* Copyright (C) 2012 Daniel Kang
* Copyright (C) 2014 Peter Ross
*
- * This file is part of Libav.
+ * This file is part of FFmpeg.
*
- * Libav is free software; you can redistribute it and/or
+ * FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
- * Libav is distributed in the hope that it will be useful,
+ * FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
- * License along with Libav; if not, write to the Free Software
+ * License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
# include "arm/vp8.h"
#endif
+#if CONFIG_VP7_DECODER && CONFIG_VP8_DECODER
+#define VPX(vp7, f) (vp7 ? vp7_ ## f : vp8_ ## f)
+#elif CONFIG_VP7_DECODER
+#define VPX(vp7, f) vp7_ ## f
+#else // CONFIG_VP8_DECODER
+#define VPX(vp7, f) vp8_ ## f
+#endif
+
static void free_buffers(VP8Context *s)
{
int i;
return frame;
}
+static enum AVPixelFormat get_pixel_format(VP8Context *s)
+{
+ enum AVPixelFormat pix_fmts[] = {
+#if CONFIG_VP8_VAAPI_HWACCEL
+ AV_PIX_FMT_VAAPI,
+#endif
+#if CONFIG_VP8_NVDEC_HWACCEL
+ AV_PIX_FMT_CUDA,
+#endif
+ AV_PIX_FMT_YUV420P,
+ AV_PIX_FMT_NONE,
+ };
+
+ return ff_get_format(s->avctx, pix_fmts);
+}
+
static av_always_inline
int update_dimensions(VP8Context *s, int width, int height, int is_vp7)
{
AVCodecContext *avctx = s->avctx;
int i, ret;
- if (width != s->avctx->width ||
+ if (width != s->avctx->width || ((width+15)/16 != s->mb_width || (height+15)/16 != s->mb_height) && s->macroblocks_base ||
height != s->avctx->height) {
vp8_decode_flush_impl(s->avctx, 1);
return ret;
}
+ if (!s->actually_webp && !is_vp7) {
+ s->pix_fmt = get_pixel_format(s);
+ if (s->pix_fmt < 0)
+ return AVERROR(EINVAL);
+ avctx->pix_fmt = s->pix_fmt;
+ }
+
s->mb_width = (s->avctx->coded_width + 15) / 16;
s->mb_height = (s->avctx->coded_height + 15) / 16;
s->mb_layout = is_vp7 || avctx->active_thread_type == FF_THREAD_SLICE &&
- FFMIN(s->num_coeff_partitions, avctx->thread_count) > 1;
+ avctx->thread_count > 1;
if (!s->mb_layout) { // Frame threading and one thread
s->macroblocks_base = av_mallocz((s->mb_width + s->mb_height * 2 + 1) *
sizeof(*s->macroblocks));
return update_dimensions(s, width, height, IS_VP8);
}
+
static void parse_segment_info(VP8Context *s)
{
VP56RangeCoder *c = &s->c;
{
const uint8_t *sizes = buf;
int i;
+ int ret;
s->num_coeff_partitions = 1 << vp8_rac_get_uint(&s->c, 2);
return -1;
s->coeff_partition_size[i] = size;
- ff_vp56_init_range_decoder(&s->coeff_partition[i], buf, size);
+ ret = ff_vp56_init_range_decoder(&s->coeff_partition[i], buf, size);
+ if (ret < 0)
+ return ret;
buf += size;
buf_size -= size;
}
s->qmat[0].chroma_qmul[1] = vp7_yac_qlookup[uvac_qi];
}
-static void get_quants(VP8Context *s)
+static void vp8_get_quants(VP8Context *s)
{
VP56RangeCoder *c = &s->c;
int i, base_qi;
s->update_altref = ref_to_update(s, update_altref, VP56_FRAME_GOLDEN2);
}
-static void copy_luma(AVFrame *dst, AVFrame *src, int width, int height)
+static void copy_chroma(AVFrame *dst, AVFrame *src, int width, int height)
{
int i, j;
}
}
-static void fade(uint8_t *dst, uint8_t *src,
- int width, int height, ptrdiff_t linesize,
+static void fade(uint8_t *dst, ptrdiff_t dst_linesize,
+ const uint8_t *src, ptrdiff_t src_linesize,
+ int width, int height,
int alpha, int beta)
{
int i, j;
-
for (j = 0; j < height; j++) {
for (i = 0; i < width; i++) {
- uint8_t y = src[j * linesize + i];
- dst[j * linesize + i] = av_clip_uint8(y + ((y * beta) >> 8) + alpha);
+ uint8_t y = src[j * src_linesize + i];
+ dst[j * dst_linesize + i] = av_clip_uint8(y + ((y * beta) >> 8) + alpha);
}
}
}
int height = s->mb_height * 16;
