Merge tag 'drm-fixes-2024-02-09' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Regular weekly fixes, xe, amdgpu and msm are most of them, with some
  misc in i915, ivpu and nouveau, scattered but nothing too intense at
  this point.

  i915:
   - gvt: docs fix, uninit var, MAINTAINERS

  ivpu:
   - add aborted job status
   - disable d3 hot delay
   - mmu fixes

  nouveau:
   - fix gsp rpc size request
   - fix dma buffer leaks
   - use common code for gsp mem ctor

  xe:
   - Fix a loop in an error path
   - Fix a missing dma-fence reference
   - Fix a retry path on userptr REMAP
   - Workaround for a false gcc warning
   - Fix missing map of the usm batch buffer in the migrate vm.
   - Fix a memory leak.
   - Fix a bad assumption of used page size
   - Fix hitting a BUG() due to zero pages to map.
   - Remove some leftover async bind queue relics

  amdgpu:
   - Misc NULL/bounds check fixes
   - ODM pipe policy fix
   - Aborted suspend fixes
   - JPEG 4.0.5 fix
   - DCN 3.5 fixes
   - PSP fix
   - DP MST fix
   - Phantom pipe fix
   - VRAM vendor fix
   - Clang fix
   - SR-IOV fix

  msm:
   - DPU:
      - fix for kernel doc warnings and smatch warnings in dpu_encoder
      - fix for smatch warning in dpu_encoder
      - fix the bus bandwidth value for SDM670
   - DP:
      - fixes to handle unknown bpc case correctly for DP
      - fix for MISC0 programming
   - GPU:
      - dmabuf vmap fix
      - a610 UBWC corruption fix (incorrect hbb)
      - revert a commit that was making GPU recovery unreliable"

* tag 'drm-fixes-2024-02-09' of git://anongit.freedesktop.org/drm/drm: (43 commits)
  drm/xe: Remove TEST_VM_ASYNC_OPS_ERROR
  drm/xe/vm: don't ignore error when in_kthread
  drm/xe: Assume large page size if VMA not yet bound
  drm/xe/display: Fix memleak in display initialization
  drm/xe: Map both mem.kernel_bb_pool and usm.bb_pool
  drm/xe: circumvent bogus stringop-overflow warning
  drm/xe: Pick correct userptr VMA to repin on REMAP op failure
  drm/xe: Take a reference in xe_exec_queue_last_fence_get()
  drm/xe: Fix loop in vm_bind_ioctl_ops_unwind
  drm/amdgpu: Fix HDP flush for VFs on nbio v7.9
  drm/amd/display: Implement bounds check for stream encoder creation in DCN301
  drm/amd/display: Increase frame-larger-than for all display_mode_vba files
  drm/amd/display: Clear phantom stream count and plane count
  drm/amdgpu: Avoid fetching VRAM vendor info
  drm/amd/display: Disable ODM by default for DCN35
  drm/amd/display: Update phantom pipe enable / disable sequence
  drm/amd/display: Fix MST Null Ptr for RV
  drm/amdgpu: Fix shared buff copy to user
  drm/amd/display: Increase eval/entry delay for DCN35
  drm/amdgpu: remove asymmetrical irq disabling in jpeg 4.0.5 suspend
  ...

57 files changed, 390 insertions, 253 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 3dfe7ea25320c6..dc5ca7a042b51f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10801,11 +10801,11 @@ F:	drivers/gpio/gpio-tangier.h
 
 INTEL GVT-g DRIVERS (Intel GPU Virtualization)
 M:	Zhenyu Wang <zhenyuw@linux.intel.com>
-M:	Zhi Wang <zhi.a.wang@intel.com>
+M:	Zhi Wang <zhi.wang.linux@gmail.com>
 L:	intel-gvt-dev@lists.freedesktop.org
 L:	intel-gfx@lists.freedesktop.org
 S:	Supported
-W:	https://01.org/igvt-g
+W:	https://github.com/intel/gvt-linux/wiki
 T:	git https://github.com/intel/gvt-linux.git
 F:	drivers/gpu/drm/i915/gvt/
 
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 9418c73ee8ef8b..4b064022698693 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -480,9 +480,8 @@ static int ivpu_pci_init(struct ivpu_device *vdev)
 	/* Clear any pending errors */
 	pcie_capability_clear_word(pdev, PCI_EXP_DEVSTA, 0x3f);
 
-	/* VPU 37XX does not require 10m D3hot delay */
-	if (ivpu_hw_gen(vdev) == IVPU_HW_37XX)
-		pdev->d3hot_delay = 0;
+	/* NPU does not require 10m D3hot delay */
+	pdev->d3hot_delay = 0;
 
 	ret = pcim_enable_device(pdev);
 	if (ret) {
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index 6576232f3e678e..5fa8bd4603d5be 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -222,7 +222,6 @@ ivpu_fw_init_wa(struct ivpu_device *vdev)
 	const struct vpu_firmware_header *fw_hdr = (const void *)vdev->fw->file->data;
 
 	if (IVPU_FW_CHECK_API_VER_LT(vdev, fw_hdr, BOOT, 3, 17) ||
-	    (ivpu_hw_gen(vdev) > IVPU_HW_37XX) ||
 	    (ivpu_test_mode & IVPU_TEST_MODE_D0I3_MSG_DISABLE))
 		vdev->wa.disable_d0i3_msg = true;
 
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index f15a93d8305782..77accd029c4a71 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -525,7 +525,7 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
 	u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES);
 
 	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, NOSNOOP_OVERRIDE_EN, val);
-	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
+	val = REG_CLR_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
 	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AR_NOSNOOP_OVERRIDE, val);
 
 	REGV_WR32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, val);
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index 704288084f3737..1c995307c11388 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -530,7 +530,7 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
 	u32 val = REGV_RD32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES);
 
 	val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, SNOOP_OVERRIDE_EN, val);
-	val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
+	val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
 	val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AR_SNOOP_OVERRIDE, val);
 
 	REGV_WR32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, val);
@@ -704,7 +704,6 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev)
 {
 	struct ivpu_hw_info *hw = vdev->hw;
 	u32 tile_disable;
-	u32 tile_enable;
 	u32 fuse;
 
 	fuse = REGB_RD32(VPU_40XX_BUTTRESS_TILE_FUSE);
@@ -725,10 +724,6 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev)
 	else
 		ivpu_dbg(vdev, MISC, "Fuse: All %d tiles enabled\n", TILE_MAX_NUM);
 
-	tile_enable = (~tile_disable) & TILE_MAX_MASK;
-
-	hw->sku = REG_SET_FLD_NUM(SKU, HW_ID, LNL_HW_ID, hw->sku);
-	hw->sku = REG_SET_FLD_NUM(SKU, TILE, tile_enable, hw->sku);
 	hw->tile_fuse = tile_disable;
 	hw->pll.profiling_freq = PLL_PROFILING_FREQ_DEFAULT;
 
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 0440bee3ecafd5..e70cfb8593390e 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -294,7 +294,7 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32
 		return -ENOENT;
 
 	if (job->file_priv->has_mmu_faults)
-		job_status = VPU_JSM_STATUS_ABORTED;
+		job_status = DRM_IVPU_JOB_STATUS_ABORTED;
 
 	job->bos[CMD_BUF_IDX]->job_status = job_status;
 	dma_fence_signal(job->done_fence);
@@ -315,7 +315,7 @@ void ivpu_jobs_abort_all(struct ivpu_device *vdev)
 	unsigned long id;
 
 	xa_for_each(&vdev->submitted_jobs_xa, id, job)
-		ivpu_job_signal_and_destroy(vdev, id, VPU_JSM_STATUS_ABORTED);
+		ivpu_job_signal_and_destroy(vdev, id, DRM_IVPU_JOB_STATUS_ABORTED);
 }
 
 static int ivpu_job_submit(struct ivpu_job *job)
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 9a3122ffce03c1..91bd640655ab36 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -72,10 +72,10 @@
 
