From: Ricardo Ribalda <ribalda@chromium.org>
To: Christoph Hellwig <hch@lst.de>,
Mauro Carvalho Chehab <mchehab@kernel.org>,
Marek Szyprowski <m.szyprowski@samsung.com>,
IOMMU DRIVERS <iommu@lists.linux-foundation.org>,
Joerg Roedel <joro@8bytes.org>,
Robin Murphy <robin.murphy@arm.com>,
Linux Doc Mailing List <linux-doc@vger.kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Linux Media Mailing List <linux-media@vger.kernel.org>,
Tomasz Figa <tfiga@chromium.org>,
Sergey Senozhatsky <senozhatsky@google.com>
Cc: Ricardo Ribalda <ribalda@chromium.org>
Subject: [PATCH 5/6] media: uvcvideo: Use dma_alloc_noncontiguos API
Date: Tue, 24 Nov 2020 16:38:44 +0100 [thread overview]
Message-ID: <20201124153845.132207-5-ribalda@chromium.org> (raw)
In-Reply-To: <20201124153845.132207-1-ribalda@chromium.org>
On architectures where the is no coherent caching such as ARM use the
dma_alloc_noncontiguos API and handle manually the cache flushing using
dma_sync_single().
With this patch on the affected architectures we can measure up to 20x
performance improvement in uvc_video_copy_data_work().
Signed-off-by: Ricardo Ribalda <ribalda@chromium.org>
---
drivers/media/usb/uvc/uvc_video.c | 74 ++++++++++++++++++++++++++-----
drivers/media/usb/uvc/uvcvideo.h | 1 +
2 files changed, 63 insertions(+), 12 deletions(-)
diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
index a6a441d92b94..9e90b261428a 100644
--- a/drivers/media/usb/uvc/uvc_video.c
+++ b/drivers/media/usb/uvc/uvc_video.c
@@ -1490,6 +1490,11 @@ static void uvc_video_encode_bulk(struct uvc_urb *uvc_urb,
urb->transfer_buffer_length = stream->urb_size - len;
}
+static inline struct device *stream_to_dmadev(struct uvc_streaming *stream)
+{
+ return stream->dev->udev->bus->controller->parent;
+}
+
static void uvc_video_complete(struct urb *urb)
{
struct uvc_urb *uvc_urb = urb->context;
@@ -1539,6 +1544,11 @@ static void uvc_video_complete(struct urb *urb)
* Process the URB headers, and optionally queue expensive memcpy tasks
* to be deferred to a work queue.
*/
+ if (uvc_urb->pages)
+ dma_sync_single_for_cpu(stream_to_dmadev(stream),
+ urb->transfer_dma,
+ urb->transfer_buffer_length,
+ DMA_FROM_DEVICE);
stream->decode(uvc_urb, buf, buf_meta);
/* If no async work is needed, resubmit the URB immediately. */
@@ -1566,8 +1576,15 @@ static void uvc_free_urb_buffers(struct uvc_streaming *stream)
continue;
#ifndef CONFIG_DMA_NONCOHERENT
- usb_free_coherent(stream->dev->udev, stream->urb_size,
- uvc_urb->buffer, uvc_urb->dma);
+ if (uvc_urb->pages) {
+ vunmap(uvc_urb->buffer);
+ dma_free_noncontiguous(stream_to_dmadev(stream),
+ stream->urb_size,
+ uvc_urb->pages, uvc_urb->dma);
+ } else {
+ usb_free_coherent(stream->dev->udev, stream->urb_size,
+ uvc_urb->buffer, uvc_urb->dma);
+ }
#else
kfree(uvc_urb->buffer);
#endif
@@ -1577,6 +1594,47 @@ static void uvc_free_urb_buffers(struct uvc_streaming *stream)
stream->urb_size = 0;
}
+#ifndef CONFIG_DMA_NONCOHERENT
+static bool uvc_alloc_urb_buffer(struct uvc_streaming *stream,
+ struct uvc_urb *uvc_urb, gfp_t gfp_flags)
+{
+ struct device *dma_dev = dma_dev = stream_to_dmadev(stream);
+
+ if (!dma_can_alloc_noncontiguous(dma_dev)) {
+ uvc_urb->buffer = usb_alloc_coherent(stream->dev->udev,
+ stream->urb_size,
