Merge tag 'drm-intel-fixes-2024-12-11' of https://gitlab.freedesktop.org/drm/i915/kernel into drm-fixes

- Don't use indexed register writes needlessly [dsb] (Ville Syrjälä)
- Stop using non-posted DSB writes for legacy LUT [color] (Ville Syrjälä)
- Fix NULL pointer dereference in capture_engine (Eugene Kobyak)
- Fix memory leak by correcting cache object name in error handler (Jiasheng Jiang)

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Tvrtko Ursulin <tursulin@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/Z1nULMrutE4HERvB@linux

Author: airlied

drivers/gpu/drm/i915/display/intel_color.c

@@ -1343,6 +1343,17 @@ static void ilk_lut_write(const struct intel_crtc_state *crtc_state,
 		intel_de_write_fw(display, reg, val);
 }
 
+static void ilk_lut_write_indexed(const struct intel_crtc_state *crtc_state,
+				  i915_reg_t reg, u32 val)
+{
+	struct intel_display *display = to_intel_display(crtc_state);
+
+	if (crtc_state->dsb_color_vblank)
+		intel_dsb_reg_write_indexed(crtc_state->dsb_color_vblank, reg, val);
+	else
+		intel_de_write_fw(display, reg, val);
+}
+
 static void ilk_load_lut_8(const struct intel_crtc_state *crtc_state,
 			   const struct drm_property_blob *blob)
 {
@@ -1357,19 +1368,29 @@ static void ilk_load_lut_8(const struct intel_crtc_state *crtc_state,
 	lut = blob->data;
 
 	/*
-	 * DSB fails to correctly load the legacy LUT
-	 * unless we either write each entry twice,
-	 * or use non-posted writes
+	 * DSB fails to correctly load the legacy LUT unless
+	 * we either write each entry twice when using posted
+	 * writes, or we use non-posted writes.
+	 *
+	 * If palette anti-collision is active during LUT
+	 * register writes:
+	 * - posted writes simply get dropped and thus the LUT
+	 *   contents may not be correctly updated
+	 * - non-posted writes are blocked and thus the LUT
+	 *   contents are always correct, but simultaneous CPU
+	 *   MMIO access will start to fail
+	 *
+	 * Choose the lesser of two evils and use posted writes.
+	 * Using posted writes is also faster, even when having
+	 * to write each register twice.
 	 */
-	if (crtc_state->dsb_color_vblank)
-		intel_dsb_nonpost_start(crtc_state->dsb_color_vblank);
-
-	for (i = 0; i < 256; i++)
+	for (i = 0; i < 256; i++) {
 		ilk_lut_write(crtc_state, LGC_PALETTE(pipe, i),
 			      i9xx_lut_8(&lut[i]));
-
-	if (crtc_state->dsb_color_vblank)
-		intel_dsb_nonpost_end(crtc_state->dsb_color_vblank);
+		if (crtc_state->dsb_color_vblank)
+			ilk_lut_write(crtc_state, LGC_PALETTE(pipe, i),
+				      i9xx_lut_8(&lut[i]));
+	}
 }
 
 static void ilk_load_lut_10(const struct intel_crtc_state *crtc_state,
@@ -1458,8 +1479,8 @@ static void bdw_load_lut_10(const struct intel_crtc_state *crtc_state,
 		      prec_index);
 
 	for (i = 0; i < lut_size; i++)
-		ilk_lut_write(crtc_state, PREC_PAL_DATA(pipe),
-			      ilk_lut_10(&lut[i]));
+		ilk_lut_write_indexed(crtc_state, PREC_PAL_DATA(pipe),
+				      ilk_lut_10(&lut[i]));
 