AVFrame *src, *dst;
- if (!s->framep[VP56_FRAME_PREVIOUS])
+ if (!s->framep[VP56_FRAME_PREVIOUS] ||
+ !s->framep[VP56_FRAME_GOLDEN]) {
+ av_log(s->avctx, AV_LOG_WARNING, "Discarding interframe without a prior keyframe!\n");
return AVERROR_INVALIDDATA;
+ }
dst =
src = s->framep[VP56_FRAME_PREVIOUS]->tf.f;
if (s->framep[VP56_FRAME_GOLDEN] == s->framep[VP56_FRAME_PREVIOUS]) {
s->framep[VP56_FRAME_PREVIOUS] = vp8_find_free_buffer(s);
if ((ret = vp8_alloc_frame(s, s->framep[VP56_FRAME_PREVIOUS], 1)) < 0)
- return ret;
+ return ret;
dst = s->framep[VP56_FRAME_PREVIOUS]->tf.f;
- copy_luma(dst, src, width, height);
+ copy_chroma(dst, src, width, height);
}
- fade(dst->data[0], src->data[0],
- width, height, dst->linesize[0], alpha, beta);
+ fade(dst->data[0], dst->linesize[0],
+ src->data[0], src->linesize[0],
+ width, height, alpha, beta);
}
return 0;
s->invisible = 0;
part1_size = AV_RL24(buf) >> 4;
- buf += 4 - s->profile;
- buf_size -= 4 - s->profile;
-
- if (buf_size < part1_size) {
+ if (buf_size < 4 - s->profile + part1_size) {
+ av_log(s->avctx, AV_LOG_ERROR, "Buffer size %d is too small, needed : %d\n", buf_size, 4 - s->profile + part1_size);
return AVERROR_INVALIDDATA;
}
+ buf += 4 - s->profile;
+ buf_size -= 4 - s->profile;
+
memcpy(s->put_pixels_tab, s->vp8dsp.put_vp8_epel_pixels_tab, sizeof(s->put_pixels_tab));
- ff_vp56_init_range_decoder(c, buf, part1_size);
+ ret = ff_vp56_init_range_decoder(c, buf, part1_size);
+ if (ret < 0)
+ return ret;
buf += part1_size;
buf_size -= part1_size;
if (vp7_feature_value_size[s->profile][i])
for (j = 0; j < 4; j++)
s->feature_value[i][j] =
- vp8_rac_get(c) ? vp8_rac_get_uint(c, vp7_feature_value_size[s->profile][i]) : 0;
+ vp8_rac_get(c) ? vp8_rac_get_uint(c, vp7_feature_value_size[s->profile][i]) : 0;
}
}
s->lf_delta.enabled = 0;
s->num_coeff_partitions = 1;
- ff_vp56_init_range_decoder(&s->coeff_partition[0], buf, buf_size);
+ ret = ff_vp56_init_range_decoder(&s->coeff_partition[0], buf, buf_size);
+ if (ret < 0)
+ return ret;
if (!s->macroblocks_base || /* first frame */
width != s->avctx->width || height != s->avctx->height ||
int width = s->avctx->width;
int height = s->avctx->height;
+ if (buf_size < 3) {
+ av_log(s->avctx, AV_LOG_ERROR, "Insufficent data (%d) for header\n", buf_size);
+ return AVERROR_INVALIDDATA;
+ }
+
s->keyframe = !(buf[0] & 1);
s->profile = (buf[0]>>1) & 7;
s->invisible = !(buf[0] & 0x10);
memset(&s->lf_delta, 0, sizeof(s->lf_delta));
}
- ff_vp56_init_range_decoder(c, buf, header_size);
+ ret = ff_vp56_init_range_decoder(c, buf, header_size);
+ if (ret < 0)
+ return ret;
buf += header_size;
buf_size -= header_size;
}
if (!s->macroblocks_base || /* first frame */
- width != s->avctx->width || height != s->avctx->height)
+ width != s->avctx->width || height != s->avctx->height ||
+ (width+15)/16 != s->mb_width || (height+15)/16 != s->mb_height)
if ((ret = vp8_update_dimensions(s, width, height)) < 0)
return ret;
- get_quants(s);
+ vp8_get_quants(s);
if (!s->keyframe) {
update_refs(s);
}
static av_always_inline
-void clamp_mv(VP8Context *s, VP56mv *dst, const VP56mv *src)
+void clamp_mv(VP8mvbounds *s, VP56mv *dst, const VP56mv *src)
{
- dst->x = av_clip(src->x, s->mv_min.x, s->mv_max.x);
- dst->y = av_clip(src->y, s->mv_min.y, s->mv_max.y);
+ dst->x = av_clip(src->x, av_clip(s->mv_min.x, INT16_MIN, INT16_MAX),
+ av_clip(s->mv_max.x, INT16_MIN, INT16_MAX));
+ dst->y = av_clip(src->y, av_clip(s->mv_min.y, INT16_MIN, INT16_MAX),
+ av_clip(s->mv_max.y, INT16_MIN, INT16_MAX));
}
/**
* Motion vector coding, 17.1.
