Merge tag 'drm-misc-next-2025-12-01-1' of https://gitlab.freedesktop.org/drm/misc/kernel into drm-next

Extra drm-misc-next for v6.19-rc1:

UAPI Changes:
- Add support for drm colorop pipeline.
- Add COLOR PIPELINE plane property.
- Add DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE.

Cross-subsystem Changes:
- Attempt to use higher order mappings in system heap allocator.
- Always taint kernel with sw-sync.

Core Changes:
- Small fixes to drm/gem.
- Support emergency restore to drm-client.
- Allocate and release fb_info in single place.
- Rework ttm pipelined eviction fence handling.

Driver Changes:
- Support the drm color pipeline in vkms, amdgfx.
- Add NVJPG driver for tegra.
- Assorted small fixes and updates to rockchip, bridge/dw-hdmi-qp,
  panthor.
- Add ASL CS5263 DP-to-HDMI simple bridge.
- Add and improve support for G LD070WX3-SL01 MIPI DSI, Samsung LTL106AL0,
  Samsung LTL106AL01, Raystar RFF500F-AWH-DNN, Winstar WF70A8SYJHLNGA,
  Wanchanglong w552946aaa, Samsung SOFEF00, Lenovo X13s panel.
- Add support for it66122 to it66121.
- Support mali-G1 gpu in panthor.

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patch.msgid.link/aa5cbd50-7676-4a59-bbed-e8428af86804@linux.intel.com

15 files changed, 1217 insertions, 128 deletions

diff --git a/drivers/gpu/drm/panthor/Makefile b/drivers/gpu/drm/panthor/Makefile
index 02db21748c12..753a32c446df 100644
--- a/drivers/gpu/drm/panthor/Makefile
+++ b/drivers/gpu/drm/panthor/Makefile
@@ -10,6 +10,7 @@ panthor-y := \
 	panthor_heap.o \
 	panthor_hw.o \
 	panthor_mmu.o \
+	panthor_pwr.o \
 	panthor_sched.o
 
 obj-$(CONFIG_DRM_PANTHOR) += panthor.o
diff --git a/drivers/gpu/drm/panthor/panthor_device.c b/drivers/gpu/drm/panthor/panthor_device.c
index 31fb8ed68199..e133b1e0ad6d 100644
--- a/drivers/gpu/drm/panthor/panthor_device.c
+++ b/drivers/gpu/drm/panthor/panthor_device.c
@@ -21,6 +21,7 @@
 #include "panthor_gpu.h"
 #include "panthor_hw.h"
 #include "panthor_mmu.h"
+#include "panthor_pwr.h"
 #include "panthor_regs.h"
 #include "panthor_sched.h"
 
@@ -113,6 +114,7 @@ void panthor_device_unplug(struct panthor_device *ptdev)
 	panthor_fw_unplug(ptdev);
 	panthor_mmu_unplug(ptdev);
 	panthor_gpu_unplug(ptdev);
+	panthor_pwr_unplug(ptdev);
 
 	pm_runtime_dont_use_autosuspend(ptdev->base.dev);
 	pm_runtime_put_sync_suspend(ptdev->base.dev);
@@ -152,8 +154,8 @@ static void panthor_device_reset_work(struct work_struct *work)
 	panthor_sched_pre_reset(ptdev);
 	panthor_fw_pre_reset(ptdev, true);
 	panthor_mmu_pre_reset(ptdev);
-	panthor_gpu_soft_reset(ptdev);
-	panthor_gpu_l2_power_on(ptdev);
+	panthor_hw_soft_reset(ptdev);
+	panthor_hw_l2_power_on(ptdev);
 	panthor_mmu_post_reset(ptdev);
 	ret = panthor_fw_post_reset(ptdev);
 	atomic_set(&ptdev->reset.pending, 0);
@@ -268,10 +270,14 @@ int panthor_device_init(struct panthor_device *ptdev)
 	if (ret)
 		goto err_rpm_put;
 
-	ret = panthor_gpu_init(ptdev);
+	ret = panthor_pwr_init(ptdev);
 	if (ret)
 		goto err_rpm_put;
 
+	ret = panthor_gpu_init(ptdev);
+	if (ret)
+		goto err_unplug_pwr;
+
 	ret = panthor_gpu_coherency_init(ptdev);
 	if (ret)
 		goto err_unplug_gpu;
@@ -312,6 +318,9 @@ err_unplug_mmu:
 err_unplug_gpu:
 	panthor_gpu_unplug(ptdev);
 
+err_unplug_pwr:
+	panthor_pwr_unplug(ptdev);
+
 err_rpm_put:
 	pm_runtime_put_sync_suspend(ptdev->base.dev);
 	return ret;
@@ -465,6 +474,7 @@ static int panthor_device_resume_hw_components(struct panthor_device *ptdev)
 {
 	int ret;
 
+	panthor_pwr_resume(ptdev);
 	panthor_gpu_resume(ptdev);
 	panthor_mmu_resume(ptdev);
 
@@ -474,6 +484,7 @@ static int panthor_device_resume_hw_components(struct panthor_device *ptdev)
 
 	panthor_mmu_suspend(ptdev);
 	panthor_gpu_suspend(ptdev);
+	panthor_pwr_suspend(ptdev);
 	return ret;
 }
 
@@ -587,6 +598,7 @@ int panthor_device_suspend(struct device *dev)
 		panthor_fw_suspend(ptdev);
 		panthor_mmu_suspend(ptdev);
 		panthor_gpu_suspend(ptdev);
+		panthor_pwr_suspend(ptdev);
 		drm_dev_exit(cookie);
 	}
 
diff --git a/drivers/gpu/drm/panthor/panthor_device.h b/drivers/gpu/drm/panthor/panthor_device.h
index f32c1868bf6d..f35e52b9546a 100644
--- a/drivers/gpu/drm/panthor/panthor_device.h
+++ b/drivers/gpu/drm/panthor/panthor_device.h
@@ -24,10 +24,12 @@ struct panthor_device;
 struct panthor_gpu;
 struct panthor_group_pool;
 struct panthor_heap_pool;
+struct panthor_hw;
 struct panthor_job;
 struct panthor_mmu;
 struct panthor_fw;
 struct panthor_perfcnt;
+struct panthor_pwr;
 struct panthor_vm;
 struct panthor_vm_pool;
 
@@ -134,6 +136,12 @@ struct panthor_device {
 	/** @csif_info: Command stream interface information. */
 	struct drm_panthor_csif_info csif_info;
 
+	/** @hw: GPU-specific data. */
+	struct panthor_hw *hw;
+
+	/** @pwr: Power control management data. */
+	struct panthor_pwr *pwr;
+
 	/** @gpu: GPU management data. */
 	struct panthor_gpu *gpu;
 
diff --git a/drivers/gpu/drm/panthor/panthor_fw.c b/drivers/gpu/drm/panthor/panthor_fw.c
index 38d87ab92eda..1a5e3c1a27fb 100644
--- a/drivers/gpu/drm/panthor/panthor_fw.c
+++ b/drivers/gpu/drm/panthor/panthor_fw.c
@@ -22,6 +22,7 @@
 #include "panthor_fw.h"
 #include "panthor_gem.h"
 #include "panthor_gpu.h"
+#include "panthor_hw.h"
 #include "panthor_mmu.h"
 #include "panthor_regs.h"
 #include "panthor_sched.h"
@@ -33,6 +34,7 @@
 #define PROGRESS_TIMEOUT_SCALE_SHIFT		10
 #define IDLE_HYSTERESIS_US			800
 #define PWROFF_HYSTERESIS_US			10000
+#define MCU_HALT_TIMEOUT_US			(1ULL * USEC_PER_SEC)
 
 /**
  * struct panthor_fw_binary_hdr - Firmware binary header.
@@ -317,6 +319,49 @@ panthor_fw_get_cs_iface(struct panthor_device *ptdev, u32 csg_slot, u32 cs_slot)
 	return &ptdev->fw->iface.streams[csg_slot][cs_slot];
 }
 
+static bool panthor_fw_has_glb_state(struct panthor_device *ptdev)
+{
+	struct panthor_fw_global_iface *glb_iface = panthor_fw_get_glb_iface(ptdev);
+
+	return glb_iface->control->version >= CSF_IFACE_VERSION(4, 1, 0);
+}
+
+static bool panthor_fw_has_64bit_ep_req(struct panthor_device *ptdev)
+{
+	struct panthor_fw_global_iface *glb_iface = panthor_fw_get_glb_iface(ptdev);
+
+	return glb_iface->control->version >= CSF_IFACE_VERSION(4, 0, 0);
+}
+
+u64 panthor_fw_csg_endpoint_req_get(struct panthor_device *ptdev,
+				    struct panthor_fw_csg_iface *csg_iface)
+{
+	if (panthor_fw_has_64bit_ep_req(ptdev))
+		return csg_iface->input->endpoint_req2;
+	else
+		return csg_iface->input->endpoint_req;
+}
+
+void panthor_fw_csg_endpoint_req_set(struct panthor_device *ptdev,
+				     struct panthor_fw_csg_iface *csg_iface, u64 value)
+{
+	if (panthor_fw_has_64bit_ep_req(ptdev))
+		csg_iface->input->endpoint_req2 = value;
+	else
+		csg_iface->input->endpoint_req = lower_32_bits(value);
+}
+
+void panthor_fw_csg_endpoint_req_update(struct panthor_device *ptdev,
+					struct panthor_fw_csg_iface *csg_iface, u64 value,
+					u64 mask)
+{
+	if (panthor_fw_has_64bit_ep_req(ptdev))
+		panthor_fw_update_reqs64(csg_iface, endpoint_req2, value, mask);
+	else
+		panthor_fw_update_reqs(csg_iface, endpoint_req, lower_32_bits(value),
+				       lower_32_bits(mask));
+}
+
 /**
  * panthor_fw_conv_timeout() - Convert a timeout into a cycle-count
  * @ptdev: Device.
@@ -996,6 +1041,9 @@ static void panthor_fw_init_global_iface(struct panthor_device *ptdev)
 					 GLB_IDLE_EN |
 					 GLB_IDLE;
 
+	if (panthor_fw_has_glb_state(ptdev))
+		glb_iface->input->ack_irq_mask |= GLB_STATE_MASK;
+
 	panthor_fw_update_reqs(glb_iface, req, GLB_IDLE_EN, GLB_IDLE_EN);
 	panthor_fw_toggle_reqs(glb_iface, req, ack,
 			       GLB_CFG_ALLOC_EN |
@@ -1069,6 +1117,54 @@ static void panthor_fw_stop(struct panthor_device *ptdev)
 		drm_err(&ptdev->base, "Failed to stop MCU");
 }
 
