From: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
To: Benjamin Herrenschmidt
<benh-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
Cc: Greg Kroah-Hartman
<gregkh-hQyY1W1yCW8ekmWlsbkhG0B+6BGkLq7r@public.gmane.org>,
linuxppc-dev-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org,
Robin Murphy <robin.murphy-5wv7dgnIgG8@public.gmane.org>,
Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
Subject: Re: [PATCH 3/5] dma-direct: refine dma_direct_alloc zone selection
Date: Thu, 27 Sep 2018 15:49:23 +0200 [thread overview]
Message-ID: <20180927134922.GA8281@lst.de> (raw)
In-Reply-To: <1811156d5a1df1166c7ab7522525619b951f047d.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
On Thu, Sep 27, 2018 at 11:45:15AM +1000, Benjamin Herrenschmidt wrote:
> I'm not sure this is entirely right.
>
> Let's say the mask is 30 bits. You will return GFP_DMA32, which will
> fail if you allocate something above 1G (which is legit for
> ZONE_DMA32).
And then we will try GFP_DMA further down in the function:
if (IS_ENABLED(CONFIG_ZONE_DMA) &&
dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
!(gfp & GFP_DMA)) {
gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
goto again;
}
This is and old optimization from x86, because chances are high that
GFP_DMA32 will give you suitable memory for the infamous 31-bit
dma mask devices (at least at boot time) and thus we don't have
to deplete the tiny ZONE_DMA pool.
WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@lst.de>
To: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Christoph Hellwig <hch@lst.de>,
iommu@lists.linux-foundation.org,
Marek Szyprowski <m.szyprowski@samsung.com>,
Robin Murphy <robin.murphy@arm.com>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org
Subject: Re: [PATCH 3/5] dma-direct: refine dma_direct_alloc zone selection
Date: Thu, 27 Sep 2018 15:49:23 +0200 [thread overview]
Message-ID: <20180927134922.GA8281@lst.de> (raw)
In-Reply-To: <1811156d5a1df1166c7ab7522525619b951f047d.camel@kernel.crashing.org>
On Thu, Sep 27, 2018 at 11:45:15AM +1000, Benjamin Herrenschmidt wrote:
> I'm not sure this is entirely right.
>
> Let's say the mask is 30 bits. You will return GFP_DMA32, which will
> fail if you allocate something above 1G (which is legit for
> ZONE_DMA32).
And then we will try GFP_DMA further down in the function:
if (IS_ENABLED(CONFIG_ZONE_DMA) &&
dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
!(gfp & GFP_DMA)) {
gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
goto again;
}
This is and old optimization from x86, because chances are high that
GFP_DMA32 will give you suitable memory for the infamous 31-bit
dma mask devices (at least at boot time) and thus we don't have
to deplete the tiny ZONE_DMA pool.
