1 files changed, 133 insertions, 37 deletions

diff --git a/src/capture/kms.c b/src/capture/kms.c
index 8b16ec9..ae0c36f 100644
--- a/src/capture/kms.c
+++ b/src/capture/kms.c
@@ -2,6 +2,7 @@
 #include "../../include/utils.h"
 #include "../../include/color_conversion.h"
 #include "../../include/cursor.h"
+#include "../../include/window/window.h"
 #include "../../kms/client/kms_client.h"
 
 #include <stdlib.h>
@@ -17,6 +18,8 @@
 #include <libavutil/mastering_display_metadata.h>
 #include <libavformat/avformat.h>
 
+#define FIND_CRTC_BY_NAME_TIMEOUT_SECONDS 2.0
+
 #define HDMI_STATIC_METADATA_TYPE1 0
 #define HDMI_EOTF_SMPTE_ST2084 2
 
@@ -55,6 +58,7 @@ typedef struct {
     AVCodecContext *video_codec_context;
     bool performance_error_shown;
     bool fast_path_failed;
+    bool mesa_supports_compute_only_vaapi_copy;
 
     //int drm_fd;
     //uint64_t prev_sequence;
@@ -62,6 +66,8 @@ typedef struct {
 
     vec2i prev_target_pos;
     vec2i prev_plane_size;
+
+    double last_time_monitor_check;
 } gsr_capture_kms;
 
 static void gsr_capture_kms_cleanup_kms_fds(gsr_capture_kms *self) {
@@ -183,17 +189,19 @@ static int gsr_capture_kms_start(gsr_capture *cap, AVCodecContext *video_codec_c
     if(kms_init_res != 0)
         return kms_init_res;
 
-    self->is_x11 = gsr_egl_get_display_server(self->params.egl) == GSR_DISPLAY_SERVER_X11;
+    self->is_x11 = gsr_window_get_display_server(self->params.egl->window) == GSR_DISPLAY_SERVER_X11;
     const gsr_connection_type connection_type = self->is_x11 ? GSR_CONNECTION_X11 : GSR_CONNECTION_DRM;
-    if(self->is_x11)
-        gsr_cursor_init(&self->x11_cursor, self->params.egl, self->params.egl->x11.dpy);
+    if(self->is_x11) {
+        Display *display = gsr_window_get_display(self->params.egl->window);
+        gsr_cursor_init(&self->x11_cursor, self->params.egl, display);
+    }
 
     MonitorCallbackUserdata monitor_callback_userdata = {
         &self->monitor_id,
         self->params.display_to_capture, strlen(self->params.display_to_capture),
         0,
     };
-    for_each_active_monitor_output(self->params.egl, connection_type, monitor_callback, &monitor_callback_userdata);
+    for_each_active_monitor_output(self->params.egl->window, self->params.egl->card_path, connection_type, monitor_callback, &monitor_callback_userdata);
 
     if(!get_monitor_by_name(self->params.egl, connection_type, self->params.display_to_capture, &monitor)) {
         fprintf(stderr, "gsr error: gsr_capture_kms_start: failed to find monitor by name \"%s\"\n", self->params.display_to_capture);
@@ -202,7 +210,7 @@ static int gsr_capture_kms_start(gsr_capture *cap, AVCodecContext *video_codec_c
     }
 
     monitor.name = self->params.display_to_capture;
-    self->monitor_rotation = drm_monitor_get_display_server_rotation(self->params.egl, &monitor);
+    self->monitor_rotation = drm_monitor_get_display_server_rotation(self->params.egl->window, &monitor);
 
     self->capture_pos = monitor.pos;
     /* Monitor size is already rotated on x11 when the monitor is rotated, no need to apply it ourselves */
@@ -214,13 +222,32 @@ static int gsr_capture_kms_start(gsr_capture *cap, AVCodecContext *video_codec_c
     /* Disable vsync */
     self->params.egl->eglSwapInterval(self->params.egl->egl_display, 0);
 
