drm fixes for 5.12-rc4

ttm:
 - Make ttm_bo_unpin() not wraparound on too many unpins.
 
 omap:
 - Fix coccicheck warning in omap.
 
 amdgpu:
 - DCN 3.0 gamma fixes
 - DCN 2.1 corrupt screen fix
 
 i915:
 - Workaround async flip + VT-d frame corruption on HSW/BDW
 - Fix NMI watchdog crash due to uninitialized OA buffer use on gen12+
 
 nouveau:
 - workaround oops with bo syncing
 -----BEGIN PGP SIGNATURE-----
 
 iQIcBAABAgAGBQJgU/RHAAoJEAx081l5xIa+ydgP/0Z/SrTj5MItgYmaBveXzTvR
 88qfdSnBXtvblcfYPCyI4hk2OKeHV26ktsQj0yi74ad6bZGXx7XZrliHIy1Of2jX
 4wP2f5J3gstj2BIEKEf7lvtR3mSwItt1V8V5mOrkCqWB2g6AusY/0KhEOjJzkJ+K
 xRYeqJFwqAa3dGi437r6P5mtqbohMcDeamOSlTLu0slOssjmKGfCZd5fAZhAk3q9
 hNWppNKGJyRXfSYoPHhqxuUr70W1mxp3/PfmZ4W/Jz9/jFt5zj5Erlds5tvYFJ4D
 c/PcOOI19CwPVFgeUfF/gq7J/FMHzo7E4Vj43Y9hzZsN/oDiF6/RMifggdjuCc0b
 uIx0IaUivpDUAb93O5BhWl/ZnYu166Cb//RgW8pF9KxInbOgvQuKyCwCcAQ115v+
 zZLbE41Hjvh4iojXoetfZ5qik3uuAQaISMQakfZ0YRpi57gt/MYX2/y9jjJnqfOa
 SvTsNlZstOj/04jXGG+ZubODb9GV2EeFsVy0ByVJyjTTKJL+ILelbazTksIQpYXv
 XNZ0KdGQwEHmCZU/s5TcE1/VAIfKUKoejjXjyYsdJPbIFMX3/16K7bPbW6GZLlC/
 w7fEXJ07ow79dVFAoy+irdwDqpGuTtP4uRk5R/MfCN+Avgw67VK0VxdsvoPuk9zq
 S6N+/DDHeQLztvbf86O4
 =r/pg
 -----END PGP SIGNATURE-----

Merge tag 'drm-fixes-2021-03-19' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Regular fixes pull, pretty small set of fixes, a couple of i915 and
  amdgpu, one ttm, one nouveau and one omap. Probably smaller than usual
  for this time, so we'll see if something pops up next week or if this
  will continue to stay small.

  Summary:

  ttm:
   - Make ttm_bo_unpin() not wraparound on too many unpins

  omap:
   - Fix coccicheck warning in omap

  amdgpu:
   - DCN 3.0 gamma fixes
   - DCN 2.1 corrupt screen fix

  i915:
   - Workaround async flip + VT-d frame corruption on HSW/BDW
   - Fix NMI watchdog crash due to uninitialized OA buffer use on gen12+

  nouveau:
   - workaround oops with bo syncing"

* tag 'drm-fixes-2021-03-19' of git://anongit.freedesktop.org/drm/drm:
  nouveau: Skip unvailable ttm page entries
  drm/amd/display: Remove MPC gamut remap logic for DCN30
  drm/amd/display: Correct algorithm for reversed gamma
  drm/omap: dsi: fix unsigned expression compared with zero
  i915/perf: Start hrtimer only if sampling the OA buffer
  drm/i915: Workaround async flip + VT-d corruption on HSW/BDW
  drm/amd/display: Copy over soc values before bounding box creation
  drm/ttm: make ttm_bo_unpin more defensive

drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c

@@ -1507,38 +1507,8 @@ static void dcn20_update_dchubp_dpp(
 	if (pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed
 			|| pipe_ctx->stream->update_flags.bits.gamut_remap
 			|| pipe_ctx->stream->update_flags.bits.out_csc) {
-		struct mpc *mpc = pipe_ctx->stream_res.opp->ctx->dc->res_pool->mpc;
-
-		if (mpc->funcs->set_gamut_remap) {
-			int i;
-			int mpcc_id = hubp->inst;
-			struct mpc_grph_gamut_adjustment adjust;
-			bool enable_remap_dpp = false;
-
-			memset(&adjust, 0, sizeof(adjust));
-			adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_BYPASS;
-
-			/* save the enablement of gamut remap for dpp */
-			enable_remap_dpp = pipe_ctx->stream->gamut_remap_matrix.enable_remap;
-
-			/* force bypass gamut remap for dpp/cm */
-			pipe_ctx->stream->gamut_remap_matrix.enable_remap = false;
-			dc->hwss.program_gamut_remap(pipe_ctx);
-
-			/* restore gamut remap flag and use this remap into mpc */
-			pipe_ctx->stream->gamut_remap_matrix.enable_remap = enable_remap_dpp;
-
-			/* build remap matrix for top plane if enabled */
-			if (enable_remap_dpp && pipe_ctx->top_pipe == NULL) {
-					adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_SW;
-					for (i = 0; i < CSC_TEMPERATURE_MATRIX_SIZE; i++)
-						adjust.temperature_matrix[i] =
-								pipe_ctx->stream->gamut_remap_matrix.matrix[i];
-			}
-			mpc->funcs->set_gamut_remap(mpc, mpcc_id, &adjust);
-		} else
-			/* dpp/cm gamut remap*/
-			dc->hwss.program_gamut_remap(pipe_ctx);
+		/* dpp/cm gamut remap*/
+		dc->hwss.program_gamut_remap(pipe_ctx);
 
 		/*call the dcn2 method which uses mpc csc*/
 		dc->hwss.program_output_csc(dc,

drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c

@@ -1595,6 +1595,11 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
 	dcn2_1_soc.num_chans = bw_params->num_channels;
 
 	ASSERT(clk_table->num_entries);
+	/* Copy dcn2_1_soc.clock_limits to clock_limits to avoid copying over null states later */
+	for (i = 0; i < dcn2_1_soc.num_states + 1; i++) {
+		clock_limits[i] = dcn2_1_soc.clock_limits[i];
+	}
+
 	for (i = 0; i < clk_table->num_entries; i++) {
 		/* loop backwards*/
 		for (closest_clk_lvl = 0, j = dcn2_1_soc.num_states - 1; j >= 0; j--) {

drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c

@@ -113,6 +113,7 @@ bool cm3_helper_translate_curve_to_hw_format(
 	struct pwl_result_data *rgb_resulted;
 	struct pwl_result_data *rgb;
 	struct pwl_result_data *rgb_plus_1;
+	struct pwl_result_data *rgb_minus_1;
 	struct fixed31_32 end_value;
 
 	int32_t region_start, region_end;
@@ -140,7 +141,7 @@ bool cm3_helper_translate_curve_to_hw_format(
 		region_start = -MAX_LOW_POINT;
 		region_end   = NUMBER_REGIONS - MAX_LOW_POINT;
 	} else {
-		/* 10 segments
+		/* 11 segments
 		 * segment is from 2^-10 to 2^0
 		 * There are less than 256 points, for optimization
 		 */
@@ -154,9 +155,10 @@ bool cm3_helper_translate_curve_to_hw_format(
 		seg_distr[7] = 4;
 		seg_distr[8] = 4;
 		seg_distr[9] = 4;
+		seg_distr[10] = 1;
 
 		region_start = -10;
-		region_end = 0;
+		region_end = 1;
 	}
 
 	for (i = region_end - region_start; i < MAX_REGIONS_NUMBER ; i++)
@@ -189,6 +191,10 @@ bool cm3_helper_translate_curve_to_hw_format(
 	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
 	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
 
+	rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red;
+	rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green;
+	rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue;
+
 	// All 3 color channels have same x
 	corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2),
 					     dc_fixpt_from_int(region_start));
@@ -259,15 +265,18 @@ bool cm3_helper_translate_curve_to_hw_format(
 
 	rgb = rgb_resulted;
 	rgb_plus_1 = rgb_resulted + 1;
+	rgb_minus_1 = rgb;
 
 	i = 1;
 	while (i != hw_points + 1) {
-		if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
-			rgb_plus_1->red = rgb->red;
-		if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
-			rgb_plus_1->green = rgb->green;
-		if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
-			rgb_plus_1->blue = rgb->blue;
+		if (i >= hw_points - 1) {
+			if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
+				rgb_plus_1->red = dc_fixpt_add(rgb->red, rgb_minus_1->delta_red);
+			if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
+				rgb_plus_1->green = dc_fixpt_add(rgb->green, rgb_minus_1->delta_green);
+			if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
+				rgb_plus_1->blue = dc_fixpt_add(rgb->blue, rgb_minus_1->delta_blue);
+		}
 
 		rgb->delta_red   = dc_fixpt_sub(rgb_plus_1->red,   rgb->red);
 		rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
@@ -283,6 +292,7 @@ bool cm3_helper_translate_curve_to_hw_format(
 		}
 