 	/*
 	 * Reset the index, otherwise it prevents the legacy palette to be
@@ -1612,16 +1633,16 @@ static void glk_load_degamma_lut(const struct intel_crtc_state *crtc_state,
 		 * ToDo: Extend to max 7.0. Enable 32 bit input value
 		 * as compared to just 16 to achieve this.
 		 */
-		ilk_lut_write(crtc_state, PRE_CSC_GAMC_DATA(pipe),
-			      DISPLAY_VER(display) >= 14 ?
-			      mtl_degamma_lut(&lut[i]) : glk_degamma_lut(&lut[i]));
+		ilk_lut_write_indexed(crtc_state, PRE_CSC_GAMC_DATA(pipe),
+				      DISPLAY_VER(display) >= 14 ?
+				      mtl_degamma_lut(&lut[i]) : glk_degamma_lut(&lut[i]));
 	}
 
 	/* Clamp values > 1.0. */
 	while (i++ < glk_degamma_lut_size(display))
-		ilk_lut_write(crtc_state, PRE_CSC_GAMC_DATA(pipe),
-			      DISPLAY_VER(display) >= 14 ?
-			      1 << 24 : 1 << 16);
+		ilk_lut_write_indexed(crtc_state, PRE_CSC_GAMC_DATA(pipe),
+				      DISPLAY_VER(display) >= 14 ?
+				      1 << 24 : 1 << 16);
 
 	ilk_lut_write(crtc_state, PRE_CSC_GAMC_INDEX(pipe), 0);
 }
@@ -1687,10 +1708,10 @@ icl_program_gamma_superfine_segment(const struct intel_crtc_state *crtc_state)
 	for (i = 0; i < 9; i++) {
 		const struct drm_color_lut *entry = &lut[i];
 
-		ilk_lut_write(crtc_state, PREC_PAL_MULTI_SEG_DATA(pipe),
-			      ilk_lut_12p4_ldw(entry));
-		ilk_lut_write(crtc_state, PREC_PAL_MULTI_SEG_DATA(pipe),
-			      ilk_lut_12p4_udw(entry));
+		ilk_lut_write_indexed(crtc_state, PREC_PAL_MULTI_SEG_DATA(pipe),
+				      ilk_lut_12p4_ldw(entry));
+		ilk_lut_write_indexed(crtc_state, PREC_PAL_MULTI_SEG_DATA(pipe),
+				      ilk_lut_12p4_udw(entry));
 	}
 
 	ilk_lut_write(crtc_state, PREC_PAL_MULTI_SEG_INDEX(pipe),
@@ -1726,10 +1747,10 @@ icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state)
 	for (i = 1; i < 257; i++) {
 		entry = &lut[i * 8];
 
-		ilk_lut_write(crtc_state, PREC_PAL_DATA(pipe),
-			      ilk_lut_12p4_ldw(entry));
-		ilk_lut_write(crtc_state, PREC_PAL_DATA(pipe),
-			      ilk_lut_12p4_udw(entry));
+		ilk_lut_write_indexed(crtc_state, PREC_PAL_DATA(pipe),
+				      ilk_lut_12p4_ldw(entry));
+		ilk_lut_write_indexed(crtc_state, PREC_PAL_DATA(pipe),
+				      ilk_lut_12p4_udw(entry));
 	}
 
 	/*
@@ -1747,10 +1768,10 @@ icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state)
 	for (i = 0; i < 256; i++) {
 		entry = &lut[i * 8 * 128];
 
-		ilk_lut_write(crtc_state, PREC_PAL_DATA(pipe),
-			      ilk_lut_12p4_ldw(entry));
-		ilk_lut_write(crtc_state, PREC_PAL_DATA(pipe),
-			      ilk_lut_12p4_udw(entry));
+		ilk_lut_write_indexed(crtc_state, PREC_PAL_DATA(pipe),
+				      ilk_lut_12p4_ldw(entry));
+		ilk_lut_write_indexed(crtc_state, PREC_PAL_DATA(pipe),
+				      ilk_lut_12p4_udw(entry));
 	}
 
 	ilk_lut_write(crtc_state, PREC_PAL_INDEX(pipe),

drivers/gpu/drm/i915/display/intel_dsb.c

@@ -273,16 +273,20 @@ static bool intel_dsb_prev_ins_is_indexed_write(struct intel_dsb *dsb, i915_reg_
 }
 