-    video_codec_context->width = FFALIGN(self->capture_size.x, 2);
-    video_codec_context->height = FFALIGN(self->capture_size.y, 2);
+    if(self->params.output_resolution.x == 0 && self->params.output_resolution.y == 0) {
+        self->params.output_resolution = self->capture_size;
+        video_codec_context->width = FFALIGN(self->capture_size.x, 2);
+        video_codec_context->height = FFALIGN(self->capture_size.y, 2);
+    } else {
+        self->params.output_resolution = scale_keep_aspect_ratio(self->capture_size, self->params.output_resolution);
+        video_codec_context->width = FFALIGN(self->params.output_resolution.x, 2);
+        video_codec_context->height = FFALIGN(self->params.output_resolution.y, 2);
+    }
+
+    self->fast_path_failed = self->params.egl->gpu_info.vendor == GSR_GPU_VENDOR_AMD && !gl_driver_version_greater_than(&self->params.egl->gpu_info, 24, 0, 9);
+    if(self->fast_path_failed)
+        fprintf(stderr, "gsr warning: gsr_capture_kms_start: your amd driver (mesa) version is known to be buggy (<= version 24.0.9), falling back to opengl copy\n");
+
+    //if(self->params.hdr) {
+    //    self->fast_path_failed = true;
+    //    fprintf(stderr, "gsr warning: gsr_capture_kms_start: recording with hdr requires shader color conversion which might be slow. If this is an issue record with -w portal instead (which converts HDR to SDR)\n");
+    //}
+
+    self->mesa_supports_compute_only_vaapi_copy = self->params.egl->gpu_info.vendor == GSR_GPU_VENDOR_AMD && gl_driver_version_greater_than(&self->params.egl->gpu_info, 24, 3, 6);
 
     frame->width = video_codec_context->width;
     frame->height = video_codec_context->height;
 
     self->video_codec_context = video_codec_context;
+    self->last_time_monitor_check = clock_get_monotonic_seconds();
     return 0;
 }
 
@@ -229,7 +256,7 @@ static void gsr_capture_kms_on_event(gsr_capture *cap, gsr_egl *egl) {
     if(!self->is_x11)
         return;
 
-    XEvent *xev = gsr_egl_get_event_data(egl);
+    XEvent *xev = gsr_window_get_event_data(egl->window);
     gsr_cursor_on_event(&self->x11_cursor, xev);
 }
 
@@ -414,7 +441,7 @@ static gsr_kms_response_item* find_monitor_drm(gsr_capture_kms *self, bool *capt
     }
 
     // Will never happen on wayland unless the target monitor has been disconnected
-    if(!drm_fd) {
+    if(!drm_fd && self->is_x11) {
         drm_fd = find_largest_drm(&self->kms_response);
         *capture_is_combined_plane = true;
     }
@@ -429,7 +456,12 @@ static gsr_kms_response_item* find_cursor_drm_if_on_monitor(gsr_capture_kms *sel
     return cursor_drm_fd;
 }
 
-static void render_drm_cursor(gsr_capture_kms *self, gsr_color_conversion *color_conversion, const gsr_kms_response_item *cursor_drm_fd, vec2i target_pos, float texture_rotation) {
+static void render_drm_cursor(gsr_capture_kms *self, gsr_color_conversion *color_conversion, const gsr_kms_response_item *cursor_drm_fd, vec2i target_pos, float texture_rotation, vec2i output_size) {
+    const vec2d scale = {
+        self->capture_size.x == 0 ? 0 : (double)output_size.x / (double)self->capture_size.x,
+        self->capture_size.y == 0 ? 0 : (double)output_size.y / (double)self->capture_size.y
+    };
+
     const bool cursor_texture_id_is_external = self->params.egl->gpu_info.vendor == GSR_GPU_VENDOR_NVIDIA;
     const vec2i cursor_size = {cursor_drm_fd->width, cursor_drm_fd->height};
 
@@ -458,6 +490,9 @@ static void render_drm_cursor(gsr_capture_kms *self, gsr_color_conversion *color
             break;
     }
 
+    cursor_pos.x *= scale.x;
+    cursor_pos.y *= scale.y;
+
     cursor_pos.x += target_pos.x;
     cursor_pos.y += target_pos.y;
 
@@ -487,34 +522,40 @@ static void render_drm_cursor(gsr_capture_kms *self, gsr_color_conversion *color
         self->params.egl->eglDestroyImage(self->params.egl->egl_display, cursor_image);
 
     self->params.egl->glEnable(GL_SCISSOR_TEST);
-    self->params.egl->glScissor(target_pos.x, target_pos.y, self->capture_size.x, self->capture_size.y);
+    self->params.egl->glScissor(target_pos.x, target_pos.y, output_size.x, output_size.y);
 
