From: Christoph Hellwig <hch@lst.de>
To: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Christoph Hellwig <hch@lst.de>, Baoquan He <bhe@redhat.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
akpm@linux-foundation.org, cl@linux.com,
John.p.donnelly@oracle.com, kexec@lists.infradead.org,
stable@vger.kernel.org, Pekka Enberg <penberg@kernel.org>,
David Rientjes <rientjes@google.com>,
Joonsoo Kim <iamjoonsoo.kim@lge.com>,
Vlastimil Babka <vbabka@suse.cz>
Subject: Re: [PATCH v3 5/5] mm/slub: do not create dma-kmalloc if no managed pages in DMA zone
Date: Thu, 23 Dec 2021 09:52:38 +0100 [thread overview]
Message-ID: <20211223085238.GA7555@lst.de> (raw)
In-Reply-To: <YcMb7+RESj1nEx9l@ip-172-31-30-232.ap-northeast-1.compute.internal>
On Wed, Dec 22, 2021 at 12:37:03PM +0000, Hyeonggon Yoo wrote:
> Oh I misunderstood this. Underlying physical address of vmalloc()-allocated memory
> can be mapped using DMA API, and it needs to be setup as scatterlist because
> the allocated memory is not physically continuous. Right?
Yes.
> BTW, looking at the API I think the scsi case can be converted to use
> dma_alloc_pages(). but driver requires 512 bytes of buffer and the API
> supports allocating by at least page size.
Overallocating is not generally a problem, but if the allocations are for
a slow path it might make more sense to stick to dma_map_* and bounce
buffer if needed.
> It's not a big problem as it allocates a single buffer but in other
> cases maybe not. Can't we use dma pool for non-coherent pages?
No.
_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec
WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@lst.de>
To: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Christoph Hellwig <hch@lst.de>, Baoquan He <bhe@redhat.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
akpm@linux-foundation.org, cl@linux.com,
John.p.donnelly@oracle.com, kexec@lists.infradead.org,
stable@vger.kernel.org, Pekka Enberg <penberg@kernel.org>,
David Rientjes <rientjes@google.com>,
Joonsoo Kim <iamjoonsoo.kim@lge.com>,
Vlastimil Babka <vbabka@suse.cz>
Subject: Re: [PATCH v3 5/5] mm/slub: do not create dma-kmalloc if no managed pages in DMA zone
Date: Thu, 23 Dec 2021 09:52:38 +0100 [thread overview]
Message-ID: <20211223085238.GA7555@lst.de> (raw)
In-Reply-To: <YcMb7+RESj1nEx9l@ip-172-31-30-232.ap-northeast-1.compute.internal>
On Wed, Dec 22, 2021 at 12:37:03PM +0000, Hyeonggon Yoo wrote:
> Oh I misunderstood this. Underlying physical address of vmalloc()-allocated memory
> can be mapped using DMA API, and it needs to be setup as scatterlist because
> the allocated memory is not physically continuous. Right?
Yes.
> BTW, looking at the API I think the scsi case can be converted to use
> dma_alloc_pages(). but driver requires 512 bytes of buffer and the API
> supports allocating by at least page size.
Overallocating is not generally a problem, but if the allocations are for
a slow path it might make more sense to stick to dma_map_* and bounce
buffer if needed.
> It's not a big problem as it allocates a single buffer but in other
> cases maybe not. Can't we use dma pool for non-coherent pages?
No.
