All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Laight <David.Laight@ACULAB.COM>
To: 'Baoquan He' <bhe@redhat.com>, Christoph Hellwig <hch@lst.de>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	"akpm@linux-foundation.org" <akpm@linux-foundation.org>,
	"cl@linux.com" <cl@linux.com>,
	"42.hyeyoo@gmail.com" <42.hyeyoo@gmail.com>,
	"penberg@kernel.org" <penberg@kernel.org>,
	"rientjes@google.com" <rientjes@google.com>,
	"iamjoonsoo.kim@lge.com" <iamjoonsoo.kim@lge.com>,
	"vbabka@suse.cz" <vbabka@suse.cz>,
	"david@redhat.com" <david@redhat.com>,
	"herbert@gondor.apana.org.au" <herbert@gondor.apana.org.au>,
	"davem@davemloft.net" <davem@davemloft.net>,
	"linux-crypto@vger.kernel.org" <linux-crypto@vger.kernel.org>,
	"steffen.klassert@secunet.com" <steffen.klassert@secunet.com>,
	"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	"hca@linux.ibm.com" <hca@linux.ibm.com>,
	"gor@linux.ibm.com" <gor@linux.ibm.com>,
	"agordeev@linux.ibm.com" <agordeev@linux.ibm.com>,
	"borntraeger@linux.ibm.com" <borntraeger@linux.ibm.com>,
	"svens@linux.ibm.com" <svens@linux.ibm.com>,
	"linux-s390@vger.kernel.org" <linux-s390@vger.kernel.org>,
	"michael@walle.cc" <michael@walle.cc>,
	"linux-i2c@vger.kernel.org" <linux-i2c@vger.kernel.org>,
	"wsa@kernel.org" <wsa@kernel.org>
Subject: RE: [PATCH 1/2] dma-mapping: check dma_mask for streaming mapping allocs
Date: Thu, 24 Feb 2022 14:27:02 +0000	[thread overview]
Message-ID: <1fead34bceda468cbe34077a28c4a4b1@AcuMS.aculab.com> (raw)
In-Reply-To: <YheSBTJY216m6izG@MiWiFi-R3L-srv>

From: Baoquan He
> Sent: 24 February 2022 14:11
...
> With my understanding, there are two kinds of DMA mapping, coherent
> mapping (which is also persistent mapping), and streaming mapping. The
> coherent mapping will be handled during driver init, and released during
> driver de-init. While streaming mapping will be done when needed at any
> time, and released after usage.

The lifetime has absolutely nothing to do with it.

It is all about how the DMA cycles (from the device) interact with
(or more don't interact with) the cpu memory cache.

For coherent mapping the cpu and device can write to (different)
words in the same cache line at the same time, and both will see
both updates.
On some systems this can only be achieved by making the memory
uncached - which significantly slows down cpu access.

For non-coherent (streaming) mapping the cpu writes back and/or
invalidates the data cache so that the dma read cycles from memory
read the correct data and the cpu re-reads the cache line after
the dma has completed.
They are only really suitable for data buffers.

	David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)


  reply	other threads:[~2022-02-24 14:27 UTC|newest]