+static bool panthor_fw_mcu_halted(struct panthor_device *ptdev)
+{
+	struct panthor_fw_global_iface *glb_iface = panthor_fw_get_glb_iface(ptdev);
+	bool halted;
+
+	halted = gpu_read(ptdev, MCU_STATUS) == MCU_STATUS_HALT;
+
+	if (panthor_fw_has_glb_state(ptdev))
+		halted &= (GLB_STATE_GET(glb_iface->output->ack) == GLB_STATE_HALT);
+
+	return halted;
+}
+
+static void panthor_fw_halt_mcu(struct panthor_device *ptdev)
+{
+	struct panthor_fw_global_iface *glb_iface = panthor_fw_get_glb_iface(ptdev);
+
+	if (panthor_fw_has_glb_state(ptdev))
+		panthor_fw_update_reqs(glb_iface, req, GLB_STATE(GLB_STATE_HALT), GLB_STATE_MASK);
+	else
+		panthor_fw_update_reqs(glb_iface, req, GLB_HALT, GLB_HALT);
+
+	gpu_write(ptdev, CSF_DOORBELL(CSF_GLB_DOORBELL_ID), 1);
+}
+
+static bool panthor_fw_wait_mcu_halted(struct panthor_device *ptdev)
+{
+	bool halted = false;
+
+	if (read_poll_timeout_atomic(panthor_fw_mcu_halted, halted, halted, 10,
+				     MCU_HALT_TIMEOUT_US, 0, ptdev)) {
+		drm_warn(&ptdev->base, "Timed out waiting for MCU to halt");
+		return false;
+	}
+
+	return true;
+}
+
+static void panthor_fw_mcu_set_active(struct panthor_device *ptdev)
+{
+	struct panthor_fw_global_iface *glb_iface = panthor_fw_get_glb_iface(ptdev);
+
+	if (panthor_fw_has_glb_state(ptdev))
+		panthor_fw_update_reqs(glb_iface, req, GLB_STATE(GLB_STATE_ACTIVE), GLB_STATE_MASK);
+	else
+		panthor_fw_update_reqs(glb_iface, req, 0, GLB_HALT);
+}
+
 /**
  * panthor_fw_pre_reset() - Call before a reset.
  * @ptdev: Device.
@@ -1085,19 +1181,13 @@ void panthor_fw_pre_reset(struct panthor_device *ptdev, bool on_hang)
 	ptdev->reset.fast = false;
 
 	if (!on_hang) {
-		struct panthor_fw_global_iface *glb_iface = panthor_fw_get_glb_iface(ptdev);
-		u32 status;
-
-		panthor_fw_update_reqs(glb_iface, req, GLB_HALT, GLB_HALT);
-		gpu_write(ptdev, CSF_DOORBELL(CSF_GLB_DOORBELL_ID), 1);
-		if (!gpu_read_poll_timeout(ptdev, MCU_STATUS, status,
-					   status == MCU_STATUS_HALT, 10,
-					   100000)) {
-			ptdev->reset.fast = true;
-		} else {
+		panthor_fw_halt_mcu(ptdev);
+		if (!panthor_fw_wait_mcu_halted(ptdev))
 			drm_warn(&ptdev->base, "Failed to cleanly suspend MCU");
-		}
+		else
+			ptdev->reset.fast = true;
 	}
+	panthor_fw_stop(ptdev);
 
 	panthor_job_irq_suspend(&ptdev->fw->irq);
 	panthor_fw_stop(ptdev);
@@ -1126,14 +1216,14 @@ int panthor_fw_post_reset(struct panthor_device *ptdev)
 		 */
 		panthor_reload_fw_sections(ptdev, true);
 	} else {
-		/* The FW detects 0 -> 1 transitions. Make sure we reset
-		 * the HALT bit before the FW is rebooted.
+		/*
+		 * If the FW was previously successfully halted in the pre-reset
+		 * operation, we need to transition it to active again before
+		 * the FW is rebooted.
 		 * This is not needed on a slow reset because FW sections are
 		 * re-initialized.
 		 */
-		struct panthor_fw_global_iface *glb_iface = panthor_fw_get_glb_iface(ptdev);
-
-		panthor_fw_update_reqs(glb_iface, req, 0, GLB_HALT);
+		panthor_fw_mcu_set_active(ptdev);
 	}
 
 	ret = panthor_fw_start(ptdev);
@@ -1171,6 +1261,10 @@ void panthor_fw_unplug(struct panthor_device *ptdev)
 		if (ptdev->fw->irq.irq)
 			panthor_job_irq_suspend(&ptdev->fw->irq);
 
+		panthor_fw_halt_mcu(ptdev);
+		if (!panthor_fw_wait_mcu_halted(ptdev))
+			drm_warn(&ptdev->base, "Failed to halt MCU on unplug");
+
 		panthor_fw_stop(ptdev);
 	}
 
@@ -1186,7 +1280,7 @@ void panthor_fw_unplug(struct panthor_device *ptdev)
 	ptdev->fw->vm = NULL;
 
 	if (!IS_ENABLED(CONFIG_PM) || pm_runtime_active(ptdev->base.dev))
-		panthor_gpu_power_off(ptdev, L2, ptdev->gpu_info.l2_present, 20000);
+		panthor_hw_l2_power_off(ptdev);
 }
 
 /**
@@ -1365,7 +1459,7 @@ int panthor_fw_init(struct panthor_device *ptdev)
 		return ret;
 	}
 
-	ret = panthor_gpu_l2_power_on(ptdev);
+	ret = panthor_hw_l2_power_on(ptdev);
 	if (ret)
 		return ret;
 
@@ -1409,3 +1503,4 @@ MODULE_FIRMWARE("arm/mali/arch10.12/mali_csffw.bin");
 MODULE_FIRMWARE("arm/mali/arch11.8/mali_csffw.bin");
 MODULE_FIRMWARE("arm/mali/arch12.8/mali_csffw.bin");
 MODULE_FIRMWARE("arm/mali/arch13.8/mali_csffw.bin");
+MODULE_FIRMWARE("arm/mali/arch14.8/mali_csffw.bin");
diff --git a/drivers/gpu/drm/panthor/panthor_fw.h b/drivers/gpu/drm/panthor/panthor_fw.h
index 6598d96c6d2a..fbdc21469ba3 100644
--- a/drivers/gpu/drm/panthor/panthor_fw.h
+++ b/drivers/gpu/drm/panthor/panthor_fw.h
@@ -167,10 +167,11 @@ struct panthor_fw_csg_input_iface {
 #define CSG_EP_REQ_TILER(x)			(((x) << 16) & GENMASK(19, 16))
 #define CSG_EP_REQ_EXCL_COMPUTE			BIT(20)
 #define CSG_EP_REQ_EXCL_FRAGMENT		BIT(21)
-#define CSG_EP_REQ_PRIORITY(x)			(((x) << 28) & GENMASK(31, 28))
 #define CSG_EP_REQ_PRIORITY_MASK		GENMASK(31, 28)
+#define CSG_EP_REQ_PRIORITY(x)			(((x) << 28) & CSG_EP_REQ_PRIORITY_MASK)
+#define CSG_EP_REQ_PRIORITY_GET(x)		(((x) & CSG_EP_REQ_PRIORITY_MASK) >> 28)
 	u32 endpoint_req;
-	u32 reserved2[2];
+	u64 endpoint_req2;
 	u64 suspend_buf;
 	u64 protm_suspend_buf;
 	u32 config;
@@ -214,6 +215,13 @@ struct panthor_fw_global_input_iface {
 #define GLB_FWCFG_UPDATE			BIT(9)
 #define GLB_IDLE_EN				BIT(10)
 #define GLB_SLEEP				BIT(12)
+#define GLB_STATE_MASK				GENMASK(14, 12)
+#define   GLB_STATE_ACTIVE			0
+#define   GLB_STATE_HALT			1
+#define   GLB_STATE_SLEEP			2
+#define   GLB_STATE_SUSPEND			3
+#define   GLB_STATE(x)				(((x) << 12) & GLB_STATE_MASK)
+#define   GLB_STATE_GET(x)			(((x) & GLB_STATE_MASK) >> 12)
 #define GLB_INACTIVE_COMPUTE			BIT(20)
 #define GLB_INACTIVE_FRAGMENT			BIT(21)
 #define GLB_INACTIVE_TILER			BIT(22)
@@ -457,6 +465,16 @@ struct panthor_fw_global_iface {
 		spin_unlock(&(__iface)->lock); \
 	} while (0)
 
+#define panthor_fw_update_reqs64(__iface, __in_reg, __val, __mask) \
+	do { \
+		u64 __cur_val, __new_val; \
+		spin_lock(&(__iface)->lock); \
+		__cur_val = READ_ONCE((__iface)->input->__in_reg); \
+		__new_val = (__cur_val & ~(__mask)) | ((__val) & (__mask)); \
+		WRITE_ONCE((__iface)->input->__in_reg, __new_val); \
+		spin_unlock(&(__iface)->lock); \
+	} while (0)
+
 struct panthor_fw_global_iface *
 panthor_fw_get_glb_iface(struct panthor_device *ptdev);
 
@@ -466,6 +484,16 @@ panthor_fw_get_csg_iface(struct panthor_device *ptdev, u32 csg_slot);
 struct panthor_fw_cs_iface *
 panthor_fw_get_cs_iface(struct panthor_device *ptdev, u32 csg_slot, u32 cs_slot);
 
+u64 panthor_fw_csg_endpoint_req_get(struct panthor_device *ptdev,
+				    struct panthor_fw_csg_iface *csg_iface);
+
+void panthor_fw_csg_endpoint_req_set(struct panthor_device *ptdev,
+				     struct panthor_fw_csg_iface *csg_iface, u64 value);
+
+void panthor_fw_csg_endpoint_req_update(struct panthor_device *ptdev,
+					struct panthor_fw_csg_iface *csg_iface, u64 value,
+					u64 mask);
+
 int panthor_fw_csg_wait_acks(struct panthor_device *ptdev, u32 csg_id, u32 req_mask,
 			     u32 *acked, u32 timeout_ms);
 
diff --git a/drivers/gpu/drm/panthor/panthor_gem.c b/drivers/gpu/drm/panthor/panthor_gem.c
index 2c12c1c58e2b..fbde78db270a 100644
--- a/drivers/gpu/drm/panthor/panthor_gem.c
+++ b/drivers/gpu/drm/panthor/panthor_gem.c
@@ -145,6 +145,9 @@ panthor_kernel_bo_create(struct panthor_device *ptdev, struct panthor_vm *vm,
 	bo = to_panthor_bo(&obj->base);
 	kbo->obj = &obj->base;
 	bo->flags = bo_flags;
+	bo->exclusive_vm_root_gem = panthor_vm_root_gem(vm);
+	drm_gem_object_get(bo->exclusive_vm_root_gem);
+	bo->base.base.resv = bo->exclusive_vm_root_gem->resv;
 
 	if (vm == panthor_fw_vm(ptdev))
 		debug_flags |= PANTHOR_DEBUGFS_GEM_USAGE_FLAG_FW_MAPPED;
@@ -168,9 +171,6 @@ panthor_kernel_bo_create(struct panthor_device *ptdev, struct panthor_vm *vm,
 		goto err_free_va;
 
 	kbo->vm = panthor_vm_get(vm);
-	bo->exclusive_vm_root_gem = panthor_vm_root_gem(vm);
-	drm_gem_object_get(bo->exclusive_vm_root_gem);
-	bo->base.base.resv = bo->exclusive_vm_root_gem->resv;
 	return kbo;
 
 err_free_va:
diff --git a/drivers/gpu/drm/panthor/panthor_gpu.c b/drivers/gpu/drm/panthor/panthor_gpu.c
index eda670229184..06b231b2460a 100644
--- a/drivers/gpu/drm/panthor/panthor_gpu.c
+++ b/drivers/gpu/drm/panthor/panthor_gpu.c
@@ -19,6 +19,7 @@
 
