Merge tag 'drm-intel-next-2019-05-24' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

Features:
- Engine discovery query (Tvrtko)
- Support for DP YCbCr4:2:0 outputs (Gwan-gyeong)
- HDCP revocation support, refactoring (Ramalingam)
- Remove DRM_AUTH from IOCTLs which also have DRM_RENDER_ALLOW (Christian König)
- Asynchronous display power disabling (Imre)
- Perma-pin uC firmware and re-enable global reset (Fernando)
- GTT remapping for display, for bigger fb size and stride (Ville)
- Enable pipe HDR mode on ICL if only HDR planes are used (Ville)
- Kconfig to tweak the busyspin durations for i915_wait_request (Chris)
- Allow multiple user handles to the same VM (Chris)
- GT/GEM runtime pm improvements using wakerefs (Chris)
- Gen 4&5 render context support (Chris)
- Allow userspace to clone contexts on creation (Chris)
- SINGLE_TIMELINE flags for context creation (Chris)
- Allow specification of parallel execbuf (Chris)

Refactoring:
- Header refactoring (Jani)
- Move GraphicsTechnology files under gt/ (Chris)
- Sideband code refactoring (Chris)

Fixes:
- ICL DSI state readout and checker fixes (Vandita)
- GLK DSI picture corruption fix (Stanislav)
- HDMI deep color fixes (Clinton, Aditya)
- Fix driver unbinding from a device in use (Janusz)
- Fix clock gating with pipe scaling (Radhakrishna)
- Disable broken FBC on GLK (Daniel Drake)
- Miscellaneous GuC fixes (Michal)
- Fix MG PHY DP register programming (Imre)
- Add missing combo PHY lane power setup (Imre)
- Workarounds for early ICL VBT issues (Imre)
- Fix fastset vs. pfit on/off on HSW EDP transcoder (Ville)
- Add readout and state check for pch_pfit.force_thru (Ville)
- Miscellaneous display fixes and refactoring (Ville)
- Display workaround fixes (Ville)
- Enable audio even if ELD is bogus (Ville)
- Fix use-after-free in reporting create.size (Chris)
- Sideband fixes to avoid BYT hard lockups (Chris)
- Workaround fixes and improvements (Chris)

Maintainer shortcomings:
- Failure to adequately describe and give credit for all changes (Jani)
Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/87sgt3n45z.fsf@intel.com

Documentation/gpu/drm-kms-helpers.rst

@@ -181,6 +181,12 @@ Panel Helper Reference
 .. kernel-doc:: drivers/gpu/drm/drm_panel_orientation_quirks.c
    :export:
 
+HDCP Helper Functions Reference
+===============================
+
+.. kernel-doc:: drivers/gpu/drm/drm_hdcp.c
+   :export:
+
 Display Port Helper Functions Reference
 =======================================
 

drivers/gpu/drm/Makefile

@@ -17,7 +17,7 @@ drm-y       :=	drm_auth.o drm_cache.o \
 		drm_plane.o drm_color_mgmt.o drm_print.o \
 		drm_dumb_buffers.o drm_mode_config.o drm_vblank.o \
 		drm_syncobj.o drm_lease.o drm_writeback.o drm_client.o \
-		drm_atomic_uapi.o
+		drm_atomic_uapi.o drm_hdcp.o
 
 drm-$(CONFIG_DRM_LEGACY) += drm_legacy_misc.o drm_bufs.o drm_context.o drm_dma.o drm_scatter.o drm_lock.o
 drm-$(CONFIG_DRM_LIB_RANDOM) += lib/drm_random.o

drivers/gpu/drm/bridge/analogix/analogix_dp_core.c

@@ -115,7 +115,7 @@ EXPORT_SYMBOL_GPL(analogix_dp_psr_enabled);
 
 int analogix_dp_enable_psr(struct analogix_dp_device *dp)
 {
-	struct edp_vsc_psr psr_vsc;
+	struct dp_sdp psr_vsc;
 
 	if (!dp->psr_enable)
 		return 0;
@@ -127,8 +127,8 @@ int analogix_dp_enable_psr(struct analogix_dp_device *dp)
 	psr_vsc.sdp_header.HB2 = 0x2;
 	psr_vsc.sdp_header.HB3 = 0x8;
 
-	psr_vsc.DB0 = 0;
-	psr_vsc.DB1 = EDP_VSC_PSR_STATE_ACTIVE | EDP_VSC_PSR_CRC_VALUES_VALID;
+	psr_vsc.db[0] = 0;
+	psr_vsc.db[1] = EDP_VSC_PSR_STATE_ACTIVE | EDP_VSC_PSR_CRC_VALUES_VALID;
 
 	return analogix_dp_send_psr_spd(dp, &psr_vsc, true);
 }
@@ -136,7 +136,7 @@ EXPORT_SYMBOL_GPL(analogix_dp_enable_psr);
 
 int analogix_dp_disable_psr(struct analogix_dp_device *dp)
 {
-	struct edp_vsc_psr psr_vsc;
+	struct dp_sdp psr_vsc;
 	int ret;
 
 	if (!dp->psr_enable)
@@ -149,8 +149,8 @@ int analogix_dp_disable_psr(struct analogix_dp_device *dp)
 	psr_vsc.sdp_header.HB2 = 0x2;
 	psr_vsc.sdp_header.HB3 = 0x8;
 
-	psr_vsc.DB0 = 0;
-	psr_vsc.DB1 = 0;
+	psr_vsc.db[0] = 0;
+	psr_vsc.db[1] = 0;
 
 	ret = drm_dp_dpcd_writeb(&dp->aux, DP_SET_POWER, DP_SET_POWER_D0);
 	if (ret != 1) {

drivers/gpu/drm/bridge/analogix/analogix_dp_core.h

@@ -254,7 +254,7 @@ void analogix_dp_enable_scrambling(struct analogix_dp_device *dp);
 void analogix_dp_disable_scrambling(struct analogix_dp_device *dp);
 void analogix_dp_enable_psr_crc(struct analogix_dp_device *dp);
 int analogix_dp_send_psr_spd(struct analogix_dp_device *dp,
-			     struct edp_vsc_psr *vsc, bool blocking);
+			     struct dp_sdp *vsc, bool blocking);
 ssize_t analogix_dp_transfer(struct analogix_dp_device *dp,
 			     struct drm_dp_aux_msg *msg);
 

drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c

@@ -1041,7 +1041,7 @@ static ssize_t analogix_dp_get_psr_status(struct analogix_dp_device *dp)
 }
 
 int analogix_dp_send_psr_spd(struct analogix_dp_device *dp,
-			     struct edp_vsc_psr *vsc, bool blocking)
+			     struct dp_sdp *vsc, bool blocking)
 {
 	unsigned int val;
 	int ret;
@@ -1069,8 +1069,8 @@ int analogix_dp_send_psr_spd(struct analogix_dp_device *dp,
 	writel(0x5D, dp->reg_base + ANALOGIX_DP_SPD_PB3);
 
 	/* configure DB0 / DB1 values */
-	writel(vsc->DB0, dp->reg_base + ANALOGIX_DP_VSC_SHADOW_DB0);
-	writel(vsc->DB1, dp->reg_base + ANALOGIX_DP_VSC_SHADOW_DB1);
+	writel(vsc->db[0], dp->reg_base + ANALOGIX_DP_VSC_SHADOW_DB0);
+	writel(vsc->db[1], dp->reg_base + ANALOGIX_DP_VSC_SHADOW_DB1);
 
 	/* set reuse spd inforframe */
 	val = readl(dp->reg_base + ANALOGIX_DP_VIDEO_CTL_3);
@@ -1092,8 +1092,8 @@ int analogix_dp_send_psr_spd(struct analogix_dp_device *dp,
 
 	ret = readx_poll_timeout(analogix_dp_get_psr_status, dp, psr_status,
 		psr_status >= 0 &&
-		((vsc->DB1 && psr_status == DP_PSR_SINK_ACTIVE_RFB) ||
-		(!vsc->DB1 && psr_status == DP_PSR_SINK_INACTIVE)), 1500,
+		((vsc->db[1] && psr_status == DP_PSR_SINK_ACTIVE_RFB) ||
+		(!vsc->db[1] && psr_status == DP_PSR_SINK_INACTIVE)), 1500,
 		DP_TIMEOUT_PSR_LOOP_MS * 1000);
 	if (ret) {
 		dev_warn(dp->dev, "Failed to apply PSR %d\n", ret);

drivers/gpu/drm/drm_atomic_uapi.c

@@ -741,7 +741,7 @@ static int drm_atomic_connector_set_property(struct drm_connector *connector,
 		state->content_type = val;
 	} else if (property == connector->scaling_mode_property) {
 		state->scaling_mode = val;
-	} else if (property == connector->content_protection_property) {
+	} else if (property == config->content_protection_property) {
 		if (val == DRM_MODE_CONTENT_PROTECTION_ENABLED) {
 			DRM_DEBUG_KMS("only drivers can set CP Enabled\n");
 			return -EINVAL;
@@ -826,7 +826,7 @@ drm_atomic_connector_get_property(struct drm_connector *connector,
 	} else if (property == config->hdr_output_metadata_property) {
 		*val = state->hdr_output_metadata ?
 			state->hdr_output_metadata->base.id : 0;
-	} else if (property == connector->content_protection_property) {
+	} else if (property == config->content_protection_property) {
 		*val = state->content_protection;
 	} else if (property == config->writeback_fb_id_property) {
 		/* Writeback framebuffer is one-shot, write and forget */

drivers/gpu/drm/drm_connector.c

@@ -823,13 +823,6 @@ static const struct drm_prop_enum_list drm_tv_subconnector_enum_list[] = {
 DRM_ENUM_NAME_FN(drm_get_tv_subconnector_name,
 		 drm_tv_subconnector_enum_list)
 
-static struct drm_prop_enum_list drm_cp_enum_list[] = {
-	{ DRM_MODE_CONTENT_PROTECTION_UNDESIRED, "Undesired" },
-	{ DRM_MODE_CONTENT_PROTECTION_DESIRED, "Desired" },
-	{ DRM_MODE_CONTENT_PROTECTION_ENABLED, "Enabled" },
-};
-DRM_ENUM_NAME_FN(drm_get_content_protection_name, drm_cp_enum_list)
-
 static const struct drm_prop_enum_list hdmi_colorspaces[] = {
 	/* For Default case, driver will set the colorspace */
 	{ DRM_MODE_COLORIMETRY_DEFAULT, "Default" },
@@ -1515,42 +1508,6 @@ int drm_connector_attach_scaling_mode_property(struct drm_connector *connector,
 }
 EXPORT_SYMBOL(drm_connector_attach_scaling_mode_property);
 
