Merge tag 'drm-next-2019-12-06' of git://anongit.freedesktop.org/drm/drm

Pull more drm updates from Dave Airlie:
 "Rob pointed out I missed his pull request for msm-next, it's been in
  next for a while outside of my tree so shouldn't cause any unexpected
  issues, it has some OCMEM support in drivers/soc that is acked by
  other maintainers as it's outside my tree.

  Otherwise it's a usual fixes pull, i915, amdgpu, the main ones, with
  some tegra, omap, mgag200 and one core fix.

  Summary:

  msm-next:
   - OCMEM support for a3xx and a4xx GPUs.
   - a510 support + display support

  core:
   - mst payload deletion fix

  i915:
   - uapi alignment fix
   - fix for power usage regression due to security fixes
   - change default preemption timeout to 640ms from 100ms
   - EHL voltage level display fixes
   - TGL DGL PHY fix
   - gvt - MI_ATOMIC cmd parser fix, CFL non-priv warning
   - CI spotted deadlock fix
   - EHL port D programming fix

  amdgpu:
   - VRAM lost fixes on BACO for CI/VI
   - navi14 DC fixes
   - misc SR-IOV, gfx10 fixes
   - XGMI fixes for arcturus
   - SRIOV fixes

  amdkfd:
   - KFD on ppc64le enabled
   - page table optimisations

  radeon:
   - fix for r1xx/2xx register checker.

  tegra:
   - displayport regression fixes
   - DMA API regression fixes

  mgag200:
   - fix devices that can't scanout except at 0 addr

  omap:
   - fix dma_addr refcounting"

* tag 'drm-next-2019-12-06' of git://anongit.freedesktop.org/drm/drm: (100 commits)
  drm/dp_mst: Correct the bug in drm_dp_update_payload_part1()
  drm/omap: fix dma_addr refcounting
  drm/tegra: Run hub cleanup on ->remove()
  drm/tegra: sor: Make the +5V HDMI supply optional
  drm/tegra: Silence expected errors on IOMMU attach
  drm/tegra: vic: Export module device table
  drm/tegra: sor: Implement system suspend/resume
  drm/tegra: Use proper IOVA address for cursor image
  drm/tegra: gem: Remove premature import restrictions
  drm/tegra: gem: Properly pin imported buffers
  drm/tegra: hub: Remove bogus connection mutex check
  ia64: agp: Replace empty define with do while
  agp: Add bridge parameter documentation
  agp: remove unused variable num_segments
  agp: move AGPGART_MINOR to include/linux/miscdevice.h
  agp: remove unused variable size in agp_generic_create_gatt_table
  drm/dp_mst: Fix build on systems with STACKTRACE_SUPPORT=n
  drm/radeon: fix r1xx/r2xx register checker for POT textures
  drm/amdgpu: fix GFX10 missing CSIB set(v3)
  drm/amdgpu: should stop GFX ring in hw_fini
  ...

117 files changed, 1771 insertions, 759 deletions

diff --git a/drivers/char/agp/frontend.c b/drivers/char/agp/frontend.c
index f6955888e676..47098648502d 100644
--- a/drivers/char/agp/frontend.c
+++ b/drivers/char/agp/frontend.c
@@ -102,14 +102,13 @@ agp_segment_priv *agp_find_seg_in_client(const struct agp_client *client,
 					    int size, pgprot_t page_prot)
 {
 	struct agp_segment_priv *seg;
-	int num_segments, i;
+	int i;
 	off_t pg_start;
 	size_t pg_count;
 
 	pg_start = offset / 4096;
 	pg_count = size / 4096;
 	seg = *(client->segments);
-	num_segments = client->num_segments;
 
 	for (i = 0; i < client->num_segments; i++) {
 		if ((seg[i].pg_start == pg_start) &&
diff --git a/drivers/char/agp/generic.c b/drivers/char/agp/generic.c
index df1edb5ec0ad..ab154a75acf0 100644
--- a/drivers/char/agp/generic.c
+++ b/drivers/char/agp/generic.c
@@ -207,6 +207,7 @@ EXPORT_SYMBOL(agp_free_memory);
 /**
  *	agp_allocate_memory  -  allocate a group of pages of a certain type.
  *
+ *	@bridge: an agp_bridge_data struct allocated for the AGP host bridge.
  *	@page_count:	size_t argument of the number of pages
  *	@type:	u32 argument of the type of memory to be allocated.
  *
@@ -355,6 +356,7 @@ EXPORT_SYMBOL_GPL(agp_num_entries);
 /**
  *	agp_copy_info  -  copy bridge state information
  *
+ *	@bridge: an agp_bridge_data struct allocated for the AGP host bridge.
  *	@info:		agp_kern_info pointer.  The caller should insure that this pointer is valid.
  *
  *	This function copies information about the agp bridge device and the state of
@@ -850,7 +852,6 @@ int agp_generic_create_gatt_table(struct agp_bridge_data *bridge)
 {
 	char *table;
 	char *table_end;
-	int size;
 	int page_order;
 	int num_entries;
 	int i;
@@ -864,25 +865,22 @@ int agp_generic_create_gatt_table(struct agp_bridge_data *bridge)
 	table = NULL;
 	i = bridge->aperture_size_idx;
 	temp = bridge->current_size;
-	size = page_order = num_entries = 0;
+	page_order = num_entries = 0;
 
 	if (bridge->driver->size_type != FIXED_APER_SIZE) {
 		do {
 			switch (bridge->driver->size_type) {
 			case U8_APER_SIZE:
-				size = A_SIZE_8(temp)->size;
 				page_order =
 				    A_SIZE_8(temp)->page_order;
 				num_entries =
 				    A_SIZE_8(temp)->num_entries;
 				break;
 			case U16_APER_SIZE:
-				size = A_SIZE_16(temp)->size;
 				page_order = A_SIZE_16(temp)->page_order;
 				num_entries = A_SIZE_16(temp)->num_entries;
 				break;
 			case U32_APER_SIZE:
-				size = A_SIZE_32(temp)->size;
 				page_order = A_SIZE_32(temp)->page_order;
 				num_entries = A_SIZE_32(temp)->num_entries;
 				break;
@@ -890,7 +888,7 @@ int agp_generic_create_gatt_table(struct agp_bridge_data *bridge)
 			case FIXED_APER_SIZE:
 			case LVL2_APER_SIZE:
 			default:
-				size = page_order = num_entries = 0;
+				page_order = num_entries = 0;
 				break;
 			}
 
@@ -920,7 +918,6 @@ int agp_generic_create_gatt_table(struct agp_bridge_data *bridge)
 			}
 		} while (!table && (i < bridge->driver->num_aperture_sizes));
 	} else {
-		size = ((struct aper_size_info_fixed *) temp)->size;
 		page_order = ((struct aper_size_info_fixed *) temp)->page_order;
 		num_entries = ((struct aper_size_info_fixed *) temp)->num_entries;
 		table = alloc_gatt_pages(page_order);
@@ -1282,6 +1279,7 @@ EXPORT_SYMBOL(agp_generic_destroy_page);
 /**
  * agp_enable  -  initialise the agp point-to-point connection.
  *
+ * @bridge: an agp_bridge_data struct allocated for the AGP host bridge.
  * @mode:	agp mode register value to configure with.
  */
 void agp_enable(struct agp_bridge_data *bridge, u32 mode)
diff --git a/drivers/firmware/qcom_scm-32.c b/drivers/firmware/qcom_scm-32.c
index bee8729525ec..48e2ef794ea3 100644
--- a/drivers/firmware/qcom_scm-32.c
+++ b/drivers/firmware/qcom_scm-32.c
@@ -442,6 +442,41 @@ int __qcom_scm_hdcp_req(struct device *dev, struct qcom_scm_hdcp_req *req,
 		req, req_cnt * sizeof(*req), resp, sizeof(*resp));
 }
 
+int __qcom_scm_ocmem_lock(struct device *dev, u32 id, u32 offset, u32 size,
+			  u32 mode)
+{
+	struct ocmem_tz_lock {
+		__le32 id;
+		__le32 offset;
+		__le32 size;
+		__le32 mode;
+	} request;
+
+	request.id = cpu_to_le32(id);
+	request.offset = cpu_to_le32(offset);
+	request.size = cpu_to_le32(size);
+	request.mode = cpu_to_le32(mode);
+
+	return qcom_scm_call(dev, QCOM_SCM_OCMEM_SVC, QCOM_SCM_OCMEM_LOCK_CMD,
+			     &request, sizeof(request), NULL, 0);
+}
+
+int __qcom_scm_ocmem_unlock(struct device *dev, u32 id, u32 offset, u32 size)
+{
+	struct ocmem_tz_unlock {
+		__le32 id;
+		__le32 offset;
+		__le32 size;
+	} request;
+
+	request.id = cpu_to_le32(id);
+	request.offset = cpu_to_le32(offset);
+	request.size = cpu_to_le32(size);
+
+	return qcom_scm_call(dev, QCOM_SCM_OCMEM_SVC, QCOM_SCM_OCMEM_UNLOCK_CMD,
+			     &request, sizeof(request), NULL, 0);
+}
+
 void __qcom_scm_init(void)
 {
 }
@@ -582,7 +617,22 @@ int __qcom_scm_assign_mem(struct device *dev, phys_addr_t mem_region,
 int __qcom_scm_restore_sec_cfg(struct device *dev, u32 device_id,
 			       u32 spare)
 {
-	return -ENODEV;
+	struct msm_scm_sec_cfg {
+		__le32 id;
+		__le32 ctx_bank_num;
+	} cfg;
+	int ret, scm_ret = 0;
+
+	cfg.id = cpu_to_le32(device_id);
+	cfg.ctx_bank_num = cpu_to_le32(spare);
+
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_MP, QCOM_SCM_RESTORE_SEC_CFG,
+			    &cfg, sizeof(cfg), &scm_ret, sizeof(scm_ret));
+
+	if (ret || scm_ret)
+		return ret ? ret : -EINVAL;
+
+	return 0;
 }
 
 int __qcom_scm_iommu_secure_ptbl_size(struct device *dev, u32 spare,
diff --git a/drivers/firmware/qcom_scm-64.c b/drivers/firmware/qcom_scm-64.c
index e1cd933ea9ae..3c5850350974 100644
--- a/drivers/firmware/qcom_scm-64.c
+++ b/drivers/firmware/qcom_scm-64.c
@@ -291,6 +291,18 @@ int __qcom_scm_hdcp_req(struct device *dev, struct qcom_scm_hdcp_req *req,
 	return ret;
 }
 
+int __qcom_scm_ocmem_lock(struct device *dev, uint32_t id, uint32_t offset,
+			  uint32_t size, uint32_t mode)
+{
+	return -ENOTSUPP;
+}
+
+int __qcom_scm_ocmem_unlock(struct device *dev, uint32_t id, uint32_t offset,
+			    uint32_t size)
+{
+	return -ENOTSUPP;
+}
+
 void __qcom_scm_init(void)
 {
 	u64 cmd;
diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c
index a729e05c21b8..1ba0df4b97ab 100644
--- a/drivers/firmware/qcom_scm.c
+++ b/drivers/firmware/qcom_scm.c
@@ -192,6 +192,46 @@ bool qcom_scm_pas_supported(u32 peripheral)
 EXPORT_SYMBOL(qcom_scm_pas_supported);
 
 /**
+ * qcom_scm_ocmem_lock_available() - is OCMEM lock/unlock interface available
+ */
+bool qcom_scm_ocmem_lock_available(void)
+{
+	return __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_OCMEM_SVC,
+					    QCOM_SCM_OCMEM_LOCK_CMD);
+}
+EXPORT_SYMBOL(qcom_scm_ocmem_lock_available);
+
+/**
+ * qcom_scm_ocmem_lock() - call OCMEM lock interface to assign an OCMEM
+ * region to the specified initiator
+ *
+ * @id:     tz initiator id
+ * @offset: OCMEM offset
+ * @size:   OCMEM size
+ * @mode:   access mode (WIDE/NARROW)
+ */
+int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, u32 size,
+			u32 mode)
+{
+	return __qcom_scm_ocmem_lock(__scm->dev, id, offset, size, mode);
+}
+EXPORT_SYMBOL(qcom_scm_ocmem_lock);
+
+/**
+ * qcom_scm_ocmem_unlock() - call OCMEM unlock interface to release an OCMEM
+ * region from the specified initiator
+ *
+ * @id:     tz initiator id
+ * @offset: OCMEM offset
+ * @size:   OCMEM size
+ */
+int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, u32 size)
+{
+	return __qcom_scm_ocmem_unlock(__scm->dev, id, offset, size);
+}
+EXPORT_SYMBOL(qcom_scm_ocmem_unlock);
+
+/**
  * qcom_scm_pas_init_image() - Initialize peripheral authentication service
  *			       state machine for a given peripheral, using the
  *			       metadata
@@ -327,6 +367,19 @@ static const struct reset_control_ops qcom_scm_pas_reset_ops = {
 	.deassert = qcom_scm_pas_reset_deassert,
 };
 
+/**
+ * qcom_scm_restore_sec_cfg_available() - Check if secure environment
+ * supports restore security config interface.
+ *
+ * Return true if restore-cfg interface is supported, false if not.
+ */
+bool qcom_scm_restore_sec_cfg_available(void)
+{
+	return __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_MP,
+					    QCOM_SCM_RESTORE_SEC_CFG);
+}
+EXPORT_SYMBOL(qcom_scm_restore_sec_cfg_available);
+
 int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare)
 {
 	return __qcom_scm_restore_sec_cfg(__scm->dev, device_id, spare);
diff --git a/drivers/firmware/qcom_scm.h b/drivers/firmware/qcom_scm.h
index baee744dbcfe..81dcf5f1138e 100644
--- a/drivers/firmware/qcom_scm.h
+++ b/drivers/firmware/qcom_scm.h
@@ -42,6 +42,15 @@ extern int __qcom_scm_hdcp_req(struct device *dev,
 
 extern void __qcom_scm_init(void);
 
+#define QCOM_SCM_OCMEM_SVC			0xf
+#define QCOM_SCM_OCMEM_LOCK_CMD		0x1
+#define QCOM_SCM_OCMEM_UNLOCK_CMD		0x2
+
+extern int __qcom_scm_ocmem_lock(struct device *dev, u32 id, u32 offset,
+				 u32 size, u32 mode);
+extern int __qcom_scm_ocmem_unlock(struct device *dev, u32 id, u32 offset,
+				   u32 size);
+
 #define QCOM_SCM_SVC_PIL		0x2
 #define QCOM_SCM_PAS_INIT_IMAGE_CMD	0x1
 #define QCOM_SCM_PAS_MEM_SETUP_CMD	0x2
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 1168351267fd..bfdadc3667e0 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -95,6 +95,7 @@ config DRM_KMS_FB_HELPER
 
 config DRM_DEBUG_DP_MST_TOPOLOGY_REFS
         bool "Enable refcount backtrace history in the DP MST helpers"
+	depends on STACKTRACE_SUPPORT
         select STACKDEPOT
         depends on DRM_KMS_HELPER
         depends on DEBUG_KERNEL
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 7d35b5b66229..888209eb8cec 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -105,11 +105,24 @@ void amdgpu_amdkfd_gpuvm_init_mem_limits(void)
 		(kfd_mem_limit.max_ttm_mem_limit >> 20));
 }
 
+/* Estimate page table size needed to represent a given memory size
+ *
+ * With 4KB pages, we need one 8 byte PTE for each 4KB of memory
+ * (factor 512, >> 9). With 2MB pages, we need one 8 byte PTE for 2MB
+ * of memory (factor 256K, >> 18). ROCm user mode tries to optimize
+ * for 2MB pages for TLB efficiency. However, small allocations and
+ * fragmented system memory still need some 4KB pages. We choose a
+ * compromise that should work in most cases without reserving too
+ * much memory for page tables unnecessarily (factor 16K, >> 14).
+ */
+#define ESTIMATE_PT_SIZE(mem_size) ((mem_size) >> 14)
+
 static int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 		uint64_t size, u32 domain, bool sg)
 {
+	uint64_t reserved_for_pt =
+		ESTIMATE_PT_SIZE(amdgpu_amdkfd_total_mem_size);
 	size_t acc_size, system_mem_needed, ttm_mem_needed, vram_needed;
-	uint64_t reserved_for_pt = amdgpu_amdkfd_total_mem_size >> 9;
 	int ret = 0;
 
 	acc_size = ttm_bo_dma_acc_size(&adev->mman.bdev, size,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 2770cba56a6b..44be3a45b25e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -1487,8 +1487,8 @@ out:
 			return ret;
 
 		/* Start rlc autoload after psp recieved all the gfx firmware */
-		if (psp->autoload_supported && ucode->ucode_id ==
-			AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM) {
+		if (psp->autoload_supported && ucode->ucode_id == (amdgpu_sriov_vf(adev) ?
+		    AMDGPU_UCODE_ID_CP_MEC2 : AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM)) {
 			ret = psp_rlc_autoload(psp);
 			if (ret) {
 				DRM_ERROR("Failed to start rlc autoload\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 7de16c0c2f20..2a8e04895595 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -27,7 +27,8 @@
 #include <linux/bits.h>
 #include "smu_v11_0_i2c.h"
 
-#define EEPROM_I2C_TARGET_ADDR 0xA0
+#define EEPROM_I2C_TARGET_ADDR_ARCTURUS  0xA8
+#define EEPROM_I2C_TARGET_ADDR_VEGA20    0xA0
 
 /*
  * The 2 macros bellow represent the actual size in bytes that
@@ -83,7 +84,7 @@ static int __update_table_header(struct amdgpu_ras_eeprom_control *control,
 {
 	int ret = 0;
 	struct i2c_msg msg = {
-			.addr	= EEPROM_I2C_TARGET_ADDR,
+			.addr	= 0,
 			.flags	= 0,
 			.len	= EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE,
 			.buf	= buff,
@@ -93,6 +94,8 @@ static int __update_table_header(struct amdgpu_ras_eeprom_control *control,
 	*(uint16_t *)buff = EEPROM_HDR_START;
 	__encode_table_header_to_buff(&control->tbl_hdr, buff + EEPROM_ADDRESS_SIZE);
 
+	msg.addr = control->i2c_address;
+
 	ret = i2c_transfer(&control->eeprom_accessor, &msg, 1);
 	if (ret < 1)
 		DRM_ERROR("Failed to write EEPROM table header, ret:%d", ret);
@@ -203,7 +206,7 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 	unsigned char buff[EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE] = { 0 };
 	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
 	struct i2c_msg msg = {
-			.addr	= EEPROM_I2C_TARGET_ADDR,
+			.addr	= 0,
 			.flags	= I2C_M_RD,
 			.len	= EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE,
 			.buf	= buff,
@@ -213,10 +216,12 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA20:
+		control->i2c_address = EEPROM_I2C_TARGET_ADDR_VEGA20;
 		ret = smu_v11_0_i2c_eeprom_control_init(&control->eeprom_accessor);
 		break;
 
 	case CHIP_ARCTURUS:
+		control->i2c_address = EEPROM_I2C_TARGET_ADDR_ARCTURUS;
 		ret = smu_i2c_eeprom_init(&adev->smu, &control->eeprom_accessor);
 		break;
 
@@ -229,6 +234,8 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 		return ret;
 	}
 
+	msg.addr = control->i2c_address;
+
 	/* Read/Create table header from EEPROM address 0 */
 	ret = i2c_transfer(&control->eeprom_accessor, &msg, 1);
 	if (ret < 1) {
@@ -408,8 +415,8 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 		 * Update bits 16,17 of EEPROM address in I2C address by setting them
 		 * to bits 1,2 of Device address byte
 		 */
-		msg->addr = EEPROM_I2C_TARGET_ADDR |
-			       ((control->next_addr & EEPROM_ADDR_MSB_MASK) >> 15);
+		msg->addr = control->i2c_address |
+			        ((control->next_addr & EEPROM_ADDR_MSB_MASK) >> 15);
 		msg->flags	= write ? 0 : I2C_M_RD;
 		msg->len	= EEPROM_ADDRESS_SIZE + EEPROM_TABLE_RECORD_SIZE;
 		msg->buf	= buff;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
index 622269957c1b..ca78f812d436 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
@@ -50,6 +50,7 @@ struct amdgpu_ras_eeprom_control {
 	struct mutex tbl_mutex;
 	bool bus_locked;
 	uint32_t tbl_byte_sum;
+	uint16_t i2c_address; // 8-bit represented address
 };
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
index c8793e6cc3c5..6373bfb47d55 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
@@ -124,13 +124,12 @@ int amdgpu_gfx_rlc_init_sr(struct amdgpu_device *adev, u32 dws)
  */
 int amdgpu_gfx_rlc_init_csb(struct amdgpu_device *adev)
 {
-	volatile u32 *dst_ptr;
 	u32 dws;
 	int r;
 
 	/* allocate clear state block */
 	adev->gfx.rlc.clear_state_size = dws = adev->gfx.rlc.funcs->get_csb_size(adev);
-	r = amdgpu_bo_create_reserved(adev, dws * 4, PAGE_SIZE,
+	r = amdgpu_bo_create_kernel(adev, dws * 4, PAGE_SIZE,
 				      AMDGPU_GEM_DOMAIN_VRAM,
 				      &adev->gfx.rlc.clear_state_obj,
 				      &adev->gfx.rlc.clear_state_gpu_addr,
@@ -141,13 +140,6 @@ int amdgpu_gfx_rlc_init_csb(struct amdgpu_device *adev)
 		return r;
 	}
 
-	/* set up the cs buffer */
-	dst_ptr = adev->gfx.rlc.cs_ptr;
-	adev->gfx.rlc.funcs->get_csb_buffer(adev, dst_ptr);
-	amdgpu_bo_kunmap(adev->gfx.rlc.clear_state_obj);
-	amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj);
-	amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 7a43993544c1..1befdee9f0f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1346,10 +1346,13 @@ static int cik_asic_reset(struct amdgpu_device *adev)
 {
 	int r;
 
-	if (cik_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)
+	if (cik_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
+		if (!adev->in_suspend)
+			amdgpu_inc_vram_lost(adev);
 		r = smu7_asic_baco_reset(adev);
-	else
+	} else {
 		r = cik_asic_pci_config_reset(adev);
+	}
 
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index ca5f0e7ea1ac..f2c1b026397b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -690,59 +690,61 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.ce_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.ce_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name);
-	err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
-	if (err)
-		goto out;
-	err = amdgpu_ucode_validate(adev->gfx.rlc_fw);
-	rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
-	version_major = le16_to_cpu(rlc_hdr->header.header_version_major);
-	version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor);
-	if (version_major == 2 && version_minor == 1)
-		adev->gfx.rlc.is_rlc_v2_1 = true;
-
-	adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version);
-	adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version);
-	adev->gfx.rlc.save_and_restore_offset =
+	if (!amdgpu_sriov_vf(adev)) {
+		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name);
+		err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
+		if (err)
+			goto out;
+		err = amdgpu_ucode_validate(adev->gfx.rlc_fw);
+		rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
+		version_major = le16_to_cpu(rlc_hdr->header.header_version_major);
+		version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor);
+		if (version_major == 2 && version_minor == 1)
+			adev->gfx.rlc.is_rlc_v2_1 = true;
+
+		adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version);
+		adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version);
+		adev->gfx.rlc.save_and_restore_offset =
 			le32_to_cpu(rlc_hdr->save_and_restore_offset);
-	adev->gfx.rlc.clear_state_descriptor_offset =
+		adev->gfx.rlc.clear_state_descriptor_offset =
 			le32_to_cpu(rlc_hdr->clear_state_descriptor_offset);
-	adev->gfx.rlc.avail_scratch_ram_locations =
+		adev->gfx.rlc.avail_scratch_ram_locations =
 			le32_to_cpu(rlc_hdr->avail_scratch_ram_locations);
-	adev->gfx.rlc.reg_restore_list_size =
+		adev->gfx.rlc.reg_restore_list_size =
 			le32_to_cpu(rlc_hdr->reg_restore_list_size);
-	adev->gfx.rlc.reg_list_format_start =
+		adev->gfx.rlc.reg_list_format_start =
 			le32_to_cpu(rlc_hdr->reg_list_format_start);
-	adev->gfx.rlc.reg_list_format_separate_start =
+		adev->gfx.rlc.reg_list_format_separate_start =
 			le32_to_cpu(rlc_hdr->reg_list_format_separate_start);
-	adev->gfx.rlc.starting_offsets_start =
+		adev->gfx.rlc.starting_offsets_start =
 			le32_to_cpu(rlc_hdr->starting_offsets_start);
-	adev->gfx.rlc.reg_list_format_size_bytes =
+		adev->gfx.rlc.reg_list_format_size_bytes =
 			le32_to_cpu(rlc_hdr->reg_list_format_size_bytes);
-	adev->gfx.rlc.reg_list_size_bytes =
+		adev->gfx.rlc.reg_list_size_bytes =
 			le32_to_cpu(rlc_hdr->reg_list_size_bytes);
-	adev->gfx.rlc.register_list_format =
+		adev->gfx.rlc.register_list_format =
 			kmalloc(adev->gfx.rlc.reg_list_format_size_bytes +
-				adev->gfx.rlc.reg_list_size_bytes, GFP_KERNEL);
-	if (!adev->gfx.rlc.register_list_format) {
-		err = -ENOMEM;
-		goto out;
-	}
+					adev->gfx.rlc.reg_list_size_bytes, GFP_KERNEL);
+		if (!adev->gfx.rlc.register_list_format) {
+			err = -ENOMEM;
+			goto out;
+		}
 
-	tmp = (unsigned int *)((uintptr_t)rlc_hdr +
-			le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes));
-	for (i = 0 ; i < (rlc_hdr->reg_list_format_size_bytes >> 2); i++)
-		adev->gfx.rlc.register_list_format[i] =	le32_to_cpu(tmp[i]);
+		tmp = (unsigned int *)((uintptr_t)rlc_hdr +
+							   le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes));
+		for (i = 0 ; i < (rlc_hdr->reg_list_format_size_bytes >> 2); i++)
+			adev->gfx.rlc.register_list_format[i] =	le32_to_cpu(tmp[i]);
 
-	adev->gfx.rlc.register_restore = adev->gfx.rlc.register_list_format + i;
+		adev->gfx.rlc.register_restore = adev->gfx.rlc.register_list_format + i;
 
-	tmp = (unsigned int *)((uintptr_t)rlc_hdr +
-			le32_to_cpu(rlc_hdr->reg_list_array_offset_bytes));
-	for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++)
-		adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]);
+		tmp = (unsigned int *)((uintptr_t)rlc_hdr +
+							   le32_to_cpu(rlc_hdr->reg_list_array_offset_bytes));
+		for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++)
+			adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]);
 
