[FFmpeg-devel,v12,07/15] avcodec/vaapi_encode: extract the init and close function to base layer

diff --git a/libavcodec/hw_base_encode.c b/libavcodec/hw_base_encode.c
index 16afaa37be..c4789380b6 100644
--- a/libavcodec/hw_base_encode.c
+++ b/libavcodec/hw_base_encode.c
@@ -592,3 +592,52 @@  end:
 
     return 0;
 }
+
+int ff_hw_base_encode_init(AVCodecContext *avctx)
+{
+    FFHWBaseEncodeContext *ctx = avctx->priv_data;
+
+    ctx->frame = av_frame_alloc();
+    if (!ctx->frame)
+        return AVERROR(ENOMEM);
+
+    if (!avctx->hw_frames_ctx) {
+        av_log(avctx, AV_LOG_ERROR, "A hardware frames reference is "
+               "required to associate the encoding device.\n");
+        return AVERROR(EINVAL);
+    }
+
+    ctx->input_frames_ref = av_buffer_ref(avctx->hw_frames_ctx);
+    if (!ctx->input_frames_ref)
+        return AVERROR(ENOMEM);
+
+    ctx->input_frames = (AVHWFramesContext *)ctx->input_frames_ref->data;
+
+    ctx->device_ref = av_buffer_ref(ctx->input_frames->device_ref);
+    if (!ctx->device_ref)
+        return AVERROR(ENOMEM);
+
+    ctx->device = (AVHWDeviceContext *)ctx->device_ref->data;
+
+    ctx->tail_pkt = av_packet_alloc();
+    if (!ctx->tail_pkt)
+        return AVERROR(ENOMEM);
+
+    return 0;
+}
+
+int ff_hw_base_encode_close(AVCodecContext *avctx)
+{
+    FFHWBaseEncodeContext *ctx = avctx->priv_data;
+
+    av_fifo_freep2(&ctx->encode_fifo);
+
+    av_frame_free(&ctx->frame);
+    av_packet_free(&ctx->tail_pkt);
+
+    av_buffer_unref(&ctx->device_ref);
+    av_buffer_unref(&ctx->input_frames_ref);
+    av_buffer_unref(&ctx->recon_frames_ref);
+
+    return 0;
+}
diff --git a/libavcodec/hw_base_encode.h b/libavcodec/hw_base_encode.h
index 81e6c87036..a062009860 100644
--- a/libavcodec/hw_base_encode.h
+++ b/libavcodec/hw_base_encode.h
@@ -19,6 +19,7 @@ 
 #ifndef AVCODEC_HW_BASE_ENCODE_H
 #define AVCODEC_HW_BASE_ENCODE_H
 
+#include "libavutil/hwcontext.h"
 #include "libavutil/fifo.h"
 
 #define MAX_DPB_SIZE 16
@@ -119,6 +120,18 @@  typedef struct FFHWBaseEncodeContext {
     // Hardware-specific hooks.
     const struct FFHWEncodePictureOperation *op;
 
+    // The hardware device context.
+    AVBufferRef    *device_ref;
+    AVHWDeviceContext *device;
+
+    // The hardware frame context containing the input frames.
+    AVBufferRef    *input_frames_ref;
+    AVHWFramesContext *input_frames;
+
+    // The hardware frame context containing the reconstructed frames.
+    AVBufferRef    *recon_frames_ref;
+    AVHWFramesContext *recon_frames;
+
     // Current encoding window, in display (input) order.
     FFHWBaseEncodePicture *pic_start, *pic_end;
     // The next picture to use as the previous reference picture in
@@ -185,6 +198,10 @@  typedef struct FFHWBaseEncodeContext {
 
 int ff_hw_base_encode_receive_packet(AVCodecContext *avctx, AVPacket *pkt);
 