 /**
- * intel_dsb_reg_write() - Emit register wriite to the DSB context
+ * intel_dsb_reg_write_indexed() - Emit register wriite to the DSB context
  * @dsb: DSB context
  * @reg: register address.
  * @val: value.
  *
  * This function is used for writing register-value pair in command
  * buffer of DSB.
+ *
+ * Note that indexed writes are slower than normal MMIO writes
+ * for a small number (less than 5 or so) of writes to the same
+ * register.
  */
-void intel_dsb_reg_write(struct intel_dsb *dsb,
-			 i915_reg_t reg, u32 val)
+void intel_dsb_reg_write_indexed(struct intel_dsb *dsb,
+				 i915_reg_t reg, u32 val)
 {
 	/*
 	 * For example the buffer will look like below for 3 dwords for auto
@@ -340,6 +344,15 @@ void intel_dsb_reg_write(struct intel_dsb *dsb,
 	}
 }
 
+void intel_dsb_reg_write(struct intel_dsb *dsb,
+			 i915_reg_t reg, u32 val)
+{
+	intel_dsb_emit(dsb, val,
+		       (DSB_OPCODE_MMIO_WRITE << DSB_OPCODE_SHIFT) |
+		       (DSB_BYTE_EN << DSB_BYTE_EN_SHIFT) |
+		       i915_mmio_reg_offset(reg));
+}
+
 static u32 intel_dsb_mask_to_byte_en(u32 mask)
 {
 	return (!!(mask & 0xff000000) << 3 |

drivers/gpu/drm/i915/display/intel_dsb.h

@@ -34,6 +34,8 @@ void intel_dsb_finish(struct intel_dsb *dsb);
 void intel_dsb_cleanup(struct intel_dsb *dsb);
 void intel_dsb_reg_write(struct intel_dsb *dsb,
 			 i915_reg_t reg, u32 val);
+void intel_dsb_reg_write_indexed(struct intel_dsb *dsb,
+				 i915_reg_t reg, u32 val);
 void intel_dsb_reg_write_masked(struct intel_dsb *dsb,
 				i915_reg_t reg, u32 mask, u32 val);
 void intel_dsb_noop(struct intel_dsb *dsb, int count);

drivers/gpu/drm/i915/i915_gpu_error.c

@@ -1643,9 +1643,21 @@ capture_engine(struct intel_engine_cs *engine,
 		return NULL;
 
 	intel_engine_get_hung_entity(engine, &ce, &rq);
-	if (rq && !i915_request_started(rq))
-		drm_info(&engine->gt->i915->drm, "Got hung context on %s with active request %lld:%lld [0x%04X] not yet started\n",
-			 engine->name, rq->fence.context, rq->fence.seqno, ce->guc_id.id);
+	if (rq && !i915_request_started(rq)) {
+		/*
+		 * We want to know also what is the guc_id of the context,
+		 * but if we don't have the context reference, then skip
+		 * printing it.
+		 */
+		if (ce)
+			drm_info(&engine->gt->i915->drm,
+				 "Got hung context on %s with active request %lld:%lld [0x%04X] not yet started\n",
+				 engine->name, rq->fence.context, rq->fence.seqno, ce->guc_id.id);
+		else
+			drm_info(&engine->gt->i915->drm,
+				 "Got hung context on %s with active request %lld:%lld not yet started\n",
+				 engine->name, rq->fence.context, rq->fence.seqno);
+	}
 
 	if (rq) {
 		capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL);

drivers/gpu/drm/i915/i915_scheduler.c

@@ -506,6 +506,6 @@ int __init i915_scheduler_module_init(void)
 	return 0;
 
 err_priorities:
-	kmem_cache_destroy(slab_priorities);
+	kmem_cache_destroy(slab_dependencies);
 	return -ENOMEM;
 }