[FFmpeg-devel] [PATCH 6/6] lavc/qsv-lavc/vpp: Promote gpu_copy to be a selectable parameter. GPU-copy is defaultly closed because it seems to be unstable.
From: ChaoX A Liu
Signed-off-by: ChaoX A Liu
---
libavcodec/qsv.c | 7 ++-
libavcodec/qsv_internal.h | 1 +
libavcodec/qsvdec.c | 22 +-
libavcodec/qsvdec_h2645.c | 12
libavcodec/qsvdec_mpeg2.c | 6 ++
libavcodec/qsvdec_vc1.c | 6 ++
libavcodec/qsvenc.h | 4
libavfilter/vf_qsvvpp.c | 8 +++-
8 files changed, 59 insertions(+), 7 deletions(-)
diff --git a/libavcodec/qsv.c b/libavcodec/qsv.c
index c180ca8..c61a29c 100644
--- a/libavcodec/qsv.c
+++ b/libavcodec/qsv.c
@@ -172,11 +172,16 @@ int ff_qsv_init_internal_session(void *avctx, QSVSession
*qs)
{
mfxIMPL impl = MFX_IMPL_AUTO_ANY;
mfxVersion ver = { { QSV_VERSION_MINOR, QSV_VERSION_MAJOR } };
+mfxInitParam par;
const char *desc;
int ret;
-ret = MFXInit(impl, &ver, &qs->session);
+memset(&par, 0, sizeof(par));
+par.Implementation = impl;
+par.Version = ver;
+par.GPUCopy = qs->gpu_copy;
+ret = MFXInitEx(par, &qs->session);
if (ret < 0) {
av_log(avctx, AV_LOG_ERROR, "Error initializing an internal MFX
session\n");
return ff_qsv_error(ret);
diff --git a/libavcodec/qsv_internal.h b/libavcodec/qsv_internal.h
index 58589df..39778a9 100644
--- a/libavcodec/qsv_internal.h
+++ b/libavcodec/qsv_internal.h
@@ -73,6 +73,7 @@ typedef struct QSVSession {
intfd_display;
VADisplay va_display;
#endif
+intgpu_copy;
} QSVSession;
/**
diff --git a/libavcodec/qsvdec.c b/libavcodec/qsvdec.c
index 2075a23..08a5eaa 100644
--- a/libavcodec/qsvdec.c
+++ b/libavcodec/qsvdec.c
@@ -176,13 +176,25 @@ static int alloc_frame(AVCodecContext *avctx, QSVFrame
*frame)
{
int ret;
-ret = ff_get_buffer(avctx, frame->frame, AV_GET_BUFFER_FLAG_REF);
-if (ret < 0)
-return ret;
-
-if (frame->frame->format == AV_PIX_FMT_QSV) {
+if (avctx->pix_fmt == AV_PIX_FMT_QSV) {
+ret = ff_get_buffer(avctx, frame->frame, AV_GET_BUFFER_FLAG_REF);
+if (ret < 0)
+return ret;
frame->surface = (mfxFrameSurface1*)frame->frame->data[3];
} else {
+/*
+ * Align frame's width x height to 128x64.
+ * It's recommended to do so if GPU_Copy is turned on.
