iommu.lists.linux-foundation.org archive mirror
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: "Björn Töpel" <bjorn.topel@intel.com>
Cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
	iommu@lists.linux-foundation.org,
	Jonathan Lemon <jonathan.lemon@gmail.com>,
	bpf@vger.kernel.org, Magnus Karlsson <magnus.karlsson@intel.com>
Subject: [PATCH 1/4] dma-mapping: add a new dma_need_sync API
Date: Mon, 29 Jun 2020 15:03:56 +0200	[thread overview]
Message-ID: <20200629130359.2690853-2-hch@lst.de> (raw)
In-Reply-To: <20200629130359.2690853-1-hch@lst.de>

Add a new API to check if calls to dma_sync_single_for_{device,cpu} are
required for a given DMA streaming mapping.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 Documentation/core-api/dma-api.rst |  8 ++++++++
 include/linux/dma-direct.h         |  1 +
 include/linux/dma-mapping.h        |  5 +++++
 kernel/dma/direct.c                |  6 ++++++
 kernel/dma/mapping.c               | 10 ++++++++++
 5 files changed, 30 insertions(+)

diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst
index 2d8d2fed731720..f41620439ef349 100644
--- a/Documentation/core-api/dma-api.rst
+++ b/Documentation/core-api/dma-api.rst
@@ -204,6 +204,14 @@ Returns the maximum size of a mapping for the device. The size parameter
 of the mapping functions like dma_map_single(), dma_map_page() and
 others should not be larger than the returned value.
 
+::
+
+	bool
+	dma_need_sync(struct device *dev, dma_addr_t dma_addr);
+
+Returns %true if dma_sync_single_for_{device,cpu} calls are required to
+transfer memory ownership.  Returns %false if those calls can be skipped.
+
 ::
 
 	unsigned long
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index cdfa400f89b3d3..5184735a0fe8eb 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -85,4 +85,5 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
 int dma_direct_supported(struct device *dev, u64 mask);
+bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 78f677cf45ab69..a33ed3954ed465 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -461,6 +461,7 @@ int dma_set_mask(struct device *dev, u64 mask);
 int dma_set_coherent_mask(struct device *dev, u64 mask);
 u64 dma_get_required_mask(struct device *dev);
 size_t dma_max_mapping_size(struct device *dev);
+bool dma_need_sync(struct device *dev, dma_addr_t dma_addr);
 unsigned long dma_get_merge_boundary(struct device *dev);
 #else /* CONFIG_HAS_DMA */
 static inline dma_addr_t dma_map_page_attrs(struct device *dev,
@@ -571,6 +572,10 @@ static inline size_t dma_max_mapping_size(struct device *dev)
 {
 	return 0;
 }
+static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+	return false;
+}
 static inline unsigned long dma_get_merge_boundary(struct device *dev)
 {
 	return 0;
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 93f578a8e613ba..95866b64758100 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -539,3 +539,9 @@ size_t dma_direct_max_mapping_size(struct device *dev)
 		return swiotlb_max_mapping_size(dev);
 	return SIZE_MAX;
 }
+
+bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+	return !dev_is_dma_coherent(dev) ||
+		is_swiotlb_buffer(dma_to_phys(dev, dma_addr));
+}
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 98e3d873792ea4..a8c18c9a796fdc 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -397,6 +397,16 @@ size_t dma_max_mapping_size(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dma_max_mapping_size);
 
+bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (dma_is_direct(ops))
+		return dma_direct_need_sync(dev, dma_addr);
+	return ops->sync_single_for_cpu || ops->sync_single_for_device;
+}
+EXPORT_SYMBOL_GPL(dma_need_sync);
+
 unsigned long dma_get_merge_boundary(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
-- 
2.26.2

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

  reply	other threads:[~2020-06-29 13:04 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-29 13:03 add an API to check if a streamming mapping needs sync calls Christoph Hellwig
2020-06-29 13:03 ` Christoph Hellwig [this message]
2020-07-06 19:42   ` [PATCH 1/4] dma-mapping: add a new dma_need_sync API Jonathan Lemon
2020-07-07  6:47     ` Christoph Hellwig
2020-07-07 15:11       ` Jonathan Lemon
2020-07-07 15:14         ` Christoph Hellwig
2020-06-29 13:03 ` [PATCH 2/4] xsk: replace the cheap_dma flag with a dma_need_sync flag Christoph Hellwig
2020-06-29 13:03 ` [PATCH 3/4] xsk: remove a double pool->dev assignment in xp_dma_map Christoph Hellwig
2020-06-29 13:03 ` [PATCH 4/4] xsk: use dma_need_sync instead of reimplenting it Christoph Hellwig
2020-06-29 13:39 ` add an API to check if a streamming mapping needs sync calls Björn Töpel
2020-06-29 14:22   ` Christoph Hellwig
2020-07-08  7:44   ` Christoph Hellwig
2020-07-08  9:01     ` Daniel Borkmann

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=20200629130359.2690853-2-hch@lst.de \
    --to=hch@lst.de \
    --cc=bjorn.topel@intel.com \
    --cc=bpf@vger.kernel.org \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jonathan.lemon@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=magnus.karlsson@intel.com \
    --cc=netdev@vger.kernel.org \
    --subject='Re: [PATCH 1/4] dma-mapping: add a new dma_need_sync API' \
    /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

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).