Hi, I took the time to investigate it and I find a few bugs which I'm
attaching a patch for them.
Yet I'm not convinced that it is a definitive fix, since the output of
swscale-test differs in some cases when scaling the whole frame or in
slices.
Also there is a few fixes needed in this patch which took me a while to
figure out because I blindly trusted the patch was correct.
2016-06-05 9:27 GMT-03:00 Michael Niedermayer <mich...@niedermayer.cc>:
> + src_tmp[0] += srcStride[0] * i * STEP;
>
here it should be:
src_tmp[0] += srcStride[0] * i;
+ if (src_tmp[2]) {
> + int step = STEP >> desc_src->log2_chroma_h;
>
+ src_tmp[1] += srcStride[1] * i * step;
> + src_tmp[2] += srcStride[2] * i * step;
> + }
> + if (src_tmp[3])
> + src_tmp[3] += srcStride[3] * i * STEP;
>
The same applies for the above code.
Regards,
Pedro.
From d0b51102b77e9a883b7b821ecd691ed36cb175ba Mon Sep 17 00:00:00 2001
From: Pedro Arthur <bygran...@gmail.com>
Date: Wed, 8 Jun 2016 21:36:16 -0300
Subject: [PATCH 1/2] swscale: fix crash with swscale-test when using slices
---
libswscale/swscale_unscaled.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/libswscale/swscale_unscaled.c b/libswscale/swscale_unscaled.c
index 4d6cfd1..b231abe 100644
--- a/libswscale/swscale_unscaled.c
+++ b/libswscale/swscale_unscaled.c
@@ -575,7 +575,7 @@ static int Rgb16ToPlanarRgb16Wrapper(SwsContext *c, const uint8_t *src[],
case AV_PIX_FMT_RGB48BE:
case AV_PIX_FMT_RGBA64LE:
case AV_PIX_FMT_RGBA64BE:
- packed16togbra16(src[0] + srcSliceY * srcStride[0], srcStride[0],
+ packed16togbra16(src[0], srcStride[0],
dst2013, stride2013, srcSliceH, alpha, swap,
16 - bpc, c->srcW);
break;
@@ -583,7 +583,7 @@ static int Rgb16ToPlanarRgb16Wrapper(SwsContext *c, const uint8_t *src[],
case AV_PIX_FMT_BGR48BE:
case AV_PIX_FMT_BGRA64LE:
case AV_PIX_FMT_BGRA64BE:
- packed16togbra16(src[0] + srcSliceY * srcStride[0], srcStride[0],
+ packed16togbra16(src[0], srcStride[0],
dst1023, stride1023, srcSliceH, alpha, swap,
16 - bpc, c->srcW);
break;
--
1.9.1
From c45a3d6dca86fbf2b622dbbb9f0562de43abab5a Mon Sep 17 00:00:00 2001
From: Pedro Arthur <bygran...@gmail.com>
Date: Wed, 8 Jun 2016 21:38:49 -0300
Subject: [PATCH 2/2] swscale: fix ring buffer size when scaling slices of a
frame
The ring buffer size should be able to store input lines
when there is not enough lines to output a single line.
---
libswscale/slice.c | 47 +++++++++++++++++++++++++++++++++++++++++++++--
libswscale/swscale.c | 10 ++++++----
2 files changed, 51 insertions(+), 6 deletions(-)
diff --git a/libswscale/slice.c b/libswscale/slice.c
index 0159a73..3da4136 100644
--- a/libswscale/slice.c
+++ b/libswscale/slice.c
@@ -210,6 +210,42 @@ static void fill_ones(SwsSlice *s, int n, int is16bit)
}
}
+/*
+ Calculates the minimum ring buffer size, it should be able to store vFilterSize
+ more n lines where n is the max difference between each adjacent slice which
+ outputs a line.
+ The n lines are needed only when there is not enough src lines to output a single
+ dst line, then we should buffer these lines to process them on the next call to scale.
