 17:04 ` Shubham Bansal
2017-05-22 20:05 ` Kees Cook
2017-05-23 2:58 ` Shubham Bansal
2017-05-23 4:27 ` Kees Cook
2017-05-22 18:58 ` Kees Cook
2017-05-22 19:08 ` Florian Fainelli
2017-05-23 3:34 ` Shubham Bansal
2017-05-23 4:22 ` Kees Cook
2017-05-23 5:03 ` Shubham Bansal
2017-05-23 5:35 ` Kees Cook
[not found] ` <CAHgaXdJa9uJYO3bODuzDRaqOas0i=zMk0jioWFXKm_=UJRtVrw@mail.gmail.com>
2017-05-23 19:32 ` Kees Cook
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=CAHgaXd+cUbmQ20sPVVG88c7QAPMQzSw710tRA8BFTU5sCafuRw@mail.gmail.com \
--to=illusionist.neo@gmail.com \
--cc=linux-arm-kernel@lists.infradead.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).