Thread overview: 74+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-02-19  0:51 [PATCH 00/22] Don't use kmalloc() with GFP_DMA Baoquan He
2022-02-19  0:52 ` [PATCH 01/22] parisc: pci-dma: remove stale code and comment Baoquan He
2022-02-19  7:07   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 02/22] net: moxa: Don't use GFP_DMA when calling dma_alloc_coherent() Baoquan He
2022-02-19  7:07   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 03/22] gpu: ipu-v3: " Baoquan He
2022-02-19  7:07   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 04/22] drm/sti: Don't use GFP_DMA when calling dma_alloc_wc() Baoquan He
2022-02-19  7:08   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 05/22] sound: n64: Don't use GFP_DMA when calling dma_alloc_coherent() Baoquan He
2022-02-19  7:08   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 06/22] fbdev: da8xx: " Baoquan He
2022-02-19  7:08   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 07/22] fbdev: mx3fb: Don't use GFP_DMA when calling dma_alloc_wc() Baoquan He
2022-02-19  7:08   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 08/22] usb: gadget: lpc32xx_udc: Don't use GFP_DMA when calling dma_alloc_coherent() Baoquan He
2022-02-19  7:09   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 09/22] usb: cdns3: " Baoquan He
2022-02-19  7:09   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 10/22] uio: pruss: " Baoquan He
2022-02-19  7:09   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 11/22] staging: emxx_udc: " Baoquan He
2022-02-19  6:51   ` Wolfram Sang
2022-02-20  1:55     ` Baoquan He
2022-02-19  7:09   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 12/22] " Baoquan He
2022-02-19  7:10   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 13/22] spi: atmel: " Baoquan He
2022-02-19  7:10   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 14/22] spi: spi-ti-qspi: " Baoquan He
2022-02-19  7:12   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 15/22] usb: cdns3: Don't use GFP_DMA32 when calling dma_pool_alloc() Baoquan He
2022-02-19  7:13   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 16/22] usb: udc: lpc32xx: Don't use GFP_DMA " Baoquan He
2022-02-19  7:13   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 17/22] net: marvell: prestera: " Baoquan He
2022-02-19  4:54   ` Jakub Kicinski
2022-02-20  2:06     ` Baoquan He
2022-02-19  7:13   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 18/22] net: ethernet: mtk-star-emac: Don't use GFP_DMA when calling dmam_alloc_coherent() Baoquan He
2022-02-19  7:13   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 19/22] ethernet: rocker: Use dma_alloc_noncoherent() for dma buffer Baoquan He
2022-02-19  7:14   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 20/22] HID: intel-ish-hid: " Baoquan He
2022-02-19  7:14   ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 21/22] mmc: wbsd: " Baoquan He
2022-02-19  7:17   ` Christoph Hellwig
2022-02-20  8:40     ` Baoquan He
2022-02-22  8:45       ` Christoph Hellwig
2022-02-22  9:14         ` Baoquan He
2022-02-22 13:11           ` Christoph Hellwig
2022-02-22 13:40             ` Baoquan He
2022-02-22 13:41             ` [PATCH 1/2] dma-mapping: check dma_mask for streaming mapping allocs Baoquan He
2022-02-22 15:59               ` Christoph Hellwig
2022-02-23  0:28                 ` Baoquan He
2022-02-23 14:25                   ` Christoph Hellwig
2022-02-23 14:57                     ` David Laight
2022-02-24 14:11                     ` Baoquan He
2022-02-24 14:27                       ` David Laight [this message]
2022-02-25 15:39                         ` 'Baoquan He'
2022-02-22 13:42             ` [PATCH 2/2] kernel/dma: rename dma_alloc_direct and dma_map_direct Baoquan He
2022-02-22 15:59               ` Christoph Hellwig
2022-02-19  0:52 ` [PATCH 22/22] mtd: rawnand: Use dma_alloc_noncoherent() for dma buffer Baoquan He
2022-02-19  7:19   ` Christoph Hellwig
2022-02-19 11:18     ` Hyeonggon Yoo
2022-02-22  8:46       ` Christoph Hellwig
2022-02-22  9:06         ` David Laight
2022-02-22 13:16           ` 'Christoph Hellwig'
2022-02-21 13:57 ` [PATCH 00/22] Don't use kmalloc() with GFP_DMA Heiko Carstens
2022-02-22  8:44   ` Christoph Hellwig
2022-02-22 13:12     ` Baoquan He
2022-02-22 13:26       ` Baoquan He
2022-02-23 19:18     ` Heiko Carstens
2022-02-24  6:33       ` Christoph Hellwig

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=1fead34bceda468cbe34077a28c4a4b1@AcuMS.aculab.com \
    --to=david.laight@aculab.com \
    --cc=42.hyeyoo@gmail.com \
    --cc=agordeev@linux.ibm.com \
    --cc=akpm@linux-foundation.org \
    --cc=bhe@redhat.com \
    --cc=borntraeger@linux.ibm.com \
    --cc=cl@linux.com \
    --cc=davem@davemloft.net \
    --cc=david@redhat.com \
    --cc=gor@linux.ibm.com \
    --cc=hca@linux.ibm.com \
    --cc=hch@lst.de \
    --cc=herbert@gondor.apana.org.au \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=linux-crypto@vger.kernel.org \
    --cc=linux-i2c@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=michael@walle.cc \
    --cc=netdev@vger.kernel.org \
    --cc=penberg@kernel.org \
    --cc=rientjes@google.com \
    --cc=steffen.klassert@secunet.com \
    --cc=svens@linux.ibm.com \
    --cc=vbabka@suse.cz \
    --cc=wsa@kernel.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 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.