From: "Stanisław Kardach" <kda@semihalf.com>
To: David Marchand <david.marchand@redhat.com>
Cc: dev <dev@dpdk.org>, Frank Zhao <Frank.Zhao@starfivetech.com>,
Sam Grove <sam.grove@sifive.com>,
Marcin Wojtas <mw@semihalf.com>,
upstream@semihalf.com,
Heinrich Schuchardt <heinrich.schuchardt@canonical.com>
Subject: Re: [PATCH v4 0/8] Introduce support for RISC-V architecture
Date: Wed, 8 Jun 2022 14:28:04 +0200 [thread overview]
Message-ID: <CALVGJWLW7or9ZTbBjW=nHE3EUpxzDEnqBeJWtiFduhLj1h8-eQ@mail.gmail.com> (raw)
In-Reply-To: <CAJFAV8zN_LVSs+YLrOeSzY5aOY41oqQuES+cvsn4bcN3AQ=wsg@mail.gmail.com>
On Wed, Jun 8, 2022 at 10:42 AM David Marchand
<david.marchand@redhat.com> wrote:
>
> On Tue, May 31, 2022 at 4:14 PM Stanislaw Kardach <kda@semihalf.com> wrote:
> >
> > This patchset adds support for building and running DPDK on 64bit RISC-V
> > architecture. The initial support targets rv64gc (rv64imafdc) ISA and
> > was tested on SiFive Unmatched development board with the Freedom U740
> > SoC running Linux (freedom-u-sdk based kernel).
> > I have tested this codebase using DPDK unit and perf tests as well as
> > test-pmd, l2fwd and l3fwd examples.
> > The NIC attached to the DUT was Intel X520-DA2 which uses ixgbe PMD.
> > On the UIO side, since U740 does not have an IOMMU, I've used igb_uio,
> > uio_pci_generic and vfio-pci noiommu drivers.
> >
> > Functional verification done using meson tests. fast-tests suite passing with
> > the default config.
> >
> > PMD verification done using a Intel x520-DA2 NIC (ixgbe) and the test-pmd
> > application. Packet transfer checked using all UIO drivers available for
> > non-IOMMU platforms: uio_pci_generic, vfio-pci noiommu and igb_uio.
> >
> > The i40e PMD driver is disabled on RISC-V as the rv64gc ISA has no vector
> > operations.
> >
> > RISCV support is currently limited to Linux as the time measurement frequency
> > discovery is tied to reading a device-tree node via procfs.
> >
> > Clang compilation currently not supported due to issues with missing relocation
> > relaxation.
> >
> > Commit 1 introduces EAL and build system support for RISC-V architecture
> > as well as documentation updates.
> > Commits 2-5 add missing defines and stubs to enable RISC-V operation in
> > non-EAL parts.
> > Commit 6 adds RISC-V specific cpuflags test.
> > Commits 7-8 add RISC-V build testing to test-meson-builds.sh and github CI.
>
> Overall, the series lgtm.
> It did not get much reviews, but the porting is straightforward and
> clean enough.
>
> I'm waiting for some compilation to finish and I will merge it for 22.07-rc1.
>
>
> Some comments that will probably require some followup patches for rc2:
>
> - I removed the known issue about --no-huge from the EAL patch.
> This seems to be a generic issue that does not block the RISC V port
> and can be re-submitted as a separate patch.
If you mean the modified entry in the known_issues, I've added it at
Heinrich's request, although I agree I should have placed it in a
separate patch.
>
>
> - I had some trouble with finding a right toolchain for test-meson-builds.sh.
> The mentionned toolchains in the cross build guide don't work for me on FC36.
> I managed to cross compile with a Bootlin toolchain, though I had to
> adjust the cross compilation file.
> I'll probably end up compiling my own toolchain later unless you have
> a better idea.
I have just checked with fedora/36 docker and it seems that only gcc
and binutils packages are there but stdlib isn't. Hence meson fails at
basic checks because it can't find "stdio.h". So that's a bug to post
to Fedora I believe.