-	if (adev->gfx.rlc.is_rlc_v2_1)
-		gfx_v10_0_init_rlc_ext_microcode(adev);
+		if (adev->gfx.rlc.is_rlc_v2_1)
+			gfx_v10_0_init_rlc_ext_microcode(adev);
+	}
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev);
@@ -993,39 +995,6 @@ static int gfx_v10_0_rlc_init(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int gfx_v10_0_csb_vram_pin(struct amdgpu_device *adev)
-{
-	int r;
-
-	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false);
-	if (unlikely(r != 0))
-		return r;
-
-	r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj,
-			AMDGPU_GEM_DOMAIN_VRAM);
-	if (!r)
-		adev->gfx.rlc.clear_state_gpu_addr =
-			amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj);
-
-	amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
-
-	return r;
-}
-
-static void gfx_v10_0_csb_vram_unpin(struct amdgpu_device *adev)
-{
-	int r;
-
-	if (!adev->gfx.rlc.clear_state_obj)
-		return;
-
-	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true);
-	if (likely(r == 0)) {
-		amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj);
-		amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
-	}
-}
-
 static void gfx_v10_0_mec_fini(struct amdgpu_device *adev)
 {
 	amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL);
@@ -1787,25 +1756,7 @@ static void gfx_v10_0_enable_gui_idle_interrupt(struct amdgpu_device *adev,
 
 static int gfx_v10_0_init_csb(struct amdgpu_device *adev)
 {
-	int r;
-
-	if (adev->in_gpu_reset) {
-		r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false);
-		if (r)
-			return r;
-
-		r = amdgpu_bo_kmap(adev->gfx.rlc.clear_state_obj,
-				   (void **)&adev->gfx.rlc.cs_ptr);
-		if (!r) {
-			adev->gfx.rlc.funcs->get_csb_buffer(adev,
-					adev->gfx.rlc.cs_ptr);
-			amdgpu_bo_kunmap(adev->gfx.rlc.clear_state_obj);
-		}
-
-		amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
-		if (r)
-			return r;
-	}
+	adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr);
 
 	/* csib */
 	WREG32_SOC15(GC, 0, mmRLC_CSIB_ADDR_HI,
@@ -1817,22 +1768,6 @@ static int gfx_v10_0_init_csb(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int gfx_v10_0_init_pg(struct amdgpu_device *adev)
-{
-	int i;
-	int r;
-
-	r = gfx_v10_0_init_csb(adev);
-	if (r)
-		return r;
-
-	for (i = 0; i < adev->num_vmhubs; i++)
-		amdgpu_gmc_flush_gpu_tlb(adev, 0, i, 0);
-
-	/* TODO: init power gating */
-	return 0;
-}
-
 void gfx_v10_0_rlc_stop(struct amdgpu_device *adev)
 {
 	u32 tmp = RREG32_SOC15(GC, 0, mmRLC_CNTL);
@@ -1925,21 +1860,16 @@ static int gfx_v10_0_rlc_resume(struct amdgpu_device *adev)
 {
 	int r;
 
-	if (amdgpu_sriov_vf(adev))
-		return 0;
-
 	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
-		r = gfx_v10_0_wait_for_rlc_autoload_complete(adev);
-		if (r)
-			return r;
 
-		r = gfx_v10_0_init_pg(adev);
+		r = gfx_v10_0_wait_for_rlc_autoload_complete(adev);
 		if (r)
 			return r;
 
-		/* enable RLC SRM */
-		gfx_v10_0_rlc_enable_srm(adev);
+		gfx_v10_0_init_csb(adev);
 
+		if (!amdgpu_sriov_vf(adev)) /* enable RLC SRM */
+			gfx_v10_0_rlc_enable_srm(adev);
 	} else {
 		adev->gfx.rlc.funcs->stop(adev);
 
@@ -1961,9 +1891,7 @@ static int gfx_v10_0_rlc_resume(struct amdgpu_device *adev)
 				return r;
 		}
 
-		r = gfx_v10_0_init_pg(adev);
-		if (r)
-			return r;
+		gfx_v10_0_init_csb(adev);
 
 		adev->gfx.rlc.funcs->start(adev);
 
@@ -2825,7 +2753,7 @@ static int gfx_v10_0_cp_gfx_resume(struct amdgpu_device *adev)
 	/* Init gfx ring 0 for pipe 0 */
 	mutex_lock(&adev->srbm_mutex);
 	gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID0);
-	mutex_unlock(&adev->srbm_mutex);
+
 	/* Set ring buffer size */
 	ring = &adev->gfx.gfx_ring[0];
 	rb_bufsz = order_base_2(ring->ring_size / 8);
@@ -2863,11 +2791,11 @@ static int gfx_v10_0_cp_gfx_resume(struct amdgpu_device *adev)
 	WREG32_SOC15(GC, 0, mmCP_RB_ACTIVE, 1);
 
 	gfx_v10_0_cp_gfx_set_doorbell(adev, ring);
+	mutex_unlock(&adev->srbm_mutex);
 
 	/* Init gfx ring 1 for pipe 1 */
 	mutex_lock(&adev->srbm_mutex);
 	gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID1);
-	mutex_unlock(&adev->srbm_mutex);
 	ring = &adev->gfx.gfx_ring[1];
 	rb_bufsz = order_base_2(ring->ring_size / 8);
 	tmp = REG_SET_FIELD(0, CP_RB1_CNTL, RB_BUFSZ, rb_bufsz);
@@ -2897,6 +2825,7 @@ static int gfx_v10_0_cp_gfx_resume(struct amdgpu_device *adev)
 	WREG32_SOC15(GC, 0, mmCP_RB1_ACTIVE, 1);
 
 	gfx_v10_0_cp_gfx_set_doorbell(adev, ring);
+	mutex_unlock(&adev->srbm_mutex);
 
 	/* Switch to pipe 0 */
 	mutex_lock(&adev->srbm_mutex);
@@ -3775,10 +3704,6 @@ static int gfx_v10_0_hw_init(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = gfx_v10_0_csb_vram_pin(adev);
-	if (r)
-		return r;
-
 	if (!amdgpu_emu_mode)
 		gfx_v10_0_init_golden_registers(adev);
 
@@ -3861,12 +3786,11 @@ static int gfx_v10_0_hw_fini(void *handle)
 	if (amdgpu_gfx_disable_kcq(adev))
 		DRM_ERROR("KCQ disable failed\n");
 	if (amdgpu_sriov_vf(adev)) {
-		pr_debug("For SRIOV client, shouldn't do anything.\n");
+		gfx_v10_0_cp_gfx_enable(adev, false);
 		return 0;
 	}
 	gfx_v10_0_cp_enable(adev, false);
 	gfx_v10_0_enable_gui_idle_interrupt(adev, false);
-	gfx_v10_0_csb_vram_unpin(adev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 791ba398f007..d92e92e5d50b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -4554,6 +4554,8 @@ static int gfx_v7_0_hw_init(void *handle)
 
 	gfx_v7_0_constants_init(adev);
 
+	/* init CSB */
+	adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr);
 	/* init rlc */
 	r = adev->gfx.rlc.funcs->resume(adev);
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index ffbde9136372..983db77999e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -1321,39 +1321,6 @@ static int gfx_v8_0_rlc_init(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int gfx_v8_0_csb_vram_pin(struct amdgpu_device *adev)
-{
-	int r;
-
-	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false);
-	if (unlikely(r != 0))
-		return r;
-
-	r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj,
-			AMDGPU_GEM_DOMAIN_VRAM);
-	if (!r)
-		adev->gfx.rlc.clear_state_gpu_addr =
-			amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj);
-
-	amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
-
-	return r;
-}
-
-static void gfx_v8_0_csb_vram_unpin(struct amdgpu_device *adev)
-{
-	int r;
-
-	if (!adev->gfx.rlc.clear_state_obj)
-		return;
-
-	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true);
-	if (likely(r == 0)) {
-		amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj);
-		amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
-	}
-}
-
 static void gfx_v8_0_mec_fini(struct amdgpu_device *adev)
 {
 	amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL);
@@ -3917,6 +3884,7 @@ static void gfx_v8_0_enable_gui_idle_interrupt(struct amdgpu_device *adev,
 
 static void gfx_v8_0_init_csb(struct amdgpu_device *adev)
 {
+	adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr);
 	/* csib */
 	WREG32(mmRLC_CSIB_ADDR_HI,
 			adev->gfx.rlc.clear_state_gpu_addr >> 32);
@@ -4837,10 +4805,6 @@ static int gfx_v8_0_hw_init(void *handle)
 	gfx_v8_0_init_golden_registers(adev);
 	gfx_v8_0_constants_init(adev);
 
-	r = gfx_v8_0_csb_vram_pin(adev);
-	if (r)
-		return r;
-
 	r = adev->gfx.rlc.funcs->resume(adev);
 	if (r)
 		return r;
@@ -4958,8 +4922,6 @@ static int gfx_v8_0_hw_fini(void *handle)
 		pr_err("rlc is busy, skip halt rlc\n");
 	amdgpu_gfx_rlc_exit_safe_mode(adev);
 
-	gfx_v8_0_csb_vram_unpin(adev);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index faf2ffce5837..66328ffa395a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1695,39 +1695,6 @@ static int gfx_v9_0_rlc_init(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int gfx_v9_0_csb_vram_pin(struct amdgpu_device *adev)
-{
-	int r;
-
-	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false);
-	if (unlikely(r != 0))
-		return r;
-
-	r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj,
-			AMDGPU_GEM_DOMAIN_VRAM);
-	if (!r)
-		adev->gfx.rlc.clear_state_gpu_addr =
-			amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj);
-
-	amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
-
-	return r;
-}
-
-static void gfx_v9_0_csb_vram_unpin(struct amdgpu_device *adev)
-{
-	int r;
-
-	if (!adev->gfx.rlc.clear_state_obj)
-		return;
-
-	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true);
-	if (likely(r == 0)) {
-		amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj);
-		amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
-	}
-}
-
 static void gfx_v9_0_mec_fini(struct amdgpu_device *adev)
 {
 	amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL);
@@ -2415,6 +2382,7 @@ static void gfx_v9_0_enable_gui_idle_interrupt(struct amdgpu_device *adev,
 
 static void gfx_v9_0_init_csb(struct amdgpu_device *adev)
 {
+	adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr);
 	/* csib */
 	WREG32_RLC(SOC15_REG_OFFSET(GC, 0, mmRLC_CSIB_ADDR_HI),
 			adev->gfx.rlc.clear_state_gpu_addr >> 32);
@@ -3706,10 +3674,6 @@ static int gfx_v9_0_hw_init(void *handle)
 
 	gfx_v9_0_constants_init(adev);
 
-	r = gfx_v9_0_csb_vram_pin(adev);
-	if (r)
-		return r;
-
 	r = adev->gfx.rlc.funcs->resume(adev);
 	if (r)
 		return r;
@@ -3791,8 +3755,6 @@ static int gfx_v9_0_hw_fini(void *handle)
 	gfx_v9_0_cp_enable(adev, false);
 	adev->gfx.rlc.funcs->stop(adev);
 
-	gfx_v9_0_csb_vram_unpin(adev);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
index 5e9ab8eb214a..c0ab71df0d90 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
@@ -33,16 +33,31 @@ int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev)
 	u32 xgmi_lfb_cntl = RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_CNTL);
 	u32 max_region =
 		REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL, PF_MAX_REGION);
+	u32 max_num_physical_nodes   = 0;
+	u32 max_physical_node_id     = 0;
+
+	switch (adev->asic_type) {
+	case CHIP_VEGA20:
+		max_num_physical_nodes   = 4;
+		max_physical_node_id     = 3;
+		break;
+	case CHIP_ARCTURUS:
+		max_num_physical_nodes   = 8;
+		max_physical_node_id     = 7;
+		break;
+	default:
+		return -EINVAL;
+	}
 
 	/* PF_MAX_REGION=0 means xgmi is disabled */
 	if (max_region) {
 		adev->gmc.xgmi.num_physical_nodes = max_region + 1;
-		if (adev->gmc.xgmi.num_physical_nodes > 4)
+		if (adev->gmc.xgmi.num_physical_nodes > max_num_physical_nodes)
 			return -EINVAL;
 
 		adev->gmc.xgmi.physical_node_id =
 			REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL, PF_LFB_REGION);
-		if (adev->gmc.xgmi.physical_node_id > 3)
+		if (adev->gmc.xgmi.physical_node_id > max_physical_node_id)
 			return -EINVAL;
 		adev->gmc.xgmi.node_segment_size = REG_GET_FIELD(
 			RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_SIZE),
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 321f8a997be8..232469507446 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -326,7 +326,8 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 
 	if (!adev->mman.buffer_funcs_enabled ||
 	    !adev->ib_pool_ready ||
-	    adev->in_gpu_reset) {
+	    adev->in_gpu_reset ||
+	    ring->sched.ready == false) {
 		gmc_v10_0_flush_vm_hub(adev, vmid, AMDGPU_GFXHUB_0, 0);
 		mutex_unlock(&adev->mman.gtt_window_lock);
 		return;
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 78e5cdc0c058..f1b171e30774 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -783,10 +783,13 @@ static int vi_asic_reset(struct amdgpu_device *adev)
 {
 	int r;
 
-	if (vi_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)
+	if (vi_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
+		if (!adev->in_suspend)
+			amdgpu_inc_vram_lost(adev);
 		r = smu7_asic_baco_reset(adev);
-	else
+	} else {
 		r = vi_asic_pci_config_reset(adev);
+	}
 
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/Kconfig b/drivers/gpu/drm/amd/amdkfd/Kconfig
index a1a35d4d594b..ba0e68057a89 100644
--- a/drivers/gpu/drm/amd/amdkfd/Kconfig
+++ b/drivers/gpu/drm/amd/amdkfd/Kconfig
@@ -5,7 +5,7 @@
 
 config HSA_AMD
 	bool "HSA kernel driver for AMD GPU devices"
-	depends on DRM_AMDGPU && (X86_64 || ARM64)
+	depends on DRM_AMDGPU && (X86_64 || ARM64 || PPC64)
 	imply AMD_IOMMU_V2 if X86_64
 	select MMU_NOTIFIER
 	help
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index 55a520a63712..778f186b3a05 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -342,7 +342,8 @@ bool dm_pp_get_clock_levels_by_type(
 	if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->get_clock_by_type) {
 		if (adev->powerplay.pp_funcs->get_clock_by_type(pp_handle,
 			dc_to_pp_clock_type(clk_type), &pp_clks)) {
-		/* Error in pplib. Provide default values. */
+			/* Error in pplib. Provide default values. */
+			get_default_clock_levels(clk_type, dc_clks);
 			return true;
 		}
 	} else if (adev->smu.ppt_funcs && adev->smu.ppt_funcs->get_clock_by_type) {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 921a36668ced..ac8c18fadefc 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1037,6 +1037,25 @@ void dcn20_pipe_control_lock(
 	if (pipe->plane_state != NULL)
 		flip_immediate = pipe->plane_state->flip_immediate;
 
+	if (flip_immediate && lock) {
+		const int TIMEOUT_FOR_FLIP_PENDING = 100000;
+		int i;
+
+		for (i = 0; i < TIMEOUT_FOR_FLIP_PENDING; ++i) {
+			if (!pipe->plane_res.hubp->funcs->hubp_is_flip_pending(pipe->plane_res.hubp))
+				break;
+			udelay(1);
+		}
+
+		if (pipe->bottom_pipe != NULL) {
+			for (i = 0; i < TIMEOUT_FOR_FLIP_PENDING; ++i) {
+				if (!pipe->bottom_pipe->plane_res.hubp->funcs->hubp_is_flip_pending(pipe->bottom_pipe->plane_res.hubp))
+					break;
+				udelay(1);
+			}
+		}
+	}
+
 	/* In flip immediate and pipe splitting case, we need to use GSL
 	 * for synchronization. Only do setup on locking and on flip type change.
 	 */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index bbd1c98564be..09793336d84f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -157,6 +157,74 @@ struct _vcs_dpi_ip_params_st dcn2_0_ip = {
 	.xfc_fill_constant_bytes = 0,
 };
 
+struct _vcs_dpi_ip_params_st dcn2_0_nv14_ip = {
+	.odm_capable = 1,
+	.gpuvm_enable = 0,
+	.hostvm_enable = 0,
+	.gpuvm_max_page_table_levels = 4,
+	.hostvm_max_page_table_levels = 4,
+	.hostvm_cached_page_table_levels = 0,
+	.num_dsc = 5,
+	.rob_buffer_size_kbytes = 168,
+	.det_buffer_size_kbytes = 164,
+	.dpte_buffer_size_in_pte_reqs_luma = 84,
+	.dpte_buffer_size_in_pte_reqs_chroma = 42,//todo
+	.dpp_output_buffer_pixels = 2560,
+	.opp_output_buffer_lines = 1,
+	.pixel_chunk_size_kbytes = 8,
+	.pte_enable = 1,
+	.max_page_table_levels = 4,
+	.pte_chunk_size_kbytes = 2,
+	.meta_chunk_size_kbytes = 2,
+	.writeback_chunk_size_kbytes = 2,
+	.line_buffer_size_bits = 789504,
+	.is_line_buffer_bpp_fixed = 0,
+	.line_buffer_fixed_bpp = 0,
+	.dcc_supported = true,
+	.max_line_buffer_lines = 12,
+	.writeback_luma_buffer_size_kbytes = 12,
+	.writeback_chroma_buffer_size_kbytes = 8,
+	.writeback_chroma_line_buffer_width_pixels = 4,
+	.writeback_max_hscl_ratio = 1,
+	.writeback_max_vscl_ratio = 1,
+	.writeback_min_hscl_ratio = 1,
+	.writeback_min_vscl_ratio = 1,
+	.writeback_max_hscl_taps = 12,
+	.writeback_max_vscl_taps = 12,
+	.writeback_line_buffer_luma_buffer_size = 0,
+	.writeback_line_buffer_chroma_buffer_size = 14643,
+	.cursor_buffer_size = 8,
+	.cursor_chunk_size = 2,
+	.max_num_otg = 5,
+	.max_num_dpp = 5,
+	.max_num_wb = 1,
+	.max_dchub_pscl_bw_pix_per_clk = 4,
+	.max_pscl_lb_bw_pix_per_clk = 2,
+	.max_lb_vscl_bw_pix_per_clk = 4,
+	.max_vscl_hscl_bw_pix_per_clk = 4,
+	.max_hscl_ratio = 8,
+	.max_vscl_ratio = 8,
+	.hscl_mults = 4,
+	.vscl_mults = 4,
+	.max_hscl_taps = 8,
+	.max_vscl_taps = 8,
+	.dispclk_ramp_margin_percent = 1,
+	.underscan_factor = 1.10,
+	.min_vblank_lines = 32, //
+	.dppclk_delay_subtotal = 77, //
+	.dppclk_delay_scl_lb_only = 16,
+	.dppclk_delay_scl = 50,
+	.dppclk_delay_cnvc_formatter = 8,
+	.dppclk_delay_cnvc_cursor = 6,
+	.dispclk_delay_subtotal = 87, //
+	.dcfclk_cstate_latency = 10, // SRExitTime
+	.max_inter_dcn_tile_repeaters = 8,
+	.xfc_supported = true,
+	.xfc_fill_bw_overhead_percent = 10.0,
+	.xfc_fill_constant_bytes = 0,
+	.ptoi_supported = 0
+};
+
 struct _vcs_dpi_soc_bounding_box_st dcn2_0_soc = {
 	/* Defaults that get patched on driver load from firmware. */
 	.clock_limits = {
@@ -854,6 +922,8 @@ static const struct resource_caps res_cap_nv14 = {
 		.num_pll = 5,
 		.num_dwb = 1,
 		.num_ddc = 5,
+		.num_vmid = 16,
+		.num_dsc = 5,
 };
 
 static const struct dc_debug_options debug_defaults_drv = {
@@ -3212,6 +3282,10 @@ static struct _vcs_dpi_soc_bounding_box_st *get_asic_rev_soc_bb(
 static struct _vcs_dpi_ip_params_st *get_asic_rev_ip_params(
 	uint32_t hw_internal_rev)
 {
+	/* NV14 */
+	if (ASICREV_IS_NAVI14_M(hw_internal_rev))
+		return &dcn2_0_nv14_ip;
+
 	/* NV12 and NV10 */
 	return &dcn2_0_ip;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 40b546c75fc2..5ff7ccedfbed 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -2548,3 +2548,12 @@ uint32_t smu_get_pptable_power_limit(struct smu_context *smu)
 
 	return ret;
 }
+
+int smu_send_smc_msg(struct smu_context *smu,
+		     enum smu_message_type msg)
+{
+	int ret;
+
+	ret = smu_send_smc_msg_with_param(smu, msg, 0);
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index 58c7c4a3053e..ce3566ca3e24 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -2130,7 +2130,6 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.set_tool_table_location = smu_v11_0_set_tool_table_location,
 	.notify_memory_pool_location = smu_v11_0_notify_memory_pool_location,
 	.system_features_control = smu_v11_0_system_features_control,
-	.send_smc_msg = smu_v11_0_send_msg,
 	.send_smc_msg_with_param = smu_v11_0_send_msg_with_param,
 	.read_smc_arg = smu_v11_0_read_arg,
 	.init_display_count = smu_v11_0_init_display_count,
diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
index 031e0c22fcc7..ac9758305ab3 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
@@ -497,8 +497,8 @@ struct pptable_funcs {
 	int (*notify_memory_pool_location)(struct smu_context *smu);
 	int (*set_last_dcef_min_deep_sleep_clk)(struct smu_context *smu);
 	int (*system_features_control)(struct smu_context *smu, bool en);
-	int (*send_smc_msg)(struct smu_context *smu, uint16_t msg);
-	int (*send_smc_msg_with_param)(struct smu_context *smu, uint16_t msg, uint32_t param);
+	int (*send_smc_msg_with_param)(struct smu_context *smu,
+				       enum smu_message_type msg, uint32_t param);
 	int (*read_smc_arg)(struct smu_context *smu, uint32_t *arg);
 	int (*init_display_count)(struct smu_context *smu, uint32_t count);
 	int (*set_allowed_mask)(struct smu_context *smu);
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index 606149085683..719844257713 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -177,10 +177,9 @@ int smu_v11_0_notify_memory_pool_location(struct smu_context *smu);
 int smu_v11_0_system_features_control(struct smu_context *smu,
 					     bool en);
 
-int smu_v11_0_send_msg(struct smu_context *smu, uint16_t msg);
-
 int
-smu_v11_0_send_msg_with_param(struct smu_context *smu, uint16_t msg,
+smu_v11_0_send_msg_with_param(struct smu_context *smu,
+			      enum smu_message_type msg,
 			      uint32_t param);
 
 int smu_v11_0_read_arg(struct smu_context *smu, uint32_t *arg);
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h
index 9b9f5df0911c..9d81d789c713 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h
@@ -44,10 +44,9 @@ int smu_v12_0_read_arg(struct smu_context *smu, uint32_t *arg);
 
 int smu_v12_0_wait_for_response(struct smu_context *smu);
 
-int smu_v12_0_send_msg(struct smu_context *smu, uint16_t msg);
-
 int
-smu_v12_0_send_msg_with_param(struct smu_context *smu, uint16_t msg,
+smu_v12_0_send_msg_with_param(struct smu_context *smu,
+			      enum smu_message_type msg,
 			      uint32_t param);
 
 int smu_v12_0_check_fw_status(struct smu_context *smu);
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index aaec884d63ed..4a14fd1f9fd5 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -2055,7 +2055,6 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.set_tool_table_location = smu_v11_0_set_tool_table_location,
 	.notify_memory_pool_location = smu_v11_0_notify_memory_pool_location,
 	.system_features_control = smu_v11_0_system_features_control,
-	.send_smc_msg = smu_v11_0_send_msg,
 	.send_smc_msg_with_param = smu_v11_0_send_msg_with_param,
 	.read_smc_arg = smu_v11_0_read_arg,
 	.init_display_count = smu_v11_0_init_display_count,
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
index 04daf7e9fe05..977bdd962e98 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
@@ -697,7 +697,6 @@ static const struct pptable_funcs renoir_ppt_funcs = {
 	.check_fw_version = smu_v12_0_check_fw_version,
 	.powergate_sdma = smu_v12_0_powergate_sdma,
 	.powergate_vcn = smu_v12_0_powergate_vcn,
-	.send_smc_msg = smu_v12_0_send_msg,
 	.send_smc_msg_with_param = smu_v12_0_send_msg_with_param,
 	.read_smc_arg = smu_v12_0_read_arg,
 	.set_gfx_cgpg = smu_v12_0_set_gfx_cgpg,
diff --git a/drivers/gpu/drm/amd/powerplay/smu_internal.h b/drivers/gpu/drm/amd/powerplay/smu_internal.h
index 8bcda7871309..8872f8b2d502 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_internal.h
+++ b/drivers/gpu/drm/amd/powerplay/smu_internal.h
@@ -75,8 +75,8 @@
 #define smu_set_default_od_settings(smu, initialize) \
 	((smu)->ppt_funcs->set_default_od_settings ? (smu)->ppt_funcs->set_default_od_settings((smu), (initialize)) : 0)
 
-#define smu_send_smc_msg(smu, msg) \
-	((smu)->ppt_funcs->send_smc_msg? (smu)->ppt_funcs->send_smc_msg((smu), (msg)) : 0)
+int smu_send_smc_msg(struct smu_context *smu, enum smu_message_type msg);
+
 #define smu_send_smc_msg_with_param(smu, msg, param) \
 	((smu)->ppt_funcs->send_smc_msg_with_param? (smu)->ppt_funcs->send_smc_msg_with_param((smu), (msg), (param)) : 0)
 #define smu_read_smc_arg(smu, arg) \
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index fc9679ea2368..e4268a627eff 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -90,36 +90,11 @@ static int smu_v11_0_wait_for_response(struct smu_context *smu)
 	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90) == 0x1 ? 0 : -EIO;
 }
 