-/**
- * drm_connector_attach_content_protection_property - attach content protection
- * property
- *
- * @connector: connector to attach CP property on.
- *
- * This is used to add support for content protection on select connectors.
- * Content Protection is intentionally vague to allow for different underlying
- * technologies, however it is most implemented by HDCP.
- *
- * The content protection will be set to &drm_connector_state.content_protection
- *
- * Returns:
- * Zero on success, negative errno on failure.
- */
-int drm_connector_attach_content_protection_property(
-		struct drm_connector *connector)
-{
-	struct drm_device *dev = connector->dev;
-	struct drm_property *prop;
-
-	prop = drm_property_create_enum(dev, 0, "Content Protection",
-					drm_cp_enum_list,
-					ARRAY_SIZE(drm_cp_enum_list));
-	if (!prop)
-		return -ENOMEM;
-
-	drm_object_attach_property(&connector->base, prop,
-				   DRM_MODE_CONTENT_PROTECTION_UNDESIRED);
-
-	connector->content_protection_property = prop;
-
-	return 0;
-}
-EXPORT_SYMBOL(drm_connector_attach_content_protection_property);
-
 /**
  * drm_mode_create_aspect_ratio_property - create aspect ratio property
  * @dev: DRM device

drivers/gpu/drm/drm_hdcp.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Intel Corporation.
+ *
+ * Authors:
+ * Ramalingam C <ramalingam.c@intel.com>
+ */
+
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/gfp.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/firmware.h>
+
+#include <drm/drm_hdcp.h>
+#include <drm/drm_sysfs.h>
+#include <drm/drm_print.h>
+#include <drm/drm_device.h>
+#include <drm/drm_property.h>
+#include <drm/drm_mode_object.h>
+#include <drm/drm_connector.h>
+
+#include "drm_internal.h"
+
+static struct hdcp_srm {
+	u32 revoked_ksv_cnt;
+	u8 *revoked_ksv_list;
+
+	/* Mutex to protect above struct member */
+	struct mutex mutex;
+} *srm_data;
+
+static inline void drm_hdcp_print_ksv(const u8 *ksv)
+{
+	DRM_DEBUG("\t%#02x, %#02x, %#02x, %#02x, %#02x\n",
+		  ksv[0], ksv[1], ksv[2], ksv[3], ksv[4]);
+}
+
+static u32 drm_hdcp_get_revoked_ksv_count(const u8 *buf, u32 vrls_length)
+{
+	u32 parsed_bytes = 0, ksv_count = 0, vrl_ksv_cnt, vrl_sz;
+
+	while (parsed_bytes < vrls_length) {
+		vrl_ksv_cnt = *buf;
+		ksv_count += vrl_ksv_cnt;
+
+		vrl_sz = (vrl_ksv_cnt * DRM_HDCP_KSV_LEN) + 1;
+		buf += vrl_sz;
+		parsed_bytes += vrl_sz;
+	}
+
+	/*
+	 * When vrls are not valid, ksvs are not considered.
+	 * Hence SRM will be discarded.
+	 */
+	if (parsed_bytes != vrls_length)
+		ksv_count = 0;
+
+	return ksv_count;
+}
+
+static u32 drm_hdcp_get_revoked_ksvs(const u8 *buf, u8 *revoked_ksv_list,
+				     u32 vrls_length)
+{
+	u32 parsed_bytes = 0, ksv_count = 0;
+	u32 vrl_ksv_cnt, vrl_ksv_sz, vrl_idx = 0;
+
+	do {
+		vrl_ksv_cnt = *buf;
+		vrl_ksv_sz = vrl_ksv_cnt * DRM_HDCP_KSV_LEN;
+
+		buf++;
+
+		DRM_DEBUG("vrl: %d, Revoked KSVs: %d\n", vrl_idx++,
+			  vrl_ksv_cnt);
+		memcpy(revoked_ksv_list, buf, vrl_ksv_sz);
+
+		ksv_count += vrl_ksv_cnt;
+		revoked_ksv_list += vrl_ksv_sz;
+		buf += vrl_ksv_sz;
+
+		parsed_bytes += (vrl_ksv_sz + 1);
+	} while (parsed_bytes < vrls_length);
+
+	return ksv_count;
+}
+
+static inline u32 get_vrl_length(const u8 *buf)
+{
+	return drm_hdcp_be24_to_cpu(buf);
+}
+
+static int drm_hdcp_parse_hdcp1_srm(const u8 *buf, size_t count)
+{
+	struct hdcp_srm_header *header;
+	u32 vrl_length, ksv_count;
+
+	if (count < (sizeof(struct hdcp_srm_header) +
+	    DRM_HDCP_1_4_VRL_LENGTH_SIZE + DRM_HDCP_1_4_DCP_SIG_SIZE)) {
+		DRM_ERROR("Invalid blob length\n");
+		return -EINVAL;
+	}
+
+	header = (struct hdcp_srm_header *)buf;
+	DRM_DEBUG("SRM ID: 0x%x, SRM Ver: 0x%x, SRM Gen No: 0x%x\n",
+		  header->srm_id,
+		  be16_to_cpu(header->srm_version), header->srm_gen_no);
+
+	WARN_ON(header->reserved);
+
+	buf = buf + sizeof(*header);
+	vrl_length = get_vrl_length(buf);
+	if (count < (sizeof(struct hdcp_srm_header) + vrl_length) ||
+	    vrl_length < (DRM_HDCP_1_4_VRL_LENGTH_SIZE +
+			  DRM_HDCP_1_4_DCP_SIG_SIZE)) {
+		DRM_ERROR("Invalid blob length or vrl length\n");
+		return -EINVAL;
+	}
+
+	/* Length of the all vrls combined */
+	vrl_length -= (DRM_HDCP_1_4_VRL_LENGTH_SIZE +
+		       DRM_HDCP_1_4_DCP_SIG_SIZE);
+
+	if (!vrl_length) {
+		DRM_ERROR("No vrl found\n");
+		return -EINVAL;
+	}
+
+	buf += DRM_HDCP_1_4_VRL_LENGTH_SIZE;
+	ksv_count = drm_hdcp_get_revoked_ksv_count(buf, vrl_length);
+	if (!ksv_count) {
+		DRM_DEBUG("Revoked KSV count is 0\n");
+		return count;
+	}
+
+	kfree(srm_data->revoked_ksv_list);
+	srm_data->revoked_ksv_list = kcalloc(ksv_count, DRM_HDCP_KSV_LEN,
+					     GFP_KERNEL);
+	if (!srm_data->revoked_ksv_list) {
+		DRM_ERROR("Out of Memory\n");
+		return -ENOMEM;
+	}
+
+	if (drm_hdcp_get_revoked_ksvs(buf, srm_data->revoked_ksv_list,
+				      vrl_length) != ksv_count) {
+		srm_data->revoked_ksv_cnt = 0;
+		kfree(srm_data->revoked_ksv_list);
+		return -EINVAL;
+	}
+
+	srm_data->revoked_ksv_cnt = ksv_count;
+	return count;
+}
+
+static int drm_hdcp_parse_hdcp2_srm(const u8 *buf, size_t count)
+{
+	struct hdcp_srm_header *header;
+	u32 vrl_length, ksv_count, ksv_sz;
+
+	if (count < (sizeof(struct hdcp_srm_header) +
+	    DRM_HDCP_2_VRL_LENGTH_SIZE + DRM_HDCP_2_DCP_SIG_SIZE)) {
+		DRM_ERROR("Invalid blob length\n");
+		return -EINVAL;
+	}
+
+	header = (struct hdcp_srm_header *)buf;
+	DRM_DEBUG("SRM ID: 0x%x, SRM Ver: 0x%x, SRM Gen No: 0x%x\n",
+		  header->srm_id & DRM_HDCP_SRM_ID_MASK,
+		  be16_to_cpu(header->srm_version), header->srm_gen_no);
+
+	if (header->reserved)
+		return -EINVAL;
+
+	buf = buf + sizeof(*header);
+	vrl_length = get_vrl_length(buf);
+
+	if (count < (sizeof(struct hdcp_srm_header) + vrl_length) ||
+	    vrl_length < (DRM_HDCP_2_VRL_LENGTH_SIZE +
+	    DRM_HDCP_2_DCP_SIG_SIZE)) {
+		DRM_ERROR("Invalid blob length or vrl length\n");
+		return -EINVAL;
+	}
+
+	/* Length of the all vrls combined */
+	vrl_length -= (DRM_HDCP_2_VRL_LENGTH_SIZE +
+		       DRM_HDCP_2_DCP_SIG_SIZE);
+
+	if (!vrl_length) {
+		DRM_ERROR("No vrl found\n");
+		return -EINVAL;
+	}
+
+	buf += DRM_HDCP_2_VRL_LENGTH_SIZE;
+	ksv_count = (*buf << 2) | DRM_HDCP_2_KSV_COUNT_2_LSBITS(*(buf + 1));
+	if (!ksv_count) {
+		DRM_DEBUG("Revoked KSV count is 0\n");
+		return count;
+	}
+
+	kfree(srm_data->revoked_ksv_list);
+	srm_data->revoked_ksv_list = kcalloc(ksv_count, DRM_HDCP_KSV_LEN,
+					     GFP_KERNEL);
+	if (!srm_data->revoked_ksv_list) {
+		DRM_ERROR("Out of Memory\n");
+		return -ENOMEM;
+	}
+
+	ksv_sz = ksv_count * DRM_HDCP_KSV_LEN;
+	buf += DRM_HDCP_2_NO_OF_DEV_PLUS_RESERVED_SZ;
+
+	DRM_DEBUG("Revoked KSVs: %d\n", ksv_count);
+	memcpy(srm_data->revoked_ksv_list, buf, ksv_sz);
+
+	srm_data->revoked_ksv_cnt = ksv_count;
+	return count;
+}
+
+static inline bool is_srm_version_hdcp1(const u8 *buf)
+{
+	return *buf == (u8)(DRM_HDCP_1_4_SRM_ID << 4);
+}
+
+static inline bool is_srm_version_hdcp2(const u8 *buf)
+{
+	return *buf == (u8)(DRM_HDCP_2_SRM_ID << 4 | DRM_HDCP_2_INDICATOR);
+}
+
+static void drm_hdcp_srm_update(const u8 *buf, size_t count)
+{
+	if (count < sizeof(struct hdcp_srm_header))
+		return;
+
+	if (is_srm_version_hdcp1(buf))
+		drm_hdcp_parse_hdcp1_srm(buf, count);
+	else if (is_srm_version_hdcp2(buf))
+		drm_hdcp_parse_hdcp2_srm(buf, count);
+}
+
+static void drm_hdcp_request_srm(struct drm_device *drm_dev)
+{
+	char fw_name[36] = "display_hdcp_srm.bin";
+	const struct firmware *fw;
+
+	int ret;
+
+	ret = request_firmware_direct(&fw, (const char *)fw_name,
+				      drm_dev->dev);
+	if (ret < 0)
+		goto exit;
+
+	if (fw->size && fw->data)
+		drm_hdcp_srm_update(fw->data, fw->size);
+
+exit:
+	release_firmware(fw);
+}
+
+/**
+ * drm_hdcp_check_ksvs_revoked - Check the revoked status of the IDs
+ *
+ * @drm_dev: drm_device for which HDCP revocation check is requested
+ * @ksvs: List of KSVs (HDCP receiver IDs)
+ * @ksv_count: KSV count passed in through @ksvs
+ *
+ * This function reads the HDCP System renewability Message(SRM Table)
+ * from userspace as a firmware and parses it for the revoked HDCP
+ * KSVs(Receiver IDs) detected by DCP LLC. Once the revoked KSVs are known,
+ * revoked state of the KSVs in the list passed in by display drivers are
+ * decided and response is sent.
+ *
+ * SRM should be presented in the name of "display_hdcp_srm.bin".
+ *
+ * Returns:
+ * TRUE on any of the KSV is revoked, else FALSE.
+ */
+bool drm_hdcp_check_ksvs_revoked(struct drm_device *drm_dev, u8 *ksvs,
+				 u32 ksv_count)
+{
+	u32 rev_ksv_cnt, cnt, i, j;
+	u8 *rev_ksv_list;
+
+	if (!srm_data)
+		return false;
+
+	mutex_lock(&srm_data->mutex);
+	drm_hdcp_request_srm(drm_dev);
+
+	rev_ksv_cnt = srm_data->revoked_ksv_cnt;
+	rev_ksv_list = srm_data->revoked_ksv_list;
+
+	/* If the Revoked ksv list is empty */
+	if (!rev_ksv_cnt || !rev_ksv_list) {
+		mutex_unlock(&srm_data->mutex);
+		return false;
+	}
+
+	for  (cnt = 0; cnt < ksv_count; cnt++) {
+		rev_ksv_list = srm_data->revoked_ksv_list;
+		for (i = 0; i < rev_ksv_cnt; i++) {
+			for (j = 0; j < DRM_HDCP_KSV_LEN; j++)
+				if (ksvs[j] != rev_ksv_list[j]) {
+					break;
+				} else if (j == (DRM_HDCP_KSV_LEN - 1)) {
+					DRM_DEBUG("Revoked KSV is ");
+					drm_hdcp_print_ksv(ksvs);
+					mutex_unlock(&srm_data->mutex);
+					return true;
+				}
+			/* Move the offset to next KSV in the revoked list */
+			rev_ksv_list += DRM_HDCP_KSV_LEN;
+		}
+
+		/* Iterate to next ksv_offset */
+		ksvs += DRM_HDCP_KSV_LEN;
+	}
+	mutex_unlock(&srm_data->mutex);
+	return false;
+}
+EXPORT_SYMBOL_GPL(drm_hdcp_check_ksvs_revoked);
+
+int drm_setup_hdcp_srm(struct class *drm_class)
+{
+	srm_data = kzalloc(sizeof(*srm_data), GFP_KERNEL);
+	if (!srm_data)
+		return -ENOMEM;
+	mutex_init(&srm_data->mutex);
+
+	return 0;
+}
+
+void drm_teardown_hdcp_srm(struct class *drm_class)
+{
+	if (srm_data) {
+		kfree(srm_data->revoked_ksv_list);
+		kfree(srm_data);
+	}
+}
+
+static struct drm_prop_enum_list drm_cp_enum_list[] = {
+	{ DRM_MODE_CONTENT_PROTECTION_UNDESIRED, "Undesired" },
+	{ DRM_MODE_CONTENT_PROTECTION_DESIRED, "Desired" },
+	{ DRM_MODE_CONTENT_PROTECTION_ENABLED, "Enabled" },
+};
+DRM_ENUM_NAME_FN(drm_get_content_protection_name, drm_cp_enum_list)
+
+/**
+ * drm_connector_attach_content_protection_property - attach content protection
+ * property
+ *
+ * @connector: connector to attach CP property on.
+ *
+ * This is used to add support for content protection on select connectors.
+ * Content Protection is intentionally vague to allow for different underlying
+ * technologies, however it is most implemented by HDCP.
+ *
+ * The content protection will be set to &drm_connector_state.content_protection
+ *
+ * Returns:
+ * Zero on success, negative errno on failure.
+ */
+int drm_connector_attach_content_protection_property(
+		struct drm_connector *connector)
+{
+	struct drm_device *dev = connector->dev;
+	struct drm_property *prop =
+			dev->mode_config.content_protection_property;
+
+	if (!prop)
+		prop = drm_property_create_enum(dev, 0, "Content Protection",
+						drm_cp_enum_list,
+						ARRAY_SIZE(drm_cp_enum_list));
+	if (!prop)
+		return -ENOMEM;
+
+	drm_object_attach_property(&connector->base, prop,
+				   DRM_MODE_CONTENT_PROTECTION_UNDESIRED);
+	dev->mode_config.content_protection_property = prop;
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_connector_attach_content_protection_property);

