sync code with last improvements from OpenBSD

sys/dev/pci/drm/amd/amdgpu/amdgpu_display.c

@@ -38,6 +38,8 @@
 #include <linux/pci.h>
 #include <linux/pm_runtime.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_damage_helper.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_fb_helper.h>
@@ -493,11 +495,29 @@ bool amdgpu_display_ddc_probe(struct amdgpu_connector *amdgpu_connector,
 	return true;
 }
 
+static int amdgpu_dirtyfb(struct drm_framebuffer *fb, struct drm_file *file,
+			  unsigned int flags, unsigned int color,
+			  struct drm_clip_rect *clips, unsigned int num_clips)
+{
+
+	if (file)
+		return -ENOSYS;
+
+	return drm_atomic_helper_dirtyfb(fb, file, flags, color, clips,
+					 num_clips);
+}
+
 static const struct drm_framebuffer_funcs amdgpu_fb_funcs = {
 	.destroy = drm_gem_fb_destroy,
 	.create_handle = drm_gem_fb_create_handle,
 };
 
+static const struct drm_framebuffer_funcs amdgpu_fb_funcs_atomic = {
+	.destroy = drm_gem_fb_destroy,
+	.create_handle = drm_gem_fb_create_handle,
+	.dirty = amdgpu_dirtyfb
+};
+
 uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev,
 					  uint64_t bo_flags)
 {
@@ -1100,7 +1120,11 @@ static int amdgpu_display_gem_fb_verify_and_init(struct drm_device *dev,
 	if (ret)
 		goto err;
 
-	ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs);
+	if (drm_drv_uses_atomic_modeset(dev))
+		ret = drm_framebuffer_init(dev, &rfb->base,
+					   &amdgpu_fb_funcs_atomic);
+	else
+		ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs);
 
 	if (ret)
 		goto err;

sys/dev/pci/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c

@@ -1269,6 +1269,13 @@ void handle_cursor_update(struct drm_plane *plane,
 	attributes.rotation_angle    = 0;
 	attributes.attribute_flags.value = 0;
 
+	/* Enable cursor degamma ROM on DCN3+ for implicit sRGB degamma in DRM
+	 * legacy gamma setup.
+	 */
+	if (crtc_state->cm_is_degamma_srgb &&
+	    adev->dm.dc->caps.color.dpp.gamma_corr)
+		attributes.attribute_flags.bits.ENABLE_CURSOR_DEGAMMA = 1;
+
 	attributes.pitch = afb->base.pitches[0] / afb->base.format->cpp[0];
 
 	if (crtc_state->stream) {

sys/dev/pci/drm/amd/display/dc/core/amdgpu_dc.c

@@ -1977,12 +1977,12 @@ enum dc_status dc_commit_streams(struct dc *dc,
 		}
 	}
 
-	/* Check for case where we are going from odm 2:1 to max
-	 *  pipe scenario.  For these cases, we will call
-	 *  commit_minimal_transition_state() to exit out of odm 2:1
-	 *  first before processing new streams
+	/* ODM Combine 2:1 power optimization is only applied for single stream
+	 * scenario, it uses extra pipes than needed to reduce power consumption
+	 * We need to switch off this feature to make room for new streams.
 	 */
-	if (stream_count == dc->res_pool->pipe_count) {
+	if (stream_count > dc->current_state->stream_count &&
+			dc->current_state->stream_count == 1) {
 		for (i = 0; i < dc->res_pool->pipe_count; i++) {
 			pipe = &dc->current_state->res_ctx.pipe_ctx[i];
 			if (pipe->next_odm_pipe)
@@ -3361,6 +3361,45 @@ void dc_dmub_update_dirty_rect(struct dc *dc,
 	}
 }
 
+static void wait_for_outstanding_hw_updates(struct dc *dc, const struct dc_state *dc_context)
+{
+/*
+ * This function calls HWSS to wait for any potentially double buffered
+ * operations to complete. It should be invoked as a pre-amble prior
+ * to full update programming before asserting any HW locks.
+ */
+	int pipe_idx;
+	int opp_inst;
+	int opp_count = dc->res_pool->pipe_count;
+	struct hubp *hubp;
+	int mpcc_inst;
+	const struct pipe_ctx *pipe_ctx;
+
+	for (pipe_idx = 0; pipe_idx < dc->res_pool->pipe_count; pipe_idx++) {
+		pipe_ctx = &dc_context->res_ctx.pipe_ctx[pipe_idx];
+
+		if (!pipe_ctx->stream)
+			continue;
+
+		if (pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear)
+			pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear(pipe_ctx->stream_res.tg);
+
+		hubp = pipe_ctx->plane_res.hubp;
+		if (!hubp)
+			continue;
+
+		mpcc_inst = hubp->inst;
+		// MPCC inst is equal to pipe index in practice
+		for (opp_inst = 0; opp_inst < opp_count; opp_inst++) {
+			if (dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst]) {
+				dc->res_pool->mpc->funcs->wait_for_idle(dc->res_pool->mpc, mpcc_inst);
+				dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst] = false;
+				break;
+			}
+		}
+	}
+}
+
 static void commit_planes_for_stream(struct dc *dc,
 		struct dc_surface_update *srf_updates,
 		int surface_count,
@@ -3378,24 +3417,9 @@ static void commit_planes_for_stream(struct dc *dc,
 	// dc->current_state anymore, so we have to cache it before we apply
 	// the new SubVP context
 	subvp_prev_use = false;
-
-
 	dc_z10_restore(dc);
-
-	if (update_type == UPDATE_TYPE_FULL) {
-		/* wait for all double-buffer activity to clear on all pipes */
-		int pipe_idx;
-
-		for (pipe_idx = 0; pipe_idx < dc->res_pool->pipe_count; pipe_idx++) {
-			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[pipe_idx];
-
-			if (!pipe_ctx->stream)
-				continue;
-
-			if (pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear)
-				pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear(pipe_ctx->stream_res.tg);
-		}
-	}
+	if (update_type == UPDATE_TYPE_FULL)
+		wait_for_outstanding_hw_updates(dc, context);
 