-int smu_v11_0_send_msg(struct smu_context *smu, uint16_t msg)
-{
-	struct amdgpu_device *adev = smu->adev;
-	int ret = 0, index = 0;
-
-	index = smu_msg_get_index(smu, msg);
-	if (index < 0)
-		return index;
-
-	smu_v11_0_wait_for_response(smu);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	smu_v11_0_send_msg_without_waiting(smu, (uint16_t)index);
-
-	ret = smu_v11_0_wait_for_response(smu);
-
-	if (ret)
-		pr_err("failed send message: %10s (%d) response %#x\n",
-		       smu_get_message_name(smu, msg), index, ret);
-
-	return ret;
-
-}
-
 int
-smu_v11_0_send_msg_with_param(struct smu_context *smu, uint16_t msg,
+smu_v11_0_send_msg_with_param(struct smu_context *smu,
+			      enum smu_message_type msg,
 			      uint32_t param)
 {
-
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0, index = 0;
 
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v12_0.c b/drivers/gpu/drm/amd/powerplay/smu_v12_0.c
index 139dd737eaa5..094cfc46adac 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v12_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v12_0.c
@@ -77,33 +77,9 @@ int smu_v12_0_wait_for_response(struct smu_context *smu)
 	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90) == 0x1 ? 0 : -EIO;
 }
 
-int smu_v12_0_send_msg(struct smu_context *smu, uint16_t msg)
-{
-	struct amdgpu_device *adev = smu->adev;
-	int ret = 0, index = 0;
-
-	index = smu_msg_get_index(smu, msg);
-	if (index < 0)
-		return index;
-
-	smu_v12_0_wait_for_response(smu);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	smu_v12_0_send_msg_without_waiting(smu, (uint16_t)index);
-
-	ret = smu_v12_0_wait_for_response(smu);
-
-	if (ret)
-		pr_err("Failed to send message 0x%x, response 0x%x\n", index,
-		       ret);
-
-	return ret;
-
-}
-
 int
-smu_v12_0_send_msg_with_param(struct smu_context *smu, uint16_t msg,
+smu_v12_0_send_msg_with_param(struct smu_context *smu,
+			      enum smu_message_type msg,
 			      uint32_t param)
 {
 	struct amdgpu_device *adev = smu->adev;
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index 0b4892833808..60b9ff097142 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -3231,7 +3231,6 @@ static const struct pptable_funcs vega20_ppt_funcs = {
 	.set_tool_table_location = smu_v11_0_set_tool_table_location,
 	.notify_memory_pool_location = smu_v11_0_notify_memory_pool_location,
 	.system_features_control = smu_v11_0_system_features_control,
-	.send_smc_msg = smu_v11_0_send_msg,
 	.send_smc_msg_with_param = smu_v11_0_send_msg_with_param,
 	.read_smc_arg = smu_v11_0_read_arg,
 	.init_display_count = smu_v11_0_init_display_count,
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index ae5809a1f19a..273dd80fabf3 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -3176,9 +3176,11 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr)
 			drm_dp_mst_topology_put_port(port);
 	}
 
-	for (i = 0; i < mgr->max_payloads; i++) {
-		if (mgr->payloads[i].payload_state != DP_PAYLOAD_DELETE_LOCAL)
+	for (i = 0; i < mgr->max_payloads; /* do nothing */) {
+		if (mgr->payloads[i].payload_state != DP_PAYLOAD_DELETE_LOCAL) {
+			i++;
 			continue;
+		}
 
 		DRM_DEBUG_KMS("removing payload %d\n", i);
 		for (j = i; j < mgr->max_payloads - 1; j++) {
diff --git a/drivers/gpu/drm/i915/Kconfig.profile b/drivers/gpu/drm/i915/Kconfig.profile
index 1799537a3228..c280b6ae38eb 100644
--- a/drivers/gpu/drm/i915/Kconfig.profile
+++ b/drivers/gpu/drm/i915/Kconfig.profile
@@ -25,7 +25,7 @@ config DRM_I915_HEARTBEAT_INTERVAL
 
 config DRM_I915_PREEMPT_TIMEOUT
 	int "Preempt timeout (ms, jiffy granularity)"
-	default 100 # milliseconds
+	default 640 # milliseconds
 	help
 	  How long to wait (in milliseconds) for a preemption event to occur
 	  when submitting a new context via execlists. If the current context
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 0caef2592a7e..ed8c7ce62119 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1273,7 +1273,9 @@ static u8 icl_calc_voltage_level(int cdclk)
 
 static u8 ehl_calc_voltage_level(int cdclk)
 {
-	if (cdclk > 312000)
+	if (cdclk > 326400)
+		return 3;
+	else if (cdclk > 312000)
 		return 2;
 	else if (cdclk > 180000)
 		return 1;
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 0d6e494b4508..c7c2b349858d 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -593,7 +593,7 @@ struct tgl_dkl_phy_ddi_buf_trans {
 	u32 dkl_de_emphasis_control;
 };
 
-static const struct tgl_dkl_phy_ddi_buf_trans tgl_dkl_phy_ddi_translations[] = {
+static const struct tgl_dkl_phy_ddi_buf_trans tgl_dkl_phy_dp_ddi_trans[] = {
 				/* VS	pre-emp	Non-trans mV	Pre-emph dB */
 	{ 0x7, 0x0, 0x00 },	/* 0	0	400mV		0 dB */
 	{ 0x5, 0x0, 0x03 },	/* 0	1	400mV		3.5 dB */
@@ -607,6 +607,20 @@ static const struct tgl_dkl_phy_ddi_buf_trans tgl_dkl_phy_ddi_translations[] = {
 	{ 0x0, 0x0, 0x00 },	/* 3	0	1200mV		0 dB HDMI default */
 };
 
+static const struct tgl_dkl_phy_ddi_buf_trans tgl_dkl_phy_hdmi_ddi_trans[] = {
+				/* HDMI Preset	VS	Pre-emph */
+	{ 0x7, 0x0, 0x0 },	/* 1		400mV	0dB */
+	{ 0x6, 0x0, 0x0 },	/* 2		500mV	0dB */
+	{ 0x4, 0x0, 0x0 },	/* 3		650mV	0dB */
+	{ 0x2, 0x0, 0x0 },	/* 4		800mV	0dB */
+	{ 0x0, 0x0, 0x0 },	/* 5		1000mV	0dB */
+	{ 0x0, 0x0, 0x5 },	/* 6		Full	-1.5 dB */
+	{ 0x0, 0x0, 0x6 },	/* 7		Full	-1.8 dB */
+	{ 0x0, 0x0, 0x7 },	/* 8		Full	-2 dB */
+	{ 0x0, 0x0, 0x8 },	/* 9		Full	-2.5 dB */
+	{ 0x0, 0x0, 0xA },	/* 10		Full	-3 dB */
+};
+
 static const struct ddi_buf_trans *
 bdw_get_buf_trans_edp(struct drm_i915_private *dev_priv, int *n_entries)
 {
@@ -898,7 +912,7 @@ static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port por
 			icl_get_combo_buf_trans(dev_priv, INTEL_OUTPUT_HDMI,
 						0, &n_entries);
 		else
-			n_entries = ARRAY_SIZE(tgl_dkl_phy_ddi_translations);
+			n_entries = ARRAY_SIZE(tgl_dkl_phy_hdmi_ddi_trans);
 		default_entry = n_entries - 1;
 	} else if (INTEL_GEN(dev_priv) == 11) {
 		if (intel_phy_is_combo(dev_priv, phy))
@@ -2371,7 +2385,7 @@ u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder)
 			icl_get_combo_buf_trans(dev_priv, encoder->type,
 						intel_dp->link_rate, &n_entries);
 		else
-			n_entries = ARRAY_SIZE(tgl_dkl_phy_ddi_translations);
+			n_entries = ARRAY_SIZE(tgl_dkl_phy_dp_ddi_trans);
 	} else if (INTEL_GEN(dev_priv) == 11) {
 		if (intel_phy_is_combo(dev_priv, phy))
 			icl_get_combo_buf_trans(dev_priv, encoder->type,
@@ -2823,8 +2837,13 @@ tgl_dkl_phy_ddi_vswing_sequence(struct intel_encoder *encoder, int link_clock,
 	const struct tgl_dkl_phy_ddi_buf_trans *ddi_translations;
 	u32 n_entries, val, ln, dpcnt_mask, dpcnt_val;
 
-	n_entries = ARRAY_SIZE(tgl_dkl_phy_ddi_translations);
-	ddi_translations = tgl_dkl_phy_ddi_translations;
+	if (encoder->type == INTEL_OUTPUT_HDMI) {
+		n_entries = ARRAY_SIZE(tgl_dkl_phy_hdmi_ddi_trans);
+		ddi_translations = tgl_dkl_phy_hdmi_ddi_trans;
+	} else {
+		n_entries = ARRAY_SIZE(tgl_dkl_phy_dp_ddi_trans);
+		ddi_translations = tgl_dkl_phy_dp_ddi_trans;
+	}
 
 	if (level >= n_entries)
 		level = n_entries - 1;
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index c61ac0c3acb5..050655a1a3d8 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -5476,15 +5476,13 @@ static bool bxt_digital_port_connected(struct intel_encoder *encoder)
 	return I915_READ(GEN8_DE_PORT_ISR) & bit;
 }
 
-static bool icl_combo_port_connected(struct drm_i915_private *dev_priv,
-				     struct intel_digital_port *intel_dig_port)
+static bool intel_combo_phy_connected(struct drm_i915_private *dev_priv,
+				      enum phy phy)
 {
-	enum port port = intel_dig_port->base.port;
-
-	if (HAS_PCH_MCC(dev_priv) && port == PORT_C)
+	if (HAS_PCH_MCC(dev_priv) && phy == PHY_C)
 		return I915_READ(SDEISR) & SDE_TC_HOTPLUG_ICP(PORT_TC1);
 
-	return I915_READ(SDEISR) & SDE_DDI_HOTPLUG_ICP(port);
+	return I915_READ(SDEISR) & SDE_DDI_HOTPLUG_ICP(phy);
 }
 
 static bool icl_digital_port_connected(struct intel_encoder *encoder)
@@ -5494,7 +5492,7 @@ static bool icl_digital_port_connected(struct intel_encoder *encoder)
 	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
 
 	if (intel_phy_is_combo(dev_priv, phy))
-		return icl_combo_port_connected(dev_priv, dig_port);
+		return intel_combo_phy_connected(dev_priv, phy);
 	else if (intel_phy_is_tc(dev_priv, phy))
 		return intel_tc_port_connected(dig_port);
 	else
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index e553ca8d98eb..337ba17b1e0e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -368,7 +368,7 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce)
 	if (!ce->timeline)
 		return NULL;
 
-	rcu_read_lock();
+	mutex_lock(&ce->timeline->mutex);
 	list_for_each_entry_reverse(rq, &ce->timeline->requests, link) {
 		if (i915_request_completed(rq))
 			break;
@@ -378,7 +378,7 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce)
 		if (engine)
 			break;
 	}
-	rcu_read_unlock();
+	mutex_unlock(&ce->timeline->mutex);
 
 	return engine;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index ee9d2bcd2c13..ef7bc41ffffa 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -310,10 +310,23 @@ int intel_context_prepare_remote_request(struct intel_context *ce,
 	GEM_BUG_ON(rq->hw_context == ce);
 
 	if (rcu_access_pointer(rq->timeline) != tl) { /* timeline sharing! */
-		err = mutex_lock_interruptible_nested(&tl->mutex,
-						      SINGLE_DEPTH_NESTING);
-		if (err)
-			return err;
+		/*
+		 * Ideally, we just want to insert our foreign fence as
+		 * a barrier into the remove context, such that this operation
+		 * occurs after all current operations in that context, and
+		 * all future operations must occur after this.
+		 *
+		 * Currently, the timeline->last_request tracking is guarded
+		 * by its mutex and so we must obtain that to atomically
+		 * insert our barrier. However, since we already hold our
+		 * timeline->mutex, we must be careful against potential
+		 * inversion if we are the kernel_context as the remote context
+		 * will itself poke at the kernel_context when it needs to
+		 * unpin. Ergo, if already locked, we drop both locks and
+		 * try again (through the magic of userspace repeating EAGAIN).
+		 */
+		if (!mutex_trylock(&tl->mutex))
+			return -EAGAIN;
 
 		/* Queue this switch after current activity by this context. */
 		err = i915_active_fence_set(&tl->last_request, rq);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index bc3b72bfa9e3..01765a7ec18f 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -100,9 +100,7 @@ execlists_num_ports(const struct intel_engine_execlists * const execlists)
 static inline struct i915_request *
 execlists_active(const struct intel_engine_execlists *execlists)
 {
-	GEM_BUG_ON(execlists->active - execlists->inflight >
-		   execlists_num_ports(execlists));
-	return READ_ONCE(*execlists->active);
+	return *READ_ONCE(execlists->active);
 }
 
 static inline void
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 5ca3ec911e50..813bd3a610d2 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -28,13 +28,13 @@
 
 #include "i915_drv.h"
 
-#include "gt/intel_gt.h"
-
+#include "intel_context.h"
 #include "intel_engine.h"
 #include "intel_engine_pm.h"
 #include "intel_engine_pool.h"
 #include "intel_engine_user.h"
-#include "intel_context.h"
+#include "intel_gt.h"
+#include "intel_gt_requests.h"
 #include "intel_lrc.h"
 #include "intel_reset.h"
 #include "intel_ring.h"
@@ -616,6 +616,7 @@ static int intel_engine_setup_common(struct intel_engine_cs *engine)
 	intel_engine_init_execlists(engine);
 	intel_engine_init_cmd_parser(engine);
 	intel_engine_init__pm(engine);
+	intel_engine_init_retire(engine);
 
 	intel_engine_pool_init(&engine->pool);
 
@@ -838,6 +839,7 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 
 	cleanup_status_page(engine);
 
+	intel_engine_fini_retire(engine);
 	intel_engine_pool_fini(&engine->pool);
 	intel_engine_fini_breadcrumbs(engine);
 	intel_engine_cleanup_cmd_parser(engine);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 874d82677179..c1dd0cd3efc7 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -73,8 +73,42 @@ static inline void __timeline_mark_unlock(struct intel_context *ce,
 
 #endif /* !IS_ENABLED(CONFIG_LOCKDEP) */
 
+static void
+__queue_and_release_pm(struct i915_request *rq,
+		       struct intel_timeline *tl,
+		       struct intel_engine_cs *engine)
+{
+	struct intel_gt_timelines *timelines = &engine->gt->timelines;
+
+	GEM_TRACE("%s\n", engine->name);
+
+	/*
+	 * We have to serialise all potential retirement paths with our
+	 * submission, as we don't want to underflow either the
+	 * engine->wakeref.counter or our timeline->active_count.
+	 *
+	 * Equally, we cannot allow a new submission to start until
+	 * after we finish queueing, nor could we allow that submitter
+	 * to retire us before we are ready!
+	 */
+	spin_lock(&timelines->lock);
+
+	/* Let intel_gt_retire_requests() retire us (acquired under lock) */
+	if (!atomic_fetch_inc(&tl->active_count))
+		list_add_tail(&tl->link, &timelines->active_list);
+
+	/* Hand the request over to HW and so engine_retire() */
+	__i915_request_queue(rq, NULL);
+
+	/* Let new submissions commence (and maybe retire this timeline) */
+	__intel_wakeref_defer_park(&engine->wakeref);
+
+	spin_unlock(&timelines->lock);
+}
+
 static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 {
+	struct intel_context *ce = engine->kernel_context;
 	struct i915_request *rq;
 	unsigned long flags;
 	bool result = true;
@@ -98,16 +132,31 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 	 * 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.
+	 *
+	 * For unlocking, there are 2 other parties and the GPU who have a
+	 * stake here.
+	 *
+	 * A new gpu user will be waiting on the engine-pm to start their
+	 * engine_unpark. New waiters are predicated on engine->wakeref.count
+	 * and so intel_wakeref_defer_park() acts like a mutex_unlock of the
+	 * engine->wakeref.
+	 *
+	 * The other party is intel_gt_retire_requests(), which is walking the
+	 * list of active timelines looking for completions. Meanwhile as soon
+	 * as we call __i915_request_queue(), the GPU may complete our request.
+	 * Ergo, if we put ourselves on the timelines.active_list
+	 * (se intel_timeline_enter()) before we increment the
+	 * engine->wakeref.count, we may see the request completion and retire
+	 * it causing an undeflow of the engine->wakeref.
 	 */
-	flags = __timeline_mark_lock(engine->kernel_context);
+	flags = __timeline_mark_lock(ce);
+	GEM_BUG_ON(atomic_read(&ce->timeline->active_count) < 0);
 
-	rq = __i915_request_create(engine->kernel_context, GFP_NOWAIT);
+	rq = __i915_request_create(ce, GFP_NOWAIT);
 	if (IS_ERR(rq))
 		/* Context switch failed, hope for the best! Maybe reset? */
 		goto out_unlock;
 
-	intel_timeline_enter(i915_request_timeline(rq));
-
 	/* Check again on the next retirement. */
 	engine->wakeref_serial = engine->serial + 1;
 	i915_request_add_active_barriers(rq);
@@ -116,13 +165,12 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 	rq->sched.attr.priority = I915_PRIORITY_BARRIER;
 	__i915_request_commit(rq);
 
-	/* Release our exclusive hold on the engine */
-	__intel_wakeref_defer_park(&engine->wakeref);
-	__i915_request_queue(rq, NULL);
+	/* Expose ourselves to the world */
+	__queue_and_release_pm(rq, ce->timeline, engine);
 
 	result = false;
 out_unlock:
-	__timeline_mark_unlock(engine->kernel_context, flags);
+	__timeline_mark_unlock(ce, flags);
 	return result;
 }
 
@@ -177,7 +225,8 @@ static int __engine_park(struct intel_wakeref *wf)
 
 	engine->execlists.no_priolist = false;
 
-	intel_gt_pm_put(engine->gt);
+	/* While gt calls i915_vma_parked(), we have to break the lock cycle */
+	intel_gt_pm_put_async(engine->gt);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.h b/drivers/gpu/drm/i915/gt/intel_engine_pm.h
index 739c50fefcef..24e20344dc22 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.h
@@ -31,6 +31,16 @@ static inline void intel_engine_pm_put(struct intel_engine_cs *engine)
 	intel_wakeref_put(&engine->wakeref);
 }
 
+static inline void intel_engine_pm_put_async(struct intel_engine_cs *engine)
+{
+	intel_wakeref_put_async(&engine->wakeref);
+}
+
+static inline void intel_engine_pm_flush(struct intel_engine_cs *engine)
+{
+	intel_wakeref_unlock_wait(&engine->wakeref);
+}
+
 void intel_engine_init__pm(struct intel_engine_cs *engine);
 
 #endif /* INTEL_ENGINE_PM_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 758f0e8ec672..17f1f1441efc 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -451,6 +451,14 @@ struct intel_engine_cs {
 
 	struct intel_engine_execlists execlists;
 
+	/*
+	 * Keep track of completed timelines on this engine for early
+	 * retirement with the goal of quickly enabling powersaving as
+	 * soon as the engine is idle.
+	 */
+	struct intel_timeline *retire;
+	struct work_struct retire_work;
+
 	/* status_notifier: list of callbacks for context-switch changes */
 	struct atomic_notifier_head context_status_notifier;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index 6187cdd06646..a459a42ad5c2 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -105,7 +105,6 @@ static int __gt_park(struct intel_wakeref *wf)
 static const struct intel_wakeref_ops wf_ops = {
 	.get = __gt_unpark,
 	.put = __gt_park,
-	.flags = INTEL_WAKEREF_PUT_ASYNC,
 };
 
 void intel_gt_pm_init_early(struct intel_gt *gt)
@@ -272,7 +271,7 @@ void intel_gt_suspend_prepare(struct intel_gt *gt)
 
 static suspend_state_t pm_suspend_target(void)
 {
-#if IS_ENABLED(CONFIG_PM_SLEEP)
+#if IS_ENABLED(CONFIG_SUSPEND) && IS_ENABLED(CONFIG_PM_SLEEP)
 	return pm_suspend_target_state;
 #else
 	return PM_SUSPEND_TO_IDLE;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
index b3e17399be9b..990efc27a4e4 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
@@ -32,6 +32,11 @@ static inline void intel_gt_pm_put(struct intel_gt *gt)
 	intel_wakeref_put(&gt->wakeref);
 }
 
+static inline void intel_gt_pm_put_async(struct intel_gt *gt)
+{
+	intel_wakeref_put_async(&gt->wakeref);
+}
+
 static inline int intel_gt_pm_wait_for_idle(struct intel_gt *gt)
 {
 	return intel_wakeref_wait_for_idle(&gt->wakeref);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index 353809ac2754..3dc13ecf41bf 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -4,6 +4,8 @@
  * Copyright © 2019 Intel Corporation
  */
 
+#include <linux/workqueue.h>
+
 #include "i915_drv.h" /* for_each_engine() */
 #include "i915_request.h"
 #include "intel_gt.h"
@@ -29,6 +31,79 @@ static void flush_submission(struct intel_gt *gt)
 		intel_engine_flush_submission(engine);
 }
 
+static void engine_retire(struct work_struct *work)
+{
+	struct intel_engine_cs *engine =
+		container_of(work, typeof(*engine), retire_work);
+	struct intel_timeline *tl = xchg(&engine->retire, NULL);
+
+	do {
+		struct intel_timeline *next = xchg(&tl->retire, NULL);
+
+		/*
+		 * Our goal here is to retire _idle_ timelines as soon as
+		 * possible (as they are idle, we do not expect userspace
+		 * to be cleaning up anytime soon).
+		 *
+		 * If the timeline is currently locked, either it is being
+		 * retired elsewhere or about to be!
+		 */
+		if (mutex_trylock(&tl->mutex)) {
+			retire_requests(tl);
+			mutex_unlock(&tl->mutex);
+		}
+		intel_timeline_put(tl);
+
+		GEM_BUG_ON(!next);
+		tl = ptr_mask_bits(next, 1);
+	} while (tl);
+}
+
+static bool add_retire(struct intel_engine_cs *engine,
+		       struct intel_timeline *tl)
+{
+	struct intel_timeline *first;
+
+	/*
+	 * We open-code a llist here to include the additional tag [BIT(0)]
+	 * so that we know when the timeline is already on a
+	 * retirement queue: either this engine or another.
+	 *
+	 * However, we rely on that a timeline can only be active on a single
+	 * engine at any one time and that add_retire() is called before the
+	 * engine releases the timeline and transferred to another to retire.
+	 */
+
+	if (READ_ONCE(tl->retire)) /* already queued */
+		return false;
+
+	intel_timeline_get(tl);
+	first = READ_ONCE(engine->retire);
+	do
+		tl->retire = ptr_pack_bits(first, 1, 1);
+	while (!try_cmpxchg(&engine->retire, &first, tl));
+
+	return !first;
+}
+
+void intel_engine_add_retire(struct intel_engine_cs *engine,
+			     struct intel_timeline *tl)
+{
+	if (add_retire(engine, tl))
+		schedule_work(&engine->retire_work);
+}
+
+void intel_engine_init_retire(struct intel_engine_cs *engine)
+{
+	INIT_WORK(&engine->retire_work, engine_retire);
+}
+
+void intel_engine_fini_retire(struct intel_engine_cs *engine)
+{
+	flush_work(&engine->retire_work);
+	GEM_BUG_ON(engine->retire);
+}
+
 long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 {
 	struct intel_gt_timelines *timelines = &gt->timelines;
@@ -52,8 +127,8 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 		}
 
 		intel_timeline_get(tl);
-		GEM_BUG_ON(!tl->active_count);
-		tl->active_count++; /* pin the list element */
+		GEM_BUG_ON(!atomic_read(&tl->active_count));
+		atomic_inc(&tl->active_count); /* pin the list element */
 		spin_unlock_irqrestore(&timelines->lock, flags);
 
 		if (timeout > 0) {
@@ -74,7 +149,7 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 
 		/* Resume iteration after dropping lock */
 		list_safe_reset_next(tl, tn, link);
-		if (!--tl->active_count)
+		if (atomic_dec_and_test(&tl->active_count))
 			list_del(&tl->link);
 		else
 			active_count += !!rcu_access_pointer(tl->last_request.fence);
@@ -83,7 +158,7 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 
 		/* Defer the final release to after the spinlock */
 		if (refcount_dec_and_test(&tl->kref.refcount)) {
-			GEM_BUG_ON(tl->active_count);
+			GEM_BUG_ON(atomic_read(&tl->active_count));
 			list_add(&tl->link, &free);
 		}
 	}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.h b/drivers/gpu/drm/i915/gt/intel_gt_requests.h
index bd31cbce47e0..d626fb115386 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.h
@@ -7,7 +7,9 @@
 #ifndef INTEL_GT_REQUESTS_H
 #define INTEL_GT_REQUESTS_H
 
+struct intel_engine_cs;
 struct intel_gt;
+struct intel_timeline;
 
 long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout);
 static inline void intel_gt_retire_requests(struct intel_gt *gt)
@@ -15,6 +17,11 @@ static inline void intel_gt_retire_requests(struct intel_gt *gt)
 	intel_gt_retire_requests_timeout(gt, 0);
 }
 
+void intel_engine_init_retire(struct intel_engine_cs *engine);
+void intel_engine_add_retire(struct intel_engine_cs *engine,
+			     struct intel_timeline *tl);
+void intel_engine_fini_retire(struct intel_engine_cs *engine);
+
 int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout);
 
 void intel_gt_init_requests(struct intel_gt *gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 0ac3b26674ad..9fdefbdc3546 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -142,6 +142,7 @@
 #include "intel_engine_pm.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
+#include "intel_gt_requests.h"
 #include "intel_lrc_reg.h"
 #include "intel_mocs.h"
 #include "intel_reset.h"
@@ -1115,9 +1116,17 @@ __execlists_schedule_out(struct i915_request *rq,
 	 * refrain from doing non-trivial work here.
 	 */
 
+	/*
+	 * If we have just completed this context, the engine may now be
+	 * idle and we want to re-enter powersaving.
+	 */
+	if (list_is_last(&rq->link, &ce->timeline->requests) &&
+	    i915_request_completed(rq))
+		intel_engine_add_retire(engine, ce->timeline);
+
 	intel_engine_context_out(engine);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
-	intel_gt_pm_put(engine->gt);
+	intel_gt_pm_put_async(engine->gt);
 
 	/*
 	 * If this is part of a virtual engine, its next request may
@@ -1937,16 +1946,17 @@ skip_submit:
 static void
 cancel_port_requests(struct intel_engine_execlists * const execlists)
 {
-	struct i915_request * const *port, *rq;
+	struct i915_request * const *port;
 
-	for (port = execlists->pending; (rq = *port); port++)
-		execlists_schedule_out(rq);
+	for (port = execlists->pending; *port; port++)
+		execlists_schedule_out(*port);
 	memset(execlists->pending, 0, sizeof(execlists->pending));
 