     gsr_color_conversion_draw(color_conversion, self->cursor_texture_id,
-        cursor_pos, cursor_size,
+        cursor_pos, (vec2i){cursor_size.x * scale.x, cursor_size.y * scale.y},
         (vec2i){0, 0}, cursor_size,
-        texture_rotation, cursor_texture_id_is_external);
+        texture_rotation, cursor_texture_id_is_external, GSR_SOURCE_COLOR_RGB);
 
     self->params.egl->glDisable(GL_SCISSOR_TEST);
 }
 
-static void render_x11_cursor(gsr_capture_kms *self, gsr_color_conversion *color_conversion, vec2i capture_pos, vec2i target_pos) {
+static void render_x11_cursor(gsr_capture_kms *self, gsr_color_conversion *color_conversion, vec2i capture_pos, vec2i target_pos, vec2i output_size) {
     if(!self->x11_cursor.visible)
         return;
 
-    gsr_cursor_tick(&self->x11_cursor, DefaultRootWindow(self->params.egl->x11.dpy));
+    const vec2d scale = {
+        self->capture_size.x == 0 ? 0 : (double)output_size.x / (double)self->capture_size.x,
+        self->capture_size.y == 0 ? 0 : (double)output_size.y / (double)self->capture_size.y
+    };
+
+    Display *display = gsr_window_get_display(self->params.egl->window);
+    gsr_cursor_tick(&self->x11_cursor, DefaultRootWindow(display));
 
     const vec2i cursor_pos = {
-        target_pos.x + self->x11_cursor.position.x - self->x11_cursor.hotspot.x - capture_pos.x,
-        target_pos.y + self->x11_cursor.position.y - self->x11_cursor.hotspot.y - capture_pos.y
+        target_pos.x + (self->x11_cursor.position.x - self->x11_cursor.hotspot.x - capture_pos.x) * scale.x,
+        target_pos.y + (self->x11_cursor.position.y - self->x11_cursor.hotspot.y - capture_pos.y) * scale.y
     };
 
     self->params.egl->glEnable(GL_SCISSOR_TEST);
-    self->params.egl->glScissor(target_pos.x, target_pos.y, self->capture_size.x, self->capture_size.y);
+    self->params.egl->glScissor(target_pos.x, target_pos.y, output_size.x, output_size.y);
 
     gsr_color_conversion_draw(color_conversion, self->x11_cursor.texture_id,
-        cursor_pos, self->x11_cursor.size,
+        cursor_pos, (vec2i){self->x11_cursor.size.x * scale.x, self->x11_cursor.size.y * scale.y},
         (vec2i){0, 0}, self->x11_cursor.size,
-        0.0f, false);
+        0.0f, false, GSR_SOURCE_COLOR_RGB);
 
     self->params.egl->glDisable(GL_SCISSOR_TEST);
 }
@@ -527,6 +568,55 @@ static void gsr_capture_kms_update_capture_size_change(gsr_capture_kms *self, gs
     }
 }
 
+static void gsr_capture_kms_update_connector_ids(gsr_capture_kms *self) {
+    const double now = clock_get_monotonic_seconds();
+    if(now - self->last_time_monitor_check < FIND_CRTC_BY_NAME_TIMEOUT_SECONDS)
+        return;
+
+    self->last_time_monitor_check = now;
+    /* TODO: Assume for now that there is only 1 framebuffer for all monitors and it doesn't change */
+    if(self->is_x11)
+        return;
+
+    self->monitor_id.num_connector_ids = 0;
+    const gsr_connection_type connection_type = self->is_x11 ? GSR_CONNECTION_X11 : GSR_CONNECTION_DRM;
+    // MonitorCallbackUserdata monitor_callback_userdata = {
+    //     &self->monitor_id,
+    //     self->params.display_to_capture, strlen(self->params.display_to_capture),
+    //     0,
+    // };
+    // for_each_active_monitor_output(self->params.egl->window, self->params.egl->card_path, connection_type, monitor_callback, &monitor_callback_userdata);
+
+    gsr_monitor monitor;
+    if(!get_monitor_by_name(self->params.egl, connection_type, self->params.display_to_capture, &monitor)) {
+        fprintf(stderr, "gsr error: gsr_capture_kms_update_connector_ids: failed to find monitor by name \"%s\"\n", self->params.display_to_capture);
+        return;
+    }
+
+    self->monitor_id.num_connector_ids = 1;
+    self->monitor_id.connector_ids[0] = monitor.connector_id;
+
+    monitor.name = self->params.display_to_capture;
+    self->monitor_rotation = drm_monitor_get_display_server_rotation(self->params.egl->window, &monitor);
+
+    self->capture_pos = monitor.pos;
+    /* Monitor size is already rotated on x11 when the monitor is rotated, no need to apply it ourselves */
+    if(self->is_x11)
+        self->capture_size = monitor.size;
+    else
+        self->capture_size = rotate_capture_size_if_rotated(self, monitor.size);
+}
+
+static void gsr_capture_kms_fail_fast_path_if_not_fast(gsr_capture_kms *self, uint32_t pixel_format) {
+    const uint8_t pixel_format_color_depth_1 = (pixel_format >> 16) & 0xFF;
+    if(!self->fast_path_failed && self->params.egl->gpu_info.vendor == GSR_GPU_VENDOR_AMD && !self->mesa_supports_compute_only_vaapi_copy && (pixel_format_color_depth_1 == '3' || pixel_format_color_depth_1 == '4')) {
+        self->fast_path_failed = true;
+        fprintf(stderr, "gsr warning: gsr_capture_kms_capture: the monitor you are recording is in 10/12-bit color format and your mesa version is <= 24.3.6, composition will be used."
+            " If you experience performance problems in the video then record on a single window on X11 or use portal capture option instead or disable 10/12-bit color option in your desktop environment settings,"
+            " or try to record the monitor on X11 instead (if you aren't already doing that) or update your mesa version.\n");
+    }
+}
+
 static int gsr_capture_kms_capture(gsr_capture *cap, AVFrame *frame, gsr_color_conversion *color_conversion) {
     gsr_capture_kms *self = cap->priv;
 