+*/
+static void get_min_buffer_size(SwsContext *c, int *out_lum_size, int *out_chr_size)
+{
+ int lumY;
+ int dstH = c->dstH;
+ int chrDstH = c->chrDstH;
+ int *lumFilterPos = c->vLumFilterPos;
+ int *chrFilterPos = c->vChrFilterPos;
+ int lumFilterSize = c->vLumFilterSize;
+ int chrFilterSize = c->vChrFilterSize;
+ int chrSubSample = c->chrSrcVSubSample;
+
+ *out_lum_size = lumFilterSize;
+ *out_chr_size = chrFilterSize;
+
+ for (lumY = 0; lumY < dstH; lumY++) {
+ int chrY = (int64_t)lumY * chrDstH / dstH;
+ int nextSlice = FFMAX(lumFilterPos[lumY] + lumFilterSize - 1,
+ ((chrFilterPos[chrY] + chrFilterSize - 1)
+ << chrSubSample));
+
+ nextSlice >>= chrSubSample;
+ nextSlice <<= chrSubSample;
+ (*out_lum_size) = FFMAX((*out_lum_size), nextSlice - lumFilterPos[lumY]);
+ (*out_chr_size) = FFMAX((*out_chr_size), (nextSlice >> chrSubSample) - chrFilterPos[chrY]);
+ }
+}
+
+
+
int ff_init_filters(SwsContext * c)
{
int i;
@@ -226,6 +262,13 @@ int ff_init_filters(SwsContext * c)
uint32_t * pal = usePal(c->srcFormat) ? c->pal_yuv : (uint32_t*)c->input_rgb2yuv_table;
int res = 0;
+ int lumBufSize;
+ int chrBufSize;
+
+ get_min_buffer_size(c, &lumBufSize, &chrBufSize);
+ lumBufSize = FFMAX(lumBufSize, c->vLumFilterSize + MAX_LINES_AHEAD);
+ chrBufSize = FFMAX(chrBufSize, c->vChrFilterSize + MAX_LINES_AHEAD);
+
if (c->dstBpc == 16)
dst_stride <<= 1;
@@ -248,13 +291,13 @@ int ff_init_filters(SwsContext * c)
res = alloc_slice(&c->slice[0], c->srcFormat, c->srcH, c->chrSrcH, c->chrSrcHSubSample, c->chrSrcVSubSample, 0);
if (res < 0) goto cleanup;
for (i = 1; i < c->numSlice-2; ++i) {
- res = alloc_slice(&c->slice[i], c->srcFormat, c->vLumFilterSize + MAX_LINES_AHEAD, c->vChrFilterSize + MAX_LINES_AHEAD, c->chrSrcHSubSample, c->chrSrcVSubSample, 0);
+ res = alloc_slice(&c->slice[i], c->srcFormat, lumBufSize, chrBufSize, c->chrSrcHSubSample, c->chrSrcVSubSample, 0);
if (res < 0) goto cleanup;
res = alloc_lines(&c->slice[i], FFALIGN(c->srcW*2+78, 16), c->srcW);
if (res < 0) goto cleanup;
}
// horizontal scaler output
- res = alloc_slice(&c->slice[i], c->srcFormat, c->vLumFilterSize + MAX_LINES_AHEAD, c->vChrFilterSize + MAX_LINES_AHEAD, c->chrDstHSubSample, c->chrDstVSubSample, 1);
+ res = alloc_slice(&c->slice[i], c->srcFormat, lumBufSize, chrBufSize, c->chrDstHSubSample, c->chrDstVSubSample, 1);
if (res < 0) goto cleanup;
res = alloc_lines(&c->slice[i], dst_stride, c->dstW);
if (res < 0) goto cleanup;
diff --git a/libswscale/swscale.c b/libswscale/swscale.c
index 2e246d9..bbea0fe 100644
--- a/libswscale/swscale.c
+++ b/libswscale/swscale.c
@@ -413,8 +413,6 @@ static int swscale(SwsContext *c, const uint8_t *src[],
lastInChrBuf = firstChrSrcY - 1;
}
- av_assert0(firstLumSrcY >= lastInLumBuf - vLumFilterSize + 1);
- av_assert0(firstChrSrcY >= lastInChrBuf - vChrFilterSize + 1);
DEBUG_BUFFERS("dstY: %d\n", dstY);
DEBUG_BUFFERS("\tfirstLumSrcY: %d lastLumSrcY: %d lastInLumBuf: %d\n",
@@ -433,10 +431,14 @@ static int swscale(SwsContext *c, const uint8_t *src[],
lastLumSrcY, lastChrSrcY);
}
+ av_assert0((lastLumSrcY - firstLumSrcY + 1) <= hout_slice->plane[0].available_lines);
+ av_assert0((lastChrSrcY - firstChrSrcY + 1) <= hout_slice->plane[1].available_lines);
+
+
posY = hout_slice->plane[0].sliceY + hout_slice->plane[0].sliceH;
if (posY <= lastLumSrcY && !hasLumHoles) {
firstPosY = FFMAX(firstLumSrcY, posY);
- lastPosY = FFMIN(lastLumSrcY + MAX_LINES_AHEAD, srcSliceY + srcSliceH - 1);
+ lastPosY = FFMIN(firstLumSrcY + hout_slice->plane[0].available_lines - 1, srcSliceY + srcSliceH - 1);
} else {
firstPosY = lastInLumBuf + 1;
lastPosY = lastLumSrcY;
@@ -445,7 +447,7 @@ static int swscale(SwsContext *c, const uint8_t *src[],
cPosY = hout_slice->plane[1].sliceY + hout_slice->plane[1].sliceH;
if (cPosY <= lastChrSrcY && !hasChrHoles) {
firstCPosY = FFMAX(firstChrSrcY, cPosY);
- lastCPosY = FFMIN(lastChrSrcY + MAX_LINES_AHEAD, AV_CEIL_RSHIFT(srcSliceY + srcSliceH, c->chrSrcVSubSample) - 1);
+ lastCPosY = FFMIN(firstChrSrcY + hout_slice->plane[1].available_lines - 1, AV_CEIL_RSHIFT(srcSliceY + srcSliceH, c->chrSrcVSubSample) - 1);
} else {
firstCPosY = lastInChrBuf + 1;
lastCPosY = lastChrSrcY;
--
1.9.1
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
