Merge tag 'drm-intel-next-2020-08-24-1' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes: - Introduce a mechanism to extend execbuf2 (Lionel) - Add syncobj timeline support (Lionel) Driver Changes: - Limit stolen mem usage on the compressed frame buffer (Ville) - Some clean-up around display's cdclk (Ville) - Some DDI changes for better DP link training according to spec (Imre) - Provide the perf pmu.module (Chris) - Remove dobious Valleyview PCI IDs (Alexei) - Add new display power saving feature for gen12+ called HOBL (Jose) - Move SKL's clock gating w/a to skl_init_clock_gating() (Ville) - Rocket Lake display additions (Matt) - Selftest: temporarily downgrade on severity of frequency scaling tests (Chris) - Introduce a new display workaround for fixing FLR related issues on new PCH. (Jose) - Temporarily disable FBC on TGL. It was the culprit of random underruns. (Uma). - Copy default modparams to mock i915_device (Chris) - Add compiler paranoia for checking HWSP values (Chris) - Remove useless gen check before calling intel_rps_boost (Chris) - Fix a null pointer dereference (Chris) - Add a couple of missing i915_active_fini() (Chris) - Update TGL display power's bw_buddy table according to update spec (Matt) - Fix couple wrong return values (Tianjia) - Selftest: Avoid passing random 0 into ilog2 (George) - Many Tiger Lake display fixes and improvements for Type-C and DP compliance (Imre, Jose) - Start the addition of PSR2 selective fetch (Jose) - Update a few DMC and HuC firmware versions (Jose) - Add gen11+ w/a to fix underuns (Matt) - Fix cmd parser desc matching with mask (Mika) Signed-off-by: Dave Airlie <airlied@redhat.com> From: Rodrigo Vivi <rodrigo.vivi@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200826232733.GA129053@intel.com
author: Dave Airlie <airlied@redhat.com> 2020-08-28 06:51:30 +0300
committer: Dave Airlie <airlied@redhat.com> 2020-08-28 07:09:31 +0300
commit: 3393649977f9a8847c659e282ea290d4b703295c (patch)
tree: 6590e13d360b3379d5cf16e6d1b99ba34519be99 /drivers/gpu/drm
parent: cbc2e82932ae01d3e8e81dd17b9e8ef8564c606e (diff)
parent: ced026e959bec5046afa310d6474e147b6294da2 (diff)
download: linux-3393649977f9a8847c659e282ea290d4b703295c.tar.xz
36 files changed, 893 insertions, 244 deletions
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index bb91dace304a..9d6cacbdb691 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -2677,7 +2677,7 @@ void intel_update_cdclk(struct drm_i915_private *dev_priv)
 	 */
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
 		intel_de_write(dev_priv, GMBUSFREQ_VLV,
-		               DIV_ROUND_UP(dev_priv->cdclk.hw.cdclk, 1000));
+			       DIV_ROUND_UP(dev_priv->cdclk.hw.cdclk, 1000));
 }
 
 static int cnp_rawclk(struct drm_i915_private *dev_priv)
@@ -2903,9 +2903,10 @@ void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv)
 		dev_priv->display.get_cdclk = i85x_get_cdclk;
 	else if (IS_I845G(dev_priv))
 		dev_priv->display.get_cdclk = fixed_200mhz_get_cdclk;
-	else { /* 830 */
-		drm_WARN(&dev_priv->drm, !IS_I830(dev_priv),
-			 "Unknown platform. Assuming 133 MHz CDCLK\n");
+	else if (IS_I830(dev_priv))
+		dev_priv->display.get_cdclk = fixed_133mhz_get_cdclk;
+
+	if (drm_WARN(&dev_priv->drm, !dev_priv->display.get_cdclk,
+		     "Unknown platform. Assuming 133 MHz CDCLK\n"))
 		dev_priv->display.get_cdclk = fixed_133mhz_get_cdclk;
-	}
 }
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.h b/drivers/gpu/drm/i915/display/intel_cdclk.h
index 5731806e4cee..6b31fde4be16 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.h
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.h
@@ -17,8 +17,8 @@ struct intel_atomic_state;
 struct intel_crtc_state;
 
 struct intel_cdclk_vals {
-	u16 refclk;
 	u32 cdclk;
+	u16 refclk;
 	u8 divider;	/* CD2X divider * 2 */
 	u8 ratio;
 };
diff --git a/drivers/gpu/drm/i915/display/intel_csr.c b/drivers/gpu/drm/i915/display/intel_csr.c
index f22a7645c249..d5db16764619 100644
--- a/drivers/gpu/drm/i915/display/intel_csr.c
+++ b/drivers/gpu/drm/i915/display/intel_csr.c
@@ -40,12 +40,12 @@
 
 #define GEN12_CSR_MAX_FW_SIZE		ICL_CSR_MAX_FW_SIZE
 
-#define RKL_CSR_PATH			"i915/rkl_dmc_ver2_01.bin"
-#define RKL_CSR_VERSION_REQUIRED	CSR_VERSION(2, 1)
+#define RKL_CSR_PATH			"i915/rkl_dmc_ver2_02.bin"
+#define RKL_CSR_VERSION_REQUIRED	CSR_VERSION(2, 2)
 MODULE_FIRMWARE(RKL_CSR_PATH);
 
-#define TGL_CSR_PATH			"i915/tgl_dmc_ver2_06.bin"
-#define TGL_CSR_VERSION_REQUIRED	CSR_VERSION(2, 6)
+#define TGL_CSR_PATH			"i915/tgl_dmc_ver2_08.bin"
+#define TGL_CSR_VERSION_REQUIRED	CSR_VERSION(2, 8)
 #define TGL_CSR_MAX_FW_SIZE		0x6000
 MODULE_FIRMWARE(TGL_CSR_PATH);
 
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 2c484b55bcdf..de5b216561d8 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -706,6 +706,42 @@ static const struct cnl_ddi_buf_trans tgl_combo_phy_ddi_translations_dp_hbr2[] =
 	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 900   900      0.0   */
 };
 
+static const struct cnl_ddi_buf_trans tgl_uy_combo_phy_ddi_translations_dp_hbr2[] = {
+						/* NT mV Trans mV db    */
+	{ 0xA, 0x35, 0x3F, 0x00, 0x00 },	/* 350   350      0.0   */
+	{ 0xA, 0x4F, 0x36, 0x00, 0x09 },	/* 350   500      3.1   */
+	{ 0xC, 0x60, 0x32, 0x00, 0x0D },	/* 350   700      6.0   */
+	{ 0xC, 0x7F, 0x2D, 0x00, 0x12 },	/* 350   900      8.2   */
+	{ 0xC, 0x47, 0x3F, 0x00, 0x00 },	/* 500   500      0.0   */
+	{ 0xC, 0x6F, 0x36, 0x00, 0x09 },	/* 500   700      2.9   */
+	{ 0x6, 0x7D, 0x32, 0x00, 0x0D },	/* 500   900      5.1   */
+	{ 0x6, 0x60, 0x3C, 0x00, 0x03 },	/* 650   700      0.6   */
+	{ 0x6, 0x7F, 0x34, 0x00, 0x0B },	/* 600   900      3.5   */
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 900   900      0.0   */
+};
+
+/*
+ * Cloned the HOBL entry to comply with the voltage and pre-emphasis entries
+ * that DisplayPort specification requires
+ */
+static const struct cnl_ddi_buf_trans tgl_combo_phy_ddi_translations_edp_hbr2_hobl[] = {
+						/* VS	pre-emp	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 0	0	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 0	1	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 0	2	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 0	3	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 1	0	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 1	1	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 1	2	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 2	0	*/
+	{ 0x6, 0x7F, 0x3F, 0x00, 0x00 },	/* 2	1	*/
+};
+
+static bool is_hobl_buf_trans(const struct cnl_ddi_buf_trans *table)
+{
+	return table == tgl_combo_phy_ddi_translations_edp_hbr2_hobl;
+}
+
 static const struct ddi_buf_trans *
 bdw_get_buf_trans_edp(struct intel_encoder *encoder, int *n_entries)
 {
@@ -1050,9 +1086,26 @@ static const struct cnl_ddi_buf_trans *
 tgl_get_combo_buf_trans(struct intel_encoder *encoder, int type, int rate,
 			int *n_entries)
 {
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp.hobl) {
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+
+		if (!intel_dp->hobl_failed && rate <= 540000) {
+			/* Same table applies to TGL, RKL and DG1 */
+			*n_entries = ARRAY_SIZE(tgl_combo_phy_ddi_translations_edp_hbr2_hobl);
+			return tgl_combo_phy_ddi_translations_edp_hbr2_hobl;
+		}
+	}
+
 	if (type == INTEL_OUTPUT_HDMI || type == INTEL_OUTPUT_EDP) {
 		return icl_get_combo_buf_trans(encoder, type, rate, n_entries);
 	} else if (rate > 270000) {
+		if (IS_TGL_U(dev_priv) || IS_TGL_Y(dev_priv)) {
+			*n_entries = ARRAY_SIZE(tgl_uy_combo_phy_ddi_translations_dp_hbr2);
+			return tgl_uy_combo_phy_ddi_translations_dp_hbr2;
+		}
+
 		*n_entries = ARRAY_SIZE(tgl_combo_phy_ddi_translations_dp_hbr2);
 		return tgl_combo_phy_ddi_translations_dp_hbr2;
 	}
@@ -2392,6 +2445,15 @@ static void icl_ddi_combo_vswing_program(struct intel_encoder *encoder,
 		level = n_entries - 1;
 	}
 
+	if (type == INTEL_OUTPUT_EDP) {
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+
+		val = EDP4K2K_MODE_OVRD_EN | EDP4K2K_MODE_OVRD_OPTIMIZED;
+		intel_dp->hobl_active = is_hobl_buf_trans(ddi_translations);
+		intel_de_rmw(dev_priv, ICL_PORT_CL_DW10(phy), val,
+			     intel_dp->hobl_active ? val : 0);
+	}
+
 	/* Set PORT_TX_DW5 */
 	val = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN0(phy));
 	val &= ~(SCALING_MODE_SEL_MASK | RTERM_SELECT_MASK |
@@ -2802,7 +2864,9 @@ hsw_set_signal_levels(struct intel_dp *intel_dp)
 static u32 icl_dpclka_cfgcr0_clk_off(struct drm_i915_private *dev_priv,
 				     enum phy phy)
 {
-	if (intel_phy_is_combo(dev_priv, phy)) {
+	if (IS_ROCKETLAKE(dev_priv)) {
+		return RKL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy);
+	} else if (intel_phy_is_combo(dev_priv, phy)) {
 		return ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy);
 	} else if (intel_phy_is_tc(dev_priv, phy)) {
 		enum tc_port tc_port = intel_port_to_tc(dev_priv,
@@ -2829,6 +2893,16 @@ static void icl_map_plls_to_ports(struct intel_encoder *encoder,
 		    (val & icl_dpclka_cfgcr0_clk_off(dev_priv, phy)) == 0);
 
 	if (intel_phy_is_combo(dev_priv, phy)) {
+		u32 mask, sel;
+
+		if (IS_ROCKETLAKE(dev_priv)) {
+			mask = RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy);
+			sel = RKL_DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, phy);
+		} else {
+			mask = ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy);
+			sel = ICL_DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, phy);
+		}
+
 		/*
 		 * Even though this register references DDIs, note that we
 		 * want to pass the PHY rather than the port (DDI).  For
@@ -2839,8 +2913,8 @@ static void icl_map_plls_to_ports(struct intel_encoder *encoder,
 		 *   Clock Select chooses the PLL for both DDIA and DDID and
 		 *   drives port A in all cases."
 		 */
-		val &= ~ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy);
-		val |= ICL_DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, phy);
+		val &= ~mask;
+		val |= sel;
 		intel_de_write(dev_priv, ICL_DPCLKA_CFGCR0, val);
 		intel_de_posting_read(dev_priv, ICL_DPCLKA_CFGCR0);
 	}
@@ -4037,8 +4111,7 @@ static void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp)
 			intel_wait_ddi_buf_idle(dev_priv, port);
 	}
 