 #include "panthor_device.h"
 #include "panthor_gpu.h"
+#include "panthor_hw.h"
 #include "panthor_regs.h"
 
 /**
@@ -241,6 +242,11 @@ int panthor_gpu_block_power_on(struct panthor_device *ptdev,
 	return 0;
 }
 
+void panthor_gpu_l2_power_off(struct panthor_device *ptdev)
+{
+	panthor_gpu_power_off(ptdev, L2, ptdev->gpu_info.l2_present, 20000);
+}
+
 /**
  * panthor_gpu_l2_power_on() - Power-on the L2-cache
  * @ptdev: Device.
@@ -368,9 +374,9 @@ void panthor_gpu_suspend(struct panthor_device *ptdev)
 {
 	/* On a fast reset, simply power down the L2. */
 	if (!ptdev->reset.fast)
-		panthor_gpu_soft_reset(ptdev);
+		panthor_hw_soft_reset(ptdev);
 	else
-		panthor_gpu_power_off(ptdev, L2, 1, 20000);
+		panthor_hw_l2_power_off(ptdev);
 
 	panthor_gpu_irq_suspend(&ptdev->gpu->irq);
 }
@@ -385,6 +391,6 @@ void panthor_gpu_suspend(struct panthor_device *ptdev)
 void panthor_gpu_resume(struct panthor_device *ptdev)
 {
 	panthor_gpu_irq_resume(&ptdev->gpu->irq, GPU_INTERRUPTS_MASK);
-	panthor_gpu_l2_power_on(ptdev);
+	panthor_hw_l2_power_on(ptdev);
 }
 
diff --git a/drivers/gpu/drm/panthor/panthor_gpu.h b/drivers/gpu/drm/panthor/panthor_gpu.h
index 7c17a8c06858..12e66f48ced1 100644
--- a/drivers/gpu/drm/panthor/panthor_gpu.h
+++ b/drivers/gpu/drm/panthor/panthor_gpu.h
@@ -46,6 +46,7 @@ int panthor_gpu_block_power_off(struct panthor_device *ptdev,
 				   type ## _PWRTRANS, \
 				   mask, timeout_us)
 
+void panthor_gpu_l2_power_off(struct panthor_device *ptdev);
 int panthor_gpu_l2_power_on(struct panthor_device *ptdev);
 int panthor_gpu_flush_caches(struct panthor_device *ptdev,
 			     u32 l2, u32 lsc, u32 other);
diff --git a/drivers/gpu/drm/panthor/panthor_hw.c b/drivers/gpu/drm/panthor/panthor_hw.c
index c44033a0bba8..87ebb7ae42c4 100644
--- a/drivers/gpu/drm/panthor/panthor_hw.c
+++ b/drivers/gpu/drm/panthor/panthor_hw.c
@@ -4,12 +4,55 @@
 #include <drm/drm_print.h>
 
 #include "panthor_device.h"
+#include "panthor_gpu.h"
 #include "panthor_hw.h"
+#include "panthor_pwr.h"
 #include "panthor_regs.h"
 
 #define GPU_PROD_ID_MAKE(arch_major, prod_major) \
 	(((arch_major) << 24) | (prod_major))
 
+/** struct panthor_hw_entry - HW arch major to panthor_hw binding entry */
+struct panthor_hw_entry {
+	/** @arch_min: Minimum supported architecture major value (inclusive) */
+	u8 arch_min;
+
+	/** @arch_max: Maximum supported architecture major value (inclusive) */
+	u8 arch_max;
+
+	/** @hwdev: Pointer to panthor_hw structure */
+	struct panthor_hw *hwdev;
+};
+
+static struct panthor_hw panthor_hw_arch_v10 = {
+	.ops = {
+		.soft_reset = panthor_gpu_soft_reset,
+		.l2_power_off = panthor_gpu_l2_power_off,
+		.l2_power_on = panthor_gpu_l2_power_on,
+	},
+};
+
+static struct panthor_hw panthor_hw_arch_v14 = {
+	.ops = {
+		.soft_reset = panthor_pwr_reset_soft,
+		.l2_power_off = panthor_pwr_l2_power_off,
+		.l2_power_on = panthor_pwr_l2_power_on,
+	},
+};
+
+static struct panthor_hw_entry panthor_hw_match[] = {
+	{
+		.arch_min = 10,
+		.arch_max = 13,
+		.hwdev = &panthor_hw_arch_v10,
+	},
+	{
+		.arch_min = 14,
+		.arch_max = 14,
+		.hwdev = &panthor_hw_arch_v14,
+	},
+};
+
 static char *get_gpu_model_name(struct panthor_device *ptdev)
 {
 	const u32 gpu_id = ptdev->gpu_info.gpu_id;
@@ -55,6 +98,12 @@ static char *get_gpu_model_name(struct panthor_device *ptdev)
 		fallthrough;
 	case GPU_PROD_ID_MAKE(13, 1):
 		return "Mali-G625";
+	case GPU_PROD_ID_MAKE(14, 0):
+		return "Mali-G1-Ultra";
+	case GPU_PROD_ID_MAKE(14, 1):
+		return "Mali-G1-Premium";
+	case GPU_PROD_ID_MAKE(14, 3):
+		return "Mali-G1-Pro";
 	}
 
 	return "(Unknown Mali GPU)";
@@ -64,7 +113,6 @@ static void panthor_gpu_info_init(struct panthor_device *ptdev)
 {
 	unsigned int i;
 
-	ptdev->gpu_info.gpu_id = gpu_read(ptdev, GPU_ID);
 	ptdev->gpu_info.csf_id = gpu_read(ptdev, GPU_CSF_ID);
 	ptdev->gpu_info.gpu_rev = gpu_read(ptdev, GPU_REVID);
 	ptdev->gpu_info.core_features = gpu_read(ptdev, GPU_CORE_FEATURES);
@@ -82,12 +130,19 @@ static void panthor_gpu_info_init(struct panthor_device *ptdev)
 
 	ptdev->gpu_info.as_present = gpu_read(ptdev, GPU_AS_PRESENT);
 
-	ptdev->gpu_info.shader_present = gpu_read64(ptdev, GPU_SHADER_PRESENT);
-	ptdev->gpu_info.tiler_present = gpu_read64(ptdev, GPU_TILER_PRESENT);
-	ptdev->gpu_info.l2_present = gpu_read64(ptdev, GPU_L2_PRESENT);
-
 	/* Introduced in arch 11.x */
 	ptdev->gpu_info.gpu_features = gpu_read64(ptdev, GPU_FEATURES);
+
+	if (panthor_hw_has_pwr_ctrl(ptdev)) {
+		/* Introduced in arch 14.x */
+		ptdev->gpu_info.l2_present = gpu_read64(ptdev, PWR_L2_PRESENT);
+		ptdev->gpu_info.tiler_present = gpu_read64(ptdev, PWR_TILER_PRESENT);
+		ptdev->gpu_info.shader_present = gpu_read64(ptdev, PWR_SHADER_PRESENT);
+	} else {
+		ptdev->gpu_info.shader_present = gpu_read64(ptdev, GPU_SHADER_PRESENT);
+		ptdev->gpu_info.tiler_present = gpu_read64(ptdev, GPU_TILER_PRESENT);
+		ptdev->gpu_info.l2_present = gpu_read64(ptdev, GPU_L2_PRESENT);
+	}
 }
 
 static void panthor_hw_info_init(struct panthor_device *ptdev)
@@ -119,8 +174,50 @@ static void panthor_hw_info_init(struct panthor_device *ptdev)
 		 ptdev->gpu_info.tiler_present);
 }
 
+static int panthor_hw_bind_device(struct panthor_device *ptdev)
+{
+	struct panthor_hw *hdev = NULL;
+	const u32 arch_major = GPU_ARCH_MAJOR(ptdev->gpu_info.gpu_id);
+	int i = 0;
+
+	for (i = 0; i < ARRAY_SIZE(panthor_hw_match); i++) {
+		struct panthor_hw_entry *entry = &panthor_hw_match[i];
+
+		if (arch_major >= entry->arch_min && arch_major <= entry->arch_max) {
+			hdev = entry->hwdev;
+			break;
+		}
+	}
+
+	if (!hdev)
+		return -EOPNOTSUPP;
+
+	ptdev->hw = hdev;
+
+	return 0;
+}
+
+static int panthor_hw_gpu_id_init(struct panthor_device *ptdev)
+{
+	ptdev->gpu_info.gpu_id = gpu_read(ptdev, GPU_ID);
+	if (!ptdev->gpu_info.gpu_id)
+		return -ENXIO;
+
+	return 0;
+}
+
 int panthor_hw_init(struct panthor_device *ptdev)
 {
+	int ret = 0;
+
+	ret = panthor_hw_gpu_id_init(ptdev);
+	if (ret)
+		return ret;
+
+	ret = panthor_hw_bind_device(ptdev);
+	if (ret)
+		return ret;
+
 	panthor_hw_info_init(ptdev);
 
 	return 0;
diff --git a/drivers/gpu/drm/panthor/panthor_hw.h b/drivers/gpu/drm/panthor/panthor_hw.h
index 0af6acc6aa6a..56c68c1e9c26 100644
--- a/drivers/gpu/drm/panthor/panthor_hw.h
+++ b/drivers/gpu/drm/panthor/panthor_hw.h
@@ -4,8 +4,53 @@
 #ifndef __PANTHOR_HW_H__
 #define __PANTHOR_HW_H__
 
-struct panthor_device;
+#include "panthor_device.h"
+#include "panthor_regs.h"
+
+/**
+ * struct panthor_hw_ops - HW operations that are specific to a GPU
+ */
+struct panthor_hw_ops {
+	/** @soft_reset: Soft reset function pointer */
+	int (*soft_reset)(struct panthor_device *ptdev);
+
+	/** @l2_power_off: L2 power off function pointer */
+	void (*l2_power_off)(struct panthor_device *ptdev);
+
+	/** @l2_power_on: L2 power on function pointer */
+	int (*l2_power_on)(struct panthor_device *ptdev);
+};
+
+/**
+ * struct panthor_hw - GPU specific register mapping and functions
+ */
+struct panthor_hw {
+	/** @features: Bitmap containing panthor_hw_feature */
+
+	/** @ops: Panthor HW specific operations */
+	struct panthor_hw_ops ops;
+};
 
 int panthor_hw_init(struct panthor_device *ptdev);
 
