Merge tag 'drm-fixes-2024-04-12' of https://gitlab.freedesktop.org/dr…

…m/kernel

Pull drm fixes from Dave Airlie:
 "Looks like everyone woke up after holidays, this weeks pull has a
  bunch of stuff all over, 2 weeks worth of amdgpu is a lot of it, then
  i915/xe have a few, a bunch of msm fixes, then some scattered driver
  fixes.

  I expect things will settle down for rc5.

  client:
   - Protect connector modes with mode_config mutex

  ast:
   - Fix soft lockup

  host1x:
   - Do not setup DMA for virtual addresses

  ivpu:
   - Fix deadlock in context_xa
   - PCI fixes
   - Fixes to error handling

  nouveau:
   - gsp: Fix OOB access
   - Fix casting

  panfrost:
   - Fix error path in MMU code

  qxl:
   - Revert "drm/qxl: simplify qxl_fence_wait"

  vmwgfx:
   - Enable DMA for SEV mappings

  i915:
   - Couple CDCLK programming fixes
   - HDCP related fix
   - 4 Bigjoiner related fixes
   - Fix for a circular locking around GuC on reset+wedged case

  xe:
   - Fix double display mutex initializations
   - Fix u32 -> u64 implicit conversions
   - Fix RING_CONTEXT_CONTROL not marked as masked

  msm:
   - DP refcount leak fix on disconnect
   - Add missing newlines to prints in msm_fb and msm_kms
   - fix dpu debugfs entry permissions
   - Fix the interface table for the catalog of X1E80100
   - fix irq message printing
   - Bindings fix to add DP node as child of mdss for mdss node
   - Minor typo fix in DP driver API which handles port status change
   - fix CHRASHDUMP_READ()
   - fix HHB (highest bank bit) for a619 to fix UBWC corruption

  amdgpu:
   - GPU reset fixes
   - Fix some confusing logging
   - UMSCH fix
   - Aborted suspend fix
   - DCN 3.5 fixes
   - S4 fix
   - MES logging fixes
   - SMU 14 fixes
   - SDMA 4.4.2 fix
   - KASAN fix
   - SMU 13.0.10 fix
   - VCN partition fix
   - GFX11 fixes
   - DWB fixes
   - Plane handling fix
   - FAMS fix
   - DCN 3.1.6 fix
   - VSC SDP fixes
   - OLED panel fix
   - GFX 11.5 fix

  amdkfd:
   - GPU reset fixes
   - fix ioctl integer overflow"

* tag 'drm-fixes-2024-04-12' of https://gitlab.freedesktop.org/drm/kernel: (65 commits)
  amdkfd: use calloc instead of kzalloc to avoid integer overflow
  drm/xe: Label RING_CONTEXT_CONTROL as masked
  drm/xe/xe_migrate: Cast to output precision before multiplying operands
  drm/xe/hwmon: Cast result to output precision on left shift of operand
  drm/xe/display: Fix double mutex initialization
  drm/amdgpu: differentiate external rev id for gfx 11.5.0
  drm/amd/display: Adjust dprefclk by down spread percentage.
  drm/amd/display: Set VSC SDP Colorimetry same way for MST and SST
  drm/amd/display: Program VSC SDP colorimetry for all DP sinks >= 1.4
  drm/amd/display: fix disable otg wa logic in DCN316
  drm/amd/display: Do not recursively call manual trigger programming
  drm/amd/display: always reset ODM mode in context when adding first plane
  drm/amdgpu: fix incorrect number of active RBs for gfx11
  drm/amd/display: Return max resolution supported by DWB
  amd/amdkfd: sync all devices to wait all processes being evicted
  drm/amdgpu: clear set_q_mode_offs when VM changed
  drm/amdgpu: Fix VCN allocation in CPX partition
  drm/amd/pm: fix the high voltage issue after unload
  drm/amd/display: Skip on writeback when it's not applicable
  drm/amdgpu: implement IRQ_STATE_ENABLE for SDMA v4.4.2
  ...