-	dp_tp_ctl = DP_TP_CTL_ENABLE |
-		    DP_TP_CTL_LINK_TRAIN_PAT1 | DP_TP_CTL_SCRAMBLE_DISABLE;
+	dp_tp_ctl = DP_TP_CTL_ENABLE | DP_TP_CTL_LINK_TRAIN_PAT1;
 	if (intel_dp->link_mst)
 		dp_tp_ctl |= DP_TP_CTL_MODE_MST;
 	else {
@@ -4061,16 +4134,10 @@ static void intel_ddi_set_link_train(struct intel_dp *intel_dp,
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 	u8 train_pat_mask = drm_dp_training_pattern_mask(intel_dp->dpcd);
-	enum port port = dp_to_dig_port(intel_dp)->base.port;
 	u32 temp;
 
 	temp = intel_de_read(dev_priv, intel_dp->regs.dp_tp_ctl);
 
-	if (dp_train_pat & DP_LINK_SCRAMBLING_DISABLE)
-		temp |= DP_TP_CTL_SCRAMBLE_DISABLE;
-	else
-		temp &= ~DP_TP_CTL_SCRAMBLE_DISABLE;
-
 	temp &= ~DP_TP_CTL_LINK_TRAIN_MASK;
 	switch (dp_train_pat & train_pat_mask) {
 	case DP_TRAINING_PATTERN_DISABLE:
@@ -4091,9 +4158,6 @@ static void intel_ddi_set_link_train(struct intel_dp *intel_dp,
 	}
 
 	intel_de_write(dev_priv, intel_dp->regs.dp_tp_ctl, temp);
-
-	intel_de_write(dev_priv, DDI_BUF_CTL(port), intel_dp->DP);
-	intel_de_posting_read(dev_priv, DDI_BUF_CTL(port));
 }
 
 static void intel_ddi_set_idle_link_train(struct intel_dp *intel_dp)
@@ -4878,6 +4942,13 @@ intel_ddi_max_lanes(struct intel_digital_port *dig_port)
 	return max_lanes;
 }
 
+static bool hti_uses_phy(struct drm_i915_private *i915, enum phy phy)
+{
+	return i915->hti_state & HDPORT_ENABLED &&
+		(i915->hti_state & HDPORT_PHY_USED_DP(phy) ||
+		 i915->hti_state & HDPORT_PHY_USED_HDMI(phy));
+}
+
 void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 {
 	struct intel_digital_port *dig_port;
@@ -4885,6 +4956,18 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 	bool init_hdmi, init_dp, init_lspcon = false;
 	enum phy phy = intel_port_to_phy(dev_priv, port);
 
+	/*
+	 * On platforms with HTI (aka HDPORT), if it's enabled at boot it may
+	 * have taken over some of the PHYs and made them unavailable to the
+	 * driver.  In that case we should skip initializing the corresponding
+	 * outputs.
+	 */
+	if (hti_uses_phy(dev_priv, phy)) {
+		drm_dbg_kms(&dev_priv->drm, "PORT %c / PHY %c reserved by HTI\n",
+			    port_name(port), phy_name(phy));
+		return;
+	}
+
 	init_hdmi = intel_bios_port_supports_dvi(dev_priv, port) ||
 		intel_bios_port_supports_hdmi(dev_priv, port);
 	init_dp = intel_bios_port_supports_dp(dev_priv, port);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index b2ec3a5141cc..7d50b7177d40 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -47,6 +47,7 @@
 #include "display/intel_ddi.h"
 #include "display/intel_dp.h"
 #include "display/intel_dp_mst.h"
+#include "display/intel_dpll_mgr.h"
 #include "display/intel_dsi.h"
 #include "display/intel_dvo.h"
 #include "display/intel_gmbus.h"
@@ -3761,6 +3762,44 @@ static int glk_max_plane_width(const struct drm_framebuffer *fb,
 	}
 }
 
+static int icl_min_plane_width(const struct drm_framebuffer *fb)
+{
+	/* Wa_14011264657, Wa_14011050563: gen11+ */
+	switch (fb->format->format) {
+	case DRM_FORMAT_C8:
+		return 18;
+	case DRM_FORMAT_RGB565:
+		return 10;
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_ABGR8888:
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_ARGB2101010:
+	case DRM_FORMAT_ABGR2101010:
+	case DRM_FORMAT_XVYU2101010:
+	case DRM_FORMAT_Y212:
+	case DRM_FORMAT_Y216:
+		return 6;
+	case DRM_FORMAT_NV12:
+		return 20;
+	case DRM_FORMAT_P010:
+	case DRM_FORMAT_P012:
+	case DRM_FORMAT_P016:
+		return 12;
+	case DRM_FORMAT_XRGB16161616F:
+	case DRM_FORMAT_XBGR16161616F:
+	case DRM_FORMAT_ARGB16161616F:
+	case DRM_FORMAT_ABGR16161616F:
+	case DRM_FORMAT_XVYU12_16161616:
+	case DRM_FORMAT_XVYU16161616:
+		return 4;
+	default:
+		return 1;
+	}
+}
+
 static int icl_max_plane_width(const struct drm_framebuffer *fb,
 			       int color_plane,
 			       unsigned int rotation)
@@ -3843,29 +3882,31 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
 	int y = plane_state->uapi.src.y1 >> 16;
 	int w = drm_rect_width(&plane_state->uapi.src) >> 16;
 	int h = drm_rect_height(&plane_state->uapi.src) >> 16;
-	int max_width;
-	int max_height;
-	u32 alignment;
-	u32 offset;
+	int max_width, min_width, max_height;
+	u32 alignment, offset;
 	int aux_plane = intel_main_to_aux_plane(fb, 0);
 	u32 aux_offset = plane_state->color_plane[aux_plane].offset;
 
-	if (INTEL_GEN(dev_priv) >= 11)
+	if (INTEL_GEN(dev_priv) >= 11) {
 		max_width = icl_max_plane_width(fb, 0, rotation);
-	else if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+		min_width = icl_min_plane_width(fb);
+	} else if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) {
 		max_width = glk_max_plane_width(fb, 0, rotation);
-	else
+		min_width = 1;
+	} else {
 		max_width = skl_max_plane_width(fb, 0, rotation);
+		min_width = 1;
+	}
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		max_height = icl_max_plane_height();
 	else
 		max_height = skl_max_plane_height();
 
-	if (w > max_width || h > max_height) {
+	if (w > max_width || w < min_width || h > max_height) {
 		drm_dbg_kms(&dev_priv->drm,
-			    "requested Y/RGB source size %dx%d too big (limit %dx%d)\n",
-			    w, h, max_width, max_height);
+			    "requested Y/RGB source size %dx%d outside limits (min: %dx1 max: %dx%d)\n",
+			    w, h, min_width, max_width, max_height);
 		return -EINVAL;
 	}
 
@@ -10802,9 +10843,18 @@ static void icl_get_ddi_pll(struct drm_i915_private *dev_priv, enum port port,
 	u32 temp;
 
 	if (intel_phy_is_combo(dev_priv, phy)) {
-		temp = intel_de_read(dev_priv, ICL_DPCLKA_CFGCR0) &
-			ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy);
-		id = temp >> ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy);
+		u32 mask, shift;
+
+		if (IS_ROCKETLAKE(dev_priv)) {
+			mask = RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy);
+			shift = RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy);
+		} else {
+			mask = ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy);
+			shift = ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy);
+		}
+
+		temp = intel_de_read(dev_priv, ICL_DPCLKA_CFGCR0) & mask;
+		id = temp >> shift;
 		port_dpll_id = ICL_PORT_DPLL_DEFAULT;
 	} else if (intel_phy_is_tc(dev_priv, phy)) {
 		u32 clk_sel = intel_de_read(dev_priv, DDI_CLK_SEL(port)) & DDI_CLK_SEL_MASK;
@@ -12760,6 +12810,9 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state,
 
 	}
 
+	if (!mode_changed)
+		intel_psr2_sel_fetch_update(state, crtc);
+
 	return 0;
 }
 
@@ -15136,6 +15189,8 @@ static void commit_pipe_config(struct intel_atomic_state *state,
 
 		if (new_crtc_state->update_pipe)
 			intel_pipe_fastset(old_crtc_state, new_crtc_state);
+
+		intel_psr2_program_trans_man_trk_ctl(new_crtc_state);
 	}
 
 	if (dev_priv->display.atomic_update_watermarks)
@@ -17894,6 +17949,13 @@ int intel_modeset_init(struct drm_i915_private *i915)
 	if (i915->max_cdclk_freq == 0)
 		intel_update_max_cdclk(i915);
 
+	/*
+	 * If the platform has HTI, we need to find out whether it has reserved
+	 * any display resources before we create our display outputs.
+	 */
+	if (INTEL_INFO(i915)->display.has_hti)
+		i915->hti_state = intel_de_read(i915, HDPORT_STATE);
+
 	/* Just disable it once at startup */
 	intel_vga_disable(i915);
 	intel_setup_outputs(i915);
diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
index 5a5cfe25085b..f549381048b3 100644
--- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c
+++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
@@ -417,6 +417,9 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 			su_blocks = su_blocks >> PSR2_SU_STATUS_SHIFT(frame);
 			seq_printf(m, "%d\t%d\n", frame, su_blocks);
 		}
+
+		seq_printf(m, "PSR2 selective fetch: %s\n",
+			   enableddisabled(psr->psr2_sel_fetch_enabled));
 	}
 
 unlock:
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index e0fcb89c736b..7946c6af4b1e 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -3927,12 +3927,13 @@ tgl_tc_cold_request(struct drm_i915_private *i915, bool block)
 	int ret;
 
 	while (1) {
-		u32 low_val = 0, high_val;
+		u32 low_val;
+		u32 high_val = 0;
 
 		if (block)
-			high_val = TGL_PCODE_EXIT_TCCOLD_DATA_H_BLOCK_REQ;
+			low_val = TGL_PCODE_EXIT_TCCOLD_DATA_L_BLOCK_REQ;
 		else
-			high_val = TGL_PCODE_EXIT_TCCOLD_DATA_H_UNBLOCK_REQ;
+			low_val = TGL_PCODE_EXIT_TCCOLD_DATA_L_UNBLOCK_REQ;
 
 		/*
 		 * Spec states that we should timeout the request after 200us
@@ -3951,8 +3952,7 @@ tgl_tc_cold_request(struct drm_i915_private *i915, bool block)
 		if (++tries == 3)
 			break;
 
-		if (ret == -EAGAIN)
-			msleep(1);
+		msleep(1);
 	}
 
 	if (ret)
@@ -5302,6 +5302,12 @@ static void icl_display_core_init(struct drm_i915_private *dev_priv,
 
 	gen9_set_dc_state(dev_priv, DC_STATE_DISABLE);
 
+	/* Wa_14011294188:ehl,jsl,tgl,rkl */
+	if (INTEL_PCH_TYPE(dev_priv) >= PCH_JSP &&
+	    INTEL_PCH_TYPE(dev_priv) < PCH_DG1)
+		intel_de_rmw(dev_priv, SOUTH_DSPCLK_GATE_D, 0,
+			     PCH_DPMGUNIT_CLOCK_GATE_DISABLE);
+
 	/* 1. Enable PCH reset handshake. */
 	intel_pch_reset_handshake(dev_priv, !HAS_PCH_NOP(dev_priv));
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index e8f809161c75..9349b15afff6 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -931,6 +931,7 @@ struct intel_crtc_state {
 
 	bool has_psr;
 	bool has_psr2;
+	bool enable_psr2_sel_fetch;
 	u32 dc3co_exitline;
 
 	/*
@@ -1073,6 +1074,8 @@ struct intel_crtc_state {
 
 	/* For DSB related info */
 	struct intel_dsb *dsb;
+
+	u32 psr2_man_track_ctl;
 };
 
 enum intel_pipe_crc_source {
@@ -1375,6 +1378,9 @@ struct intel_dp {
 
 	/* Display stream compression testing */
 	bool force_dsc_en;
+
+	bool hobl_failed;
+	bool hobl_active;
 };
 
 enum lspcon_vendor {
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index a23ed7290843..f2c8b56be9ea 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -410,10 +410,17 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 		    intel_connector->base.base.id,
 		    intel_connector->base.name,
 		    intel_dp->link_rate, intel_dp->lane_count);
-	if (!intel_dp_get_link_train_fallback_values(intel_dp,
-						     intel_dp->link_rate,
-						     intel_dp->lane_count))
-		/* Schedule a Hotplug Uevent to userspace to start modeset */
-		schedule_work(&intel_connector->modeset_retry_work);
-	return;
+
+	if (intel_dp->hobl_active) {
+		drm_dbg_kms(&dp_to_i915(intel_dp)->drm,
+			    "Link Training failed with HOBL active, not enabling it from now on");
+		intel_dp->hobl_failed = true;
+	} else if (intel_dp_get_link_train_fallback_values(intel_dp,
+							   intel_dp->link_rate,
+							   intel_dp->lane_count)) {
+		return;
+	}
+
+	/* Schedule a Hotplug Uevent to userspace to start modeset */
+	schedule_work(&intel_connector->modeset_retry_work);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index aeb6ee395cce..81ab975fe4f0 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -3475,6 +3475,14 @@ static void icl_update_active_dpll(struct intel_atomic_state *state,
 	icl_set_active_port_dpll(crtc_state, port_dpll_id);
 }
 