+static inline int panthor_hw_soft_reset(struct panthor_device *ptdev)
+{
+	return ptdev->hw->ops.soft_reset(ptdev);
+}
+
+static inline int panthor_hw_l2_power_on(struct panthor_device *ptdev)
+{
+	return ptdev->hw->ops.l2_power_on(ptdev);
+}
+
+static inline void panthor_hw_l2_power_off(struct panthor_device *ptdev)
+{
+	ptdev->hw->ops.l2_power_off(ptdev);
+}
+
+static inline bool panthor_hw_has_pwr_ctrl(struct panthor_device *ptdev)
+{
+	return GPU_ARCH_MAJOR(ptdev->gpu_info.gpu_id) >= 14;
+}
+
 #endif /* __PANTHOR_HW_H__ */
diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c
index 478ea98db95c..d4839d282689 100644
--- a/drivers/gpu/drm/panthor/panthor_mmu.c
+++ b/drivers/gpu/drm/panthor/panthor_mmu.c
@@ -904,10 +904,9 @@ static int panthor_vm_unmap_pages(struct panthor_vm *vm, u64 iova, u64 size)
 {
 	struct panthor_device *ptdev = vm->ptdev;
 	struct io_pgtable_ops *ops = vm->pgtbl_ops;
+	u64 start_iova = iova;
 	u64 offset = 0;
 
-	drm_dbg(&ptdev->base, "unmap: as=%d, iova=%llx, len=%llx", vm->as.id, iova, size);
-
 	while (offset < size) {
 		size_t unmapped_sz = 0, pgcount;
 		size_t pgsize = get_pgsize(iova + offset, size - offset, &pgcount);
@@ -922,6 +921,12 @@ static int panthor_vm_unmap_pages(struct panthor_vm *vm, u64 iova, u64 size)
 			panthor_vm_flush_range(vm, iova, offset + unmapped_sz);
 			return  -EINVAL;
 		}
+
+		drm_dbg(&ptdev->base,
+			"unmap: as=%d, iova=0x%llx, sz=%llu, va=0x%llx, pgcnt=%zu, pgsz=%zu",
+			vm->as.id, start_iova, size, iova + offset,
+			unmapped_sz / pgsize, pgsize);
+
 		offset += unmapped_sz;
 	}
 
@@ -937,6 +942,7 @@ panthor_vm_map_pages(struct panthor_vm *vm, u64 iova, int prot,
 	struct scatterlist *sgl;
 	struct io_pgtable_ops *ops = vm->pgtbl_ops;
 	u64 start_iova = iova;
+	u64 start_size = size;
 	int ret;
 
 	if (!size)
@@ -956,15 +962,18 @@ panthor_vm_map_pages(struct panthor_vm *vm, u64 iova, int prot,
 		len = min_t(size_t, len, size);
 		size -= len;
 
-		drm_dbg(&ptdev->base, "map: as=%d, iova=%llx, paddr=%pad, len=%zx",
-			vm->as.id, iova, &paddr, len);
-
 		while (len) {
 			size_t pgcount, mapped = 0;
 			size_t pgsize = get_pgsize(iova | paddr, len, &pgcount);
 
