mirror of https://lore.kernel.org/lkml/
 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
Cc: linmag7@gmail.com
Subject: [PATCH v3 0/2] alpha: enable DMA CMA support
Date: Sun, 15 Nov 2026 11:37:41 +0100	[thread overview]
Message-ID: <20261115103809.1288167-1-linmag7@gmail.com> (raw)

Changes since v2, following Matt Turner's review:

- Initialize jump labels before parsing early parameters, so handlers
  can safely change static keys. Carry Matt's Reviewed-by on patch 1.
- Page-align sizes in both coherent allocation and free. The CMA helper
  assumes a page-aligned size; truncating an unaligned request can cause
  an undersized allocation, an overwrite, and release of unowned pages.
- Change the failure message to "allocation failed".

V2 was boot-tested on a three-CPU AlphaServer ES40 with cma=64M,
including 32 MiB, 24 KiB and 8 KiB allocation tests and GFP_ATOMIC
bypass checks. All of those sizes were page multiples, so they did
not exercise the alignment bug. Those results are not validation
of v3; build and runtime validation of this revision remain pending.

Planned regression cases include 12 KiB and 20 KiB requests, checking
zeroing, mapped size, and allocation/release accounting against the
page-rounded size on each CPU. Repeat the existing static-key tests
on a combined kernel with jump-label v3.

Reservation policy is unchanged: prefer top-down placement below the
direct-map and usable RAM limits, with generic cma= range overrides.
Other reservation-size boots and no-IOMMU testing remain outstanding.

Magnus Lindholm (2):
  alpha: parse early parameters before reserving contiguous memory
  alpha: enable contiguous memory allocation for coherent DMA

 .../io/dma-contiguous/arch-support.txt        |  2 +-
 arch/alpha/Kconfig                            |  1 +
 arch/alpha/kernel/pci_iommu.c                 | 19 ++++++++++++------
 arch/alpha/kernel/setup.c                     | 20 +++++++++++++++++++
 4 files changed, 35 insertions(+), 7 deletions(-)


base-commit: 0b4cadbe7c39d830dec35c4a2655483de0dae568
-- 
2.43.0


             reply	other threads:[~2026-11-15 10:38 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-15 10:37 Magnus Lindholm [this message]
2026-11-15 10:37 ` [PATCH v3 1/2] alpha: parse early parameters before reserving contiguous memory Magnus Lindholm
2026-11-15 10:37 ` [PATCH v3 2/2] alpha: enable contiguous memory allocation for coherent DMA 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=20261115103809.1288167-1-linmag7@gmail.com \
    --to=linmag7@gmail.com \
    --cc=linux-alpha@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mattst88@gmail.com \
    --cc=richard.henderson@linaro.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

all inboxes | Powered by JetHome®