+int ff_hw_base_encode_init(AVCodecContext *avctx);
+
+int ff_hw_base_encode_close(AVCodecContext *avctx);
+
 #define HW_BASE_ENCODE_COMMON_OPTIONS \
     { "async_depth", "Maximum processing parallelism. " \
       "Increase this to improve single channel performance.", \
diff --git a/libavcodec/vaapi_encode.c b/libavcodec/vaapi_encode.c
index 1055fca0b1..1b3bab2c14 100644
--- a/libavcodec/vaapi_encode.c
+++ b/libavcodec/vaapi_encode.c
@@ -314,7 +314,7 @@  static int vaapi_encode_issue(AVCodecContext *avctx,
 
     av_log(avctx, AV_LOG_DEBUG, "Input surface is %#x.\n", pic->input_surface);
 
-    err = av_hwframe_get_buffer(ctx->recon_frames_ref, base_pic->recon_image, 0);
+    err = av_hwframe_get_buffer(base_ctx->recon_frames_ref, base_pic->recon_image, 0);
     if (err < 0) {
         err = AVERROR(ENOMEM);
         goto fail;
@@ -996,9 +996,10 @@  static const VAEntrypoint vaapi_encode_entrypoints_low_power[] = {
 
 static av_cold int vaapi_encode_profile_entrypoint(AVCodecContext *avctx)
 {
-    VAAPIEncodeContext      *ctx = avctx->priv_data;
-    VAProfile    *va_profiles    = NULL;
-    VAEntrypoint *va_entrypoints = NULL;
+    FFHWBaseEncodeContext *base_ctx = avctx->priv_data;
+    VAAPIEncodeContext         *ctx = avctx->priv_data;
+    VAProfile       *va_profiles    = NULL;
+    VAEntrypoint    *va_entrypoints = NULL;
     VAStatus vas;
     const VAEntrypoint *usable_entrypoints;
     const VAAPIEncodeProfile *profile;
@@ -1021,10 +1022,10 @@  static av_cold int vaapi_encode_profile_entrypoint(AVCodecContext *avctx)
         usable_entrypoints = vaapi_encode_entrypoints_normal;
     }
 
-    desc = av_pix_fmt_desc_get(ctx->input_frames->sw_format);
+    desc = av_pix_fmt_desc_get(base_ctx->input_frames->sw_format);
     if (!desc) {
         av_log(avctx, AV_LOG_ERROR, "Invalid input pixfmt (%d).\n",
-               ctx->input_frames->sw_format);
+               base_ctx->input_frames->sw_format);
         return AVERROR(EINVAL);
     }
     depth = desc->comp[0].depth;
@@ -2131,20 +2132,21 @@  static int vaapi_encode_alloc_output_buffer(FFRefStructOpaque opaque, void *obj)
 
 static av_cold int vaapi_encode_create_recon_frames(AVCodecContext *avctx)
 {
-    VAAPIEncodeContext *ctx = avctx->priv_data;
+    FFHWBaseEncodeContext *base_ctx = avctx->priv_data;
+    VAAPIEncodeContext         *ctx = avctx->priv_data;
     AVVAAPIHWConfig *hwconfig = NULL;
     AVHWFramesConstraints *constraints = NULL;
     enum AVPixelFormat recon_format;
     int err, i;
 
-    hwconfig = av_hwdevice_hwconfig_alloc(ctx->device_ref);
+    hwconfig = av_hwdevice_hwconfig_alloc(base_ctx->device_ref);
     if (!hwconfig) {
         err = AVERROR(ENOMEM);
         goto fail;
     }
     hwconfig->config_id = ctx->va_config;
 