drivers/gpu/drm/drm_internal.h

@@ -108,6 +108,7 @@ void drm_sysfs_connector_remove(struct drm_connector *connector);
 void drm_sysfs_lease_event(struct drm_device *dev);
 
 /* drm_gem.c */
+struct drm_gem_object;
 int drm_gem_init(struct drm_device *dev);
 void drm_gem_destroy(struct drm_device *dev);
 int drm_gem_handle_create_tail(struct drm_file *file_priv,
@@ -203,3 +204,7 @@ int drm_syncobj_query_ioctl(struct drm_device *dev, void *data,
 void drm_framebuffer_print_info(struct drm_printer *p, unsigned int indent,
 				const struct drm_framebuffer *fb);
 int drm_framebuffer_debugfs_init(struct drm_minor *minor);
+
+/* drm_hdcp.c */
+int drm_setup_hdcp_srm(struct class *drm_class);
+void drm_teardown_hdcp_srm(struct class *drm_class);

drivers/gpu/drm/drm_sysfs.c

@@ -78,6 +78,7 @@ int drm_sysfs_init(void)
 	}
 
 	drm_class->devnode = drm_devnode;
+	drm_setup_hdcp_srm(drm_class);
 	return 0;
 }
 
@@ -90,6 +91,7 @@ void drm_sysfs_destroy(void)
 {
 	if (IS_ERR_OR_NULL(drm_class))
 		return;
+	drm_teardown_hdcp_srm(drm_class);
 	class_remove_file(drm_class, &class_attr_version.attr);
 	class_destroy(drm_class);
 	drm_class = NULL;

drivers/gpu/drm/i915/Kconfig

@@ -133,3 +133,9 @@ depends on DRM_I915
 depends on EXPERT
 source "drivers/gpu/drm/i915/Kconfig.debug"
 endmenu
+
+menu "drm/i915 Profile Guided Optimisation"
+	visible if EXPERT
+	depends on DRM_I915
+	source "drivers/gpu/drm/i915/Kconfig.profile"
+endmenu

drivers/gpu/drm/i915/Kconfig.profile

+config DRM_I915_SPIN_REQUEST
+	int
+	default 5 # microseconds
+	help
+	  Before sleeping waiting for a request (GPU operation) to complete,
+	  we may spend some time polling for its completion. As the IRQ may
+	  take a non-negligible time to setup, we do a short spin first to
+	  check if the request will complete in the time it would have taken
+	  us to enable the interrupt.
+
+	  May be 0 to disable the initial spin. In practice, we estimate
+	  the cost of enabling the interrupt (if currently disabled) to be
+	  a few microseconds.

drivers/gpu/drm/i915/Makefile

@@ -35,32 +35,56 @@ subdir-ccflags-y += \
 # Extra header tests
 include $(src)/Makefile.header-test
 
+subdir-ccflags-y += -I$(src)
+
 # Please keep these build lists sorted!
 
 # core driver code
 i915-y += i915_drv.o \
 	  i915_irq.o \
-	  i915_memcpy.o \
-	  i915_mm.o \
 	  i915_params.o \
 	  i915_pci.o \
-	  i915_reset.o \
 	  i915_suspend.o \
-	  i915_sw_fence.o \
-	  i915_syncmap.o \
 	  i915_sysfs.o \
-	  i915_user_extensions.o \
 	  intel_csr.o \
 	  intel_device_info.o \
 	  intel_pm.o \
 	  intel_runtime_pm.o \
-	  intel_workarounds.o
+	  intel_wakeref.o \
+	  intel_uncore.o
+
+# core library code
+i915-y += \
+	i915_memcpy.o \
+	i915_mm.o \
+	i915_sw_fence.o \
+	i915_syncmap.o \
+	i915_user_extensions.o
 
 i915-$(CONFIG_COMPAT)   += i915_ioc32.o
 i915-$(CONFIG_DEBUG_FS) += i915_debugfs.o intel_pipe_crc.o
 i915-$(CONFIG_PERF_EVENTS) += i915_pmu.o
 
-# GEM code
+# "Graphics Technology" (aka we talk to the gpu)
+obj-y += gt/
+gt-y += \
+	gt/intel_breadcrumbs.o \
+	gt/intel_context.o \
+	gt/intel_engine_cs.o \
+	gt/intel_engine_pm.o \
+	gt/intel_gt_pm.o \
+	gt/intel_hangcheck.o \
+	gt/intel_lrc.o \
+	gt/intel_reset.o \
+	gt/intel_ringbuffer.o \
+	gt/intel_mocs.o \
+	gt/intel_sseu.o \
+	gt/intel_workarounds.o
+gt-$(CONFIG_DRM_I915_SELFTEST) += \
+	gt/mock_engine.o
+i915-y += $(gt-y)
+
+# GEM (Graphics Execution Management) code
 i915-y += \
 	  i915_active.o \
 	  i915_cmd_parser.o \
@@ -75,6 +99,7 @@ i915-y += \
 	  i915_gem_internal.o \
 	  i915_gem.o \
 	  i915_gem_object.o \
+	  i915_gem_pm.o \
 	  i915_gem_render_state.o \
 	  i915_gem_shrinker.o \
 	  i915_gem_stolen.o \
@@ -88,14 +113,6 @@ i915-y += \
 	  i915_timeline.o \
 	  i915_trace_points.o \
 	  i915_vma.o \
-	  intel_breadcrumbs.o \
-	  intel_context.o \
-	  intel_engine_cs.o \
-	  intel_hangcheck.o \
-	  intel_lrc.o \
-	  intel_mocs.o \
-	  intel_ringbuffer.o \
-	  intel_uncore.o \
 	  intel_wopcm.o
 
 # general-purpose microcontroller (GuC) support
@@ -159,8 +176,8 @@ i915-y += dvo_ch7017.o \
 	  intel_dsi_dcs_backlight.o \
 	  intel_dsi_vbt.o \
 	  intel_dvo.o \
+	  intel_gmbus.o \
 	  intel_hdmi.o \
-	  intel_i2c.o \
 	  intel_lspcon.o \
 	  intel_lvds.o \
 	  intel_panel.o \
@@ -176,6 +193,7 @@ i915-$(CONFIG_DRM_I915_SELFTEST) += \
 	selftests/i915_random.o \
 	selftests/i915_selftest.o \
 	selftests/igt_flush_test.o \
+	selftests/igt_gem_utils.o \
 	selftests/igt_live_test.o \
 	selftests/igt_reset.o \
 	selftests/igt_spinner.o

drivers/gpu/drm/i915/Makefile.header-test

@@ -4,37 +4,65 @@
 # Test the headers are compilable as standalone units
 header_test := \
 	i915_active_types.h \
+	i915_debugfs.h \
+	i915_drv.h \
 	i915_gem_context_types.h \
+	i915_gem_pm.h \
+	i915_irq.h \
+	i915_params.h \
 	i915_priolist_types.h \
+	i915_reg.h \
 	i915_scheduler_types.h \
 	i915_timeline_types.h \
+	i915_utils.h \
+	intel_acpi.h \
+	intel_atomic.h \
 	intel_atomic_plane.h \
 	intel_audio.h \
+	intel_bios.h \
 	intel_cdclk.h \
 	intel_color.h \
+	intel_combo_phy.h \
 	intel_connector.h \
-	intel_context_types.h \
 	intel_crt.h \
 	intel_csr.h \
 	intel_ddi.h \
 	intel_dp.h \
+	intel_dp_aux_backlight.h \
+	intel_dp_link_training.h \
+	intel_dp_mst.h \
+	intel_dpio_phy.h \
+	intel_dpll_mgr.h \
+	intel_drv.h \
+	intel_dsi.h \
+	intel_dsi_dcs_backlight.h \
 	intel_dvo.h \
-	intel_engine_types.h \
+	intel_dvo_dev.h \
 	intel_fbc.h \
 	intel_fbdev.h \
+	intel_fifo_underrun.h \
 	intel_frontbuffer.h \
+	intel_gmbus.h \
 	intel_hdcp.h \
 	intel_hdmi.h \
+	intel_hotplug.h \
+	intel_lpe_audio.h \
 	intel_lspcon.h \
 	intel_lvds.h \
+	intel_overlay.h \
 	intel_panel.h \
 	intel_pipe_crc.h \
 	intel_pm.h \
 	intel_psr.h \
+	intel_quirks.h \
+	intel_runtime_pm.h \
 	intel_sdvo.h \
+	intel_sideband.h \
 	intel_sprite.h \
 	intel_tv.h \
-	intel_workarounds_types.h
+	intel_uncore.h \
+	intel_vdsc.h \
+	intel_wakeref.h
 
 quiet_cmd_header_test = HDRTEST $@
       cmd_header_test = echo "\#include \"$(<F)\"" > $@

drivers/gpu/drm/i915/dvo_ch7017.c

@@ -25,7 +25,8 @@
  *
  */
 
-#include "dvo.h"
+#include "intel_drv.h"
+#include "intel_dvo_dev.h"
 
