linux-media.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Sergey Senozhatsky <senozhatsky@chromium.org>
To: Hans Verkuil <hans.verkuil@cisco.com>,
	Tomasz Figa <tfiga@chromium.org>,
	Mauro Carvalho Chehab <mchehab@kernel.org>,
	Kyungmin Park <kyungmin.park@samsung.com>,
	Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Sakari Ailus <sakari.ailus@iki.fi>,
	Laurent Pinchart <laurent.pinchart@ideasonboard.com>,
	Pawel Osciak <posciak@chromium.org>,
	linux-media@vger.kernel.org, linux-kernel@vger.kernel.org,
	Sergey Senozhatsky <senozhatsky@chromium.org>
Subject: [RFC][PATCHv2 03/12] videobuf2: add V4L2_FLAG_MEMORY_NON_CONSISTENT flag
Date: Tue,  4 Feb 2020 11:56:32 +0900	[thread overview]
Message-ID: <20200204025641.218376-4-senozhatsky@chromium.org> (raw)
In-Reply-To: <20200204025641.218376-1-senozhatsky@chromium.org>

By setting or clearing V4L2_FLAG_MEMORY_NON_CONSISTENT flag
user-space should be able to set or clear queue's NON_CONSISTENT
->dma_attrs. Queue's ->dma_attrs are passed to the underlying
allocator in __vb2_buf_mem_alloc(), so thus user-space is able
to request vb2 buffer's memory to be either consistent (coherent)
or non-consistent.

Change-Id: Ib333081c482e23c9a89386078293e19c3fd59076
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
---
 Documentation/media/uapi/v4l/buffer.rst | 27 +++++++++++++++++++++++++
 include/uapi/linux/videodev2.h          |  2 ++
 2 files changed, 29 insertions(+)

diff --git a/Documentation/media/uapi/v4l/buffer.rst b/Documentation/media/uapi/v4l/buffer.rst
index 9149b57728e5..af007daf0591 100644
--- a/Documentation/media/uapi/v4l/buffer.rst
+++ b/Documentation/media/uapi/v4l/buffer.rst
@@ -705,6 +705,33 @@ Buffer Flags
 
 .. c:type:: v4l2_memory
 
+Memory Consistency Flags
+========================
+
+.. tabularcolumns:: |p{7.0cm}|p{2.2cm}|p{8.3cm}|
+
+.. cssclass:: longtable
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       3 1 4
+
+    * .. _`V4L2_FLAG_MEMORY_NON_CONSISTENT`:
+
+      - ``V4L2_FLAG_MEMORY_NON_CONSISTENT``
+      - 0x00000001
+      - vb2 buffer is allocated either in consistent (it will be automatically
+	coherent between CPU and bus) or non-consistent memory. The latter
+	can provide performance gains, for instance CPU cache sync/flush
+	operations can be avoided if the buffer is accesed by the corresponding
+	device only and CPU does not read/write to/from that buffer. However,
+	this requires extra care from the driver -- it must guarantee memory
+	consistency by issuing cache flush/sync when consistency is needed.
+	If this flag is set V4L2 will attempt to allocate vb2 buffer in
+	non-consistent memory. This flag is ignored if queue does not report
+        :ret:`V4L2_BUF_CAP_SUPPORTS_CACHE_HINTS` capability.
+
 enum v4l2_memory
 ================
 
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 5f9357dcb060..72efc1c544cd 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -189,6 +189,8 @@ enum v4l2_memory {
 	V4L2_MEMORY_DMABUF           = 4,
 };
 
