vo_direct3d: remove bitmap packer

See previous comments.

video/out/vo_direct3d.c

@@ -38,7 +38,6 @@
 #include "common/common.h"
 #include "w32_common.h"
 #include "sub/osd.h"
-#include "bitmap_packer.h"
 
 // shaders generated by fxc.exe from d3d_shader_yuv.hlsl
 #include "d3d_shader_420p.h"
@@ -105,7 +104,6 @@ struct osdpart {
     struct d3dtex texture;
     int num_vertices;
     vertex_osd *vertices;
-    struct bitmap_packer *packer;
 };
 
 enum shaders {
@@ -1215,13 +1213,8 @@ static int preinit(struct vo *vo)
     priv->vo = vo;
     priv->log = vo->log;
 
-    for (int n = 0; n < MAX_OSD_PARTS; n++) {
+    for (int n = 0; n < MAX_OSD_PARTS; n++)
-        struct osdpart *osd = talloc_ptrtype(priv, osd);
+        priv->osd[n] = talloc_zero(priv, struct osdpart);
-        *osd = (struct osdpart) {
-            .packer = talloc_zero(osd, struct bitmap_packer),
-        };
-        priv->osd[n] = osd;
-    }
 
     priv->d3d9_dll = LoadLibraryA("d3d9.dll");
     if (!priv->d3d9_dll) {
@@ -1536,34 +1529,45 @@ error_exit:
     return NULL;
 }
 
+static D3DCOLOR ass_to_d3d_color(uint32_t color)
+{
+    uint32_t r = (color >> 24) & 0xff;
+    uint32_t g = (color >> 16) & 0xff;
+    uint32_t b = (color >> 8) & 0xff;
+    uint32_t a = 0xff - (color & 0xff);
+    return D3DCOLOR_ARGB(a, r, g, b);
+}
+
+static int next_pow2(int v)
+{
+    for (int x = 0; x < 30; x++) {
+        if ((1 << x) >= v)
+            return 1 << x;
+    }
+    return INT_MAX;
+}
+
 static bool upload_osd(d3d_priv *priv, struct osdpart *osd,
                        struct sub_bitmaps *imgs)
 {
     D3DFORMAT fmt = priv->osd_fmt_table[imgs->format];
 
-    osd->packer->w_max = priv->max_texture_width;
+    assert(imgs->packed);
-    osd->packer->h_max = priv->max_texture_height;
 
-    osd->packer->padding = imgs->scaled; // assume 2x2 filter on scaling
+    osd->change_id = imgs->change_id;
-    int r = packer_pack_from_subbitmaps(osd->packer, imgs);
+    osd->num_vertices = 0;
-    if (r < 0) {
-        MP_ERR(priv, "OSD bitmaps do not fit on "
-            "a surface with the maximum supported size %dx%d.\n",
-            osd->packer->w_max, osd->packer->h_max);
-        return false;
-    }
 
-    if (osd->packer->w > osd->texture.tex_w
+    if (imgs->packed_w > osd->texture.tex_w
-        || osd->packer->h > osd->texture.tex_h
+        || imgs->packed_h > osd->texture.tex_h
         || osd->format != imgs->format)
     {
         osd->format = imgs->format;
 
-        int new_w = osd->packer->w;
+        int new_w = next_pow2(imgs->packed_w);
-        int new_h = osd->packer->h;
+        int new_h = next_pow2(imgs->packed_h);
         d3d_fix_texture_size(priv, &new_w, &new_h);
 
-        MP_DBG(priv, "reallocate OSD surface.\n");
+        MP_DBG(priv, "reallocate OSD surface to %dx%d.\n", new_w, new_h);
 
         d3dtex_release(priv, &osd->texture);
         d3dtex_allocate(priv, &osd->texture, fmt, new_w, new_h);
@@ -1572,9 +1576,7 @@ static bool upload_osd(d3d_priv *priv, struct osdpart *osd,
             return false; // failed to allocate
     }
 
-    struct pos bb[2];
+    RECT dirty_rc = { 0, 0, imgs->packed_w, imgs->packed_h };
-    packer_get_bb(osd->packer, bb);
-    RECT dirty_rc = { bb[0].x, bb[0].y, bb[1].x, bb[1].y };
 
     D3DLOCKED_RECT locked_rect;
 
@@ -1586,66 +1588,26 @@ static bool upload_osd(d3d_priv *priv, struct osdpart *osd,
     }
 
     int ps = fmt == D3DFMT_A8 ? 1 : 4;
-    packer_copy_subbitmaps(osd->packer, imgs, locked_rect.pBits, ps,
+    memcpy_pic(locked_rect.pBits, imgs->packed->planes[0], ps * imgs->packed_w,
-                           locked_rect.Pitch);
+               imgs->packed_h, locked_rect.Pitch, imgs->packed->stride[0]);
 
     if (FAILED(IDirect3DTexture9_UnlockRect(osd->texture.system, 0))) {
         MP_ERR(priv, "OSD texture unlock failed.\n");
         return false;
     }
 
