accel/ivpu: Add PM support

  - Implement cold and warm firmware boot flows
  - Add hang recovery support
  - Add runtime power management support

Co-developed-by: Krystian Pradzynski <krystian.pradzynski@linux.intel.com>
Signed-off-by: Krystian Pradzynski <krystian.pradzynski@linux.intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20230117092723.60441-8-jacek.lawrynowicz@linux.intel.com

drivers/accel/ivpu/Makefile

@@ -10,6 +10,7 @@ intel_vpu-y := \
 	ivpu_job.o \
 	ivpu_jsm_msg.o \
 	ivpu_mmu.o \
-	ivpu_mmu_context.o
+	ivpu_mmu_context.o \
+	ivpu_pm.o
 
 obj-$(CONFIG_DRM_ACCEL_IVPU) += intel_vpu.o

drivers/accel/ivpu/ivpu_drv.c

@@ -24,6 +24,7 @@
 #include "ivpu_jsm_msg.h"
 #include "ivpu_mmu.h"
 #include "ivpu_mmu_context.h"
+#include "ivpu_pm.h"
 
 #ifndef DRIVER_VERSION_STR
 #define DRIVER_VERSION_STR __stringify(DRM_IVPU_DRIVER_MAJOR) "." \
@@ -462,6 +463,10 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	if (!vdev->ipc)
 		return -ENOMEM;
 
+	vdev->pm = drmm_kzalloc(&vdev->drm, sizeof(*vdev->pm), GFP_KERNEL);
+	if (!vdev->pm)
+		return -ENOMEM;
+
 	vdev->hw->ops = &ivpu_hw_mtl_ops;
 	vdev->platform = IVPU_PLATFORM_INVALID;
 	vdev->context_xa_limit.min = IVPU_GLOBAL_CONTEXT_MMU_SSID + 1;
@@ -521,6 +526,12 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 		goto err_fw_fini;
 	}
 
+	ret = ivpu_pm_init(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to initialize PM: %d\n", ret);
+		goto err_ipc_fini;
+	}
+
 	ret = ivpu_job_done_thread_init(vdev);
 	if (ret) {
 		ivpu_err(vdev, "Failed to initialize job done thread: %d\n", ret);
@@ -539,6 +550,8 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 		goto err_job_done_thread_fini;
 	}
 
+	ivpu_pm_enable(vdev);
+
 	return 0;
 
 err_job_done_thread_fini:
@@ -559,6 +572,7 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 
 static void ivpu_dev_fini(struct ivpu_device *vdev)
 {
+	ivpu_pm_disable(vdev);
 	ivpu_shutdown(vdev);
 	ivpu_job_done_thread_fini(vdev);
 	ivpu_ipc_fini(vdev);
@@ -611,11 +625,25 @@ static void ivpu_remove(struct pci_dev *pdev)
 	ivpu_dev_fini(vdev);
 }
 
+static const struct dev_pm_ops ivpu_drv_pci_pm = {
+	SET_SYSTEM_SLEEP_PM_OPS(ivpu_pm_suspend_cb, ivpu_pm_resume_cb)
+	SET_RUNTIME_PM_OPS(ivpu_pm_runtime_suspend_cb, ivpu_pm_runtime_resume_cb, NULL)
+};
+
+static const struct pci_error_handlers ivpu_drv_pci_err = {
+	.reset_prepare = ivpu_pm_reset_prepare_cb,
+	.reset_done = ivpu_pm_reset_done_cb,
+};
+
 static struct pci_driver ivpu_pci_driver = {
 	.name = KBUILD_MODNAME,
 	.id_table = ivpu_pci_ids,
 	.probe = ivpu_probe,
 	.remove = ivpu_remove,
+	.driver = {
+		.pm = &ivpu_drv_pci_pm,
+	},
+	.err_handler = &ivpu_drv_pci_err,
 };
 
 module_pci_driver(ivpu_pci_driver);

drivers/accel/ivpu/ivpu_drv.h

@@ -76,6 +76,7 @@ struct ivpu_hw_info;
 struct ivpu_mmu_info;
 struct ivpu_fw_info;
 struct ivpu_ipc_info;
+struct ivpu_pm_info;
 
 struct ivpu_device {
 	struct drm_device drm;
@@ -89,6 +90,7 @@ struct ivpu_device {
 	struct ivpu_mmu_info *mmu;
 	struct ivpu_fw_info *fw;
 	struct ivpu_ipc_info *ipc;
+	struct ivpu_pm_info *pm;
 
 	struct ivpu_mmu_context gctx;
 	struct xarray context_xa;

drivers/accel/ivpu/ivpu_fw.c

@@ -14,6 +14,7 @@
 #include "ivpu_gem.h"
 #include "ivpu_hw.h"
 #include "ivpu_ipc.h"
+#include "ivpu_pm.h"
 