+#define V4L2_FLAG_MEMORY_NON_CONSISTENT		(1 << 0)
+
 /* see also http://vektor.theorem.ca/graphics/ycbcr/ */
 enum v4l2_colorspace {
 	/*
-- 
2.25.0.341.g760bfbb309-goog


  parent reply	other threads:[~2020-02-04  2:57 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-04  2:56 [RFC][PATCHv2 00/12] Implement V4L2_BUF_FLAG_NO_CACHE_* flags Sergey Senozhatsky
2020-02-04  2:56 ` [RFC][PATCHv2 01/12] videobuf2: add cache management members Sergey Senozhatsky
2020-02-19  8:05   ` Hans Verkuil
2020-02-19  8:16     ` Sergey Senozhatsky
2020-02-19  8:27       ` Hans Verkuil
2020-02-04  2:56 ` [RFC][PATCHv2 02/12] videobuf2: handle V4L2 buffer cache flags Sergey Senozhatsky
2020-02-05  8:13   ` Sergey Senozhatsky
2020-02-19  8:07   ` Hans Verkuil
2020-02-19  8:13     ` Sergey Senozhatsky
2020-02-19  8:25       ` Hans Verkuil
2020-02-19  8:46   ` Hans Verkuil
2020-02-04  2:56 ` Sergey Senozhatsky [this message]
2020-02-13  7:08   ` [RFC][PATCHv2 03/12] videobuf2: add V4L2_FLAG_MEMORY_NON_CONSISTENT flag Tomasz Figa
2020-02-19  8:19   ` Hans Verkuil
2020-02-19  8:56   ` Hans Verkuil
2020-02-25  7:45     ` Sergey Senozhatsky
2020-02-04  2:56 ` [RFC][PATCHv2 04/12] videobuf2: add queue memory consistency parameter Sergey Senozhatsky
2020-02-04  2:56 ` [RFC][PATCHv2 05/12] videobuf2: handle V4L2_FLAG_MEMORY_NON_CONSISTENT flag Sergey Senozhatsky
2020-02-19  8:25   ` Hans Verkuil
2020-02-19  8:59     ` Sergey Senozhatsky
2020-02-19  9:04       ` Hans Verkuil
2020-02-19  8:48   ` Hans Verkuil
2020-02-19  9:05     ` Sergey Senozhatsky
2020-02-19  9:11       ` Hans Verkuil
2020-02-04  2:56 ` [RFC][PATCHv2 06/12] videobuf2: factor out planes prepare/finish functions Sergey Senozhatsky
2020-02-04  2:56 ` [RFC][PATCHv2 07/12] videobuf2: do not sync caches when we are allowed not to Sergey Senozhatsky
2020-02-04  2:56 ` [RFC][PATCHv2 08/12] videobuf2: check ->synced flag in prepare() and finish() Sergey Senozhatsky
2020-02-04  2:56 ` [RFC][PATCHv2 09/12] videobuf2: let user-space know if driver supports cache hints Sergey Senozhatsky
2020-02-19  8:33   ` Hans Verkuil
2020-02-19  8:45     ` Sergey Senozhatsky
2020-02-19  8:56       ` Hans Verkuil
2020-02-04  2:56 ` [RFC][PATCHv2 10/12] videobuf2: add begin/end cpu_access callbacks to dma-contig Sergey Senozhatsky
2020-02-04  2:56 ` [RFC][PATCHv2 11/12] videobuf2: add begin/end cpu_access callbacks to dma-sg Sergey Senozhatsky
2020-02-19  8:35   ` Hans Verkuil
2020-02-19  8:42     ` Sergey Senozhatsky
2020-02-04  2:56 ` [RFC][PATCHv2 12/12] videobuf2: don't test db_attach in dma-contig prepare and finish Sergey Senozhatsky
2020-02-19  8:53 ` [RFC][PATCHv2 00/12] Implement V4L2_BUF_FLAG_NO_CACHE_* flags Hans Verkuil
2020-02-26 11:20   ` Sergey Senozhatsky

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=20200204025641.218376-4-senozhatsky@chromium.org \
    --to=senozhatsky@chromium.org \
    --cc=hans.verkuil@cisco.com \
    --cc=kyungmin.park@samsung.com \
    --cc=laurent.pinchart@ideasonboard.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-media@vger.kernel.org \
    --cc=m.szyprowski@samsung.com \
    --cc=mchehab@kernel.org \
    --cc=posciak@chromium.org \
    --cc=sakari.ailus@iki.fi \
    --cc=tfiga@chromium.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).