-    return d3dtex_update(priv, &osd->texture);
+    if (!d3dtex_update(priv, &osd->texture))
-}
+        return false;
 
-static struct osdpart *generate_osd(d3d_priv *priv, struct sub_bitmaps *imgs)
+    // We need 2 primitives per quad which makes 6 vertices.
-{
+    osd->num_vertices = imgs->num_parts * 6;
-    if (imgs->num_parts == 0 || !priv->osd_fmt_table[imgs->format])
+    MP_TARRAY_GROW(osd, osd->vertices, osd->num_vertices);
-        return NULL;
-
-    struct osdpart *osd = priv->osd[imgs->render_index];
-
-    if (imgs->change_id != osd->change_id) {
-        if (!upload_osd(priv, osd, imgs))
-            osd->packer->count = 0;
-
-        osd->change_id = imgs->change_id;
-        osd->num_vertices = 0;
-    }
-
-    return osd->packer->count ? osd : NULL;
-}
-
-static D3DCOLOR ass_to_d3d_color(uint32_t color)
-{
-    uint32_t r = (color >> 24) & 0xff;
-    uint32_t g = (color >> 16) & 0xff;
-    uint32_t b = (color >> 8) & 0xff;
-    uint32_t a = 0xff - (color & 0xff);
-    return D3DCOLOR_ARGB(a, r, g, b);
-}
-
-static void draw_osd_cb(void *ctx, struct sub_bitmaps *imgs)
-{
-    d3d_priv *priv = ctx;
-
-    struct osdpart *osd = generate_osd(priv, imgs);
-    if (!osd)
-        return;
-
-    if (osd->packer->count && !osd->num_vertices) {
-        // We need 2 primitives per quad which makes 6 vertices (we could reduce
-        // the number of vertices by using an indexed vertex array, but it's
-        // probably not worth doing)
-        osd->num_vertices = osd->packer->count * 6;
-        osd->vertices = talloc_realloc(osd, osd->vertices, vertex_osd,
-                                       osd->num_vertices);
 
     float tex_w = osd->texture.tex_w;
     float tex_h = osd->texture.tex_h;
 
-        for (int n = 0; n < osd->packer->count; n++) {
+    for (int n = 0; n < imgs->num_parts; n++) {
         struct sub_bitmap *b = &imgs->parts[n];
-            struct pos p = osd->packer->result[n];
 
         D3DCOLOR color = imgs->format == SUBBITMAP_LIBASS
                         ? ass_to_d3d_color(b->libass.color)
@@ -1655,10 +1617,10 @@ static void draw_osd_cb(void *ctx, struct sub_bitmaps *imgs)
         float y0 = b->y;
         float x1 = b->x + b->dw;
         float y1 = b->y + b->dh;
-            float tx0 = p.x / tex_w;
+        float tx0 = b->src_x / tex_w;
-            float ty0 = p.y / tex_h;
+        float ty0 = b->src_y / tex_h;
-            float tx1 = (p.x + b->w) / tex_w;
+        float tx1 = (b->src_x + b->w) / tex_w;
-            float ty1 = (p.y + b->h) / tex_h;
+        float ty1 = (b->src_y + b->h) / tex_h;
 
         vertex_osd *v = &osd->vertices[n * 6];
         v[0] = (vertex_osd) { x0, y0, 0, color, tx0, ty0 };
@@ -1668,8 +1630,31 @@ static void draw_osd_cb(void *ctx, struct sub_bitmaps *imgs)
         v[4] = v[2];
         v[5] = v[1];
     }
+
+    return true;
 }
 
+static struct osdpart *generate_osd(d3d_priv *priv, struct sub_bitmaps *imgs)
+{
+    if (imgs->num_parts == 0 || !priv->osd_fmt_table[imgs->format])
+        return NULL;
+
+    struct osdpart *osd = priv->osd[imgs->render_index];
+
+    if (imgs->change_id != osd->change_id)
+        upload_osd(priv, osd, imgs);
+
+    return osd->num_vertices ? osd : NULL;
+}
+
+static void draw_osd_cb(void *ctx, struct sub_bitmaps *imgs)
+{
+    d3d_priv *priv = ctx;
+
+    struct osdpart *osd = generate_osd(priv, imgs);
+    if (!osd)
+        return;
+
     d3d_begin_scene(priv);
 
     IDirect3DDevice9_SetRenderState(priv->d3d_device,