@@ -546,6 +636,8 @@ static int gsr_capture_kms_capture(gsr_capture *cap, AVFrame *frame, gsr_color_c
         return -1;
     }
 
+    gsr_capture_kms_update_connector_ids(self);
+
     bool capture_is_combined_plane = false;
     const gsr_kms_response_item *drm_fd = find_monitor_drm(self, &capture_is_combined_plane);
     if(!drm_fd) {
@@ -558,13 +650,21 @@ static int gsr_capture_kms_capture(gsr_capture *cap, AVFrame *frame, gsr_color_c
 
     if(!self->performance_error_shown && self->monitor_rotation != GSR_MONITOR_ROT_0 && video_codec_context_is_vaapi(self->video_codec_context) && self->params.egl->gpu_info.vendor == GSR_GPU_VENDOR_AMD) {
         self->performance_error_shown = true;
-        fprintf(stderr,"gsr warning: gsr_capture_kms_capture: the monitor you are recording is rotated, composition will have to be used."
-            " If you are experience performance problems in the video then record a single window on X11 or use portal capture option instead\n");
+        self->fast_path_failed = true;
+        fprintf(stderr, "gsr warning: gsr_capture_kms_capture: the monitor you are recording is rotated, composition will have to be used."
+            " If you experience performance problems in the video then record a single window on X11 or use portal capture option instead\n");
     }
 
-    const float texture_rotation = monitor_rotation_to_radians(self->monitor_rotation);
-    const vec2i target_pos = { max_int(0, frame->width / 2 - self->capture_size.x / 2), max_int(0, frame->height / 2 - self->capture_size.y / 2) };
+    gsr_capture_kms_fail_fast_path_if_not_fast(self, drm_fd->pixel_format);
+
     self->capture_size = rotate_capture_size_if_rotated(self, (vec2i){ drm_fd->src_w, drm_fd->src_h });
+
+    const bool is_scaled = self->params.output_resolution.x > 0 && self->params.output_resolution.y > 0;
+    vec2i output_size = is_scaled ? self->params.output_resolution : self->capture_size;
+    output_size = scale_keep_aspect_ratio(self->capture_size, output_size);
+
+    const float texture_rotation = monitor_rotation_to_radians(self->monitor_rotation);
+    const vec2i target_pos = { max_int(0, frame->width / 2 - output_size.x / 2), max_int(0, frame->height / 2 - output_size.y / 2) };
     gsr_capture_kms_update_capture_size_change(self, color_conversion, target_pos, drm_fd);
 