 			ret = ops->map_pages(ops, iova, paddr, pgsize, pgcount, prot,
 					     GFP_KERNEL, &mapped);
+
+			drm_dbg(&ptdev->base,
+				"map: as=%d, iova=0x%llx, sz=%llu, va=0x%llx, pa=%pad, pgcnt=%zu, pgsz=%zu",
+				vm->as.id, start_iova, start_size, iova, &paddr,
+				mapped / pgsize, pgsize);
+
 			iova += mapped;
 			paddr += mapped;
 			len -= mapped;
diff --git a/drivers/gpu/drm/panthor/panthor_pwr.c b/drivers/gpu/drm/panthor/panthor_pwr.c
new file mode 100644
index 000000000000..57cfc7ce715b
--- /dev/null
+++ b/drivers/gpu/drm/panthor/panthor_pwr.c
@@ -0,0 +1,549 @@
+// SPDX-License-Identifier: GPL-2.0 or MIT
+/* Copyright 2025 ARM Limited. All rights reserved. */
+
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/cleanup.h>
+#include <linux/iopoll.h>
+#include <linux/wait.h>
+
+#include <drm/drm_managed.h>
+#include <drm/drm_print.h>
+
+#include "panthor_device.h"
+#include "panthor_hw.h"
+#include "panthor_pwr.h"
+#include "panthor_regs.h"
+
+#define PWR_INTERRUPTS_MASK \
+	(PWR_IRQ_POWER_CHANGED_SINGLE | \
+	 PWR_IRQ_POWER_CHANGED_ALL | \
+	 PWR_IRQ_DELEGATION_CHANGED | \
+	 PWR_IRQ_RESET_COMPLETED | \
+	 PWR_IRQ_RETRACT_COMPLETED | \
+	 PWR_IRQ_INSPECT_COMPLETED | \
+	 PWR_IRQ_COMMAND_NOT_ALLOWED | \
+	 PWR_IRQ_COMMAND_INVALID)
+
+#define PWR_ALL_CORES_MASK		GENMASK_U64(63, 0)
+
+#define PWR_DOMAIN_MAX_BITS		16
+
+#define PWR_TRANSITION_TIMEOUT_US	(2ULL * USEC_PER_SEC)
+
+#define PWR_RETRACT_TIMEOUT_US		(2ULL * USEC_PER_MSEC)
+
+#define PWR_RESET_TIMEOUT_MS		500
+
+/**
+ * struct panthor_pwr - PWR_CONTROL block management data.
+ */
+struct panthor_pwr {
+	/** @irq: PWR irq. */
+	struct panthor_irq irq;
+
+	/** @reqs_lock: Lock protecting access to pending_reqs. */
+	spinlock_t reqs_lock;
+
+	/** @pending_reqs: Pending PWR requests. */
+	u32 pending_reqs;
+
+	/** @reqs_acked: PWR request wait queue. */
+	wait_queue_head_t reqs_acked;
+};
+
+static void panthor_pwr_irq_handler(struct panthor_device *ptdev, u32 status)
+{
+	spin_lock(&ptdev->pwr->reqs_lock);
+	gpu_write(ptdev, PWR_INT_CLEAR, status);
+
+	if (unlikely(status & PWR_IRQ_COMMAND_NOT_ALLOWED))
+		drm_err(&ptdev->base, "PWR_IRQ: COMMAND_NOT_ALLOWED");
+
+	if (unlikely(status & PWR_IRQ_COMMAND_INVALID))
+		drm_err(&ptdev->base, "PWR_IRQ: COMMAND_INVALID");
+
+	if (status & ptdev->pwr->pending_reqs) {
+		ptdev->pwr->pending_reqs &= ~status;
+		wake_up_all(&ptdev->pwr->reqs_acked);
+	}
+	spin_unlock(&ptdev->pwr->reqs_lock);
+}
+PANTHOR_IRQ_HANDLER(pwr, PWR, panthor_pwr_irq_handler);
+
+static void panthor_pwr_write_command(struct panthor_device *ptdev, u32 command, u64 args)
+{
+	if (args)
+		gpu_write64(ptdev, PWR_CMDARG, args);
+
+	gpu_write(ptdev, PWR_COMMAND, command);
+}
+
+static bool reset_irq_raised(struct panthor_device *ptdev)
+{
+	return gpu_read(ptdev, PWR_INT_RAWSTAT) & PWR_IRQ_RESET_COMPLETED;
+}
+
+static bool reset_pending(struct panthor_device *ptdev)
+{
+	return (ptdev->pwr->pending_reqs & PWR_IRQ_RESET_COMPLETED);
+}
+
+static int panthor_pwr_reset(struct panthor_device *ptdev, u32 reset_cmd)
+{
+	scoped_guard(spinlock_irqsave, &ptdev->pwr->reqs_lock) {
+		if (reset_pending(ptdev)) {
+			drm_WARN(&ptdev->base, 1, "Reset already pending");
+		} else {
+			ptdev->pwr->pending_reqs |= PWR_IRQ_RESET_COMPLETED;
+			gpu_write(ptdev, PWR_INT_CLEAR, PWR_IRQ_RESET_COMPLETED);
+			panthor_pwr_write_command(ptdev, reset_cmd, 0);
+		}
+	}
+
+	if (!wait_event_timeout(ptdev->pwr->reqs_acked, !reset_pending(ptdev),
+				msecs_to_jiffies(PWR_RESET_TIMEOUT_MS))) {
+		guard(spinlock_irqsave)(&ptdev->pwr->reqs_lock);
+
+		if (reset_pending(ptdev) && !reset_irq_raised(ptdev)) {
+			drm_err(&ptdev->base, "RESET timed out (0x%x)", reset_cmd);
+			return -ETIMEDOUT;
+		}
+
+		ptdev->pwr->pending_reqs &= ~PWR_IRQ_RESET_COMPLETED;
+	}
+
+	return 0;
+}
+
+static const char *get_domain_name(u8 domain)
+{
+	switch (domain) {
+	case PWR_COMMAND_DOMAIN_L2:
+		return "L2";
+	case PWR_COMMAND_DOMAIN_TILER:
+		return "Tiler";
+	case PWR_COMMAND_DOMAIN_SHADER:
+		return "Shader";
+	case PWR_COMMAND_DOMAIN_BASE:
+		return "Base";
+	case PWR_COMMAND_DOMAIN_STACK:
+		return "Stack";
+	}
+	return "Unknown";
+}
+
+static u32 get_domain_base(u8 domain)
+{
+	switch (domain) {
+	case PWR_COMMAND_DOMAIN_L2:
+		return PWR_L2_PRESENT;
+	case PWR_COMMAND_DOMAIN_TILER:
+		return PWR_TILER_PRESENT;
+	case PWR_COMMAND_DOMAIN_SHADER:
+		return PWR_SHADER_PRESENT;
+	case PWR_COMMAND_DOMAIN_BASE:
+		return PWR_BASE_PRESENT;
+	case PWR_COMMAND_DOMAIN_STACK:
+		return PWR_STACK_PRESENT;
+	}
+	return 0;
+}
+
+static u32 get_domain_ready_reg(u32 domain)
+{
+	return get_domain_base(domain) + (PWR_L2_READY - PWR_L2_PRESENT);
+}
+
+static u32 get_domain_pwrtrans_reg(u32 domain)
+{
+	return get_domain_base(domain) + (PWR_L2_PWRTRANS - PWR_L2_PRESENT);
+}
+
+static bool is_valid_domain(u32 domain)
+{
+	return get_domain_base(domain) != 0;
+}
+
+static bool has_rtu(struct panthor_device *ptdev)
+{
+	return ptdev->gpu_info.gpu_features & GPU_FEATURES_RAY_TRAVERSAL;
+}
+
+static u8 get_domain_subdomain(struct panthor_device *ptdev, u32 domain)
+{
+	if (domain == PWR_COMMAND_DOMAIN_SHADER && has_rtu(ptdev))
+		return PWR_COMMAND_SUBDOMAIN_RTU;
+
+	return 0;
+}
+
+static int panthor_pwr_domain_wait_transition(struct panthor_device *ptdev, u32 domain,
+					      u32 timeout_us)
+{
+	u32 pwrtrans_reg = get_domain_pwrtrans_reg(domain);
+	u64 val;
+	int ret = 0;
+
+	ret = gpu_read64_poll_timeout(ptdev, pwrtrans_reg, val, !(PWR_ALL_CORES_MASK & val), 100,
+				      timeout_us);
+	if (ret) {
+		drm_err(&ptdev->base, "%s domain power in transition, pwrtrans(0x%llx)",
+			get_domain_name(domain), val);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void panthor_pwr_debug_info_show(struct panthor_device *ptdev)
+{
+	drm_info(&ptdev->base, "GPU_FEATURES:    0x%016llx", gpu_read64(ptdev, GPU_FEATURES));
+	drm_info(&ptdev->base, "PWR_STATUS:      0x%016llx", gpu_read64(ptdev, PWR_STATUS));
+	drm_info(&ptdev->base, "L2_PRESENT:      0x%016llx", gpu_read64(ptdev, PWR_L2_PRESENT));
+	drm_info(&ptdev->base, "L2_PWRTRANS:     0x%016llx", gpu_read64(ptdev, PWR_L2_PWRTRANS));
+	drm_info(&ptdev->base, "L2_READY:        0x%016llx", gpu_read64(ptdev, PWR_L2_READY));
+	drm_info(&ptdev->base, "TILER_PRESENT:   0x%016llx", gpu_read64(ptdev, PWR_TILER_PRESENT));
+	drm_info(&ptdev->base, "TILER_PWRTRANS:  0x%016llx", gpu_read64(ptdev, PWR_TILER_PWRTRANS));
+	drm_info(&ptdev->base, "TILER_READY:     0x%016llx", gpu_read64(ptdev, PWR_TILER_READY));
+	drm_info(&ptdev->base, "SHADER_PRESENT:  0x%016llx", gpu_read64(ptdev, PWR_SHADER_PRESENT));
+	drm_info(&ptdev->base, "SHADER_PWRTRANS: 0x%016llx", gpu_read64(ptdev, PWR_SHADER_PWRTRANS));
+	drm_info(&ptdev->base, "SHADER_READY:    0x%016llx", gpu_read64(ptdev, PWR_SHADER_READY));
+}
+
+static int panthor_pwr_domain_transition(struct panthor_device *ptdev, u32 cmd, u32 domain,
+					 u64 mask, u32 timeout_us)
+{
+	u32 ready_reg = get_domain_ready_reg(domain);
+	u32 pwr_cmd = PWR_COMMAND_DEF(cmd, domain, get_domain_subdomain(ptdev, domain));
+	u64 expected_val = 0;
+	u64 val;
+	int ret = 0;
+
+	if (drm_WARN_ON(&ptdev->base, !is_valid_domain(domain)))
+		return -EINVAL;
+
+	switch (cmd) {
+	case PWR_COMMAND_POWER_DOWN:
+		expected_val = 0;
+		break;
+	case PWR_COMMAND_POWER_UP:
+		expected_val = mask;
+		break;
+	default:
+		drm_err(&ptdev->base, "Invalid power domain transition command (0x%x)", cmd);
+		return -EINVAL;
+	}
+
+	ret = panthor_pwr_domain_wait_transition(ptdev, domain, timeout_us);
+	if (ret)
+		return ret;
+
+	/* domain already in target state, return early */
+	if ((gpu_read64(ptdev, ready_reg) & mask) == expected_val)
+		return 0;
+
+	panthor_pwr_write_command(ptdev, pwr_cmd, mask);
+
+	ret = gpu_read64_poll_timeout(ptdev, ready_reg, val, (mask & val) == expected_val, 100,
+				      timeout_us);
+	if (ret) {
+		drm_err(&ptdev->base,
+			"timeout waiting on %s power domain transition, cmd(0x%x), arg(0x%llx)",
+			get_domain_name(domain), pwr_cmd, mask);
+		panthor_pwr_debug_info_show(ptdev);
+		return ret;
+	}
+
+	return 0;
+}
+
+#define panthor_pwr_domain_power_off(__ptdev, __domain, __mask, __timeout_us)            \
+	panthor_pwr_domain_transition(__ptdev, PWR_COMMAND_POWER_DOWN, __domain, __mask, \
+				      __timeout_us)
+
+#define panthor_pwr_domain_power_on(__ptdev, __domain, __mask, __timeout_us) \
+	panthor_pwr_domain_transition(__ptdev, PWR_COMMAND_POWER_UP, __domain, __mask, __timeout_us)
+
+/**
+ * retract_domain() - Retract control of a domain from MCU
+ * @ptdev: Device.
+ * @domain: Domain to retract the control
+ *
+ * Retracting L2 domain is not expected since it won't be delegated.
+ *
+ * Return: 0 on success or retracted already.
+ *         -EPERM if domain is L2.
+ *         A negative error code otherwise.
+ */
+static int retract_domain(struct panthor_device *ptdev, u32 domain)
+{
+	const u32 pwr_cmd = PWR_COMMAND_DEF(PWR_COMMAND_RETRACT, domain, 0);
+	const u64 pwr_status = gpu_read64(ptdev, PWR_STATUS);
+	const u64 delegated_mask = PWR_STATUS_DOMAIN_DELEGATED(domain);
+	const u64 allow_mask = PWR_STATUS_DOMAIN_ALLOWED(domain);
+	u64 val;
+	int ret;
+
+	if (drm_WARN_ON(&ptdev->base, domain == PWR_COMMAND_DOMAIN_L2))
+		return -EPERM;
+
+	ret = gpu_read64_poll_timeout(ptdev, PWR_STATUS, val, !(PWR_STATUS_RETRACT_PENDING & val),
+				      0, PWR_RETRACT_TIMEOUT_US);
+	if (ret) {
+		drm_err(&ptdev->base, "%s domain retract pending", get_domain_name(domain));
+		return ret;
+	}
+
+	if (!(pwr_status & delegated_mask)) {
+		drm_dbg(&ptdev->base, "%s domain already retracted", get_domain_name(domain));
+		return 0;
+	}
+
+	panthor_pwr_write_command(ptdev, pwr_cmd, 0);
+
+	/*
+	 * On successful retraction
+	 * allow-flag will be set with delegated-flag being cleared.
+	 */
+	ret = gpu_read64_poll_timeout(ptdev, PWR_STATUS, val,
+				      ((delegated_mask | allow_mask) & val) == allow_mask, 10,
+				      PWR_TRANSITION_TIMEOUT_US);
+	if (ret) {
+		drm_err(&ptdev->base, "Retracting %s domain timeout, cmd(0x%x)",
+			get_domain_name(domain), pwr_cmd);
+		return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * delegate_domain() - Delegate control of a domain to MCU
+ * @ptdev: Device.
+ * @domain: Domain to delegate the control
+ *
+ * Delegating L2 domain is prohibited.
+ *
+ * Return:
+ * *       0 on success or delegated already.
+ * *       -EPERM if domain is L2.
+ * *       A negative error code otherwise.
+ */
+static int delegate_domain(struct panthor_device *ptdev, u32 domain)
+{
+	const u32 pwr_cmd = PWR_COMMAND_DEF(PWR_COMMAND_DELEGATE, domain, 0);
+	const u64 pwr_status = gpu_read64(ptdev, PWR_STATUS);
+	const u64 allow_mask = PWR_STATUS_DOMAIN_ALLOWED(domain);
+	const u64 delegated_mask = PWR_STATUS_DOMAIN_DELEGATED(domain);
+	u64 val;
+	int ret;
+
+	if (drm_WARN_ON(&ptdev->base, domain == PWR_COMMAND_DOMAIN_L2))
+		return -EPERM;
+
+	/* Already delegated, exit early */
+	if (pwr_status & delegated_mask)
+		return 0;
+
+	/* Check if the command is allowed before delegating. */
+	if (!(pwr_status & allow_mask)) {
+		drm_warn(&ptdev->base, "Delegating %s domain not allowed", get_domain_name(domain));
+		return -EPERM;
+	}
+
+	ret = panthor_pwr_domain_wait_transition(ptdev, domain, PWR_TRANSITION_TIMEOUT_US);
+	if (ret)
+		return ret;
+
+	panthor_pwr_write_command(ptdev, pwr_cmd, 0);
+
+	/*
+	 * On successful delegation
+	 * allow-flag will be cleared with delegated-flag being set.
+	 */
+	ret = gpu_read64_poll_timeout(ptdev, PWR_STATUS, val,
+				      ((delegated_mask | allow_mask) & val) == delegated_mask,
+				      10, PWR_TRANSITION_TIMEOUT_US);
+	if (ret) {
+		drm_err(&ptdev->base, "Delegating %s domain timeout, cmd(0x%x)",
+			get_domain_name(domain), pwr_cmd);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int panthor_pwr_delegate_domains(struct panthor_device *ptdev)
+{
+	int ret;
+
+	if (!ptdev->pwr)
+		return 0;
+
+	ret = delegate_domain(ptdev, PWR_COMMAND_DOMAIN_SHADER);
+	if (ret)
+		return ret;
+
+	ret = delegate_domain(ptdev, PWR_COMMAND_DOMAIN_TILER);
+	if (ret)
+		goto err_retract_shader;
+
+	return 0;
+
+err_retract_shader:
+	retract_domain(ptdev, PWR_COMMAND_DOMAIN_SHADER);
+
+	return ret;
+}
+
+/**
+ * panthor_pwr_domain_force_off - Forcefully power down a domain.
+ * @ptdev: Device.
+ * @domain: Domain to forcefully power down.
+ *
+ * This function will attempt to retract and power off the requested power
+ * domain. However, if retraction fails, the operation is aborted. If power off
+ * fails, the domain will remain retracted and under the host control.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+static int panthor_pwr_domain_force_off(struct panthor_device *ptdev, u32 domain)
+{
+	const u64 domain_ready = gpu_read64(ptdev, get_domain_ready_reg(domain));
+	int ret;
+
+	/* Domain already powered down, early exit. */
+	if (!domain_ready)
+		return 0;
+
+	/* Domain has to be in host control to issue power off command. */
+	ret = retract_domain(ptdev, domain);
+	if (ret)
+		return ret;
+
+	return panthor_pwr_domain_power_off(ptdev, domain, domain_ready, PWR_TRANSITION_TIMEOUT_US);
+}
+
+void panthor_pwr_unplug(struct panthor_device *ptdev)
+{
+	unsigned long flags;
+
+	if (!ptdev->pwr)
+		return;
+
+	/* Make sure the IRQ handler is not running after that point. */
+	panthor_pwr_irq_suspend(&ptdev->pwr->irq);
+
+	/* Wake-up all waiters. */
+	spin_lock_irqsave(&ptdev->pwr->reqs_lock, flags);
+	ptdev->pwr->pending_reqs = 0;
+	wake_up_all(&ptdev->pwr->reqs_acked);
+	spin_unlock_irqrestore(&ptdev->pwr->reqs_lock, flags);
+}
+
+int panthor_pwr_init(struct panthor_device *ptdev)
+{
+	struct panthor_pwr *pwr;
+	int err, irq;
+
+	if (!panthor_hw_has_pwr_ctrl(ptdev))
+		return 0;
+
+	pwr = drmm_kzalloc(&ptdev->base, sizeof(*pwr), GFP_KERNEL);
+	if (!pwr)
+		return -ENOMEM;
+
+	spin_lock_init(&pwr->reqs_lock);
+	init_waitqueue_head(&pwr->reqs_acked);
+	ptdev->pwr = pwr;
+
+	irq = platform_get_irq_byname(to_platform_device(ptdev->base.dev), "gpu");
+	if (irq < 0)
+		return irq;
+
+	err = panthor_request_pwr_irq(ptdev, &pwr->irq, irq, PWR_INTERRUPTS_MASK);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+int panthor_pwr_reset_soft(struct panthor_device *ptdev)
+{
+	if (!(gpu_read64(ptdev, PWR_STATUS) & PWR_STATUS_ALLOW_SOFT_RESET)) {
+		drm_err(&ptdev->base, "RESET_SOFT not allowed");
+		return -EOPNOTSUPP;
+	}
+
+	return panthor_pwr_reset(ptdev, PWR_COMMAND_RESET_SOFT);
+}
+
+void panthor_pwr_l2_power_off(struct panthor_device *ptdev)
+{
+	const u64 l2_allow_mask = PWR_STATUS_DOMAIN_ALLOWED(PWR_COMMAND_DOMAIN_L2);
+	const u64 pwr_status = gpu_read64(ptdev, PWR_STATUS);
+
+	/* Abort if L2 power off constraints are not satisfied */
+	if (!(pwr_status & l2_allow_mask)) {
+		drm_warn(&ptdev->base, "Power off L2 domain not allowed");
+		return;
+	}
+
+	/* It is expected that when halting the MCU, it would power down its
+	 * delegated domains. However, an unresponsive or hung MCU may not do
+	 * so, which is why we need to check and retract the domains back into
+	 * host control to be powered down in the right order before powering
+	 * down the L2.
+	 */
+	if (panthor_pwr_domain_force_off(ptdev, PWR_COMMAND_DOMAIN_TILER))
+		return;
+
+	if (panthor_pwr_domain_force_off(ptdev, PWR_COMMAND_DOMAIN_SHADER))
+		return;
+
+	panthor_pwr_domain_power_off(ptdev, PWR_COMMAND_DOMAIN_L2, ptdev->gpu_info.l2_present,
+				     PWR_TRANSITION_TIMEOUT_US);
+}
+
+int panthor_pwr_l2_power_on(struct panthor_device *ptdev)
+{
+	const u32 pwr_status = gpu_read64(ptdev, PWR_STATUS);
+	const u32 l2_allow_mask = PWR_STATUS_DOMAIN_ALLOWED(PWR_COMMAND_DOMAIN_L2);
+	int ret;
+
+	if ((pwr_status & l2_allow_mask) == 0) {
+		drm_warn(&ptdev->base, "Power on L2 domain not allowed");
+		return -EPERM;
+	}
+
+	ret = panthor_pwr_domain_power_on(ptdev, PWR_COMMAND_DOMAIN_L2, ptdev->gpu_info.l2_present,
+					  PWR_TRANSITION_TIMEOUT_US);
+	if (ret)
+		return ret;
+
+	/* Delegate control of the shader and tiler power domains to the MCU as
+	 * it can better manage which shader/tiler cores need to be powered up
+	 * or can be powered down based on currently running jobs.
+	 *
+	 * If the shader and tiler domains are already delegated to the MCU,
+	 * this call would just return early.
+	 */
+	return panthor_pwr_delegate_domains(ptdev);
+}
+
+void panthor_pwr_suspend(struct panthor_device *ptdev)
+{
+	if (!ptdev->pwr)
+		return;
+
+	panthor_pwr_irq_suspend(&ptdev->pwr->irq);
+}
+
+void panthor_pwr_resume(struct panthor_device *ptdev)
+{
+	if (!ptdev->pwr)
+		return;
+
+	panthor_pwr_irq_resume(&ptdev->pwr->irq, PWR_INTERRUPTS_MASK);
+}
diff --git a/drivers/gpu/drm/panthor/panthor_pwr.h b/drivers/gpu/drm/panthor/panthor_pwr.h
new file mode 100644
index 000000000000..adf1f6136abc
--- /dev/null
+++ b/drivers/gpu/drm/panthor/panthor_pwr.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2025 ARM Limited. All rights reserved. */
+
+#ifndef __PANTHOR_PWR_H__
+#define __PANTHOR_PWR_H__
+
+struct panthor_device;
+
+void panthor_pwr_unplug(struct panthor_device *ptdev);
+
+int panthor_pwr_init(struct panthor_device *ptdev);
+
+int panthor_pwr_reset_soft(struct panthor_device *ptdev);
+
+void panthor_pwr_l2_power_off(struct panthor_device *ptdev);
+
+int panthor_pwr_l2_power_on(struct panthor_device *ptdev);
+
+void panthor_pwr_suspend(struct panthor_device *ptdev);
+
+void panthor_pwr_resume(struct panthor_device *ptdev);
+
+#endif /* __PANTHOR_PWR_H__ */
diff --git a/drivers/gpu/drm/panthor/panthor_regs.h b/drivers/gpu/drm/panthor/panthor_regs.h
index 8fa69f33e911..08bf06c452d6 100644
--- a/drivers/gpu/drm/panthor/panthor_regs.h
+++ b/drivers/gpu/drm/panthor/panthor_regs.h
@@ -74,6 +74,7 @@
 