Documentation/devicetree/bindings/display/msm/qcom,sm8150-mdss.yaml

@@ -53,6 +53,15 @@ patternProperties:
       compatible:
         const: qcom,sm8150-dpu
 
+  "^displayport-controller@[0-9a-f]+$":
+    type: object
+    additionalProperties: true
+
+    properties:
+      compatible:
+        contains:
+          const: qcom,sm8150-dp
+
   "^dsi@[0-9a-f]+$":
     type: object
     additionalProperties: true

drivers/accel/ivpu/ivpu_drv.c

@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #include <linux/firmware.h>
@@ -131,22 +131,6 @@ static int ivpu_get_capabilities(struct ivpu_device *vdev, struct drm_ivpu_param
 	return 0;
 }
 
-static int ivpu_get_core_clock_rate(struct ivpu_device *vdev, u64 *clk_rate)
-{
-	int ret;
-
-	ret = ivpu_rpm_get_if_active(vdev);
-	if (ret < 0)
-		return ret;
-
-	*clk_rate = ret ? ivpu_hw_reg_pll_freq_get(vdev) : 0;
-
-	if (ret)
-		ivpu_rpm_put(vdev);
-
-	return 0;
-}
-
 static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 {
 	struct ivpu_file_priv *file_priv = file->driver_priv;
@@ -170,7 +154,7 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 		args->value = vdev->platform;
 		break;
 	case DRM_IVPU_PARAM_CORE_CLOCK_RATE:
-		ret = ivpu_get_core_clock_rate(vdev, &args->value);
+		args->value = ivpu_hw_ratio_to_freq(vdev, vdev->hw->pll.max_ratio);
 		break;
 	case DRM_IVPU_PARAM_NUM_CONTEXTS:
 		args->value = ivpu_get_context_count(vdev);
@@ -387,12 +371,15 @@ int ivpu_shutdown(struct ivpu_device *vdev)
 {
 	int ret;
 
-	ivpu_prepare_for_reset(vdev);
+	/* Save PCI state before powering down as it sometimes gets corrupted if NPU hangs */
+	pci_save_state(to_pci_dev(vdev->drm.dev));
 
 	ret = ivpu_hw_power_down(vdev);
 	if (ret)
 		ivpu_warn(vdev, "Failed to power down HW: %d\n", ret);
 
+	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
+
 	return ret;
 }
 
@@ -530,7 +517,7 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	vdev->context_xa_limit.min = IVPU_USER_CONTEXT_MIN_SSID;
 	vdev->context_xa_limit.max = IVPU_USER_CONTEXT_MAX_SSID;
 	atomic64_set(&vdev->unique_id_counter, 0);
-	xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC);
+	xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
 	xa_init_flags(&vdev->submitted_jobs_xa, XA_FLAGS_ALLOC1);
 	xa_init_flags(&vdev->db_xa, XA_FLAGS_ALLOC1);
 	lockdep_set_class(&vdev->submitted_jobs_xa.xa_lock, &submitted_jobs_xa_lock_class_key);
@@ -560,11 +547,11 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	/* Power up early so the rest of init code can access VPU registers */
 	ret = ivpu_hw_power_up(vdev);
 	if (ret)
-		goto err_power_down;
+		goto err_shutdown;
 
 	ret = ivpu_mmu_global_context_init(vdev);
 	if (ret)
-		goto err_power_down;
+		goto err_shutdown;
 
 	ret = ivpu_mmu_init(vdev);
 	if (ret)
@@ -601,10 +588,8 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	ivpu_mmu_reserved_context_fini(vdev);
 err_mmu_gctx_fini:
 	ivpu_mmu_global_context_fini(vdev);
-err_power_down:
-	ivpu_hw_power_down(vdev);
-	if (IVPU_WA(d3hot_after_power_off))
-		pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
+err_shutdown:
+	ivpu_shutdown(vdev);
 err_xa_destroy:
 	xa_destroy(&vdev->db_xa);
 	xa_destroy(&vdev->submitted_jobs_xa);
@@ -628,9 +613,8 @@ static void ivpu_bo_unbind_all_user_contexts(struct ivpu_device *vdev)
 static void ivpu_dev_fini(struct ivpu_device *vdev)
 {
 	ivpu_pm_disable(vdev);
+	ivpu_prepare_for_reset(vdev);
 	ivpu_shutdown(vdev);
-	if (IVPU_WA(d3hot_after_power_off))
-		pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
 