 #define IVPU_MMU_Q_COUNT_LOG2		4 /* 16 entries */
 #define IVPU_MMU_Q_COUNT		((u32)1 << IVPU_MMU_Q_COUNT_LOG2)
-#define IVPU_MMU_Q_WRAP_BIT		(IVPU_MMU_Q_COUNT << 1)
-#define IVPU_MMU_Q_WRAP_MASK		(IVPU_MMU_Q_WRAP_BIT - 1)
-#define IVPU_MMU_Q_IDX_MASK		(IVPU_MMU_Q_COUNT - 1)
+#define IVPU_MMU_Q_WRAP_MASK            GENMASK(IVPU_MMU_Q_COUNT_LOG2, 0)
+#define IVPU_MMU_Q_IDX_MASK             (IVPU_MMU_Q_COUNT - 1)
 #define IVPU_MMU_Q_IDX(val)		((val) & IVPU_MMU_Q_IDX_MASK)
+#define IVPU_MMU_Q_WRP(val)             ((val) & IVPU_MMU_Q_COUNT)
 
 #define IVPU_MMU_CMDQ_CMD_SIZE		16
 #define IVPU_MMU_CMDQ_SIZE		(IVPU_MMU_Q_COUNT * IVPU_MMU_CMDQ_CMD_SIZE)
@@ -475,20 +475,32 @@ static int ivpu_mmu_cmdq_wait_for_cons(struct ivpu_device *vdev)
 	return 0;
 }
 
+static bool ivpu_mmu_queue_is_full(struct ivpu_mmu_queue *q)
+{
+	return ((IVPU_MMU_Q_IDX(q->prod) == IVPU_MMU_Q_IDX(q->cons)) &&
+		(IVPU_MMU_Q_WRP(q->prod) != IVPU_MMU_Q_WRP(q->cons)));
+}
+
+static bool ivpu_mmu_queue_is_empty(struct ivpu_mmu_queue *q)
+{
+	return ((IVPU_MMU_Q_IDX(q->prod) == IVPU_MMU_Q_IDX(q->cons)) &&
+		(IVPU_MMU_Q_WRP(q->prod) == IVPU_MMU_Q_WRP(q->cons)));
+}
+
 static int ivpu_mmu_cmdq_cmd_write(struct ivpu_device *vdev, const char *name, u64 data0, u64 data1)
 {
-	struct ivpu_mmu_queue *q = &vdev->mmu->cmdq;
-	u64 *queue_buffer = q->base;
-	int idx = IVPU_MMU_Q_IDX(q->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer));
+	struct ivpu_mmu_queue *cmdq = &vdev->mmu->cmdq;
+	u64 *queue_buffer = cmdq->base;
+	int idx = IVPU_MMU_Q_IDX(cmdq->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer));
 
-	if (!CIRC_SPACE(IVPU_MMU_Q_IDX(q->prod), IVPU_MMU_Q_IDX(q->cons), IVPU_MMU_Q_COUNT)) {
+	if (ivpu_mmu_queue_is_full(cmdq)) {
 		ivpu_err(vdev, "Failed to write MMU CMD %s\n", name);
 		return -EBUSY;
 	}
 
 	queue_buffer[idx] = data0;
 	queue_buffer[idx + 1] = data1;
-	q->prod = (q->prod + 1) & IVPU_MMU_Q_WRAP_MASK;
+	cmdq->prod = (cmdq->prod + 1) & IVPU_MMU_Q_WRAP_MASK;
 
 	ivpu_dbg(vdev, MMU, "CMD write: %s data: 0x%llx 0x%llx\n", name, data0, data1);
 
@@ -560,7 +572,6 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev)
 	mmu->cmdq.cons = 0;
 
 	memset(mmu->evtq.base, 0, IVPU_MMU_EVTQ_SIZE);
-	clflush_cache_range(mmu->evtq.base, IVPU_MMU_EVTQ_SIZE);
 	mmu->evtq.prod = 0;
 	mmu->evtq.cons = 0;
 
@@ -874,14 +885,10 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev)
 	u32 *evt = evtq->base + (idx * IVPU_MMU_EVTQ_CMD_SIZE);
 
 	evtq->prod = REGV_RD32(IVPU_MMU_REG_EVTQ_PROD_SEC);
-	if (!CIRC_CNT(IVPU_MMU_Q_IDX(evtq->prod), IVPU_MMU_Q_IDX(evtq->cons), IVPU_MMU_Q_COUNT))
+	if (ivpu_mmu_queue_is_empty(evtq))
 		return NULL;
 
-	clflush_cache_range(evt, IVPU_MMU_EVTQ_CMD_SIZE);
-
 	evtq->cons = (evtq->cons + 1) & IVPU_MMU_Q_WRAP_MASK;
-	REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, evtq->cons);
-
 	return evt;
 }
 
@@ -902,6 +909,7 @@ void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev)
 		}
 
 		ivpu_mmu_user_context_mark_invalid(vdev, ssid);
+		REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, vdev->mmu->evtq.cons);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 3d8a48f46b0156..6dce81a061ab1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1078,6 +1078,8 @@ struct amdgpu_device {
 	bool				in_s3;
 	bool				in_s4;
 	bool				in_s0ix;
+	/* indicate amdgpu suspension status */
+	bool				suspend_complete;
 
 	enum pp_mp1_state               mp1_state;
 	struct amdgpu_doorbell_index doorbell_index;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 971acf01bea606..211501ea91694d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2476,6 +2476,7 @@ static int amdgpu_pmops_suspend(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 
+	adev->suspend_complete = false;
 	if (amdgpu_acpi_is_s0ix_active(adev))
 		adev->in_s0ix = true;
 	else if (amdgpu_acpi_is_s3_active(adev))
@@ -2490,6 +2491,7 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 
+	adev->suspend_complete = true;
 	if (amdgpu_acpi_should_gpu_reset(adev))
 		return amdgpu_asic_reset(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
index 468a67b302d4c1..ca5c86e5f7cd67 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
@@ -362,7 +362,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 		}
 	}
 
-	if (copy_to_user((char *)buf, context->mem_context.shared_buf, shared_buf_len))
+	if (copy_to_user((char *)&buf[copy_pos], context->mem_context.shared_buf, shared_buf_len))
 		ret = -EFAULT;
 
 err_free_shared_buf:
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 69c50091074601..3bc6943365a4ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3034,6 +3034,14 @@ static int gfx_v9_0_cp_gfx_start(struct amdgpu_device *adev)
 
 	gfx_v9_0_cp_gfx_enable(adev, true);
 
+	/* Now only limit the quirk on the APU gfx9 series and already
+	 * confirmed that the APU gfx10/gfx11 needn't such update.
+	 */
+	if (adev->flags & AMD_IS_APU &&
+			adev->in_s3 && !adev->suspend_complete) {
+		DRM_INFO(" Will skip the CSB packet resubmit\n");
+		return 0;
+	}
 	r = amdgpu_ring_alloc(ring, gfx_v9_0_get_csb_size(adev) + 4 + 3);
 	if (r) {
 		DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 40a00ea0009f6a..e67a62db9e1262 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1947,14 +1947,6 @@ static int gmc_v9_0_init_mem_ranges(struct amdgpu_device *adev)
 
 static void gmc_v9_4_3_init_vram_info(struct amdgpu_device *adev)
 {
-	static const u32 regBIF_BIOS_SCRATCH_4 = 0x50;
-	u32 vram_info;
-
-	/* Only for dGPU, vendor informaton is reliable */
-	if (!amdgpu_sriov_vf(adev) && !(adev->flags & AMD_IS_APU)) {
-		vram_info = RREG32(regBIF_BIOS_SCRATCH_4);
-		adev->gmc.vram_vendor = vram_info & 0xF;
-	}
 	adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM;
 	adev->gmc.vram_width = 128 * 64;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
index bc38b90f8cf88e..88ea58d5c4abf5 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
@@ -674,14 +674,6 @@ static int jpeg_v4_0_set_powergating_state(void *handle,
 	return ret;
 }
 
-static int jpeg_v4_0_set_interrupt_state(struct amdgpu_device *adev,
-					struct amdgpu_irq_src *source,
-					unsigned type,
-					enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
 static int jpeg_v4_0_set_ras_interrupt_state(struct amdgpu_device *adev,
 					struct amdgpu_irq_src *source,
 					unsigned int type,
@@ -765,7 +757,6 @@ static void jpeg_v4_0_set_dec_ring_funcs(struct amdgpu_device *adev)
 }
 
 static const struct amdgpu_irq_src_funcs jpeg_v4_0_irq_funcs = {
-	.set = jpeg_v4_0_set_interrupt_state,
 	.process = jpeg_v4_0_process_interrupt,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
index 6ede85b28cc8c0..78b74daf4eebfc 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
@@ -181,7 +181,6 @@ static int jpeg_v4_0_5_hw_fini(void *handle)
 			RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS))
 			jpeg_v4_0_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
 	}
-	amdgpu_irq_put(adev, &adev->jpeg.inst->irq, 0);
 
 	return 0;
 }
@@ -516,14 +515,6 @@ static int jpeg_v4_0_5_set_powergating_state(void *handle,
 	return ret;
 }
 