 #define FW_GLOBAL_MEM_START	(2ull * SZ_1G)
 #define FW_GLOBAL_MEM_END	(3ull * SZ_1G)
@@ -361,9 +362,12 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 	/* In case of warm boot we only have to reset the entrypoint addr */
 	if (!ivpu_fw_is_cold_boot(vdev)) {
 		boot_params->save_restore_ret_address = 0;
+		vdev->pm->is_warmboot = true;
 		return;
 	}
 
+	vdev->pm->is_warmboot = false;
+
 	boot_params->magic = VPU_BOOT_PARAMS_MAGIC;
 	boot_params->vpu_id = to_pci_dev(vdev->drm.dev)->bus->number;
 	boot_params->frequency = ivpu_hw_reg_pll_freq_get(vdev);

drivers/accel/ivpu/ivpu_hw_mtl.c

@@ -10,6 +10,7 @@
 #include "ivpu_hw.h"
 #include "ivpu_ipc.h"
 #include "ivpu_mmu.h"
+#include "ivpu_pm.h"
 
 #define TILE_FUSE_ENABLE_BOTH	     0x0
 #define TILE_FUSE_ENABLE_UPPER	     0x1
@@ -921,18 +922,23 @@ static void ivpu_hw_mtl_irq_disable(struct ivpu_device *vdev)
 static void ivpu_hw_mtl_irq_wdt_nce_handler(struct ivpu_device *vdev)
 {
 	ivpu_err_ratelimited(vdev, "WDT NCE irq\n");
+
+	ivpu_pm_schedule_recovery(vdev);
 }
 
 static void ivpu_hw_mtl_irq_wdt_mss_handler(struct ivpu_device *vdev)
 {
 	ivpu_err_ratelimited(vdev, "WDT MSS irq\n");
 
 	ivpu_hw_wdt_disable(vdev);
+	ivpu_pm_schedule_recovery(vdev);
 }
 
 static void ivpu_hw_mtl_irq_noc_firewall_handler(struct ivpu_device *vdev)
 {
 	ivpu_err_ratelimited(vdev, "NOC Firewall irq\n");
+
+	ivpu_pm_schedule_recovery(vdev);
 }
 
 /* Handler for IRQs from VPU core (irqV) */
@@ -970,6 +976,7 @@ static u32 ivpu_hw_mtl_irqv_handler(struct ivpu_device *vdev, int irq)
 static u32 ivpu_hw_mtl_irqb_handler(struct ivpu_device *vdev, int irq)
 {
 	u32 status = REGB_RD32(MTL_BUTTRESS_INTERRUPT_STAT) & BUTTRESS_IRQ_MASK;
+	bool schedule_recovery = false;
 
 	if (status == 0)
 		return 0;
@@ -983,6 +990,7 @@ static u32 ivpu_hw_mtl_irqb_handler(struct ivpu_device *vdev, int irq)
 	if (REG_TEST_FLD(MTL_BUTTRESS_INTERRUPT_STAT, ATS_ERR, status)) {
 		ivpu_err(vdev, "ATS_ERR irq 0x%016llx", REGB_RD64(MTL_BUTTRESS_ATS_ERR_LOG_0));
 		REGB_WR32(MTL_BUTTRESS_ATS_ERR_CLEAR, 0x1);
+		schedule_recovery = true;
 	}
 
 	if (REG_TEST_FLD(MTL_BUTTRESS_INTERRUPT_STAT, UFI_ERR, status)) {
@@ -993,6 +1001,7 @@ static u32 ivpu_hw_mtl_irqb_handler(struct ivpu_device *vdev, int irq)
 			 REG_GET_FLD(MTL_BUTTRESS_UFI_ERR_LOG, AXI_ID, ufi_log),
 			 REG_GET_FLD(MTL_BUTTRESS_UFI_ERR_LOG, CQ_ID, ufi_log));
 		REGB_WR32(MTL_BUTTRESS_UFI_ERR_CLEAR, 0x1);
+		schedule_recovery = true;
 	}
 
 	/*
@@ -1005,6 +1014,9 @@ static u32 ivpu_hw_mtl_irqb_handler(struct ivpu_device *vdev, int irq)
 	/* Re-enable global interrupt */
 	REGB_WR32(MTL_BUTTRESS_GLOBAL_INT_MASK, 0x0);
 
+	if (schedule_recovery)
+		ivpu_pm_schedule_recovery(vdev);
+
 	return status;
 }
 

drivers/accel/ivpu/ivpu_ipc.c

@@ -14,6 +14,7 @@
 #include "ivpu_hw_reg_io.h"
 #include "ivpu_ipc.h"
 #include "ivpu_jsm_msg.h"
+#include "ivpu_pm.h"
 