 	ivpu_jobs_abort_all(vdev);
 	ivpu_job_done_consumer_fini(vdev);

drivers/accel/ivpu/ivpu_drv.h

@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #ifndef __IVPU_DRV_H__
@@ -90,7 +90,6 @@
 struct ivpu_wa_table {
 	bool punit_disabled;
 	bool clear_runtime_mem;
-	bool d3hot_after_power_off;
 	bool interrupt_clear_with_0;
 	bool disable_clock_relinquish;
 	bool disable_d0i3_msg;

drivers/accel/ivpu/ivpu_hw.h

@@ -21,6 +21,7 @@ struct ivpu_hw_ops {
 	u32 (*profiling_freq_get)(struct ivpu_device *vdev);
 	void (*profiling_freq_drive)(struct ivpu_device *vdev, bool enable);
 	u32 (*reg_pll_freq_get)(struct ivpu_device *vdev);
+	u32 (*ratio_to_freq)(struct ivpu_device *vdev, u32 ratio);
 	u32 (*reg_telemetry_offset_get)(struct ivpu_device *vdev);
 	u32 (*reg_telemetry_size_get)(struct ivpu_device *vdev);
 	u32 (*reg_telemetry_enable_get)(struct ivpu_device *vdev);
@@ -130,6 +131,11 @@ static inline u32 ivpu_hw_reg_pll_freq_get(struct ivpu_device *vdev)
 	return vdev->hw->ops->reg_pll_freq_get(vdev);
 };
 
+static inline u32 ivpu_hw_ratio_to_freq(struct ivpu_device *vdev, u32 ratio)
+{
+	return vdev->hw->ops->ratio_to_freq(vdev, ratio);
+}
+
 static inline u32 ivpu_hw_reg_telemetry_offset_get(struct ivpu_device *vdev)
 {
 	return vdev->hw->ops->reg_telemetry_offset_get(vdev);

drivers/accel/ivpu/ivpu_hw_37xx.c

@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #include "ivpu_drv.h"
@@ -75,7 +75,6 @@ static void ivpu_hw_wa_init(struct ivpu_device *vdev)
 {
 	vdev->wa.punit_disabled = false;
 	vdev->wa.clear_runtime_mem = false;
-	vdev->wa.d3hot_after_power_off = true;
 
 	REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, BUTTRESS_ALL_IRQ_MASK);
 	if (REGB_RD32(VPU_37XX_BUTTRESS_INTERRUPT_STAT) == BUTTRESS_ALL_IRQ_MASK) {
@@ -86,7 +85,6 @@ static void ivpu_hw_wa_init(struct ivpu_device *vdev)
 
 	IVPU_PRINT_WA(punit_disabled);
 	IVPU_PRINT_WA(clear_runtime_mem);
-	IVPU_PRINT_WA(d3hot_after_power_off);
 	IVPU_PRINT_WA(interrupt_clear_with_0);
 }
 
@@ -805,12 +803,12 @@ static void ivpu_hw_37xx_profiling_freq_drive(struct ivpu_device *vdev, bool ena
 	/* Profiling freq - is a debug feature. Unavailable on VPU 37XX. */
 }
 
-static u32 ivpu_hw_37xx_pll_to_freq(u32 ratio, u32 config)
+static u32 ivpu_hw_37xx_ratio_to_freq(struct ivpu_device *vdev, u32 ratio)
 {
 	u32 pll_clock = PLL_REF_CLK_FREQ * ratio;
 	u32 cpu_clock;
 
-	if ((config & 0xff) == PLL_RATIO_4_3)
+	if ((vdev->hw->config & 0xff) == PLL_RATIO_4_3)
 		cpu_clock = pll_clock * 2 / 4;
 	else
 		cpu_clock = pll_clock * 2 / 5;
@@ -829,7 +827,7 @@ static u32 ivpu_hw_37xx_reg_pll_freq_get(struct ivpu_device *vdev)
 	if (!ivpu_is_silicon(vdev))
 		return PLL_SIMULATION_FREQ;
 