+ */
+frame->frame->format = avctx->pix_fmt;
+frame->frame->width = FFALIGN(avctx->width, 128);
+frame->frame->height = FFALIGN(avctx->height, 64);
+ret = av_frame_get_buffer(frame->frame, 64);
+if (ret < 0)
+return ret;
+frame->frame->width = avctx->width;
+frame->frame->height = avctx->height;
+
frame->surface_internal.Info.BitDepthLuma = 8;
frame->surface_internal.Info.BitDepthChroma = 8;
frame->surface_internal.Info.FourCC = MFX_FOURCC_NV12;
diff --git a/libavcodec/qsvdec_h2645.c b/libavcodec/qsvdec_h2645.c
index 208302b..a4adc10 100755
--- a/libavcodec/qsvdec_h2645.c
+++ b/libavcodec/qsvdec_h2645.c
@@ -248,6 +248,12 @@ static const AVOption hevc_options[] = {
{ "load_plugins", "A :-separate list of hexadecimal plugin UIDs to load in
an internal session",
OFFSET(qsv.load_plugins), AV_OPT_TYPE_STRING, { .str = "" }, 0, 0, VD
},
+
+{ "gpu_copy", "Enable gpu copy in sysmem mode [default = off]",
OFFSET(qsv.internal_qs.gpu_copy), AV_OPT_TYPE_INT, { .i64 = MFX_GPUCOPY_OFF },
MFX_GPUCOPY_DEFAULT, MFX_GPUCOPY_OFF, .flags = VD, "gpu_copy" },
+{ "default", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = MFX_GPUCOPY_DEFAULT },
0, 0, .flags = VD, "gpu_copy" },
+{ "on", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = MFX_GPUCOPY_ON },
0, 0, .flags = VD, "gpu_copy" },
+{ "off", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = MFX_GPUCOPY_OFF },
0, 0, .flags = VD, "gpu_copy" },
+
{ NULL },
};
@@ -286,6 +292,12 @@ AVHWAccel ff_h264_qsv_hwaccel = {
static const AVOption options[] = {
{ "async_depth", "Internal parallelization depth, the higher the value the
higher the latency.", OFFSET(qsv.async_depth), AV_OPT_TYPE_INT, { .i64 =
ASYNC_DEPTH_DEFAULT }, 0, INT_MAX, VD },
+
+{ "gpu_copy", "Enable gpu copy in sysmem mode [default = off]",
OFFSET(qsv.internal_qs.gpu_copy), AV_OPT_TYPE_INT, { .i64 = MFX_GPUCOPY_OFF },
MFX_GPUCOPY_DEFAULT, MFX_GPUCOPY_OFF, .flags = VD, "gpu_copy" },
+{ "default", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = MFX_GPUCOPY_DEFAULT },
0, 0, .flags = VD, "gpu_copy" },
+{ "on", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = MFX_GPUCOPY_ON },
0, 0, .flags = VD, "gpu_copy" },
+{ "off", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = MFX_GPUCOPY_OFF },
0, 0, .flags = VD, "gpu_copy" },
+
{ NULL },
};
diff --git a/libavcodec/qsvdec_mpeg2.c b/libavcodec/qsvdec_mpeg2.c
index 70ccbc5..5e2354a 100644
--- a/libavcodec/qsvdec_mpeg2.c
+++ b/libavcodec/qsvdec_mpeg2.c
@@ -72,6 +72,12 @@ AVHWAccel ff_mpeg2_qsv_hwaccel = {
#define VD AV_OPT_FLAG_VIDEO_PARAM | AV_OPT_FLAG_DECODING_PARAM
static const AVOptio
[FFmpeg-devel] [PATCH 6/6] lavc/qsv-lavc/vpp: Promote gpu_copy to be a selectable parameter. GPU-copy is defaultly closed because it seems to be unstable.
From: ChaoX A Liu
Signed-off-by: ChaoX A Liu
---
libavcodec/qsv.c | 7 ++-
libavcodec/qsv_internal.h | 1 +
libavcodec/qsvdec.c | 22 +-
libavcodec/qsvdec_h2645.c | 12
libavcodec/qsvdec_mpeg2.c | 6 ++
libavcodec/qsvdec_vc1.c | 6 ++
libavcodec/qsvenc.h | 4
libavfilter/vf_vpp.c | 8 +++-
8 files changed, 59 insertions(+), 7 deletions(-)
diff --git a/libavcodec/qsv.c b/libavcodec/qsv.c
index c180ca8..c61a29c 100644
--- a/libavcodec/qsv.c
+++ b/libavcodec/qsv.c
@@ -172,11 +172,16 @@ int ff_qsv_init_internal_session(void *avctx, QSVSession
*qs)
{
mfxIMPL impl = MFX_IMPL_AUTO_ANY;
mfxVersion ver = { { QSV_VERSION_MINOR, QSV_VERSION_MAJOR } };
+mfxInitParam par;
const char *desc;
int ret;
-ret = MFXInit(impl, &ver, &qs->session);
+memset(&par, 0, sizeof(par));
+par.Implementation = impl;
+par.Version = ver;
+par.GPUCopy = qs->gpu_copy;
+ret = MFXInitEx(par, &qs->session);
if (ret < 0) {
av_log(avctx, AV_LOG_ERROR, "Error initializing an internal MFX
session\n");
return ff_qsv_error(ret);
diff --git a/libavcodec/qsv_internal.h b/libavcodec/qsv_internal.h
index 58589df..39778a9 100644
--- a/libavcodec/qsv_internal.h
+++ b/libavcodec/qsv_internal.h
@@ -73,6 +73,7 @@ typedef struct QSVSession {
intfd_display;
VADisplay va_display;
#endif
+intgpu_copy;
} QSVSession;
/**
diff --git a/libavcodec/qsvdec.c b/libavcodec/qsvdec.c
index 2075a23..08a5eaa 100644
--- a/libavcodec/qsvdec.c
+++ b/libavcodec/qsvdec.c
@@ -176,13 +176,25 @@ static int alloc_frame(AVCodecContext *avctx, QSVFrame
*frame)
{
int ret;
-ret = ff_get_buffer(avctx, frame->frame, AV_GET_BUFFER_FLAG_REF);
-if (ret < 0)
-return ret;
-
-if (frame->frame->format == AV_PIX_FMT_QSV) {
+if (avctx->pix_fmt == AV_PIX_FMT_QSV) {
+ret = ff_get_buffer(avctx, frame->frame, AV_GET_BUFFER_FLAG_REF);
+if (ret < 0)
+return ret;
frame->surface = (mfxFrameSurface1*)frame->frame->data[3];
} else {
+/*
+ * Align frame's width x height to 128x64.