next prev parent reply other threads:[~2021-12-23 8:52 UTC|newest]
Thread overview: 74+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-12-13 12:27 [PATCH v3 0/5] Avoid requesting page from DMA zone when no managed pages Baoquan He
2021-12-13 12:27 ` Baoquan He
2021-12-13 12:27 ` [PATCH v3 1/5] docs: kernel-parameters: Update to reflect the current default size of atomic pool Baoquan He
2021-12-13 12:27 ` Baoquan He
2021-12-13 14:20 ` john.p.donnelly
2021-12-13 14:20 ` john.p.donnelly
2021-12-13 12:27 ` [PATCH v3 2/5] dma-pool: allow user to disable " Baoquan He
2021-12-13 12:27 ` Baoquan He
2021-12-13 14:21 ` john.p.donnelly
2021-12-13 14:21 ` john.p.donnelly
2021-12-13 12:27 ` [PATCH v3 3/5] mm_zone: add function to check if managed dma zone exists Baoquan He
2021-12-13 12:27 ` Baoquan He
2021-12-13 14:22 ` john.p.donnelly
2021-12-13 14:22 ` john.p.donnelly
2021-12-16 10:52 ` David Hildenbrand
2021-12-16 10:52 ` David Hildenbrand
2021-12-13 12:27 ` [PATCH v3 4/5] dma/pool: create dma atomic pool only if dma zone has managed pages Baoquan He
2021-12-13 12:27 ` Baoquan He
2021-12-13 12:27 ` Baoquan He
2021-12-13 14:23 ` john.p.donnelly
2021-12-13 14:23 ` john.p.donnelly
2021-12-13 14:23 ` john.p.donnelly
2021-12-13 12:27 ` [PATCH v3 5/5] mm/slub: do not create dma-kmalloc if no managed pages in DMA zone Baoquan He
2021-12-13 12:27 ` Baoquan He
2021-12-13 13:43 ` Hyeonggon Yoo
2021-12-13 13:43 ` Hyeonggon Yoo
2021-12-14 5:32 ` Baoquan He
2021-12-14 5:32 ` Baoquan He
2021-12-14 10:09 ` Vlastimil Babka
2021-12-14 10:09 ` Vlastimil Babka
2021-12-14 10:28 ` Christoph Lameter
2021-12-14 10:28 ` Christoph Lameter
2021-12-15 4:48 ` Hyeonggon Yoo
2021-12-15 4:48 ` Hyeonggon Yoo
2021-12-15 7:03 ` Hyeonggon Yoo
2021-12-15 7:03 ` Hyeonggon Yoo
2021-12-15 7:27 ` Christoph Hellwig
2021-12-15 7:27 ` Christoph Hellwig
2021-12-15 10:34 ` Vlastimil Babka
2021-12-15 10:34 ` Vlastimil Babka
2021-12-15 11:51 ` David Laight
2021-12-15 11:51 ` David Laight
2021-12-15 13:41 ` Baoquan He
2021-12-15 13:41 ` Baoquan He
2021-12-17 11:38 ` Hyeonggon Yoo
2021-12-17 11:38 ` Hyeonggon Yoo
2021-12-20 7:32 ` Baoquan He
2021-12-20 7:32 ` Baoquan He
2022-01-07 11:56 ` Hyeonggon Yoo
2022-01-07 11:56 ` Hyeonggon Yoo
2021-12-15 14:42 ` Baoquan He
2021-12-15 14:42 ` Baoquan He
2021-12-15 10:08 ` Baoquan He
2021-12-15 10:08 ` Baoquan He
2021-12-17 11:38 ` Hyeonggon Yoo
2021-12-17 11:38 ` Hyeonggon Yoo
2021-12-21 8:56 ` Christoph Hellwig
2021-12-21 8:56 ` Christoph Hellwig
2021-12-22 12:37 ` Hyeonggon Yoo
2021-12-22 12:37 ` Hyeonggon Yoo
2021-12-23 8:52 ` Christoph Hellwig [this message]
2021-12-23 8:52 ` Christoph Hellwig
2021-12-13 14:24 ` john.p.donnelly
2021-12-13 14:24 ` john.p.donnelly
2021-12-14 16:31 ` Christoph Hellwig
2021-12-14 16:31 ` Christoph Hellwig
2021-12-14 17:07 ` john.p.donnelly
2021-12-14 17:07 ` john.p.donnelly
2021-12-15 7:27 ` Christoph Hellwig
2021-12-15 7:27 ` Christoph Hellwig
2021-12-13 21:05 ` [PATCH v3 0/5] Avoid requesting page from DMA zone when no managed pages Andrew Morton
2021-12-13 21:05 ` Andrew Morton
2021-12-14 0:35 ` Baoquan He
2021-12-14 0:35 ` Baoquan He
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=20211223085238.GA7555@lst.de \
--to=hch@lst.de \
--cc=42.hyeyoo@gmail.com \
--cc=John.p.donnelly@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=bhe@redhat.com \
--cc=cl@linux.com \
--cc=iamjoonsoo.kim@lge.com \
--cc=kexec@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=penberg@kernel.org \
--cc=rientjes@google.com \
--cc=stable@vger.kernel.org \
--cc=vbabka@suse.cz \
/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.