+static u32 intel_get_hti_plls(struct drm_i915_private *i915)
+{
+	if (!(i915->hti_state & HDPORT_ENABLED))
+		return 0;
+
+	return REG_FIELD_GET(HDPORT_DPLL_USED_MASK, i915->hti_state);
+}
+
 static bool icl_get_combo_phy_dpll(struct intel_atomic_state *state,
 				   struct intel_crtc *crtc,
 				   struct intel_encoder *encoder)
@@ -3504,13 +3512,22 @@ static bool icl_get_combo_phy_dpll(struct intel_atomic_state *state,
 
 	icl_calc_dpll_state(dev_priv, &pll_params, &port_dpll->hw_state);
 
-	if (IS_ELKHARTLAKE(dev_priv) && port != PORT_A)
+	if (IS_ROCKETLAKE(dev_priv)) {
 		dpll_mask =
 			BIT(DPLL_ID_EHL_DPLL4) |
 			BIT(DPLL_ID_ICL_DPLL1) |
 			BIT(DPLL_ID_ICL_DPLL0);
-	else
+	} else if (IS_ELKHARTLAKE(dev_priv) && port != PORT_A) {
+		dpll_mask =
+			BIT(DPLL_ID_EHL_DPLL4) |
+			BIT(DPLL_ID_ICL_DPLL1) |
+			BIT(DPLL_ID_ICL_DPLL0);
+	} else {
 		dpll_mask = BIT(DPLL_ID_ICL_DPLL1) | BIT(DPLL_ID_ICL_DPLL0);
+	}
+
+	/* Eliminate DPLLs from consideration if reserved by HTI */
+	dpll_mask &= ~intel_get_hti_plls(dev_priv);
 
 	port_dpll->pll = intel_find_shared_dpll(state, crtc,
 						&port_dpll->hw_state,
@@ -3791,7 +3808,12 @@ static bool icl_pll_get_hw_state(struct drm_i915_private *dev_priv,
 	if (!(val & PLL_ENABLE))
 		goto out;
 
-	if (INTEL_GEN(dev_priv) >= 12) {
+	if (IS_ROCKETLAKE(dev_priv)) {
+		hw_state->cfgcr0 = intel_de_read(dev_priv,
+						 RKL_DPLL_CFGCR0(id));
+		hw_state->cfgcr1 = intel_de_read(dev_priv,
+						 RKL_DPLL_CFGCR1(id));
+	} else if (INTEL_GEN(dev_priv) >= 12) {
 		hw_state->cfgcr0 = intel_de_read(dev_priv,
 						 TGL_DPLL_CFGCR0(id));
 		hw_state->cfgcr1 = intel_de_read(dev_priv,
@@ -3844,7 +3866,10 @@ static void icl_dpll_write(struct drm_i915_private *dev_priv,
 	const enum intel_dpll_id id = pll->info->id;
 	i915_reg_t cfgcr0_reg, cfgcr1_reg;
 
-	if (INTEL_GEN(dev_priv) >= 12) {
+	if (IS_ROCKETLAKE(dev_priv)) {
+		cfgcr0_reg = RKL_DPLL_CFGCR0(id);
+		cfgcr1_reg = RKL_DPLL_CFGCR1(id);
+	} else if (INTEL_GEN(dev_priv) >= 12) {
 		cfgcr0_reg = TGL_DPLL_CFGCR0(id);
 		cfgcr1_reg = TGL_DPLL_CFGCR1(id);
 	} else {
@@ -4276,6 +4301,21 @@ static const struct intel_dpll_mgr tgl_pll_mgr = {
 	.dump_hw_state = icl_dump_hw_state,
 };
 
+static const struct dpll_info rkl_plls[] = {
+	{ "DPLL 0", &combo_pll_funcs, DPLL_ID_ICL_DPLL0, 0 },
+	{ "DPLL 1", &combo_pll_funcs, DPLL_ID_ICL_DPLL1, 0 },
+	{ "DPLL 4", &combo_pll_funcs, DPLL_ID_EHL_DPLL4, 0 },
+	{ },
+};
+
+static const struct intel_dpll_mgr rkl_pll_mgr = {
+	.dpll_info = rkl_plls,
+	.get_dplls = icl_get_dplls,
+	.put_dplls = icl_put_dplls,
+	.update_ref_clks = icl_update_dpll_ref_clks,
+	.dump_hw_state = icl_dump_hw_state,
+};
+
 /**
  * intel_shared_dpll_init - Initialize shared DPLLs
  * @dev: drm device
@@ -4289,7 +4329,9 @@ void intel_shared_dpll_init(struct drm_device *dev)
 	const struct dpll_info *dpll_info;
 	int i;
 
-	if (INTEL_GEN(dev_priv) >= 12)
+	if (IS_ROCKETLAKE(dev_priv))
+		dpll_mgr = &rkl_pll_mgr;
+	else if (INTEL_GEN(dev_priv) >= 12)
 		dpll_mgr = &tgl_pll_mgr;
 	else if (IS_ELKHARTLAKE(dev_priv))
 		dpll_mgr = &ehl_pll_mgr;
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index 24c3a0f212c6..135f5e8a4d70 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -424,6 +424,14 @@ static void intel_fbc_deactivate(struct drm_i915_private *dev_priv,
 	fbc->no_fbc_reason = reason;
 }
 
+static u64 intel_fbc_cfb_base_max(struct drm_i915_private *i915)
+{
+	if (INTEL_GEN(i915) >= 5 || IS_G4X(i915))
+		return BIT_ULL(28);
+	else
+		return BIT_ULL(32);
+}
+
 static int find_compression_threshold(struct drm_i915_private *dev_priv,
 				      struct drm_mm_node *node,
 				      unsigned int size,
@@ -442,6 +450,8 @@ static int find_compression_threshold(struct drm_i915_private *dev_priv,
 	else
 		end = U64_MAX;
 
+	end = min(end, intel_fbc_cfb_base_max(dev_priv));
+
 	/* HACK: This code depends on what we will do in *_enable_fbc. If that
 	 * code changes, this code needs to change as well.
 	 *
@@ -1416,6 +1426,13 @@ static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv)
 	if (!HAS_FBC(dev_priv))
 		return 0;
 
+	/*
+	 * Fbc is causing random underruns in CI execution on TGL platforms.
+	 * Disabling the same while the problem is being debugged and analyzed.
+	 */
+	if (IS_TIGERLAKE(dev_priv))
+		return 0;
+
 	if (IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9)
 		return 1;
 
diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.c b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
index 2979ed2588eb..d898b370d7a4 100644
--- a/drivers/gpu/drm/i915/display/intel_frontbuffer.c
+++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
@@ -232,6 +232,8 @@ static void frontbuffer_release(struct kref *ref)
 	RCU_INIT_POINTER(obj->frontbuffer, NULL);
 	spin_unlock(&to_i915(obj->base.dev)->fb_tracking.lock);
 
+	i915_active_fini(&front->write);
+
 	i915_gem_object_put(obj);
 	kfree_rcu(front, rcu);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index bf9e320c547d..2b004ee9619c 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -553,6 +553,22 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp)
 		val |= EDP_PSR2_FAST_WAKE(7);
 	}
 
+	if (dev_priv->psr.psr2_sel_fetch_enabled) {
+		/* WA 1408330847 */
+		if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_A0) ||
+		    IS_RKL_REVID(dev_priv, RKL_REVID_A0, RKL_REVID_A0))
+			intel_de_rmw(dev_priv, CHICKEN_PAR1_1,
+				     DIS_RAM_BYPASS_PSR2_MAN_TRACK,
+				     DIS_RAM_BYPASS_PSR2_MAN_TRACK);
+
+		intel_de_write(dev_priv,
+			       PSR2_MAN_TRK_CTL(dev_priv->psr.transcoder),
+			       PSR2_MAN_TRK_CTL_ENABLE);
+	} else if (HAS_PSR2_SEL_FETCH(dev_priv)) {
+		intel_de_write(dev_priv,
+			       PSR2_MAN_TRK_CTL(dev_priv->psr.transcoder), 0);
+	}
+
 	/*
 	 * PSR2 HW is incorrectly using EDP_PSR_TP1_TP3_SEL and BSpec is
 	 * recommending keep this bit unset while PSR2 is enabled.
@@ -663,6 +679,38 @@ tgl_dc3co_exitline_compute_config(struct intel_dp *intel_dp,
 	crtc_state->dc3co_exitline = crtc_vdisplay - exit_scanlines;
 }
 
+static bool intel_psr2_sel_fetch_config_valid(struct intel_dp *intel_dp,
+					      struct intel_crtc_state *crtc_state)
+{
+	struct intel_atomic_state *state = to_intel_atomic_state(crtc_state->uapi.state);
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	struct intel_plane_state *plane_state;
+	struct intel_plane *plane;
+	int i;
+
+	if (!dev_priv->params.enable_psr2_sel_fetch) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "PSR2 sel fetch not enabled, disabled by parameter\n");
+		return false;
+	}
+
+	if (crtc_state->uapi.async_flip) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "PSR2 sel fetch not enabled, async flip enabled\n");
+		return false;
+	}
+
+	for_each_new_intel_plane_in_state(state, plane, plane_state, i) {
+		if (plane_state->uapi.rotation != DRM_MODE_ROTATE_0) {
+			drm_dbg_kms(&dev_priv->drm,
+				    "PSR2 sel fetch not enabled, plane rotated\n");
+			return false;
+		}
+	}
+
+	return crtc_state->enable_psr2_sel_fetch = true;
+}
+
 static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 				    struct intel_crtc_state *crtc_state)
 {
@@ -732,22 +780,17 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 		return false;
 	}
 
-	/*
-	 * Some platforms lack PSR2 HW tracking and instead require manual
-	 * tracking by software.  In this case, the driver is required to track
-	 * the areas that need updates and program hardware to send selective
-	 * updates.
-	 *
-	 * So until the software tracking is implemented, PSR2 needs to be
-	 * disabled for platforms without PSR2 HW tracking.
-	 */
-	if (!HAS_PSR_HW_TRACKING(dev_priv)) {
-		drm_dbg_kms(&dev_priv->drm,
-			    "No PSR2 HW tracking in the platform\n");
-		return false;
+	if (HAS_PSR2_SEL_FETCH(dev_priv)) {
+		if (!intel_psr2_sel_fetch_config_valid(intel_dp, crtc_state) &&
+		    !HAS_PSR_HW_TRACKING(dev_priv)) {
+			drm_dbg_kms(&dev_priv->drm,
+				    "PSR2 not enabled, selective fetch not valid and no HW tracking available\n");
+			return false;
+		}
 	}
 
-	if (crtc_hdisplay > psr_max_h || crtc_vdisplay > psr_max_v) {
+	if (!crtc_state->enable_psr2_sel_fetch &&
+	    (crtc_hdisplay > psr_max_h || crtc_vdisplay > psr_max_v)) {
 		drm_dbg_kms(&dev_priv->drm,
 			    "PSR2 not enabled, resolution %dx%d > max supported %dx%d\n",
 			    crtc_hdisplay, crtc_vdisplay,
@@ -898,6 +941,11 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp,
 		val |= EXITLINE_ENABLE;
 		intel_de_write(dev_priv, EXITLINE(cpu_transcoder), val);
 	}
+
+	if (HAS_PSR_HW_TRACKING(dev_priv))
+		intel_de_rmw(dev_priv, CHICKEN_PAR1_1, IGNORE_PSR2_HW_TRACKING,
+			     dev_priv->psr.psr2_sel_fetch_enabled ?
+			     IGNORE_PSR2_HW_TRACKING : 0);
 }
 
 static void intel_psr_enable_locked(struct drm_i915_private *dev_priv,
@@ -919,6 +967,7 @@ static void intel_psr_enable_locked(struct drm_i915_private *dev_priv,
 	/* DC5/DC6 requires at least 6 idle frames */
 	val = usecs_to_jiffies(intel_get_frame_time_us(crtc_state) * 6);
 	dev_priv->psr.dc3co_exit_delay = val;
+	dev_priv->psr.psr2_sel_fetch_enabled = crtc_state->enable_psr2_sel_fetch;
 