-	for (port = execlists->active; (rq = *port); port++)
-		execlists_schedule_out(rq);
-	execlists->active =
-		memset(execlists->inflight, 0, sizeof(execlists->inflight));
+	/* Mark the end of active before we overwrite *active */
+	for (port = xchg(&execlists->active, execlists->pending); *port; port++)
+		execlists_schedule_out(*port);
+	WRITE_ONCE(execlists->active,
+		   memset(execlists->inflight, 0, sizeof(execlists->inflight)));
 }
 
 static inline void
@@ -2099,23 +2109,27 @@ static void process_csb(struct intel_engine_cs *engine)
 		else
 			promote = gen8_csb_parse(execlists, buf + 2 * head);
 		if (promote) {
+			struct i915_request * const *old = execlists->active;
+
+			/* Point active to the new ELSP; prevent overwriting */
+			WRITE_ONCE(execlists->active, execlists->pending);
+			set_timeslice(engine);
+
 			if (!inject_preempt_hang(execlists))
 				ring_set_paused(engine, 0);
 
 			/* cancel old inflight, prepare for switch */
-			trace_ports(execlists, "preempted", execlists->active);
-			while (*execlists->active)
-				execlists_schedule_out(*execlists->active++);
+			trace_ports(execlists, "preempted", old);
+			while (*old)
+				execlists_schedule_out(*old++);
 
 			/* switch pending to inflight */
 			GEM_BUG_ON(!assert_pending_valid(execlists, "promote"));
-			execlists->active =
-				memcpy(execlists->inflight,
-				       execlists->pending,
-				       execlists_num_ports(execlists) *
-				       sizeof(*execlists->pending));
-
-			set_timeslice(engine);
+			WRITE_ONCE(execlists->active,
+				   memcpy(execlists->inflight,
+					  execlists->pending,
+					  execlists_num_ports(execlists) *
+					  sizeof(*execlists->pending)));
 
 			WRITE_ONCE(execlists->pending[0], NULL);
 		} else {
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index f03e000051c1..c97423a76642 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -1114,7 +1114,7 @@ int intel_engine_reset(struct intel_engine_cs *engine, const char *msg)
 out:
 	intel_engine_cancel_stop_cs(engine);
 	reset_finish_engine(engine);
-	intel_engine_pm_put(engine);
+	intel_engine_pm_put_async(engine);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c
index ece20504d240..374b28f13ca0 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring.c
@@ -57,9 +57,10 @@ int intel_ring_pin(struct intel_ring *ring)
 
 	i915_vma_make_unshrinkable(vma);
 
-	GEM_BUG_ON(ring->vaddr);
-	ring->vaddr = addr;
+	/* Discard any unused bytes beyond that submitted to hw. */
+	intel_ring_reset(ring, ring->emit);
 
+	ring->vaddr = addr;
 	return 0;
 
 err_ring:
@@ -85,20 +86,14 @@ void intel_ring_unpin(struct intel_ring *ring)
 	if (!atomic_dec_and_test(&ring->pin_count))
 		return;
 
-	/* Discard any unused bytes beyond that submitted to hw. */
-	intel_ring_reset(ring, ring->emit);
-
 	i915_vma_unset_ggtt_write(vma);
 	if (i915_vma_is_map_and_fenceable(vma))
 		i915_vma_unpin_iomap(vma);
 	else
 		i915_gem_object_unpin_map(vma->obj);
 
-	GEM_BUG_ON(!ring->vaddr);
-	ring->vaddr = NULL;
-
-	i915_vma_unpin(vma);
 	i915_vma_make_purgeable(vma);
+	i915_vma_unpin(vma);
 }
 
 static struct i915_vma *create_ring_vma(struct i915_ggtt *ggtt, int size)
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 14ad10acd548..649798c184fb 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -282,6 +282,7 @@ void intel_timeline_fini(struct intel_timeline *timeline)
 {
 	GEM_BUG_ON(atomic_read(&timeline->pin_count));
 	GEM_BUG_ON(!list_empty(&timeline->requests));
+	GEM_BUG_ON(timeline->retire);
 
 	if (timeline->hwsp_cacheline)
 		cacheline_free(timeline->hwsp_cacheline);
@@ -339,15 +340,33 @@ void intel_timeline_enter(struct intel_timeline *tl)
 	struct intel_gt_timelines *timelines = &tl->gt->timelines;
 	unsigned long flags;
 
+	/*
+	 * Pretend we are serialised by the timeline->mutex.
+	 *
+	 * While generally true, there are a few exceptions to the rule
+	 * for the engine->kernel_context being used to manage power
+	 * transitions. As the engine_park may be called from under any
+	 * timeline, it uses the power mutex as a global serialisation
+	 * lock to prevent any other request entering its timeline.
+	 *
+	 * The rule is generally tl->mutex, otherwise engine->wakeref.mutex.
+	 *
+	 * However, intel_gt_retire_request() does not know which engine
+	 * it is retiring along and so cannot partake in the engine-pm
+	 * barrier, and there we use the tl->active_count as a means to
+	 * pin the timeline in the active_list while the locks are dropped.
+	 * Ergo, as that is outside of the engine-pm barrier, we need to
+	 * use atomic to manipulate tl->active_count.
+	 */
 	lockdep_assert_held(&tl->mutex);
-
 	GEM_BUG_ON(!atomic_read(&tl->pin_count));
-	if (tl->active_count++)
+
+	if (atomic_add_unless(&tl->active_count, 1, 0))
 		return;
-	GEM_BUG_ON(!tl->active_count); /* overflow? */
 
 	spin_lock_irqsave(&timelines->lock, flags);
-	list_add(&tl->link, &timelines->active_list);
+	if (!atomic_fetch_inc(&tl->active_count))
+		list_add_tail(&tl->link, &timelines->active_list);
 	spin_unlock_irqrestore(&timelines->lock, flags);
 }
 
@@ -356,14 +375,16 @@ void intel_timeline_exit(struct intel_timeline *tl)
 	struct intel_gt_timelines *timelines = &tl->gt->timelines;
 	unsigned long flags;
 
+	/* See intel_timeline_enter() */
 	lockdep_assert_held(&tl->mutex);
 
-	GEM_BUG_ON(!tl->active_count);
-	if (--tl->active_count)
+	GEM_BUG_ON(!atomic_read(&tl->active_count));
+	if (atomic_add_unless(&tl->active_count, -1, 1))
 		return;
 
 	spin_lock_irqsave(&timelines->lock, flags);
-	list_del(&tl->link);
+	if (atomic_dec_and_test(&tl->active_count))
+		list_del(&tl->link);
 	spin_unlock_irqrestore(&timelines->lock, flags);
 
 	/*
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline_types.h b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
index 98d9ee166379..aaf15cbe1ce1 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
@@ -42,7 +42,7 @@ struct intel_timeline {
 	 * from the intel_context caller plus internal atomicity.
 	 */
 	atomic_t pin_count;
-	unsigned int active_count;
+	atomic_t active_count;
 
 	const u32 *hwsp_seqno;
 	struct i915_vma *hwsp_ggtt;
@@ -66,6 +66,9 @@ struct intel_timeline {
 	 */
 	struct i915_active_fence last_request;
 
+	/** A chain of completed timelines ready for early retirement. */
+	struct intel_timeline *retire;
+
 	/**
 	 * We track the most recent seqno that we wait on in every context so
 	 * that we only have to emit a new await and dependency on a more
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
index 20b9c83f43ad..cbf6b0735272 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
@@ -51,11 +51,12 @@ static int live_engine_pm(void *arg)
 				pr_err("intel_engine_pm_get_if_awake(%s) failed under %s\n",
 				       engine->name, p->name);
 			else
-				intel_engine_pm_put(engine);
-			intel_engine_pm_put(engine);
+				intel_engine_pm_put_async(engine);
+			intel_engine_pm_put_async(engine);
 			p->critical_section_end();
 
-			/* engine wakeref is sync (instant) */
+			intel_engine_pm_flush(engine);
+
 			if (intel_engine_pm_is_awake(engine)) {
 				pr_err("%s is still awake after flushing pm\n",
 				       engine->name);
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index 6a3ac8cde95d..21a176cd8acc 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -1599,9 +1599,9 @@ static int cmd_handler_mi_op_2f(struct parser_exec_state *s)
 	if (!(cmd_val(s, 0) & (1 << 22)))
 		return ret;
 
-	/* check if QWORD */
-	if (DWORD_FIELD(0, 20, 19) == 1)
-		valid_len += 8;
+	/* check inline data */
+	if (cmd_val(s, 0) & BIT(18))
+		valid_len = CMD_LEN(9);
 	ret = gvt_check_valid_cmd_length(cmd_length(s),
 			valid_len);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index bd12af349123..bb9fe6bf5275 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -460,6 +460,7 @@ static int pipeconf_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 static i915_reg_t force_nonpriv_white_list[] = {
 	GEN9_CS_DEBUG_MODE1, //_MMIO(0x20ec)
 	GEN9_CTX_PREEMPT_REG,//_MMIO(0x2248)
+	PS_INVOCATION_COUNT,//_MMIO(0x2348)
 	GEN8_CS_CHICKEN1,//_MMIO(0x2580)
 	_MMIO(0x2690),
 	_MMIO(0x2694),
@@ -508,7 +509,7 @@ static inline bool in_whitelist(unsigned int reg)
 static int force_nonpriv_write(struct intel_vgpu *vgpu,
 	unsigned int offset, void *p_data, unsigned int bytes)
 {
-	u32 reg_nonpriv = *(u32 *)p_data;
+	u32 reg_nonpriv = (*(u32 *)p_data) & REG_GENMASK(25, 2);
 	int ring_id = intel_gvt_render_mmio_to_ring_id(vgpu->gvt, offset);
 	u32 ring_base;
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
@@ -528,7 +529,7 @@ static int force_nonpriv_write(struct intel_vgpu *vgpu,
 			bytes);
 	} else
 		gvt_err("vgpu(%d) Invalid FORCE_NONPRIV write %x at offset %x\n",
-			vgpu->id, reg_nonpriv, offset);
+			vgpu->id, *(u32 *)p_data, offset);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index 3c424cb90702..a19e7d89bc8a 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -672,12 +672,13 @@ void i915_active_acquire_barrier(struct i915_active *ref)
 	 * populated by i915_request_add_active_barriers() to point to the
 	 * request that will eventually release them.
 	 */
-	spin_lock_irqsave_nested(&ref->tree_lock, flags, SINGLE_DEPTH_NESTING);
 	llist_for_each_safe(pos, next, take_preallocated_barriers(ref)) {
 		struct active_node *node = barrier_from_ll(pos);
 		struct intel_engine_cs *engine = barrier_to_engine(node);
 		struct rb_node **p, *parent;
 
+		spin_lock_irqsave_nested(&ref->tree_lock, flags,
+					 SINGLE_DEPTH_NESTING);
 		parent = NULL;
 		p = &ref->tree.rb_node;
 		while (*p) {
@@ -693,12 +694,12 @@ void i915_active_acquire_barrier(struct i915_active *ref)
 		}
 		rb_link_node(&node->node, parent, p);
 		rb_insert_color(&node->node, &ref->tree);
+		spin_unlock_irqrestore(&ref->tree_lock, flags);
 
 		GEM_BUG_ON(!intel_engine_pm_is_awake(engine));
 		llist_add(barrier_to_ll(node), &engine->barrier_tasks);
 		intel_engine_pm_put(engine);
 	}
-	spin_unlock_irqrestore(&ref->tree_lock, flags);
 }
 
 void i915_request_add_active_barriers(struct i915_request *rq)
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 0d40dccd1409..2814218c5ba1 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -190,7 +190,7 @@ static u64 get_rc6(struct intel_gt *gt)
 	val = 0;
 	if (intel_gt_pm_get_if_awake(gt)) {
 		val = __get_rc6(gt);
-		intel_gt_pm_put(gt);
+		intel_gt_pm_put_async(gt);
 	}
 
 	spin_lock_irqsave(&pmu->lock, flags);
@@ -343,7 +343,7 @@ engines_sample(struct intel_gt *gt, unsigned int period_ns)
 
 skip:
 		spin_unlock_irqrestore(&engine->uncore->lock, flags);
-		intel_engine_pm_put(engine);
+		intel_engine_pm_put_async(engine);
 	}
 }
 
@@ -368,7 +368,7 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns)
 		if (intel_gt_pm_get_if_awake(gt)) {
 			val = intel_uncore_read_notrace(uncore, GEN6_RPSTAT1);
 			val = intel_get_cagf(rps, val);
-			intel_gt_pm_put(gt);
+			intel_gt_pm_put_async(gt);
 		}
 
 		add_sample_mult(&pmu->sample[__I915_SAMPLE_FREQ_ACT],
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index c27cfef9281c..ef25ce6e395e 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -103,15 +103,18 @@ query_engine_info(struct drm_i915_private *i915,
 	struct drm_i915_engine_info __user *info_ptr;
 	struct drm_i915_query_engine_info query;
 	struct drm_i915_engine_info info = { };
+	unsigned int num_uabi_engines = 0;
 	struct intel_engine_cs *engine;
 	int len, ret;
 
 	if (query_item->flags)
 		return -EINVAL;
 
+	for_each_uabi_engine(engine, i915)
+		num_uabi_engines++;
+
 	len = sizeof(struct drm_i915_query_engine_info) +
-	      RUNTIME_INFO(i915)->num_engines *
-	      sizeof(struct drm_i915_engine_info);
+	      num_uabi_engines * sizeof(struct drm_i915_engine_info);
 
 	ret = copy_query_item(&query, sizeof(query), len, query_item);
 	if (ret != 0)
diff --git a/drivers/gpu/drm/i915/intel_wakeref.c b/drivers/gpu/drm/i915/intel_wakeref.c
index 868cc78048d0..59aa1b6f1827 100644
--- a/drivers/gpu/drm/i915/intel_wakeref.c
+++ b/drivers/gpu/drm/i915/intel_wakeref.c
@@ -54,7 +54,8 @@ int __intel_wakeref_get_first(struct intel_wakeref *wf)
 
 static void ____intel_wakeref_put_last(struct intel_wakeref *wf)
 {
-	if (!atomic_dec_and_test(&wf->count))
+	INTEL_WAKEREF_BUG_ON(atomic_read(&wf->count) <= 0);
+	if (unlikely(!atomic_dec_and_test(&wf->count)))
 		goto unlock;
 
 	/* ops->put() must reschedule its own release on error/deferral */
@@ -67,13 +68,12 @@ unlock:
 	mutex_unlock(&wf->mutex);
 }
 
-void __intel_wakeref_put_last(struct intel_wakeref *wf)
+void __intel_wakeref_put_last(struct intel_wakeref *wf, unsigned long flags)
 {
 	INTEL_WAKEREF_BUG_ON(work_pending(&wf->work));
 
 	/* Assume we are not in process context and so cannot sleep. */
-	if (wf->ops->flags & INTEL_WAKEREF_PUT_ASYNC ||
-	    !mutex_trylock(&wf->mutex)) {
+	if (flags & INTEL_WAKEREF_PUT_ASYNC || !mutex_trylock(&wf->mutex)) {
 		schedule_work(&wf->work);
 		return;
 	}
@@ -109,8 +109,17 @@ void __intel_wakeref_init(struct intel_wakeref *wf,
 
 int intel_wakeref_wait_for_idle(struct intel_wakeref *wf)
 {
-	return wait_var_event_killable(&wf->wakeref,
-				       !intel_wakeref_is_active(wf));
+	int err;
+
+	might_sleep();
+
+	err = wait_var_event_killable(&wf->wakeref,
+				      !intel_wakeref_is_active(wf));
+	if (err)
+		return err;
+
+	intel_wakeref_unlock_wait(wf);
+	return 0;
 }
 
 static void wakeref_auto_timeout(struct timer_list *t)
diff --git a/drivers/gpu/drm/i915/intel_wakeref.h b/drivers/gpu/drm/i915/intel_wakeref.h
index 5f0c972a80fb..da6e8fd506e6 100644
--- a/drivers/gpu/drm/i915/intel_wakeref.h
+++ b/drivers/gpu/drm/i915/intel_wakeref.h
@@ -9,6 +9,7 @@
 
 #include <linux/atomic.h>
 #include <linux/bits.h>
+#include <linux/lockdep.h>
 #include <linux/mutex.h>
 #include <linux/refcount.h>
 #include <linux/stackdepot.h>
@@ -29,9 +30,6 @@ typedef depot_stack_handle_t intel_wakeref_t;
 struct intel_wakeref_ops {
 	int (*get)(struct intel_wakeref *wf);
 	int (*put)(struct intel_wakeref *wf);
-
-	unsigned long flags;
-#define INTEL_WAKEREF_PUT_ASYNC BIT(0)
 };
 
 struct intel_wakeref {
@@ -57,7 +55,7 @@ void __intel_wakeref_init(struct intel_wakeref *wf,
 } while (0)
 
 int __intel_wakeref_get_first(struct intel_wakeref *wf);
-void __intel_wakeref_put_last(struct intel_wakeref *wf);
+void __intel_wakeref_put_last(struct intel_wakeref *wf, unsigned long flags);
 
 /**
  * intel_wakeref_get: Acquire the wakeref
@@ -100,10 +98,9 @@ intel_wakeref_get_if_active(struct intel_wakeref *wf)
 }
 
 /**
- * intel_wakeref_put: Release the wakeref
- * @i915: the drm_i915_private device
+ * intel_wakeref_put_flags: Release the wakeref
  * @wf: the wakeref
- * @fn: callback for releasing the wakeref, called only on final release.
+ * @flags: control flags
  *
  * Release our hold on the wakeref. When there are no more users,
  * the runtime pm wakeref will be released after the @fn callback is called
@@ -116,11 +113,25 @@ intel_wakeref_get_if_active(struct intel_wakeref *wf)
  * code otherwise.
  */
 static inline void
-intel_wakeref_put(struct intel_wakeref *wf)
+__intel_wakeref_put(struct intel_wakeref *wf, unsigned long flags)
+#define INTEL_WAKEREF_PUT_ASYNC BIT(0)
 {
 	INTEL_WAKEREF_BUG_ON(atomic_read(&wf->count) <= 0);
 	if (unlikely(!atomic_add_unless(&wf->count, -1, 1)))
-		__intel_wakeref_put_last(wf);
+		__intel_wakeref_put_last(wf, flags);
+}
+
+static inline void
+intel_wakeref_put(struct intel_wakeref *wf)
+{
+	might_sleep();
+	__intel_wakeref_put(wf, 0);
+}
+
+static inline void
+intel_wakeref_put_async(struct intel_wakeref *wf)
+{
+	__intel_wakeref_put(wf, INTEL_WAKEREF_PUT_ASYNC);
 }
 
 /**
@@ -152,6 +163,21 @@ intel_wakeref_unlock(struct intel_wakeref *wf)
 }
 
 /**
+ * intel_wakeref_unlock_wait: Wait until the active callback is complete
+ * @wf: the wakeref
+ *
+ * Waits for the active callback (under the @wf->mutex or another CPU) is
+ * complete.
+ */
+static inline void
+intel_wakeref_unlock_wait(struct intel_wakeref *wf)
+{
+	mutex_lock(&wf->mutex);
+	mutex_unlock(&wf->mutex);
+	flush_work(&wf->work);
+}
+
+/**
  * intel_wakeref_is_active: Query whether the wakeref is currently held
  * @wf: the wakeref
  *
@@ -170,6 +196,7 @@ intel_wakeref_is_active(const struct intel_wakeref *wf)
 static inline void
 __intel_wakeref_defer_park(struct intel_wakeref *wf)
 {
+	lockdep_assert_held(&wf->mutex);
 	INTEL_WAKEREF_BUG_ON(atomic_read(&wf->count));
 	atomic_set_release(&wf->count, 1);
 }
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c
index 397f8b0a9af8..d43951caeea0 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.c
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.c
@@ -30,6 +30,8 @@ module_param_named(modeset, mgag200_modeset, int, 0400);
 static struct drm_driver driver;
 
 static const struct pci_device_id pciidlist[] = {
+	{ PCI_VENDOR_ID_MATROX, 0x522, PCI_VENDOR_ID_SUN, 0x4852, 0, 0,
+		G200_SE_A | MGAG200_FLAG_HW_BUG_NO_STARTADD},
 	{ PCI_VENDOR_ID_MATROX, 0x522, PCI_ANY_ID, PCI_ANY_ID, 0, 0, G200_SE_A },
 	{ PCI_VENDOR_ID_MATROX, 0x524, PCI_ANY_ID, PCI_ANY_ID, 0, 0, G200_SE_B },
 	{ PCI_VENDOR_ID_MATROX, 0x530, PCI_ANY_ID, PCI_ANY_ID, 0, 0, G200_EV },
@@ -60,6 +62,35 @@ static void mga_pci_remove(struct pci_dev *pdev)
 
 DEFINE_DRM_GEM_FOPS(mgag200_driver_fops);
 
+static bool mgag200_pin_bo_at_0(const struct mga_device *mdev)
+{
+	return mdev->flags & MGAG200_FLAG_HW_BUG_NO_STARTADD;
+}
+
+int mgag200_driver_dumb_create(struct drm_file *file,
+			       struct drm_device *dev,
+			       struct drm_mode_create_dumb *args)
+{
+	struct mga_device *mdev = dev->dev_private;
+	unsigned long pg_align;
+
+	if (WARN_ONCE(!dev->vram_mm, "VRAM MM not initialized"))
+		return -EINVAL;
+
+	pg_align = 0ul;
+
+	/*
+	 * Aligning scanout buffers to the size of the video ram forces
+	 * placement at offset 0. Works around a bug where HW does not
+	 * respect 'startadd' field.
+	 */
+	if (mgag200_pin_bo_at_0(mdev))
+		pg_align = PFN_UP(mdev->mc.vram_size);
+
+	return drm_gem_vram_fill_create_dumb(file, dev, &dev->vram_mm->bdev,
+					     pg_align, false, args);
+}
+
 static struct drm_driver driver = {
 	.driver_features = DRIVER_GEM | DRIVER_MODESET,
 	.load = mgag200_driver_load,
@@ -71,7 +102,10 @@ static struct drm_driver driver = {
 	.major = DRIVER_MAJOR,
 	.minor = DRIVER_MINOR,
 	.patchlevel = DRIVER_PATCHLEVEL,
-	DRM_GEM_VRAM_DRIVER
+	.debugfs_init = drm_vram_mm_debugfs_init,
+	.dumb_create = mgag200_driver_dumb_create,
+	.dumb_map_offset = drm_gem_vram_driver_dumb_mmap_offset,
+	.gem_prime_mmap = drm_gem_prime_mmap,
 };
 
 static struct pci_driver mgag200_pci_driver = {
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h
index 0ea9a525e57d..aa32aad222c2 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.h
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.h
@@ -150,6 +150,12 @@ enum mga_type {
 	G200_EW3,
 };
 
+/* HW does not handle 'startadd' field correct. */
+#define MGAG200_FLAG_HW_BUG_NO_STARTADD	(1ul << 8)
+
+#define MGAG200_TYPE_MASK	(0x000000ff)
+#define MGAG200_FLAG_MASK	(0x00ffff00)
+
 #define IS_G200_SE(mdev) (mdev->type == G200_SE_A || mdev->type == G200_SE_B)
 
 struct mga_device {
@@ -181,6 +187,18 @@ struct mga_device {
 	u32 unique_rev_id;
 };
 
+static inline enum mga_type
+mgag200_type_from_driver_data(kernel_ulong_t driver_data)
+{
+	return (enum mga_type)(driver_data & MGAG200_TYPE_MASK);
+}
+
+static inline unsigned long
+mgag200_flags_from_driver_data(kernel_ulong_t driver_data)
+{
+	return driver_data & MGAG200_FLAG_MASK;
+}
+
 				/* mgag200_mode.c */
 int mgag200_modeset_init(struct mga_device *mdev);
 void mgag200_modeset_fini(struct mga_device *mdev);
diff --git a/drivers/gpu/drm/mgag200/mgag200_main.c b/drivers/gpu/drm/mgag200/mgag200_main.c
index 5f74aabcd3df..e1bc5b0aa774 100644
--- a/drivers/gpu/drm/mgag200/mgag200_main.c
+++ b/drivers/gpu/drm/mgag200/mgag200_main.c
@@ -94,7 +94,8 @@ static int mgag200_device_init(struct drm_device *dev,
 	struct mga_device *mdev = dev->dev_private;
 	int ret, option;
 
-	mdev->type = flags;
+	mdev->flags = mgag200_flags_from_driver_data(flags);
+	mdev->type = mgag200_type_from_driver_data(flags);
 
 	/* Hardcode the number of CRTCs to 1 */
 	mdev->num_crtc = 1;
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index e9160ce39cbb..6deaa7d01654 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -7,6 +7,7 @@ config DRM_MSM
 	depends on OF && COMMON_CLK
 	depends on MMU
 	depends on INTERCONNECT || !INTERCONNECT
+	depends on QCOM_OCMEM || QCOM_OCMEM=n
 	select QCOM_MDT_LOADER if ARCH_QCOM
 	select REGULATOR
 	select DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 5f7e98028eaf..7ad14937fcdf 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -6,10 +6,6 @@
  * Copyright (c) 2014 The Linux Foundation. All rights reserved.
  */
 
-#ifdef CONFIG_MSM_OCMEM
-#  include <mach/ocmem.h>
-#endif
-
 #include "a3xx_gpu.h"
 
 #define A3XX_INT0_MASK \
@@ -195,9 +191,9 @@ static int a3xx_hw_init(struct msm_gpu *gpu)
 		gpu_write(gpu, REG_A3XX_RBBM_GPR0_CTL, 0x00000000);
 
 	/* Set the OCMEM base address for A330, etc */
-	if (a3xx_gpu->ocmem_hdl) {
+	if (a3xx_gpu->ocmem.hdl) {
 		gpu_write(gpu, REG_A3XX_RB_GMEM_BASE_ADDR,
-			(unsigned int)(a3xx_gpu->ocmem_base >> 14));
+			(unsigned int)(a3xx_gpu->ocmem.base >> 14));
 	}
 
 	/* Turn on performance counters: */
@@ -318,10 +314,7 @@ static void a3xx_destroy(struct msm_gpu *gpu)
 
 	adreno_gpu_cleanup(adreno_gpu);
 