 		++rgb_plus_1;
+		rgb_minus_1 = rgb;
 		++rgb;
 		++i;
 	}

drivers/gpu/drm/i915/i915_perf.c

@@ -603,7 +603,6 @@ static int append_oa_sample(struct i915_perf_stream *stream,
 {
 	int report_size = stream->oa_buffer.format_size;
 	struct drm_i915_perf_record_header header;
-	u32 sample_flags = stream->sample_flags;
 
 	header.type = DRM_I915_PERF_RECORD_SAMPLE;
 	header.pad = 0;
@@ -617,10 +616,8 @@ static int append_oa_sample(struct i915_perf_stream *stream,
 		return -EFAULT;
 	buf += sizeof(header);
 
-	if (sample_flags & SAMPLE_OA_REPORT) {
-		if (copy_to_user(buf, report, report_size))
-			return -EFAULT;
-	}
+	if (copy_to_user(buf, report, report_size))
+		return -EFAULT;
 
 	(*offset) += header.size;
 
@@ -2682,7 +2679,7 @@ static void i915_oa_stream_enable(struct i915_perf_stream *stream)
 
 	stream->perf->ops.oa_enable(stream);
 
-	if (stream->periodic)
+	if (stream->sample_flags & SAMPLE_OA_REPORT)
 		hrtimer_start(&stream->poll_check_timer,
 			      ns_to_ktime(stream->poll_oa_period),
 			      HRTIMER_MODE_REL_PINNED);
@@ -2745,7 +2742,7 @@ static void i915_oa_stream_disable(struct i915_perf_stream *stream)
 {
 	stream->perf->ops.oa_disable(stream);
 
-	if (stream->periodic)
+	if (stream->sample_flags & SAMPLE_OA_REPORT)
 		hrtimer_cancel(&stream->poll_check_timer);
 }
 
@@ -3028,7 +3025,7 @@ static ssize_t i915_perf_read(struct file *file,
 	 * disabled stream as an error. In particular it might otherwise lead
 	 * to a deadlock for blocking file descriptors...
 	 */
-	if (!stream->enabled)
+	if (!stream->enabled || !(stream->sample_flags & SAMPLE_OA_REPORT))
 		return -EIO;
 
 	if (!(file->f_flags & O_NONBLOCK)) {

drivers/gpu/drm/i915/i915_reg.h

@@ -3316,7 +3316,18 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 
 #define ILK_DISPLAY_CHICKEN1	_MMIO(0x42000)
 #define   ILK_FBCQ_DIS		(1 << 22)
-#define	  ILK_PABSTRETCH_DIS	(1 << 21)
+#define   ILK_PABSTRETCH_DIS	REG_BIT(21)
+#define   ILK_SABSTRETCH_DIS	REG_BIT(20)
+#define   IVB_PRI_STRETCH_MAX_MASK	REG_GENMASK(21, 20)
+#define   IVB_PRI_STRETCH_MAX_X8	REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 0)
+#define   IVB_PRI_STRETCH_MAX_X4	REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 1)
+#define   IVB_PRI_STRETCH_MAX_X2	REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 2)
+#define   IVB_PRI_STRETCH_MAX_X1	REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 3)
+#define   IVB_SPR_STRETCH_MAX_MASK	REG_GENMASK(19, 18)
+#define   IVB_SPR_STRETCH_MAX_X8	REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 0)
+#define   IVB_SPR_STRETCH_MAX_X4	REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 1)
+#define   IVB_SPR_STRETCH_MAX_X2	REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 2)
+#define   IVB_SPR_STRETCH_MAX_X1	REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 3)
 