*/
-static int read_mv_component(VP56RangeCoder *c, const uint8_t *p, int vp7)
+static av_always_inline int read_mv_component(VP56RangeCoder *c, const uint8_t *p, int vp7)
{
int bit, x = 0;
return (x && vp56_rac_get_prob(c, p[1])) ? -x : x;
}
+static int vp7_read_mv_component(VP56RangeCoder *c, const uint8_t *p)
+{
+ return read_mv_component(c, p, 1);
+}
+
+static int vp8_read_mv_component(VP56RangeCoder *c, const uint8_t *p)
+{
+ return read_mv_component(c, p, 0);
+}
+
static av_always_inline
const uint8_t *get_submv_prob(uint32_t left, uint32_t top, int is_vp7)
{
mb->mode = VP8_MVMODE_SPLIT;
mb->mv = mb->bmv[decode_splitmvs(s, c, mb, layout, IS_VP7) - 1];
} else {
- mb->mv.y += read_mv_component(c, s->prob->mvc[0], IS_VP7);
- mb->mv.x += read_mv_component(c, s->prob->mvc[1], IS_VP7);
+ mb->mv.y += vp7_read_mv_component(c, s->prob->mvc[0]);
+ mb->mv.x += vp7_read_mv_component(c, s->prob->mvc[1]);
mb->bmv[0] = mb->mv;
}
} else {
}
static av_always_inline
-void vp8_decode_mvs(VP8Context *s, VP8Macroblock *mb,
+void vp8_decode_mvs(VP8Context *s, VP8mvbounds *mv_bounds, VP8Macroblock *mb,
int mb_x, int mb_y, int layout)
{
VP8Macroblock *mb_edge[3] = { 0 /* top */,
if (vp56_rac_get_prob_branchy(c, vp8_mode_contexts[cnt[CNT_NEAREST]][1])) {
if (vp56_rac_get_prob_branchy(c, vp8_mode_contexts[cnt[CNT_NEAR]][2])) {
/* Choose the best mv out of 0,0 and the nearest mv */
- clamp_mv(s, &mb->mv, &near_mv[CNT_ZERO + (cnt[CNT_NEAREST] >= cnt[CNT_ZERO])]);
+ clamp_mv(mv_bounds, &mb->mv, &near_mv[CNT_ZERO + (cnt[CNT_NEAREST] >= cnt[CNT_ZERO])]);
cnt[CNT_SPLITMV] = ((mb_edge[VP8_EDGE_LEFT]->mode == VP8_MVMODE_SPLIT) +
(mb_edge[VP8_EDGE_TOP]->mode == VP8_MVMODE_SPLIT)) * 2 +
(mb_edge[VP8_EDGE_TOPLEFT]->mode == VP8_MVMODE_SPLIT);
mb->mode = VP8_MVMODE_SPLIT;
mb->mv = mb->bmv[decode_splitmvs(s, c, mb, layout, IS_VP8) - 1];
} else {
- mb->mv.y += read_mv_component(c, s->prob->mvc[0], IS_VP8);
- mb->mv.x += read_mv_component(c, s->prob->mvc[1], IS_VP8);
+ mb->mv.y += vp8_read_mv_component(c, s->prob->mvc[0]);
+ mb->mv.x += vp8_read_mv_component(c, s->prob->mvc[1]);
mb->bmv[0] = mb->mv;
}
} else {
- clamp_mv(s, &mb->mv, &near_mv[CNT_NEAR]);
+ clamp_mv(mv_bounds, &mb->mv, &near_mv[CNT_NEAR]);
mb->bmv[0] = mb->mv;
}
} else {
- clamp_mv(s, &mb->mv, &near_mv[CNT_NEAREST]);
+ clamp_mv(mv_bounds, &mb->mv, &near_mv[CNT_NEAREST]);
mb->bmv[0] = mb->mv;
}
} else {
{
uint8_t *intra4x4 = mb->intra4x4_pred_mode_mb;
- if (layout == 1) {
+ if (layout) {
VP8Macroblock *mb_top = mb - s->mb_width - 1;
memcpy(mb->intra4x4_pred_mode_top, mb_top->intra4x4_pred_mode_top, 4);
}
int x, y;
uint8_t *top;
uint8_t *const left = s->intra4x4_pred_mode_left;
- if (layout == 1)
+ if (layout)
top = mb->intra4x4_pred_mode_top;
else
top = s->intra4x4_pred_mode_top + 4 * mb_x;
}
static av_always_inline
-void decode_mb_mode(VP8Context *s, VP8Macroblock *mb, int mb_x, int mb_y,