-static int jpeg_v4_0_5_set_interrupt_state(struct amdgpu_device *adev,
-					struct amdgpu_irq_src *source,
-					unsigned type,
-					enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
 static int jpeg_v4_0_5_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
@@ -603,7 +594,6 @@ static void jpeg_v4_0_5_set_dec_ring_funcs(struct amdgpu_device *adev)
 }
 
 static const struct amdgpu_irq_src_funcs jpeg_v4_0_5_irq_funcs = {
-	.set = jpeg_v4_0_5_set_interrupt_state,
 	.process = jpeg_v4_0_5_process_interrupt,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index e90f3378080345..b4723d68eab0f9 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -431,6 +431,12 @@ static void nbio_v7_9_init_registers(struct amdgpu_device *adev)
 	u32 inst_mask;
 	int i;
 
+	if (amdgpu_sriov_vf(adev))
+		adev->rmmio_remap.reg_offset =
+			SOC15_REG_OFFSET(
+				NBIO, 0,
+				regBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL)
+			<< 2;
 	WREG32_SOC15(NBIO, 0, regXCC_DOORBELL_FENCE,
 		0xff & ~(adev->gfx.xcc_mask));
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 15033efec2bac0..c64c01e2944a2e 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1298,10 +1298,32 @@ static int soc15_common_suspend(void *handle)
 	return soc15_common_hw_fini(adev);
 }
 
+static bool soc15_need_reset_on_resume(struct amdgpu_device *adev)
+{
+	u32 sol_reg;
+
+	sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
+
+	/* Will reset for the following suspend abort cases.
+	 * 1) Only reset limit on APU side, dGPU hasn't checked yet.
+	 * 2) S3 suspend abort and TOS already launched.
+	 */
+	if (adev->flags & AMD_IS_APU && adev->in_s3 &&
+			!adev->suspend_complete &&
+			sol_reg)
+		return true;
+
+	return false;
+}
+
 static int soc15_common_resume(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (soc15_need_reset_on_resume(adev)) {
+		dev_info(adev->dev, "S3 suspend abort case, let's reset ASIC.\n");
+		soc15_asic_reset(adev);
+	}
 	return soc15_common_hw_init(adev);
 }
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d292f290cd6ebb..59d2eee72a3297 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -10731,11 +10731,13 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 			goto fail;
 		}
 
-		ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
-		if (ret) {
-			DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
-			ret = -EINVAL;
-			goto fail;
+		if (dc_resource_is_dsc_encoding_supported(dc)) {
+			ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
+			if (ret) {
+				DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
+				ret = -EINVAL;
+				goto fail;
+			}
 		}
 
 		ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context, vars);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index aa7c02ba948e9c..2c424e435962d4 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -3817,7 +3817,9 @@ static void commit_planes_for_stream(struct dc *dc,
 		 * programming has completed (we turn on phantom OTG in order
 		 * to complete the plane disable for phantom pipes).
 		 */
-		dc->hwss.apply_ctx_to_hw(dc, context);
+
+		if (dc->hwss.disable_phantom_streams)
+			dc->hwss.disable_phantom_streams(dc, context);
 	}
 
 	if (update_type != UPDATE_TYPE_FAST)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
index 88c6436b28b69c..180ac47868c22a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
@@ -291,11 +291,14 @@ void dc_state_destruct(struct dc_state *state)
 		dc_stream_release(state->phantom_streams[i]);
 		state->phantom_streams[i] = NULL;
 	}
+	state->phantom_stream_count = 0;
 
 	for (i = 0; i < state->phantom_plane_count; i++) {
 		dc_plane_state_release(state->phantom_planes[i]);
 		state->phantom_planes[i] = NULL;
 	}
+	state->phantom_plane_count = 0;
+
 	state->stream_mask = 0;
 	memset(&state->res_ctx, 0, sizeof(state->res_ctx));
 	memset(&state->pp_display_cfg, 0, sizeof(state->pp_display_cfg));
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 6042a5a6a44f8c..59ade76ffb18d5 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -72,11 +72,11 @@ CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index dd781a20692ee6..ba76dd4a2ce29a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -1288,7 +1288,7 @@ static bool update_pipes_with_split_flags(struct dc *dc, struct dc_state *contex
 	return updated;
 }
 
-static bool should_allow_odm_power_optimization(struct dc *dc,
+static bool should_apply_odm_power_optimization(struct dc *dc,
 		struct dc_state *context, struct vba_vars_st *v, int *split,
 		bool *merge)
 {
@@ -1392,9 +1392,12 @@ static void try_odm_power_optimization_and_revalidate(
 {
 	int i;
 	unsigned int new_vlevel;
+	unsigned int cur_policy[MAX_PIPES];
 
-	for (i = 0; i < pipe_cnt; i++)
+	for (i = 0; i < pipe_cnt; i++) {
+		cur_policy[i] = pipes[i].pipe.dest.odm_combine_policy;
 		pipes[i].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1;
+	}
 
 	new_vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, pipe_cnt);
 
@@ -1403,6 +1406,9 @@ static void try_odm_power_optimization_and_revalidate(
 		memset(merge, 0, MAX_PIPES * sizeof(bool));
 		*vlevel = dcn20_validate_apply_pipe_split_flags(dc, context, new_vlevel, split, merge);
 		context->bw_ctx.dml.vba.VoltageLevel = *vlevel;
+	} else {
+		for (i = 0; i < pipe_cnt; i++)
+			pipes[i].pipe.dest.odm_combine_policy = cur_policy[i];
 	}
 }
 
@@ -1580,7 +1586,7 @@ static void dcn32_full_validate_bw_helper(struct dc *dc,
 		}
 	}
 
-	if (should_allow_odm_power_optimization(dc, context, vba, split, merge))
+	if (should_apply_odm_power_optimization(dc, context, vba, split, merge))
 		try_odm_power_optimization_and_revalidate(
 				dc, context, pipes, split, merge, vlevel, *pipe_cnt);
 
@@ -2209,7 +2215,8 @@ bool dcn32_internal_validate_bw(struct dc *dc,
 		int i;
 
 		pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate);
-		dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes);
+		if (!dc->config.enable_windowed_mpo_odm)
+			dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes);
 
 		/* repopulate_pipes = 1 means the pipes were either split or merged. In this case
 		 * we have to re-calculate the DET allocation and run through DML once more to
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index 2352428bcea3ca..01493c49bd7a08 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1476,7 +1476,7 @@ static enum dc_status dce110_enable_stream_timing(
 	return DC_OK;
 }
 
-static enum dc_status apply_single_controller_ctx_to_hw(
+enum dc_status dce110_apply_single_controller_ctx_to_hw(
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context,
 		struct dc *dc)
@@ -2302,7 +2302,7 @@ enum dc_status dce110_apply_ctx_to_hw(
 		if (pipe_ctx->top_pipe || pipe_ctx->prev_odm_pipe)
 			continue;
 
-		status = apply_single_controller_ctx_to_hw(
+		status = dce110_apply_single_controller_ctx_to_hw(
 				pipe_ctx,
 				context,
 				dc);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
index 08028a1779ae81..ed3cc3648e8e23 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
@@ -39,6 +39,10 @@ enum dc_status dce110_apply_ctx_to_hw(
 		struct dc *dc,
 		struct dc_state *context);
 
+enum dc_status dce110_apply_single_controller_ctx_to_hw(
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context,
+		struct dc *dc);
 
 void dce110_enable_stream(struct pipe_ctx *pipe_ctx);
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
index 4853ecac53f91f..931ac8ed7069d7 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
@@ -2561,7 +2561,7 @@ void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx)
 		tg->funcs->setup_vertical_interrupt2(tg, start_line);
 }
 