 #define CH7017_TV_DISPLAY_MODE		0x00
 #define CH7017_FLICKER_FILTER		0x01

drivers/gpu/drm/i915/dvo_ch7xxx.c

@@ -26,7 +26,8 @@ SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 **************************************************************************/
 
-#include "dvo.h"
+#include "intel_drv.h"
+#include "intel_dvo_dev.h"
 
 #define CH7xxx_REG_VID		0x4a
 #define CH7xxx_REG_DID		0x4b

drivers/gpu/drm/i915/dvo_ivch.c

@@ -29,7 +29,8 @@
  *
  */
 
-#include "dvo.h"
+#include "intel_drv.h"
+#include "intel_dvo_dev.h"
 
 /*
  * register definitions for the i82807aa.

drivers/gpu/drm/i915/dvo_ns2501.c

@@ -26,9 +26,10 @@
  *
  */
 
-#include "dvo.h"
-#include "i915_reg.h"
 #include "i915_drv.h"
+#include "i915_reg.h"
+#include "intel_drv.h"
+#include "intel_dvo_dev.h"
 
 #define NS2501_VID 0x1305
 #define NS2501_DID 0x6726

drivers/gpu/drm/i915/dvo_sil164.c

@@ -26,7 +26,8 @@ SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 **************************************************************************/
 
-#include "dvo.h"
+#include "intel_drv.h"
+#include "intel_dvo_dev.h"
 
 #define SIL164_VID 0x0001
 #define SIL164_DID 0x0006

drivers/gpu/drm/i915/dvo_tfp410.c

@@ -25,7 +25,8 @@
  *
  */
 
-#include "dvo.h"
+#include "intel_drv.h"
+#include "intel_dvo_dev.h"
 
 /* register definitions according to the TFP410 data sheet */
 #define TFP410_VID		0x014C

drivers/gpu/drm/i915/gt/Makefile

+# Extra header tests
+include $(src)/Makefile.header-test

drivers/gpu/drm/i915/gt/Makefile.header-test

+# SPDX-License-Identifier: MIT
+# Copyright © 2019 Intel Corporation
+
+# Test the headers are compilable as standalone units
+header_test := $(notdir $(wildcard $(src)/*.h))
+
+quiet_cmd_header_test = HDRTEST $@
+      cmd_header_test = echo "\#include \"$(<F)\"" > $@
+
+header_test_%.c: %.h
+	$(call cmd,header_test)
+
+extra-$(CONFIG_DRM_I915_WERROR) += \
+	$(foreach h,$(header_test),$(patsubst %.h,header_test_%.o,$(h)))
+
+clean-files += $(foreach h,$(header_test),$(patsubst %.h,header_test_%.c,$(h)))

drivers/gpu/drm/i915/intel_breadcrumbs.c → drivers/gpu/drm/i915/gt/intel_breadcrumbs.c

@@ -81,6 +81,22 @@ static inline bool __request_completed(const struct i915_request *rq)
 	return i915_seqno_passed(__hwsp_seqno(rq), rq->fence.seqno);
 }
 
+__maybe_unused static bool
+check_signal_order(struct intel_context *ce, struct i915_request *rq)
+{
+	if (!list_is_last(&rq->signal_link, &ce->signals) &&
+	    i915_seqno_passed(rq->fence.seqno,
+			      list_next_entry(rq, signal_link)->fence.seqno))
+		return false;
+
+	if (!list_is_first(&rq->signal_link, &ce->signals) &&
+	    i915_seqno_passed(list_prev_entry(rq, signal_link)->fence.seqno,
+			      rq->fence.seqno))
+		return false;
+
+	return true;
+}
+
 static bool
 __dma_fence_signal(struct dma_fence *fence)
 {
@@ -130,6 +146,8 @@ void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
 			struct i915_request *rq =
 				list_entry(pos, typeof(*rq), signal_link);
 
+			GEM_BUG_ON(!check_signal_order(ce, rq));
+
 			if (!__request_completed(rq))
 				break;
 
@@ -312,6 +330,7 @@ bool i915_request_enable_breadcrumb(struct i915_request *rq)
 		list_add(&rq->signal_link, pos);
 		if (pos == &ce->signals) /* catch transitions from empty list */
 			list_move_tail(&ce->signal_link, &b->signalers);
+		GEM_BUG_ON(!check_signal_order(ce, rq));
 
 		set_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
 		spin_unlock(&b->irq_lock);

drivers/gpu/drm/i915/gt/intel_context.c

+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "i915_gem_context.h"
+#include "i915_globals.h"
+
+#include "intel_context.h"
+#include "intel_engine.h"
+#include "intel_engine_pm.h"
+
+static struct i915_global_context {
+	struct i915_global base;
+	struct kmem_cache *slab_ce;
+} global;
+
+static struct intel_context *intel_context_alloc(void)
+{
+	return kmem_cache_zalloc(global.slab_ce, GFP_KERNEL);
+}
+
+void intel_context_free(struct intel_context *ce)
+{
+	kmem_cache_free(global.slab_ce, ce);
+}
+
+struct intel_context *
+intel_context_create(struct i915_gem_context *ctx,
+		     struct intel_engine_cs *engine)
+{
+	struct intel_context *ce;
+
+	ce = intel_context_alloc();
+	if (!ce)
+		return ERR_PTR(-ENOMEM);
+
+	intel_context_init(ce, ctx, engine);
+	return ce;
+}
+
+int __intel_context_do_pin(struct intel_context *ce)
+{
+	int err;
+
+	if (mutex_lock_interruptible(&ce->pin_mutex))
+		return -EINTR;
+
+	if (likely(!atomic_read(&ce->pin_count))) {
+		intel_wakeref_t wakeref;
+
+		err = 0;
+		with_intel_runtime_pm(ce->engine->i915, wakeref)
+			err = ce->ops->pin(ce);
+		if (err)
+			goto err;
+
+		i915_gem_context_get(ce->gem_context); /* for ctx->ppgtt */
+
+		intel_context_get(ce);
+		smp_mb__before_atomic(); /* flush pin before it is visible */
+	}
+
+	atomic_inc(&ce->pin_count);
+	GEM_BUG_ON(!intel_context_is_pinned(ce)); /* no overflow! */
+
+	mutex_unlock(&ce->pin_mutex);
+	return 0;
+
+err:
+	mutex_unlock(&ce->pin_mutex);
+	return err;
+}
+
+void intel_context_unpin(struct intel_context *ce)
+{
+	if (likely(atomic_add_unless(&ce->pin_count, -1, 1)))
+		return;
+
+	/* We may be called from inside intel_context_pin() to evict another */
+	intel_context_get(ce);
+	mutex_lock_nested(&ce->pin_mutex, SINGLE_DEPTH_NESTING);
+
+	if (likely(atomic_dec_and_test(&ce->pin_count))) {
+		ce->ops->unpin(ce);
+
+		i915_gem_context_put(ce->gem_context);
+		intel_context_put(ce);
+	}
+
+	mutex_unlock(&ce->pin_mutex);
+	intel_context_put(ce);
+}
+
+static void intel_context_retire(struct i915_active_request *active,
+				 struct i915_request *rq)
+{
+	struct intel_context *ce =
+		container_of(active, typeof(*ce), active_tracker);
+
+	intel_context_unpin(ce);
+}
+
+void
+intel_context_init(struct intel_context *ce,
+		   struct i915_gem_context *ctx,
+		   struct intel_engine_cs *engine)
+{
+	GEM_BUG_ON(!engine->cops);
+
+	kref_init(&ce->ref);
+
+	ce->gem_context = ctx;
+	ce->engine = engine;
+	ce->ops = engine->cops;
+	ce->sseu = engine->sseu;
+	ce->saturated = 0;
+
+	INIT_LIST_HEAD(&ce->signal_link);
+	INIT_LIST_HEAD(&ce->signals);
+
+	mutex_init(&ce->pin_mutex);
+
+	i915_active_request_init(&ce->active_tracker,
+				 NULL, intel_context_retire);
+}
+
+static void i915_global_context_shrink(void)
+{
+	kmem_cache_shrink(global.slab_ce);
+}
+
+static void i915_global_context_exit(void)
+{
+	kmem_cache_destroy(global.slab_ce);
+}
+
+static struct i915_global_context global = { {
+	.shrink = i915_global_context_shrink,
+	.exit = i915_global_context_exit,
+} };
+
+int __init i915_global_context_init(void)
+{
+	global.slab_ce = KMEM_CACHE(intel_context, SLAB_HWCACHE_ALIGN);
+	if (!global.slab_ce)
+		return -ENOMEM;
+
+	i915_global_register(&global.base);
+	return 0;
+}
+
+void intel_context_enter_engine(struct intel_context *ce)
+{
+	intel_engine_pm_get(ce->engine);
+}
+
+void intel_context_exit_engine(struct intel_context *ce)
+{
+	ce->saturated = 0;
+	intel_engine_pm_put(ce->engine);
+}
+
+struct i915_request *intel_context_create_request(struct intel_context *ce)
+{
+	struct i915_request *rq;
+	int err;
+
+	err = intel_context_pin(ce);
+	if (unlikely(err))
+		return ERR_PTR(err);
+
+	rq = i915_request_create(ce);
+	intel_context_unpin(ce);
+
+	return rq;
+}

drivers/gpu/drm/i915/intel_context.h → drivers/gpu/drm/i915/gt/intel_context.h

@@ -12,58 +12,66 @@
 #include "intel_context_types.h"
 #include "intel_engine_types.h"
 
-struct intel_context *intel_context_alloc(void);
-void intel_context_free(struct intel_context *ce);
-
 void intel_context_init(struct intel_context *ce,
 			struct i915_gem_context *ctx,
 			struct intel_engine_cs *engine);
 
-/**
- * intel_context_lookup - Find the matching HW context for this (ctx, engine)
- * @ctx - the parent GEM context
- * @engine - the target HW engine
- *
- * May return NULL if the HW context hasn't been instantiated (i.e. unused).
- */
 struct intel_context *
-intel_context_lookup(struct i915_gem_context *ctx,
+intel_context_create(struct i915_gem_context *ctx,
 		     struct intel_engine_cs *engine);
 
+void intel_context_free(struct intel_context *ce);
+
 /**
- * intel_context_pin_lock - Stablises the 'pinned' status of the HW context
- * @ctx - the parent GEM context
- * @engine - the target HW engine
+ * intel_context_lock_pinned - Stablises the 'pinned' status of the HW context
+ * @ce - the context
  *
  * Acquire a lock on the pinned status of the HW context, such that the context
  * can neither be bound to the GPU or unbound whilst the lock is held, i.e.
  * intel_context_is_pinned() remains stable.
  */
-struct intel_context *
-intel_context_pin_lock(struct i915_gem_context *ctx,
-		       struct intel_engine_cs *engine);
+static inline int intel_context_lock_pinned(struct intel_context *ce)
+	__acquires(ce->pin_mutex)
+{
+	return mutex_lock_interruptible(&ce->pin_mutex);
+}
 
+/**
+ * intel_context_is_pinned - Reports the 'pinned' status
+ * @ce - the context
+ *
+ * While in use by the GPU, the context, along with its ring and page
+ * tables is pinned into memory and the GTT.
+ *
+ * Returns: true if the context is currently pinned for use by the GPU.
+ */
 static inline bool
 intel_context_is_pinned(struct intel_context *ce)
 {
 	return atomic_read(&ce->pin_count);
 }
 