-    constraints = av_hwdevice_get_hwframe_constraints(ctx->device_ref,
+    constraints = av_hwdevice_get_hwframe_constraints(base_ctx->device_ref,
                                                       hwconfig);
     if (!constraints) {
         err = AVERROR(ENOMEM);
@@ -2157,9 +2159,9 @@  static av_cold int vaapi_encode_create_recon_frames(AVCodecContext *avctx)
     recon_format = AV_PIX_FMT_NONE;
     if (constraints->valid_sw_formats) {
         for (i = 0; constraints->valid_sw_formats[i] != AV_PIX_FMT_NONE; i++) {
-            if (ctx->input_frames->sw_format ==
+            if (base_ctx->input_frames->sw_format ==
                 constraints->valid_sw_formats[i]) {
-                recon_format = ctx->input_frames->sw_format;
+                recon_format = base_ctx->input_frames->sw_format;
                 break;
             }
         }
@@ -2170,7 +2172,7 @@  static av_cold int vaapi_encode_create_recon_frames(AVCodecContext *avctx)
         }
     } else {
         // No idea what to use; copy input format.
-        recon_format = ctx->input_frames->sw_format;
+        recon_format = base_ctx->input_frames->sw_format;
     }
     av_log(avctx, AV_LOG_DEBUG, "Using %s as format of "
            "reconstructed frames.\n", av_get_pix_fmt_name(recon_format));
@@ -2191,19 +2193,19 @@  static av_cold int vaapi_encode_create_recon_frames(AVCodecContext *avctx)
     av_freep(&hwconfig);
     av_hwframe_constraints_free(&constraints);
 
-    ctx->recon_frames_ref = av_hwframe_ctx_alloc(ctx->device_ref);
-    if (!ctx->recon_frames_ref) {
+    base_ctx->recon_frames_ref = av_hwframe_ctx_alloc(base_ctx->device_ref);
+    if (!base_ctx->recon_frames_ref) {
         err = AVERROR(ENOMEM);
         goto fail;
     }
-    ctx->recon_frames = (AVHWFramesContext*)ctx->recon_frames_ref->data;
+    base_ctx->recon_frames = (AVHWFramesContext*)base_ctx->recon_frames_ref->data;
 
-    ctx->recon_frames->format    = AV_PIX_FMT_VAAPI;
-    ctx->recon_frames->sw_format = recon_format;
-    ctx->recon_frames->width     = ctx->surface_width;
-    ctx->recon_frames->height    = ctx->surface_height;
+    base_ctx->recon_frames->format    = AV_PIX_FMT_VAAPI;
+    base_ctx->recon_frames->sw_format = recon_format;
+    base_ctx->recon_frames->width     = ctx->surface_width;
+    base_ctx->recon_frames->height    = ctx->surface_height;
 
-    err = av_hwframe_ctx_init(ctx->recon_frames_ref);
+    err = av_hwframe_ctx_init(base_ctx->recon_frames_ref);
     if (err < 0) {
         av_log(avctx, AV_LOG_ERROR, "Failed to initialise reconstructed "
                "frame context: %d.\n", err);
@@ -2235,44 +2237,16 @@  av_cold int ff_vaapi_encode_init(AVCodecContext *avctx)
     VAStatus vas;
     int err;
 
+    err = ff_hw_base_encode_init(avctx);
+    if (err < 0)
+        goto fail;
+
     ctx->va_config  = VA_INVALID_ID;
     ctx->va_context = VA_INVALID_ID;
 
     base_ctx->op = &vaapi_op;
 