+void decode_mb_mode(VP8Context *s, VP8mvbounds *mv_bounds,
+ VP8Macroblock *mb, int mb_x, int mb_y,
uint8_t *segment, uint8_t *ref, int layout, int is_vp7)
{
VP56RangeCoder *c = &s->c;
*segment = 0;
for (i = 0; i < 4; i++) {
if (s->feature_enabled[i]) {
- if (vp56_rac_get_prob(c, s->feature_present_prob[i])) {
+ if (vp56_rac_get_prob_branchy(c, s->feature_present_prob[i])) {
int index = vp8_rac_get_tree(c, vp7_feature_index_tree,
s->feature_index_prob[i]);
av_log(s->avctx, AV_LOG_WARNING,
}
}
}
- } else if (s->segmentation.update_map)
- *segment = vp8_rac_get_tree(c, vp8_segmentid_tree, s->prob->segmentid);
- else if (s->segmentation.enabled)
+ } else if (s->segmentation.update_map) {
+ int bit = vp56_rac_get_prob(c, s->prob->segmentid[0]);
+ *segment = vp56_rac_get_prob(c, s->prob->segmentid[1+bit]) + 2*bit;
+ } else if (s->segmentation.enabled)
*segment = ref ? *ref : *segment;
mb->segment = *segment;
} else {
const uint32_t modes = (is_vp7 ? vp7_pred4x4_mode
: vp8_pred4x4_mode)[mb->mode] * 0x01010101u;
- if (s->mb_layout == 1)
+ if (s->mb_layout)
AV_WN32A(mb->intra4x4_pred_mode_top, modes);
else
AV_WN32A(s->intra4x4_pred_mode_top + 4 * mb_x, modes);
if (is_vp7)
vp7_decode_mvs(s, mb, mb_x, mb_y, layout);
else
- vp8_decode_mvs(s, mb, mb_x, mb_y, layout);
+ vp8_decode_mvs(s, mv_bounds, mb, mb_x, mb_y, layout);
} else {
// intra MB, 16.1
mb->mode = vp8_rac_get_tree(c, vp8_pred16x16_tree_inter, s->prob->pred16x16);
* @param zero_nhood the initial prediction context for number of surrounding
* all-zero blocks (only left/top, so 0-2)
* @param qmul array holding the dc/ac dequant factor at position 0/1
+ * @param scan scan pattern (VP7 only)
*
* @return 0 if no coeffs were decoded
* otherwise, the index of the last coeff decoded plus one
int copy = 0;
ptrdiff_t linesize = s->linesize;
uint8_t *dst = ptr + 4 * x;
- DECLARE_ALIGNED(4, uint8_t, copy_dst)[5 * 8];
+ LOCAL_ALIGNED(4, uint8_t, copy_dst, [5 * 8]);
if ((y == 0 || x == 3) && mb_y == 0) {
topright = tr_top;
if (AV_RN32A(mv)) {
ptrdiff_t src_linesize = linesize;
- int mx = (mv->x << 1) & 7, mx_idx = subpel_idx[0][mx];
- int my = (mv->y << 1) & 7, my_idx = subpel_idx[0][my];
+ int mx = (mv->x * 2) & 7, mx_idx = subpel_idx[0][mx];
+ int my = (mv->y * 2) & 7, my_idx = subpel_idx[0][my];
x_off += mv->x >> 2;
y_off += mv->y >> 2;
s->vdsp.emulated_edge_mc(td->edge_emu_buffer,
src1 - my_idx * linesize - mx_idx,
EDGE_EMU_LINESIZE, linesize,
- block_w + subpel_idx[1][mx], block_h + subpel_idx[1][my],
+ block_w + subpel_idx[1][mx],
+ block_h + subpel_idx[1][my],
x_off - mx_idx, y_off - my_idx, width, height);
src1 = td->edge_emu_buffer + mx_idx + EDGE_EMU_LINESIZE * my_idx;
mc_func[my_idx][mx_idx](dst1, linesize, src1, EDGE_EMU_LINESIZE, block_h, mx, my);
s->vdsp.emulated_edge_mc(td->edge_emu_buffer,
src2 - my_idx * linesize - mx_idx,
EDGE_EMU_LINESIZE, linesize,