 	/*
 	 * If a PSR error happened and the driver is reloaded, the EDP_PSR_IIR
@@ -1058,6 +1107,13 @@ static void intel_psr_disable_locked(struct intel_dp *intel_dp)
 				    psr_status_mask, 2000))
 		drm_err(&dev_priv->drm, "Timed out waiting PSR idle state\n");
 
+	/* WA 1408330847 */
+	if (dev_priv->psr.psr2_sel_fetch_enabled &&
+	    (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_A0) ||
+	     IS_RKL_REVID(dev_priv, RKL_REVID_A0, RKL_REVID_A0)))
+		intel_de_rmw(dev_priv, CHICKEN_PAR1_1,
+			     DIS_RAM_BYPASS_PSR2_MAN_TRACK, 0);
+
 	/* Disable PSR on Sink */
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, 0);
 
@@ -1115,6 +1171,32 @@ static void psr_force_hw_tracking_exit(struct drm_i915_private *dev_priv)
 		intel_psr_exit(dev_priv);
 }
 
+void intel_psr2_program_trans_man_trk_ctl(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	struct i915_psr *psr = &dev_priv->psr;
+
+	if (!HAS_PSR2_SEL_FETCH(dev_priv) ||
+	    !crtc_state->enable_psr2_sel_fetch)
+		return;
+
+	intel_de_write(dev_priv, PSR2_MAN_TRK_CTL(psr->transcoder),
+		       crtc_state->psr2_man_track_ctl);
+}
+
+void intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
+				 struct intel_crtc *crtc)
+{
+	struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
+
+	if (!crtc_state->enable_psr2_sel_fetch)
+		return;
+
+	crtc_state->psr2_man_track_ctl = PSR2_MAN_TRK_CTL_ENABLE |
+					 PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME;
+}
+
 /**
  * intel_psr_update - Update PSR state
  * @intel_dp: Intel DP
diff --git a/drivers/gpu/drm/i915/display/intel_psr.h b/drivers/gpu/drm/i915/display/intel_psr.h
index b4515186d5f4..6a83c8e682e6 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.h
+++ b/drivers/gpu/drm/i915/display/intel_psr.h
@@ -13,6 +13,8 @@ struct drm_connector_state;
 struct drm_i915_private;
 struct intel_crtc_state;
 struct intel_dp;
+struct intel_crtc;
+struct intel_atomic_state;
 
 #define CAN_PSR(dev_priv) (HAS_PSR(dev_priv) && dev_priv->psr.sink_support)
 void intel_psr_init_dpcd(struct intel_dp *intel_dp);
@@ -43,5 +45,8 @@ void intel_psr_atomic_check(struct drm_connector *connector,
 			    struct drm_connector_state *old_state,
 			    struct drm_connector_state *new_state);
 void intel_psr_set_force_mode_changed(struct intel_dp *intel_dp);
+void intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
+				 struct intel_crtc *crtc);
+void intel_psr2_program_trans_man_trk_ctl(const struct intel_crtc_state *crtc_state);
 
 #endif /* __INTEL_PSR_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index d03860fef2d7..c26ca029fc0a 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -2843,8 +2843,9 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane,
 static bool gen12_plane_supports_mc_ccs(struct drm_i915_private *dev_priv,
 					enum plane_id plane_id)
 {
-	/* Wa_14010477008:tgl[a0..c0] */
-	if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_C0))
+	/* Wa_14010477008:tgl[a0..c0],rkl[all] */
+	if (IS_ROCKETLAKE(dev_priv) ||
+	    IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_C0))
 		return false;
 
 	return plane_id < PLANE_SPRITE4;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 6b4ec66cb558..02b1630f513e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -26,6 +26,7 @@
 #include "i915_gem_ioctls.h"
 #include "i915_sw_fence_work.h"
 #include "i915_trace.h"
+#include "i915_user_extensions.h"
 
 struct eb_vma {
 	struct i915_vma *vma;
@@ -222,6 +223,13 @@ struct eb_vma_array {
  * the batchbuffer in trusted mode, otherwise the ioctl is rejected.
  */
 
+struct eb_fence {
+	struct drm_syncobj *syncobj; /* Use with ptr_mask_bits() */
+	struct dma_fence *dma_fence;
+	u64 value;
+	struct dma_fence_chain *chain_fence;
+};
+
 struct i915_execbuffer {
 	struct drm_i915_private *i915; /** i915 backpointer */
 	struct drm_file *file; /** per-file lookup tables and limits */
@@ -281,6 +289,9 @@ struct i915_execbuffer {
 	int lut_size;
 	struct hlist_head *buckets; /** ht for relocation handles */
 	struct eb_vma_array *array;
+
+	struct eb_fence *fences;
+	unsigned long num_fences;
 };
 
 static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
@@ -1622,7 +1633,8 @@ static int i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
 		return -EINVAL;
 
 	/* Kernel clipping was a DRI1 misfeature */
-	if (!(exec->flags & I915_EXEC_FENCE_ARRAY)) {
+	if (!(exec->flags & (I915_EXEC_FENCE_ARRAY |
+			     I915_EXEC_USE_EXTENSIONS))) {
 		if (exec->num_cliprects || exec->cliprects_ptr)
 			return -EINVAL;
 	}
@@ -2201,107 +2213,241 @@ eb_pin_engine(struct i915_execbuffer *eb,
 }
 
 static void
-__free_fence_array(struct drm_syncobj **fences, unsigned int n)
+__free_fence_array(struct eb_fence *fences, unsigned int n)
 {
-	while (n--)
-		drm_syncobj_put(ptr_mask_bits(fences[n], 2));
+	while (n--) {
+		drm_syncobj_put(ptr_mask_bits(fences[n].syncobj, 2));
+		dma_fence_put(fences[n].dma_fence);
+		kfree(fences[n].chain_fence);
+	}
 	kvfree(fences);
 }
 
-static struct drm_syncobj **
-get_fence_array(struct drm_i915_gem_execbuffer2 *args,
-		struct drm_file *file)
+static int
+add_timeline_fence_array(struct i915_execbuffer *eb,
+			 const struct drm_i915_gem_execbuffer_ext_timeline_fences *timeline_fences)
 {
-	const unsigned long nfences = args->num_cliprects;
-	struct drm_i915_gem_exec_fence __user *user;
-	struct drm_syncobj **fences;
-	unsigned long n;
-	int err;
+	struct drm_i915_gem_exec_fence __user *user_fences;
+	u64 __user *user_values;
+	struct eb_fence *f;
+	u64 nfences;
+	int err = 0;
 
-	if (!(args->flags & I915_EXEC_FENCE_ARRAY))
-		return NULL;
+	nfences = timeline_fences->fence_count;
+	if (!nfences)
+		return 0;
 
 	/* Check multiplication overflow for access_ok() and kvmalloc_array() */
 	BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long));
 	if (nfences > min_t(unsigned long,
-			    ULONG_MAX / sizeof(*user),
-			    SIZE_MAX / sizeof(*fences)))
-		return ERR_PTR(-EINVAL);
+			    ULONG_MAX / sizeof(*user_fences),
+			    SIZE_MAX / sizeof(*f)) - eb->num_fences)
+		return -EINVAL;
 
-	user = u64_to_user_ptr(args->cliprects_ptr);
-	if (!access_ok(user, nfences * sizeof(*user)))
-		return ERR_PTR(-EFAULT);
+	user_fences = u64_to_user_ptr(timeline_fences->handles_ptr);
+	if (!access_ok(user_fences, nfences * sizeof(*user_fences)))
+		return -EFAULT;
+
+	user_values = u64_to_user_ptr(timeline_fences->values_ptr);
+	if (!access_ok(user_values, nfences * sizeof(*user_values)))
+		return -EFAULT;
 
-	fences = kvmalloc_array(nfences, sizeof(*fences),
-				__GFP_NOWARN | GFP_KERNEL);
-	if (!fences)
-		return ERR_PTR(-ENOMEM);
+	f = krealloc(eb->fences,
+		     (eb->num_fences + nfences) * sizeof(*f),
+		     __GFP_NOWARN | GFP_KERNEL);
+	if (!f)
+		return -ENOMEM;
+
+	eb->fences = f;
+	f += eb->num_fences;
 
-	for (n = 0; n < nfences; n++) {
-		struct drm_i915_gem_exec_fence fence;
+	BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) &
+		     ~__I915_EXEC_FENCE_UNKNOWN_FLAGS);
+
+	while (nfences--) {
+		struct drm_i915_gem_exec_fence user_fence;
 		struct drm_syncobj *syncobj;
+		struct dma_fence *fence = NULL;
+		u64 point;
+
+		if (__copy_from_user(&user_fence,
+				     user_fences++,
+				     sizeof(user_fence)))
+			return -EFAULT;
+
+		if (user_fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS)
+			return -EINVAL;
+
+		if (__get_user(point, user_values++))
+			return -EFAULT;
 
-		if (__copy_from_user(&fence, user++, sizeof(fence))) {
-			err = -EFAULT;
-			goto err;
+		syncobj = drm_syncobj_find(eb->file, user_fence.handle);
+		if (!syncobj) {
+			DRM_DEBUG("Invalid syncobj handle provided\n");
+			return -ENOENT;
 		}
 
-		if (fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS) {
-			err = -EINVAL;
-			goto err;
+		fence = drm_syncobj_fence_get(syncobj);
+
+		if (!fence && user_fence.flags &&
+		    !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) {
+			DRM_DEBUG("Syncobj handle has no fence\n");
+			drm_syncobj_put(syncobj);
+			return -EINVAL;
 		}
 
-		syncobj = drm_syncobj_find(file, fence.handle);
+		if (fence)
+			err = dma_fence_chain_find_seqno(&fence, point);
+
+		if (err && !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) {
+			DRM_DEBUG("Syncobj handle missing requested point %llu\n", point);
+			drm_syncobj_put(syncobj);
+			return err;
+		}
+
+		/*
+		 * A point might have been signaled already and
+		 * garbage collected from the timeline. In this case
+		 * just ignore the point and carry on.
+		 */
+		if (!fence && !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) {
+			drm_syncobj_put(syncobj);
+			continue;
+		}
+
+		/*
+		 * For timeline syncobjs we need to preallocate chains for
+		 * later signaling.
+		 */
+		if (point != 0 && user_fence.flags & I915_EXEC_FENCE_SIGNAL) {
+			/*
+			 * Waiting and signaling the same point (when point !=
+			 * 0) would break the timeline.
+			 */
+			if (user_fence.flags & I915_EXEC_FENCE_WAIT) {
+				DRM_DEBUG("Trying to wait & signal the same timeline point.\n");
+				dma_fence_put(fence);
+				drm_syncobj_put(syncobj);
+				return -EINVAL;
+			}
+
+			f->chain_fence =
+				kmalloc(sizeof(*f->chain_fence),
+					GFP_KERNEL);
+			if (!f->chain_fence) {
+				drm_syncobj_put(syncobj);
+				dma_fence_put(fence);
+				return -ENOMEM;
+			}
+		} else {
+			f->chain_fence = NULL;
+		}
+
+		f->syncobj = ptr_pack_bits(syncobj, user_fence.flags, 2);
+		f->dma_fence = fence;
+		f->value = point;
+		f++;
+		eb->num_fences++;
+	}
+
+	return 0;
+}
+
+static int add_fence_array(struct i915_execbuffer *eb)
+{
+	struct drm_i915_gem_execbuffer2 *args = eb->args;
+	struct drm_i915_gem_exec_fence __user *user;
+	unsigned long num_fences = args->num_cliprects;
+	struct eb_fence *f;
+
+	if (!(args->flags & I915_EXEC_FENCE_ARRAY))
+		return 0;
+
+	if (!num_fences)
+		return 0;
+
+	/* Check multiplication overflow for access_ok() and kvmalloc_array() */
+	BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long));
+	if (num_fences > min_t(unsigned long,
+			       ULONG_MAX / sizeof(*user),
+			       SIZE_MAX / sizeof(*f) - eb->num_fences))
+		return -EINVAL;
+
+	user = u64_to_user_ptr(args->cliprects_ptr);
+	if (!access_ok(user, num_fences * sizeof(*user)))
+		return -EFAULT;
+
+	f = krealloc(eb->fences,
+		     (eb->num_fences + num_fences) * sizeof(*f),
+		     __GFP_NOWARN | GFP_KERNEL);
+	if (!f)
+		return -ENOMEM;
+
+	eb->fences = f;
+	f += eb->num_fences;
+	while (num_fences--) {
+		struct drm_i915_gem_exec_fence user_fence;
+		struct drm_syncobj *syncobj;
+		struct dma_fence *fence = NULL;
+
+		if (__copy_from_user(&user_fence, user++, sizeof(user_fence)))
+			return -EFAULT;
+
+		if (user_fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS)
+			return -EINVAL;
+
+		syncobj = drm_syncobj_find(eb->file, user_fence.handle);
 		if (!syncobj) {
 			DRM_DEBUG("Invalid syncobj handle provided\n");
-			err = -ENOENT;
-			goto err;
+			return -ENOENT;
+		}
+
+		if (user_fence.flags & I915_EXEC_FENCE_WAIT) {
+			fence = drm_syncobj_fence_get(syncobj);
+			if (!fence) {
+				DRM_DEBUG("Syncobj handle has no fence\n");
+				drm_syncobj_put(syncobj);
+				return -EINVAL;
+			}
 		}
 