-	return ivpu_hw_37xx_pll_to_freq(pll_curr_ratio, vdev->hw->config);
+	return ivpu_hw_37xx_ratio_to_freq(vdev, pll_curr_ratio);
 }
 
 static u32 ivpu_hw_37xx_reg_telemetry_offset_get(struct ivpu_device *vdev)
@@ -1052,6 +1050,7 @@ const struct ivpu_hw_ops ivpu_hw_37xx_ops = {
 	.profiling_freq_get = ivpu_hw_37xx_profiling_freq_get,
 	.profiling_freq_drive = ivpu_hw_37xx_profiling_freq_drive,
 	.reg_pll_freq_get = ivpu_hw_37xx_reg_pll_freq_get,
+	.ratio_to_freq = ivpu_hw_37xx_ratio_to_freq,
 	.reg_telemetry_offset_get = ivpu_hw_37xx_reg_telemetry_offset_get,
 	.reg_telemetry_size_get = ivpu_hw_37xx_reg_telemetry_size_get,
 	.reg_telemetry_enable_get = ivpu_hw_37xx_reg_telemetry_enable_get,

drivers/accel/ivpu/ivpu_hw_40xx.c

@@ -980,6 +980,11 @@ static u32 ivpu_hw_40xx_reg_pll_freq_get(struct ivpu_device *vdev)
 	return PLL_RATIO_TO_FREQ(pll_curr_ratio);
 }
 
+static u32 ivpu_hw_40xx_ratio_to_freq(struct ivpu_device *vdev, u32 ratio)
+{
+	return PLL_RATIO_TO_FREQ(ratio);
+}
+
 static u32 ivpu_hw_40xx_reg_telemetry_offset_get(struct ivpu_device *vdev)
 {
 	return REGB_RD32(VPU_40XX_BUTTRESS_VPU_TELEMETRY_OFFSET);
@@ -1230,6 +1235,7 @@ const struct ivpu_hw_ops ivpu_hw_40xx_ops = {
 	.profiling_freq_get = ivpu_hw_40xx_profiling_freq_get,
 	.profiling_freq_drive = ivpu_hw_40xx_profiling_freq_drive,
 	.reg_pll_freq_get = ivpu_hw_40xx_reg_pll_freq_get,
+	.ratio_to_freq = ivpu_hw_40xx_ratio_to_freq,
 	.reg_telemetry_offset_get = ivpu_hw_40xx_reg_telemetry_offset_get,
 	.reg_telemetry_size_get = ivpu_hw_40xx_reg_telemetry_size_get,
 	.reg_telemetry_enable_get = ivpu_hw_40xx_reg_telemetry_enable_get,

drivers/accel/ivpu/ivpu_ipc.c

@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #include <linux/genalloc.h>
@@ -501,7 +501,11 @@ int ivpu_ipc_init(struct ivpu_device *vdev)
 	spin_lock_init(&ipc->cons_lock);
 	INIT_LIST_HEAD(&ipc->cons_list);
 	INIT_LIST_HEAD(&ipc->cb_msg_list);
-	drmm_mutex_init(&vdev->drm, &ipc->lock);
+	ret = drmm_mutex_init(&vdev->drm, &ipc->lock);
+	if (ret) {
+		ivpu_err(vdev, "Failed to initialize ipc->lock, ret %d\n", ret);
+		goto err_free_rx;
+	}
 	ivpu_ipc_reset(vdev);
 	return 0;
 

drivers/accel/ivpu/ivpu_mmu.c

@@ -278,23 +278,23 @@ static const char *ivpu_mmu_event_to_str(u32 cmd)
 	case IVPU_MMU_EVT_F_VMS_FETCH:
 		return "Fetch of VMS caused external abort";
 	default:
-		return "Unknown CMDQ command";
+		return "Unknown event";
 	}
 }
 