 #define IPC_MAX_RX_MSG	128
 #define IS_KTHREAD()	(get_current()->flags & PF_KTHREAD)
@@ -294,18 +295,27 @@ int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
 {
 	struct vpu_jsm_msg hb_req = { .type = VPU_JSM_MSG_QUERY_ENGINE_HB };
 	struct vpu_jsm_msg hb_resp;
-	int ret;
+	int ret, hb_ret;
+
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
 
 	ret = ivpu_ipc_send_receive_internal(vdev, req, expected_resp_type, resp,
 					     channel, timeout_ms);
 	if (ret != -ETIMEDOUT)
-		return ret;
+		goto rpm_put;
 
-	ret = ivpu_ipc_send_receive_internal(vdev, &hb_req, VPU_JSM_MSG_QUERY_ENGINE_HB_DONE,
-					     &hb_resp, VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
-	if (ret == -ETIMEDOUT)
+	hb_ret = ivpu_ipc_send_receive_internal(vdev, &hb_req, VPU_JSM_MSG_QUERY_ENGINE_HB_DONE,
+						&hb_resp, VPU_IPC_CHAN_ASYNC_CMD,
+						vdev->timeout.jsm);
+	if (hb_ret == -ETIMEDOUT) {
 		ivpu_hw_diagnose_failure(vdev);
+		ivpu_pm_schedule_recovery(vdev);
+	}
 
+rpm_put:
+	ivpu_rpm_put(vdev);
 	return ret;
 }
 

drivers/accel/ivpu/ivpu_job.c

@@ -17,6 +17,7 @@
 #include "ivpu_ipc.h"
 #include "ivpu_job.h"
 #include "ivpu_jsm_msg.h"
+#include "ivpu_pm.h"
 
 #define CMD_BUF_IDX	     0
 #define JOB_ID_JOB_MASK	     GENMASK(7, 0)
@@ -270,6 +271,9 @@ static void job_release(struct kref *ref)
 
 	ivpu_dbg(vdev, KREF, "Job released: id %u\n", job->job_id);
 	kfree(job);
+
+	/* Allow the VPU to get suspended, must be called after ivpu_file_priv_put() */
+	ivpu_rpm_put(vdev);
 }
 
 static void job_put(struct ivpu_job *job)
@@ -286,11 +290,16 @@ ivpu_create_job(struct ivpu_file_priv *file_priv, u32 engine_idx, u32 bo_count)
 	struct ivpu_device *vdev = file_priv->vdev;
 	struct ivpu_job *job;
 	size_t buf_size;
+	int ret;
+
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return NULL;
 
 	buf_size = sizeof(*job) + bo_count * sizeof(struct ivpu_bo *);
 	job = kzalloc(buf_size, GFP_KERNEL);
 	if (!job)
-		return NULL;
+		goto err_rpm_put;
 
 	kref_init(&job->ref);
 
@@ -311,6 +320,8 @@ ivpu_create_job(struct ivpu_file_priv *file_priv, u32 engine_idx, u32 bo_count)
 
 err_free_job:
 	kfree(job);
+err_rpm_put:
+	ivpu_rpm_put(vdev);
 	return NULL;
 }
 
@@ -565,6 +576,7 @@ static int ivpu_job_done_thread(void *arg)
 			if (jobs_submitted && !xa_empty(&vdev->submitted_jobs_xa)) {
 				ivpu_err(vdev, "TDR detected, timeout %d ms", timeout);
 				ivpu_hw_diagnose_failure(vdev);
+				ivpu_pm_schedule_recovery(vdev);
 			}
 		}
 	}

drivers/accel/ivpu/ivpu_mmu.c

@@ -11,6 +11,7 @@
 #include "ivpu_hw_reg_io.h"
 #include "ivpu_mmu.h"
 #include "ivpu_mmu_context.h"
+#include "ivpu_pm.h"
 
 #define IVPU_MMU_IDR0_REF		0x080f3e0f
 #define IVPU_MMU_IDR0_REF_SIMICS	0x080f3e1f
@@ -814,6 +815,7 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev)
 
 void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev)
 {
+	bool schedule_recovery = false;
 	u32 *event;
 	u32 ssid;
 
@@ -823,9 +825,14 @@ void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev)
 		ivpu_mmu_dump_event(vdev, event);
 
 		ssid = FIELD_GET(IVPU_MMU_EVT_SSID_MASK, event[0]);
-		if (ssid != IVPU_GLOBAL_CONTEXT_MMU_SSID)
+		if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID)
+			schedule_recovery = true;
+		else
 			ivpu_mmu_user_context_mark_invalid(vdev, ssid);
 	}
+
+	if (schedule_recovery)
+		ivpu_pm_schedule_recovery(vdev);
 }
 
 void ivpu_mmu_irq_gerr_handler(struct ivpu_device *vdev)