 
 /*
@@ -8039,6 +8050,16 @@ enum {
 
 #define _CHICKEN_PIPESL_1_A	0x420b0
 #define _CHICKEN_PIPESL_1_B	0x420b4
+#define  HSW_PRI_STRETCH_MAX_MASK	REG_GENMASK(28, 27)
+#define  HSW_PRI_STRETCH_MAX_X8		REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 0)
+#define  HSW_PRI_STRETCH_MAX_X4		REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 1)
+#define  HSW_PRI_STRETCH_MAX_X2		REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 2)
+#define  HSW_PRI_STRETCH_MAX_X1		REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 3)
+#define  HSW_SPR_STRETCH_MAX_MASK	REG_GENMASK(26, 25)
+#define  HSW_SPR_STRETCH_MAX_X8		REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 0)
+#define  HSW_SPR_STRETCH_MAX_X4		REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 1)
+#define  HSW_SPR_STRETCH_MAX_X2		REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 2)
+#define  HSW_SPR_STRETCH_MAX_X1		REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 3)
 #define  HSW_FBCQ_DIS			(1 << 22)
 #define  BDW_DPRS_MASK_VBLANK_SRD	(1 << 0)
 #define CHICKEN_PIPESL_1(pipe) _MMIO_PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B)

drivers/gpu/drm/i915/intel_pm.c

@@ -7245,11 +7245,16 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv)
 	intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR1_1,
 		   intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR1_1) | DPA_MASK_VBLANK_SRD);
 
-	/* WaPsrDPRSUnmaskVBlankInSRD:bdw */
 	for_each_pipe(dev_priv, pipe) {
+		/* WaPsrDPRSUnmaskVBlankInSRD:bdw */
 		intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe),
 			   intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe)) |
 			   BDW_DPRS_MASK_VBLANK_SRD);
+
+		/* Undocumented but fixes async flip + VT-d corruption */
+		if (intel_vtd_active())
+			intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe),
+					 HSW_PRI_STRETCH_MAX_MASK, HSW_PRI_STRETCH_MAX_X1);
 	}
 
 	/* WaVSRefCountFullforceMissDisable:bdw */
@@ -7285,11 +7290,20 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv)
 
 static void hsw_init_clock_gating(struct drm_i915_private *dev_priv)
 {
+	enum pipe pipe;
+
 	/* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */
 	intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A),
 		   intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A)) |
 		   HSW_FBCQ_DIS);
 
+	for_each_pipe(dev_priv, pipe) {
+		/* Undocumented but fixes async flip + VT-d corruption */
+		if (intel_vtd_active())
+			intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe),
+					 HSW_PRI_STRETCH_MAX_MASK, HSW_PRI_STRETCH_MAX_X1);
+	}
+
 	/* This is required by WaCatErrorRejectionIssue:hsw */
 	intel_uncore_write(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
 		   intel_uncore_read(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |

drivers/gpu/drm/nouveau/nouveau_bo.c

@@ -551,6 +551,10 @@ nouveau_bo_sync_for_device(struct nouveau_bo *nvbo)
 
 	if (!ttm_dma)
 		return;
+	if (!ttm_dma->pages) {
+		NV_DEBUG(drm, "ttm_dma 0x%p: pages NULL\n", ttm_dma);
+		return;
+	}
 
 	/* Don't waste time looping if the object is coherent */
 	if (nvbo->force_coherent)
@@ -583,6 +587,10 @@ nouveau_bo_sync_for_cpu(struct nouveau_bo *nvbo)
 
 	if (!ttm_dma)
 		return;
+	if (!ttm_dma->pages) {
+		NV_DEBUG(drm, "ttm_dma 0x%p: pages NULL\n", ttm_dma);
+		return;
+	}
 
 	/* Don't waste time looping if the object is coherent */
 	if (nvbo->force_coherent)

drivers/gpu/drm/omapdrm/dss/dsi.c

@@ -2149,11 +2149,12 @@ static int dsi_vc_send_short(struct dsi_data *dsi, int vc,
 			     const struct mipi_dsi_msg *msg)
 {
 	struct mipi_dsi_packet pkt;
+	int ret;
 	u32 r;
 
-	r = mipi_dsi_create_packet(&pkt, msg);
-	if (r < 0)
-		return r;
+	ret = mipi_dsi_create_packet(&pkt, msg);
+	if (ret < 0)
+		return ret;
 
 	WARN_ON(!dsi_bus_is_locked(dsi));
 

include/drm/ttm/ttm_bo_api.h

@@ -612,9 +612,11 @@ static inline void ttm_bo_pin(struct ttm_buffer_object *bo)
 static inline void ttm_bo_unpin(struct ttm_buffer_object *bo)
 {
 	dma_resv_assert_held(bo->base.resv);
-	WARN_ON_ONCE(!bo->pin_count);
 	WARN_ON_ONCE(!kref_read(&bo->kref));
-	--bo->pin_count;
+	if (bo->pin_count)
+		--bo->pin_count;
+	else
+		WARN_ON_ONCE(true);
 }
 
 int ttm_mem_evict_first(struct ttm_bo_device *bdev,