-static void dcn20_reset_back_end_for_pipe(
+void dcn20_reset_back_end_for_pipe(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
index b94c85340abff7..d950b3e54ec2c7 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
@@ -84,6 +84,10 @@ enum dc_status dcn20_enable_stream_timing(
 void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
 void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
 void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_reset_back_end_for_pipe(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context);
 void dcn20_init_blank(
 		struct dc *dc,
 		struct timing_generator *tg);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
index 8e88dcaf88f5b2..5c7f380a84f91e 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
@@ -206,28 +206,32 @@ void dcn21_set_abm_immediate_disable(struct pipe_ctx *pipe_ctx)
 void dcn21_set_pipe(struct pipe_ctx *pipe_ctx)
 {
 	struct abm *abm = pipe_ctx->stream_res.abm;
-	uint32_t otg_inst = pipe_ctx->stream_res.tg->inst;
+	struct timing_generator *tg = pipe_ctx->stream_res.tg;
 	struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl;
 	struct dmcu *dmcu = pipe_ctx->stream->ctx->dc->res_pool->dmcu;
+	uint32_t otg_inst;
+
+	if (!abm && !tg && !panel_cntl)
+		return;
+
+	otg_inst = tg->inst;
 
 	if (dmcu) {
 		dce110_set_pipe(pipe_ctx);
 		return;
 	}
 
-	if (abm && panel_cntl) {
-		if (abm->funcs && abm->funcs->set_pipe_ex) {
-			abm->funcs->set_pipe_ex(abm,
+	if (abm->funcs && abm->funcs->set_pipe_ex) {
+		abm->funcs->set_pipe_ex(abm,
 					otg_inst,
 					SET_ABM_PIPE_NORMAL,
 					panel_cntl->inst,
 					panel_cntl->pwrseq_inst);
-		} else {
-				dmub_abm_set_pipe(abm, otg_inst,
-						SET_ABM_PIPE_NORMAL,
-						panel_cntl->inst,
-						panel_cntl->pwrseq_inst);
-		}
+	} else {
+		dmub_abm_set_pipe(abm, otg_inst,
+				  SET_ABM_PIPE_NORMAL,
+				  panel_cntl->inst,
+				  panel_cntl->pwrseq_inst);
 	}
 }
 
@@ -237,34 +241,35 @@ bool dcn21_set_backlight_level(struct pipe_ctx *pipe_ctx,
 {
 	struct dc_context *dc = pipe_ctx->stream->ctx;
 	struct abm *abm = pipe_ctx->stream_res.abm;
+	struct timing_generator *tg = pipe_ctx->stream_res.tg;
 	struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl;
+	uint32_t otg_inst;
+
+	if (!abm && !tg && !panel_cntl)
+		return false;
+
+	otg_inst = tg->inst;
 
 	if (dc->dc->res_pool->dmcu) {
 		dce110_set_backlight_level(pipe_ctx, backlight_pwm_u16_16, frame_ramp);
 		return true;
 	}
 
-	if (abm != NULL) {
-		uint32_t otg_inst = pipe_ctx->stream_res.tg->inst;
-
-		if (abm && panel_cntl) {
-			if (abm->funcs && abm->funcs->set_pipe_ex) {
-				abm->funcs->set_pipe_ex(abm,
-						otg_inst,
-						SET_ABM_PIPE_NORMAL,
-						panel_cntl->inst,
-						panel_cntl->pwrseq_inst);
-			} else {
-					dmub_abm_set_pipe(abm,
-							otg_inst,
-							SET_ABM_PIPE_NORMAL,
-							panel_cntl->inst,
-							panel_cntl->pwrseq_inst);
-			}
-		}
+	if (abm->funcs && abm->funcs->set_pipe_ex) {
+		abm->funcs->set_pipe_ex(abm,
+					otg_inst,
+					SET_ABM_PIPE_NORMAL,
+					panel_cntl->inst,
+					panel_cntl->pwrseq_inst);
+	} else {
+		dmub_abm_set_pipe(abm,
+				  otg_inst,
+				  SET_ABM_PIPE_NORMAL,
+				  panel_cntl->inst,
+				  panel_cntl->pwrseq_inst);
 	}
 
-	if (abm && abm->funcs && abm->funcs->set_backlight_level_pwm)
+	if (abm->funcs && abm->funcs->set_backlight_level_pwm)
 		abm->funcs->set_backlight_level_pwm(abm, backlight_pwm_u16_16,
 			frame_ramp, 0, panel_cntl->inst);
 	else
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
index 6c9299c7683df1..aa36d7a56ca8c3 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
@@ -1474,9 +1474,44 @@ void dcn32_update_dsc_pg(struct dc *dc,
 	}
 }
 
+void dcn32_disable_phantom_streams(struct dc *dc, struct dc_state *context)
+{
+	struct dce_hwseq *hws = dc->hwseq;
+	int i;
+
+	for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) {
+		struct pipe_ctx *pipe_ctx_old =
+			&dc->current_state->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (!pipe_ctx_old->stream)
+			continue;
+
+		if (dc_state_get_pipe_subvp_type(dc->current_state, pipe_ctx_old) != SUBVP_PHANTOM)
+			continue;
+
+		if (pipe_ctx_old->top_pipe || pipe_ctx_old->prev_odm_pipe)
+			continue;
+
+		if (!pipe_ctx->stream || pipe_need_reprogram(pipe_ctx_old, pipe_ctx) ||
+				(pipe_ctx->stream && dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM)) {
+			struct clock_source *old_clk = pipe_ctx_old->clock_source;
+
+			if (hws->funcs.reset_back_end_for_pipe)
+				hws->funcs.reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state);
+			if (hws->funcs.enable_stream_gating)
+				hws->funcs.enable_stream_gating(dc, pipe_ctx_old);
+			if (old_clk)
+				old_clk->funcs->cs_power_down(old_clk);
+		}
+	}
+}
+
 void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context)
 {
 	unsigned int i;
+	enum dc_status status = DC_OK;
+	struct dce_hwseq *hws = dc->hwseq;
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
@@ -1497,16 +1532,39 @@ void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context)
 		}
 	}
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
-
-		if (new_pipe->stream && dc_state_get_pipe_subvp_type(context, new_pipe) == SUBVP_PHANTOM) {
-			// If old context or new context has phantom pipes, apply
-			// the phantom timings now. We can't change the phantom
-			// pipe configuration safely without driver acquiring
-			// the DMCUB lock first.
-			dc->hwss.apply_ctx_to_hw(dc, context);
-			break;
+		struct pipe_ctx *pipe_ctx_old =
+					&dc->current_state->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (pipe_ctx->stream == NULL)
+			continue;
+
+		if (dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM)
+			continue;
+
+		if (pipe_ctx->stream == pipe_ctx_old->stream &&
+			pipe_ctx->stream->link->link_state_valid) {
+			continue;
 		}
+
+		if (pipe_ctx_old->stream && !pipe_need_reprogram(pipe_ctx_old, pipe_ctx))
+			continue;
+
+		if (pipe_ctx->top_pipe || pipe_ctx->prev_odm_pipe)
+			continue;
+
+		if (hws->funcs.apply_single_controller_ctx_to_hw)
+			status = hws->funcs.apply_single_controller_ctx_to_hw(
+					pipe_ctx,
+					context,
+					dc);
+
+		ASSERT(status == DC_OK);
+
+#ifdef CONFIG_DRM_AMD_DC_FP
+		if (hws->funcs.resync_fifo_dccg_dio)
+			hws->funcs.resync_fifo_dccg_dio(hws, dc, context);
+#endif
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
index cecf7f0f567190..069e20bc87c0a7 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
@@ -111,6 +111,8 @@ void dcn32_update_dsc_pg(struct dc *dc,
 
 void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context);
 