-#ifdef CONFIG_MSM_OCMEM
-	if (a3xx_gpu->ocmem_base)
-		ocmem_free(OCMEM_GRAPHICS, a3xx_gpu->ocmem_hdl);
-#endif
+	adreno_gpu_ocmem_cleanup(&a3xx_gpu->ocmem);
 
 	kfree(a3xx_gpu);
 }
@@ -494,17 +487,10 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 
 	/* if needed, allocate gmem: */
 	if (adreno_is_a330(adreno_gpu)) {
-#ifdef CONFIG_MSM_OCMEM
-		/* TODO this is different/missing upstream: */
-		struct ocmem_buf *ocmem_hdl =
-				ocmem_allocate(OCMEM_GRAPHICS, adreno_gpu->gmem);
-
-		a3xx_gpu->ocmem_hdl = ocmem_hdl;
-		a3xx_gpu->ocmem_base = ocmem_hdl->addr;
-		adreno_gpu->gmem = ocmem_hdl->len;
-		DBG("using %dK of OCMEM at 0x%08x", adreno_gpu->gmem / 1024,
-				a3xx_gpu->ocmem_base);
-#endif
+		ret = adreno_gpu_ocmem_init(&adreno_gpu->base.pdev->dev,
+					    adreno_gpu, &a3xx_gpu->ocmem);
+		if (ret)
+			goto fail;
 	}
 
 	if (!gpu->aspace) {
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.h b/drivers/gpu/drm/msm/adreno/a3xx_gpu.h
index 5dc33e5ea53b..c555fb13e0d7 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.h
@@ -19,8 +19,7 @@ struct a3xx_gpu {
 	struct adreno_gpu base;
 
 	/* if OCMEM is used for GMEM: */
-	uint32_t ocmem_base;
-	void *ocmem_hdl;
+	struct adreno_ocmem ocmem;
 };
 #define to_a3xx_gpu(x) container_of(x, struct a3xx_gpu, base)
 
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index ab2b752566d8..b01388a9e89e 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -2,9 +2,6 @@
 /* Copyright (c) 2014 The Linux Foundation. All rights reserved.
  */
 #include "a4xx_gpu.h"
-#ifdef CONFIG_MSM_OCMEM
-#  include <soc/qcom/ocmem.h>
-#endif
 
 #define A4XX_INT0_MASK \
 	(A4XX_INT0_RBBM_AHB_ERROR |        \
@@ -188,7 +185,7 @@ static int a4xx_hw_init(struct msm_gpu *gpu)
 			(1 << 30) | 0xFFFF);
 
 	gpu_write(gpu, REG_A4XX_RB_GMEM_BASE_ADDR,
-			(unsigned int)(a4xx_gpu->ocmem_base >> 14));
+			(unsigned int)(a4xx_gpu->ocmem.base >> 14));
 
 	/* Turn on performance counters: */
 	gpu_write(gpu, REG_A4XX_RBBM_PERFCTR_CTL, 0x01);
@@ -318,10 +315,7 @@ static void a4xx_destroy(struct msm_gpu *gpu)
 
 	adreno_gpu_cleanup(adreno_gpu);
 
-#ifdef CONFIG_MSM_OCMEM
-	if (a4xx_gpu->ocmem_base)
-		ocmem_free(OCMEM_GRAPHICS, a4xx_gpu->ocmem_hdl);
-#endif
+	adreno_gpu_ocmem_cleanup(&a4xx_gpu->ocmem);
 
 	kfree(a4xx_gpu);
 }
@@ -578,17 +572,10 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev)
 
 	/* if needed, allocate gmem: */
 	if (adreno_is_a4xx(adreno_gpu)) {
-#ifdef CONFIG_MSM_OCMEM
-		/* TODO this is different/missing upstream: */
-		struct ocmem_buf *ocmem_hdl =
-				ocmem_allocate(OCMEM_GRAPHICS, adreno_gpu->gmem);
-
-		a4xx_gpu->ocmem_hdl = ocmem_hdl;
-		a4xx_gpu->ocmem_base = ocmem_hdl->addr;
-		adreno_gpu->gmem = ocmem_hdl->len;
-		DBG("using %dK of OCMEM at 0x%08x", adreno_gpu->gmem / 1024,
-				a4xx_gpu->ocmem_base);
-#endif
+		ret = adreno_gpu_ocmem_init(dev->dev, adreno_gpu,
+					    &a4xx_gpu->ocmem);
+		if (ret)
+			goto fail;
 	}
 
 	if (!gpu->aspace) {
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.h b/drivers/gpu/drm/msm/adreno/a4xx_gpu.h
index d506311ee240..a01448cba2ea 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.h
@@ -16,8 +16,7 @@ struct a4xx_gpu {
 	struct adreno_gpu base;
 
 	/* if OCMEM is used for GMEM: */
-	uint32_t ocmem_base;
-	void *ocmem_hdl;
+	struct adreno_ocmem ocmem;
 };
 #define to_a4xx_gpu(x) container_of(x, struct a4xx_gpu, base)
 
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index e9c55d1d6c04..b02e2042547f 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -353,6 +353,9 @@ static int a5xx_me_init(struct msm_gpu *gpu)
 		 * 2D mode 3 draw
 		 */
 		OUT_RING(ring, 0x0000000B);
+	} else if (adreno_is_a510(adreno_gpu)) {
+		/* Workaround for token and syncs */
+		OUT_RING(ring, 0x00000001);
 	} else {
 		/* No workarounds enabled */
 		OUT_RING(ring, 0x00000000);
@@ -568,15 +571,24 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 		0x00100000 + adreno_gpu->gmem - 1);
 	gpu_write(gpu, REG_A5XX_UCHE_GMEM_RANGE_MAX_HI, 0x00000000);
 
-	gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x40);
-	if (adreno_is_a530(adreno_gpu))
-		gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x40);
-	if (adreno_is_a540(adreno_gpu))
-		gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x400);
-	gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x80000060);
-	gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x40201B16);
-
-	gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, (0x400 << 11 | 0x300 << 22));
+	if (adreno_is_a510(adreno_gpu)) {
+		gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x20);
+		gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x20);
+		gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x40000030);
+		gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x20100D0A);
+		gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL,
+			  (0x200 << 11 | 0x200 << 22));
+	} else {
+		gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x40);
+		if (adreno_is_a530(adreno_gpu))
+			gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x40);
+		if (adreno_is_a540(adreno_gpu))
+			gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x400);
+		gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x80000060);
+		gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x40201B16);
+		gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL,
+			  (0x400 << 11 | 0x300 << 22));
+	}
 
 	if (adreno_gpu->info->quirks & ADRENO_QUIRK_TWO_PASS_USE_WFI)
 		gpu_rmw(gpu, REG_A5XX_PC_DBG_ECO_CNTL, 0, (1 << 8));
@@ -589,6 +601,19 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	/* Enable ME/PFP split notification */
 	gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL1, 0xA6FFFFFF);
 
+	/*
+	 *  In A5x, CCU can send context_done event of a particular context to
+	 *  UCHE which ultimately reaches CP even when there is valid
+	 *  transaction of that context inside CCU. This can let CP to program
+	 *  config registers, which will make the "valid transaction" inside
+	 *  CCU to be interpreted differently. This can cause gpu fault. This
+	 *  bug is fixed in latest A510 revision. To enable this bug fix -
+	 *  bit[11] of RB_DBG_ECO_CNTL need to be set to 0, default is 1
+	 *  (disable). For older A510 version this bit is unused.
+	 */
+	if (adreno_is_a510(adreno_gpu))
+		gpu_rmw(gpu, REG_A5XX_RB_DBG_ECO_CNTL, (1 << 11), 0);
+
 	/* Enable HWCG */
 	a5xx_set_hwcg(gpu, true);
 
@@ -635,7 +660,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	/* UCHE */
 	gpu_write(gpu, REG_A5XX_CP_PROTECT(16), ADRENO_PROTECT_RW(0xE80, 16));
 
-	if (adreno_is_a530(adreno_gpu))
+	if (adreno_is_a530(adreno_gpu) || adreno_is_a510(adreno_gpu))
 		gpu_write(gpu, REG_A5XX_CP_PROTECT(17),
 			ADRENO_PROTECT_RW(0x10000, 0x8000));
 
@@ -679,7 +704,8 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 
 	a5xx_preempt_hw_init(gpu);
 
-	a5xx_gpmu_ucode_init(gpu);
+	if (!adreno_is_a510(adreno_gpu))
+		a5xx_gpmu_ucode_init(gpu);
 
 	ret = a5xx_ucode_init(gpu);
 	if (ret)
@@ -712,7 +738,8 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	}
 
 	/*
-	 * Try to load a zap shader into the secure world. If successful
+	 * If the chip that we are using does support loading one, then
+	 * try to load a zap shader into the secure world. If successful
 	 * we can use the CP to switch out of secure mode. If not then we
 	 * have no resource but to try to switch ourselves out manually. If we
 	 * guessed wrong then access to the RBBM_SECVID_TRUST_CNTL register will
@@ -1066,6 +1093,7 @@ static void a5xx_dump(struct msm_gpu *gpu)
 
 static int a5xx_pm_resume(struct msm_gpu *gpu)
 {
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	int ret;
 
 	/* Turn on the core power */
@@ -1073,6 +1101,15 @@ static int a5xx_pm_resume(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
+	if (adreno_is_a510(adreno_gpu)) {
+		/* Halt the sp_input_clk at HM level */
+		gpu_write(gpu, REG_A5XX_RBBM_CLOCK_CNTL, 0x00000055);
+		a5xx_set_hwcg(gpu, true);
+		/* Turn on sp_input_clk at HM level */
+		gpu_rmw(gpu, REG_A5XX_RBBM_CLOCK_CNTL, 0xff, 0);
+		return 0;
+	}
+
 	/* Turn the RBCCU domain first to limit the chances of voltage droop */
 	gpu_write(gpu, REG_A5XX_GPMU_RBCCU_POWER_CNTL, 0x778000);
 
@@ -1101,9 +1138,17 @@ static int a5xx_pm_resume(struct msm_gpu *gpu)
 
 static int a5xx_pm_suspend(struct msm_gpu *gpu)
 {
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	u32 mask = 0xf;
+
+	/* A510 has 3 XIN ports in VBIF */
+	if (adreno_is_a510(adreno_gpu))
+		mask = 0x7;
+
 	/* Clear the VBIF pipe before shutting down */
-	gpu_write(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL0, 0xF);
-	spin_until((gpu_read(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL1) & 0xF) == 0xF);
+	gpu_write(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL0, mask);
+	spin_until((gpu_read(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL1) &
+				mask) == mask);
 
 	gpu_write(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL0, 0);
 
@@ -1289,7 +1334,7 @@ static void a5xx_gpu_state_destroy(struct kref *kref)
 	kfree(a5xx_state);
 }
 
-int a5xx_gpu_state_put(struct msm_gpu_state *state)
+static int a5xx_gpu_state_put(struct msm_gpu_state *state)
 {
 	if (IS_ERR_OR_NULL(state))
 		return 1;
@@ -1299,8 +1344,8 @@ int a5xx_gpu_state_put(struct msm_gpu_state *state)
 
 
 #if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
-void a5xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
-		struct drm_printer *p)
+static void a5xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		      struct drm_printer *p)
 {
 	int i, j;
 	u32 pos = 0;
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c
index a3a06db675ba..321a8061fd32 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_power.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c
@@ -297,6 +297,10 @@ int a5xx_power_init(struct msm_gpu *gpu)
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	int ret;
 
+	/* Not all A5xx chips have a GPMU */
+	if (adreno_is_a510(adreno_gpu))
+		return 0;
+
 	/* Set up the limits management */
 	if (adreno_is_a530(adreno_gpu))
 		a530_lm_setup(gpu);
@@ -326,6 +330,9 @@ void a5xx_gpmu_ucode_init(struct msm_gpu *gpu)
 	unsigned int *data, *ptr, *cmds;
 	unsigned int cmds_size;
 
+	if (adreno_is_a510(adreno_gpu))
+		return;
+
 	if (a5xx_gpu->gpmu_bo)
 		return;
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 0888e0df660d..fbbdf86504f5 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -115,6 +115,21 @@ static const struct adreno_info gpulist[] = {
 		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a4xx_gpu_init,
 	}, {
+		.rev   = ADRENO_REV(5, 1, 0, ANY_ID),
+		.revn = 510,
+		.name = "A510",
+		.fw = {
+			[ADRENO_FW_PM4] = "a530_pm4.fw",
+			[ADRENO_FW_PFP] = "a530_pfp.fw",
+		},
+		.gmem = SZ_256K,
+		/*
+		 * Increase inactive period to 250 to avoid bouncing
+		 * the GDSC which appears to make it grumpy
+		 */
+		.inactive_period = 250,
+		.init = a5xx_gpu_init,
+	}, {
 		.rev = ADRENO_REV(5, 3, 0, 2),
 		.revn = 530,
 		.name = "A530",
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 048c8be426f3..0783e4b5486a 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -14,6 +14,7 @@
 #include <linux/pm_opp.h>
 #include <linux/slab.h>
 #include <linux/soc/qcom/mdt_loader.h>
+#include <soc/qcom/ocmem.h>
 #include "adreno_gpu.h"
 #include "msm_gem.h"
 #include "msm_mmu.h"
@@ -893,6 +894,45 @@ static int adreno_get_pwrlevels(struct device *dev,
 	return 0;
 }
 
+int adreno_gpu_ocmem_init(struct device *dev, struct adreno_gpu *adreno_gpu,
+			  struct adreno_ocmem *adreno_ocmem)
+{
+	struct ocmem_buf *ocmem_hdl;
+	struct ocmem *ocmem;
+
+	ocmem = of_get_ocmem(dev);
+	if (IS_ERR(ocmem)) {
+		if (PTR_ERR(ocmem) == -ENODEV) {
+			/*
+			 * Return success since either the ocmem property was
+			 * not specified in device tree, or ocmem support is
+			 * not compiled into the kernel.
+			 */
+			return 0;
+		}
+
+		return PTR_ERR(ocmem);
+	}
+
+	ocmem_hdl = ocmem_allocate(ocmem, OCMEM_GRAPHICS, adreno_gpu->gmem);
+	if (IS_ERR(ocmem_hdl))
+		return PTR_ERR(ocmem_hdl);
+
+	adreno_ocmem->ocmem = ocmem;
+	adreno_ocmem->base = ocmem_hdl->addr;
+	adreno_ocmem->hdl = ocmem_hdl;
+	adreno_gpu->gmem = ocmem_hdl->len;
+
+	return 0;
+}
+
+void adreno_gpu_ocmem_cleanup(struct adreno_ocmem *adreno_ocmem)
+{
+	if (adreno_ocmem && adreno_ocmem->base)
+		ocmem_free(adreno_ocmem->ocmem, OCMEM_GRAPHICS,
+			   adreno_ocmem->hdl);
+}
+
 int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		struct adreno_gpu *adreno_gpu,
 		const struct adreno_gpu_funcs *funcs, int nr_rings)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index c7441fb8313e..e71a7570ef72 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -126,6 +126,12 @@ struct adreno_gpu {
 };
 #define to_adreno_gpu(x) container_of(x, struct adreno_gpu, base)
 
+struct adreno_ocmem {
+	struct ocmem *ocmem;
+	unsigned long base;
+	void *hdl;
+};
+
 /* platform config data (ie. from DT, or pdata) */
 struct adreno_platform_config {
 	struct adreno_rev rev;
@@ -206,6 +212,11 @@ static inline int adreno_is_a430(struct adreno_gpu *gpu)
        return gpu->revn == 430;
 }
 
+static inline int adreno_is_a510(struct adreno_gpu *gpu)
+{
+	return gpu->revn == 510;
+}
+
 static inline int adreno_is_a530(struct adreno_gpu *gpu)
 {
 	return gpu->revn == 530;
@@ -236,6 +247,10 @@ void adreno_dump(struct msm_gpu *gpu);
 void adreno_wait_ring(struct msm_ringbuffer *ring, uint32_t ndwords);
 struct msm_ringbuffer *adreno_active_ring(struct msm_gpu *gpu);
 
+int adreno_gpu_ocmem_init(struct device *dev, struct adreno_gpu *adreno_gpu,
+			  struct adreno_ocmem *ocmem);
+void adreno_gpu_ocmem_cleanup(struct adreno_ocmem *ocmem);
+
 int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		struct adreno_gpu *gpu, const struct adreno_gpu_funcs *funcs,
 		int nr_rings);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
index cdbea38b8697..f1bc6a1af7a7 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
@@ -55,8 +55,7 @@ static void dpu_core_irq_callback_handler(void *arg, int irq_idx)
 int dpu_core_irq_idx_lookup(struct dpu_kms *dpu_kms,
 		enum dpu_intr_type intr_type, u32 instance_idx)
 {
-	if (!dpu_kms || !dpu_kms->hw_intr ||
-			!dpu_kms->hw_intr->ops.irq_idx_lookup)
+	if (!dpu_kms->hw_intr || !dpu_kms->hw_intr->ops.irq_idx_lookup)
 		return -EINVAL;
 
 	return dpu_kms->hw_intr->ops.irq_idx_lookup(intr_type,
@@ -73,7 +72,7 @@ static int _dpu_core_irq_enable(struct dpu_kms *dpu_kms, int irq_idx)
 	unsigned long irq_flags;
 	int ret = 0, enable_count;
 
-	if (!dpu_kms || !dpu_kms->hw_intr ||
+	if (!dpu_kms->hw_intr ||
 			!dpu_kms->irq_obj.enable_counts ||
 			!dpu_kms->irq_obj.irq_counts) {
 		DPU_ERROR("invalid params\n");
@@ -114,7 +113,7 @@ int dpu_core_irq_enable(struct dpu_kms *dpu_kms, int *irq_idxs, u32 irq_count)
 {
 	int i, ret = 0, counts;
 
-	if (!dpu_kms || !irq_idxs || !irq_count) {
+	if (!irq_idxs || !irq_count) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -138,7 +137,7 @@ static int _dpu_core_irq_disable(struct dpu_kms *dpu_kms, int irq_idx)
 {
 	int ret = 0, enable_count;
 
-	if (!dpu_kms || !dpu_kms->hw_intr || !dpu_kms->irq_obj.enable_counts) {
+	if (!dpu_kms->hw_intr || !dpu_kms->irq_obj.enable_counts) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -169,7 +168,7 @@ int dpu_core_irq_disable(struct dpu_kms *dpu_kms, int *irq_idxs, u32 irq_count)
 {
 	int i, ret = 0, counts;
 
-	if (!dpu_kms || !irq_idxs || !irq_count) {
+	if (!irq_idxs || !irq_count) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -186,7 +185,7 @@ int dpu_core_irq_disable(struct dpu_kms *dpu_kms, int *irq_idxs, u32 irq_count)
 
 u32 dpu_core_irq_read(struct dpu_kms *dpu_kms, int irq_idx, bool clear)
 {
-	if (!dpu_kms || !dpu_kms->hw_intr ||
+	if (!dpu_kms->hw_intr ||
 			!dpu_kms->hw_intr->ops.get_interrupt_status)
 		return 0;
 
@@ -205,7 +204,7 @@ int dpu_core_irq_register_callback(struct dpu_kms *dpu_kms, int irq_idx,
 {
 	unsigned long irq_flags;
 
-	if (!dpu_kms || !dpu_kms->irq_obj.irq_cb_tbl) {
+	if (!dpu_kms->irq_obj.irq_cb_tbl) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -240,7 +239,7 @@ int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx,
 {
 	unsigned long irq_flags;
 
-	if (!dpu_kms || !dpu_kms->irq_obj.irq_cb_tbl) {
+	if (!dpu_kms->irq_obj.irq_cb_tbl) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -274,8 +273,7 @@ int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx,
 
 static void dpu_clear_all_irqs(struct dpu_kms *dpu_kms)
 {
-	if (!dpu_kms || !dpu_kms->hw_intr ||
-			!dpu_kms->hw_intr->ops.clear_all_irqs)
+	if (!dpu_kms->hw_intr || !dpu_kms->hw_intr->ops.clear_all_irqs)
 		return;
 
 	dpu_kms->hw_intr->ops.clear_all_irqs(dpu_kms->hw_intr);
@@ -283,8 +281,7 @@ static void dpu_clear_all_irqs(struct dpu_kms *dpu_kms)
 
 static void dpu_disable_all_irqs(struct dpu_kms *dpu_kms)
 {
-	if (!dpu_kms || !dpu_kms->hw_intr ||
-			!dpu_kms->hw_intr->ops.disable_all_irqs)
+	if (!dpu_kms->hw_intr || !dpu_kms->hw_intr->ops.disable_all_irqs)
 		return;
 
 	dpu_kms->hw_intr->ops.disable_all_irqs(dpu_kms->hw_intr);
@@ -343,18 +340,8 @@ void dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
 
 void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms)
 {
-	struct msm_drm_private *priv;
 	int i;
 
-	if (!dpu_kms->dev) {
-		DPU_ERROR("invalid drm device\n");
-		return;
-	} else if (!dpu_kms->dev->dev_private) {
-		DPU_ERROR("invalid device private\n");
-		return;
-	}
-	priv = dpu_kms->dev->dev_private;
-
 	pm_runtime_get_sync(&dpu_kms->pdev->dev);
 	dpu_clear_all_irqs(dpu_kms);
 	dpu_disable_all_irqs(dpu_kms);
@@ -379,18 +366,8 @@ void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms)
 
 void dpu_core_irq_uninstall(struct dpu_kms *dpu_kms)
 {
-	struct msm_drm_private *priv;
 	int i;
 
-	if (!dpu_kms->dev) {
-		DPU_ERROR("invalid drm device\n");
-		return;
-	} else if (!dpu_kms->dev->dev_private) {
-		DPU_ERROR("invalid device private\n");
-		return;
-	}
-	priv = dpu_kms->dev->dev_private;
-
 	pm_runtime_get_sync(&dpu_kms->pdev->dev);
 	for (i = 0; i < dpu_kms->irq_obj.total_irqs; i++)
 		if (atomic_read(&dpu_kms->irq_obj.enable_counts[i]) ||
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index 09a49b59bb5b..11f2bebe3869 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -32,18 +32,7 @@ enum dpu_perf_mode {
 static struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc)
 {
 	struct msm_drm_private *priv;
-
-	if (!crtc->dev || !crtc->dev->dev_private) {
-		DPU_ERROR("invalid device\n");
-		return NULL;
-	}
-
 	priv = crtc->dev->dev_private;
-	if (!priv || !priv->kms) {
-		DPU_ERROR("invalid kms\n");
-		return NULL;
-	}
-
 	return to_dpu_kms(priv->kms);
 }
 
@@ -116,7 +105,7 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
 	}
 
 	kms = _dpu_crtc_get_kms(crtc);
-	if (!kms || !kms->catalog) {
+	if (!kms->catalog) {
 		DPU_ERROR("invalid parameters\n");
 		return 0;
 	}
@@ -215,7 +204,6 @@ static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms,
 void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc)
 {
 	struct dpu_crtc *dpu_crtc;
-	struct dpu_crtc_state *dpu_cstate;
 	struct dpu_kms *kms;
 
 	if (!crtc) {
@@ -224,13 +212,12 @@ void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc)
 	}
 
 	kms = _dpu_crtc_get_kms(crtc);
-	if (!kms || !kms->catalog) {
+	if (!kms->catalog) {
 		DPU_ERROR("invalid kms\n");
 		return;
 	}
 
 	dpu_crtc = to_dpu_crtc(crtc);
-	dpu_cstate = to_dpu_crtc_state(crtc->state);
 
 	if (atomic_dec_return(&kms->bandwidth_ref) > 0)
 		return;
@@ -287,7 +274,6 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
 	u64 clk_rate = 0;
 	struct dpu_crtc *dpu_crtc;
 	struct dpu_crtc_state *dpu_cstate;
-	struct msm_drm_private *priv;
 	struct dpu_kms *kms;
 	int ret;
 
@@ -297,11 +283,10 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
 	}
 
 	kms = _dpu_crtc_get_kms(crtc);
-	if (!kms || !kms->catalog) {
+	if (!kms->catalog) {
 		DPU_ERROR("invalid kms\n");
 		return -EINVAL;
 	}
-	priv = kms->dev->dev_private;
 
 	dpu_crtc = to_dpu_crtc(crtc);
 	dpu_cstate = to_dpu_crtc_state(crtc->state);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index ce59adff06aa..f197dce54576 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -266,11 +266,20 @@ enum dpu_intf_mode dpu_crtc_get_intf_mode(struct drm_crtc *crtc)
 {
 	struct drm_encoder *encoder;
 
-	if (!crtc || !crtc->dev) {
+	if (!crtc) {
 		DPU_ERROR("invalid crtc\n");
 		return INTF_MODE_NONE;
 	}
 
+	/*
+	 * TODO: This function is called from dpu debugfs and as part of atomic
+	 * check. When called from debugfs, the crtc->mutex must be held to
+	 * read crtc->state. However reading crtc->state from atomic check isn't
+	 * allowed (unless you have a good reason, a big comment, and a deep
+	 * understanding of how the atomic/modeset locks work (<- and this is
+	 * probably not possible)). So we'll keep the WARN_ON here for now, but
+	 * really we need to figure out a better way to track our operating mode
+	 */
 	WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
 
 	/* TODO: Returns the first INTF_MODE, could there be multiple values? */
@@ -694,7 +703,7 @@ static void dpu_crtc_disable(struct drm_crtc *crtc,
 	unsigned long flags;
 	bool release_bandwidth = false;
 
-	if (!crtc || !crtc->dev || !crtc->dev->dev_private || !crtc->state) {
+	if (!crtc || !crtc->state) {
 		DPU_ERROR("invalid crtc\n");
 		return;
 	}
@@ -766,7 +775,7 @@ static void dpu_crtc_enable(struct drm_crtc *crtc,
 	struct msm_drm_private *priv;
 	bool request_bandwidth;
 
-	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+	if (!crtc) {
 		DPU_ERROR("invalid crtc\n");
 		return;
 	}
@@ -1288,13 +1297,8 @@ struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane,
 {
 	struct drm_crtc *crtc = NULL;
 	struct dpu_crtc *dpu_crtc = NULL;
-	struct msm_drm_private *priv = NULL;
-	struct dpu_kms *kms = NULL;
 	int i;
 
