1 files changed, 115 insertions, 19 deletions

diff --git a/drivers/gpu/drm/panthor/panthor_fw.c b/drivers/gpu/drm/panthor/panthor_fw.c
index df767e82148a..1a5e3c1a27fb 100644
--- a/drivers/gpu/drm/panthor/panthor_fw.c
+++ b/drivers/gpu/drm/panthor/panthor_fw.c
@@ -16,11 +16,13 @@
 
 #include <drm/drm_drv.h>
 #include <drm/drm_managed.h>
+#include <drm/drm_print.h>
 
 #include "panthor_device.h"
 #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"
@@ -32,6 +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.
@@ -316,6 +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.
@@ -995,6 +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 |
@@ -1068,6 +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.
@@ -1084,19 +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);
@@ -1125,14 +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);
@@ -1163,13 +1254,17 @@ void panthor_fw_unplug(struct panthor_device *ptdev)
 {
 	struct panthor_fw_section *section;
 
-	cancel_delayed_work_sync(&ptdev->fw->watchdog.ping_work);
+	disable_delayed_work_sync(&ptdev->fw->watchdog.ping_work);
 
 	if (!IS_ENABLED(CONFIG_PM) || pm_runtime_active(ptdev->base.dev)) {
 		/* Make sure the IRQ handler cannot be called after that point. */
 		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);
 	}
 
@@ -1185,7 +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);
 }
 
 /**
@@ -1364,7 +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;
 
@@ -1408,3 +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");