From: Christoph Hellwig <hch@lst.de>
To: Paul Burton <paul.burton@mips.com>
Cc: Christoph Hellwig <hch@lst.de>,
Ralf Baechle <ralf@linux-mips.org>,
James Hogan <jhogan@kernel.org>, Ley Foon Tan <lftan@altera.com>,
Michal Simek <monstr@monstr.eu>,
Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>,
"linux-mips@vger.kernel.org" <linux-mips@vger.kernel.org>,
"iommu@lists.linux-foundation.org"
<iommu@lists.linux-foundation.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"linux-fbdev@vger.kernel.org" <linux-fbdev@vger.kernel.org>
Subject: Re: [PATCH 4/7] dma-direct: provide generic support for uncached kernel segments
Date: Wed, 01 May 2019 17:29:12 +0000 [thread overview]
Message-ID: <20190501172912.GA19375@lst.de> (raw)
In-Reply-To: <20190501171857.chfxqntvm6r4xrr4@pburton-laptop>
[-- Attachment #1: Type: text/plain, Size: 564 bytes --]
On Wed, May 01, 2019 at 05:18:59PM +0000, Paul Burton wrote:
> I'm not so sure about this part though.
>
> On MIPS we currently don't clear the allocated memory with memset. Is
> doing that really necessary?
We are clearling it on mips, it is inside dma_direct_alloc_pages.
> If it is necessary then as-is this code will clear the allocated memory
> using uncached writes which will be pretty slow. It would be much more
> efficient to perform the memset before arch_dma_prep_coherent() & before
> converting ret to an uncached address.
Yes, we could do that.
[-- Attachment #2: 0001-dma-direct-provide-generic-support-for-uncached-kern.patch --]
[-- Type: text/x-patch, Size: 3565 bytes --]
From 247ca658ebeb7c8d04918747ec8a0da45c36bcb8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 28 Apr 2019 13:23:26 -0500
Subject: dma-direct: provide generic support for uncached kernel segments
A few architectures support uncached kernel segments. In that case we get
an uncached mapping for a given physica address by using an offset in the
uncached segement. Implement support for this scheme in the generic
dma-direct code instead of duplicating it in arch hooks.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
arch/Kconfig | 8 ++++++++
include/linux/dma-noncoherent.h | 3 +++
kernel/dma/direct.c | 17 +++++++++++++++--
3 files changed, 26 insertions(+), 2 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 33687dddd86a..ea22a8c894ec 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -249,6 +249,14 @@ config ARCH_HAS_FORTIFY_SOURCE
config ARCH_HAS_SET_MEMORY
bool
+#
+# Select if arch has an uncached kernel segment and provides the
+# uncached_kernel_address / cached_kernel_address symbols to use it
+#
+config ARCH_HAS_UNCACHED_SEGMENT
+ select ARCH_HAS_DMA_PREP_COHERENT
+ bool
+
# Select if arch init_task must go in the __init_task_data section
config ARCH_TASK_STRUCT_ON_STACK
bool
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index 9741767e400f..7e0126a04e02 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -80,4 +80,7 @@ static inline void arch_dma_prep_coherent(struct page *page, size_t size)
}
#endif /* CONFIG_ARCH_HAS_DMA_PREP_COHERENT */
+void *uncached_kernel_address(void *addr);
+void *cached_kernel_address(void *addr);
+
#endif /* _LINUX_DMA_NONCOHERENT_H */
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 2c2772e9702a..6688e1cee7d1 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -171,6 +171,13 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
*dma_handle = phys_to_dma(dev, page_to_phys(page));
}
memset(ret, 0, size);
+
+ if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+ !dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_NON_CONSISTENT)) {
+ arch_dma_prep_coherent(page, size);
+ ret = uncached_kernel_address(ret);
+ }
+
return ret;
}
@@ -189,13 +196,18 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
if (force_dma_unencrypted())
set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
+
+ if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+ !dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_NON_CONSISTENT))
+ cpu_addr = cached_kernel_address(cpu_addr);
__dma_direct_free_pages(dev, size, virt_to_page(cpu_addr));
}
void *dma_direct_alloc(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
{
- if (!dev_is_dma_coherent(dev))
+ if (!IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+ !dev_is_dma_coherent(dev))
return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
return dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
}
@@ -203,7 +215,8 @@ void *dma_direct_alloc(struct device *dev, size_t size,
void dma_direct_free(struct device *dev, size_t size,
void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
{
- if (!dev_is_dma_coherent(dev))
+ if (!IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+ !dev_is_dma_coherent(dev))
arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
else
dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
--
2.20.1
next prev parent reply other threads:[~2019-05-01 17:29 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-04-30 11:00 provide generic support for uncached segements in dma-direct Christoph Hellwig
2019-04-30 11:00 ` [PATCH 1/7] MIPS: remove the _dma_cache_wback_inv export Christoph Hellwig
2019-04-30 11:00 ` [PATCH 2/7] au1100fb: fix DMA API abuse Christoph Hellwig
2019-05-06 13:49 ` Bartlomiej Zolnierkiewicz
2019-05-07 6:36 ` Christoph Hellwig
2019-06-03 6:49 ` Christoph Hellwig
2019-04-30 11:00 ` [PATCH 3/7] dma-mapping: add a Kconfig symbol to indicate arch_dma_prep_coherent presence Christoph Hellwig
2019-04-30 11:00 ` [PATCH 4/7] dma-direct: provide generic support for uncached kernel segments Christoph Hellwig
2019-05-01 17:18 ` Paul Burton
2019-05-01 17:29 ` Christoph Hellwig [this message]
2019-05-01 17:40 ` Paul Burton
2019-05-01 17:49 ` Christoph Hellwig
2019-05-02 0:08 ` Paul Burton
2019-05-02 13:11 ` Christoph Hellwig
2019-04-30 11:00 ` [PATCH 5/7] MIPS: use the generic uncached segment support in dma-direct Christoph Hellwig
2019-04-30 20:10 ` Paul Burton
2019-04-30 20:29 ` Christoph Hellwig
2019-04-30 21:11 ` Paul Burton
2019-04-30 21:15 ` Christoph Hellwig
2019-05-01 13:13 ` [PATCH 5/7 v2] " Christoph Hellwig
2019-05-01 17:13 ` Paul Burton
2019-06-03 6:48 ` Christoph Hellwig
2019-07-03 8:54 ` Arnd Bergmann
2019-07-03 12:13 ` Christoph Hellwig
2019-04-30 11:00 ` [PATCH 6/7] nios2: " Christoph Hellwig
2019-04-30 11:00 ` [PATCH 7/7] microblaze: " 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=20190501172912.GA19375@lst.de \
--to=hch@lst.de \
--cc=b.zolnierkie@samsung.com \
--cc=iommu@lists.linux-foundation.org \
--cc=jhogan@kernel.org \
--cc=lftan@altera.com \
--cc=linux-fbdev@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mips@vger.kernel.org \
--cc=monstr@monstr.eu \
--cc=paul.burton@mips.com \
--cc=ralf@linux-mips.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 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).