+void dcn32_disable_phantom_streams(struct dc *dc, struct dc_state *context);
+
 void dcn32_init_blank(
 		struct dc *dc,
 		struct timing_generator *tg);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
index 427cfc8c24a4b7..e8ac94a005b83a 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
@@ -109,6 +109,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = {
 	.get_dcc_en_bits = dcn10_get_dcc_en_bits,
 	.commit_subvp_config = dcn32_commit_subvp_config,
 	.enable_phantom_streams = dcn32_enable_phantom_streams,
+	.disable_phantom_streams = dcn32_disable_phantom_streams,
 	.subvp_pipe_control_lock = dcn32_subvp_pipe_control_lock,
 	.update_visual_confirm_color = dcn10_update_visual_confirm_color,
 	.subvp_pipe_control_lock_fast = dcn32_subvp_pipe_control_lock_fast,
@@ -159,6 +160,8 @@ static const struct hwseq_private_funcs dcn32_private_funcs = {
 	.set_pixels_per_cycle = dcn32_set_pixels_per_cycle,
 	.resync_fifo_dccg_dio = dcn32_resync_fifo_dccg_dio,
 	.is_dp_dig_pixel_rate_div_policy = dcn32_is_dp_dig_pixel_rate_div_policy,
+	.apply_single_controller_ctx_to_hw = dce110_apply_single_controller_ctx_to_hw,
+	.reset_back_end_for_pipe = dcn20_reset_back_end_for_pipe,
 };
 
 void dcn32_hw_sequencer_init_functions(struct dc *dc)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
index a5439938331814..64ca7c66509b79 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
@@ -379,6 +379,7 @@ struct hw_sequencer_funcs {
 			struct dc_cursor_attributes *cursor_attr);
 	void (*commit_subvp_config)(struct dc *dc, struct dc_state *context);
 	void (*enable_phantom_streams)(struct dc *dc, struct dc_state *context);
+	void (*disable_phantom_streams)(struct dc *dc, struct dc_state *context);
 	void (*subvp_pipe_control_lock)(struct dc *dc,
 			struct dc_state *context,
 			bool lock,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
index 6137cf09aa54d2..b3c62a82cb1cf1 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
@@ -165,8 +165,15 @@ struct hwseq_private_funcs {
 	void (*set_pixels_per_cycle)(struct pipe_ctx *pipe_ctx);
 	void (*resync_fifo_dccg_dio)(struct dce_hwseq *hws, struct dc *dc,
 			struct dc_state *context);
+	enum dc_status (*apply_single_controller_ctx_to_hw)(
+			struct pipe_ctx *pipe_ctx,
+			struct dc_state *context,
+			struct dc *dc);
 	bool (*is_dp_dig_pixel_rate_div_policy)(struct pipe_ctx *pipe_ctx);
 #endif
+	void (*reset_back_end_for_pipe)(struct dc *dc,
+			struct pipe_ctx *pipe_ctx,
+			struct dc_state *context);
 };
 
 struct dce_hwseq {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index c958ef37b78a66..77a60aa9f27bbf 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -427,22 +427,18 @@ struct pipe_ctx *resource_get_primary_dpp_pipe(const struct pipe_ctx *dpp_pipe);
 int resource_get_mpc_slice_index(const struct pipe_ctx *dpp_pipe);
 
 /*
- * Get number of MPC "cuts" of the plane associated with the pipe. MPC slice
- * count is equal to MPC splits + 1. For example if a plane is cut 3 times, it
- * will have 4 pieces of slice.
- * return - 0 if pipe is not used for a plane with MPCC combine. otherwise
- * the number of MPC "cuts" for the plane.
+ * Get the number of MPC slices associated with the pipe.
+ * The function returns 0 if the pipe is not associated with an MPC combine
+ * pipe topology.
  */
-int resource_get_mpc_slice_count(const struct pipe_ctx *opp_head);
+int resource_get_mpc_slice_count(const struct pipe_ctx *pipe);
 
 /*
- * Get number of ODM "cuts" of the timing associated with the pipe. ODM slice
- * count is equal to ODM splits + 1. For example if a timing is cut 3 times, it
- * will have 4 pieces of slice.
- * return - 0 if pipe is not used for ODM combine. otherwise
- * the number of ODM "cuts" for the timing.
+ * Get the number of ODM slices associated with the pipe.
+ * The function returns 0 if the pipe is not associated with an ODM combine
+ * pipe topology.
  */
-int resource_get_odm_slice_count(const struct pipe_ctx *otg_master);
+int resource_get_odm_slice_count(const struct pipe_ctx *pipe);
 
 /* Get the ODM slice index counting from 0 from left most slice */
 int resource_get_odm_slice_index(const struct pipe_ctx *opp_head);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
index 511ff6b5b98567..7538b548c57251 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
@@ -999,7 +999,7 @@ static struct stream_encoder *dcn301_stream_encoder_create(enum engine_id eng_id
 	vpg = dcn301_vpg_create(ctx, vpg_inst);
 	afmt = dcn301_afmt_create(ctx, afmt_inst);
 
-	if (!enc1 || !vpg || !afmt) {
+	if (!enc1 || !vpg || !afmt || eng_id >= ARRAY_SIZE(stream_enc_regs)) {
 		kfree(enc1);
 		kfree(vpg);
 		kfree(afmt);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
index c4d71e7f18af47..6f10052caeef02 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
@@ -1829,7 +1829,21 @@ int dcn32_populate_dml_pipes_from_context(
 		dcn32_zero_pipe_dcc_fraction(pipes, pipe_cnt);
 		DC_FP_END();
 		pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch;
-		pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+		if (dc->config.enable_windowed_mpo_odm &&
+				dc->debug.enable_single_display_2to1_odm_policy) {
+			switch (resource_get_odm_slice_count(pipe)) {
+			case 2:
+				pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1;
+				break;
+			case 4:
+				pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_4to1;
+				break;
+			default:
+				pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+			}
+		} else {
+			pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+		}
 		pipes[pipe_cnt].pipe.src.gpuvm_min_page_size_kbytes = 256; // according to spreadsheet
 		pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
 		pipes[pipe_cnt].pipe.scale_ratio_depth.lb_depth = dm_lb_19;
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 761ec989187568..1c3d89264ef72c 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
@@ -780,8 +780,8 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.disable_z10 = false,
 	.ignore_pg = true,
 	.psp_disabled_wa = true,
-	.ips2_eval_delay_us = 200,
-	.ips2_entry_delay_us = 400,
+	.ips2_eval_delay_us = 1650,
+	.ips2_entry_delay_us = 800,
 	.static_screen_wait_frames = 2,
 };
 
@@ -2130,6 +2130,7 @@ static bool dcn35_resource_construct(
 	dc->dml2_options.dcn_pipe_count = pool->base.pipe_count;
 	dc->dml2_options.use_native_pstate_optimization = true;
 	dc->dml2_options.use_native_soc_bb_construction = true;
+	dc->dml2_options.minimize_dispclk_using_odm = false;
 	if (dc->config.EnableMinDispClkODM)
 		dc->dml2_options.minimize_dispclk_using_odm = true;
 	dc->dml2_options.enable_windowed_mpo_odm = dc->config.enable_windowed_mpo_odm;
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index b5d6e3352071f5..3089029abba481 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -140,7 +140,7 @@ config DRM_I915_GVT_KVMGT
 
 	  Note that this driver only supports newer device from Broadwell on.
 	  For further information and setup guide, you can visit:
-	  http://01.org/igvt-g.
+	  https://github.com/intel/gvt-linux/wiki.
 
 	  If in doubt, say "N".
 
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 90f6c1ece57d44..efcb00472be247 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -2849,8 +2849,7 @@ static int handle_mmio(struct intel_gvt_mmio_table_iter *iter, u32 offset,
 	for (i = start; i < end; i += 4) {
 		p = intel_gvt_find_mmio_info(gvt, i);
 		if (p) {
-			WARN(1, "dup mmio definition offset %x\n",
-				info->offset);
+			WARN(1, "dup mmio definition offset %x\n", i);
 
 			/* We return -EEXIST here to make GVT-g load fail.
 			 * So duplicated MMIO can be found as soon as
diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c
index e98b6d69a91ab7..9b6d87c8b5831c 100644
--- a/drivers/gpu/drm/i915/intel_gvt.c
+++ b/drivers/gpu/drm/i915/intel_gvt.c
@@ -41,7 +41,7 @@
  * To virtualize GPU resources GVT-g driver depends on hypervisor technology
  * e.g KVM/VFIO/mdev, Xen, etc. to provide resource access trapping capability
  * and be virtualized within GVT-g device module. More architectural design
- * doc is available on https://01.org/group/2230/documentation-list.
+ * doc is available on https://github.com/intel/gvt-linux/wiki.
  */
 
 static LIST_HEAD(intel_gvt_devices);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 83380bc92a00a9..6a4b489d44e517 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -144,10 +144,6 @@ enum dpu_enc_rc_states {
  *			to track crtc in the disable() hook which is called
  *			_after_ encoder_mask is cleared.
  * @connector:		If a mode is set, cached pointer to the active connector
- * @crtc_kickoff_cb:		Callback into CRTC that will flush & start
- *				all CTL paths
- * @crtc_kickoff_cb_data:	Opaque user data given to crtc_kickoff_cb
- * @debugfs_root:		Debug file system root file node
  * @enc_lock:			Lock around physical encoder
  *				create/destroy/enable/disable
  * @frame_busy_mask:		Bitmask tracking which phys_enc we are still
@@ -2072,7 +2068,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 	}
 