+ * It's recommended to do so if GPU_Copy is turned on.
+ */
+frame->frame->format = avctx->pix_fmt;
+frame->frame->width = FFALIGN(avctx->width, 128);
+frame->frame->height = FFALIGN(avctx->height, 64);
+ret = av_frame_get_buffer(frame->frame, 64);
+if (ret < 0)
+return ret;
+frame->frame->width = avctx->width;
+frame->frame->height = avctx->height;
+
frame->surface_internal.Info.BitDepthLuma = 8;
frame->surface_internal.Info.BitDepthChroma = 8;
frame->surface_internal.Info.FourCC = MFX_FOURCC_NV12;
diff --git a/libavcodec/qsvdec_h2645.c b/libavcodec/qsvdec_h2645.c
index 208302b..a4adc10 100755
--- a/libavcodec/qsvdec_h2645.c
+++ b/libavcodec/qsvdec_h2645.c
@@ -248,6 +248,12 @@ static const AVOption hevc_options[] = {
{ "load_plugins", "A :-separate list of hexadecimal plugin UIDs to load in
an internal session",
OFFSET(qsv.load_plugins), AV_OPT_TYPE_STRING, { .str = "" }, 0, 0, VD
},
+
+{ "gpu_copy", "Enable gpu copy in sysmem mode [default = off]",
OFFSET(qsv.internal_qs.gpu_copy), AV_OPT_TYPE_INT, { .i64 = MFX_GPUCOPY_OFF },
MFX_GPUCOPY_DEFAULT, MFX_GPUCOPY_OFF, .flags = VD, "gpu_copy" },
+{ "default", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = MFX_GPUCOPY_DEFAULT },
0, 0, .flags = VD, "gpu_copy" },
+{ "on", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = MFX_GPUCOPY_ON },
0, 0, .flags = VD, "gpu_copy" },
+{ "off", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = MFX_GPUCOPY_OFF },
0, 0, .flags = VD, "gpu_copy" },
+
{ NULL },
};
@@ -286,6 +292,12 @@ AVHWAccel ff_h264_qsv_hwaccel = {
static const AVOption options[] = {
{ "async_depth", "Internal parallelization depth, the higher the value the
higher the latency.", OFFSET(qsv.async_depth), AV_OPT_TYPE_INT, { .i64 =
ASYNC_DEPTH_DEFAULT }, 0, INT_MAX, VD },
+
+{ "gpu_copy", "Enable gpu copy in sysmem mode [default = off]",
OFFSET(qsv.internal_qs.gpu_copy), AV_OPT_TYPE_INT, { .i64 = MFX_GPUCOPY_OFF },
MFX_GPUCOPY_DEFAULT, MFX_GPUCOPY_OFF, .flags = VD, "gpu_copy" },
+{ "default", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = MFX_GPUCOPY_DEFAULT },
0, 0, .flags = VD, "gpu_copy" },
+{ "on", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = MFX_GPUCOPY_ON },
0, 0, .flags = VD, "gpu_copy" },
+{ "off", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = MFX_GPUCOPY_OFF },
0, 0, .flags = VD, "gpu_copy" },
+
{ NULL },
};
diff --git a/libavcodec/qsvdec_mpeg2.c b/libavcodec/qsvdec_mpeg2.c
index 70ccbc5..5e2354a 100644
--- a/libavcodec/qsvdec_mpeg2.c
+++ b/libavcodec/qsvdec_mpeg2.c
@@ -72,6 +72,12 @@ AVHWAccel ff_mpeg2_qsv_hwaccel = {
#define VD AV_OPT_FLAG_VIDEO_PARAM | AV_OPT_FLAG_DECODING_PARAM
static const AVOptio