-static inline void intel_context_pin_unlock(struct intel_context *ce)
-__releases(ce->pin_mutex)
+/**
+ * intel_context_unlock_pinned - Releases the earlier locking of 'pinned' status
+ * @ce - the context
+ *
+ * Releases the lock earlier acquired by intel_context_unlock_pinned().
+ */
+static inline void intel_context_unlock_pinned(struct intel_context *ce)
+	__releases(ce->pin_mutex)
 {
 	mutex_unlock(&ce->pin_mutex);
 }
 
-struct intel_context *
-__intel_context_insert(struct i915_gem_context *ctx,
-		       struct intel_engine_cs *engine,
-		       struct intel_context *ce);
-void
-__intel_context_remove(struct intel_context *ce);
+int __intel_context_do_pin(struct intel_context *ce);
 
-struct intel_context *
-intel_context_pin(struct i915_gem_context *ctx, struct intel_engine_cs *engine);
+static inline int intel_context_pin(struct intel_context *ce)
+{
+	if (likely(atomic_inc_not_zero(&ce->pin_count)))
+		return 0;
+
+	return __intel_context_do_pin(ce);
+}
 
 static inline void __intel_context_pin(struct intel_context *ce)
 {
@@ -73,6 +81,27 @@ static inline void __intel_context_pin(struct intel_context *ce)
 
 void intel_context_unpin(struct intel_context *ce);
 
+void intel_context_enter_engine(struct intel_context *ce);
+void intel_context_exit_engine(struct intel_context *ce);
+
+static inline void intel_context_enter(struct intel_context *ce)
+{
+	if (!ce->active_count++)
+		ce->ops->enter(ce);
+}
+
+static inline void intel_context_mark_active(struct intel_context *ce)
+{
+	++ce->active_count;
+}
+
+static inline void intel_context_exit(struct intel_context *ce)
+{
+	GEM_BUG_ON(!ce->active_count);
+	if (!--ce->active_count)
+		ce->ops->exit(ce);
+}
+
 static inline struct intel_context *intel_context_get(struct intel_context *ce)
 {
 	kref_get(&ce->ref);
@@ -84,4 +113,18 @@ static inline void intel_context_put(struct intel_context *ce)
 	kref_put(&ce->ref, ce->ops->destroy);
 }
 
+static inline void intel_context_timeline_lock(struct intel_context *ce)
+	__acquires(&ce->ring->timeline->mutex)
+{
+	mutex_lock(&ce->ring->timeline->mutex);
+}
+
+static inline void intel_context_timeline_unlock(struct intel_context *ce)
+	__releases(&ce->ring->timeline->mutex)
+{
+	mutex_unlock(&ce->ring->timeline->mutex);
+}
+
+struct i915_request *intel_context_create_request(struct intel_context *ce);
+
 #endif /* __INTEL_CONTEXT_H__ */

drivers/gpu/drm/i915/intel_context_types.h → drivers/gpu/drm/i915/gt/intel_context_types.h

@@ -10,11 +10,11 @@
 #include <linux/kref.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
-#include <linux/rbtree.h>
 #include <linux/types.h>
 
 #include "i915_active_types.h"
 #include "intel_engine_types.h"
+#include "intel_sseu.h"
 
 struct i915_gem_context;
 struct i915_vma;
@@ -25,20 +25,13 @@ struct intel_context_ops {
 	int (*pin)(struct intel_context *ce);
 	void (*unpin)(struct intel_context *ce);
 
+	void (*enter)(struct intel_context *ce);
+	void (*exit)(struct intel_context *ce);
+
 	void (*reset)(struct intel_context *ce);
 	void (*destroy)(struct kref *kref);
 };
 
-/*
- * Powergating configuration for a particular (context,engine).
- */
-struct intel_sseu {
-	u8 slice_mask;
-	u8 subslice_mask;
-	u8 min_eus_per_subslice;
-	u8 max_eus_per_subslice;
-};
-
 struct intel_context {
 	struct kref ref;
 
@@ -46,7 +39,6 @@ struct intel_context {
 	struct intel_engine_cs *engine;
 	struct intel_engine_cs *active;
 
-	struct list_head active_link;
 	struct list_head signal_link;
 	struct list_head signals;
 
@@ -56,6 +48,8 @@ struct intel_context {
 	u32 *lrc_reg_state;
 	u64 lrc_desc;
 
+	unsigned int active_count; /* notionally protected by timeline->mutex */
+
 	atomic_t pin_count;
 	struct mutex pin_mutex; /* guards pinning and associated on-gpuing */
 
@@ -68,7 +62,6 @@ struct intel_context {
 	struct i915_active_request active_tracker;
 
 	const struct intel_context_ops *ops;
-	struct rb_node node;
 
 	/** sseu: Control eu/slice partitioning */
 	struct intel_sseu sseu;

drivers/gpu/drm/i915/intel_ringbuffer.h → drivers/gpu/drm/i915/gt/intel_engine.h

@@ -106,24 +106,6 @@ hangcheck_action_to_str(const enum intel_engine_hangcheck_action a)
 
 void intel_engines_set_scheduler_caps(struct drm_i915_private *i915);
 
-static inline bool __execlists_need_preempt(int prio, int last)
-{
-	/*
-	 * Allow preemption of low -> normal -> high, but we do
-	 * not allow low priority tasks to preempt other low priority
-	 * tasks under the impression that latency for low priority
-	 * tasks does not matter (as much as background throughput),
-	 * so kiss.
-	 *
-	 * More naturally we would write
-	 *	prio >= max(0, last);
-	 * except that we wish to prevent triggering preemption at the same
-	 * priority level: the task that is running should remain running
-	 * to preserve FIFO ordering of dependencies.
-	 */
-	return prio > max(I915_PRIORITY_NORMAL - 1, last);
-}
-
 static inline void
 execlists_set_active(struct intel_engine_execlists *execlists,
 		     unsigned int bit)
@@ -233,8 +215,6 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value)
  */
 #define I915_GEM_HWS_PREEMPT		0x32
 #define I915_GEM_HWS_PREEMPT_ADDR	(I915_GEM_HWS_PREEMPT * sizeof(u32))
-#define I915_GEM_HWS_HANGCHECK		0x34
-#define I915_GEM_HWS_HANGCHECK_ADDR	(I915_GEM_HWS_HANGCHECK * sizeof(u32))
 #define I915_GEM_HWS_SEQNO		0x40
 #define I915_GEM_HWS_SEQNO_ADDR		(I915_GEM_HWS_SEQNO * sizeof(u32))
 #define I915_GEM_HWS_SCRATCH		0x80
@@ -362,14 +342,16 @@ __intel_ring_space(unsigned int head, unsigned int tail, unsigned int size)
 	return (head - tail - CACHELINE_BYTES) & (size - 1);
 }
 
-int intel_engine_setup_common(struct intel_engine_cs *engine);
+int intel_engines_init_mmio(struct drm_i915_private *i915);
+int intel_engines_setup(struct drm_i915_private *i915);
+int intel_engines_init(struct drm_i915_private *i915);
+void intel_engines_cleanup(struct drm_i915_private *i915);
+
 int intel_engine_init_common(struct intel_engine_cs *engine);
 void intel_engine_cleanup_common(struct intel_engine_cs *engine);
 
-int intel_init_render_ring_buffer(struct intel_engine_cs *engine);
-int intel_init_bsd_ring_buffer(struct intel_engine_cs *engine);
-int intel_init_blt_ring_buffer(struct intel_engine_cs *engine);
-int intel_init_vebox_ring_buffer(struct intel_engine_cs *engine);
+int intel_ring_submission_setup(struct intel_engine_cs *engine);
+int intel_ring_submission_init(struct intel_engine_cs *engine);
 
 int intel_engine_stop_cs(struct intel_engine_cs *engine);
 void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine);
@@ -382,6 +364,8 @@ u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine);
 void intel_engine_get_instdone(struct intel_engine_cs *engine,
 			       struct intel_instdone *instdone);
 
+void intel_engine_init_execlists(struct intel_engine_cs *engine);
+
 void intel_engine_init_breadcrumbs(struct intel_engine_cs *engine);
 void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine);
 
@@ -458,19 +442,14 @@ static inline void intel_engine_reset(struct intel_engine_cs *engine,
 {
 	if (engine->reset.reset)
 		engine->reset.reset(engine, stalled);
+	engine->serial++; /* contexts lost */
 }
 
-void intel_engines_sanitize(struct drm_i915_private *i915, bool force);
-void intel_gt_resume(struct drm_i915_private *i915);
-
 bool intel_engine_is_idle(struct intel_engine_cs *engine);
 bool intel_engines_are_idle(struct drm_i915_private *dev_priv);
 
 void intel_engine_lost_context(struct intel_engine_cs *engine);
 
-void intel_engines_park(struct drm_i915_private *i915);
-void intel_engines_unpark(struct drm_i915_private *i915);
-
 void intel_engines_reset_default_submission(struct drm_i915_private *i915);
 unsigned int intel_engines_has_context_isolation(struct drm_i915_private *i915);
 
@@ -567,17 +546,4 @@ static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists)
 
 #endif
 
-static inline u32
-intel_engine_next_hangcheck_seqno(struct intel_engine_cs *engine)
-{
-	return engine->hangcheck.next_seqno =
-		next_pseudo_random32(engine->hangcheck.next_seqno);
-}
-
-static inline u32
-intel_engine_get_hangcheck_seqno(struct intel_engine_cs *engine)
-{
-	return intel_read_status_page(engine, I915_GEM_HWS_HANGCHECK);
-}
-
 #endif /* _INTEL_RINGBUFFER_H_ */

