prores: Change type of stride parameters to ptrdiff_t

This avoids SIMD-optimized functions having to sign-extend their
line size argument manually to be able to do pointer arithmetic.

Also adjust parameter names to be "linesize" everywhere.

libavcodec/proresdsp.c

@@ -36,11 +36,11 @@
 /**
  * Add bias value, clamp and output pixels of a slice
  */
-static void put_pixels(uint16_t *dst, int stride, const int16_t *in)
+static void put_pixels(uint16_t *dst, ptrdiff_t linesize, const int16_t *in)
 {
     int x, y, src_offset, dst_offset;
 
-    for (y = 0, dst_offset = 0; y < 8; y++, dst_offset += stride) {
+    for (y = 0, dst_offset = 0; y < 8; y++, dst_offset += linesize) {
         for (x = 0; x < 8; x++) {
             src_offset = (y << 3) + x;
 
@@ -49,7 +49,7 @@ static void put_pixels(uint16_t *dst, int stride, const int16_t *in)
     }
 }
 
-static void prores_idct_put_c(uint16_t *out, int linesize, int16_t *block, const int16_t *qmat)
+static void prores_idct_put_c(uint16_t *out, ptrdiff_t linesize, int16_t *block, const int16_t *qmat)
 {
     ff_prores_idct(block, qmat);
     put_pixels(out, linesize >> 1, block);

libavcodec/proresdsp.h

@@ -23,6 +23,7 @@
 #ifndef AVCODEC_PRORESDSP_H
 #define AVCODEC_PRORESDSP_H
 
+#include <stddef.h>
 #include <stdint.h>
 
 #define PRORES_BITS_PER_SAMPLE 10 ///< output precision of prores decoder
@@ -30,7 +31,7 @@
 typedef struct ProresDSPContext {
     int idct_permutation_type;
     uint8_t idct_permutation[64];
-    void (* idct_put) (uint16_t *out, int linesize, int16_t *block, const int16_t *qmat);
+    void (*idct_put)(uint16_t *out, ptrdiff_t linesize, int16_t *block, const int16_t *qmat);
 } ProresDSPContext;
 
 void ff_proresdsp_init(ProresDSPContext *dsp);

libavcodec/proresenc.c

@@ -192,7 +192,7 @@ typedef struct ProresContext {
     const uint8_t *scantable;
 
     void (*fdct)(FDCTDSPContext *fdsp, const uint16_t *src,
-                 int linesize, int16_t *block);
+                 ptrdiff_t linesize, int16_t *block);
     FDCTDSPContext fdsp;
 
     const AVFrame *pic;
@@ -223,13 +223,13 @@ typedef struct ProresContext {
 } ProresContext;
 
 static void get_slice_data(ProresContext *ctx, const uint16_t *src,
-                           int linesize, int x, int y, int w, int h,
+                           ptrdiff_t linesize, int x, int y, int w, int h,
                            int16_t *blocks, uint16_t *emu_buf,
                            int mbs_per_slice, int blocks_per_mb, int is_chroma)
 {
     const uint16_t *esrc;
     const int mb_width = 4 * blocks_per_mb;
-    int elinesize;
+    ptrdiff_t elinesize;
     int i, j, k;
 
     for (i = 0; i < mbs_per_slice; i++, src += mb_width) {
@@ -294,7 +294,7 @@ static void get_slice_data(ProresContext *ctx, const uint16_t *src,
 }
 
 static void get_alpha_data(ProresContext *ctx, const uint16_t *src,
-                           int linesize, int x, int y, int w, int h,
+                           ptrdiff_t linesize, int x, int y, int w, int h,
                            int16_t *blocks, int mbs_per_slice, int abits)
 {
     const int slice_width = 16 * mbs_per_slice;
@@ -417,7 +417,7 @@ static void encode_acs(PutBitContext *pb, int16_t *blocks,
 }
 
 static int encode_slice_plane(ProresContext *ctx, PutBitContext *pb,
-                              const uint16_t *src, int linesize,
+                              const uint16_t *src, ptrdiff_t linesize,
                               int mbs_per_slice, int16_t *blocks,
                               int blocks_per_mb, int plane_size_factor,
                               const int16_t *qmat)
@@ -511,7 +511,8 @@ static int encode_slice(AVCodecContext *avctx, const AVFrame *pic,
     int total_size = 0;
     const uint16_t *src;
     int slice_width_factor = av_log2(mbs_per_slice);
-    int num_cblocks, pwidth, linesize, line_add;
+    int num_cblocks, pwidth, line_add;
+    ptrdiff_t linesize;
     int plane_factor, is_chroma;
     uint16_t *qmat;
 
@@ -667,7 +668,7 @@ static int estimate_acs(int *error, int16_t *blocks, int blocks_per_slice,
 }
 
 static int estimate_slice_plane(ProresContext *ctx, int *error, int plane,
-                                const uint16_t *src, int linesize,
+                                const uint16_t *src, ptrdiff_t linesize,
                                 int mbs_per_slice,
                                 int blocks_per_mb, int plane_size_factor,
                                 const int16_t *qmat, ProresThreadData *td)
@@ -701,7 +702,7 @@ static int est_alpha_diff(int cur, int prev, int abits)
 }
 
 static int estimate_alpha_plane(ProresContext *ctx, int *error,
-                                const uint16_t *src, int linesize,
+                                const uint16_t *src, ptrdiff_t linesize,
                                 int mbs_per_slice, int quant,
                                 int16_t *blocks)
 {
@@ -1112,7 +1113,7 @@ static av_cold int encode_close(AVCodecContext *avctx)
 }
 
 static void prores_fdct(FDCTDSPContext *fdsp, const uint16_t *src,
-                        int linesize, int16_t *block)
+                        ptrdiff_t linesize, int16_t *block)
 {
     int x, y;
     const uint16_t *tsrc = src;

libavcodec/x86/proresdsp.asm

@@ -326,11 +326,10 @@ SECTION .text
     SUMSUB_SHPK m2,  m3,  m4,  m5,  m6,  m7,  %2
 %endmacro
 
-; void ff_prores_idct_put_10_<opt>(uint8_t *pixels, int stride,
+; void ff_prores_idct_put_10_<opt>(uint8_t *pixels, ptrdiff_t linesize,
 ;                                  int16_t *block, const int16_t *qmat);
 %macro idct_put_fn 1
 cglobal prores_idct_put_10, 4, 4, %1
-    movsxd      r1,  r1d
     pxor        m15, m15           ; zero
 
     ; for (i = 0; i < 8; i++)

libavcodec/x86/proresdsp_init.c

@@ -25,11 +25,11 @@
 #include "libavcodec/idctdsp.h"
 #include "libavcodec/proresdsp.h"
 
-void ff_prores_idct_put_10_sse2(uint16_t *dst, int linesize,
+void ff_prores_idct_put_10_sse2(uint16_t *dst, ptrdiff_t linesize,
                                 int16_t *block, const int16_t *qmat);
-void ff_prores_idct_put_10_sse4(uint16_t *dst, int linesize,
+void ff_prores_idct_put_10_sse4(uint16_t *dst, ptrdiff_t linesize,
                                 int16_t *block, const int16_t *qmat);
-void ff_prores_idct_put_10_avx (uint16_t *dst, int linesize,
+void ff_prores_idct_put_10_avx (uint16_t *dst, ptrdiff_t linesize,
                                 int16_t *block, const int16_t *qmat);
 
 av_cold void ff_proresdsp_init_x86(ProresDSPContext *dsp)