-	priv = dev->dev_private;
-	kms = to_dpu_kms(priv->kms);
-
 	dpu_crtc = kzalloc(sizeof(*dpu_crtc), GFP_KERNEL);
 	if (!dpu_crtc)
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index d82ea994063f..f96e142c4361 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -645,11 +645,6 @@ static void _dpu_encoder_update_vsync_source(struct dpu_encoder_virt *dpu_enc,
 	priv = drm_enc->dev->dev_private;
 
 	dpu_kms = to_dpu_kms(priv->kms);
-	if (!dpu_kms) {
-		DPU_ERROR("invalid dpu_kms\n");
-		return;
-	}
-
 	hw_mdptop = dpu_kms->hw_mdp;
 	if (!hw_mdptop) {
 		DPU_ERROR("invalid mdptop\n");
@@ -735,8 +730,7 @@ static int dpu_encoder_resource_control(struct drm_encoder *drm_enc,
 	struct msm_drm_private *priv;
 	bool is_vid_mode = false;
 
-	if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private ||
-			!drm_enc->crtc) {
+	if (!drm_enc || !drm_enc->dev || !drm_enc->crtc) {
 		DPU_ERROR("invalid parameters\n");
 		return -EINVAL;
 	}
@@ -1092,17 +1086,13 @@ static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc)
 	struct msm_drm_private *priv;
 	struct dpu_kms *dpu_kms;
 
-	if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private) {
+	if (!drm_enc || !drm_enc->dev) {
 		DPU_ERROR("invalid parameters\n");
 		return;
 	}
 
 	priv = drm_enc->dev->dev_private;
 	dpu_kms = to_dpu_kms(priv->kms);
-	if (!dpu_kms) {
-		DPU_ERROR("invalid dpu_kms\n");
-		return;
-	}
 
 	dpu_enc = to_dpu_encoder_virt(drm_enc);
 	if (!dpu_enc || !dpu_enc->cur_master) {
@@ -1184,7 +1174,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 	struct dpu_encoder_virt *dpu_enc = NULL;
 	struct msm_drm_private *priv;
 	struct dpu_kms *dpu_kms;
-	struct drm_display_mode *mode;
 	int i = 0;
 
 	if (!drm_enc) {
@@ -1193,9 +1182,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 	} else if (!drm_enc->dev) {
 		DPU_ERROR("invalid dev\n");
 		return;
-	} else if (!drm_enc->dev->dev_private) {
-		DPU_ERROR("invalid dev_private\n");
-		return;
 	}
 
 	dpu_enc = to_dpu_encoder_virt(drm_enc);
@@ -1204,8 +1190,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 	mutex_lock(&dpu_enc->enc_lock);
 	dpu_enc->enabled = false;
 
-	mode = &drm_enc->crtc->state->adjusted_mode;
-
 	priv = drm_enc->dev->dev_private;
 	dpu_kms = to_dpu_kms(priv->kms);
 
@@ -1734,8 +1718,7 @@ static void dpu_encoder_vsync_event_handler(struct timer_list *t)
 	struct msm_drm_private *priv;
 	struct msm_drm_thread *event_thread;
 
-	if (!drm_enc->dev || !drm_enc->dev->dev_private ||
-			!drm_enc->crtc) {
+	if (!drm_enc->dev || !drm_enc->crtc) {
 		DPU_ERROR("invalid parameters\n");
 		return;
 	}
@@ -1914,8 +1897,6 @@ static int _dpu_encoder_debugfs_status_open(struct inode *inode,
 static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
 {
 	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
-	struct msm_drm_private *priv;
-	struct dpu_kms *dpu_kms;
 	int i;
 
 	static const struct file_operations debugfs_status_fops = {
@@ -1927,14 +1908,11 @@ static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
 
 	char name[DPU_NAME_SIZE];
 
-	if (!drm_enc->dev || !drm_enc->dev->dev_private) {
+	if (!drm_enc->dev) {
 		DPU_ERROR("invalid encoder or kms\n");
 		return -EINVAL;
 	}
 
-	priv = drm_enc->dev->dev_private;
-	dpu_kms = to_dpu_kms(priv->kms);
-
 	snprintf(name, DPU_NAME_SIZE, "encoder%u", drm_enc->base.id);
 
 	/* create overall sub-directory for the encoder */
@@ -2042,9 +2020,8 @@ static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc,
 	enum dpu_intf_type intf_type;
 	struct dpu_enc_phys_init_params phys_params;
 
-	if (!dpu_enc || !dpu_kms) {
-		DPU_ERROR("invalid arg(s), enc %d kms %d\n",
-				dpu_enc != 0, dpu_kms != 0);
+	if (!dpu_enc) {
+		DPU_ERROR("invalid arg(s), enc %d\n", dpu_enc != 0);
 		return -EINVAL;
 	}
 
@@ -2133,14 +2110,12 @@ static void dpu_encoder_frame_done_timeout(struct timer_list *t)
 	struct dpu_encoder_virt *dpu_enc = from_timer(dpu_enc, t,
 			frame_done_timer);
 	struct drm_encoder *drm_enc = &dpu_enc->base;
-	struct msm_drm_private *priv;
 	u32 event;
 
-	if (!drm_enc->dev || !drm_enc->dev->dev_private) {
+	if (!drm_enc->dev) {
 		DPU_ERROR("invalid parameters\n");
 		return;
 	}
-	priv = drm_enc->dev->dev_private;
 
 	if (!dpu_enc->frame_busy_mask[0] || !dpu_enc->crtc_frame_event_cb) {
 		DRM_DEBUG_KMS("id:%u invalid timeout frame_busy_mask=%lu\n",
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
index 2923b63d95fe..047960949fbb 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
@@ -124,13 +124,11 @@ static void dpu_encoder_phys_cmd_pp_rd_ptr_irq(void *arg, int irq_idx)
 static void dpu_encoder_phys_cmd_ctl_start_irq(void *arg, int irq_idx)
 {
 	struct dpu_encoder_phys *phys_enc = arg;
-	struct dpu_encoder_phys_cmd *cmd_enc;
 
 	if (!phys_enc || !phys_enc->hw_ctl)
 		return;
 
 	DPU_ATRACE_BEGIN("ctl_start_irq");
-	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
 
 	atomic_add_unless(&phys_enc->pending_ctlstart_cnt, -1, 0);
 
@@ -316,13 +314,9 @@ end:
 static void dpu_encoder_phys_cmd_irq_control(struct dpu_encoder_phys *phys_enc,
 		bool enable)
 {
-	struct dpu_encoder_phys_cmd *cmd_enc;
-
 	if (!phys_enc)
 		return;
 
-	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
-
 	trace_dpu_enc_phys_cmd_irq_ctrl(DRMID(phys_enc->parent),
 			phys_enc->hw_pp->idx - PINGPONG_0,
 			enable, atomic_read(&phys_enc->vblank_refcount));
@@ -355,7 +349,6 @@ static void dpu_encoder_phys_cmd_tearcheck_config(
 	struct drm_display_mode *mode;
 	bool tc_enable = true;
 	u32 vsync_hz;
-	struct msm_drm_private *priv;
 	struct dpu_kms *dpu_kms;
 
 	if (!phys_enc || !phys_enc->hw_pp) {
@@ -373,11 +366,6 @@ static void dpu_encoder_phys_cmd_tearcheck_config(
 	}
 
 	dpu_kms = phys_enc->dpu_kms;
-	if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev_private) {
-		DPU_ERROR("invalid device\n");
-		return;
-	}
-	priv = dpu_kms->dev->dev_private;
 
 	/*
 	 * TE default: dsi byte clock calculated base on 70 fps;
@@ -650,13 +638,10 @@ static int dpu_encoder_phys_cmd_wait_for_tx_complete(
 		struct dpu_encoder_phys *phys_enc)
 {
 	int rc;
-	struct dpu_encoder_phys_cmd *cmd_enc;
 
 	if (!phys_enc)
 		return -EINVAL;
 
-	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
-
 	rc = _dpu_encoder_phys_cmd_wait_for_idle(phys_enc);
 	if (rc) {
 		DRM_ERROR("failed wait_for_idle: id:%u ret:%d intf:%d\n",
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
index b9c84fb4d4a1..3123ef873cdf 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
@@ -374,7 +374,7 @@ static void dpu_encoder_phys_vid_mode_set(
 		struct drm_display_mode *mode,
 		struct drm_display_mode *adj_mode)
 {
-	if (!phys_enc || !phys_enc->dpu_kms) {
+	if (!phys_enc) {
 		DPU_ERROR("invalid encoder/kms\n");
 		return;
 	}
@@ -566,16 +566,13 @@ static void dpu_encoder_phys_vid_prepare_for_kickoff(
 
 static void dpu_encoder_phys_vid_disable(struct dpu_encoder_phys *phys_enc)
 {
-	struct msm_drm_private *priv;
 	unsigned long lock_flags;
 	int ret;
 
-	if (!phys_enc || !phys_enc->parent || !phys_enc->parent->dev ||
-			!phys_enc->parent->dev->dev_private) {
+	if (!phys_enc || !phys_enc->parent || !phys_enc->parent->dev) {
 		DPU_ERROR("invalid encoder/device\n");
 		return;
 	}
-	priv = phys_enc->parent->dev->dev_private;
 
 	if (!phys_enc->hw_intf || !phys_enc->hw_ctl) {
 		DPU_ERROR("invalid hw_intf %d hw_ctl %d\n",
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 58b0485dc375..6c92f0fbeac9 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -30,10 +30,6 @@
 #define CREATE_TRACE_POINTS
 #include "dpu_trace.h"
 
-static const char * const iommu_ports[] = {
-		"mdp_0",
-};
-
 /*
  * To enable overall DRM driver logging
  * # echo 0x2 > /sys/module/drm/parameters/debug
@@ -68,16 +64,14 @@ static int _dpu_danger_signal_status(struct seq_file *s,
 		bool danger_status)
 {
 	struct dpu_kms *kms = (struct dpu_kms *)s->private;
-	struct msm_drm_private *priv;
 	struct dpu_danger_safe_status status;
 	int i;
 
-	if (!kms->dev || !kms->dev->dev_private || !kms->hw_mdp) {
+	if (!kms->hw_mdp) {
 		DPU_ERROR("invalid arg(s)\n");
 		return 0;
 	}
 
-	priv = kms->dev->dev_private;
 	memset(&status, 0, sizeof(struct dpu_danger_safe_status));
 
 	pm_runtime_get_sync(&kms->pdev->dev);
@@ -153,13 +147,7 @@ static int _dpu_debugfs_show_regset32(struct seq_file *s, void *data)
 		return 0;
 
 	dev = dpu_kms->dev;
-	if (!dev)
-		return 0;
-
 	priv = dev->dev_private;
-	if (!priv)
-		return 0;
-
 	base = dpu_kms->mmio + regset->offset;
 
 	/* insert padding spaces, if needed */
@@ -280,7 +268,6 @@ static void dpu_kms_prepare_commit(struct msm_kms *kms,
 		struct drm_atomic_state *state)
 {
 	struct dpu_kms *dpu_kms;
-	struct msm_drm_private *priv;
 	struct drm_device *dev;
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
@@ -292,10 +279,6 @@ static void dpu_kms_prepare_commit(struct msm_kms *kms,
 	dpu_kms = to_dpu_kms(kms);
 	dev = dpu_kms->dev;
 
-	if (!dev || !dev->dev_private)
-		return;
-	priv = dev->dev_private;
-
 	/* Call prepare_commit for all affected encoders */
 	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
 		drm_for_each_encoder_mask(encoder, crtc->dev,
@@ -333,7 +316,6 @@ void dpu_kms_encoder_enable(struct drm_encoder *encoder)
 	if (funcs && funcs->commit)
 		funcs->commit(encoder);
 
-	WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
 	drm_for_each_crtc(crtc, dev) {
 		if (!(crtc->state->encoder_mask & drm_encoder_mask(encoder)))
 			continue;
@@ -464,16 +446,6 @@ static void _dpu_kms_drm_obj_destroy(struct dpu_kms *dpu_kms)
 	struct msm_drm_private *priv;
 	int i;
 
-	if (!dpu_kms) {
-		DPU_ERROR("invalid dpu_kms\n");
-		return;
-	} else if (!dpu_kms->dev) {
-		DPU_ERROR("invalid dev\n");
-		return;
-	} else if (!dpu_kms->dev->dev_private) {
-		DPU_ERROR("invalid dev_private\n");
-		return;
-	}
 	priv = dpu_kms->dev->dev_private;
 
 	for (i = 0; i < priv->num_crtcs; i++)
@@ -505,7 +477,6 @@ static int _dpu_kms_drm_obj_init(struct dpu_kms *dpu_kms)
 
 	int primary_planes_idx = 0, cursor_planes_idx = 0, i, ret;
 	int max_crtc_count;
-
 	dev = dpu_kms->dev;
 	priv = dev->dev_private;
 	catalog = dpu_kms->catalog;
@@ -585,8 +556,6 @@ static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms)
 	int i;
 
 	dev = dpu_kms->dev;
-	if (!dev)
-		return;
 
 	if (dpu_kms->hw_intr)
 		dpu_hw_intr_destroy(dpu_kms->hw_intr);
@@ -725,8 +694,7 @@ static void _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms)
 
 	mmu = dpu_kms->base.aspace->mmu;
 
-	mmu->funcs->detach(mmu, (const char **)iommu_ports,
-			ARRAY_SIZE(iommu_ports));
+	mmu->funcs->detach(mmu);
 	msm_gem_address_space_put(dpu_kms->base.aspace);
 
 	dpu_kms->base.aspace = NULL;
@@ -752,8 +720,7 @@ static int _dpu_kms_mmu_init(struct dpu_kms *dpu_kms)
 		return PTR_ERR(aspace);
 	}
 
-	ret = aspace->mmu->funcs->attach(aspace->mmu, iommu_ports,
-			ARRAY_SIZE(iommu_ports));
+	ret = aspace->mmu->funcs->attach(aspace->mmu);
 	if (ret) {
 		DPU_ERROR("failed to attach iommu %d\n", ret);
 		msm_gem_address_space_put(aspace);
@@ -803,16 +770,7 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 
 	dpu_kms = to_dpu_kms(kms);
 	dev = dpu_kms->dev;
-	if (!dev) {
-		DPU_ERROR("invalid device\n");
-		return rc;
-	}
-
 	priv = dev->dev_private;
-	if (!priv) {
-		DPU_ERROR("invalid private data\n");
-		return rc;
-	}
 
 	atomic_set(&dpu_kms->bandwidth_ref, 0);
 
@@ -974,7 +932,7 @@ struct msm_kms *dpu_kms_init(struct drm_device *dev)
 	struct dpu_kms *dpu_kms;
 	int irq;
 
-	if (!dev || !dev->dev_private) {
+	if (!dev) {
 		DPU_ERROR("drm device node invalid\n");
 		return ERR_PTR(-EINVAL);
 	}
@@ -1064,11 +1022,6 @@ static int __maybe_unused dpu_runtime_suspend(struct device *dev)
 	struct dss_module_power *mp = &dpu_kms->mp;
 
 	ddev = dpu_kms->dev;
-	if (!ddev) {
-		DPU_ERROR("invalid drm_device\n");
-		return rc;
-	}
-
 	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false);
 	if (rc)
 		DPU_ERROR("clock disable failed rc:%d\n", rc);
@@ -1086,11 +1039,6 @@ static int __maybe_unused dpu_runtime_resume(struct device *dev)
 	struct dss_module_power *mp = &dpu_kms->mp;
 
 	ddev = dpu_kms->dev;
-	if (!ddev) {
-		DPU_ERROR("invalid drm_device\n");
-		return rc;
-	}
-
 	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
 	if (rc) {
 		DPU_ERROR("clock enable failed rc:%d\n", rc);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
index 959d03e007fa..c6169e7df19d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
@@ -139,10 +139,6 @@ struct vsync_info {
 
 #define to_dpu_kms(x) container_of(x, struct dpu_kms, base)
 
-/* get struct msm_kms * from drm_device * */
-#define ddev_to_msm_kms(D) ((D) && (D)->dev_private ? \
-		((struct msm_drm_private *)((D)->dev_private))->kms : NULL)
-
 /**
  * Debugfs functions - extra helper functions for debugfs support
  *
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
index 8d24b79fd400..991f4c8f8a12 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
@@ -154,10 +154,6 @@ void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms,
 	u32 ot_lim;
 	int ret, i;
 
-	if (!dpu_kms) {
-		DPU_ERROR("invalid arguments\n");
-		return;
-	}
 	mdp = dpu_kms->hw_mdp;
 
 	for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
@@ -214,7 +210,7 @@ void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms,
 	const struct dpu_vbif_qos_tbl *qos_tbl;
 	int i;
 
-	if (!dpu_kms || !params || !dpu_kms->hw_mdp) {
+	if (!params || !dpu_kms->hw_mdp) {
 		DPU_ERROR("invalid arguments\n");
 		return;
 	}
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
index 50711ccc8691..dda05436f716 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
@@ -157,10 +157,6 @@ static long mdp4_round_pixclk(struct msm_kms *kms, unsigned long rate,
 	}
 }
 
-static const char * const iommu_ports[] = {
-	"mdp_port0_cb0", "mdp_port1_cb0",
-};
-
 static void mdp4_destroy(struct msm_kms *kms)
 {
 	struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms));
@@ -172,8 +168,7 @@ static void mdp4_destroy(struct msm_kms *kms)
 	drm_gem_object_put_unlocked(mdp4_kms->blank_cursor_bo);
 
 	if (aspace) {
-		aspace->mmu->funcs->detach(aspace->mmu,
-				iommu_ports, ARRAY_SIZE(iommu_ports));
+		aspace->mmu->funcs->detach(aspace->mmu);
 		msm_gem_address_space_put(aspace);
 	}
 
@@ -524,8 +519,7 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 
 		kms->aspace = aspace;
 
-		ret = aspace->mmu->funcs->attach(aspace->mmu, iommu_ports,
-				ARRAY_SIZE(iommu_ports));
+		ret = aspace->mmu->funcs->attach(aspace->mmu);
 		if (ret)
 			goto fail;
 	} else {
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
index f6e71ff539ca..1f48f64539a2 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
@@ -14,7 +14,7 @@ struct mdp5_cfg_handler {
 /* mdp5_cfg must be exposed (used in mdp5.xml.h) */
 const struct mdp5_cfg_hw *mdp5_cfg = NULL;
 
-const struct mdp5_cfg_hw msm8x74v1_config = {
+static const struct mdp5_cfg_hw msm8x74v1_config = {
 	.name = "msm8x74v1",
 	.mdp = {
 		.count = 1,
@@ -98,7 +98,7 @@ const struct mdp5_cfg_hw msm8x74v1_config = {
 	.max_clk = 200000000,
 };
 
-const struct mdp5_cfg_hw msm8x74v2_config = {
+static const struct mdp5_cfg_hw msm8x74v2_config = {
 	.name = "msm8x74",
 	.mdp = {
 		.count = 1,
@@ -180,7 +180,7 @@ const struct mdp5_cfg_hw msm8x74v2_config = {
 	.max_clk = 200000000,
 };
 
-const struct mdp5_cfg_hw apq8084_config = {
+static const struct mdp5_cfg_hw apq8084_config = {
 	.name = "apq8084",
 	.mdp = {
 		.count = 1,
@@ -275,7 +275,7 @@ const struct mdp5_cfg_hw apq8084_config = {
 	.max_clk = 320000000,
 };
 
-const struct mdp5_cfg_hw msm8x16_config = {
+static const struct mdp5_cfg_hw msm8x16_config = {
 	.name = "msm8x16",
 	.mdp = {
 		.count = 1,
@@ -342,7 +342,7 @@ const struct mdp5_cfg_hw msm8x16_config = {
 	.max_clk = 320000000,
 };
 
-const struct mdp5_cfg_hw msm8x94_config = {
+static const struct mdp5_cfg_hw msm8x94_config = {
 	.name = "msm8x94",
 	.mdp = {
 		.count = 1,
@@ -437,7 +437,7 @@ const struct mdp5_cfg_hw msm8x94_config = {
 	.max_clk = 400000000,
 };
 
-const struct mdp5_cfg_hw msm8x96_config = {
+static const struct mdp5_cfg_hw msm8x96_config = {
 	.name = "msm8x96",
 	.mdp = {
 		.count = 1,
@@ -545,7 +545,104 @@ const struct mdp5_cfg_hw msm8x96_config = {
 	.max_clk = 412500000,
 };
 
-const struct mdp5_cfg_hw msm8917_config = {
+const struct mdp5_cfg_hw msm8x76_config = {
+	.name = "msm8x76",
+	.mdp = {
+		.count = 1,
+		.caps = MDP_CAP_SMP |
+			MDP_CAP_DSC |
+			MDP_CAP_SRC_SPLIT |
+			0,
+	},
+	.ctl = {
+		.count = 3,
+		.base = { 0x01000, 0x01200, 0x01400 },
+		.flush_hw_mask = 0xffffffff,
+	},
+	.smp = {
+		.mmb_count = 10,
+		.mmb_size = 10240,
+		.clients = {
+			[SSPP_VIG0] = 1, [SSPP_VIG1] = 9,
+			[SSPP_DMA0] = 4,
+			[SSPP_RGB0] = 7, [SSPP_RGB1] = 8,
+		},
+	},
+	.pipe_vig = {
+		.count = 2,
+		.base = { 0x04000, 0x06000 },
+		.caps = MDP_PIPE_CAP_HFLIP	|
+			MDP_PIPE_CAP_VFLIP	|
+			MDP_PIPE_CAP_SCALE	|
+			MDP_PIPE_CAP_CSC	|
+			MDP_PIPE_CAP_DECIMATION	|
+			MDP_PIPE_CAP_SW_PIX_EXT	|
+			0,
+	},
+	.pipe_rgb = {
+		.count = 2,
+		.base = { 0x14000, 0x16000 },
+		.caps = MDP_PIPE_CAP_HFLIP	|
+			MDP_PIPE_CAP_VFLIP	|
+			MDP_PIPE_CAP_DECIMATION	|
+			MDP_PIPE_CAP_SW_PIX_EXT	|
+			0,
+	},
+	.pipe_dma = {
+		.count = 1,
+		.base = { 0x24000 },
+		.caps = MDP_PIPE_CAP_HFLIP	|
+			MDP_PIPE_CAP_VFLIP	|
+			MDP_PIPE_CAP_SW_PIX_EXT	|
+			0,
+	},
+	.pipe_cursor = {
+		.count = 1,
+		.base = { 0x440DC },
+		.caps = MDP_PIPE_CAP_HFLIP	|
+			MDP_PIPE_CAP_VFLIP	|
+			MDP_PIPE_CAP_SW_PIX_EXT	|
+			MDP_PIPE_CAP_CURSOR	|
+			0,
+	},
+	.lm = {
+		.count = 2,
+		.base = { 0x44000, 0x45000 },
+		.instances = {
+				{ .id = 0, .pp = 0, .dspp = 0,
+				  .caps = MDP_LM_CAP_DISPLAY, },
+				{ .id = 1, .pp = -1, .dspp = -1,
+				  .caps = MDP_LM_CAP_WB },
+			     },
+		.nb_stages = 8,
+		.max_width = 2560,
+		.max_height = 0xFFFF,
+	},
+	.dspp = {
+		.count = 1,
+		.base = { 0x54000 },
+
+	},
+	.pp = {
+		.count = 3,
+		.base = { 0x70000, 0x70800, 0x72000 },
+	},
+	.dsc = {
+		.count = 2,
+		.base = { 0x80000, 0x80400 },
+	},
+	.intf = {
+		.base = { 0x6a000, 0x6a800, 0x6b000 },
+		.connect = {
+			[0] = INTF_DISABLED,
+			[1] = INTF_DSI,
+			[2] = INTF_DSI,
+		},
+	},
+	.max_clk = 360000000,
+};
+
+static const struct mdp5_cfg_hw msm8917_config = {
 	.name = "msm8917",
 	.mdp = {
 		.count = 1,
@@ -630,7 +727,7 @@ const struct mdp5_cfg_hw msm8917_config = {
 	.max_clk = 320000000,
 };
 
-const struct mdp5_cfg_hw msm8998_config = {
+static const struct mdp5_cfg_hw msm8998_config = {
 	.name = "msm8998",
 	.mdp = {
 		.count = 1,
@@ -745,6 +842,7 @@ static const struct mdp5_cfg_handler cfg_handlers_v1[] = {
 	{ .revision = 6, .config = { .hw = &msm8x16_config } },
 	{ .revision = 9, .config = { .hw = &msm8x94_config } },
 	{ .revision = 7, .config = { .hw = &msm8x96_config } },
+	{ .revision = 11, .config = { .hw = &msm8x76_config } },
 	{ .revision = 15, .config = { .hw = &msm8917_config } },
 };
 
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index eb0b4b7dc7cc..05cc04f729d6 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -214,7 +214,6 @@ static void blend_setup(struct drm_crtc *crtc)
 	struct mdp5_pipeline *pipeline = &mdp5_cstate->pipeline;
 	struct mdp5_kms *mdp5_kms = get_kms(crtc);
 	struct drm_plane *plane;
-	const struct mdp5_cfg_hw *hw_cfg;
 	struct mdp5_plane_state *pstate, *pstates[STAGE_MAX + 1] = {NULL};
 	const struct mdp_format *format;
 	struct mdp5_hw_mixer *mixer = pipeline->mixer;
@@ -232,8 +231,6 @@ static void blend_setup(struct drm_crtc *crtc)
 	u32 val;
 #define blender(stage)	((stage) - STAGE0)
 
-	hw_cfg = mdp5_cfg_get_hw_config(mdp5_kms->cfg);
-
 	spin_lock_irqsave(&mdp5_crtc->lm_lock, flags);
 
 	/* ctl could be released already when we are shutting down: */
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index 91cd76a2bab1..e43ecd4be10a 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -19,10 +19,6 @@
 #include "msm_mmu.h"
 #include "mdp5_kms.h"
 
-static const char *iommu_ports[] = {
-		"mdp_0",
-};
-
 static int mdp5_hw_init(struct msm_kms *kms)
 {
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
@@ -233,8 +229,7 @@ static void mdp5_kms_destroy(struct msm_kms *kms)
 		mdp5_pipe_destroy(mdp5_kms->hwpipes[i]);
 
 	if (aspace) {
-		aspace->mmu->funcs->detach(aspace->mmu,
-				iommu_ports, ARRAY_SIZE(iommu_ports));
+		aspace->mmu->funcs->detach(aspace->mmu);
 		msm_gem_address_space_put(aspace);
 	}
 }
@@ -314,6 +309,10 @@ int mdp5_disable(struct mdp5_kms *mdp5_kms)
 	mdp5_kms->enable_count--;
 	WARN_ON(mdp5_kms->enable_count < 0);
 