next prev parent reply other threads:[~2018-09-27 13:49 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-09-20 18:52 dma mask related fixups (including full bus_dma_mask support) Christoph Hellwig
2018-09-20 18:52 ` [PATCH 1/5] dma-mapping: make the get_required_mask method available unconditionally Christoph Hellwig
[not found] ` <20180920185247.20037-2-hch-jcswGhMUV9g@public.gmane.org>
2018-09-27 1:28 ` Benjamin Herrenschmidt
2018-09-27 1:28 ` Benjamin Herrenschmidt
2018-09-20 18:52 ` [PATCH 2/5] dma-direct: add an explicit dma_direct_get_required_mask Christoph Hellwig
[not found] ` <20180920185247.20037-3-hch-jcswGhMUV9g@public.gmane.org>
2018-09-27 1:31 ` Benjamin Herrenschmidt
2018-09-27 1:31 ` Benjamin Herrenschmidt
2018-09-27 14:12 ` Robin Murphy
2018-09-27 15:28 ` Christoph Hellwig
[not found] ` <20180927152818.GC10566-jcswGhMUV9g@public.gmane.org>
2018-09-27 15:35 ` Robin Murphy
2018-09-27 15:35 ` Robin Murphy
2018-09-20 18:52 ` [PATCH 3/5] dma-direct: refine dma_direct_alloc zone selection Christoph Hellwig
[not found] ` <20180920185247.20037-4-hch-jcswGhMUV9g@public.gmane.org>
2018-09-27 1:45 ` Benjamin Herrenschmidt
2018-09-27 1:45 ` Benjamin Herrenschmidt
[not found] ` <1811156d5a1df1166c7ab7522525619b951f047d.camel-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>
2018-09-27 13:49 ` Christoph Hellwig [this message]
2018-09-27 13:49 ` Christoph Hellwig
[not found] ` <20180927134922.GA8281-jcswGhMUV9g@public.gmane.org>
2018-09-28 0:06 ` Benjamin Herrenschmidt
2018-09-28 0:06 ` Benjamin Herrenschmidt
2018-09-28 0:06 ` Benjamin Herrenschmidt
2018-09-28 15:46 ` Christoph Hellwig
2018-09-28 15:46 ` Christoph Hellwig
2018-09-27 14:30 ` Robin Murphy
2018-09-27 15:30 ` Christoph Hellwig
[not found] ` <20180927153028.GD10566-jcswGhMUV9g@public.gmane.org>
2018-09-27 15:38 ` Robin Murphy
2018-09-27 15:38 ` Robin Murphy
[not found] ` <2b98d7b2-bf74-ccc9-881a-a91e2c9949c3-5wv7dgnIgG8@public.gmane.org>
2018-09-27 15:41 ` Christoph Hellwig
2018-09-27 15:41 ` Christoph Hellwig
2018-09-20 18:52 ` [PATCH 4/5] dma-direct: implement complete bus_dma_mask handling Christoph Hellwig
[not found] ` <20180920185247.20037-5-hch-jcswGhMUV9g@public.gmane.org>
2018-09-27 14:58 ` Robin Murphy
2018-09-27 14:58 ` Robin Murphy
2018-09-27 15:32 ` Christoph Hellwig
2018-09-27 16:14 ` Robin Murphy
2018-09-27 16:14 ` Robin Murphy
[not found] ` <967e98b1-99ab-8f95-4c89-6156ce489b93-5wv7dgnIgG8@public.gmane.org>
2018-09-27 16:27 ` Christoph Hellwig
2018-09-27 16:27 ` Christoph Hellwig
2018-09-27 16:27 ` Christoph Hellwig
[not found] ` <20180927162737.GA11974-jcswGhMUV9g@public.gmane.org>
2018-09-27 16:41 ` Robin Murphy
2018-09-27 16:41 ` Robin Murphy
2018-09-27 16:41 ` Robin Murphy
2018-09-20 18:52 ` [PATCH 5/5] dma-direct: always allow dma mask <= physiscal memory size Christoph Hellwig
[not found] ` <20180920185247.20037-6-hch-jcswGhMUV9g@public.gmane.org>
2018-09-27 1:50 ` Benjamin Herrenschmidt
2018-09-27 1:50 ` Benjamin Herrenschmidt
2018-09-27 13:49 ` Christoph Hellwig
2018-09-27 15:07 ` Robin Murphy
-- strict thread matches above, loose matches on Subject: below --
2018-09-27 22:35 dma mask related fixups (including full bus_dma_mask support) v2 Christoph Hellwig
2018-09-27 22:35 ` [PATCH 3/5] dma-direct: refine dma_direct_alloc zone selection Christoph Hellwig
2018-09-27 22:35 ` 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=20180927134922.GA8281@lst.de \
--to=hch-jcswghmuv9g@public.gmane.org \
--cc=benh-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org \
--cc=gregkh-hQyY1W1yCW8ekmWlsbkhG0B+6BGkLq7r@public.gmane.org \
--cc=iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linuxppc-dev-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org \
--cc=robin.murphy-5wv7dgnIgG8@public.gmane.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.