 	if (get_seamless_boot_stream_count(context) > 0 && surface_count > 0) {
 		/* Optimize seamless boot flag keeps clocks and watermarks high until

sys/dev/pci/drm/amd/display/dc/dcn10/dcn10_mpc.c

@@ -212,8 +212,9 @@ struct mpcc *mpc1_insert_plane(
 		/* check insert_above_mpcc exist in tree->opp_list */
 		struct mpcc *temp_mpcc = tree->opp_list;
 
-		while (temp_mpcc && temp_mpcc->mpcc_bot != insert_above_mpcc)
-			temp_mpcc = temp_mpcc->mpcc_bot;
+		if (temp_mpcc != insert_above_mpcc)
+			while (temp_mpcc && temp_mpcc->mpcc_bot != insert_above_mpcc)
+				temp_mpcc = temp_mpcc->mpcc_bot;
 		if (temp_mpcc == NULL)
 			return NULL;
 	}

sys/dev/pci/drm/amd/display/dc/dcn20/dcn20_hwseq.c

@@ -1515,17 +1515,6 @@ static void dcn20_update_dchubp_dpp(
 			|| plane_state->update_flags.bits.global_alpha_change
 			|| plane_state->update_flags.bits.per_pixel_alpha_change) {
 		// MPCC inst is equal to pipe index in practice
-		int mpcc_inst = hubp->inst;
-		int opp_inst;
-		int opp_count = dc->res_pool->pipe_count;
-
-		for (opp_inst = 0; opp_inst < opp_count; opp_inst++) {
-			if (dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst]) {
-				dc->res_pool->mpc->funcs->wait_for_idle(dc->res_pool->mpc, mpcc_inst);
-				dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst] = false;
-				break;
-			}
-		}
 		hws->funcs.update_mpcc(dc, pipe_ctx);
 	}
 

sys/dev/pci/drm/amd/display/modules/freesync/freesync.c

@@ -338,7 +338,9 @@ static void apply_below_the_range(struct core_freesync *core_freesync,
 		 *  - Delta for CEIL: delta_from_mid_point_in_us_1
 		 *  - Delta for FLOOR: delta_from_mid_point_in_us_2
 		 */
-		if ((last_render_time_in_us / mid_point_frames_ceil) < in_out_vrr->min_duration_in_us) {
+		if (mid_point_frames_ceil &&
+		    (last_render_time_in_us / mid_point_frames_ceil) <
+		    in_out_vrr->min_duration_in_us) {
 			/* Check for out of range.
 			 * If using CEIL produces a value that is out of range,
 			 * then we are forced to use FLOOR.
@@ -385,8 +387,9 @@ static void apply_below_the_range(struct core_freesync *core_freesync,
 		/* Either we've calculated the number of frames to insert,
 		 * or we need to insert min duration frames
 		 */
-		if (last_render_time_in_us / frames_to_insert <
-				in_out_vrr->min_duration_in_us){
+		if (frames_to_insert &&
+		    (last_render_time_in_us / frames_to_insert) <
+		    in_out_vrr->min_duration_in_us){
 			frames_to_insert -= (frames_to_insert > 1) ?
 					1 : 0;
 		}

sys/dev/pci/drm/i915/gt/intel_engine_types.h

@@ -56,6 +56,7 @@ struct intel_breadcrumbs;
 
 typedef u32 intel_engine_mask_t;
 #define ALL_ENGINES ((intel_engine_mask_t)~0ul)
+#define VIRTUAL_ENGINES BIT(BITS_PER_TYPE(intel_engine_mask_t) - 1)
 
 struct intel_hw_status_page {
 	struct list_head timelines;

sys/dev/pci/drm/i915/gt/uc/intel_guc_submission.c

@@ -5121,6 +5121,11 @@ guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count,
 
 	ve->base.flags = I915_ENGINE_IS_VIRTUAL;
 