 		BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) &
 			     ~__I915_EXEC_FENCE_UNKNOWN_FLAGS);
 
-		fences[n] = ptr_pack_bits(syncobj, fence.flags, 2);
+		f->syncobj = ptr_pack_bits(syncobj, user_fence.flags, 2);
+		f->dma_fence = fence;
+		f->value = 0;
+		f->chain_fence = NULL;
+		f++;
+		eb->num_fences++;
 	}
 
-	return fences;
-
-err:
-	__free_fence_array(fences, n);
-	return ERR_PTR(err);
+	return 0;
 }
 
-static void
-put_fence_array(struct drm_i915_gem_execbuffer2 *args,
-		struct drm_syncobj **fences)
+static void put_fence_array(struct eb_fence *fences, int num_fences)
 {
 	if (fences)
-		__free_fence_array(fences, args->num_cliprects);
+		__free_fence_array(fences, num_fences);
 }
 
 static int
-await_fence_array(struct i915_execbuffer *eb,
-		  struct drm_syncobj **fences)
+await_fence_array(struct i915_execbuffer *eb)
 {
-	const unsigned int nfences = eb->args->num_cliprects;
 	unsigned int n;
 	int err;
 
-	for (n = 0; n < nfences; n++) {
+	for (n = 0; n < eb->num_fences; n++) {
 		struct drm_syncobj *syncobj;
-		struct dma_fence *fence;
 		unsigned int flags;
 
-		syncobj = ptr_unpack_bits(fences[n], &flags, 2);
-		if (!(flags & I915_EXEC_FENCE_WAIT))
-			continue;
+		syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2);
 
-		fence = drm_syncobj_fence_get(syncobj);
-		if (!fence)
-			return -EINVAL;
+		if (!eb->fences[n].dma_fence)
+			continue;
 
-		err = i915_request_await_dma_fence(eb->request, fence);
-		dma_fence_put(fence);
+		err = i915_request_await_dma_fence(eb->request,
+						   eb->fences[n].dma_fence);
 		if (err < 0)
 			return err;
 	}
@@ -2309,26 +2455,47 @@ await_fence_array(struct i915_execbuffer *eb,
 	return 0;
 }
 
-static void
-signal_fence_array(struct i915_execbuffer *eb,
-		   struct drm_syncobj **fences)
+static void signal_fence_array(const struct i915_execbuffer *eb)
 {
-	const unsigned int nfences = eb->args->num_cliprects;
 	struct dma_fence * const fence = &eb->request->fence;
 	unsigned int n;
 
-	for (n = 0; n < nfences; n++) {
+	for (n = 0; n < eb->num_fences; n++) {
 		struct drm_syncobj *syncobj;
 		unsigned int flags;
 
-		syncobj = ptr_unpack_bits(fences[n], &flags, 2);
+		syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2);
 		if (!(flags & I915_EXEC_FENCE_SIGNAL))
 			continue;
 
-		drm_syncobj_replace_fence(syncobj, fence);
+		if (eb->fences[n].chain_fence) {
+			drm_syncobj_add_point(syncobj,
+					      eb->fences[n].chain_fence,
+					      fence,
+					      eb->fences[n].value);
+			/*
+			 * The chain's ownership is transferred to the
+			 * timeline.
+			 */
+			eb->fences[n].chain_fence = NULL;
+		} else {
+			drm_syncobj_replace_fence(syncobj, fence);
+		}
 	}
 }
 
+static int
+parse_timeline_fences(struct i915_user_extension __user *ext, void *data)
+{
+	struct i915_execbuffer *eb = data;
+	struct drm_i915_gem_execbuffer_ext_timeline_fences timeline_fences;
+
+	if (copy_from_user(&timeline_fences, ext, sizeof(timeline_fences)))
+		return -EFAULT;
+
+	return add_timeline_fence_array(eb, &timeline_fences);
+}
+
 static void retire_requests(struct intel_timeline *tl, struct i915_request *end)
 {
 	struct i915_request *rq, *rn;
@@ -2370,12 +2537,37 @@ static void eb_request_add(struct i915_execbuffer *eb)
 	mutex_unlock(&tl->mutex);
 }
 
+static const i915_user_extension_fn execbuf_extensions[] = {
+	[DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES] = parse_timeline_fences,
+};
+
+static int
+parse_execbuf2_extensions(struct drm_i915_gem_execbuffer2 *args,
+			  struct i915_execbuffer *eb)
+{
+	if (!(args->flags & I915_EXEC_USE_EXTENSIONS))
+		return 0;
+
+	/* The execbuf2 extension mechanism reuses cliprects_ptr. So we cannot
+	 * have another flag also using it at the same time.
+	 */
+	if (eb->args->flags & I915_EXEC_FENCE_ARRAY)
+		return -EINVAL;
+
+	if (args->num_cliprects != 0)
+		return -EINVAL;
+
+	return i915_user_extensions(u64_to_user_ptr(args->cliprects_ptr),
+				    execbuf_extensions,
+				    ARRAY_SIZE(execbuf_extensions),
+				    eb);
+}
+
 static int
 i915_gem_do_execbuffer(struct drm_device *dev,
 		       struct drm_file *file,
 		       struct drm_i915_gem_execbuffer2 *args,
-		       struct drm_i915_gem_exec_object2 *exec,
-		       struct drm_syncobj **fences)
+		       struct drm_i915_gem_exec_object2 *exec)
 {
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct i915_execbuffer eb;
@@ -2405,6 +2597,9 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	eb.batch_len = args->batch_len;
 	eb.trampoline = NULL;
 
+	eb.fences = NULL;
+	eb.num_fences = 0;
+
 	eb.batch_flags = 0;
 	if (args->flags & I915_EXEC_SECURE) {
 		if (INTEL_GEN(i915) >= 11)
@@ -2422,14 +2617,24 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	if (args->flags & I915_EXEC_IS_PINNED)
 		eb.batch_flags |= I915_DISPATCH_PINNED;
 
+	err = parse_execbuf2_extensions(args, &eb);
+	if (err)
+		goto err_ext;
+
+	err = add_fence_array(&eb);
+	if (err)
+		goto err_ext;
+
 #define IN_FENCES (I915_EXEC_FENCE_IN | I915_EXEC_FENCE_SUBMIT)
 	if (args->flags & IN_FENCES) {
 		if ((args->flags & IN_FENCES) == IN_FENCES)
 			return -EINVAL;
 
 		in_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
-		if (!in_fence)
-			return -EINVAL;
+		if (!in_fence) {
+			err = -EINVAL;
+			goto err_ext;
+		}
 	}
 #undef IN_FENCES
 
@@ -2539,8 +2744,8 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 			goto err_request;
 	}
 
-	if (fences) {
-		err = await_fence_array(&eb, fences);
+	if (eb.fences) {
+		err = await_fence_array(&eb);
 		if (err)
 			goto err_request;
 	}
@@ -2571,8 +2776,8 @@ err_request:
 	i915_request_get(eb.request);
 	eb_request_add(&eb);
 
-	if (fences)
-		signal_fence_array(&eb, fences);
+	if (eb.fences)
+		signal_fence_array(&eb);
 
 	if (out_fence) {
 		if (err == 0) {
@@ -2605,6 +2810,8 @@ err_out_fence:
 		put_unused_fd(out_fence_fd);
 err_in_fence:
 	dma_fence_put(in_fence);
+err_ext:
+	put_fence_array(eb.fences, eb.num_fences);
 	return err;
 }
 
@@ -2699,7 +2906,7 @@ i915_gem_execbuffer_ioctl(struct drm_device *dev, void *data,
 			exec2_list[i].flags = 0;
 	}
 
-	err = i915_gem_do_execbuffer(dev, file, &exec2, exec2_list, NULL);
+	err = i915_gem_do_execbuffer(dev, file, &exec2, exec2_list);
 	if (exec2.flags & __EXEC_HAS_RELOC) {
 		struct drm_i915_gem_exec_object __user *user_exec_list =
 			u64_to_user_ptr(args->buffers_ptr);
@@ -2731,7 +2938,6 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct drm_i915_gem_execbuffer2 *args = data;
 	struct drm_i915_gem_exec_object2 *exec2_list;
-	struct drm_syncobj **fences = NULL;
 	const size_t count = args->buffer_count;
 	int err;
 
@@ -2759,15 +2965,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 		return -EFAULT;
 	}
 
-	if (args->flags & I915_EXEC_FENCE_ARRAY) {
-		fences = get_fence_array(args, file);
-		if (IS_ERR(fences)) {
-			kvfree(exec2_list);
-			return PTR_ERR(fences);
-		}
-	}
-
-	err = i915_gem_do_execbuffer(dev, file, args, exec2_list, fences);
+	err = i915_gem_do_execbuffer(dev, file, args, exec2_list);
 
 	/*
 	 * Now that we have begun execution of the batchbuffer, we ignore
@@ -2808,7 +3006,6 @@ end:;
 	}
 
 	args->flags &= ~__I915_EXEC_UNKNOWN_FLAGS;
-	put_fence_array(args, fences);
 	kvfree(exec2_list);
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 24322ef08aa4..d03da2f64a49 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -4555,7 +4555,7 @@ static int gen8_emit_flush_render(struct i915_request *request,
 			vf_flush_wa = true;
 
 		/* WaForGAMHang:kbl */
-		if (IS_KBL_REVID(request->engine->i915, 0, KBL_REVID_B0))
+		if (IS_KBL_GT_REVID(request->engine->i915, 0, KBL_REVID_B0))
 			dc_flush_wa = true;
 	}
 
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 5726cd0a37e0..be5a4685c991 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -52,6 +52,24 @@
  * - Public functions to init or apply the given workaround type.
  */
 
+/*
+ * KBL revision ID ordering is bizarre; higher revision ID's map to lower
+ * steppings in some cases.  So rather than test against the revision ID
+ * directly, let's map that into our own range of increasing ID's that we
+ * can test against in a regular manner.
+ */
+
+const struct i915_rev_steppings kbl_revids[] = {
+	[0] = { .gt_stepping = KBL_REVID_A0, .disp_stepping = KBL_REVID_A0 },
+	[1] = { .gt_stepping = KBL_REVID_B0, .disp_stepping = KBL_REVID_B0 },
+	[2] = { .gt_stepping = KBL_REVID_C0, .disp_stepping = KBL_REVID_B0 },
+	[3] = { .gt_stepping = KBL_REVID_D0, .disp_stepping = KBL_REVID_B0 },
+	[4] = { .gt_stepping = KBL_REVID_F0, .disp_stepping = KBL_REVID_C0 },
+	[5] = { .gt_stepping = KBL_REVID_C0, .disp_stepping = KBL_REVID_B1 },
+	[6] = { .gt_stepping = KBL_REVID_D1, .disp_stepping = KBL_REVID_B1 },
+	[7] = { .gt_stepping = KBL_REVID_G0, .disp_stepping = KBL_REVID_C0 },
+};
+
 static void wa_init_start(struct i915_wa_list *wal, const char *name, const char *engine_name)
 {
 	wal->name = name;
@@ -470,7 +488,7 @@ static void kbl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	gen9_ctx_workarounds_init(engine, wal);
 
