public inbox for linux-doc@vger.kernel.org
 help / color / mirror / Atom feed
From: Magnus Lindholm <linmag7@gmail.com>
To: richard.henderson@linaro.org, mattst88@gmail.com,
	linux-kernel@vger.kernel.org, linux-alpha@vger.kernel.org,
	corbet@lwn.net, skhan@linuxfoundation.org,
	linux-doc@vger.kernel.org
Cc: glaubitz@physik.fu-berlin.de, macro@orcam.me.uk,
	macro@redhat.com, mcree@orcon.net.nz, ink@unseen.parts,
	Magnus Lindholm <linmag7@gmail.com>
Subject: [PATCH 0/1] alpha: enable DMA CMA support (HAVE_DMA_CONTIGUOUS)
Date: Thu, 19 Feb 2026 21:53:48 +0100	[thread overview]
Message-ID: <20260219205514.4434-1-linmag7@gmail.com> (raw)

This series enables CONFIG_DMA_CMA support on Alpha by selecting
HAVE_DMA_CONTIGUOUS and wiring up the required architecture hooks.

Alpha previously relied solely on high-order page allocator
allocations for coherent DMA buffers. With memory compaction now
functional, CMA can be safely enabled to provide reliable
physically contiguous allocations under fragmentation.

Testing was performed on an Alpha UP2000+ (SMP) and a DS10 (UP)
using a custom kernel module that verified the following:

  - Correct CMA reservation via "cma=64M"
  - CmaTotal/CmaFree reporting in /proc/meminfo
  - Successful 32 MiB dma_alloc_coherent() allocations
  - CmaFree reduction and recovery after free
  - Successful allocations under heavy memory load

No allocation failures were observed.

Magnus Lindholm (1):
  alpha: enable DMA CMA support (HAVE_DMA_CONTIGUOUS)

 .../io/dma-contiguous/arch-support.txt        |  2 +-
 arch/alpha/Kconfig                            |  1 +
 arch/alpha/kernel/pci_iommu.c                 | 46 +++++++++++++++++++
 arch/alpha/kernel/setup.c                     | 16 +++++++
 4 files changed, 64 insertions(+), 1 deletion(-)

-- 
2.52.0


             reply	other threads:[~2026-02-19 20:55 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-02-19 20:53 Magnus Lindholm [this message]
2026-02-19 20:53 ` [PATCH 1/1] alpha: enable DMA CMA support (HAVE_DMA_CONTIGUOUS) Magnus Lindholm

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=20260219205514.4434-1-linmag7@gmail.com \
    --to=linmag7@gmail.com \
    --cc=corbet@lwn.net \
    --cc=glaubitz@physik.fu-berlin.de \
    --cc=ink@unseen.parts \
    --cc=linux-alpha@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=macro@orcam.me.uk \
    --cc=macro@redhat.com \
    --cc=mattst88@gmail.com \
    --cc=mcree@orcon.net.nz \
    --cc=richard.henderson@linaro.org \
    --cc=skhan@linuxfoundation.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