- block_w + subpel_idx[1][mx], block_h + subpel_idx[1][my],
+ block_w + subpel_idx[1][mx],
+ block_h + subpel_idx[1][my],
x_off - mx_idx, y_off - my_idx, width, height);
src2 = td->edge_emu_buffer + mx_idx + EDGE_EMU_LINESIZE * my_idx;
mc_func[my_idx][mx_idx](dst2, linesize, src2, EDGE_EMU_LINESIZE, block_h, mx, my);
VP8Context *s = avctx->priv_data;
int mb_x, mb_y;
- s->mv_min.y = -MARGIN;
- s->mv_max.y = ((s->mb_height - 1) << 6) + MARGIN;
+ s->mv_bounds.mv_min.y = -MARGIN;
+ s->mv_bounds.mv_max.y = ((s->mb_height - 1) << 6) + MARGIN;
for (mb_y = 0; mb_y < s->mb_height; mb_y++) {
VP8Macroblock *mb = s->macroblocks_base +
((s->mb_width + 1) * (mb_y + 1) + 1);
AV_WN32A(s->intra4x4_pred_mode_left, DC_PRED * 0x01010101);
- s->mv_min.x = -MARGIN;
- s->mv_max.x = ((s->mb_width - 1) << 6) + MARGIN;
+ s->mv_bounds.mv_min.x = -MARGIN;
+ s->mv_bounds.mv_max.x = ((s->mb_width - 1) << 6) + MARGIN;
for (mb_x = 0; mb_x < s->mb_width; mb_x++, mb_xy++, mb++) {
if (mb_y == 0)
AV_WN32A((mb - s->mb_width - 1)->intra4x4_pred_mode_top,
DC_PRED * 0x01010101);
- decode_mb_mode(s, mb, mb_x, mb_y, curframe->seg_map->data + mb_xy,
+ decode_mb_mode(s, &s->mv_bounds, mb, mb_x, mb_y, curframe->seg_map->data + mb_xy,
prev_frame && prev_frame->seg_map ?
prev_frame->seg_map->data + mb_xy : NULL, 1, is_vp7);
- s->mv_min.x -= 64;
- s->mv_max.x -= 64;
+ s->mv_bounds.mv_min.x -= 64;
+ s->mv_bounds.mv_max.x -= 64;
}
- s->mv_min.y -= 64;
- s->mv_max.y -= 64;
+ s->mv_bounds.mv_min.y -= 64;
+ s->mv_bounds.mv_max.y -= 64;
}
}
#define check_thread_pos(td, otd, mb_x_check, mb_y_check) \
do { \
int tmp = (mb_y_check << 16) | (mb_x_check & 0xFFFF); \
- if (otd->thread_mb_pos < tmp) { \
+ if (atomic_load(&otd->thread_mb_pos) < tmp) { \
pthread_mutex_lock(&otd->lock); \
- td->wait_mb_pos = tmp; \
+ atomic_store(&td->wait_mb_pos, tmp); \
do { \
- if (otd->thread_mb_pos >= tmp) \
+ if (atomic_load(&otd->thread_mb_pos) >= tmp) \
break; \
pthread_cond_wait(&otd->cond, &otd->lock); \
} while (1); \
- td->wait_mb_pos = INT_MAX; \
+ atomic_store(&td->wait_mb_pos, INT_MAX); \
pthread_mutex_unlock(&otd->lock); \
} \
- } while (0);
+ } while (0)
#define update_pos(td, mb_y, mb_x) \
do { \
int sliced_threading = (avctx->active_thread_type == FF_THREAD_SLICE) && \
(num_jobs > 1); \
int is_null = !next_td || !prev_td; \
- int pos_check = (is_null) ? 1 \
- : (next_td != td && \
- pos >= next_td->wait_mb_pos) || \
- (prev_td != td && \
- pos >= prev_td->wait_mb_pos); \
- td->thread_mb_pos = pos; \
+ int pos_check = (is_null) ? 1 : \
+ (next_td != td && pos >= atomic_load(&next_td->wait_mb_pos)) || \
+ (prev_td != td && pos >= atomic_load(&prev_td->wait_mb_pos)); \
+ atomic_store(&td->thread_mb_pos, pos); \
if (sliced_threading && pos_check) { \
pthread_mutex_lock(&td->lock); \
pthread_cond_broadcast(&td->cond); \
pthread_mutex_unlock(&td->lock); \
} \
- } while (0);
+ } while (0)