+	if (mdp5_kms->tbu_rt_clk)
+		clk_disable_unprepare(mdp5_kms->tbu_rt_clk);
+	if (mdp5_kms->tbu_clk)
+		clk_disable_unprepare(mdp5_kms->tbu_clk);
 	clk_disable_unprepare(mdp5_kms->ahb_clk);
 	clk_disable_unprepare(mdp5_kms->axi_clk);
 	clk_disable_unprepare(mdp5_kms->core_clk);
@@ -334,6 +333,10 @@ int mdp5_enable(struct mdp5_kms *mdp5_kms)
 	clk_prepare_enable(mdp5_kms->core_clk);
 	if (mdp5_kms->lut_clk)
 		clk_prepare_enable(mdp5_kms->lut_clk);
+	if (mdp5_kms->tbu_clk)
+		clk_prepare_enable(mdp5_kms->tbu_clk);
+	if (mdp5_kms->tbu_rt_clk)
+		clk_prepare_enable(mdp5_kms->tbu_rt_clk);
 
 	return 0;
 }
@@ -466,14 +469,11 @@ static int modeset_init(struct mdp5_kms *mdp5_kms)
 {
 	struct drm_device *dev = mdp5_kms->dev;
 	struct msm_drm_private *priv = dev->dev_private;
-	const struct mdp5_cfg_hw *hw_cfg;
 	unsigned int num_crtcs;
 	int i, ret, pi = 0, ci = 0;
 	struct drm_plane *primary[MAX_BASES] = { NULL };
 	struct drm_plane *cursor[MAX_BASES] = { NULL };
 
-	hw_cfg = mdp5_cfg_get_hw_config(mdp5_kms->cfg);
-
 	/*
 	 * Construct encoders and modeset initialize connector devices
 	 * for each external display interface.
@@ -737,8 +737,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 
 		kms->aspace = aspace;
 
-		ret = aspace->mmu->funcs->attach(aspace->mmu, iommu_ports,
-				ARRAY_SIZE(iommu_ports));
+		ret = aspace->mmu->funcs->attach(aspace->mmu);
 		if (ret) {
 			DRM_DEV_ERROR(&pdev->dev, "failed to attach iommu: %d\n",
 				ret);
@@ -974,6 +973,8 @@ static int mdp5_init(struct platform_device *pdev, struct drm_device *dev)
 
 	/* optional clocks: */
 	get_clk(pdev, &mdp5_kms->lut_clk, "lut", false);
+	get_clk(pdev, &mdp5_kms->tbu_clk, "tbu", false);
+	get_clk(pdev, &mdp5_kms->tbu_rt_clk, "tbu_rt", false);
 
 	/* we need to set a default rate before enabling.  Set a safe
 	 * rate first, then figure out hw revision, and then set a
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h
index d1bf4fdfc815..128866742593 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h
@@ -53,6 +53,8 @@ struct mdp5_kms {
 	struct clk *ahb_clk;
 	struct clk *core_clk;
 	struct clk *lut_clk;
+	struct clk *tbu_clk;
+	struct clk *tbu_rt_clk;
 	struct clk *vsync_clk;
 
 	/*
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
index b31cfb554fa2..d7fa2c49e741 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
@@ -121,7 +121,6 @@ uint32_t mdp5_smp_calculate(struct mdp5_smp *smp,
 	struct mdp5_kms *mdp5_kms = get_kms(smp);
 	int rev = mdp5_cfg_get_hw_rev(mdp5_kms->cfg);
 	int i, hsub, nplanes, nlines;
-	u32 fmt = format->base.pixel_format;
 	uint32_t blkcfg = 0;
 
 	nplanes = info->num_planes;
@@ -135,7 +134,6 @@ uint32_t mdp5_smp_calculate(struct mdp5_smp *smp,
 	 * them together, writes to SMP using a single client.
 	 */
 	if ((rev > 0) && (format->chroma_sample > CHROMA_FULL)) {
-		fmt = DRM_FORMAT_NV24;
 		nplanes = 2;
 
 		/* if decimation is enabled, HW decimates less on the
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
index b7b7c1a9164a..86ad3fdf207d 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
@@ -66,6 +66,26 @@ static const struct msm_dsi_config msm8916_dsi_cfg = {
 	.num_dsi = 1,
 };
 
+static const char * const dsi_8976_bus_clk_names[] = {
+	"mdp_core", "iface", "bus",
+};
+
+static const struct msm_dsi_config msm8976_dsi_cfg = {
+	.io_offset = DSI_6G_REG_SHIFT,
+	.reg_cfg = {
+		.num = 3,
+		.regs = {
+			{"gdsc", -1, -1},
+			{"vdda", 100000, 100},	/* 1.2 V */
+			{"vddio", 100000, 100},	/* 1.8 V */
+		},
+	},
+	.bus_clk_names = dsi_8976_bus_clk_names,
+	.num_bus_clks = ARRAY_SIZE(dsi_8976_bus_clk_names),
+	.io_start = { 0x1a94000, 0x1a96000 },
+	.num_dsi = 2,
+};
+
 static const struct msm_dsi_config msm8994_dsi_cfg = {
 	.io_offset = DSI_6G_REG_SHIFT,
 	.reg_cfg = {
@@ -147,7 +167,7 @@ static const struct msm_dsi_config sdm845_dsi_cfg = {
 	.num_dsi = 2,
 };
 
-const static struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = {
+static const struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = {
 	.link_clk_enable = dsi_link_clk_enable_v2,
 	.link_clk_disable = dsi_link_clk_disable_v2,
 	.clk_init_ver = dsi_clk_init_v2,
@@ -158,7 +178,7 @@ const static struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = {
 	.calc_clk_rate = dsi_calc_clk_rate_v2,
 };
 
-const static struct msm_dsi_host_cfg_ops msm_dsi_6g_host_ops = {
+static const struct msm_dsi_host_cfg_ops msm_dsi_6g_host_ops = {
 	.link_clk_enable = dsi_link_clk_enable_6g,
 	.link_clk_disable = dsi_link_clk_disable_6g,
 	.clk_init_ver = NULL,
@@ -169,7 +189,7 @@ const static struct msm_dsi_host_cfg_ops msm_dsi_6g_host_ops = {
 	.calc_clk_rate = dsi_calc_clk_rate_6g,
 };
 
-const static struct msm_dsi_host_cfg_ops msm_dsi_6g_v2_host_ops = {
+static const struct msm_dsi_host_cfg_ops msm_dsi_6g_v2_host_ops = {
 	.link_clk_enable = dsi_link_clk_enable_6g,
 	.link_clk_disable = dsi_link_clk_disable_6g,
 	.clk_init_ver = dsi_clk_init_6g_v2,
@@ -197,6 +217,8 @@ static const struct msm_dsi_cfg_handler dsi_cfg_handlers[] = {
 		&msm8916_dsi_cfg, &msm_dsi_6g_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_4_1,
 		&msm8996_dsi_cfg, &msm_dsi_6g_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_4_2,
+		&msm8976_dsi_cfg, &msm_dsi_6g_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_0,
 		&msm8998_dsi_cfg, &msm_dsi_6g_v2_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_1,
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
index e2b7a7dfbe49..50a37ceb6a25 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
@@ -17,6 +17,7 @@
 #define MSM_DSI_6G_VER_MINOR_V1_3	0x10030000
 #define MSM_DSI_6G_VER_MINOR_V1_3_1	0x10030001
 #define MSM_DSI_6G_VER_MINOR_V1_4_1	0x10040001
+#define MSM_DSI_6G_VER_MINOR_V1_4_2	0x10040002
 #define MSM_DSI_6G_VER_MINOR_V2_2_0	0x20000000
 #define MSM_DSI_6G_VER_MINOR_V2_2_1	0x20020001
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 1e7b1be25bb0..458cec82ae13 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -1293,14 +1293,13 @@ static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len)
 static int dsi_cmd_dma_rx(struct msm_dsi_host *msm_host,
 			u8 *buf, int rx_byte, int pkt_size)
 {
-	u32 *lp, *temp, data;
+	u32 *temp, data;
 	int i, j = 0, cnt;
 	u32 read_cnt;
 	u8 reg[16];
 	int repeated_bytes = 0;
 	int buf_offset = buf - msm_host->rx_buf;
 
-	lp = (u32 *)buf;
 	temp = (u32 *)reg;
 	cnt = (rx_byte + 3) >> 2;
 	if (cnt > 4)
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index 3522863a4984..b0cfa67d2a57 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -145,7 +145,7 @@ int msm_dsi_dphy_timing_calc_v2(struct msm_dsi_dphy_timing *timing,
 {
 	const unsigned long bit_rate = clk_req->bitclk_rate;
 	const unsigned long esc_rate = clk_req->escclk_rate;
-	s32 ui, ui_x8, lpx;
+	s32 ui, ui_x8;
 	s32 tmax, tmin;
 	s32 pcnt0 = 50;
 	s32 pcnt1 = 50;
@@ -175,7 +175,6 @@ int msm_dsi_dphy_timing_calc_v2(struct msm_dsi_dphy_timing *timing,
 
 	ui = mult_frac(NSEC_PER_MSEC, coeff, bit_rate / 1000);
 	ui_x8 = ui << 3;
-	lpx = mult_frac(NSEC_PER_MSEC, coeff, esc_rate / 1000);
 
 	temp = S_DIV_ROUND_UP(38 * coeff - val_ckln * ui, ui_x8);
 	tmin = max_t(s32, temp, 0);
@@ -262,7 +261,7 @@ int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
 {
 	const unsigned long bit_rate = clk_req->bitclk_rate;
 	const unsigned long esc_rate = clk_req->escclk_rate;
-	s32 ui, ui_x8, lpx;
+	s32 ui, ui_x8;
 	s32 tmax, tmin;
 	s32 pcnt0 = 50;
 	s32 pcnt1 = 50;
@@ -284,7 +283,6 @@ int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
 
 	ui = mult_frac(NSEC_PER_MSEC, coeff, bit_rate / 1000);
 	ui_x8 = ui << 3;
-	lpx = mult_frac(NSEC_PER_MSEC, coeff, esc_rate / 1000);
 
 	temp = S_DIV_ROUND_UP(38 * coeff, ui_x8);
 	tmin = max_t(s32, temp, 0);
@@ -485,6 +483,8 @@ static const struct of_device_id dsi_phy_dt_match[] = {
 #ifdef CONFIG_DRM_MSM_DSI_28NM_PHY
 	{ .compatible = "qcom,dsi-phy-28nm-hpm",
 	  .data = &dsi_phy_28nm_hpm_cfgs },
+	{ .compatible = "qcom,dsi-phy-28nm-hpm-fam-b",
+	  .data = &dsi_phy_28nm_hpm_famb_cfgs },
 	{ .compatible = "qcom,dsi-phy-28nm-lp",
 	  .data = &dsi_phy_28nm_lp_cfgs },
 #endif
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
index c4069ce6afe6..24b294ed3059 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
@@ -40,6 +40,7 @@ struct msm_dsi_phy_cfg {
 };
 
 extern const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_cfgs;
+extern const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_famb_cfgs;
 extern const struct msm_dsi_phy_cfg dsi_phy_28nm_lp_cfgs;
 extern const struct msm_dsi_phy_cfg dsi_phy_20nm_cfgs;
 extern const struct msm_dsi_phy_cfg dsi_phy_28nm_8960_cfgs;
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c
index b3f678f6c2aa..c3c580cfd8b1 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c
@@ -39,15 +39,10 @@ static void dsi_28nm_dphy_set_timing(struct msm_dsi_phy *phy,
 		DSI_28nm_PHY_TIMING_CTRL_11_TRIG3_CMD(0));
 }
 
-static void dsi_28nm_phy_regulator_ctrl(struct msm_dsi_phy *phy, bool enable)
+static void dsi_28nm_phy_regulator_enable_dcdc(struct msm_dsi_phy *phy)
 {
 	void __iomem *base = phy->reg_base;
 
-	if (!enable) {
-		dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CAL_PWR_CFG, 0);
-		return;
-	}
-
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_0, 0x0);
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CAL_PWR_CFG, 1);
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_5, 0);
@@ -56,6 +51,39 @@ static void dsi_28nm_phy_regulator_ctrl(struct msm_dsi_phy *phy, bool enable)
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_1, 0x9);
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_0, 0x7);
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_4, 0x20);
+	dsi_phy_write(phy->base + REG_DSI_28nm_PHY_LDO_CNTRL, 0x00);
+}
+
+static void dsi_28nm_phy_regulator_enable_ldo(struct msm_dsi_phy *phy)
+{
+	void __iomem *base = phy->reg_base;
+
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_0, 0x0);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CAL_PWR_CFG, 0);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_5, 0x7);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_3, 0);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_2, 0x1);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_1, 0x1);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_4, 0x20);
+
+	if (phy->cfg->type == MSM_DSI_PHY_28NM_LP)
+		dsi_phy_write(phy->base + REG_DSI_28nm_PHY_LDO_CNTRL, 0x05);
+	else
+		dsi_phy_write(phy->base + REG_DSI_28nm_PHY_LDO_CNTRL, 0x0d);
+}
+
+static void dsi_28nm_phy_regulator_ctrl(struct msm_dsi_phy *phy, bool enable)
+{
+	if (!enable) {
+		dsi_phy_write(phy->reg_base +
+			      REG_DSI_28nm_PHY_REGULATOR_CAL_PWR_CFG, 0);
+		return;
+	}
+
+	if (phy->regulator_ldo_mode)
+		dsi_28nm_phy_regulator_enable_ldo(phy);
+	else
+		dsi_28nm_phy_regulator_enable_dcdc(phy);
 }
 
 static int dsi_28nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
@@ -77,8 +105,6 @@ static int dsi_28nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
 
 	dsi_28nm_phy_regulator_ctrl(phy, true);
 
-	dsi_phy_write(base + REG_DSI_28nm_PHY_LDO_CNTRL, 0x00);
-
 	dsi_28nm_dphy_set_timing(phy, timing);
 
 	dsi_phy_write(base + REG_DSI_28nm_PHY_CTRL_1, 0x00);
@@ -142,6 +168,24 @@ const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_cfgs = {
 	.num_dsi_phy = 2,
 };
 
+const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_famb_cfgs = {
+	.type = MSM_DSI_PHY_28NM_HPM,
+	.src_pll_truthtable = { {true, true}, {false, true} },
+	.reg_cfg = {
+		.num = 1,
+		.regs = {
+			{"vddio", 100000, 100},
+		},
+	},
+	.ops = {
+		.enable = dsi_28nm_phy_enable,
+		.disable = dsi_28nm_phy_disable,
+		.init = msm_dsi_phy_init_common,
+	},
+	.io_start = { 0x1a94400, 0x1a96400 },
+	.num_dsi_phy = 2,
+};
+
 const struct msm_dsi_phy_cfg dsi_phy_28nm_lp_cfgs = {
 	.type = MSM_DSI_PHY_28NM_LP,
 	.src_pll_truthtable = { {true, true}, {true, true} },
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c
index 1697e61f9c2f..8a38d4b95102 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c
@@ -29,8 +29,12 @@ static int msm_hdmi_phy_resource_init(struct hdmi_phy *phy)
 		reg = devm_regulator_get(dev, cfg->reg_names[i]);
 		if (IS_ERR(reg)) {
 			ret = PTR_ERR(reg);
-			DRM_DEV_ERROR(dev, "failed to get phy regulator: %s (%d)\n",
-				cfg->reg_names[i], ret);
+			if (ret != -EPROBE_DEFER) {
+				DRM_DEV_ERROR(dev,
+					      "failed to get phy regulator: %s (%d)\n",
+					      cfg->reg_names[i], ret);
+			}
+
 			return ret;
 		}
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index a052364a5d74..18f3a5c53ffb 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -16,6 +16,7 @@
 #include <linux/pm_opp.h>
 #include <linux/devfreq.h>
 #include <linux/devcoredump.h>
+#include <linux/sched/task.h>
 
 /*
  * Power Management:
@@ -838,7 +839,7 @@ msm_gpu_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev,
 		return ERR_CAST(aspace);
 	}
 
-	ret = aspace->mmu->funcs->attach(aspace->mmu, NULL, 0);
+	ret = aspace->mmu->funcs->attach(aspace->mmu);
 	if (ret) {
 		msm_gem_address_space_put(aspace);
 		return ERR_PTR(ret);
@@ -995,8 +996,7 @@ void msm_gpu_cleanup(struct msm_gpu *gpu)
 	msm_gem_kernel_put(gpu->memptrs_bo, gpu->aspace, false);
 
 	if (!IS_ERR_OR_NULL(gpu->aspace)) {
-		gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu,
-			NULL, 0);
+		gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu);
 		msm_gem_address_space_put(gpu->aspace);
 	}
 }
diff --git a/drivers/gpu/drm/msm/msm_gpummu.c b/drivers/gpu/drm/msm/msm_gpummu.c
index 34f643a0c28a..34980d8eb7ad 100644
--- a/drivers/gpu/drm/msm/msm_gpummu.c
+++ b/drivers/gpu/drm/msm/msm_gpummu.c
@@ -21,14 +21,12 @@ struct msm_gpummu {
 #define GPUMMU_PAGE_SIZE SZ_4K
 #define TABLE_SIZE (sizeof(uint32_t) * GPUMMU_VA_RANGE / GPUMMU_PAGE_SIZE)
 
-static int msm_gpummu_attach(struct msm_mmu *mmu, const char * const *names,
-		int cnt)
+static int msm_gpummu_attach(struct msm_mmu *mmu)
 {
 	return 0;
 }
 
-static void msm_gpummu_detach(struct msm_mmu *mmu, const char * const *names,
-		int cnt)
+static void msm_gpummu_detach(struct msm_mmu *mmu)
 {
 }
 
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 8c95c31e2b12..ad58cfe5998e 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -23,16 +23,14 @@ static int msm_fault_handler(struct iommu_domain *domain, struct device *dev,
 	return 0;
 }
 
-static int msm_iommu_attach(struct msm_mmu *mmu, const char * const *names,
-			    int cnt)
+static int msm_iommu_attach(struct msm_mmu *mmu)
 {
 	struct msm_iommu *iommu = to_msm_iommu(mmu);
 
 	return iommu_attach_device(iommu->domain, mmu->dev);
 }
 
-static void msm_iommu_detach(struct msm_mmu *mmu, const char * const *names,
-			     int cnt)
+static void msm_iommu_detach(struct msm_mmu *mmu)
 {
 	struct msm_iommu *iommu = to_msm_iommu(mmu);
 
diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h
index 871d56303697..67a623f14319 100644
--- a/drivers/gpu/drm/msm/msm_mmu.h
+++ b/drivers/gpu/drm/msm/msm_mmu.h
@@ -10,8 +10,8 @@
 #include <linux/iommu.h>
 
 struct msm_mmu_funcs {
-	int (*attach)(struct msm_mmu *mmu, const char * const *names, int cnt);
-	void (*detach)(struct msm_mmu *mmu, const char * const *names, int cnt);
+	int (*attach)(struct msm_mmu *mmu);
+	void (*detach)(struct msm_mmu *mmu);
 	int (*map)(struct msm_mmu *mmu, uint64_t iova, struct sg_table *sgt,
 			unsigned len, int prot);
 	int (*unmap)(struct msm_mmu *mmu, uint64_t iova, unsigned len);
diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c
index c7832a951039..af7ceb246c7c 100644
--- a/drivers/gpu/drm/msm/msm_rd.c
+++ b/drivers/gpu/drm/msm/msm_rd.c
@@ -298,7 +298,7 @@ void msm_rd_debugfs_cleanup(struct msm_drm_private *priv)
 
 static void snapshot_buf(struct msm_rd_state *rd,
 		struct msm_gem_submit *submit, int idx,
-		uint64_t iova, uint32_t size)
+		uint64_t iova, uint32_t size, bool full)
 {
 	struct msm_gem_object *obj = submit->bos[idx].obj;
 	unsigned offset = 0;
@@ -318,6 +318,9 @@ static void snapshot_buf(struct msm_rd_state *rd,
 	rd_write_section(rd, RD_GPUADDR,
 			(uint32_t[3]){ iova, size, iova >> 32 }, 12);
 
+	if (!full)
+		return;
+
 	/* But only dump the contents of buffers marked READ */
 	if (!(submit->bos[idx].flags & MSM_SUBMIT_BO_READ))
 		return;
@@ -381,18 +384,21 @@ void msm_rd_dump_submit(struct msm_rd_state *rd, struct msm_gem_submit *submit,
 	rd_write_section(rd, RD_CMD, msg, ALIGN(n, 4));
 
 	for (i = 0; i < submit->nr_bos; i++)
-		if (should_dump(submit, i))
-			snapshot_buf(rd, submit, i, 0, 0);
+		snapshot_buf(rd, submit, i, 0, 0, should_dump(submit, i));
 
 	for (i = 0; i < submit->nr_cmds; i++) {
-		uint64_t iova = submit->cmd[i].iova;
 		uint32_t szd  = submit->cmd[i].size; /* in dwords */
 
 		/* snapshot cmdstream bo's (if we haven't already): */
 		if (!should_dump(submit, i)) {
 			snapshot_buf(rd, submit, submit->cmd[i].idx,
-					submit->cmd[i].iova, szd * 4);
+					submit->cmd[i].iova, szd * 4, true);
 		}
+	}
+
+	for (i = 0; i < submit->nr_cmds; i++) {
+		uint64_t iova = submit->cmd[i].iova;
+		uint32_t szd  = submit->cmd[i].size; /* in dwords */
 
 		switch (submit->cmd[i].type) {
 		case MSM_SUBMIT_CMD_IB_TARGET_BUF:
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index e518d93ca6df..d08ae95ecc0a 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -843,9 +843,13 @@ fail:
  */
 static void omap_gem_unpin_locked(struct drm_gem_object *obj)
 {
+	struct omap_drm_private *priv = obj->dev->dev_private;
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	int ret;
 
+	if (omap_gem_is_contiguous(omap_obj) || !priv->has_dmm)
+		return;
+
 	if (refcount_dec_and_test(&omap_obj->dma_addr_cnt)) {
 		ret = tiler_unpin(omap_obj->block);
 		if (ret) {
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 7089dfc8c2a9..110fb38004b1 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -1826,8 +1826,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 			track->textures[i].use_pitch = 1;
 		} else {
 			track->textures[i].use_pitch = 0;
-			track->textures[i].width = 1 << ((idx_value >> RADEON_TXFORMAT_WIDTH_SHIFT) & RADEON_TXFORMAT_WIDTH_MASK);
-			track->textures[i].height = 1 << ((idx_value >> RADEON_TXFORMAT_HEIGHT_SHIFT) & RADEON_TXFORMAT_HEIGHT_MASK);
+			track->textures[i].width = 1 << ((idx_value & RADEON_TXFORMAT_WIDTH_MASK) >> RADEON_TXFORMAT_WIDTH_SHIFT);
+			track->textures[i].height = 1 << ((idx_value & RADEON_TXFORMAT_HEIGHT_MASK) >> RADEON_TXFORMAT_HEIGHT_SHIFT);
 		}
 		if (idx_value & RADEON_TXFORMAT_CUBIC_MAP_ENABLE)
 			track->textures[i].tex_coord_type = 2;
diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c
index 840401413c58..f5f2ffea5ab2 100644
--- a/drivers/gpu/drm/radeon/r200.c
+++ b/drivers/gpu/drm/radeon/r200.c
@@ -476,8 +476,8 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 			track->textures[i].use_pitch = 1;
 		} else {
 			track->textures[i].use_pitch = 0;
-			track->textures[i].width = 1 << ((idx_value >> RADEON_TXFORMAT_WIDTH_SHIFT) & RADEON_TXFORMAT_WIDTH_MASK);
-			track->textures[i].height = 1 << ((idx_value >> RADEON_TXFORMAT_HEIGHT_SHIFT) & RADEON_TXFORMAT_HEIGHT_MASK);
+			track->textures[i].width = 1 << ((idx_value & RADEON_TXFORMAT_WIDTH_MASK) >> RADEON_TXFORMAT_WIDTH_SHIFT);
+			track->textures[i].height = 1 << ((idx_value & RADEON_TXFORMAT_HEIGHT_MASK) >> RADEON_TXFORMAT_HEIGHT_SHIFT);
 		}
 		if (idx_value & R200_TXFORMAT_LOOKUP_DISABLE)
 			track->textures[i].lookup_disable = true;
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index 5b1f9ff97576..714af052fbef 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -837,16 +837,15 @@ static int tegra_cursor_atomic_check(struct drm_plane *plane,
 static void tegra_cursor_atomic_update(struct drm_plane *plane,
 				       struct drm_plane_state *old_state)
 {
-	struct tegra_bo *bo = tegra_fb_get_plane(plane->state->fb, 0);
+	struct tegra_plane_state *state = to_tegra_plane_state(plane->state);
 	struct tegra_dc *dc = to_tegra_dc(plane->state->crtc);
-	struct drm_plane_state *state = plane->state;
 	u32 value = CURSOR_CLIP_DISPLAY;
 
 	/* rien ne va plus */
 	if (!plane->state->crtc || !plane->state->fb)
 		return;
 
-	switch (state->crtc_w) {
+	switch (plane->state->crtc_w) {
 	case 32:
 		value |= CURSOR_SIZE_32x32;
 		break;
@@ -864,16 +863,16 @@ static void tegra_cursor_atomic_update(struct drm_plane *plane,
 		break;
 
 	default:
-		WARN(1, "cursor size %ux%u not supported\n", state->crtc_w,
-		     state->crtc_h);
+		WARN(1, "cursor size %ux%u not supported\n",
+		     plane->state->crtc_w, plane->state->crtc_h);
 		return;
 	}
 
-	value |= (bo->iova >> 10) & 0x3fffff;
+	value |= (state->iova[0] >> 10) & 0x3fffff;
 	tegra_dc_writel(dc, value, DC_DISP_CURSOR_START_ADDR);
 
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	value = (bo->iova >> 32) & 0x3;
+	value = (state->iova[0] >> 32) & 0x3;
 	tegra_dc_writel(dc, value, DC_DISP_CURSOR_START_ADDR_HI);
 #endif
 
@@ -892,7 +891,8 @@ static void tegra_cursor_atomic_update(struct drm_plane *plane,
 	tegra_dc_writel(dc, value, DC_DISP_BLEND_CURSOR_CONTROL);
 
 	/* position the cursor */
-	value = (state->crtc_y & 0x3fff) << 16 | (state->crtc_x & 0x3fff);
+	value = (plane->state->crtc_y & 0x3fff) << 16 |
+		(plane->state->crtc_x & 0x3fff);
 	tegra_dc_writel(dc, value, DC_DISP_CURSOR_POSITION);
 }
 