 #define GPU_FEATURES					0x60
 #define   GPU_FEATURES_RAY_INTERSECTION			BIT(2)
+#define   GPU_FEATURES_RAY_TRAVERSAL			BIT(5)
 
 #define GPU_TIMESTAMP_OFFSET				0x88
 #define GPU_CYCLE_COUNT					0x90
@@ -209,4 +210,82 @@
 #define CSF_DOORBELL(i)					(0x80000 + ((i) * 0x10000))
 #define CSF_GLB_DOORBELL_ID				0
 
+/* PWR Control registers */
+
+#define PWR_CONTROL_BASE				0x800
+#define PWR_CTRL_REG(x)					(PWR_CONTROL_BASE + (x))
+
+#define PWR_INT_RAWSTAT					PWR_CTRL_REG(0x0)
+#define PWR_INT_CLEAR					PWR_CTRL_REG(0x4)
+#define PWR_INT_MASK					PWR_CTRL_REG(0x8)
+#define PWR_INT_STAT					PWR_CTRL_REG(0xc)
+#define   PWR_IRQ_POWER_CHANGED_SINGLE			BIT(0)
+#define   PWR_IRQ_POWER_CHANGED_ALL			BIT(1)
+#define   PWR_IRQ_DELEGATION_CHANGED			BIT(2)
+#define   PWR_IRQ_RESET_COMPLETED			BIT(3)
+#define   PWR_IRQ_RETRACT_COMPLETED			BIT(4)
+#define   PWR_IRQ_INSPECT_COMPLETED			BIT(5)
+#define   PWR_IRQ_COMMAND_NOT_ALLOWED			BIT(30)
+#define   PWR_IRQ_COMMAND_INVALID			BIT(31)
+
+#define PWR_STATUS					PWR_CTRL_REG(0x20)
+#define   PWR_STATUS_ALLOW_L2				BIT_U64(0)
+#define   PWR_STATUS_ALLOW_TILER			BIT_U64(1)
+#define   PWR_STATUS_ALLOW_SHADER			BIT_U64(8)
+#define   PWR_STATUS_ALLOW_BASE				BIT_U64(14)
+#define   PWR_STATUS_ALLOW_STACK			BIT_U64(15)
+#define   PWR_STATUS_DOMAIN_ALLOWED(x)			BIT_U64(x)
+#define   PWR_STATUS_DELEGATED_L2			BIT_U64(16)
+#define   PWR_STATUS_DELEGATED_TILER			BIT_U64(17)
+#define   PWR_STATUS_DELEGATED_SHADER			BIT_U64(24)
+#define   PWR_STATUS_DELEGATED_BASE			BIT_U64(30)
+#define   PWR_STATUS_DELEGATED_STACK			BIT_U64(31)
+#define   PWR_STATUS_DELEGATED_SHIFT			16
+#define   PWR_STATUS_DOMAIN_DELEGATED(x)		BIT_U64((x) + PWR_STATUS_DELEGATED_SHIFT)
+#define   PWR_STATUS_ALLOW_SOFT_RESET			BIT_U64(33)
+#define   PWR_STATUS_ALLOW_FAST_RESET			BIT_U64(34)
+#define   PWR_STATUS_POWER_PENDING			BIT_U64(41)
+#define   PWR_STATUS_RESET_PENDING			BIT_U64(42)
+#define   PWR_STATUS_RETRACT_PENDING			BIT_U64(43)
+#define   PWR_STATUS_INSPECT_PENDING			BIT_U64(44)
+
+#define PWR_COMMAND					PWR_CTRL_REG(0x28)
+#define   PWR_COMMAND_POWER_UP				0x10
+#define   PWR_COMMAND_POWER_DOWN			0x11
+#define   PWR_COMMAND_DELEGATE				0x20
+#define   PWR_COMMAND_RETRACT				0x21
+#define   PWR_COMMAND_RESET_SOFT			0x31
+#define   PWR_COMMAND_RESET_FAST			0x32
+#define   PWR_COMMAND_INSPECT				0xF0
+#define   PWR_COMMAND_DOMAIN_L2				0
+#define   PWR_COMMAND_DOMAIN_TILER			1
+#define   PWR_COMMAND_DOMAIN_SHADER			8
+#define   PWR_COMMAND_DOMAIN_BASE			14
+#define   PWR_COMMAND_DOMAIN_STACK			15
+#define   PWR_COMMAND_SUBDOMAIN_RTU			BIT(0)
+#define   PWR_COMMAND_DEF(cmd, domain, subdomain)	\
+	(((subdomain) << 16) | ((domain) << 8) | (cmd))
+
+#define PWR_CMDARG					PWR_CTRL_REG(0x30)
+
+#define PWR_L2_PRESENT					PWR_CTRL_REG(0x100)
+#define PWR_L2_READY					PWR_CTRL_REG(0x108)
+#define PWR_L2_PWRTRANS					PWR_CTRL_REG(0x110)
+#define PWR_L2_PWRACTIVE				PWR_CTRL_REG(0x118)
+#define PWR_TILER_PRESENT				PWR_CTRL_REG(0x140)
+#define PWR_TILER_READY					PWR_CTRL_REG(0x148)
+#define PWR_TILER_PWRTRANS				PWR_CTRL_REG(0x150)
+#define PWR_TILER_PWRACTIVE				PWR_CTRL_REG(0x158)
+#define PWR_SHADER_PRESENT				PWR_CTRL_REG(0x200)
+#define PWR_SHADER_READY				PWR_CTRL_REG(0x208)
+#define PWR_SHADER_PWRTRANS				PWR_CTRL_REG(0x210)
+#define PWR_SHADER_PWRACTIVE				PWR_CTRL_REG(0x218)
+#define PWR_BASE_PRESENT				PWR_CTRL_REG(0x380)
+#define PWR_BASE_READY					PWR_CTRL_REG(0x388)
+#define PWR_BASE_PWRTRANS				PWR_CTRL_REG(0x390)
+#define PWR_BASE_PWRACTIVE				PWR_CTRL_REG(0x398)
+#define PWR_STACK_PRESENT				PWR_CTRL_REG(0x3c0)
+#define PWR_STACK_READY					PWR_CTRL_REG(0x3c8)
+#define PWR_STACK_PWRTRANS				PWR_CTRL_REG(0x3d0)
+
 #endif
diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c
index e74ca071159d..b834123a6560 100644
--- a/drivers/gpu/drm/panthor/panthor_sched.c
+++ b/drivers/gpu/drm/panthor/panthor_sched.c
@@ -364,17 +364,20 @@ struct panthor_queue {
 	/** @name: DRM scheduler name for this queue. */
 	char *name;
 