drivers/gpu/drm/i915/gt/intel_engine_pm.c

+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "i915_drv.h"
+
+#include "intel_engine.h"
+#include "intel_engine_pm.h"
+#include "intel_gt_pm.h"
+
+static int __engine_unpark(struct intel_wakeref *wf)
+{
+	struct intel_engine_cs *engine =
+		container_of(wf, typeof(*engine), wakeref);
+	void *map;
+
+	GEM_TRACE("%s\n", engine->name);
+
+	intel_gt_pm_get(engine->i915);
+
+	/* Pin the default state for fast resets from atomic context. */
+	map = NULL;
+	if (engine->default_state)
+		map = i915_gem_object_pin_map(engine->default_state,
+					      I915_MAP_WB);
+	if (!IS_ERR_OR_NULL(map))
+		engine->pinned_default_state = map;
+
+	if (engine->unpark)
+		engine->unpark(engine);
+
+	intel_engine_init_hangcheck(engine);
+	return 0;
+}
+
+void intel_engine_pm_get(struct intel_engine_cs *engine)
+{
+	intel_wakeref_get(engine->i915, &engine->wakeref, __engine_unpark);
+}
+
+void intel_engine_park(struct intel_engine_cs *engine)
+{
+	/*
+	 * We are committed now to parking this engine, make sure there
+	 * will be no more interrupts arriving later and the engine
+	 * is truly idle.
+	 */
+	if (wait_for(intel_engine_is_idle(engine), 10)) {
+		struct drm_printer p = drm_debug_printer(__func__);
+
+		dev_err(engine->i915->drm.dev,
+			"%s is not idle before parking\n",
+			engine->name);
+		intel_engine_dump(engine, &p, NULL);
+	}
+}
+
+static bool switch_to_kernel_context(struct intel_engine_cs *engine)
+{
+	struct i915_request *rq;
+
+	/* Already inside the kernel context, safe to power down. */
+	if (engine->wakeref_serial == engine->serial)
+		return true;
+
+	/* GPU is pointing to the void, as good as in the kernel context. */
+	if (i915_reset_failed(engine->i915))
+		return true;
+
+	/*
+	 * Note, we do this without taking the timeline->mutex. We cannot
+	 * as we may be called while retiring the kernel context and so
+	 * already underneath the timeline->mutex. Instead we rely on the
+	 * exclusive property of the __engine_park that prevents anyone
+	 * else from creating a request on this engine. This also requires
+	 * that the ring is empty and we avoid any waits while constructing
+	 * the context, as they assume protection by the timeline->mutex.
+	 * This should hold true as we can only park the engine after
+	 * retiring the last request, thus all rings should be empty and
+	 * all timelines idle.
+	 */
+	rq = __i915_request_create(engine->kernel_context, GFP_NOWAIT);
+	if (IS_ERR(rq))
+		/* Context switch failed, hope for the best! Maybe reset? */
+		return true;
+
+	/* Check again on the next retirement. */
+	engine->wakeref_serial = engine->serial + 1;
+	__i915_request_commit(rq);
+
+	return false;
+}
+
+static int __engine_park(struct intel_wakeref *wf)
+{
+	struct intel_engine_cs *engine =
+		container_of(wf, typeof(*engine), wakeref);
+
+	/*
+	 * If one and only one request is completed between pm events,
+	 * we know that we are inside the kernel context and it is
+	 * safe to power down. (We are paranoid in case that runtime
+	 * suspend causes corruption to the active context image, and
+	 * want to avoid that impacting userspace.)
+	 */
+	if (!switch_to_kernel_context(engine))
+		return -EBUSY;
+
+	GEM_TRACE("%s\n", engine->name);
+
+	intel_engine_disarm_breadcrumbs(engine);
+
+	/* Must be reset upon idling, or we may miss the busy wakeup. */
+	GEM_BUG_ON(engine->execlists.queue_priority_hint != INT_MIN);
+
+	if (engine->park)
+		engine->park(engine);
+
+	if (engine->pinned_default_state) {
+		i915_gem_object_unpin_map(engine->default_state);
+		engine->pinned_default_state = NULL;
+	}
+
+	engine->execlists.no_priolist = false;
+
+	intel_gt_pm_put(engine->i915);
+	return 0;
+}
+
+void intel_engine_pm_put(struct intel_engine_cs *engine)
+{
+	intel_wakeref_put(engine->i915, &engine->wakeref, __engine_park);
+}
+
+void intel_engine_init__pm(struct intel_engine_cs *engine)
+{
+	intel_wakeref_init(&engine->wakeref);
+}
+
+int intel_engines_resume(struct drm_i915_private *i915)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	intel_gt_pm_get(i915);
+	for_each_engine(engine, i915, id) {
+		intel_engine_pm_get(engine);
+		engine->serial++; /* kernel context lost */
+		err = engine->resume(engine);
+		intel_engine_pm_put(engine);
+		if (err) {
+			dev_err(i915->drm.dev,
+				"Failed to restart %s (%d)\n",
+				engine->name, err);
+			break;
+		}
+	}
+	intel_gt_pm_put(i915);
+
+	return err;
+}

drivers/gpu/drm/i915/gt/intel_engine_pm.h

+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef INTEL_ENGINE_PM_H
+#define INTEL_ENGINE_PM_H
+
+struct drm_i915_private;
+struct intel_engine_cs;
+
+void intel_engine_pm_get(struct intel_engine_cs *engine);
+void intel_engine_pm_put(struct intel_engine_cs *engine);
+
+void intel_engine_park(struct intel_engine_cs *engine);
+
+void intel_engine_init__pm(struct intel_engine_cs *engine);
+
+int intel_engines_resume(struct drm_i915_private *i915);
+
+#endif /* INTEL_ENGINE_PM_H */

drivers/gpu/drm/i915/intel_engine_types.h → drivers/gpu/drm/i915/gt/intel_engine_types.h

@@ -14,14 +14,15 @@
 #include <linux/types.h>
 
 #include "i915_gem.h"
+#include "i915_gem_batch_pool.h"
+#include "i915_pmu.h"
 #include "i915_priolist_types.h"
 #include "i915_selftest.h"
 #include "i915_timeline_types.h"
+#include "intel_sseu.h"
+#include "intel_wakeref.h"
 #include "intel_workarounds_types.h"
 
-#include "i915_gem_batch_pool.h"
-#include "i915_pmu.h"
-
 #define I915_MAX_SLICES	3
 #define I915_MAX_SUBSLICES 8
 
@@ -52,8 +53,8 @@ struct intel_instdone {
 
 struct intel_engine_hangcheck {
 	u64 acthd;
-	u32 last_seqno;
-	u32 next_seqno;
+	u32 last_ring;
+	u32 last_head;
 	unsigned long action_timestamp;
 	struct intel_instdone instdone;
 };
@@ -226,6 +227,7 @@ struct intel_engine_execlists {
 	 * @queue: queue of requests, in priority lists
 	 */
 	struct rb_root_cached queue;
+	struct rb_root_cached virtual;
 
 	/**
 	 * @csb_write: control register for Context Switch buffer
@@ -278,6 +280,10 @@ struct intel_engine_cs {
 	u32 context_size;
 	u32 mmio_base;
 
+	u32 uabi_capabilities;
+
+	struct intel_sseu sseu;
+
 	struct intel_ring *buffer;
 
 	struct i915_timeline timeline;
@@ -285,6 +291,10 @@ struct intel_engine_cs {
 	struct intel_context *kernel_context; /* pinned */
 	struct intel_context *preempt_context; /* pinned; optional */
 
+	unsigned long serial;
+
+	unsigned long wakeref_serial;
+	struct intel_wakeref wakeref;
 	struct drm_i915_gem_object *default_state;
 	void *pinned_default_state;
 
@@ -357,7 +367,7 @@ struct intel_engine_cs {
 	void		(*irq_enable)(struct intel_engine_cs *engine);
 	void		(*irq_disable)(struct intel_engine_cs *engine);
 
-	int		(*init_hw)(struct intel_engine_cs *engine);
+	int		(*resume)(struct intel_engine_cs *engine);
 
 	struct {
 		void (*prepare)(struct intel_engine_cs *engine);
@@ -397,6 +407,13 @@ struct intel_engine_cs {
 	 */
 	void		(*submit_request)(struct i915_request *rq);
 
+	/*
+	 * Called on signaling of a SUBMIT_FENCE, passing along the signaling
+	 * request down to the bonded pairs.
+	 */
+	void            (*bond_execute)(struct i915_request *rq,
+					struct dma_fence *signal);
+
 	/*
 	 * Call when the priority on a request has changed and it and its
 	 * dependencies may need rescheduling. Note the request itself may
@@ -413,7 +430,7 @@ struct intel_engine_cs {
 	 */
 	void		(*cancel_requests)(struct intel_engine_cs *engine);
 
-	void		(*cleanup)(struct intel_engine_cs *engine);
+	void		(*destroy)(struct intel_engine_cs *engine);
 
 	struct intel_engine_execlists execlists;
 
@@ -438,6 +455,7 @@ struct intel_engine_cs {
 #define I915_ENGINE_HAS_PREEMPTION   BIT(2)
 #define I915_ENGINE_HAS_SEMAPHORES   BIT(3)
 #define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(4)
+#define I915_ENGINE_IS_VIRTUAL       BIT(5)
 	unsigned int flags;
 
 	/*
@@ -527,6 +545,12 @@ intel_engine_needs_breadcrumb_tasklet(const struct intel_engine_cs *engine)
 	return engine->flags & I915_ENGINE_NEEDS_BREADCRUMB_TASKLET;
 }
 
+static inline bool
+intel_engine_is_virtual(const struct intel_engine_cs *engine)
+{
+	return engine->flags & I915_ENGINE_IS_VIRTUAL;
+}
+
 #define instdone_slice_mask(dev_priv__) \
 	(IS_GEN(dev_priv__, 7) ? \
 	 1 : RUNTIME_INFO(dev_priv__)->sseu.slice_mask)

drivers/gpu/drm/i915/gt/intel_gt_pm.c

+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "intel_gt_pm.h"
+#include "intel_pm.h"
+#include "intel_wakeref.h"
+
+static void pm_notify(struct drm_i915_private *i915, int state)
+{
+	blocking_notifier_call_chain(&i915->gt.pm_notifications, state, i915);
+}
+
+static int intel_gt_unpark(struct intel_wakeref *wf)
+{
+	struct drm_i915_private *i915 =
+		container_of(wf, typeof(*i915), gt.wakeref);
+
+	GEM_TRACE("\n");
+
+	/*
+	 * It seems that the DMC likes to transition between the DC states a lot
+	 * when there are no connected displays (no active power domains) during
+	 * command submission.
+	 *
+	 * This activity has negative impact on the performance of the chip with
+	 * huge latencies observed in the interrupt handler and elsewhere.
+	 *
+	 * Work around it by grabbing a GT IRQ power domain whilst there is any
+	 * GT activity, preventing any DC state transitions.
+	 */
+	i915->gt.awake = intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
+	GEM_BUG_ON(!i915->gt.awake);
+
+	intel_enable_gt_powersave(i915);
+
+	i915_update_gfx_val(i915);
+	if (INTEL_GEN(i915) >= 6)
+		gen6_rps_busy(i915);
+
+	i915_pmu_gt_unparked(i915);
+
+	i915_queue_hangcheck(i915);
+
+	pm_notify(i915, INTEL_GT_UNPARK);
+
+	return 0;
+}
+
+void intel_gt_pm_get(struct drm_i915_private *i915)
+{
+	intel_wakeref_get(i915, &i915->gt.wakeref, intel_gt_unpark);
+}
+
+static int intel_gt_park(struct intel_wakeref *wf)
+{
+	struct drm_i915_private *i915 =
+		container_of(wf, typeof(*i915), gt.wakeref);
+	intel_wakeref_t wakeref = fetch_and_zero(&i915->gt.awake);
+
+	GEM_TRACE("\n");
+
+	pm_notify(i915, INTEL_GT_PARK);
+
+	i915_pmu_gt_parked(i915);
+	if (INTEL_GEN(i915) >= 6)
+		gen6_rps_idle(i915);
+
+	GEM_BUG_ON(!wakeref);
+	intel_display_power_put(i915, POWER_DOMAIN_GT_IRQ, wakeref);
+
+	return 0;
+}
+
+void intel_gt_pm_put(struct drm_i915_private *i915)
+{
+	intel_wakeref_put(i915, &i915->gt.wakeref, intel_gt_park);
+}
+
+void intel_gt_pm_init(struct drm_i915_private *i915)
+{
+	intel_wakeref_init(&i915->gt.wakeref);
+	BLOCKING_INIT_NOTIFIER_HEAD(&i915->gt.pm_notifications);
+}
+
+static bool reset_engines(struct drm_i915_private *i915)
+{
+	if (INTEL_INFO(i915)->gpu_reset_clobbers_display)
+		return false;
+
+	return intel_gpu_reset(i915, ALL_ENGINES) == 0;
+}
+
+/**
+ * intel_gt_sanitize: called after the GPU has lost power
+ * @i915: the i915 device
+ * @force: ignore a failed reset and sanitize engine state anyway
+ *
+ * Anytime we reset the GPU, either with an explicit GPU reset or through a
+ * PCI power cycle, the GPU loses state and we must reset our state tracking
+ * to match. Note that calling intel_gt_sanitize() if the GPU has not
+ * been reset results in much confusion!
+ */
+void intel_gt_sanitize(struct drm_i915_private *i915, bool force)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	GEM_TRACE("\n");
+
+	if (!reset_engines(i915) && !force)
+		return;
+
+	for_each_engine(engine, i915, id)
+		intel_engine_reset(engine, false);
+}
+
+void intel_gt_resume(struct drm_i915_private *i915)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	/*
+	 * After resume, we may need to poke into the pinned kernel
+	 * contexts to paper over any damage caused by the sudden suspend.
+	 * Only the kernel contexts should remain pinned over suspend,
+	 * allowing us to fixup the user contexts on their first pin.
+	 */
+	for_each_engine(engine, i915, id) {
+		struct intel_context *ce;
+
+		ce = engine->kernel_context;
+		if (ce)
+			ce->ops->reset(ce);
+
+		ce = engine->preempt_context;
+		if (ce)
+			ce->ops->reset(ce);
+	}
+}

drivers/gpu/drm/i915/gt/intel_gt_pm.h

+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef INTEL_GT_PM_H
+#define INTEL_GT_PM_H
+
+#include <linux/types.h>
+
+struct drm_i915_private;
+
+enum {
+	INTEL_GT_UNPARK,
+	INTEL_GT_PARK,
+};
+
+void intel_gt_pm_get(struct drm_i915_private *i915);
+void intel_gt_pm_put(struct drm_i915_private *i915);
+
+void intel_gt_pm_init(struct drm_i915_private *i915);
+
+void intel_gt_sanitize(struct drm_i915_private *i915, bool force);
+void intel_gt_resume(struct drm_i915_private *i915);
+
+#endif /* INTEL_GT_PM_H */

drivers/gpu/drm/i915/intel_hangcheck.c → drivers/gpu/drm/i915/gt/intel_hangcheck.c