#else
-#define check_thread_pos(td, otd, mb_x_check, mb_y_check)
-#define update_pos(td, mb_y, mb_x)
+#define check_thread_pos(td, otd, mb_x_check, mb_y_check) while(0)
+#define update_pos(td, mb_y, mb_x) while(0)
#endif
-static void vp8_decode_mb_row_no_filter(AVCodecContext *avctx, void *tdata,
+static av_always_inline int decode_mb_row_no_filter(AVCodecContext *avctx, void *tdata,
int jobnr, int threadnr, int is_vp7)
{
VP8Context *s = avctx->priv_data;
VP8ThreadData *prev_td, *next_td, *td = &s->thread_data[threadnr];
- int mb_y = td->thread_mb_pos >> 16;
+ int mb_y = atomic_load(&td->thread_mb_pos) >> 16;
int mb_x, mb_xy = mb_y * s->mb_width;
int num_jobs = s->num_jobs;
VP8Frame *curframe = s->curframe, *prev_frame = s->prev_frame;
curframe->tf.f->data[1] + 8 * mb_y * s->uvlinesize,
curframe->tf.f->data[2] + 8 * mb_y * s->uvlinesize
};
+
+ if (c->end <= c->buffer && c->bits >= 0)
+ return AVERROR_INVALIDDATA;
+
if (mb_y == 0)
prev_td = td;
else
if (!is_vp7 || mb_y == 0)
memset(td->left_nnz, 0, sizeof(td->left_nnz));
- s->mv_min.x = -MARGIN;
- s->mv_max.x = ((s->mb_width - 1) << 6) + MARGIN;
+ td->mv_bounds.mv_min.x = -MARGIN;
+ td->mv_bounds.mv_max.x = ((s->mb_width - 1) << 6) + MARGIN;
for (mb_x = 0; mb_x < s->mb_width; mb_x++, mb_xy++, mb++) {
+ if (c->end <= c->buffer && c->bits >= 0)
+ return AVERROR_INVALIDDATA;
// Wait for previous thread to read mb_x+2, and reach mb_y-1.
if (prev_td != td) {
if (threadnr != 0) {
dst[2] - dst[1], 2);
if (!s->mb_layout)
- decode_mb_mode(s, mb, mb_x, mb_y, curframe->seg_map->data + mb_xy,
+ decode_mb_mode(s, &td->mv_bounds, mb, mb_x, mb_y, curframe->seg_map->data + mb_xy,
prev_frame && prev_frame->seg_map ?
prev_frame->seg_map->data + mb_xy : NULL, 0, is_vp7);
dst[0] += 16;
dst[1] += 8;
dst[2] += 8;
- s->mv_min.x -= 64;
- s->mv_max.x -= 64;
+ td->mv_bounds.mv_min.x -= 64;
+ td->mv_bounds.mv_max.x -= 64;
if (mb_x == s->mb_width + 1) {
update_pos(td, mb_y, s->mb_width + 3);
update_pos(td, mb_y, mb_x);
}
}
+ return 0;
}
-static void vp8_filter_mb_row(AVCodecContext *avctx, void *tdata,
+static int vp7_decode_mb_row_no_filter(AVCodecContext *avctx, void *tdata,
+ int jobnr, int threadnr)
+{
+ return decode_mb_row_no_filter(avctx, tdata, jobnr, threadnr, 1);
+}
+
+static int vp8_decode_mb_row_no_filter(AVCodecContext *avctx, void *tdata,
+ int jobnr, int threadnr)
+{
+ return decode_mb_row_no_filter(avctx, tdata, jobnr, threadnr, 0);
+}
+
+static av_always_inline void filter_mb_row(AVCodecContext *avctx, void *tdata,
int jobnr, int threadnr, int is_vp7)
{
VP8Context *s = avctx->priv_data;
VP8ThreadData *td = &s->thread_data[threadnr];
- int mb_x, mb_y = td->thread_mb_pos >> 16, num_jobs = s->num_jobs;
+ int mb_x, mb_y = atomic_load(&td->thread_mb_pos) >> 16, num_jobs = s->num_jobs;
AVFrame *curframe = s->curframe->tf.f;
VP8Macroblock *mb;
VP8ThreadData *prev_td, *next_td;