 	/* reset the merge 3D HW block */
-	if (phys_enc->hw_pp->merge_3d) {
+	if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) {
 		phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d,
 				BLEND_3D_NONE);
 		if (phys_enc->hw_ctl->ops.update_pending_flush_merge_3d)
@@ -2103,7 +2099,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 	if (phys_enc->hw_wb)
 		intf_cfg.wb = phys_enc->hw_wb->idx;
 
-	if (phys_enc->hw_pp->merge_3d)
+	if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d)
 		intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx;
 
 	if (ctl->ops.reset_intf_cfg)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
index b58a9c2ae326ca..724537ab776dfd 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -29,7 +29,6 @@ static inline bool reserved_by_other(uint32_t *res_map, int idx,
 /**
  * struct dpu_rm_requirements - Reservation requirements parameter bundle
  * @topology:  selected topology for the display
- * @hw_res:	   Hardware resources required as reported by the encoders
  */
 struct dpu_rm_requirements {
 	struct msm_display_topology topology;
@@ -204,6 +203,8 @@ static bool _dpu_rm_needs_split_display(const struct msm_display_topology *top)
  * _dpu_rm_get_lm_peer - get the id of a mixer which is a peer of the primary
  * @rm: dpu resource manager handle
  * @primary_idx: index of primary mixer in rm->mixer_blks[]
+ *
+ * Returns: lm peer mixed id on success or %-EINVAL on error
  */
 static int _dpu_rm_get_lm_peer(struct dpu_rm *rm, int primary_idx)
 {
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
index 77a8d9366ed7b0..fb588fde298a2d 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -135,11 +135,6 @@ static void dp_ctrl_config_ctrl(struct dp_ctrl_private *ctrl)
 	tbd = dp_link_get_test_bits_depth(ctrl->link,
 			ctrl->panel->dp_mode.bpp);
 
-	if (tbd == DP_TEST_BIT_DEPTH_UNKNOWN) {
-		pr_debug("BIT_DEPTH not set. Configure default\n");
-		tbd = DP_TEST_BIT_DEPTH_8;
-	}
-
 	config |= tbd << DP_CONFIGURATION_CTRL_BPC_SHIFT;
 
 	/* Num of Lanes */
diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c
index 98427d45e9a7e3..49dfac1fd1ef21 100644
--- a/drivers/gpu/drm/msm/dp/dp_link.c
+++ b/drivers/gpu/drm/msm/dp/dp_link.c
@@ -7,6 +7,7 @@
 
 #include <drm/drm_print.h>
 
+#include "dp_reg.h"
 #include "dp_link.h"
 #include "dp_panel.h"
 
@@ -1082,7 +1083,7 @@ int dp_link_process_request(struct dp_link *dp_link)
 
 int dp_link_get_colorimetry_config(struct dp_link *dp_link)
 {
-	u32 cc;
+	u32 cc = DP_MISC0_COLORIMERY_CFG_LEGACY_RGB;
 	struct dp_link_private *link;
 
 	if (!dp_link) {
@@ -1096,10 +1097,11 @@ int dp_link_get_colorimetry_config(struct dp_link *dp_link)
 	 * Unless a video pattern CTS test is ongoing, use RGB_VESA
 	 * Only RGB_VESA and RGB_CEA supported for now
 	 */
-	if (dp_link_is_video_pattern_requested(link))
-		cc = link->dp_link.test_video.test_dyn_range;
-	else
-		cc = DP_TEST_DYNAMIC_RANGE_VESA;
+	if (dp_link_is_video_pattern_requested(link)) {
+		if (link->dp_link.test_video.test_dyn_range &
+					DP_TEST_DYNAMIC_RANGE_CEA)
+			cc = DP_MISC0_COLORIMERY_CFG_CEA_RGB;
+	}
 
 	return cc;
 }
@@ -1179,6 +1181,9 @@ void dp_link_reset_phy_params_vx_px(struct dp_link *dp_link)
 u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp)
 {
 	u32 tbd;
+	struct dp_link_private *link;
+
+	link = container_of(dp_link, struct dp_link_private, dp_link);
 
 	/*
 	 * Few simplistic rules and assumptions made here:
@@ -1196,12 +1201,13 @@ u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp)
 		tbd = DP_TEST_BIT_DEPTH_10;
 		break;
 	default:
-		tbd = DP_TEST_BIT_DEPTH_UNKNOWN;
+		drm_dbg_dp(link->drm_dev, "bpp=%d not supported, use bpc=8\n",
+			   bpp);
+		tbd = DP_TEST_BIT_DEPTH_8;
 		break;
 	}
 
-	if (tbd != DP_TEST_BIT_DEPTH_UNKNOWN)
-		tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT);
+	tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT);
 
 	return tbd;
 }
diff --git a/drivers/gpu/drm/msm/dp/dp_reg.h b/drivers/gpu/drm/msm/dp/dp_reg.h
index ea85a691e72b5c..78785ed4b40c49 100644
--- a/drivers/gpu/drm/msm/dp/dp_reg.h
+++ b/drivers/gpu/drm/msm/dp/dp_reg.h
@@ -143,6 +143,9 @@
 #define DP_MISC0_COLORIMETRY_CFG_SHIFT		(0x00000001)
 #define DP_MISC0_TEST_BITS_DEPTH_SHIFT		(0x00000005)
 
+#define DP_MISC0_COLORIMERY_CFG_LEGACY_RGB	(0)
+#define DP_MISC0_COLORIMERY_CFG_CEA_RGB		(0x04)
+
 #define REG_DP_VALID_BOUNDARY			(0x00000030)
 #define REG_DP_VALID_BOUNDARY_2			(0x00000034)
 
diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c
index 455b2e3a0cdd48..35423d10aafa90 100644
--- a/drivers/gpu/drm/msm/msm_mdss.c
+++ b/drivers/gpu/drm/msm/msm_mdss.c
@@ -562,6 +562,7 @@ static const struct msm_mdss_data sdm670_data = {
 	.ubwc_enc_version = UBWC_2_0,
 	.ubwc_dec_version = UBWC_2_0,
 	.highest_bank_bit = 1,
+	.reg_bus_bw = 76800,
 };
 
 static const struct msm_mdss_data sdm845_data = {
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
index d1437c08645f90..6f5d376d8fcc1e 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
@@ -9,7 +9,7 @@
 #define GSP_PAGE_SIZE  BIT(GSP_PAGE_SHIFT)
 
 struct nvkm_gsp_mem {
-	u32 size;
+	size_t size;
 	void *data;
 	dma_addr_t addr;
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index 5e1fa176aac4a4..a41735ab60683f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -997,6 +997,32 @@ r535_gsp_rpc_get_gsp_static_info(struct nvkm_gsp *gsp)
 	return 0;
 }
 
+static void
+nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem)
+{
+	if (mem->data) {
+		/*
+		 * Poison the buffer to catch any unexpected access from
+		 * GSP-RM if the buffer was prematurely freed.
+		 */
+		memset(mem->data, 0xFF, mem->size);
+
+		dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr);
+		memset(mem, 0, sizeof(*mem));
+	}
+}
+
+static int
+nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, size_t size, struct nvkm_gsp_mem *mem)
+{
+	mem->size = size;
+	mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL);
+	if (WARN_ON(!mem->data))
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int
 r535_gsp_postinit(struct nvkm_gsp *gsp)
 {
@@ -1024,6 +1050,13 @@ r535_gsp_postinit(struct nvkm_gsp *gsp)
 
 	nvkm_inth_allow(&gsp->subdev.inth);
 	nvkm_wr32(device, 0x110004, 0x00000040);
+
+	/* Release the DMA buffers that were needed only for boot and init */
+	nvkm_gsp_mem_dtor(gsp, &gsp->boot.fw);
+	nvkm_gsp_mem_dtor(gsp, &gsp->libos);
+	nvkm_gsp_mem_dtor(gsp, &gsp->rmargs);
+	nvkm_gsp_mem_dtor(gsp, &gsp->wpr_meta);
+
 	return ret;
 }
 