-	/**
-	 * @remaining_time: Time remaining before the job timeout expires.
-	 *
-	 * The job timeout is suspended when the queue is not scheduled by the
-	 * FW. Every time we suspend the timer, we need to save the remaining
-	 * time so we can restore it later on.
-	 */
-	unsigned long remaining_time;
+	/** @timeout: Queue timeout related fields. */
+	struct {
+		/** @timeout.work: Work executed when a queue timeout occurs. */
+		struct delayed_work work;
 
-	/** @timeout_suspended: True if the job timeout was suspended. */
-	bool timeout_suspended;
+		/**
+		 * @timeout.remaining: Time remaining before a queue timeout.
+		 *
+		 * When the timer is running, this value is set to MAX_SCHEDULE_TIMEOUT.
+		 * When the timer is suspended, it's set to the time remaining when the
+		 * timer was suspended.
+		 */
+		unsigned long remaining;
+	} timeout;
 
 	/**
 	 * @doorbell_id: Doorbell assigned to this queue.
@@ -899,6 +902,10 @@ static void group_free_queue(struct panthor_group *group, struct panthor_queue *
 	if (IS_ERR_OR_NULL(queue))
 		return;
 
+	/* This should have been disabled before that point. */
+	drm_WARN_ON(&group->ptdev->base,
+		    disable_delayed_work_sync(&queue->timeout.work));
+
 	if (queue->entity.fence_context)
 		drm_sched_entity_destroy(&queue->entity);
 
@@ -1046,6 +1053,115 @@ group_unbind_locked(struct panthor_group *group)
 	return 0;
 }
 
+static bool
+group_is_idle(struct panthor_group *group)
+{
+	struct panthor_device *ptdev = group->ptdev;
+	u32 inactive_queues;
+
+	if (group->csg_id >= 0)
+		return ptdev->scheduler->csg_slots[group->csg_id].idle;
+
+	inactive_queues = group->idle_queues | group->blocked_queues;
+	return hweight32(inactive_queues) == group->queue_count;
+}
+
+static void
+queue_reset_timeout_locked(struct panthor_queue *queue)
+{
+	lockdep_assert_held(&queue->fence_ctx.lock);
+
+	if (queue->timeout.remaining != MAX_SCHEDULE_TIMEOUT) {
+		mod_delayed_work(queue->scheduler.timeout_wq,
+				 &queue->timeout.work,
+				 msecs_to_jiffies(JOB_TIMEOUT_MS));
+	}
+}
+
+static bool
+group_can_run(struct panthor_group *group)
+{
+	return group->state != PANTHOR_CS_GROUP_TERMINATED &&
+	       group->state != PANTHOR_CS_GROUP_UNKNOWN_STATE &&
+	       !group->destroyed && group->fatal_queues == 0 &&
+	       !group->timedout;
+}
+
+static bool
+queue_timeout_is_suspended(struct panthor_queue *queue)
+{
+	/* When running, the remaining time is set to MAX_SCHEDULE_TIMEOUT. */
+	return queue->timeout.remaining != MAX_SCHEDULE_TIMEOUT;
+}
+
+static void
+queue_suspend_timeout_locked(struct panthor_queue *queue)
+{
+	unsigned long qtimeout, now;
+	struct panthor_group *group;
+	struct panthor_job *job;
+	bool timer_was_active;
+
+	lockdep_assert_held(&queue->fence_ctx.lock);
+
+	/* Already suspended, nothing to do. */
+	if (queue_timeout_is_suspended(queue))
+		return;
+
+	job = list_first_entry_or_null(&queue->fence_ctx.in_flight_jobs,
+				       struct panthor_job, node);
+	group = job ? job->group : NULL;
+
+	/* If the queue is blocked and the group is idle, we want the timer to
+	 * keep running because the group can't be unblocked by other queues,
+	 * so it has to come from an external source, and we want to timebox
+	 * this external signalling.
+	 */
+	if (group && group_can_run(group) &&
+	    (group->blocked_queues & BIT(job->queue_idx)) &&
+	    group_is_idle(group))
+		return;
+
+	now = jiffies;
+	qtimeout = queue->timeout.work.timer.expires;
+
+	/* Cancel the timer. */
+	timer_was_active = cancel_delayed_work(&queue->timeout.work);
+	if (!timer_was_active || !job)
+		queue->timeout.remaining = msecs_to_jiffies(JOB_TIMEOUT_MS);
+	else if (time_after(qtimeout, now))
+		queue->timeout.remaining = qtimeout - now;
+	else
+		queue->timeout.remaining = 0;
+
+	if (WARN_ON_ONCE(queue->timeout.remaining > msecs_to_jiffies(JOB_TIMEOUT_MS)))
+		queue->timeout.remaining = msecs_to_jiffies(JOB_TIMEOUT_MS);
+}
+
+static void
+queue_suspend_timeout(struct panthor_queue *queue)
+{
+	spin_lock(&queue->fence_ctx.lock);
+	queue_suspend_timeout_locked(queue);
+	spin_unlock(&queue->fence_ctx.lock);
+}
+
+static void
+queue_resume_timeout(struct panthor_queue *queue)
+{
+	spin_lock(&queue->fence_ctx.lock);
+
+	if (queue_timeout_is_suspended(queue)) {
+		mod_delayed_work(queue->scheduler.timeout_wq,
+				 &queue->timeout.work,
+				 queue->timeout.remaining);
+
+		queue->timeout.remaining = MAX_SCHEDULE_TIMEOUT;
+	}
+
+	spin_unlock(&queue->fence_ctx.lock);
+}
+
 /**
  * cs_slot_prog_locked() - Program a queue slot
  * @ptdev: Device.
@@ -1084,10 +1200,8 @@ cs_slot_prog_locked(struct panthor_device *ptdev, u32 csg_id, u32 cs_id)
 			       CS_IDLE_EMPTY |
 			       CS_STATE_MASK |
 			       CS_EXTRACT_EVENT);
-	if (queue->iface.input->insert != queue->iface.input->extract && queue->timeout_suspended) {
-		drm_sched_resume_timeout(&queue->scheduler, queue->remaining_time);
-		queue->timeout_suspended = false;
-	}
+	if (queue->iface.input->insert != queue->iface.input->extract)
+		queue_resume_timeout(queue);
 }
 
 /**
@@ -1114,14 +1228,7 @@ cs_slot_reset_locked(struct panthor_device *ptdev, u32 csg_id, u32 cs_id)
 			       CS_STATE_STOP,
 			       CS_STATE_MASK);
 
-	/* If the queue is blocked, we want to keep the timeout running, so
-	 * we can detect unbounded waits and kill the group when that happens.
-	 */
-	if (!(group->blocked_queues & BIT(cs_id)) && !queue->timeout_suspended) {
-		queue->remaining_time = drm_sched_suspend_timeout(&queue->scheduler);
-		queue->timeout_suspended = true;
-		WARN_ON(queue->remaining_time > msecs_to_jiffies(JOB_TIMEOUT_MS));
-	}
+	queue_suspend_timeout(queue);
 
 	return 0;
 }
@@ -1140,11 +1247,13 @@ csg_slot_sync_priority_locked(struct panthor_device *ptdev, u32 csg_id)
 {
 	struct panthor_csg_slot *csg_slot = &ptdev->scheduler->csg_slots[csg_id];
 	struct panthor_fw_csg_iface *csg_iface;
+	u64 endpoint_req;
 
 	lockdep_assert_held(&ptdev->scheduler->lock);
 
 	csg_iface = panthor_fw_get_csg_iface(ptdev, csg_id);
-	csg_slot->priority = (csg_iface->input->endpoint_req & CSG_EP_REQ_PRIORITY_MASK) >> 28;
+	endpoint_req = panthor_fw_csg_endpoint_req_get(ptdev, csg_iface);
+	csg_slot->priority = CSG_EP_REQ_PRIORITY_GET(endpoint_req);
 }
 
 /**
@@ -1304,6 +1413,7 @@ csg_slot_prog_locked(struct panthor_device *ptdev, u32 csg_id, u32 priority)
 	struct panthor_csg_slot *csg_slot;
 	struct panthor_group *group;
 	u32 queue_mask = 0, i;
+	u64 endpoint_req;
 
 	lockdep_assert_held(&ptdev->scheduler->lock);
 
@@ -1330,10 +1440,12 @@ csg_slot_prog_locked(struct panthor_device *ptdev, u32 csg_id, u32 priority)
 	csg_iface->input->allow_compute = group->compute_core_mask;
 	csg_iface->input->allow_fragment = group->fragment_core_mask;
 	csg_iface->input->allow_other = group->tiler_core_mask;
-	csg_iface->input->endpoint_req = CSG_EP_REQ_COMPUTE(group->max_compute_cores) |
-					 CSG_EP_REQ_FRAGMENT(group->max_fragment_cores) |
-					 CSG_EP_REQ_TILER(group->max_tiler_cores) |
-					 CSG_EP_REQ_PRIORITY(priority);
+	endpoint_req = CSG_EP_REQ_COMPUTE(group->max_compute_cores) |
+		       CSG_EP_REQ_FRAGMENT(group->max_fragment_cores) |
+		       CSG_EP_REQ_TILER(group->max_tiler_cores) |
+		       CSG_EP_REQ_PRIORITY(priority);
+	panthor_fw_csg_endpoint_req_set(ptdev, csg_iface, endpoint_req);
+
 	csg_iface->input->config = panthor_vm_as(group->vm);
 
 	if (group->suspend_buf)
@@ -1916,28 +2028,6 @@ tick_ctx_is_full(const struct panthor_scheduler *sched,
 	return ctx->group_count == sched->csg_slot_count;
 }
 