 	/* WaToEnableHwFixForPushConstHWBug:kbl */
-	if (IS_KBL_REVID(i915, KBL_REVID_C0, REVID_FOREVER))
+	if (IS_KBL_GT_REVID(i915, KBL_REVID_C0, REVID_FOREVER))
 		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
 				  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
 
@@ -596,8 +614,8 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN11_DIS_PICK_2ND_EU);
 }
 
-static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
-				     struct i915_wa_list *wal)
+static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine,
+				       struct i915_wa_list *wal)
 {
 	/*
 	 * Wa_1409142259:tgl
@@ -607,12 +625,28 @@ static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	 * Wa_1409207793:tgl
 	 * Wa_1409178076:tgl
 	 * Wa_1408979724:tgl
+	 * Wa_14010443199:rkl
+	 * Wa_14010698770:rkl
 	 */
 	WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
 			  GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
 
+	/* WaDisableGPGPUMidThreadPreemption:gen12 */
+	WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1,
+			    GEN9_PREEMPT_GPGPU_LEVEL_MASK,
+			    GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL);
+}
+
+static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
+				     struct i915_wa_list *wal)
+{
+	gen12_ctx_workarounds_init(engine, wal);
+
 	/*
-	 * Wa_1604555607:gen12 and Wa_1608008084:gen12
+	 * Wa_1604555607:tgl,rkl
+	 *
+	 * Note that the implementation of this workaround is further modified
+	 * according to the FF_MODE2 guidance given by Wa_1608008084:gen12.
 	 * FF_MODE2 register will return the wrong value when read. The default
 	 * value for this register is zero for all fields and there are no bit
 	 * masks. So instead of doing a RMW we should just write the GS Timer
@@ -623,11 +657,6 @@ static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	       FF_MODE2_GS_TIMER_MASK | FF_MODE2_TDS_TIMER_MASK,
 	       FF_MODE2_GS_TIMER_224  | FF_MODE2_TDS_TIMER_128,
 	       0);
-
-	/* WaDisableGPGPUMidThreadPreemption:tgl */
-	WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1,
-			    GEN9_PREEMPT_GPGPU_LEVEL_MASK,
-			    GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL);
 }
 
 static void
@@ -642,8 +671,10 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine,
 
 	wa_init_start(wal, name, engine->name);
 
-	if (IS_GEN(i915, 12))
+	if (IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915))
 		tgl_ctx_workarounds_init(engine, wal);
+	else if (IS_GEN(i915, 12))
+		gen12_ctx_workarounds_init(engine, wal);
 	else if (IS_GEN(i915, 11))
 		icl_ctx_workarounds_init(engine, wal);
 	else if (IS_CANNONLAKE(i915))
@@ -995,7 +1026,7 @@ kbl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 	gen9_gt_workarounds_init(i915, wal);
 
 	/* WaDisableDynamicCreditSharing:kbl */
-	if (IS_KBL_REVID(i915, 0, KBL_REVID_B0))
+	if (IS_KBL_GT_REVID(i915, 0, KBL_REVID_B0))
 		wa_write_or(wal,
 			    GAMT_CHKN_BIT_REG,
 			    GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING);
@@ -1176,9 +1207,16 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 }
 
 static void
-tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+gen12_gt_workarounds_init(struct drm_i915_private *i915,
+			  struct i915_wa_list *wal)
 {
 	wa_init_mcr(i915, wal);
+}
+
+static void
+tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	gen12_gt_workarounds_init(i915, wal);
 
 	/* Wa_1409420604:tgl */
 	if (IS_TGL_REVID(i915, TGL_REVID_A0, TGL_REVID_A0))
@@ -1196,8 +1234,10 @@ tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 static void
 gt_init_workarounds(struct drm_i915_private *i915, struct i915_wa_list *wal)
 {
-	if (IS_GEN(i915, 12))
+	if (IS_TIGERLAKE(i915))
 		tgl_gt_workarounds_init(i915, wal);
+	else if (IS_GEN(i915, 12))
+		gen12_gt_workarounds_init(i915, wal);
 	else if (IS_GEN(i915, 11))
 		icl_gt_workarounds_init(i915, wal);
 	else if (IS_CANNONLAKE(i915))
@@ -1630,18 +1670,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			    GEN12_DISABLE_POSH_BUSY_FF_DOP_CG);
 
 		/*
-		 * Wa_1607030317:tgl
-		 * Wa_1607186500:tgl
-		 * Wa_1607297627:tgl there is 3 entries for this WA on BSpec, 2
-		 * of then says it is fixed on B0 the other one says it is
-		 * permanent
-		 */
-		wa_masked_en(wal,
-			     GEN6_RC_SLEEP_PSMI_CONTROL,
-			     GEN12_WAIT_FOR_EVENT_POWER_DOWN_DISABLE |
-			     GEN8_RC_SEMA_IDLE_MSG_DISABLE);
-
-		/*
 		 * Wa_1606679103:tgl
 		 * (see also Wa_1606682166:icl)
 		 */
@@ -1654,22 +1682,17 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			    VSUNIT_CLKGATE_DIS_TGL);
 	}
 
-	if (IS_TIGERLAKE(i915)) {
-		/* Wa_1606931601:tgl */
+	if (IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) {
+		/* Wa_1606931601:tgl,rkl */
 		wa_masked_en(wal, GEN7_ROW_CHICKEN2, GEN12_DISABLE_EARLY_READ);
 
-		/* Wa_1409804808:tgl */
+		/* Wa_1409804808:tgl,rkl */
 		wa_masked_en(wal, GEN7_ROW_CHICKEN2,
 			     GEN12_PUSH_CONST_DEREF_HOLD_DIS);
 
-		/* Wa_1606700617:tgl */
-		wa_masked_en(wal,
-			     GEN9_CS_DEBUG_MODE1,
-			     FF_DOP_CLOCK_GATE_DISABLE);
-
 		/*
 		 * Wa_1409085225:tgl
-		 * Wa_14010229206:tgl
+		 * Wa_14010229206:tgl,rkl
 		 */
 		wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_TDL_PUSH);
 
@@ -1677,9 +1700,29 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		 * Wa_1407928979:tgl A*
 		 * Wa_18011464164:tgl B0+
 		 * Wa_22010931296:tgl B0+
+		 * Wa_14010919138:rkl
 		 */
 		wa_write_or(wal, GEN7_FF_THREAD_MODE,
 			    GEN12_FF_TESSELATION_DOP_GATE_DISABLE);
+
+		/*
+		 * Wa_1607030317:tgl
+		 * Wa_1607186500:tgl
+		 * Wa_1607297627:tgl,rkl there are multiple entries for this
+		 * WA in the BSpec; some indicate this is an A0-only WA,
+		 * others indicate it applies to all steppings.
+		 */
+		wa_masked_en(wal,
+			     GEN6_RC_SLEEP_PSMI_CONTROL,
+			     GEN12_WAIT_FOR_EVENT_POWER_DOWN_DISABLE |
+			     GEN8_RC_SEMA_IDLE_MSG_DISABLE);
+	}
+
+	if (IS_TIGERLAKE(i915)) {
+		/* Wa_1606700617:tgl */
+		wa_masked_en(wal,
+			     GEN9_CS_DEBUG_MODE1,
+			     FF_DOP_CLOCK_GATE_DISABLE);
 	}
 
 	if (IS_GEN(i915, 11)) {
@@ -1898,7 +1941,7 @@ xcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 	struct drm_i915_private *i915 = engine->i915;
 
 	/* WaKBLVECSSemaphoreWaitPoll:kbl */
-	if (IS_KBL_REVID(i915, KBL_REVID_A0, KBL_REVID_E0)) {
+	if (IS_KBL_GT_REVID(i915, KBL_REVID_A0, KBL_REVID_E0)) {
 		wa_write(wal,
 			 RING_SEMA_WAIT_POLL(engine->mmio_base),
 			 1);
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
index 73243ba59c7d..e73854dd2fe0 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
@@ -47,7 +47,10 @@ static int pulse_active(struct i915_active *active)
 
 static void pulse_free(struct kref *kref)
 {
-	kfree(container_of(kref, struct pulse, kref));
+	struct pulse *p = container_of(kref, typeof(*p), kref);
+
+	i915_active_fini(&p->active);
+	kfree(p);
 }
 
 static void pulse_put(struct pulse *p)
diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c
index 8624f5d2a1f3..34b403d47840 100644
--- a/drivers/gpu/drm/i915/gt/selftest_rps.c
+++ b/drivers/gpu/drm/i915/gt/selftest_rps.c
@@ -700,7 +700,7 @@ int live_rps_frequency_cs(void *arg)
 				f = act; /* may skip ahead [pcu granularity] */
 			}
 
-			err = -EINVAL;
+			err = -EINTR; /* ignore error, continue on with test */
 		}
 
 err_vma:
@@ -841,7 +841,7 @@ int live_rps_frequency_srm(void *arg)
 				f = act; /* may skip ahead [pcu granularity] */
 			}
 
-			err = -EINVAL;
+			err = -EINTR; /* ignore error, continue on with test */
 		}
 
 err_vma:
diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index fb5b7d3498a6..6564c989dbee 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -491,7 +491,7 @@ checked_intel_timeline_create(struct intel_gt *gt)
 	if (IS_ERR(tl))
 		return tl;
 
-	if (*tl->hwsp_seqno != tl->seqno) {
+	if (READ_ONCE(*tl->hwsp_seqno) != tl->seqno) {
 		pr_err("Timeline created with incorrect breadcrumb, found %x, expected %x\n",
 		       *tl->hwsp_seqno, tl->seqno);
 		intel_timeline_put(tl);
@@ -561,9 +561,9 @@ static int live_hwsp_engine(void *arg)
 	for (n = 0; n < count; n++) {
 		struct intel_timeline *tl = timelines[n];
 
-		if (!err && *tl->hwsp_seqno != n) {
-			pr_err("Invalid seqno stored in timeline %lu @ %x, found 0x%x\n",
-			       n, tl->hwsp_offset, *tl->hwsp_seqno);
+		if (!err && READ_ONCE(*tl->hwsp_seqno) != n) {
+			GEM_TRACE_ERR("Invalid seqno:%lu stored in timeline %llu @ %x, found 0x%x\n",
+				      n, tl->fence_context, tl->hwsp_offset, *tl->hwsp_seqno);
 			GEM_TRACE_DUMP();
 			err = -EINVAL;
 		}
@@ -633,9 +633,9 @@ out:
 	for (n = 0; n < count; n++) {
 		struct intel_timeline *tl = timelines[n];
 
-		if (!err && *tl->hwsp_seqno != n) {
-			pr_err("Invalid seqno stored in timeline %lu @ %x, found 0x%x\n",
-			       n, tl->hwsp_offset, *tl->hwsp_seqno);
+		if (!err && READ_ONCE(*tl->hwsp_seqno) != n) {
+			GEM_TRACE_ERR("Invalid seqno:%lu stored in timeline %llu @ %x, found 0x%x\n",
+				      n, tl->fence_context, tl->hwsp_offset, *tl->hwsp_seqno);
 			GEM_TRACE_DUMP();
 			err = -EINVAL;
 		}
@@ -733,7 +733,8 @@ static int live_hwsp_wrap(void *arg)
 			goto out;
 		}
 
-		if (*hwsp_seqno[0] != seqno[0] || *hwsp_seqno[1] != seqno[1]) {
+		if (READ_ONCE(*hwsp_seqno[0]) != seqno[0] ||
+		    READ_ONCE(*hwsp_seqno[1]) != seqno[1]) {
 			pr_err("Bad timeline values: found (%x, %x), expected (%x, %x)\n",
 			       *hwsp_seqno[0], *hwsp_seqno[1],
 			       seqno[0], seqno[1]);
@@ -966,9 +967,10 @@ static int live_hwsp_recycle(void *arg)
 				break;
 			}
 