@@ -1532,27 +1565,6 @@ r535_gsp_msg_run_cpu_sequencer(void *priv, u32 fn, void *repv, u32 repc)
 	return 0;
 }
 
-static void
-nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem)
-{
-	if (mem->data) {
-		dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr);
-		mem->data = NULL;
-	}
-}
-
-static int
-nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, u32 size, struct nvkm_gsp_mem *mem)
-{
-	mem->size = size;
-	mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL);
-	if (WARN_ON(!mem->data))
-		return -ENOMEM;
-
-	return 0;
-}
-
-
 static int
 r535_gsp_booter_unload(struct nvkm_gsp *gsp, u32 mbox0, u32 mbox1)
 {
@@ -1938,20 +1950,20 @@ nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3)
  * See kgspCreateRadix3_IMPL
  */
 static int
-nvkm_gsp_radix3_sg(struct nvkm_device *device, struct sg_table *sgt, u64 size,
+nvkm_gsp_radix3_sg(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size,
 		   struct nvkm_gsp_radix3 *rx3)
 {
 	u64 addr;
 
 	for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--) {
 		u64 *ptes;
-		int idx;
+		size_t bufsize;
+		int ret, idx;
 
-		rx3->mem[i].size = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
-		rx3->mem[i].data = dma_alloc_coherent(device->dev, rx3->mem[i].size,
-						      &rx3->mem[i].addr, GFP_KERNEL);
-		if (WARN_ON(!rx3->mem[i].data))
-			return -ENOMEM;
+		bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
+		ret = nvkm_gsp_mem_ctor(gsp, bufsize, &rx3->mem[i]);
+		if (ret)
+			return ret;
 
 		ptes = rx3->mem[i].data;
 		if (i == 2) {
@@ -1991,7 +2003,7 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend)
 		if (ret)
 			return ret;
 
-		ret = nvkm_gsp_radix3_sg(gsp->subdev.device, &gsp->sr.sgt, len, &gsp->sr.radix3);
+		ret = nvkm_gsp_radix3_sg(gsp, &gsp->sr.sgt, len, &gsp->sr.radix3);
 		if (ret)
 			return ret;
 
@@ -2150,6 +2162,11 @@ r535_gsp_dtor(struct nvkm_gsp *gsp)
 	mutex_destroy(&gsp->cmdq.mutex);
 
 	r535_gsp_dtor_fws(gsp);
+
+	nvkm_gsp_mem_dtor(gsp, &gsp->shm.mem);
+	nvkm_gsp_mem_dtor(gsp, &gsp->loginit);
+	nvkm_gsp_mem_dtor(gsp, &gsp->logintr);
+	nvkm_gsp_mem_dtor(gsp, &gsp->logrm);
 }
 
 int
@@ -2194,7 +2211,7 @@ r535_gsp_oneinit(struct nvkm_gsp *gsp)
 	memcpy(gsp->sig.data, data, size);
 
 	/* Build radix3 page table for ELF image. */
-	ret = nvkm_gsp_radix3_sg(device, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3);
+	ret = nvkm_gsp_radix3_sg(gsp, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 85f082396d42da..d442b893275b97 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -1178,21 +1178,24 @@ static void drm_sched_run_job_work(struct work_struct *w)
 	struct drm_sched_entity *entity;
 	struct dma_fence *fence;
 	struct drm_sched_fence *s_fence;
-	struct drm_sched_job *sched_job = NULL;
+	struct drm_sched_job *sched_job;
 	int r;
 
 	if (READ_ONCE(sched->pause_submit))
 		return;
 
 	/* Find entity with a ready job */
-	while (!sched_job && (entity = drm_sched_select_entity(sched))) {
-		sched_job = drm_sched_entity_pop_job(entity);
-		if (!sched_job)
-			complete_all(&entity->entity_idle);
-	}
+	entity = drm_sched_select_entity(sched);
 	if (!entity)
 		return;	/* No more work */
 
+	sched_job = drm_sched_entity_pop_job(entity);
+	if (!sched_job) {
+		complete_all(&entity->entity_idle);
+		drm_sched_run_job_queue(sched);
+		return;
+	}
+
 	s_fence = sched_job->s_fence;
 
 	atomic_add(sched_job->credits, &sched->credit_count);
diff --git a/drivers/gpu/drm/xe/xe_display.c b/drivers/gpu/drm/xe/xe_display.c
index 74391d9b11ae0e..e4db069f0db3f1 100644
--- a/drivers/gpu/drm/xe/xe_display.c
+++ b/drivers/gpu/drm/xe/xe_display.c
@@ -134,8 +134,6 @@ static void xe_display_fini_nommio(struct drm_device *dev, void *dummy)
 
 int xe_display_init_nommio(struct xe_device *xe)
 {
-	int err;
-
 	if (!xe->info.enable_display)
 		return 0;
 
@@ -145,10 +143,6 @@ int xe_display_init_nommio(struct xe_device *xe)
 	/* This must be called before any calls to HAS_PCH_* */
 	intel_detect_pch(xe);
 
-	err = intel_power_domains_init(xe);
-	if (err)
-		return err;
-
 	return drmm_add_action_or_reset(&xe->drm, xe_display_fini_nommio, xe);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index bcfc4127c7c59f..254b1d3af4cb56 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -926,20 +926,24 @@ void xe_exec_queue_last_fence_put_unlocked(struct xe_exec_queue *q)
  * @q: The exec queue
  * @vm: The VM the engine does a bind or exec for
  *
- * Get last fence, does not take a ref
+ * Get last fence, takes a ref
  *
  * Returns: last fence if not signaled, dma fence stub if signaled
  */
 struct dma_fence *xe_exec_queue_last_fence_get(struct xe_exec_queue *q,
 					       struct xe_vm *vm)
 {
+	struct dma_fence *fence;
+
 	xe_exec_queue_last_fence_lockdep_assert(q, vm);
 
 	if (q->last_fence &&
 	    test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &q->last_fence->flags))
 		xe_exec_queue_last_fence_put(q, vm);
 
-	return q->last_fence ? q->last_fence : dma_fence_get_stub();
+	fence = q->last_fence ? q->last_fence : dma_fence_get_stub();
+	dma_fence_get(fence);
+	return fence;
 }
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 3af2adec129561..35474ddbaf97ec 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -437,7 +437,10 @@ static int all_fw_domain_init(struct xe_gt *gt)
 		 * USM has its only SA pool to non-block behind user operations
 		 */
 		if (gt_to_xe(gt)->info.has_usm) {
-			gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt), SZ_1M, 16);
+			struct xe_device *xe = gt_to_xe(gt);
+
+			gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt),
+								IS_DGFX(xe) ? SZ_1M : SZ_512K, 16);
 			if (IS_ERR(gt->usm.bb_pool)) {
 				err = PTR_ERR(gt->usm.bb_pool);
 				goto err_force_wake;
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 9c2fe1697d6eef..73f08f1924df2e 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -335,7 +335,7 @@ int xe_guc_pagefault_handler(struct xe_guc *guc, u32 *msg, u32 len)
 		return -EPROTO;
 
 	asid = FIELD_GET(PFD_ASID, msg[1]);
-	pf_queue = &gt->usm.pf_queue[asid % NUM_PF_QUEUE];
+	pf_queue = gt->usm.pf_queue + (asid % NUM_PF_QUEUE);
 
 	spin_lock_irqsave(&pf_queue->lock, flags);
 	full = pf_queue_full(pf_queue);
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 5c6c5462425217..70480c30560215 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -170,11 +170,6 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 	if (!IS_DGFX(xe)) {
 		/* Write out batch too */
 		m->batch_base_ofs = NUM_PT_SLOTS * XE_PAGE_SIZE;
-		if (xe->info.has_usm) {
-			batch = tile->primary_gt->usm.bb_pool->bo;
-			m->usm_batch_base_ofs = m->batch_base_ofs;
-		}
-
 		for (i = 0; i < batch->size;
 		     i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
 		     XE_PAGE_SIZE) {
@@ -185,6 +180,24 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 				  entry);
 			level++;
 		}
+		if (xe->info.has_usm) {
+			xe_tile_assert(tile, batch->size == SZ_1M);
+
+			batch = tile->primary_gt->usm.bb_pool->bo;
+			m->usm_batch_base_ofs = m->batch_base_ofs + SZ_1M;
+			xe_tile_assert(tile, batch->size == SZ_512K);
+
+			for (i = 0; i < batch->size;
+			     i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
+			     XE_PAGE_SIZE) {
+				entry = vm->pt_ops->pte_encode_bo(batch, i,
+								  pat_index, 0);
+
+				xe_map_wr(xe, &bo->vmap, map_ofs + level * 8, u64,
+					  entry);
+				level++;
+			}
+		}
 	} else {
 		u64 batch_addr = xe_bo_addr(batch, 0, XE_PAGE_SIZE);
 