What does work in terms of cross-compiling is using a
riscv-gnu-toolchain tarball + modified cross-file (i.e. from here:
https://github.com/riscv-collab/riscv-gnu-toolchain/releases/tag/2022.06.03).
That most likely won't work for building RPMs but for static
compilations it might be enough.
Or you could use a Ubuntu docker and cross-compile there (though the
same problem as before):
docker run -v /path/to/dpdk:/opt/dpdk -it ubuntu:jammy /bin/bash
Or a VM as Heinrich suggested.
>
> At least the compilation in GHA works.
That's because I've used Ubuntu as a base, which has a proper
toolchain setup. Also riscv-gnu-toolchain project targets Ubuntu, so
that helps.
>
>
> - The hardcoded pkg-config path in config/riscv/riscv64_linux_gcc does
> not seem generic.
> It is probably not a big issue, but I'd rather move it to a Ubuntu
> specific cross compile meson file.
> WDYT?
I think I'll rename the config file.
In theory, the man file of pkg-config
(https://linux.die.net/man/1/pkg-config) mentions the default
searching path as prefix/lib/pkgconfig. Prefix being
/usr/riscv64-linux-gnu the generic location should be
/usr/riscv64-linux-gnu/lib/pkgconfig but Ubuntu doesn't follow that.
There are no RISC-V cross-libs offering pkg-config neither in Ubuntu
or Fedora so I can't really tell what's the best path to use. Though
that also means we won't hit this issue for some time.
>
>
> - I adjusted some coding style in some asm and some indentation and
> wording in meson.
Thanks!
>
>
> - The cross compilation guide mentions using
> crossbuild-essential-riscv64 for Ubuntu.
> We should switch to it in GHA.
> Though after trying myself, there is an issue in the C++ headers check
> in GHA for some acl header including rte_vect.h.
> Can you have a look?
I'm testing a fix for this. I have not taken C++ type conversion rules
into account.
>
>
> - There was a patch from Heinrich about native compilation, can you review it?
I see it was merged but your question from that thread still stands.
I'm compiling native now to check.
>
>
> --
> David Marchand
>
prev parent reply other threads:[~2022-06-08 12:28 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-05-31 14:12 Stanislaw Kardach
2022-05-31 14:13 ` [PATCH v4 1/8] eal: add initial " Stanislaw Kardach
2022-05-31 14:13 ` [PATCH v4 2/8] net/ixgbe: enable vector stubs for RISC-V Stanislaw Kardach
2022-05-31 14:13 ` [PATCH v4 3/8] net/memif: set memfd syscall ID on RISC-V Stanislaw Kardach
2022-05-31 14:13 ` [PATCH v4 4/8] net/tap: set BPF syscall ID for RISC-V Stanislaw Kardach
2022-05-31 14:13 ` [PATCH v4 5/8] examples/l3fwd: enable RISC-V operation Stanislaw Kardach
2022-05-31 14:13 ` [PATCH v4 6/8] test/cpuflags: add test for RISC-V cpu flag Stanislaw Kardach
2022-05-31 14:13 ` [PATCH v4 7/8] devtools: add RISC-V to test-meson-builds.sh Stanislaw Kardach
2022-05-31 14:13 ` [PATCH v4 8/8] ci: add RISCV64 cross compilation job Stanislaw Kardach
2022-06-08 8:41 ` [PATCH v4 0/8] Introduce support for RISC-V architecture David Marchand
2022-06-08 9:31 ` David Marchand
2022-06-08 9:48 ` Stanisław Kardach
2022-06-08 9:51 ` Heinrich Schuchardt
2022-06-08 12:28 ` Stanisław Kardach [this message]
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='CALVGJWLW7or9ZTbBjW=nHE3EUpxzDEnqBeJWtiFduhLj1h8-eQ@mail.gmail.com' \
--to=kda@semihalf.com \
--cc=Frank.Zhao@starfivetech.com \
--cc=david.marchand@redhat.com \
--cc=dev@dpdk.org \
--cc=heinrich.schuchardt@canonical.com \
--cc=mw@semihalf.com \
--cc=sam.grove@sifive.com \
--cc=upstream@semihalf.com \
/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).