     vec2i capture_pos = self->capture_pos;
@@ -586,7 +686,7 @@ static int gsr_capture_kms_capture(gsr_capture *cap, AVFrame *frame, gsr_color_c
             pitches[i] = drm_fd->dma_buf[i].pitch;
             modifiers[i] = drm_fd->modifier;
         }
-        if(!vaapi_copy_drm_planes_to_video_surface(self->video_codec_context, frame, (vec2i){capture_pos.x, capture_pos.y}, self->capture_size, target_pos, self->capture_size, drm_fd->pixel_format, (vec2i){drm_fd->width, drm_fd->height}, fds, offsets, pitches, modifiers, drm_fd->num_dma_bufs)) {
+        if(!vaapi_copy_drm_planes_to_video_surface(self->video_codec_context, frame, (vec2i){capture_pos.x, capture_pos.y}, self->capture_size, target_pos, output_size, drm_fd->pixel_format, (vec2i){drm_fd->width, drm_fd->height}, fds, offsets, pitches, modifiers, drm_fd->num_dma_bufs)) {
             fprintf(stderr, "gsr error: gsr_capture_kms_capture: vaapi_copy_drm_planes_to_video_surface failed, falling back to opengl copy. Please report this as an issue at https://github.com/dec05eba/gpu-screen-recorder-issues\n");
             self->fast_path_failed = true;
         }
@@ -602,20 +702,22 @@ static int gsr_capture_kms_capture(gsr_capture *cap, AVFrame *frame, gsr_color_c
         }
 
         gsr_color_conversion_draw(color_conversion, self->external_texture_fallback ? self->external_input_texture_id : self->input_texture_id,
-            target_pos, self->capture_size,
+            target_pos, output_size,
             capture_pos, self->capture_size,
-            texture_rotation, self->external_texture_fallback);
+            texture_rotation, self->external_texture_fallback, GSR_SOURCE_COLOR_RGB);
     }
 
     if(self->params.record_cursor) {
         gsr_kms_response_item *cursor_drm_fd = find_cursor_drm_if_on_monitor(self, drm_fd->connector_id, capture_is_combined_plane);
         // The cursor is handled by x11 on x11 instead of using the cursor drm plane because on prime systems with a dedicated nvidia gpu
         // the cursor plane is not available when the cursor is on the monitor controlled by the nvidia device.
+        // TODO: This doesn't work properly with software cursor on x11 since it will draw the x11 cursor on top of the cursor already in the framebuffer.
+        // Detect if software cursor is used on x11 somehow.
         if(self->is_x11) {
             const vec2i cursor_monitor_offset = self->capture_pos;
-            render_x11_cursor(self, color_conversion, cursor_monitor_offset, target_pos);
+            render_x11_cursor(self, color_conversion, cursor_monitor_offset, target_pos, output_size);
         } else if(cursor_drm_fd) {
-            render_drm_cursor(self, color_conversion, cursor_drm_fd, target_pos, texture_rotation);
+            render_drm_cursor(self, color_conversion, cursor_drm_fd, target_pos, texture_rotation, output_size);
         }
     }
 
@@ -634,11 +736,6 @@ static bool gsr_capture_kms_should_stop(gsr_capture *cap, bool *err) {
     return false;
 }
 
-static gsr_source_color gsr_capture_kms_get_source_color(gsr_capture *cap) {
-    (void)cap;
-    return GSR_SOURCE_COLOR_RGB;
-}
-
 static bool gsr_capture_kms_uses_external_image(gsr_capture *cap) {
     (void)cap;
     return true;
@@ -664,8 +761,8 @@ static bool gsr_capture_kms_set_hdr_metadata(gsr_capture *cap, AVMasteringDispla
     mastering_display_metadata->min_luminance = av_make_q(self->hdr_metadata.hdmi_metadata_type1.min_display_mastering_luminance, 10000);
     mastering_display_metadata->max_luminance = av_make_q(self->hdr_metadata.hdmi_metadata_type1.max_display_mastering_luminance, 1);
 
-    mastering_display_metadata->has_primaries = mastering_display_metadata->display_primaries[0][0].num > 0;
-    mastering_display_metadata->has_luminance = mastering_display_metadata->max_luminance.num > 0;
+    mastering_display_metadata->has_primaries = true;
+    mastering_display_metadata->has_luminance = true;
 
     return true;
 }
@@ -725,7 +822,6 @@ gsr_capture* gsr_capture_kms_create(const gsr_capture_kms_params *params) {
         //.tick = gsr_capture_kms_tick,
         .should_stop = gsr_capture_kms_should_stop,
         .capture = gsr_capture_kms_capture,
-        .get_source_color = gsr_capture_kms_get_source_color,
         .uses_external_image = gsr_capture_kms_uses_external_image,
         .set_hdr_metadata = gsr_capture_kms_set_hdr_metadata,
         //.is_damaged = gsr_capture_kms_is_damaged,