+ gfp_flags | __GFP_NOWARN,
+ &uvc_urb->dma);
+ return uvc_urb->buffer != NULL;
+ }
+
+ uvc_urb->pages = dma_alloc_noncontiguous(dma_dev, stream->urb_size,
+ &uvc_urb->dma,
+ gfp_flags | __GFP_NOWARN, 0);
+ if (!uvc_urb->pages)
+ return false;
+
+ uvc_urb->buffer = vmap(uvc_urb->pages,
+ PAGE_ALIGN(stream->urb_size) >> PAGE_SHIFT,
+ VM_DMA_COHERENT, PAGE_KERNEL);
+ if (!uvc_urb->buffer) {
+ dma_free_noncontiguous(dma_dev, stream->urb_size,
+ uvc_urb->pages, uvc_urb->dma);
+ return false;
+ }
+
+ return true;
+}
+#else
+static bool uvc_alloc_urb_buffer(struct uvc_streaming *stream,
+ struct uvc_urb *uvc_urb, gfp_t gfp_flags)
+{
+ uvc_urb->buffer = kmalloc(stream->urb_size, gfp_flags | __GFP_NOWARN);
+
+ return uvc_urb->buffer != NULL;
+}
+#endif
+
/*
* Allocate transfer buffers. This function can be called with buffers
* already allocated when resuming from suspend, in which case it will
@@ -1607,19 +1665,11 @@ static int uvc_alloc_urb_buffers(struct uvc_streaming *stream,
/* Retry allocations until one succeed. */
for (; npackets > 1; npackets /= 2) {
+ stream->urb_size = psize * npackets;
for (i = 0; i < UVC_URBS; ++i) {
struct uvc_urb *uvc_urb = &stream->uvc_urb[i];
- stream->urb_size = psize * npackets;
-#ifndef CONFIG_DMA_NONCOHERENT
- uvc_urb->buffer = usb_alloc_coherent(
- stream->dev->udev, stream->urb_size,
- gfp_flags | __GFP_NOWARN, &uvc_urb->dma);
-#else
- uvc_urb->buffer =
- kmalloc(stream->urb_size, gfp_flags | __GFP_NOWARN);
-#endif
- if (!uvc_urb->buffer) {
+ if (!uvc_alloc_urb_buffer(stream, uvc_urb, gfp_flags)) {
uvc_free_urb_buffers(stream);
break;
}
diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
index a3dfacf069c4..3e3ef1f1daa5 100644
--- a/drivers/media/usb/uvc/uvcvideo.h
+++ b/drivers/media/usb/uvc/uvcvideo.h
@@ -532,6 +532,7 @@ struct uvc_urb {
char *buffer;
dma_addr_t dma;
+ struct page **pages;
unsigned int async_operations;
struct uvc_copy_op copy_operations[UVC_MAX_PACKETS];
--
2.29.2.454.gaff20da3a2-goog
next prev parent reply other threads:[~2020-11-24 15:39 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-24 15:38 [PATCH 1/6] dma-mapping: remove the {alloc,free}_noncoherent methods Ricardo Ribalda
2020-11-24 15:38 ` [PATCH 2/6] dma-direct: use __GFP_ZERO in dma_direct_alloc_pages Ricardo Ribalda
2020-11-30 8:27 ` Christoph Hellwig
2020-11-24 15:38 ` [PATCH 3/6] dma-iommu: remove __iommu_dma_mmap Ricardo Ribalda
2020-11-30 8:28 ` Christoph Hellwig
2020-11-24 15:38 ` [PATCH 4/6] WIP: add a dma_alloc_contiguous API Ricardo Ribalda
2020-11-24 15:38 ` Ricardo Ribalda [this message]
2020-11-24 16:29 ` [PATCH 5/6] media: uvcvideo: Use dma_alloc_noncontiguos API Robin Murphy
2020-11-24 17:25 ` Ricardo Ribalda
2020-11-24 15:38 ` [PATCH 6/6] TEST-ONLY: media: uvcvideo: Add statistics for measuring performance Ricardo Ribalda
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=20201124153845.132207-5-ribalda@chromium.org \
--to=ribalda@chromium.org \
--cc=hch@lst.de \
--cc=iommu@lists.linux-foundation.org \
--cc=joro@8bytes.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-media@vger.kernel.org \
--cc=m.szyprowski@samsung.com \
--cc=mchehab@kernel.org \
--cc=robin.murphy@arm.com \
--cc=senozhatsky@google.com \
--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).