}
}
+static void vp7_filter_mb_row(AVCodecContext *avctx, void *tdata,
+ int jobnr, int threadnr)
+{
+ filter_mb_row(avctx, tdata, jobnr, threadnr, 1);
+}
+
+static void vp8_filter_mb_row(AVCodecContext *avctx, void *tdata,
+ int jobnr, int threadnr)
+{
+ filter_mb_row(avctx, tdata, jobnr, threadnr, 0);
+}
+
static av_always_inline
int vp78_decode_mb_row_sliced(AVCodecContext *avctx, void *tdata, int jobnr,
int threadnr, int is_vp7)
VP8ThreadData *next_td = NULL, *prev_td = NULL;
VP8Frame *curframe = s->curframe;
int mb_y, num_jobs = s->num_jobs;
+ int ret;
td->thread_nr = threadnr;
+ td->mv_bounds.mv_min.y = -MARGIN - 64 * threadnr;
+ td->mv_bounds.mv_max.y = ((s->mb_height - 1) << 6) + MARGIN - 64 * threadnr;
for (mb_y = jobnr; mb_y < s->mb_height; mb_y += num_jobs) {
- if (mb_y >= s->mb_height)
- break;
- td->thread_mb_pos = mb_y << 16;
- vp8_decode_mb_row_no_filter(avctx, tdata, jobnr, threadnr, is_vp7);
+ atomic_store(&td->thread_mb_pos, mb_y << 16);
+ ret = s->decode_mb_row_no_filter(avctx, tdata, jobnr, threadnr);
+ if (ret < 0) {
+ update_pos(td, s->mb_height, INT_MAX & 0xFFFF);
+ return ret;
+ }
if (s->deblock_filter)
- vp8_filter_mb_row(avctx, tdata, jobnr, threadnr, is_vp7);
+ s->filter_mb_row(avctx, tdata, jobnr, threadnr);
update_pos(td, mb_y, INT_MAX & 0xFFFF);
- s->mv_min.y -= 64;
- s->mv_max.y -= 64;
+ td->mv_bounds.mv_min.y -= 64 * num_jobs;
+ td->mv_bounds.mv_max.y -= 64 * num_jobs;
if (avctx->active_thread_type == FF_THREAD_FRAME)
ff_thread_report_progress(&curframe->tf, mb_y, 0);
if (s->actually_webp) {
// avctx->pix_fmt already set in caller.
} else if (!is_vp7 && s->pix_fmt == AV_PIX_FMT_NONE) {
- enum AVPixelFormat pix_fmts[] = {
-#if CONFIG_VP8_VAAPI_HWACCEL
- AV_PIX_FMT_VAAPI,
-#endif
- AV_PIX_FMT_YUV420P,
- AV_PIX_FMT_NONE,
- };
-
- s->pix_fmt = ff_get_format(s->avctx, pix_fmts);
+ s->pix_fmt = get_pixel_format(s);
if (s->pix_fmt < 0) {
ret = AVERROR(EINVAL);
goto err;
// release no longer referenced frames
for (i = 0; i < 5; i++)
- if (s->frames[i].tf.f->data[0] &&
+ if (s->frames[i].tf.f->buf[0] &&
&s->frames[i] != prev_frame &&
&s->frames[i] != s->framep[VP56_FRAME_PREVIOUS] &&
&s->frames[i] != s->framep[VP56_FRAME_GOLDEN] &&
curframe->tf.f->key_frame = s->keyframe;
curframe->tf.f->pict_type = s->keyframe ? AV_PICTURE_TYPE_I
: AV_PICTURE_TYPE_P;
- if ((ret = vp8_alloc_frame(s, curframe, referenced))) {
- av_log(avctx, AV_LOG_ERROR, "get_buffer() failed!\n");
+ if ((ret = vp8_alloc_frame(s, curframe, referenced)) < 0)
goto err;
- }
// check if golden and altref are swapped
if (s->update_altref != VP56_FRAME_NONE)
s->num_jobs = num_jobs;
s->curframe = curframe;
s->prev_frame = prev_frame;
- s->mv_min.y = -MARGIN;
- s->mv_max.y = ((s->mb_height - 1) << 6) + MARGIN;
+ s->mv_bounds.mv_min.y = -MARGIN;
+ s->mv_bounds.mv_max.y = ((s->mb_height - 1) << 6) + MARGIN;
for (i = 0; i < MAX_THREADS; i++) {