+#ifdef notyet
+	BUILD_BUG_ON(ilog2(VIRTUAL_ENGINES) < I915_NUM_ENGINES);
+#endif
+	ve->base.mask = VIRTUAL_ENGINES;
+
 	intel_context_init(&ve->context, &ve->base);
 
 	for (n = 0; n < count; n++) {

sys/dev/pci/drm/i915/gvt/gtt.c

@@ -1179,6 +1179,7 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,
 {
 	const struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
 	kvm_pfn_t pfn;
+	int ret;
 
 	if (!HAS_PAGE_SIZES(vgpu->gvt->gt->i915, I915_GTT_PAGE_SIZE_2M))
 		return 0;
@@ -1188,7 +1189,13 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,
 	pfn = gfn_to_pfn(vgpu->vfio_device.kvm, ops->get_pfn(entry));
 	if (is_error_noslot_pfn(pfn))
 		return -EINVAL;
-	return PageTransHuge(pfn_to_page(pfn));
+
+	if (!pfn_valid(pfn))
+		return -EINVAL;
+
+	ret = PageTransHuge(pfn_to_page(pfn));
+	kvm_release_pfn_clean(pfn);
+	return ret;
 }
 
 static int split_2MB_gtt_entry(struct intel_vgpu *vgpu,
@@ -2880,24 +2887,6 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old)
 	ggtt_invalidate(gvt->gt);
 }
 
-/**
- * intel_vgpu_reset_gtt - reset the all GTT related status
- * @vgpu: a vGPU
- *
- * This function is called from vfio core to reset reset all
- * GTT related status, including GGTT, PPGTT, scratch page.
- *
- */
-void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu)
-{
-	/* Shadow pages are only created when there is no page
-	 * table tracking data, so remove page tracking data after
-	 * removing the shadow pages.
-	 */
-	intel_vgpu_destroy_all_ppgtt_mm(vgpu);
-	intel_vgpu_reset_ggtt(vgpu, true);
-}
-
 /**
  * intel_gvt_restore_ggtt - restore all vGPU's ggtt entries
  * @gvt: intel gvt device

sys/dev/pci/drm/i915/gvt/gtt.h

@@ -224,7 +224,6 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old);
 void intel_vgpu_invalidate_ppgtt(struct intel_vgpu *vgpu);
 
 int intel_gvt_init_gtt(struct intel_gvt *gvt);
-void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu);
 void intel_gvt_clean_gtt(struct intel_gvt *gvt);
 
 struct intel_vgpu_mm *intel_gvt_find_ppgtt_mm(struct intel_vgpu *vgpu,

sys/dev/pci/drm/i915/i915_request.c

@@ -141,9 +141,7 @@ static void i915_fence_release(struct dma_fence *fence)
 	i915_sw_fence_fini(&rq->semaphore);
 
 	/*
-	 * Keep one request on each engine for reserved use under mempressure
-	 * do not use with virtual engines as this really is only needed for
-	 * kernel contexts.
+	 * Keep one request on each engine for reserved use under mempressure.
 	 *
 	 * We do not hold a reference to the engine here and so have to be
 	 * very careful in what rq->engine we poke. The virtual engine is
@@ -173,8 +171,7 @@ static void i915_fence_release(struct dma_fence *fence)
 	 * know that if the rq->execution_mask is a single bit, rq->engine
 	 * can be a physical engine with the exact corresponding mask.
 	 */
-	if (!intel_engine_is_virtual(rq->engine) &&
-	    is_power_of_2(rq->execution_mask) &&
+	if (is_power_of_2(rq->execution_mask) &&
 	    !cmpxchg(&rq->engine->request_pool, NULL, rq))
 		return;
 

sys/dev/pci/if_aq_pci.c

@@ -1,4 +1,4 @@
-/* $OpenBSD: if_aq_pci.c,v 1.23 2023/08/15 08:27:30 miod Exp $ */
+/* $OpenBSD: if_aq_pci.c,v 1.24 2023/09/19 14:14:35 jsg Exp $ */
 /*	$NetBSD: if_aq.c,v 1.27 2021/06/16 00:21:18 riastradh Exp $	*/
 
 /*
@@ -2606,7 +2606,7 @@ aq_hw_init_rx_path(struct aq_softc *sc)
 		    0, AQ2_RPF_TAG_VLAN_MASK | AQ2_RPF_TAG_UNTAG_MASK,
 		    AQ2_ART_ACTION_DROP);
 
-		for (int i = 0; i < 8; i++) {
+		for (i = 0; i < 8; i++) {
 			aq2_filter_art_set(sc, AQ2_RPF_INDEX_PCP_TO_TC + i,
 			    (i << AQ2_RPF_TAG_PCP_SHIFT), AQ2_RPF_TAG_PCP_MASK,
 			    AQ2_ART_ACTION_ASSIGN_TC(i % sc->sc_nqueues));