-			if (*tl->hwsp_seqno != count) {
-				pr_err("Invalid seqno stored in timeline %lu @ tl->hwsp_offset, found 0x%x\n",
-				       count, *tl->hwsp_seqno);
+			if (READ_ONCE(*tl->hwsp_seqno) != count) {
+				GEM_TRACE_ERR("Invalid seqno:%lu stored in timeline %llu @ %x found 0x%x\n",
+					      count, tl->fence_context,
+					      tl->hwsp_offset, *tl->hwsp_seqno);
 				GEM_TRACE_DUMP();
 				err = -EINVAL;
 			}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index 59b27aba15c6..80e8b6c3bc8c 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -51,8 +51,8 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
  * Note that RKL uses the same firmware as TGL.
  */
 #define INTEL_UC_FIRMWARE_DEFS(fw_def, guc_def, huc_def) \
-	fw_def(ROCKETLAKE,  0, guc_def(tgl, 35, 2, 0), huc_def(tgl,  7, 0, 12)) \
-	fw_def(TIGERLAKE,   0, guc_def(tgl, 35, 2, 0), huc_def(tgl,  7, 0, 12)) \
+	fw_def(ROCKETLAKE,  0, guc_def(tgl, 35, 2, 0), huc_def(tgl,  7, 5, 0)) \
+	fw_def(TIGERLAKE,   0, guc_def(tgl, 35, 2, 0), huc_def(tgl,  7, 5, 0)) \
 	fw_def(ELKHARTLAKE, 0, guc_def(ehl, 33, 0, 4), huc_def(ehl,  9, 0, 0)) \
 	fw_def(ICELAKE,     0, guc_def(icl, 33, 0, 0), huc_def(icl,  9, 0, 0)) \
 	fw_def(COMETLAKE,   5, guc_def(cml, 33, 0, 0), huc_def(cml,  4, 0, 0)) \
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index d960d0be5bd2..1e1253207425 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -758,7 +758,6 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 	intel_engine_mask_t tmp, mask = engine->mask;
 	struct llist_node *first = NULL, *last = NULL;
 	struct intel_gt *gt = engine->gt;
-	int err;
 
 	GEM_BUG_ON(i915_active_is_idle(ref));
 
@@ -781,10 +780,8 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 		node = reuse_idle_barrier(ref, idx);
 		if (!node) {
 			node = kmem_cache_alloc(global.slab_cache, GFP_KERNEL);
-			if (!node) {
-				err = ENOMEM;
+			if (!node)
 				goto unwind;
-			}
 
 			RCU_INIT_POINTER(node->base.fence, NULL);
 			node->base.cb.func = node_retire;
@@ -832,7 +829,7 @@ unwind:
 
 		kmem_cache_free(global.slab_cache, node);
 	}
-	return err;
+	return -ENOMEM;
 }
 
 void i915_active_acquire_barrier(struct i915_active *ref)
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 372354d33f55..5ac4a999f05a 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -1204,6 +1204,12 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 	return dst;
 }
 
+static inline bool cmd_desc_is(const struct drm_i915_cmd_descriptor * const desc,
+			       const u32 cmd)
+{
+	return desc->cmd.value == (cmd & desc->cmd.mask);
+}
+
 static bool check_cmd(const struct intel_engine_cs *engine,
 		      const struct drm_i915_cmd_descriptor *desc,
 		      const u32 *cmd, u32 length)
@@ -1242,19 +1248,19 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 			 * allowed mask/value pair given in the whitelist entry.
 			 */
 			if (reg->mask) {
-				if (desc->cmd.value == MI_LOAD_REGISTER_MEM) {
+				if (cmd_desc_is(desc, MI_LOAD_REGISTER_MEM)) {
 					DRM_DEBUG("CMD: Rejected LRM to masked register 0x%08X\n",
 						  reg_addr);
 					return false;
 				}
 
-				if (desc->cmd.value == MI_LOAD_REGISTER_REG) {
+				if (cmd_desc_is(desc, MI_LOAD_REGISTER_REG)) {
 					DRM_DEBUG("CMD: Rejected LRR to masked register 0x%08X\n",
 						  reg_addr);
 					return false;
 				}
 
-				if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1) &&
+				if (cmd_desc_is(desc, MI_LOAD_REGISTER_IMM(1)) &&
 				    (offset + 2 > length ||
 				     (cmd[offset + 1] & reg->mask) != reg->value)) {
 					DRM_DEBUG("CMD: Rejected LRI to masked register 0x%08X\n",
@@ -1478,7 +1484,7 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 			break;
 		}
 
-		if (desc->cmd.value == MI_BATCH_BUFFER_START) {
+		if (cmd_desc_is(desc, MI_BATCH_BUFFER_START)) {
 			ret = check_bbstart(cmd, offset, length, batch_length,
 					    batch_addr, shadow_addr,
 					    jump_whitelist);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 5fd5af4bc855..e6918c7c0709 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -392,7 +392,7 @@ static void intel_detect_preproduction_hw(struct drm_i915_private *dev_priv)
 	pre |= IS_HSW_EARLY_SDV(dev_priv);
 	pre |= IS_SKL_REVID(dev_priv, 0, SKL_REVID_F0);
 	pre |= IS_BXT_REVID(dev_priv, 0, BXT_REVID_B_LAST);
-	pre |= IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0);
+	pre |= IS_KBL_GT_REVID(dev_priv, 0, KBL_REVID_A0);
 	pre |= IS_GLK_REVID(dev_priv, 0, GLK_REVID_A2);
 
 	if (pre) {
@@ -1846,7 +1846,8 @@ static struct drm_driver driver = {
 	 */
 	.driver_features =
 	    DRIVER_GEM |
-	    DRIVER_RENDER | DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_SYNCOBJ,
+	    DRIVER_RENDER | DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_SYNCOBJ |
+	    DRIVER_SYNCOBJ_TIMELINE,
 	.release = i915_driver_release,
 	.open = i915_driver_open,
 	.lastclose = i915_driver_lastclose,
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e4f7f6518945..1314e0e92c41 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -108,8 +108,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20200715"
-#define DRIVER_TIMESTAMP	1594811881
+#define DRIVER_DATE		"20200824"
+#define DRIVER_TIMESTAMP	1598293597
 
 struct drm_i915_gem_object;
 
@@ -506,6 +506,7 @@ struct i915_psr {
 	bool link_standby;
 	bool colorimetry_support;
 	bool psr2_enabled;
+	bool psr2_sel_fetch_enabled;
 	u8 sink_sync_latency;
 	ktime_t last_entry_attempt;
 	ktime_t last_exit;
@@ -1045,6 +1046,14 @@ struct drm_i915_private {
 	struct intel_l3_parity l3_parity;
 
 	/*
+	 * HTI (aka HDPORT) state read during initial hw readout.  Most
+	 * platforms don't have HTI, so this will just stay 0.  Those that do
+	 * will use this later to figure out which PLLs and PHYs are unavailable
+	 * for driver usage.
+	 */
+	u32 hti_state;
+
+	/*
 	 * edram size in MB.
 	 * Cannot be determined by PCIID. You must always read a register.
 	 */
@@ -1489,6 +1498,12 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define IS_ICL_WITH_PORT_F(dev_priv) \
 	IS_SUBPLATFORM(dev_priv, INTEL_ICELAKE, INTEL_SUBPLATFORM_PORTF)
 
+#define IS_TGL_U(dev_priv) \
+	IS_SUBPLATFORM(dev_priv, INTEL_TIGERLAKE, INTEL_SUBPLATFORM_ULT)
+
+#define IS_TGL_Y(dev_priv) \
+	IS_SUBPLATFORM(dev_priv, INTEL_TIGERLAKE, INTEL_SUBPLATFORM_ULX)
+
 #define SKL_REVID_A0		0x0
 #define SKL_REVID_B0		0x1
 #define SKL_REVID_C0		0x2
@@ -1509,14 +1524,34 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define IS_BXT_REVID(dev_priv, since, until) \
 	(IS_BROXTON(dev_priv) && IS_REVID(dev_priv, since, until))
 
-#define KBL_REVID_A0		0x0
-#define KBL_REVID_B0		0x1
-#define KBL_REVID_C0		0x2
-#define KBL_REVID_D0		0x3
-#define KBL_REVID_E0		0x4
+enum {
+	KBL_REVID_A0,
+	KBL_REVID_B0,
+	KBL_REVID_B1,
+	KBL_REVID_C0,
+	KBL_REVID_D0,
+	KBL_REVID_D1,
+	KBL_REVID_E0,
+	KBL_REVID_F0,
+	KBL_REVID_G0,
+};
+
+struct i915_rev_steppings {
+	u8 gt_stepping;
+	u8 disp_stepping;
+};
+
+/* Defined in intel_workarounds.c */
+extern const struct i915_rev_steppings kbl_revids[];
 
-#define IS_KBL_REVID(dev_priv, since, until) \
-	(IS_KABYLAKE(dev_priv) && IS_REVID(dev_priv, since, until))
+#define IS_KBL_GT_REVID(dev_priv, since, until) \
+	(IS_KABYLAKE(dev_priv) && \
+	 kbl_revids[INTEL_REVID(dev_priv)].gt_stepping >= since && \
+	 kbl_revids[INTEL_REVID(dev_priv)].gt_stepping <= until)
+#define IS_KBL_DISP_REVID(dev_priv, since, until) \
+	(IS_KABYLAKE(dev_priv) && \
+	 kbl_revids[INTEL_REVID(dev_priv)].disp_stepping >= since && \
+	 kbl_revids[INTEL_REVID(dev_priv)].disp_stepping <= until)
 
 #define GLK_REVID_A0		0x0
 #define GLK_REVID_A1		0x1
@@ -1665,6 +1700,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define HAS_PSR(dev_priv)		 (INTEL_INFO(dev_priv)->display.has_psr)
 #define HAS_PSR_HW_TRACKING(dev_priv) \
 	(INTEL_INFO(dev_priv)->display.has_psr_hw_tracking)
+#define HAS_PSR2_SEL_FETCH(dev_priv)	 (INTEL_GEN(dev_priv) >= 12)
 #define HAS_TRANSCODER(dev_priv, trans)	 ((INTEL_INFO(dev_priv)->cpu_transcoder_mask & BIT(trans)) != 0)
 
 #define HAS_RC6(dev_priv)		 (INTEL_INFO(dev_priv)->has_rc6)
diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index 421613219ae9..f96032c60a12 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -132,6 +132,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 	case I915_PARAM_HAS_EXEC_BATCH_FIRST:
 	case I915_PARAM_HAS_EXEC_FENCE_ARRAY:
 	case I915_PARAM_HAS_EXEC_SUBMIT_FENCE:
+	case I915_PARAM_HAS_EXEC_TIMELINE_FENCES:
 		/* For the time being all of these are always true;
 		 * if some supported hardware does not have one of these
 		 * features this value needs to be provided from
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 8d8db9ff0a48..7f139ea4a90b 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -102,6 +102,11 @@ i915_param_named(psr_safest_params, bool, 0400,
 	"is helpful to detect if PSR issues are related to bad values set in "
 	" VBT. (0=use VBT parameters, 1=use safest parameters)");
 
+i915_param_named_unsafe(enable_psr2_sel_fetch, bool, 0400,
+	"Enable PSR2 selective fetch "
+	"(0=disabled, 1=enabled) "
+	"Default: 0");
+
 i915_param_named_unsafe(force_probe, charp, 0400,
 	"Force probe the driver for specified devices. "
 	"See CONFIG_DRM_I915_FORCE_PROBE for details.");
diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h
index 53fb5ba8fbed..330c03e2b4f7 100644
--- a/drivers/gpu/drm/i915/i915_params.h
+++ b/drivers/gpu/drm/i915/i915_params.h
@@ -54,6 +54,7 @@ struct drm_printer;
 	param(int, enable_fbc, -1, 0600) \
 	param(int, enable_psr, -1, 0600) \
 	param(bool, psr_safest_params, false, 0600) \
+	param(bool, enable_psr2_sel_fetch, false, 0600) \
 	param(int, disable_power_well, -1, 0400) \
 	param(int, enable_ips, 1, 0600) \
 	param(int, invert_brightness, 0, 0600) \
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 2338f92ce490..366ddfc8df6b 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -890,6 +890,7 @@ static const struct intel_device_info rkl_info = {
 	.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) |
 		BIT(TRANSCODER_C),
 	.require_force_probe = 1,
+	.display.has_hti = 1,
 	.display.has_psr_hw_tracking = 0,
 	.platform_engine_mask =
 		BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0),
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 4e796ff4d7d0..ac691927e29d 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1898,6 +1898,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define  PWR_DOWN_LN_3_1_0		(0xb << 4)
 #define  PWR_DOWN_LN_MASK		(0xf << 4)
 #define  PWR_DOWN_LN_SHIFT		4
+#define  EDP4K2K_MODE_OVRD_EN		(1 << 3)
+#define  EDP4K2K_MODE_OVRD_OPTIMIZED	(1 << 2)
 