- s->thread_data[i].thread_mb_pos = 0;
- s->thread_data[i].wait_mb_pos = INT_MAX;
+ VP8ThreadData *td = &s->thread_data[i];
+ atomic_init(&td->thread_mb_pos, 0);
+ atomic_init(&td->wait_mb_pos, INT_MAX);
}
-
if (is_vp7)
avctx->execute2(avctx, vp7_decode_mb_row_sliced, s->thread_data, NULL,
num_jobs);
VP8Context *s = avctx->priv_data;
int i;
+ if (!s)
+ return 0;
+
vp8_decode_flush_impl(avctx, 1);
for (i = 0; i < FF_ARRAY_ELEMS(s->frames); i++)
av_frame_free(&s->frames[i].tf.f);
int ret;
s->avctx = avctx;
+ s->vp7 = avctx->codec->id == AV_CODEC_ID_VP7;
s->pix_fmt = AV_PIX_FMT_NONE;
avctx->pix_fmt = AV_PIX_FMT_YUV420P;
avctx->internal->allocate_progress = 1;
if (CONFIG_VP7_DECODER && is_vp7) {
ff_h264_pred_init(&s->hpc, AV_CODEC_ID_VP7, 8, 1);
ff_vp7dsp_init(&s->vp8dsp);
+ s->decode_mb_row_no_filter = vp7_decode_mb_row_no_filter;
+ s->filter_mb_row = vp7_filter_mb_row;
} else if (CONFIG_VP8_DECODER && !is_vp7) {
ff_h264_pred_init(&s->hpc, AV_CODEC_ID_VP8, 8, 1);
ff_vp8dsp_init(&s->vp8dsp);
+ s->decode_mb_row_no_filter = vp8_decode_mb_row_no_filter;
+ s->filter_mb_row = vp8_filter_mb_row;
}
/* does not change for VP8 */
}
#if CONFIG_VP8_DECODER
+#if HAVE_THREADS
static av_cold int vp8_decode_init_thread_copy(AVCodecContext *avctx)
{
VP8Context *s = avctx->priv_data;
return 0;
}
-#define REBASE(pic) pic ? pic - &s_src->frames[0] + &s->frames[0] : NULL
+#define REBASE(pic) ((pic) ? (pic) - &s_src->frames[0] + &s->frames[0] : NULL)
static int vp8_decode_update_thread_context(AVCodecContext *dst,
const AVCodecContext *src)
s->mb_height = s_src->mb_height;
}
+ s->pix_fmt = s_src->pix_fmt;
s->prob[0] = s_src->prob[!s_src->update_probabilities];
s->segmentation = s_src->segmentation;
s->lf_delta = s_src->lf_delta;
memcpy(s->sign_bias, s_src->sign_bias, sizeof(s->sign_bias));
for (i = 0; i < FF_ARRAY_ELEMS(s_src->frames); i++) {
- if (s_src->frames[i].tf.f->data[0]) {
+ if (s_src->frames[i].tf.f->buf[0]) {
int ret = vp8_ref_frame(s, &s->frames[i], &s_src->frames[i]);
if (ret < 0)
return ret;
return 0;
}
+#endif /* HAVE_THREADS */
#endif /* CONFIG_VP8_DECODER */
#if CONFIG_VP7_DECODER
.decode = ff_vp8_decode_frame,
.capabilities = AV_CODEC_CAP_DR1 | AV_CODEC_CAP_FRAME_THREADS |
AV_CODEC_CAP_SLICE_THREADS,
+ .flush = vp8_decode_flush,
+ .init_thread_copy = ONLY_IF_THREADS_ENABLED(vp8_decode_init_thread_copy),
+ .update_thread_context = ONLY_IF_THREADS_ENABLED(vp8_decode_update_thread_context),
.hw_configs = (const AVCodecHWConfigInternal*[]) {
#if CONFIG_VP8_VAAPI_HWACCEL
HWACCEL_VAAPI(vp8),
+#endif
+#if CONFIG_VP8_NVDEC_HWACCEL
+ HWACCEL_NVDEC(vp8),
#endif
NULL
},
- .flush = vp8_decode_flush,
- .init_thread_copy = ONLY_IF_THREADS_ENABLED(vp8_decode_init_thread_copy),
- .update_thread_context = ONLY_IF_THREADS_ENABLED(vp8_decode_update_thread_context),
};
#endif /* CONFIG_VP7_DECODER */
projects / ffmpeg / blobdiff