@@ -22,12 +22,13 @@
  *
  */
 
+#include "intel_reset.h"
 #include "i915_drv.h"
-#include "i915_reset.h"
 
 struct hangcheck {
 	u64 acthd;
-	u32 seqno;
+	u32 ring;
+	u32 head;
 	enum intel_engine_hangcheck_action action;
 	unsigned long action_timestamp;
 	int deadlock;
@@ -133,26 +134,31 @@ static void hangcheck_load_sample(struct intel_engine_cs *engine,
 				  struct hangcheck *hc)
 {
 	hc->acthd = intel_engine_get_active_head(engine);
-	hc->seqno = intel_engine_get_hangcheck_seqno(engine);
+	hc->ring = ENGINE_READ(engine, RING_START);
+	hc->head = ENGINE_READ(engine, RING_HEAD);
 }
 
 static void hangcheck_store_sample(struct intel_engine_cs *engine,
 				   const struct hangcheck *hc)
 {
 	engine->hangcheck.acthd = hc->acthd;
-	engine->hangcheck.last_seqno = hc->seqno;
+	engine->hangcheck.last_ring = hc->ring;
+	engine->hangcheck.last_head = hc->head;
 }
 
 static enum intel_engine_hangcheck_action
 hangcheck_get_action(struct intel_engine_cs *engine,
 		     const struct hangcheck *hc)
 {
-	if (engine->hangcheck.last_seqno != hc->seqno)
-		return ENGINE_ACTIVE_SEQNO;
-
 	if (intel_engine_is_idle(engine))
 		return ENGINE_IDLE;
 
+	if (engine->hangcheck.last_ring != hc->ring)
+		return ENGINE_ACTIVE_SEQNO;
+
+	if (engine->hangcheck.last_head != hc->head)
+		return ENGINE_ACTIVE_SEQNO;
+
 	return engine_stuck(engine, hc->acthd);
 }
 
@@ -256,6 +262,7 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	unsigned int hung = 0, stuck = 0, wedged = 0;
+	intel_wakeref_t wakeref;
 
 	if (!i915_modparams.enable_hangcheck)
 		return;
@@ -266,6 +273,10 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 	if (i915_terminally_wedged(dev_priv))
 		return;
 
+	wakeref = intel_runtime_pm_get_if_in_use(dev_priv);
+	if (!wakeref)
+		return;
+
 	/* As enabling the GPU requires fairly extensive mmio access,
 	 * periodically arm the mmio checker to see if we are triggering
 	 * any invalid access.
@@ -313,6 +324,8 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 	if (hung)
 		hangcheck_declare_hang(dev_priv, hung, stuck);
 
+	intel_runtime_pm_put(dev_priv, wakeref);
+
 	/* Reset timer in case GPU hangs without another request being added */
 	i915_queue_hangcheck(dev_priv);
 }
@@ -330,5 +343,5 @@ void intel_hangcheck_init(struct drm_i915_private *i915)
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
-#include "selftests/intel_hangcheck.c"
+#include "selftest_hangcheck.c"
 #endif

drivers/gpu/drm/i915/intel_lrc.h → drivers/gpu/drm/i915/gt/intel_lrc.h

@@ -24,8 +24,7 @@
 #ifndef _INTEL_LRC_H_
 #define _INTEL_LRC_H_
 
-#include "intel_ringbuffer.h"
-#include "i915_gem_context.h"
+#include "intel_engine.h"
 
 /* Execlists regs */
 #define RING_ELSP(base)				_MMIO((base) + 0x230)
@@ -67,8 +66,9 @@ enum {
 
 /* Logical Rings */
 void intel_logical_ring_cleanup(struct intel_engine_cs *engine);
-int logical_render_ring_init(struct intel_engine_cs *engine);
-int logical_xcs_ring_init(struct intel_engine_cs *engine);
+
+int intel_execlists_submission_setup(struct intel_engine_cs *engine);
+int intel_execlists_submission_init(struct intel_engine_cs *engine);
 
 /* Logical Ring Contexts */
 
@@ -99,7 +99,6 @@ int logical_xcs_ring_init(struct intel_engine_cs *engine);
 struct drm_printer;
 
 struct drm_i915_private;
-struct i915_gem_context;
 
 void intel_execlists_set_default_submission(struct intel_engine_cs *engine);
 
@@ -115,6 +114,17 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 							const char *prefix),
 				   unsigned int max);
 
-u32 gen8_make_rpcs(struct drm_i915_private *i915, struct intel_sseu *ctx_sseu);
+struct intel_context *
+intel_execlists_create_virtual(struct i915_gem_context *ctx,
+			       struct intel_engine_cs **siblings,
+			       unsigned int count);
+
+struct intel_context *
+intel_execlists_clone_virtual(struct i915_gem_context *ctx,
+			      struct intel_engine_cs *src);
+
+int intel_virtual_engine_attach_bond(struct intel_engine_cs *engine,
+				     const struct intel_engine_cs *master,
+				     const struct intel_engine_cs *sibling);
 
 #endif /* _INTEL_LRC_H_ */

drivers/gpu/drm/i915/intel_mocs.c → drivers/gpu/drm/i915/gt/intel_mocs.c

@@ -20,9 +20,11 @@
  * SOFTWARE.
  */
 
+#include "i915_drv.h"
+
+#include "intel_engine.h"
 #include "intel_mocs.h"
 #include "intel_lrc.h"
-#include "intel_ringbuffer.h"
 
 /* structures required */
 struct drm_i915_mocs_entry {

drivers/gpu/drm/i915/intel_mocs.h → drivers/gpu/drm/i915/gt/intel_mocs.h

@@ -49,7 +49,9 @@
  * context handling keep the MOCS in step.
  */
 
-#include "i915_drv.h"
+struct drm_i915_private;
+struct i915_request;
+struct intel_engine_cs;
 
 int intel_rcs_context_init_mocs(struct i915_request *rq);
 void intel_mocs_init_l3cc_table(struct drm_i915_private *dev_priv);

drivers/gpu/drm/i915/i915_reset.c → drivers/gpu/drm/i915/gt/intel_reset.c

@@ -9,9 +9,13 @@
 
 #include "i915_drv.h"
 #include "i915_gpu_error.h"
-#include "i915_reset.h"
+#include "i915_irq.h"
+#include "intel_engine_pm.h"
+#include "intel_gt_pm.h"
+#include "intel_reset.h"
 
 #include "intel_guc.h"
+#include "intel_overlay.h"
 
 #define RESET_MAX_RETRIES 3
 
@@ -641,9 +645,6 @@ int intel_gpu_reset(struct drm_i915_private *i915,
 
 bool intel_has_gpu_reset(struct drm_i915_private *i915)
 {
-	if (USES_GUC(i915))
-		return false;
-
 	if (!i915_modparams.reset)
 		return NULL;
 
@@ -683,6 +684,7 @@ static void reset_prepare_engine(struct intel_engine_cs *engine)
 	 * written to the powercontext is undefined and so we may lose
 	 * GPU state upon resume, i.e. fail to restart after a reset.
 	 */
+	intel_engine_pm_get(engine);
 	intel_uncore_forcewake_get(engine->uncore, FORCEWAKE_ALL);
 	engine->reset.prepare(engine);
 }
@@ -718,6 +720,7 @@ static void reset_prepare(struct drm_i915_private *i915)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
+	intel_gt_pm_get(i915);
 	for_each_engine(engine, i915, id)
 		reset_prepare_engine(engine);
 
@@ -755,48 +758,10 @@ static int gt_reset(struct drm_i915_private *i915,
 static void reset_finish_engine(struct intel_engine_cs *engine)
 {
 	engine->reset.finish(engine);
+	intel_engine_pm_put(engine);
 	intel_uncore_forcewake_put(engine->uncore, FORCEWAKE_ALL);
 }
 
-struct i915_gpu_restart {
-	struct work_struct work;
-	struct drm_i915_private *i915;
-};
-
-static void restart_work(struct work_struct *work)
-{
-	struct i915_gpu_restart *arg = container_of(work, typeof(*arg), work);
-	struct drm_i915_private *i915 = arg->i915;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	intel_wakeref_t wakeref;
-
-	wakeref = intel_runtime_pm_get(i915);
-	mutex_lock(&i915->drm.struct_mutex);
-	WRITE_ONCE(i915->gpu_error.restart, NULL);
-
-	for_each_engine(engine, i915, id) {
-		struct i915_request *rq;
-
-		/*
-		 * Ostensibily, we always want a context loaded for powersaving,
-		 * so if the engine is idle after the reset, send a request
-		 * to load our scratch kernel_context.
-		 */
-		if (!intel_engine_is_idle(engine))
-			continue;
-
-		rq = i915_request_alloc(engine, i915->kernel_context);
-		if (!IS_ERR(rq))
-			i915_request_add(rq);
-	}
-
-	mutex_unlock(&i915->drm.struct_mutex);
-	intel_runtime_pm_put(i915, wakeref);
-
-	kfree(arg);
-}
-
 static void reset_finish(struct drm_i915_private *i915)
 {
 	struct intel_engine_cs *engine;
@@ -806,29 +771,7 @@ static void reset_finish(struct drm_i915_private *i915)
 		reset_finish_engine(engine);
 		intel_engine_signal_breadcrumbs(engine);
 	}
-}
-
-static void reset_restart(struct drm_i915_private *i915)
-{
-	struct i915_gpu_restart *arg;
-
-	/*
-	 * Following the reset, ensure that we always reload context for
-	 * powersaving, and to correct engine->last_retired_context. Since
-	 * this requires us to submit a request, queue a worker to do that
-	 * task for us to evade any locking here.
-	 */
-	if (READ_ONCE(i915->gpu_error.restart))
-		return;
-
-	arg = kmalloc(sizeof(*arg), GFP_KERNEL);
-	if (arg) {
-		arg->i915 = i915;
-		INIT_WORK(&arg->work, restart_work);
-
-		WRITE_ONCE(i915->gpu_error.restart, arg);
-		queue_work(i915->wq, &arg->work);
-	}
+	intel_gt_pm_put(i915);
 }
 
 static void nop_submit_request(struct i915_request *request)
@@ -889,6 +832,7 @@ static void __i915_gem_set_wedged(struct drm_i915_private *i915)
 	 * in nop_submit_request.
 	 */
 	synchronize_rcu_expedited();
+	set_bit(I915_WEDGED, &error->flags);
 
 	/* Mark all executing requests as skipped */
 	for_each_engine(engine, i915, id)
@@ -896,9 +840,6 @@ static void __i915_gem_set_wedged(struct drm_i915_private *i915)
 
 	reset_finish(i915);
 
-	smp_mb__before_atomic();
-	set_bit(I915_WEDGED, &error->flags);
-
 	GEM_TRACE("end\n");
 }
 