-    /* If you add something that can fail above this av_frame_alloc(),
-     * modify ff_vaapi_encode_close() accordingly. */
-    base_ctx->frame = av_frame_alloc();
-    if (!base_ctx->frame) {
-        return AVERROR(ENOMEM);
-    }
-
-    if (!avctx->hw_frames_ctx) {
-        av_log(avctx, AV_LOG_ERROR, "A hardware frames reference is "
-               "required to associate the encoding device.\n");
-        return AVERROR(EINVAL);
-    }
-
-    ctx->input_frames_ref = av_buffer_ref(avctx->hw_frames_ctx);
-    if (!ctx->input_frames_ref) {
-        err = AVERROR(ENOMEM);
-        goto fail;
-    }
-    ctx->input_frames = (AVHWFramesContext*)ctx->input_frames_ref->data;
-
-    ctx->device_ref = av_buffer_ref(ctx->input_frames->device_ref);
-    if (!ctx->device_ref) {
-        err = AVERROR(ENOMEM);
-        goto fail;
-    }
-    ctx->device = (AVHWDeviceContext*)ctx->device_ref->data;
-    ctx->hwctx = ctx->device->hwctx;
-
-    base_ctx->tail_pkt = av_packet_alloc();
-    if (!base_ctx->tail_pkt) {
-        err = AVERROR(ENOMEM);
-        goto fail;
-    }
+    ctx->hwctx = base_ctx->device->hwctx;
 
     err = vaapi_encode_profile_entrypoint(avctx);
     if (err < 0)
@@ -2339,7 +2313,7 @@  av_cold int ff_vaapi_encode_init(AVCodecContext *avctx)
     if (err < 0)
         goto fail;
 
-    recon_hwctx = ctx->recon_frames->hwctx;
+    recon_hwctx = base_ctx->recon_frames->hwctx;
     vas = vaCreateContext(ctx->hwctx->display, ctx->va_config,
                           ctx->surface_width, ctx->surface_height,
                           VA_PROGRESSIVE,
@@ -2467,16 +2441,10 @@  av_cold int ff_vaapi_encode_close(AVCodecContext *avctx)
         ctx->va_config = VA_INVALID_ID;
     }
 
-    av_frame_free(&base_ctx->frame);
-    av_packet_free(&base_ctx->tail_pkt);
-
     av_freep(&ctx->codec_sequence_params);
     av_freep(&ctx->codec_picture_params);
-    av_fifo_freep2(&base_ctx->encode_fifo);
 
-    av_buffer_unref(&ctx->recon_frames_ref);
-    av_buffer_unref(&ctx->input_frames_ref);
-    av_buffer_unref(&ctx->device_ref);
+    ff_hw_base_encode_close(avctx);
 
     return 0;
 }
diff --git a/libavcodec/vaapi_encode.h b/libavcodec/vaapi_encode.h
index 5e442d9c23..d5d7d27a07 100644
--- a/libavcodec/vaapi_encode.h
+++ b/libavcodec/vaapi_encode.h
@@ -219,18 +219,8 @@  typedef struct VAAPIEncodeContext {
     VAConfigID      va_config;
     VAContextID     va_context;
 
-    AVBufferRef    *device_ref;
-    AVHWDeviceContext *device;
     AVVAAPIDeviceContext *hwctx;
 
-    // The hardware frame context containing the input frames.
-    AVBufferRef    *input_frames_ref;
-    AVHWFramesContext *input_frames;
-
-    // The hardware frame context containing the reconstructed frames.
-    AVBufferRef    *recon_frames_ref;
-    AVHWFramesContext *recon_frames;
-
     // Pool of (reusable) bitstream output buffers.
     struct FFRefStructPool *output_buffer_pool;
 
diff --git a/libavcodec/vaapi_encode_av1.c b/libavcodec/vaapi_encode_av1.c
index 1c9235acd9..a590f4cd8b 100644
--- a/libavcodec/vaapi_encode_av1.c
+++ b/libavcodec/vaapi_encode_av1.c
@@ -373,7 +373,7 @@  static int vaapi_encode_av1_init_sequence_params(AVCodecContext *avctx)
     memset(sh_obu, 0, sizeof(*sh_obu));
     sh_obu->header.obu_type = AV1_OBU_SEQUENCE_HEADER;
 
