| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20201125221917.150463-1-ribalda@chromium.org>
Date: Wed, 25 Nov 2020 23:19:17 +0100
From: Ricardo Ribalda <ribalda@...omium.org>
To: Marek Szyprowski <m.szyprowski@...sung.com>,
Robin Murphy <robin.murphy@....com>,
Christoph Hellwig <hch@....de>,
Mauro Carvalho Chehab <mchehab@...nel.org>,
IOMMU DRIVERS <iommu@...ts.linux-foundation.org>,
Joerg Roedel <joro@...tes.org>,
Linux Doc Mailing List <linux-doc@...r.kernel.org>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
Linux Media Mailing List <linux-media@...r.kernel.org>,
Tomasz Figa <tfiga@...omium.org>,
Sergey Senozhatsky <senozhatsky@...gle.com>
Cc: Ricardo Ribalda <ribalda@...omium.org>
Subject: [PATCH v3 5/6] media: uvcvideo: Use dma_alloc_noncontiguos API
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_sgtable().
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@...omium.org>
---
v3: Thanks to Marek Szyprowski
Use dma_sync_sgtable and _for_cpu()
drivers/media/usb/uvc/uvc_video.c | 93 +++++++++++++++++++++++++++----
drivers/media/usb/uvc/uvcvideo.h | 2 +
2 files changed, 83 insertions(+), 12 deletions(-)
diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
index a6a441d92b94..06ebd7a3877b 100644
--- a/drivers/media/usb/uvc/uvc_video.c
+++ b/drivers/media/usb/uvc/uvc_video.c
@@ -1097,6 +1097,11 @@ static int uvc_video_decode_start(struct uvc_streaming *stream,
return data[0];
}
+static inline struct device *stream_to_dmadev(struct uvc_streaming *stream)
+{
+ return stream->dev->udev->bus->controller->parent;
+}
+
/*
* uvc_video_decode_data_work: Asynchronous memcpy processing
*
@@ -1118,6 +1123,9 @@ static void uvc_video_copy_data_work(struct work_struct *work)
uvc_queue_buffer_release(op->buf);
}
+ if (uvc_urb->pages)
+ dma_sync_sgtable_for_device(stream_to_dmadev(uvc_urb->stream),
+ &uvc_urb->sgt, DMA_FROM_DEVICE);
ret = usb_submit_urb(uvc_urb->urb, GFP_KERNEL);
if (ret < 0)
uvc_printk(KERN_ERR, "Failed to resubmit video URB (%d).\n",
@@ -1539,10 +1547,17 @@ 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_sgtable_for_cpu(stream_to_dmadev(stream),
+ &uvc_urb->sgt, DMA_FROM_DEVICE);
stream->decode(uvc_urb, buf, buf_meta);
/* If no async work is needed, resubmit the URB immediately. */
if (!uvc_urb->async_operations) {
+ if (uvc_urb->pages)
+ dma_sync_sgtable_for_device(stream_to_dmadev(stream),
+ &uvc_urb->sgt,
+ DMA_FROM_DEVICE);
ret = usb_submit_urb(uvc_urb->urb, GFP_ATOMIC);
if (ret < 0)
uvc_printk(KERN_ERR,
@@ -1566,8 +1581,16 @@ 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) {
+ sg_free_table(&uvc_urb->sgt);
+ 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 +1600,56 @@ 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;
+ }
+
+ if (sg_alloc_table_from_pages(&uvc_urb->sgt, uvc_urb->pages,
+ PAGE_ALIGN(stream->urb_size) >> PAGE_SHIFT, 0,
+ stream->urb_size, GFP_KERNEL)) {
+ vunmap(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 +1680,11 @@ 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;
}
@@ -1891,6 +1956,10 @@ static int uvc_video_start_transfer(struct uvc_streaming *stream,
/* Submit the URBs. */
for_each_uvc_urb(uvc_urb, stream) {
+ if (uvc_urb->pages)
+ dma_sync_sgtable_for_device(stream_to_dmadev(stream),
+ &uvc_urb->sgt,
+ DMA_FROM_DEVICE);
ret = usb_submit_urb(uvc_urb->urb, gfp_flags);
if (ret < 0) {
uvc_printk(KERN_ERR, "Failed to submit URB %u (%d).\n",
diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
index a3dfacf069c4..3e6618a2ac82 100644
--- a/drivers/media/usb/uvc/uvcvideo.h
+++ b/drivers/media/usb/uvc/uvcvideo.h
@@ -532,6 +532,8 @@ struct uvc_urb {
char *buffer;
dma_addr_t dma;
+ struct page **pages;
+ struct sg_table sgt;
unsigned int async_operations;
struct uvc_copy_op copy_operations[UVC_MAX_PACKETS];
--
2.29.2.454.gaff20da3a2-goog
Powered by blists - more mailing lists