 #define ICL_PORT_CL_DW12(phy)		_MMIO(_ICL_PORT_CL_DW(12, phy))
 #define   ICL_LANE_ENABLE_AUX		(1 << 0)
@@ -2919,6 +2921,12 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MBUS_BBOX_CTL_S1		_MMIO(0x45040)
 #define MBUS_BBOX_CTL_S2		_MMIO(0x45044)
 
+#define HDPORT_STATE			_MMIO(0x45050)
+#define   HDPORT_DPLL_USED_MASK		REG_GENMASK(14, 12)
+#define   HDPORT_PHY_USED_DP(phy)	REG_BIT(2 * (phy) + 2)
+#define   HDPORT_PHY_USED_HDMI(phy)	REG_BIT(2 * (phy) + 1)
+#define   HDPORT_ENABLED		REG_BIT(0)
+
 /* Make render/texture TLB fetches lower priorty than associated data
  *   fetches. This is not turned on by default
  */
@@ -7870,6 +7878,7 @@ enum {
 # define CHICKEN3_DGMG_DONE_FIX_DISABLE		(1 << 2)
 
 #define CHICKEN_PAR1_1			_MMIO(0x42080)
+#define  DIS_RAM_BYPASS_PSR2_MAN_TRACK	(1 << 16)
 #define  SKL_DE_COMPRESSED_HASH_MODE	(1 << 15)
 #define  DPA_MASK_VBLANK_SRD		(1 << 15)
 #define  FORCE_ARB_IDLE_PLANES		(1 << 14)
@@ -8711,6 +8720,7 @@ enum {
 #define  PCH_GMBUSUNIT_CLOCK_GATE_DISABLE (1 << 31)
 #define  PCH_DPLUNIT_CLOCK_GATE_DISABLE (1 << 30)
 #define  PCH_DPLSUNIT_CLOCK_GATE_DISABLE (1 << 29)
+#define  PCH_DPMGUNIT_CLOCK_GATE_DISABLE (1 << 15)
 #define  PCH_CPUNIT_CLOCK_GATE_DISABLE (1 << 14)
 #define  CNP_PWM_CGE_GATING_DISABLE (1 << 13)
 #define  PCH_LP_PARTITION_LEVEL_DISABLE  (1 << 12)
@@ -9217,8 +9227,8 @@ enum {
 #define   DISPLAY_IPS_CONTROL			0x19
 #define   TGL_PCODE_TCCOLD			0x26
 #define     TGL_PCODE_EXIT_TCCOLD_DATA_L_EXIT_FAILED	REG_BIT(0)
-#define     TGL_PCODE_EXIT_TCCOLD_DATA_H_BLOCK_REQ	0
-#define     TGL_PCODE_EXIT_TCCOLD_DATA_H_UNBLOCK_REQ	REG_BIT(0)
+#define     TGL_PCODE_EXIT_TCCOLD_DATA_L_BLOCK_REQ	0
+#define     TGL_PCODE_EXIT_TCCOLD_DATA_L_UNBLOCK_REQ	REG_BIT(0)
             /* See also IPS_CTL */
 #define     IPS_PCODE_CONTROL			(1 << 30)
 #define   HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL	0x1A
@@ -10277,12 +10287,18 @@ enum skl_power_gate {
 
 #define ICL_DPCLKA_CFGCR0			_MMIO(0x164280)
 #define  ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy)	(1 << _PICK(phy, 10, 11, 24))
+#define  RKL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy)	REG_BIT((phy) + 10)
 #define  ICL_DPCLKA_CFGCR0_TC_CLK_OFF(tc_port)	(1 << ((tc_port) < PORT_TC4 ? \
 						       (tc_port) + 12 : \
 						       (tc_port) - PORT_TC4 + 21))
 #define  ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy)	((phy) * 2)
 #define  ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy)	(3 << ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy))
 #define  ICL_DPCLKA_CFGCR0_DDI_CLK_SEL(pll, phy)	((pll) << ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy))
+#define  RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy)	_PICK(phy, 0, 2, 4, 27)
+#define  RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy) \
+	(3 << RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy))
+#define  RKL_DPCLKA_CFGCR0_DDI_CLK_SEL(pll, phy) \
+	((pll) << RKL_DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(phy))
 
 /* CNL PLL */
 #define DPLL0_ENABLE		0x46010
@@ -10503,19 +10519,21 @@ enum skl_power_gate {
 
 #define _TGL_DPLL0_CFGCR0		0x164284
 #define _TGL_DPLL1_CFGCR0		0x16428C
-/* TODO: add DPLL4 */
 #define _TGL_TBTPLL_CFGCR0		0x16429C
 #define TGL_DPLL_CFGCR0(pll)		_MMIO_PLL3(pll, _TGL_DPLL0_CFGCR0, \
 						  _TGL_DPLL1_CFGCR0, \
 						  _TGL_TBTPLL_CFGCR0)
+#define RKL_DPLL_CFGCR0(pll)		_MMIO_PLL(pll, _TGL_DPLL0_CFGCR0, \
+						  _TGL_DPLL1_CFGCR0)
 
 #define _TGL_DPLL0_CFGCR1		0x164288
 #define _TGL_DPLL1_CFGCR1		0x164290
-/* TODO: add DPLL4 */
 #define _TGL_TBTPLL_CFGCR1		0x1642A0
 #define TGL_DPLL_CFGCR1(pll)		_MMIO_PLL3(pll, _TGL_DPLL0_CFGCR1, \
 						   _TGL_DPLL1_CFGCR1, \
 						   _TGL_TBTPLL_CFGCR1)
+#define RKL_DPLL_CFGCR1(pll)		_MMIO_PLL(pll, _TGL_DPLL0_CFGCR1, \
+						  _TGL_DPLL1_CFGCR1)
 
 #define _DKL_PHY1_BASE			0x168000
 #define _DKL_PHY2_BASE			0x169000
@@ -12336,4 +12354,10 @@ enum skl_power_gate {
 #define   DSB_ENABLE			(1 << 31)
 #define   DSB_STATUS			(1 << 0)
 
+#define TGL_ROOT_DEVICE_ID		0x9A00
+#define TGL_ROOT_DEVICE_MASK		0xFF00
+#define TGL_ROOT_DEVICE_SKU_MASK	0xF
+#define TGL_ROOT_DEVICE_SKU_ULX		0x2
+#define TGL_ROOT_DEVICE_SKU_ULT		0x4
+
 #endif /* _I915_REG_H_ */
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 0b2fe55e6194..7a05850ca931 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1783,11 +1783,8 @@ long i915_request_wait(struct i915_request *rq,
 	 * but at a cost of spending more power processing the workload
 	 * (bad for battery).
 	 */
-	if (flags & I915_WAIT_PRIORITY) {
-		if (!i915_request_started(rq) &&
-		    INTEL_GEN(rq->engine->i915) >= 6)
-			intel_rps_boost(rq);
-	}
+	if (flags & I915_WAIT_PRIORITY && !i915_request_started(rq))
+		intel_rps_boost(rq);
 
 	wait.tsk = current;
 	if (dma_fence_add_callback(&rq->fence, &wait.cb, request_wait_wake))
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 40c590db3c76..e2aa5bc3a6e0 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -346,6 +346,25 @@ void intel_device_info_subplatform_init(struct drm_i915_private *i915)
 		mask = BIT(INTEL_SUBPLATFORM_PORTF);
 	}
 
+	if (IS_TIGERLAKE(i915)) {
+		struct pci_dev *root, *pdev = i915->drm.pdev;
+
+		root = list_first_entry(&pdev->bus->devices, typeof(*root), bus_list);
+
+		drm_WARN_ON(&i915->drm, mask);
+		drm_WARN_ON(&i915->drm, (root->device & TGL_ROOT_DEVICE_MASK) !=
+			    TGL_ROOT_DEVICE_ID);
+
+		switch (root->device & TGL_ROOT_DEVICE_SKU_MASK) {
+		case TGL_ROOT_DEVICE_SKU_ULX:
+			mask = BIT(INTEL_SUBPLATFORM_ULX);
+			break;
+		case TGL_ROOT_DEVICE_SKU_ULT:
+			mask = BIT(INTEL_SUBPLATFORM_ULT);
+			break;
+		}
+	}
+
 	GEM_BUG_ON(mask & ~INTEL_SUBPLATFORM_BITS);
 
 	RUNTIME_INFO(i915)->platform_mask[pi] |= mask;
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index fd2385457ab6..6a3d607218aa 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -146,6 +146,7 @@ enum intel_ppgtt_type {
 	func(has_gmch); \
 	func(has_hdcp); \
 	func(has_hotplug); \
+	func(has_hti); \
 	func(has_ipc); \
 	func(has_modular_fia); \
 	func(has_overlay); \
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index cfabbe0481ab..b4bd19266b8c 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -100,12 +100,6 @@ static void gen9_init_clock_gating(struct drm_i915_private *dev_priv)
 	 */
 	I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) |
 		   DISP_FBC_MEMORY_WAKE);
-
-	if (IS_SKYLAKE(dev_priv)) {
-		/* WaDisableDopClockGating */
-		I915_WRITE(GEN7_MISCCPCTL, I915_READ(GEN7_MISCCPCTL)
-			   & ~GEN7_DOP_CLOCK_GATE_ENABLE);
-	}
 }
 
 static void bxt_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -7223,12 +7217,12 @@ static void kbl_init_clock_gating(struct drm_i915_private *dev_priv)
 	gen9_init_clock_gating(dev_priv);
 
 	/* WaDisableSDEUnitClockGating:kbl */
-	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+	if (IS_KBL_GT_REVID(dev_priv, 0, KBL_REVID_B0))
 		I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
 			   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
 	/* WaDisableGamClockGating:kbl */
-	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+	if (IS_KBL_GT_REVID(dev_priv, 0, KBL_REVID_B0))
 		I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) |
 			   GEN6_GAMUNIT_CLOCK_GATE_DISABLE);
 
@@ -7251,6 +7245,10 @@ static void skl_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	gen9_init_clock_gating(dev_priv);
 
+	/* WaDisableDopClockGating:skl */
+	I915_WRITE(GEN7_MISCCPCTL, I915_READ(GEN7_MISCCPCTL) &
+		   ~GEN7_DOP_CLOCK_GATE_ENABLE);
+
 	/* WAC6entrylatency:skl */
 	I915_WRITE(FBC_LLC_READ_CTRL, I915_READ(FBC_LLC_READ_CTRL) |
 		   FBC_LLC_FULLY_OPEN);
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 57dd6f5122ee..c1dcd4b91bda 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -331,7 +331,7 @@ static int __igt_breadcrumbs_smoketest(void *arg)
 		if (!wait) {
 			i915_sw_fence_commit(submit);
 			heap_fence_put(submit);
-			err = ENOMEM;
+			err = -ENOMEM;
 			break;
 		}
author	Dave Airlie <airlied@redhat.com>	2020-08-28 06:51:30 +0300
committer	Dave Airlie <airlied@redhat.com>	2020-08-28 07:09:31 +0300
commit	3393649977f9a8847c659e282ea290d4b703295c (patch)
tree	6590e13d360b3379d5cf16e6d1b99ba34519be99 /drivers/gpu/drm
parent	cbc2e82932ae01d3e8e81dd17b9e8ef8564c606e (diff)
parent	ced026e959bec5046afa310d6474e147b6294da2 (diff)
download	linux-3393649977f9a8847c659e282ea290d4b703295c.tar.xz