From: Baruch Siach <baruch@tkos.co.il>
To: Yang Shi <yang@os.amperecomputing.com>
Cc: catalin.marinas@arm.com, will@kernel.org, ptesarik@suse.com,
hch@lst.de, jiangyutang@os.amperecomputing.com,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH] arm64: mm: fix zone_dma_limit calculation
Date: Tue, 26 Nov 2024 08:27:19 +0200 [thread overview]
Message-ID: <87ttbu8q7s.fsf@tarshish> (raw)
In-Reply-To: <20241125171650.77424-1-yang@os.amperecomputing.com> (Yang Shi's message of "Mon, 25 Nov 2024 09:16:50 -0800")
Hi Yang,
On Mon, Nov 25 2024, Yang Shi wrote:
> The commit ba0fb44aed47 ("dma-mapping: replace zone_dma_bits by
> zone_dma_limit") changed how zone_dma_limit was calculated. Now it
> returns the memsize limit in IORT or device tree instead of U32_MAX if
> the memsize limit is greater than U32_MAX.
Can you give a concrete example of memory layout and dma-ranges that
demonstrates this issue?
> This resulted in DMA allocations may use GFP_DMA even though the devices
> don't require it. It caused regression on our two sockets systems due
> to excessive remote memory access.
That is, DMA zone used to cover all memory before commit ba0fb44aed47,
but now DMA zone is limited to the smallest dma-ranges. Is that correct?
Thanks,
baruch
> Fixes: ba0fb44aed47 ("dma-mapping: replace zone_dma_bits by zone_dma_limit")
> Cc: <stable@vger.kernel.org> [6.12+]
> Reported-by: Yutang Jiang <jiangyutang@os.amperecomputing.com>
> Tested-by: Yutang Jiang <jiangyutang@os.amperecomputing.com>
> Signed-off-by: Yang Shi <yang@os.amperecomputing.com>
> ---
> arch/arm64/mm/init.c | 17 ++++++++---------
> 1 file changed, 8 insertions(+), 9 deletions(-)
>
> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
> index d21f67d67cf5..ccdef53872a0 100644
> --- a/arch/arm64/mm/init.c
> +++ b/arch/arm64/mm/init.c
> @@ -117,15 +117,6 @@ static void __init arch_reserve_crashkernel(void)
>
> static phys_addr_t __init max_zone_phys(phys_addr_t zone_limit)
> {
> - /**
> - * Information we get from firmware (e.g. DT dma-ranges) describe DMA
> - * bus constraints. Devices using DMA might have their own limitations.
> - * Some of them rely on DMA zone in low 32-bit memory. Keep low RAM
> - * DMA zone on platforms that have RAM there.
> - */
> - if (memblock_start_of_DRAM() < U32_MAX)
> - zone_limit = min(zone_limit, U32_MAX);
> -
> return min(zone_limit, memblock_end_of_DRAM() - 1) + 1;
> }
>
> @@ -141,6 +132,14 @@ static void __init zone_sizes_init(void)
> acpi_zone_dma_limit = acpi_iort_dma_get_max_cpu_address();
> dt_zone_dma_limit = of_dma_get_max_cpu_address(NULL);
> zone_dma_limit = min(dt_zone_dma_limit, acpi_zone_dma_limit);
> + /*
> + * Information we get from firmware (e.g. DT dma-ranges) describe DMA
> + * bus constraints. Devices using DMA might have their own limitations.
> + * Some of them rely on DMA zone in low 32-bit memory. Keep low RAM
> + * DMA zone on platforms that have RAM there.
> + */
> + if (memblock_start_of_DRAM() < U32_MAX)
> + zone_dma_limit = min(zone_dma_limit, U32_MAX);
> arm64_dma_phys_limit = max_zone_phys(zone_dma_limit);
> max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
> #endif
--
~. .~ Tk Open Systems
=}------------------------------------------------ooO--U--Ooo------------{=
- baruch@tkos.co.il - tel: +972.52.368.4656, http://www.tkos.co.il -
next prev parent reply other threads:[~2024-11-26 6:28 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-25 17:16 [PATCH] arm64: mm: fix zone_dma_limit calculation Yang Shi
2024-11-26 6:27 ` Baruch Siach [this message]
2024-11-26 17:38 ` Yang Shi
2024-11-27 17:49 ` Catalin Marinas
2024-11-29 18:06 ` Robin Murphy
2024-11-29 19:38 ` Catalin Marinas
2024-12-02 16:41 ` Yang Shi
2024-12-03 21:20 ` Catalin Marinas
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=87ttbu8q7s.fsf@tarshish \
--to=baruch@tkos.co.il \
--cc=catalin.marinas@arm.com \
--cc=hch@lst.de \
--cc=jiangyutang@os.amperecomputing.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=ptesarik@suse.com \
--cc=will@kernel.org \
--cc=yang@os.amperecomputing.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).