mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Marek Szyprowski <m.szyprowski@samsung.com>
To: "Ritesh Harjani (IBM)" <ritesh.list@gmail.com>,
	linux-mips@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
	iommu@lists.linux.dev, linux-kernel@vger.kernel.org,
	"Christophe Leroy (CS GROUP)" <chleroy@kernel.org>
Cc: Robin Murphy <robin.murphy@arm.com>,
	Christoph Hellwig <hch@infradead.org>,
	Thomas Bogendoerfer <tsbogend@alpha.franken.de>,
	Madhavan Srinivasan <maddy@linux.ibm.com>,
	Michael Ellerman <mpe@ellerman.id.au>,
	Nicholas Piggin <npiggin@gmail.com>,
	Shrikanth Hegde <sshegde@linux.ibm.com>,
	Chris Zankel <chris@zankel.net>,
	Max Filippov <jcmvbkbc@gmail.com>
Subject: Re: [PATCH v2 4/7] powerpc/mm: handle highmem pages in arch_dma_prep_coherent()
Date: Thu, 19 Nov 2026 14:17:49 +0100	[thread overview]
Message-ID: <2b64e853-89a7-4fa5-a4f8-2c6b0b62bf74@samsung.com> (raw)
In-Reply-To: <jym96n4p.ritesh.list@gmail.com>

On 19.11.2026 13:07, Ritesh Harjani (IBM) wrote:
> Marek Szyprowski <m.szyprowski@samsung.com> writes:
>
>> arch_dma_prep_coherent() performs the cache maintenance on the address
>> returned by page_address(). On 32-bit powerpc with CONFIG_HIGHMEM that
>> is NULL for a highmem page which is not kmapped, so the flush would
>> operate on the wrong virtual range and leave the dirty lines of the
>> buffer in place.
>>
>> The generic DMA code may pass highmem pages to this hook:
>> dma_direct_alloc() handles a highmem page returned by
>> dma_alloc_contiguous() by forcing the remap path, which calls
>> arch_dma_prep_coherent() on that page before creating the uncached
>> mapping. This cannot happen on powerpc today only because it does not
>> select HAVE_DMA_CONTIGUOUS, so dma-direct never gets a highmem page
>> there, but nothing in the hook's contract rules it out.
>>
>> Use __dma_sync_page() with DMA_BIDIRECTIONAL, which the
>> arch_sync_dma_for_*() hooks already use and which kmaps highmem pages
>> one at a time. Without CONFIG_HIGHMEM it does the same
>> flush_dcache_range() on the linear mapping as before.
>>
> Does that mean, this change can add additional overhead for
> CONFIG_HIGHMEM=y kernels, where the buffer received still belongs to
> lowmem? (Because of extra per-page book keeping like
> local_irq_save/restore, kmap_xxx). Thoughts?
>
> Although functionally the change looks correct to me. But maybe
> __dma_sync_page() on powerpc side could use some cleanups (outside of
> this patch series perhaps).
Indeed, __dma_sync_page() could be improved by calling __dma_sync_page_highmem()
only for highmem pages. Something like:


diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
index e646256365d5..199ce0467b58 100644
--- a/arch/powerpc/mm/dma-noncoherent.c
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -97,11 +97,12 @@ static void __dma_sync_page(phys_addr_t paddr, size_t size, int dir)
        unsigned offset = paddr & ~PAGE_MASK;

 #ifdef CONFIG_HIGHMEM
-       __dma_sync_page_highmem(page, offset, size, dir);
-#else
-       unsigned long start = (unsigned long)page_address(page) + offset;
-       __dma_sync((void *)start, size, dir);
+       if (PageHighMem(pfn_to_page(PHYS_PFN(paddr + size - 1)))) {
+               __dma_sync_page_highmem(page, offset, size, dir);
+               return;
+       }
 #endif
+       __dma_sync(page_address(page) + offset, size, dir);
 }

 void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,


Do You want me to add it as another patch for this series?

Best regards
-- 
Marek Szyprowski, PhD
Samsung R&D Institute Poland


  reply	other threads:[~2026-11-19 13:17 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CGME20261110094846eucas1p140d5ebfe71b47d4e4b5e2162ba051c51@eucas1p1.samsung.com>
2026-11-10  9:48 ` [PATCH v2 0/7] dma-mapping: DMA_ATTR_NO_KERNEL_MAPPING related fixes Marek Szyprowski
     [not found]   ` <CGME20261110094847eucas1p125691a852f3621482adae13de1205223@eucas1p1.samsung.com>
2026-11-10  9:48     ` [PATCH v2 1/7] xtensa: write back dirty lines in arch_dma_prep_coherent() Marek Szyprowski
2026-11-10 12:40       ` Max Filippov
     [not found]   ` <CGME20261110094848eucas1p2577d7a3c60643a040e599dfa1bf97f08@eucas1p2.samsung.com>
2026-11-10  9:48     ` [PATCH v2 2/7] xtensa: handle highmem pages " Marek Szyprowski
2026-11-10 12:42       ` Max Filippov
     [not found]   ` <CGME20261110094849eucas1p2ece5eda5ed8c159ec05951bb8a3052be@eucas1p2.samsung.com>
2026-11-10  9:48     ` [PATCH v2 3/7] MIPS: mm: " Marek Szyprowski
2026-11-16 19:07       ` Thomas Bogendoerfer
     [not found]   ` <CGME20261110094850eucas1p1f10fa1473aca341473077f60a088b490@eucas1p1.samsung.com>
2026-11-10  9:48     ` [PATCH v2 4/7] powerpc/mm: " Marek Szyprowski
2026-11-19 12:07       ` Ritesh Harjani
2026-11-19 13:17         ` Marek Szyprowski [this message]
     [not found]   ` <CGME20261110094851eucas1p10eccf143e36dcc8933008074dee399c9@eucas1p1.samsung.com>
2026-11-10  9:48     ` [PATCH v2 5/7] dma-mapping: document that arch_dma_prep_coherent() must handle highmem Marek Szyprowski
     [not found]   ` <CGME20261110094852eucas1p28920baba9ddde5dbb2760e45fee7179a@eucas1p2.samsung.com>
2026-11-10  9:48     ` [PATCH v2 6/7] dma-direct: do not skip cache maintenance for highmem pages in no-mapping allocations Marek Szyprowski
     [not found]   ` <CGME20261110094853eucas1p2c89af10eb0d4611c4fc080d559696015@eucas1p2.samsung.com>
2026-11-10  9:48     ` [PATCH v2 7/7] dma-direct: zero memory allocated with DMA_ATTR_NO_KERNEL_MAPPING Marek Szyprowski

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=2b64e853-89a7-4fa5-a4f8-2c6b0b62bf74@samsung.com \
    --to=m.szyprowski@samsung.com \
    --cc=chleroy@kernel.org \
    --cc=chris@zankel.net \
    --cc=hch@infradead.org \
    --cc=iommu@lists.linux.dev \
    --cc=jcmvbkbc@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mips@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=maddy@linux.ibm.com \
    --cc=mpe@ellerman.id.au \
    --cc=npiggin@gmail.com \
    --cc=ritesh.list@gmail.com \
    --cc=robin.murphy@arm.com \
    --cc=sshegde@linux.ibm.com \
    --cc=tsbogend@alpha.franken.de \
    /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®