-static bool
-group_is_idle(struct panthor_group *group)
-{
-	struct panthor_device *ptdev = group->ptdev;
-	u32 inactive_queues;
-
-	if (group->csg_id >= 0)
-		return ptdev->scheduler->csg_slots[group->csg_id].idle;
-
-	inactive_queues = group->idle_queues | group->blocked_queues;
-	return hweight32(inactive_queues) == group->queue_count;
-}
-
-static bool
-group_can_run(struct panthor_group *group)
-{
-	return group->state != PANTHOR_CS_GROUP_TERMINATED &&
-	       group->state != PANTHOR_CS_GROUP_UNKNOWN_STATE &&
-	       !group->destroyed && group->fatal_queues == 0 &&
-	       !group->timedout;
-}
-
 static void
 tick_ctx_pick_groups_from_list(const struct panthor_scheduler *sched,
 			       struct panthor_sched_tick_ctx *ctx,
@@ -2231,9 +2321,9 @@ tick_ctx_apply(struct panthor_scheduler *sched, struct panthor_sched_tick_ctx *c
 				continue;
 			}
 
-			panthor_fw_update_reqs(csg_iface, endpoint_req,
-					       CSG_EP_REQ_PRIORITY(new_csg_prio),
-					       CSG_EP_REQ_PRIORITY_MASK);
+			panthor_fw_csg_endpoint_req_update(ptdev, csg_iface,
+							   CSG_EP_REQ_PRIORITY(new_csg_prio),
+							   CSG_EP_REQ_PRIORITY_MASK);
 			csgs_upd_ctx_queue_reqs(ptdev, &upd_ctx, csg_id,
 						csg_iface->output->ack ^ CSG_ENDPOINT_CONFIG,
 						CSG_ENDPOINT_CONFIG);
@@ -2619,6 +2709,7 @@ static void group_schedule_locked(struct panthor_group *group, u32 queue_mask)
 static void queue_stop(struct panthor_queue *queue,
 		       struct panthor_job *bad_job)
 {
+	disable_delayed_work_sync(&queue->timeout.work);
 	drm_sched_stop(&queue->scheduler, bad_job ? &bad_job->base : NULL);
 }
 
@@ -2630,6 +2721,7 @@ static void queue_start(struct panthor_queue *queue)
 	list_for_each_entry(job, &queue->scheduler.pending_list, base.list)
 		job->base.s_fence->parent = dma_fence_get(job->done_fence);
 
+	enable_delayed_work(&queue->timeout.work);
 	drm_sched_start(&queue->scheduler, 0);
 }
 
@@ -2696,7 +2788,6 @@ void panthor_sched_suspend(struct panthor_device *ptdev)
 {
 	struct panthor_scheduler *sched = ptdev->scheduler;
 	struct panthor_csg_slots_upd_ctx upd_ctx;
-	struct panthor_group *group;
 	u32 suspended_slots;
 	u32 i;
 
@@ -2750,13 +2841,23 @@ void panthor_sched_suspend(struct panthor_device *ptdev)
 		while (slot_mask) {
 			u32 csg_id = ffs(slot_mask) - 1;
 			struct panthor_csg_slot *csg_slot = &sched->csg_slots[csg_id];
+			struct panthor_group *group = csg_slot->group;
 
 			/* Terminate command timedout, but the soft-reset will
 			 * automatically terminate all active groups, so let's
 			 * force the state to halted here.
 			 */
-			if (csg_slot->group->state != PANTHOR_CS_GROUP_TERMINATED)
-				csg_slot->group->state = PANTHOR_CS_GROUP_TERMINATED;
+			if (group->state != PANTHOR_CS_GROUP_TERMINATED) {
+				group->state = PANTHOR_CS_GROUP_TERMINATED;
+
+				/* Reset the queue slots manually if the termination
+				 * request failed.
+				 */
+				for (i = 0; i < group->queue_count; i++) {
+					if (group->queues[i])
+						cs_slot_reset_locked(ptdev, csg_id, i);
+				}
+			}
 			slot_mask &= ~BIT(csg_id);
 		}
 	}
@@ -2786,8 +2887,8 @@ void panthor_sched_suspend(struct panthor_device *ptdev)
 
 	for (i = 0; i < sched->csg_slot_count; i++) {
 		struct panthor_csg_slot *csg_slot = &sched->csg_slots[i];
+		struct panthor_group *group = csg_slot->group;
 
-		group = csg_slot->group;
 		if (!group)
 			continue;
 
@@ -2916,35 +3017,47 @@ void panthor_fdinfo_gather_group_samples(struct panthor_file *pfile)
 	xa_unlock(&gpool->xa);
 }
 
-static void group_sync_upd_work(struct work_struct *work)
+static bool queue_check_job_completion(struct panthor_queue *queue)
 {
-	struct panthor_group *group =
-		container_of(work, struct panthor_group, sync_upd_work);
+	struct panthor_syncobj_64b *syncobj = NULL;
 	struct panthor_job *job, *job_tmp;
+	bool cookie, progress = false;
 	LIST_HEAD(done_jobs);
-	u32 queue_idx;
-	bool cookie;
 
 	cookie = dma_fence_begin_signalling();
-	for (queue_idx = 0; queue_idx < group->queue_count; queue_idx++) {
-		struct panthor_queue *queue = group->queues[queue_idx];
-		struct panthor_syncobj_64b *syncobj;
+	spin_lock(&queue->fence_ctx.lock);
+	list_for_each_entry_safe(job, job_tmp, &queue->fence_ctx.in_flight_jobs, node) {
+		if (!syncobj) {
+			struct panthor_group *group = job->group;
 
-		if (!queue)
-			continue;
+			syncobj = group->syncobjs->kmap +
+				  (job->queue_idx * sizeof(*syncobj));
+		}
 
-		syncobj = group->syncobjs->kmap + (queue_idx * sizeof(*syncobj));
+		if (syncobj->seqno < job->done_fence->seqno)
+			break;
 
-		spin_lock(&queue->fence_ctx.lock);
-		list_for_each_entry_safe(job, job_tmp, &queue->fence_ctx.in_flight_jobs, node) {
-			if (syncobj->seqno < job->done_fence->seqno)
-				break;
+		list_move_tail(&job->node, &done_jobs);
+		dma_fence_signal_locked(job->done_fence);
+	}
 
-			list_move_tail(&job->node, &done_jobs);
-			dma_fence_signal_locked(job->done_fence);
-		}
-		spin_unlock(&queue->fence_ctx.lock);
+	if (list_empty(&queue->fence_ctx.in_flight_jobs)) {
+		/* If we have no job left, we cancel the timer, and reset remaining
+		 * time to its default so it can be restarted next time
+		 * queue_resume_timeout() is called.
+		 */
+		queue_suspend_timeout_locked(queue);
+
+		/* If there's no job pending, we consider it progress to avoid a
+		 * spurious timeout if the timeout handler and the sync update
+		 * handler raced.
+		 */
+		progress = true;
+	} else if (!list_empty(&done_jobs)) {
+		queue_reset_timeout_locked(queue);
+		progress = true;
 	}
+	spin_unlock(&queue->fence_ctx.lock);
 	dma_fence_end_signalling(cookie);
 
 	list_for_each_entry_safe(job, job_tmp, &done_jobs, node) {
@@ -2954,6 +3067,27 @@ static void group_sync_upd_work(struct work_struct *work)
 		panthor_job_put(&job->base);
 	}
 
+	return progress;
+}
+
+static void group_sync_upd_work(struct work_struct *work)
+{
+	struct panthor_group *group =
+		container_of(work, struct panthor_group, sync_upd_work);
+	u32 queue_idx;
+	bool cookie;
+
+	cookie = dma_fence_begin_signalling();
+	for (queue_idx = 0; queue_idx < group->queue_count; queue_idx++) {
+		struct panthor_queue *queue = group->queues[queue_idx];
+
+		if (!queue)
+			continue;
+
+		queue_check_job_completion(queue);
+	}
+	dma_fence_end_signalling(cookie);
+
 	group_put(group);
 }
 
@@ -3201,17 +3335,6 @@ queue_run_job(struct drm_sched_job *sched_job)
 	queue->iface.input->insert = job->ringbuf.end;
 
 	if (group->csg_id < 0) {
-		/* If the queue is blocked, we want to keep the timeout running, so we
-		 * can detect unbounded waits and kill the group when that happens.
-		 * Otherwise, we suspend the timeout so the time we spend waiting for
-		 * a CSG slot is not counted.
-		 */
-		if (!(group->blocked_queues & BIT(job->queue_idx)) &&
-		    !queue->timeout_suspended) {
-			queue->remaining_time = drm_sched_suspend_timeout(&queue->scheduler);
-			queue->timeout_suspended = true;
-		}
-
 		group_schedule_locked(group, BIT(job->queue_idx));
 	} else {
 		gpu_write(ptdev, CSF_DOORBELL(queue->doorbell_id), 1);
@@ -3220,6 +3343,7 @@ queue_run_job(struct drm_sched_job *sched_job)
 			pm_runtime_get(ptdev->base.dev);
 			sched->pm.has_ref = true;
 		}
+		queue_resume_timeout(queue);
 		panthor_devfreq_record_busy(sched->ptdev);
 	}
 
@@ -3269,7 +3393,6 @@ queue_timedout_job(struct drm_sched_job *sched_job)
 	mutex_unlock(&sched->lock);
 
 	queue_start(queue);
-
 	return DRM_GPU_SCHED_STAT_RESET;
 }
 
@@ -3312,6 +3435,17 @@ static u32 calc_profiling_ringbuf_num_slots(struct panthor_device *ptdev,
 	return DIV_ROUND_UP(cs_ringbuf_size, min_profiled_job_instrs * sizeof(u64));
 }
 
+static void queue_timeout_work(struct work_struct *work)
+{
+	struct panthor_queue *queue = container_of(work, struct panthor_queue,
+						   timeout.work.work);
+	bool progress;
+
+	progress = queue_check_job_completion(queue);
+	if (!progress)
+		drm_sched_fault(&queue->scheduler);
+}
+
 static struct panthor_queue *
 group_create_queue(struct panthor_group *group,
 		   const struct drm_panthor_queue_create *args,
@@ -3328,7 +3462,7 @@ group_create_queue(struct panthor_group *group,
 		 * their profiling status.
 		 */
 		.credit_limit = args->ringbuf_size / sizeof(u64),
-		.timeout = msecs_to_jiffies(JOB_TIMEOUT_MS),
+		.timeout = MAX_SCHEDULE_TIMEOUT,
 		.timeout_wq = group->ptdev->reset.wq,
 		.dev = group->ptdev->base.dev,
 	};
@@ -3350,6 +3484,8 @@ group_create_queue(struct panthor_group *group,
 	if (!queue)
 		return ERR_PTR(-ENOMEM);
 
+	queue->timeout.remaining = msecs_to_jiffies(JOB_TIMEOUT_MS);
+	INIT_DELAYED_WORK(&queue->timeout.work, queue_timeout_work);
 	queue->fence_ctx.id = dma_fence_context_alloc(1);
 	spin_lock_init(&queue->fence_ctx.lock);
 	INIT_LIST_HEAD(&queue->fence_ctx.in_flight_jobs);