@@ -2017,7 +2017,7 @@ static int tegra_dc_init(struct host1x_client *client)
 		dev_warn(dc->dev, "failed to allocate syncpoint\n");
 
 	err = host1x_client_iommu_attach(client);
-	if (err < 0) {
+	if (err < 0 && err != -ENODEV) {
 		dev_err(client->dev, "failed to attach to domain: %d\n", err);
 		return err;
 	}
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 56e5e7a5c108..f455ce71e85d 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -920,10 +920,8 @@ int host1x_client_iommu_attach(struct host1x_client *client)
 
 	if (tegra->domain) {
 		group = iommu_group_get(client->dev);
-		if (!group) {
-			dev_err(client->dev, "failed to get IOMMU group\n");
+		if (!group)
 			return -ENODEV;
-		}
 
 		if (domain != tegra->domain) {
 			err = iommu_attach_group(tegra->domain, group);
@@ -1243,6 +1241,9 @@ static int host1x_drm_remove(struct host1x_device *dev)
 	drm_atomic_helper_shutdown(drm);
 	drm_mode_config_cleanup(drm);
 
+	if (tegra->hub)
+		tegra_display_hub_cleanup(tegra->hub);
+
 	err = host1x_device_exit(dev);
 	if (err < 0)
 		dev_err(&dev->dev, "host1x device cleanup failed: %d\n", err);
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index 746dae32c484..bc15b430156d 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -27,6 +27,29 @@ static void tegra_bo_put(struct host1x_bo *bo)
 	drm_gem_object_put_unlocked(&obj->gem);
 }
 
+/* XXX move this into lib/scatterlist.c? */
+static int sg_alloc_table_from_sg(struct sg_table *sgt, struct scatterlist *sg,
+				  unsigned int nents, gfp_t gfp_mask)
+{
+	struct scatterlist *dst;
+	unsigned int i;
+	int err;
+
+	err = sg_alloc_table(sgt, nents, gfp_mask);
+	if (err < 0)
+		return err;
+
+	dst = sgt->sgl;
+
+	for (i = 0; i < nents; i++) {
+		sg_set_page(dst, sg_page(sg), sg->length, 0);
+		dst = sg_next(dst);
+		sg = sg_next(sg);
+	}
+
+	return 0;
+}
+
 static struct sg_table *tegra_bo_pin(struct device *dev, struct host1x_bo *bo,
 				     dma_addr_t *phys)
 {
@@ -52,11 +75,31 @@ static struct sg_table *tegra_bo_pin(struct device *dev, struct host1x_bo *bo,
 		return ERR_PTR(-ENOMEM);
 
 	if (obj->pages) {
+		/*
+		 * If the buffer object was allocated from the explicit IOMMU
+		 * API code paths, construct an SG table from the pages.
+		 */
 		err = sg_alloc_table_from_pages(sgt, obj->pages, obj->num_pages,
 						0, obj->gem.size, GFP_KERNEL);
 		if (err < 0)
 			goto free;
+	} else if (obj->sgt) {
+		/*
+		 * If the buffer object already has an SG table but no pages
+		 * were allocated for it, it means the buffer was imported and
+		 * the SG table needs to be copied to avoid overwriting any
+		 * other potential users of the original SG table.
+		 */
+		err = sg_alloc_table_from_sg(sgt, obj->sgt->sgl, obj->sgt->nents,
+					     GFP_KERNEL);
+		if (err < 0)
+			goto free;
 	} else {
+		/*
+		 * If the buffer object had no pages allocated and if it was
+		 * not imported, it had to be allocated with the DMA API, so
+		 * the DMA API helper can be used.
+		 */
 		err = dma_get_sgtable(dev, sgt, obj->vaddr, obj->iova,
 				      obj->gem.size);
 		if (err < 0)
@@ -397,13 +440,6 @@ static struct tegra_bo *tegra_bo_import(struct drm_device *drm,
 		err = tegra_bo_iommu_map(tegra, bo);
 		if (err < 0)
 			goto detach;
-	} else {
-		if (bo->sgt->nents > 1) {
-			err = -EINVAL;
-			goto detach;
-		}
-
-		bo->iova = sg_dma_address(bo->sgt->sgl);
 	}
 
 	bo->gem.import_attach = attach;
diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c
index 2b4082d0bc9e..47d985ac7cd7 100644
--- a/drivers/gpu/drm/tegra/hub.c
+++ b/drivers/gpu/drm/tegra/hub.c
@@ -605,11 +605,8 @@ static struct tegra_display_hub_state *
 tegra_display_hub_get_state(struct tegra_display_hub *hub,
 			    struct drm_atomic_state *state)
 {
-	struct drm_device *drm = dev_get_drvdata(hub->client.parent);
 	struct drm_private_state *priv;
 
-	WARN_ON(!drm_modeset_is_locked(&drm->mode_config.connection_mutex));
-
 	priv = drm_atomic_get_private_obj_state(state, &hub->base);
 	if (IS_ERR(priv))
 		return ERR_CAST(priv);
diff --git a/drivers/gpu/drm/tegra/plane.c b/drivers/gpu/drm/tegra/plane.c
index 163b590be224..cadcdd9ea427 100644
--- a/drivers/gpu/drm/tegra/plane.c
+++ b/drivers/gpu/drm/tegra/plane.c
@@ -129,6 +129,17 @@ static int tegra_dc_pin(struct tegra_dc *dc, struct tegra_plane_state *state)
 				goto unpin;
 			}
 
+			/*
+			 * The display controller needs contiguous memory, so
+			 * fail if the buffer is discontiguous and we fail to
+			 * map its SG table to a single contiguous chunk of
+			 * I/O virtual memory.
+			 */
+			if (err > 1) {
+				err = -EINVAL;
+				goto unpin;
+			}
+
 			state->iova[i] = sg_dma_address(sgt->sgl);
 			state->sgt[i] = sgt;
 		} else {
diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c
index 615cb319fa8b..a68d3b36b972 100644
--- a/drivers/gpu/drm/tegra/sor.c
+++ b/drivers/gpu/drm/tegra/sor.c
@@ -3912,8 +3912,7 @@ static int tegra_sor_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int tegra_sor_suspend(struct device *dev)
+static int tegra_sor_runtime_suspend(struct device *dev)
 {
 	struct tegra_sor *sor = dev_get_drvdata(dev);
 	int err;
@@ -3935,7 +3934,7 @@ static int tegra_sor_suspend(struct device *dev)
 	return 0;
 }
 
-static int tegra_sor_resume(struct device *dev)
+static int tegra_sor_runtime_resume(struct device *dev)
 {
 	struct tegra_sor *sor = dev_get_drvdata(dev);
 	int err;
@@ -3967,10 +3966,39 @@ static int tegra_sor_resume(struct device *dev)
 
 	return 0;
 }
-#endif
+
+static int tegra_sor_suspend(struct device *dev)
+{
+	struct tegra_sor *sor = dev_get_drvdata(dev);
+	int err;
+
+	if (sor->hdmi_supply) {
+		err = regulator_disable(sor->hdmi_supply);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+
+static int tegra_sor_resume(struct device *dev)
+{
+	struct tegra_sor *sor = dev_get_drvdata(dev);
+	int err;
+
+	if (sor->hdmi_supply) {
+		err = regulator_enable(sor->hdmi_supply);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
 
 static const struct dev_pm_ops tegra_sor_pm_ops = {
-	SET_RUNTIME_PM_OPS(tegra_sor_suspend, tegra_sor_resume, NULL)
+	SET_RUNTIME_PM_OPS(tegra_sor_runtime_suspend, tegra_sor_runtime_resume,
+			   NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(tegra_sor_suspend, tegra_sor_resume)
 };
 
 struct platform_driver tegra_sor_driver = {
diff --git a/drivers/gpu/drm/tegra/vic.c b/drivers/gpu/drm/tegra/vic.c
index 9444ba183990..3526c2892ddb 100644
--- a/drivers/gpu/drm/tegra/vic.c
+++ b/drivers/gpu/drm/tegra/vic.c
@@ -167,7 +167,7 @@ static int vic_init(struct host1x_client *client)
 	int err;
 
 	err = host1x_client_iommu_attach(client);
-	if (err < 0) {
+	if (err < 0 && err != -ENODEV) {
 		dev_err(vic->dev, "failed to attach to domain: %d\n", err);
 		return err;
 	}
@@ -386,13 +386,14 @@ static const struct vic_config vic_t194_config = {
 	.supports_sid = true,
 };
 
-static const struct of_device_id vic_match[] = {
+static const struct of_device_id tegra_vic_of_match[] = {
 	{ .compatible = "nvidia,tegra124-vic", .data = &vic_t124_config },
 	{ .compatible = "nvidia,tegra210-vic", .data = &vic_t210_config },
 	{ .compatible = "nvidia,tegra186-vic", .data = &vic_t186_config },
 	{ .compatible = "nvidia,tegra194-vic", .data = &vic_t194_config },
 	{ },
 };
+MODULE_DEVICE_TABLE(of, tegra_vic_of_match);
 
 static int vic_probe(struct platform_device *pdev)
 {
@@ -516,7 +517,7 @@ static const struct dev_pm_ops vic_pm_ops = {
 struct platform_driver tegra_vic_driver = {
 	.driver = {
 		.name = "tegra-vic",
-		.of_match_table = vic_match,
+		.of_match_table = tegra_vic_of_match,
 		.pm = &vic_pm_ops
 	},
 	.probe = vic_probe,
diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index c6df8b43fa6d..79d826553ac8 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -66,6 +66,16 @@ config QCOM_MDT_LOADER
 	tristate
 	select QCOM_SCM
 
+config QCOM_OCMEM
+	tristate "Qualcomm On Chip Memory (OCMEM) driver"
+	depends on ARCH_QCOM
+	select QCOM_SCM
+	help
+          The On Chip Memory (OCMEM) allocator allows various clients to
+          allocate memory from OCMEM based on performance, latency and power
+          requirements. This is typically used by the GPU, camera/video, and
+          audio components on some Snapdragon SoCs.
+
 config QCOM_PM
 	bool "Qualcomm Power Management"
 	depends on ARCH_QCOM && !ARM64
diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index 2559fe948ce0..9fb35c8a495e 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -6,6 +6,7 @@ obj-$(CONFIG_QCOM_COMMAND_DB) += cmd-db.o
 obj-$(CONFIG_QCOM_GLINK_SSR) +=	glink_ssr.o
 obj-$(CONFIG_QCOM_GSBI)	+=	qcom_gsbi.o
 obj-$(CONFIG_QCOM_MDT_LOADER)	+= mdt_loader.o
+obj-$(CONFIG_QCOM_OCMEM)	+= ocmem.o
 obj-$(CONFIG_QCOM_PM)	+=	spm.o
 obj-$(CONFIG_QCOM_QMI_HELPERS)	+= qmi_helpers.o
 qmi_helpers-y	+= qmi_encdec.o qmi_interface.o
diff --git a/drivers/soc/qcom/ocmem.c b/drivers/soc/qcom/ocmem.c
new file mode 100644
index 000000000000..7f9e9944d1ea
--- /dev/null
+++ b/drivers/soc/qcom/ocmem.c
@@ -0,0 +1,433 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * The On Chip Memory (OCMEM) allocator allows various clients to allocate
+ * memory from OCMEM based on performance, latency and power requirements.
+ * This is typically used by the GPU, camera/video, and audio components on
+ * some Snapdragon SoCs.
+ *
+ * Copyright (C) 2019 Brian Masney <masneyb@onstation.org>
+ * Copyright (C) 2015 Red Hat. Author: Rob Clark <robdclark@gmail.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/qcom_scm.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <soc/qcom/ocmem.h>
+
+enum region_mode {
+	WIDE_MODE = 0x0,
+	THIN_MODE,
+	MODE_DEFAULT = WIDE_MODE,
+};
+
+enum ocmem_macro_state {
+	PASSTHROUGH = 0,
+	PERI_ON = 1,
+	CORE_ON = 2,
+	CLK_OFF = 4,
+};
+
+struct ocmem_region {
+	bool interleaved;
+	enum region_mode mode;
+	unsigned int num_macros;
+	enum ocmem_macro_state macro_state[4];
+	unsigned long macro_size;
+	unsigned long region_size;
+};
+
+struct ocmem_config {
+	uint8_t num_regions;
+	unsigned long macro_size;
+};
+
+struct ocmem {
+	struct device *dev;
+	const struct ocmem_config *config;
+	struct resource *memory;
+	void __iomem *mmio;
+	unsigned int num_ports;
+	unsigned int num_macros;
+	bool interleaved;
+	struct ocmem_region *regions;
+	unsigned long active_allocations;
+};
+
+#define OCMEM_MIN_ALIGN				SZ_64K
+#define OCMEM_MIN_ALLOC				SZ_64K
+
+#define OCMEM_REG_HW_VERSION			0x00000000
+#define OCMEM_REG_HW_PROFILE			0x00000004
+
+#define OCMEM_REG_REGION_MODE_CTL		0x00001000
+#define OCMEM_REGION_MODE_CTL_REG0_THIN		0x00000001
+#define OCMEM_REGION_MODE_CTL_REG1_THIN		0x00000002
+#define OCMEM_REGION_MODE_CTL_REG2_THIN		0x00000004
+#define OCMEM_REGION_MODE_CTL_REG3_THIN		0x00000008
+
+#define OCMEM_REG_GFX_MPU_START			0x00001004
+#define OCMEM_REG_GFX_MPU_END			0x00001008
+
+#define OCMEM_HW_PROFILE_NUM_PORTS(val)		FIELD_PREP(0x0000000f, (val))
+#define OCMEM_HW_PROFILE_NUM_MACROS(val)	FIELD_PREP(0x00003f00, (val))
+
+#define OCMEM_HW_PROFILE_LAST_REGN_HALFSIZE	0x00010000
+#define OCMEM_HW_PROFILE_INTERLEAVING		0x00020000
+#define OCMEM_REG_GEN_STATUS			0x0000000c
+
+#define OCMEM_REG_PSGSC_STATUS			0x00000038
+#define OCMEM_REG_PSGSC_CTL(i0)			(0x0000003c + 0x1*(i0))
+
+#define OCMEM_PSGSC_CTL_MACRO0_MODE(val)	FIELD_PREP(0x00000007, (val))
+#define OCMEM_PSGSC_CTL_MACRO1_MODE(val)	FIELD_PREP(0x00000070, (val))
+#define OCMEM_PSGSC_CTL_MACRO2_MODE(val)	FIELD_PREP(0x00000700, (val))
+#define OCMEM_PSGSC_CTL_MACRO3_MODE(val)	FIELD_PREP(0x00007000, (val))
+
+#define OCMEM_CLK_CORE_IDX			0
+static struct clk_bulk_data ocmem_clks[] = {
+	{
+		.id = "core",
+	},
+	{
+		.id = "iface",
+	},
+};
+
+static inline void ocmem_write(struct ocmem *ocmem, u32 reg, u32 data)
+{
+	writel(data, ocmem->mmio + reg);
+}
+
+static inline u32 ocmem_read(struct ocmem *ocmem, u32 reg)
+{
+	return readl(ocmem->mmio + reg);
+}
+
+static void update_ocmem(struct ocmem *ocmem)
+{
+	uint32_t region_mode_ctrl = 0x0;
+	int i;
+
+	if (!qcom_scm_ocmem_lock_available()) {
+		for (i = 0; i < ocmem->config->num_regions; i++) {
+			struct ocmem_region *region = &ocmem->regions[i];
+
+			if (region->mode == THIN_MODE)
+				region_mode_ctrl |= BIT(i);
+		}
+
+		dev_dbg(ocmem->dev, "ocmem_region_mode_control %x\n",
+			region_mode_ctrl);
+		ocmem_write(ocmem, OCMEM_REG_REGION_MODE_CTL, region_mode_ctrl);
+	}
+
+	for (i = 0; i < ocmem->config->num_regions; i++) {
+		struct ocmem_region *region = &ocmem->regions[i];
+		u32 data;
+
+		data = OCMEM_PSGSC_CTL_MACRO0_MODE(region->macro_state[0]) |
+			OCMEM_PSGSC_CTL_MACRO1_MODE(region->macro_state[1]) |
+			OCMEM_PSGSC_CTL_MACRO2_MODE(region->macro_state[2]) |
+			OCMEM_PSGSC_CTL_MACRO3_MODE(region->macro_state[3]);
+
+		ocmem_write(ocmem, OCMEM_REG_PSGSC_CTL(i), data);
+	}
+}
+
+static unsigned long phys_to_offset(struct ocmem *ocmem,
+				    unsigned long addr)
+{
+	if (addr < ocmem->memory->start || addr >= ocmem->memory->end)
+		return 0;
+
+	return addr - ocmem->memory->start;
+}
+
+static unsigned long device_address(struct ocmem *ocmem,
+				    enum ocmem_client client,
+				    unsigned long addr)
+{
+	WARN_ON(client != OCMEM_GRAPHICS);
+
+	/* TODO: gpu uses phys_to_offset, but others do not.. */
+	return phys_to_offset(ocmem, addr);
+}
+
+static void update_range(struct ocmem *ocmem, struct ocmem_buf *buf,
+			 enum ocmem_macro_state mstate, enum region_mode rmode)
+{
+	unsigned long offset = 0;
+	int i, j;
+
+	for (i = 0; i < ocmem->config->num_regions; i++) {
+		struct ocmem_region *region = &ocmem->regions[i];
+
+		if (buf->offset <= offset && offset < buf->offset + buf->len)
+			region->mode = rmode;
+
+		for (j = 0; j < region->num_macros; j++) {
+			if (buf->offset <= offset &&
+			    offset < buf->offset + buf->len)
+				region->macro_state[j] = mstate;
+
+			offset += region->macro_size;
+		}
+	}
+
+	update_ocmem(ocmem);
+}
+
+struct ocmem *of_get_ocmem(struct device *dev)
+{
+	struct platform_device *pdev;
+	struct device_node *devnode;
+
+	devnode = of_parse_phandle(dev->of_node, "sram", 0);
+	if (!devnode || !devnode->parent) {
+		dev_err(dev, "Cannot look up sram phandle\n");
+		return ERR_PTR(-ENODEV);
+	}
+
+	pdev = of_find_device_by_node(devnode->parent);
+	if (!pdev) {
+		dev_err(dev, "Cannot find device node %s\n", devnode->name);
+		return ERR_PTR(-EPROBE_DEFER);
+	}
+
+	return platform_get_drvdata(pdev);
+}
+EXPORT_SYMBOL(of_get_ocmem);
+
+struct ocmem_buf *ocmem_allocate(struct ocmem *ocmem, enum ocmem_client client,
+				 unsigned long size)
+{
+	struct ocmem_buf *buf;
+	int ret;
+
+	/* TODO: add support for other clients... */
+	if (WARN_ON(client != OCMEM_GRAPHICS))
+		return ERR_PTR(-ENODEV);
+
+	if (size < OCMEM_MIN_ALLOC || !IS_ALIGNED(size, OCMEM_MIN_ALIGN))
+		return ERR_PTR(-EINVAL);
+
+	if (test_and_set_bit_lock(BIT(client), &ocmem->active_allocations))
+		return ERR_PTR(-EBUSY);
+
+	buf = kzalloc(sizeof(*buf), GFP_KERNEL);
+	if (!buf) {
+		ret = -ENOMEM;
+		goto err_unlock;
+	}
+
+	buf->offset = 0;
+	buf->addr = device_address(ocmem, client, buf->offset);
+	buf->len = size;
+
+	update_range(ocmem, buf, CORE_ON, WIDE_MODE);
+
+	if (qcom_scm_ocmem_lock_available()) {
+		ret = qcom_scm_ocmem_lock(QCOM_SCM_OCMEM_GRAPHICS_ID,
+					  buf->offset, buf->len, WIDE_MODE);
+		if (ret) {
+			dev_err(ocmem->dev, "could not lock: %d\n", ret);
+			ret = -EINVAL;
+			goto err_kfree;
+		}
+	} else {
+		ocmem_write(ocmem, OCMEM_REG_GFX_MPU_START, buf->offset);
+		ocmem_write(ocmem, OCMEM_REG_GFX_MPU_END,
+			    buf->offset + buf->len);
+	}
+
+	dev_dbg(ocmem->dev, "using %ldK of OCMEM at 0x%08lx for client %d\n",
+		size / 1024, buf->addr, client);
+
+	return buf;
+
+err_kfree:
+	kfree(buf);
+err_unlock:
+	clear_bit_unlock(BIT(client), &ocmem->active_allocations);
+
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL(ocmem_allocate);
+
+void ocmem_free(struct ocmem *ocmem, enum ocmem_client client,
+		struct ocmem_buf *buf)
+{
+	/* TODO: add support for other clients... */
+	if (WARN_ON(client != OCMEM_GRAPHICS))
+		return;
+
+	update_range(ocmem, buf, CLK_OFF, MODE_DEFAULT);
+
+	if (qcom_scm_ocmem_lock_available()) {
+		int ret;
+
+		ret = qcom_scm_ocmem_unlock(QCOM_SCM_OCMEM_GRAPHICS_ID,
+					    buf->offset, buf->len);
+		if (ret)
+			dev_err(ocmem->dev, "could not unlock: %d\n", ret);
+	} else {
+		ocmem_write(ocmem, OCMEM_REG_GFX_MPU_START, 0x0);
+		ocmem_write(ocmem, OCMEM_REG_GFX_MPU_END, 0x0);
+	}
+
+	kfree(buf);
+
+	clear_bit_unlock(BIT(client), &ocmem->active_allocations);
+}
+EXPORT_SYMBOL(ocmem_free);
+
+static int ocmem_dev_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	unsigned long reg, region_size;
+	int i, j, ret, num_banks;
+	struct resource *res;
+	struct ocmem *ocmem;
+
+	if (!qcom_scm_is_available())
+		return -EPROBE_DEFER;
+
+	ocmem = devm_kzalloc(dev, sizeof(*ocmem), GFP_KERNEL);
+	if (!ocmem)
+		return -ENOMEM;
+
+	ocmem->dev = dev;
+	ocmem->config = device_get_match_data(dev);
+
+	ret = devm_clk_bulk_get(dev, ARRAY_SIZE(ocmem_clks), ocmem_clks);
+	if (ret) {
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "Unable to get clocks\n");
+
+		return ret;
+	}
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ctrl");
+	ocmem->mmio = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(ocmem->mmio)) {
+		dev_err(&pdev->dev, "Failed to ioremap ocmem_ctrl resource\n");
+		return PTR_ERR(ocmem->mmio);
+	}
+
+	ocmem->memory = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						     "mem");
+	if (!ocmem->memory) {
+		dev_err(dev, "Could not get mem region\n");
+		return -ENXIO;
+	}
+
+	/* The core clock is synchronous with graphics */
+	WARN_ON(clk_set_rate(ocmem_clks[OCMEM_CLK_CORE_IDX].clk, 1000) < 0);
+
+	ret = clk_bulk_prepare_enable(ARRAY_SIZE(ocmem_clks), ocmem_clks);
+	if (ret) {
+		dev_info(ocmem->dev, "Failed to enable clocks\n");
+		return ret;
+	}
+
+	if (qcom_scm_restore_sec_cfg_available()) {
+		dev_dbg(dev, "configuring scm\n");
+		ret = qcom_scm_restore_sec_cfg(QCOM_SCM_OCMEM_DEV_ID, 0);
+		if (ret) {
+			dev_err(dev, "Could not enable secure configuration\n");
+			goto err_clk_disable;
+		}
+	}
+
+	reg = ocmem_read(ocmem, OCMEM_REG_HW_PROFILE);
+	ocmem->num_ports = OCMEM_HW_PROFILE_NUM_PORTS(reg);
+	ocmem->num_macros = OCMEM_HW_PROFILE_NUM_MACROS(reg);
+	ocmem->interleaved = !!(reg & OCMEM_HW_PROFILE_INTERLEAVING);
+
+	num_banks = ocmem->num_ports / 2;
+	region_size = ocmem->config->macro_size * num_banks;
+
+	dev_info(dev, "%u ports, %u regions, %u macros, %sinterleaved\n",
+		 ocmem->num_ports, ocmem->config->num_regions,
+		 ocmem->num_macros, ocmem->interleaved ? "" : "not ");
+
+	ocmem->regions = devm_kcalloc(dev, ocmem->config->num_regions,
+				      sizeof(struct ocmem_region), GFP_KERNEL);
+	if (!ocmem->regions) {
+		ret = -ENOMEM;
+		goto err_clk_disable;
+	}
+
+	for (i = 0; i < ocmem->config->num_regions; i++) {
+		struct ocmem_region *region = &ocmem->regions[i];
+
+		if (WARN_ON(num_banks > ARRAY_SIZE(region->macro_state))) {
+			ret = -EINVAL;
+			goto err_clk_disable;
+		}
+
+		region->mode = MODE_DEFAULT;
+		region->num_macros = num_banks;
+
+		if (i == (ocmem->config->num_regions - 1) &&
+		    reg & OCMEM_HW_PROFILE_LAST_REGN_HALFSIZE) {
+			region->macro_size = ocmem->config->macro_size / 2;
+			region->region_size = region_size / 2;
+		} else {
+			region->macro_size = ocmem->config->macro_size;
+			region->region_size = region_size;
+		}
+
+		for (j = 0; j < ARRAY_SIZE(region->macro_state); j++)
+			region->macro_state[j] = CLK_OFF;
+	}
+
+	platform_set_drvdata(pdev, ocmem);
+
+	return 0;
+
+err_clk_disable:
+	clk_bulk_disable_unprepare(ARRAY_SIZE(ocmem_clks), ocmem_clks);
+	return ret;
+}
+
+static int ocmem_dev_remove(struct platform_device *pdev)
+{
+	clk_bulk_disable_unprepare(ARRAY_SIZE(ocmem_clks), ocmem_clks);
+
+	return 0;
+}
+
+static const struct ocmem_config ocmem_8974_config = {
+	.num_regions = 3,
+	.macro_size = SZ_128K,
+};
+
+static const struct of_device_id ocmem_of_match[] = {
+	{ .compatible = "qcom,msm8974-ocmem", .data = &ocmem_8974_config },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, ocmem_of_match);
+
+static struct platform_driver ocmem_driver = {
+	.probe = ocmem_dev_probe,
+	.remove = ocmem_dev_remove,
+	.driver = {
+		.name = "ocmem",
+		.of_match_table = ocmem_of_match,
+	},
+};
+
+module_platform_driver(ocmem_driver);
+
+MODULE_DESCRIPTION("On Chip Memory (OCMEM) allocator for some Snapdragon SoCs");
+MODULE_LICENSE("GPL v2");