-    desc = av_pix_fmt_desc_get(priv->common.input_frames->sw_format);
+    desc = av_pix_fmt_desc_get(base_ctx->input_frames->sw_format);
     av_assert0(desc);
 
     sh->seq_profile  = avctx->profile;
diff --git a/libavcodec/vaapi_encode_h264.c b/libavcodec/vaapi_encode_h264.c
index 2f91655d18..eacfb12706 100644
--- a/libavcodec/vaapi_encode_h264.c
+++ b/libavcodec/vaapi_encode_h264.c
@@ -308,7 +308,7 @@  static int vaapi_encode_h264_init_sequence_params(AVCodecContext *avctx)
     memset(sps, 0, sizeof(*sps));
     memset(pps, 0, sizeof(*pps));
 
-    desc = av_pix_fmt_desc_get(priv->common.input_frames->sw_format);
+    desc = av_pix_fmt_desc_get(base_ctx->input_frames->sw_format);
     av_assert0(desc);
     if (desc->nb_components == 1 || desc->log2_chroma_w != 1 || desc->log2_chroma_h != 1) {
         av_log(avctx, AV_LOG_ERROR, "Chroma format of input pixel format "
diff --git a/libavcodec/vaapi_encode_h265.c b/libavcodec/vaapi_encode_h265.c
index 6befe3426e..509251c97a 100644
--- a/libavcodec/vaapi_encode_h265.c
+++ b/libavcodec/vaapi_encode_h265.c
@@ -278,7 +278,7 @@  static int vaapi_encode_h265_init_sequence_params(AVCodecContext *avctx)
     memset(pps, 0, sizeof(*pps));
 
 
-    desc = av_pix_fmt_desc_get(priv->common.input_frames->sw_format);
+    desc = av_pix_fmt_desc_get(base_ctx->input_frames->sw_format);
     av_assert0(desc);
     if (desc->nb_components == 1) {
         chroma_format = 0;
diff --git a/libavcodec/vaapi_encode_mjpeg.c b/libavcodec/vaapi_encode_mjpeg.c
index 4c31881e6a..48dc677bec 100644
--- a/libavcodec/vaapi_encode_mjpeg.c
+++ b/libavcodec/vaapi_encode_mjpeg.c
@@ -222,6 +222,7 @@  static int vaapi_encode_mjpeg_write_extra_buffer(AVCodecContext *avctx,
 static int vaapi_encode_mjpeg_init_picture_params(AVCodecContext *avctx,
                                                   VAAPIEncodePicture *vaapi_pic)
 {
+    FFHWBaseEncodeContext       *base_ctx = avctx->priv_data;
     VAAPIEncodeMJPEGContext         *priv = avctx->priv_data;
     const FFHWBaseEncodePicture      *pic = &vaapi_pic->base;
     JPEGRawFrameHeader                *fh = &priv->frame_header;
@@ -235,7 +236,7 @@  static int vaapi_encode_mjpeg_init_picture_params(AVCodecContext *avctx,
 
     av_assert0(pic->type == FF_HW_PICTURE_TYPE_IDR);
 
-    desc = av_pix_fmt_desc_get(priv->common.input_frames->sw_format);
+    desc = av_pix_fmt_desc_get(base_ctx->input_frames->sw_format);
     av_assert0(desc);
     if (desc->flags & AV_PIX_FMT_FLAG_RGB)
         components = components_rgb;
@@ -437,10 +438,11 @@  static int vaapi_encode_mjpeg_init_slice_params(AVCodecContext *avctx,
 
 static av_cold int vaapi_encode_mjpeg_get_encoder_caps(AVCodecContext *avctx)
 {
+    FFHWBaseEncodeContext *base_ctx = avctx->priv_data;
     VAAPIEncodeContext *ctx = avctx->priv_data;
     const AVPixFmtDescriptor *desc;
 
-    desc = av_pix_fmt_desc_get(ctx->input_frames->sw_format);
+    desc = av_pix_fmt_desc_get(base_ctx->input_frames->sw_format);
     av_assert0(desc);
 
     ctx->surface_width  = FFALIGN(avctx->width,  8 << desc->log2_chroma_w);