From: patchwork-bot+linux-riscv@kernel.org
To: Troy Mitchell <troy@kernel.org>
Cc: linux-riscv@lists.infradead.org, pjw@kernel.org,
palmer@dabbelt.com, aou@eecs.berkeley.edu, alex@ghiti.fr,
bhelgaas@google.com, linux-pci@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH] riscv: pci: allow write-combining mmap of PCI BARs
Date: Wed, 11 Nov 2026 02:00:05 +0000 [thread overview]
Message-ID: <179436240542.644035.285193769766011336.git-patchwork-notify@kernel.org> (raw)
In-Reply-To: <20261110-riscv-pci-mmap-wc-v1-1-1d16fb8c74b4@kernel.org>
Hello:
This patch was applied to riscv/linux.git (fixes)
by Paul Walmsley <pjw@kernel.org>:
On Tue, 10 Nov 2026 15:04:49 +0000 you wrote:
> Define arch_can_pci_mmap_wc() for RISC-V, so that the PCI core can
> create resourceN_wc in sysfs for prefetchable BARs. Without it, the only
> sysfs mapping of such a BAR is resourceN, which uses pgprot_device():
> with Svpbmt or XTheadMae that is the IO memory type, where every access
> is strongly ordered and nothing is merged.
>
> resourceN_wc is mapped with pgprot_writecombine(), which selects the NC
> memory type when the kernel uses Svpbmt or XTheadMae. Without either,
> _PAGE_NOCACHE is 0 and pgprot_writecombine() changes nothing, so
> resourceN_wc would get the same PMA-defined attributes as resourceN and
> no write-combining at all. Make arch_can_pci_mmap_wc() true only when
> _PAGE_NOCACHE is non-zero. On 64-bit this is a runtime check, as
> _PAGE_NOCACHE is chosen at boot from the CPU extensions; on 32-bit it is
> always 0, so nothing changes there.
>
> [...]
Here is the summary with links:
- riscv: pci: allow write-combining mmap of PCI BARs
https://git.kernel.org/riscv/c/79fc9d9467a1
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv
WARNING: multiple messages have this Message-ID (diff)
From: patchwork-bot+linux-riscv@kernel.org
To: Troy Mitchell <troy@kernel.org>
Cc: linux-riscv@lists.infradead.org, pjw@kernel.org,
palmer@dabbelt.com, aou@eecs.berkeley.edu, alex@ghiti.fr,
bhelgaas@google.com, linux-pci@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH] riscv: pci: allow write-combining mmap of PCI BARs
Date: Wed, 11 Nov 2026 02:00:05 +0000 [thread overview]
Message-ID: <179436240542.644035.285193769766011336.git-patchwork-notify@kernel.org> (raw)
In-Reply-To: <20261110-riscv-pci-mmap-wc-v1-1-1d16fb8c74b4@kernel.org>
Hello:
This patch was applied to riscv/linux.git (fixes)
by Paul Walmsley <pjw@kernel.org>:
On Tue, 10 Nov 2026 15:04:49 +0000 you wrote:
> Define arch_can_pci_mmap_wc() for RISC-V, so that the PCI core can
> create resourceN_wc in sysfs for prefetchable BARs. Without it, the only
> sysfs mapping of such a BAR is resourceN, which uses pgprot_device():
> with Svpbmt or XTheadMae that is the IO memory type, where every access
> is strongly ordered and nothing is merged.
>
> resourceN_wc is mapped with pgprot_writecombine(), which selects the NC
> memory type when the kernel uses Svpbmt or XTheadMae. Without either,
> _PAGE_NOCACHE is 0 and pgprot_writecombine() changes nothing, so
> resourceN_wc would get the same PMA-defined attributes as resourceN and
> no write-combining at all. Make arch_can_pci_mmap_wc() true only when
> _PAGE_NOCACHE is non-zero. On 64-bit this is a runtime check, as
> _PAGE_NOCACHE is chosen at boot from the CPU extensions; on 32-bit it is
> always 0, so nothing changes there.
>
> [...]
Here is the summary with links:
- riscv: pci: allow write-combining mmap of PCI BARs
https://git.kernel.org/riscv/c/79fc9d9467a1
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
next prev parent reply other threads:[~2026-11-11 2:00 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-10 15:04 [PATCH] riscv: pci: allow write-combining mmap of PCI BARs Troy Mitchell
2026-11-10 15:04 ` Troy Mitchell
2026-11-10 15:10 ` sashiko-bot
2026-11-11 2:00 ` patchwork-bot+linux-riscv [this message]
2026-11-11 2:00 ` patchwork-bot+linux-riscv
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=179436240542.644035.285193769766011336.git-patchwork-notify@kernel.org \
--to=patchwork-bot+linux-riscv@kernel.org \
--cc=alex@ghiti.fr \
--cc=aou@eecs.berkeley.edu \
--cc=bhelgaas@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=linux-riscv@lists.infradead.org \
--cc=palmer@dabbelt.com \
--cc=pjw@kernel.org \
--cc=troy@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.