@@ -956,7 +897,7 @@ static bool __i915_gem_unset_wedged(struct drm_i915_private *i915)
 	}
 	mutex_unlock(&i915->gt.timelines.mutex);
 
-	intel_engines_sanitize(i915, false);
+	intel_gt_sanitize(i915, false);
 
 	/*
 	 * Undo nop_submit_request. We prevent all new i915 requests from
@@ -1034,7 +975,6 @@ void i915_reset(struct drm_i915_private *i915,
 	GEM_TRACE("flags=%lx\n", error->flags);
 
 	might_sleep();
-	assert_rpm_wakelock_held(i915);
 	GEM_BUG_ON(!test_bit(I915_RESET_BACKOFF, &error->flags));
 
 	/* Clear any previous failed attempts at recovery. Time to try again. */
@@ -1087,8 +1027,6 @@ void i915_reset(struct drm_i915_private *i915,
 
 finish:
 	reset_finish(i915);
-	if (!__i915_wedged(error))
-		reset_restart(i915);
 	return;
 
 taint:
@@ -1104,7 +1042,7 @@ void i915_reset(struct drm_i915_private *i915,
 	 * rather than continue on into oblivion. For everyone else,
 	 * the system should still plod along, but they have been warned!
 	 */
-	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
+	add_taint_for_CI(TAINT_WARN);
 error:
 	__i915_gem_set_wedged(i915);
 	goto finish;
@@ -1137,6 +1075,9 @@ int i915_reset_engine(struct intel_engine_cs *engine, const char *msg)
 	GEM_TRACE("%s flags=%lx\n", engine->name, error->flags);
 	GEM_BUG_ON(!test_bit(I915_RESET_ENGINE + engine->id, &error->flags));
 
+	if (!intel_wakeref_active(&engine->wakeref))
+		return 0;
+
 	reset_prepare_engine(engine);
 
 	if (msg)
@@ -1168,7 +1109,7 @@ int i915_reset_engine(struct intel_engine_cs *engine, const char *msg)
 	 * have been reset to their default values. Follow the init_ring
 	 * process to program RING_MODE, HWSP and re-enable submission.
 	 */
-	ret = engine->init_hw(engine);
+	ret = engine->resume(engine);
 	if (ret)
 		goto out;
 
@@ -1425,25 +1366,6 @@ int i915_terminally_wedged(struct drm_i915_private *i915)
 	return __i915_wedged(error) ? -EIO : 0;
 }
 
-bool i915_reset_flush(struct drm_i915_private *i915)
-{
-	int err;
-
-	cancel_delayed_work_sync(&i915->gpu_error.hangcheck_work);
-
-	flush_workqueue(i915->wq);
-	GEM_BUG_ON(READ_ONCE(i915->gpu_error.restart));
-
-	mutex_lock(&i915->drm.struct_mutex);
-	err = i915_gem_wait_for_idle(i915,
-				     I915_WAIT_LOCKED |
-				     I915_WAIT_FOR_IDLE_BOOST,
-				     MAX_SCHEDULE_TIMEOUT);
-	mutex_unlock(&i915->drm.struct_mutex);
-
-	return !err;
-}
-
 static void i915_wedge_me(struct work_struct *work)
 {
 	struct i915_wedge_me *w = container_of(work, typeof(*w), work.work);
@@ -1472,3 +1394,7 @@ void __i915_fini_wedge(struct i915_wedge_me *w)
 	destroy_delayed_work_on_stack(&w->work);
 	w->i915 = NULL;
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_reset.c"
+#endif

drivers/gpu/drm/i915/i915_reset.h → drivers/gpu/drm/i915/gt/intel_reset.h

@@ -11,7 +11,7 @@
 #include <linux/types.h>
 #include <linux/srcu.h>
 
-#include "intel_engine_types.h"
+#include "gt/intel_engine_types.h"
 
 struct drm_i915_private;
 struct i915_request;
@@ -34,7 +34,6 @@ int i915_reset_engine(struct intel_engine_cs *engine,
 		      const char *reason);
 
 void i915_reset_request(struct i915_request *rq, bool guilty);
-bool i915_reset_flush(struct drm_i915_private *i915);
 
 int __must_check i915_reset_trylock(struct drm_i915_private *i915);
 void i915_reset_unlock(struct drm_i915_private *i915, int tag);

drivers/gpu/drm/i915/gt/intel_sseu.c

+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "intel_lrc_reg.h"
+#include "intel_sseu.h"
+
+u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
+			 const struct intel_sseu *req_sseu)
+{
+	const struct sseu_dev_info *sseu = &RUNTIME_INFO(i915)->sseu;
+	bool subslice_pg = sseu->has_subslice_pg;
+	struct intel_sseu ctx_sseu;
+	u8 slices, subslices;
+	u32 rpcs = 0;
+
+	/*
+	 * No explicit RPCS request is needed to ensure full
+	 * slice/subslice/EU enablement prior to Gen9.
+	 */
+	if (INTEL_GEN(i915) < 9)
+		return 0;
+
+	/*
+	 * If i915/perf is active, we want a stable powergating configuration
+	 * on the system.
+	 *
+	 * We could choose full enablement, but on ICL we know there are use
+	 * cases which disable slices for functional, apart for performance
+	 * reasons. So in this case we select a known stable subset.
+	 */
+	if (!i915->perf.oa.exclusive_stream) {
+		ctx_sseu = *req_sseu;
+	} else {
+		ctx_sseu = intel_sseu_from_device_info(sseu);
+
+		if (IS_GEN(i915, 11)) {
+			/*
+			 * We only need subslice count so it doesn't matter
+			 * which ones we select - just turn off low bits in the
+			 * amount of half of all available subslices per slice.
+			 */
+			ctx_sseu.subslice_mask =
+				~(~0 << (hweight8(ctx_sseu.subslice_mask) / 2));
+			ctx_sseu.slice_mask = 0x1;
+		}
+	}
+
+	slices = hweight8(ctx_sseu.slice_mask);
+	subslices = hweight8(ctx_sseu.subslice_mask);
+
+	/*
+	 * Since the SScount bitfield in GEN8_R_PWR_CLK_STATE is only three bits
+	 * wide and Icelake has up to eight subslices, specfial programming is
+	 * needed in order to correctly enable all subslices.
+	 *
+	 * According to documentation software must consider the configuration
+	 * as 2x4x8 and hardware will translate this to 1x8x8.
+	 *
+	 * Furthemore, even though SScount is three bits, maximum documented
+	 * value for it is four. From this some rules/restrictions follow:
+	 *
+	 * 1.
+	 * If enabled subslice count is greater than four, two whole slices must
+	 * be enabled instead.
+	 *
+	 * 2.
+	 * When more than one slice is enabled, hardware ignores the subslice
+	 * count altogether.
+	 *
+	 * From these restrictions it follows that it is not possible to enable
+	 * a count of subslices between the SScount maximum of four restriction,
+	 * and the maximum available number on a particular SKU. Either all
+	 * subslices are enabled, or a count between one and four on the first
+	 * slice.
+	 */
+	if (IS_GEN(i915, 11) &&
+	    slices == 1 &&
+	    subslices > min_t(u8, 4, hweight8(sseu->subslice_mask[0]) / 2)) {
+		GEM_BUG_ON(subslices & 1);
+
+		subslice_pg = false;
+		slices *= 2;
+	}
+
+	/*
+	 * Starting in Gen9, render power gating can leave
+	 * slice/subslice/EU in a partially enabled state. We
+	 * must make an explicit request through RPCS for full
+	 * enablement.
+	 */
+	if (sseu->has_slice_pg) {
+		u32 mask, val = slices;
+
+		if (INTEL_GEN(i915) >= 11) {
+			mask = GEN11_RPCS_S_CNT_MASK;
+			val <<= GEN11_RPCS_S_CNT_SHIFT;
+		} else {
+			mask = GEN8_RPCS_S_CNT_MASK;
+			val <<= GEN8_RPCS_S_CNT_SHIFT;
+		}
+
+		GEM_BUG_ON(val & ~mask);
+		val &= mask;
+
+		rpcs |= GEN8_RPCS_ENABLE | GEN8_RPCS_S_CNT_ENABLE | val;
+	}
+
+	if (subslice_pg) {
+		u32 val = subslices;
+
+		val <<= GEN8_RPCS_SS_CNT_SHIFT;
+
+		GEM_BUG_ON(val & ~GEN8_RPCS_SS_CNT_MASK);
+		val &= GEN8_RPCS_SS_CNT_MASK;
+
+		rpcs |= GEN8_RPCS_ENABLE | GEN8_RPCS_SS_CNT_ENABLE | val;
+	}
+
+	if (sseu->has_eu_pg) {
+		u32 val;
+
+		val = ctx_sseu.min_eus_per_subslice << GEN8_RPCS_EU_MIN_SHIFT;
+		GEM_BUG_ON(val & ~GEN8_RPCS_EU_MIN_MASK);
+		val &= GEN8_RPCS_EU_MIN_MASK;
+
+		rpcs |= val;
+
+		val = ctx_sseu.max_eus_per_subslice << GEN8_RPCS_EU_MAX_SHIFT;
+		GEM_BUG_ON(val & ~GEN8_RPCS_EU_MAX_MASK);
+		val &= GEN8_RPCS_EU_MAX_MASK;
+
+		rpcs |= val;
+
+		rpcs |= GEN8_RPCS_ENABLE;
+	}
+
+	return rpcs;
+}

drivers/gpu/drm/i915/gt/intel_sseu.h

+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef __INTEL_SSEU_H__
+#define __INTEL_SSEU_H__
+
+#include <linux/types.h>
+
+struct drm_i915_private;
+
+#define GEN_MAX_SLICES		(6) /* CNL upper bound */
+#define GEN_MAX_SUBSLICES	(8) /* ICL upper bound */
+
+struct sseu_dev_info {
+	u8 slice_mask;
+	u8 subslice_mask[GEN_MAX_SLICES];
+	u16 eu_total;
+	u8 eu_per_subslice;
+	u8 min_eu_in_pool;
+	/* For each slice, which subslice(s) has(have) 7 EUs (bitfield)? */
+	u8 subslice_7eu[3];
+	u8 has_slice_pg:1;
+	u8 has_subslice_pg:1;
+	u8 has_eu_pg:1;
+
+	/* Topology fields */
+	u8 max_slices;
+	u8 max_subslices;
+	u8 max_eus_per_subslice;
+
+	/* We don't have more than 8 eus per subslice at the moment and as we
+	 * store eus enabled using bits, no need to multiply by eus per
+	 * subslice.
+	 */
+	u8 eu_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICES];
+};
+
+/*
+ * Powergating configuration for a particular (context,engine).
+ */
+struct intel_sseu {
+	u8 slice_mask;
+	u8 subslice_mask;
+	u8 min_eus_per_subslice;
+	u8 max_eus_per_subslice;
+};
+
+static inline struct intel_sseu
+intel_sseu_from_device_info(const struct sseu_dev_info *sseu)
+{
+	struct intel_sseu value = {
+		.slice_mask = sseu->slice_mask,
+		.subslice_mask = sseu->subslice_mask[0],
+		.min_eus_per_subslice = sseu->max_eus_per_subslice,
+		.max_eus_per_subslice = sseu->max_eus_per_subslice,
+	};
+
+	return value;
+}
+
+u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
+			 const struct intel_sseu *req_sseu);
+
+#endif /* __INTEL_SSEU_H__ */

drivers/gpu/drm/i915/intel_workarounds_types.h → drivers/gpu/drm/i915/gt/intel_workarounds_types.h

@@ -15,6 +15,7 @@ struct i915_wa {
 	i915_reg_t	reg;
 	u32		mask;
 	u32		val;
+	u32		read;
 };
 
 struct i915_wa_list {