@@ -1204,8 +1217,11 @@ static bool no_in_syncs(struct xe_vm *vm, struct xe_exec_queue *q,
 	}
 	if (q) {
 		fence = xe_exec_queue_last_fence_get(q, vm);
-		if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+		if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
+			dma_fence_put(fence);
 			return false;
+		}
+		dma_fence_put(fence);
 	}
 
 	return true;
diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
index 01106a1156ad82..4e2ccad0e52fab 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@@ -274,7 +274,6 @@ int xe_sched_job_last_fence_add_dep(struct xe_sched_job *job, struct xe_vm *vm)
 	struct dma_fence *fence;
 
 	fence = xe_exec_queue_last_fence_get(job->q, vm);
-	dma_fence_get(fence);
 
 	return drm_sched_job_add_dependency(&job->drm, fence);
 }
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index e4c220cf9115e9..aab92bee1d7cf2 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -307,7 +307,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
 	/* Easy case... */
 	if (!num_in_fence) {
 		fence = xe_exec_queue_last_fence_get(q, vm);
-		dma_fence_get(fence);
 		return fence;
 	}
 
@@ -322,7 +321,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
 		}
 	}
 	fences[current_fence++] = xe_exec_queue_last_fence_get(q, vm);
-	dma_fence_get(fences[current_fence - 1]);
 	cf = dma_fence_array_create(num_in_fence, fences,
 				    vm->composite_fence_ctx,
 				    vm->composite_fence_seqno++,
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 30db264d34a323..865e10d0a06aa3 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -37,8 +37,6 @@
 #include "generated/xe_wa_oob.h"
 #include "xe_wa.h"
 
-#define TEST_VM_ASYNC_OPS_ERROR
-
 static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
 {
 	return vm->gpuvm.r_obj;
@@ -114,11 +112,8 @@ retry:
 					  num_pages - pinned,
 					  read_only ? 0 : FOLL_WRITE,
 					  &pages[pinned]);
-		if (ret < 0) {
-			if (in_kthread)
-				ret = 0;
+		if (ret < 0)
 			break;
-		}
 
 		pinned += ret;
 		ret = 0;
@@ -1984,6 +1979,7 @@ static int xe_vm_prefetch(struct xe_vm *vm, struct xe_vma *vma,
 					xe_exec_queue_last_fence_get(wait_exec_queue, vm);
 
 				xe_sync_entry_signal(&syncs[i], NULL, fence);
+				dma_fence_put(fence);
 			}
 		}
 
@@ -2064,7 +2060,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
 	struct drm_gem_object *obj = bo ? &bo->ttm.base : NULL;
 	struct drm_gpuva_ops *ops;
 	struct drm_gpuva_op *__op;
-	struct xe_vma_op *op;
 	struct drm_gpuvm_bo *vm_bo;
 	int err;
 
@@ -2111,15 +2106,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
 	if (IS_ERR(ops))
 		return ops;
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	if (operation & FORCE_ASYNC_OP_ERROR) {
-		op = list_first_entry_or_null(&ops->list, struct xe_vma_op,
-					      base.entry);
-		if (op)
-			op->inject_error = true;
-	}
-#endif
-
 	drm_gpuva_for_each_op(__op, ops) {
 		struct xe_vma_op *op = gpuva_op_to_vma_op(__op);
 
@@ -2199,8 +2185,10 @@ static u64 xe_vma_max_pte_size(struct xe_vma *vma)
 		return SZ_1G;
 	else if (vma->gpuva.flags & XE_VMA_PTE_2M)
 		return SZ_2M;
+	else if (vma->gpuva.flags & XE_VMA_PTE_4K)
+		return SZ_4K;
 
-	return SZ_4K;
+	return SZ_1G;	/* Uninitialized, used max size */
 }
 
 static u64 xe_vma_set_pte_size(struct xe_vma *vma, u64 size)
@@ -2530,13 +2518,25 @@ retry_userptr:
 	}
 	drm_exec_fini(&exec);
 
-	if (err == -EAGAIN && xe_vma_is_userptr(vma)) {
+	if (err == -EAGAIN) {
 		lockdep_assert_held_write(&vm->lock);
-		err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
-		if (!err)
-			goto retry_userptr;
 
-		trace_xe_vma_fail(vma);
+		if (op->base.op == DRM_GPUVA_OP_REMAP) {
+			if (!op->remap.unmap_done)
+				vma = gpuva_to_vma(op->base.remap.unmap->va);
+			else if (op->remap.prev)
+				vma = op->remap.prev;
+			else
+				vma = op->remap.next;
+		}
+
+		if (xe_vma_is_userptr(vma)) {
+			err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
+			if (!err)
+				goto retry_userptr;
+
+			trace_xe_vma_fail(vma);
+		}
 	}
 
 	return err;
@@ -2548,13 +2548,6 @@ static int xe_vma_op_execute(struct xe_vm *vm, struct xe_vma_op *op)
 
 	lockdep_assert_held_write(&vm->lock);
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	if (op->inject_error) {
-		op->inject_error = false;
-		return -ENOMEM;
-	}
-#endif
-
 	switch (op->base.op) {
 	case DRM_GPUVA_OP_MAP:
 		ret = __xe_vma_op_execute(vm, op->map.vma, op);
@@ -2669,7 +2662,7 @@ static void vm_bind_ioctl_ops_unwind(struct xe_vm *vm,
 {
 	int i;
 
-	for (i = num_ops_list - 1; i; ++i) {
+	for (i = num_ops_list - 1; i >= 0; --i) {
 		struct drm_gpuva_ops *__ops = ops[i];
 		struct drm_gpuva_op *__op;
 
@@ -2714,16 +2707,9 @@ static int vm_bind_ioctl_ops_execute(struct xe_vm *vm,
 	return 0;
 }
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-#define SUPPORTED_FLAGS	\
-	(FORCE_ASYNC_OP_ERROR | DRM_XE_VM_BIND_FLAG_READONLY | \
-	 DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | 0xffff)
-#else
 #define SUPPORTED_FLAGS	\
 	(DRM_XE_VM_BIND_FLAG_READONLY | \
-	 DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | \
-	 0xffff)
-#endif
+	 DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL)
 #define XE_64K_PAGE_MASK 0xffffull
 #define ALL_DRM_XE_SYNCS_FLAGS (DRM_XE_SYNCS_FLAG_WAIT_FOR_OP)
 
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 1fec66ae2eb2dd..5ac9c5bebabc3c 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -21,9 +21,6 @@ struct xe_bo;
 struct xe_sync_entry;
 struct xe_vm;
 
-#define TEST_VM_ASYNC_OPS_ERROR
-#define FORCE_ASYNC_OP_ERROR	BIT(31)
-
 #define XE_VMA_READ_ONLY	DRM_GPUVA_USERBITS
 #define XE_VMA_DESTROYED	(DRM_GPUVA_USERBITS << 1)
 #define XE_VMA_ATOMIC_PTE_BIT	(DRM_GPUVA_USERBITS << 2)
@@ -360,11 +357,6 @@ struct xe_vma_op {
 	/** @flags: operation flags */
 	enum xe_vma_op_flags flags;
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	/** @inject_error: inject error to test async op error handling */
-	bool inject_error;
-#endif
-
 	union {
 		/** @map: VMA map operation specific data */
 		struct xe_vma_op_map map;
diff --git a/include/uapi/drm/ivpu_accel.h b/include/uapi/drm/ivpu_accel.h
index 63c49318a86307..19a13468eca5e4 100644
--- a/include/uapi/drm/ivpu_accel.h
+++ b/include/uapi/drm/ivpu_accel.h
@@ -305,6 +305,7 @@ struct drm_ivpu_submit {
 
 /* drm_ivpu_bo_wait job status codes */
 #define DRM_IVPU_JOB_STATUS_SUCCESS 0
+#define DRM_IVPU_JOB_STATUS_ABORTED 256
 
 /**
  * struct drm_ivpu_bo_wait - Wait for BO to become inactive