 static const char *ivpu_mmu_cmdq_err_to_str(u32 err)
 {
 	switch (err) {
 	case IVPU_MMU_CERROR_NONE:
-		return "No CMDQ Error";
+		return "No error";
 	case IVPU_MMU_CERROR_ILL:
 		return "Illegal command";
 	case IVPU_MMU_CERROR_ABT:
-		return "External abort on CMDQ read";
+		return "External abort on command queue read";
 	case IVPU_MMU_CERROR_ATC_INV_SYNC:
 		return "Sync failed to complete ATS invalidation";
 	default:
-		return "Unknown CMDQ Error";
+		return "Unknown error";
 	}
 }
 

drivers/accel/ivpu/ivpu_pm.c

@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #include <linux/highmem.h>
@@ -58,14 +58,11 @@ static int ivpu_suspend(struct ivpu_device *vdev)
 {
 	int ret;
 
-	/* Save PCI state before powering down as it sometimes gets corrupted if NPU hangs */
-	pci_save_state(to_pci_dev(vdev->drm.dev));
+	ivpu_prepare_for_reset(vdev);
 
 	ret = ivpu_shutdown(vdev);
 	if (ret)
-		ivpu_err(vdev, "Failed to shutdown VPU: %d\n", ret);
-
-	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
+		ivpu_err(vdev, "Failed to shutdown NPU: %d\n", ret);
 
 	return ret;
 }
@@ -74,10 +71,10 @@ static int ivpu_resume(struct ivpu_device *vdev)
 {
 	int ret;
 
-	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0);
+retry:
 	pci_restore_state(to_pci_dev(vdev->drm.dev));
+	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0);
 
-retry:
 	ret = ivpu_hw_power_up(vdev);
 	if (ret) {
 		ivpu_err(vdev, "Failed to power up HW: %d\n", ret);
@@ -100,6 +97,7 @@ static int ivpu_resume(struct ivpu_device *vdev)
 	ivpu_mmu_disable(vdev);
 err_power_down:
 	ivpu_hw_power_down(vdev);
+	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
 
 	if (!ivpu_fw_is_cold_boot(vdev)) {
 		ivpu_pm_prepare_cold_boot(vdev);

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -210,6 +210,7 @@ extern int amdgpu_async_gfx_ring;
 extern int amdgpu_mcbp;
 extern int amdgpu_discovery;
 extern int amdgpu_mes;
+extern int amdgpu_mes_log_enable;
 extern int amdgpu_mes_kiq;
 extern int amdgpu_noretry;
 extern int amdgpu_force_asic_type;

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -4135,18 +4135,22 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 					adev->ip_blocks[i].status.hw = true;
 				}
 			}
+		} else if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 10) &&
+				   !amdgpu_device_has_display_hardware(adev)) {
+					r = psp_gpu_reset(adev);
 		} else {
-			tmp = amdgpu_reset_method;
-			/* It should do a default reset when loading or reloading the driver,
-			 * regardless of the module parameter reset_method.
-			 */
-			amdgpu_reset_method = AMD_RESET_METHOD_NONE;
-			r = amdgpu_asic_reset(adev);
-			amdgpu_reset_method = tmp;
-			if (r) {
-				dev_err(adev->dev, "asic reset on init failed\n");
-				goto failed;
-			}
+				tmp = amdgpu_reset_method;
+				/* It should do a default reset when loading or reloading the driver,
+				 * regardless of the module parameter reset_method.
+				 */
+				amdgpu_reset_method = AMD_RESET_METHOD_NONE;
+				r = amdgpu_asic_reset(adev);
+				amdgpu_reset_method = tmp;
+		}
+
+		if (r) {
+		  dev_err(adev->dev, "asic reset on init failed\n");
+		  goto failed;
 		}
 	}
 

drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c

@@ -1896,6 +1896,7 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block);
 		break;
 	case IP_VERSION(14, 0, 0):
+	case IP_VERSION(14, 0, 1):
 		amdgpu_device_ip_block_add(adev, &smu_v14_0_ip_block);
 		break;
 	default: