accel/ivpu: Introduce a new DRM driver for Intel VPU

VPU stands for Versatile Processing Unit and it's a CPU-integrated
inference accelerator for Computer Vision and Deep Learning
applications.

The VPU device consist of following components:
  - Buttress - provides CPU to VPU integration, interrupt, frequency and
    power management.
  - Memory Management Unit (based on ARM MMU-600) - translates VPU to
    host DMA addresses, isolates user workloads.
  - RISC based microcontroller - executes firmware that provides job
    execution API for the kernel-mode driver
  - Neural Compute Subsystem (NCS) - does the actual work, provides
    Compute and Copy engines.
  - Network on Chip (NoC) - network fabric connecting all the components

This driver supports VPU IP v2.7 integrated into Intel Meteor Lake
client CPUs (14th generation).

Module sources are at drivers/accel/ivpu and module name is
"intel_vpu.ko".

This patch includes only very besic functionality:
  - module, PCI device and IRQ initialization
  - register definitions and low level register manipulation functions
  - SET/GET_PARAM ioctls
  - power up without firmware
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: Oded Gabbay <ogabbay@kernel.org>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20230117092723.60441-2-jacek.lawrynowicz@linux.intel.com

MAINTAINERS

@@ -6894,6 +6894,15 @@ T:	git https://git.kernel.org/pub/scm/linux/kernel/git/ogabbay/accel.git
 F:	Documentation/accel/
 F:	drivers/accel/
 
+DRM ACCEL DRIVERS FOR INTEL VPU
+M:	Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
+M:	Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
+L:	dri-devel@lists.freedesktop.org
+S:	Supported
+T:	git git://anongit.freedesktop.org/drm/drm-misc
+F:	drivers/accel/ivpu/
+F:	include/uapi/drm/ivpu_accel.h
+
 DRM DRIVERS FOR ALLWINNER A10
 M:	Maxime Ripard <mripard@kernel.org>
 M:	Chen-Yu Tsai <wens@csie.org>

drivers/Makefile

@@ -189,3 +189,4 @@ obj-$(CONFIG_COUNTER)		+= counter/
 obj-$(CONFIG_MOST)		+= most/
 obj-$(CONFIG_PECI)		+= peci/
 obj-$(CONFIG_HTE)		+= hte/
+obj-$(CONFIG_DRM_ACCEL)	+= accel/
\ No newline at end of file

drivers/accel/Kconfig

@@ -22,3 +22,5 @@ menuconfig DRM_ACCEL
 	  major number than GPUs, and will be exposed to user-space using
 	  different device files, called accel/accel* (in /dev, sysfs
 	  and debugfs).
+
+source "drivers/accel/ivpu/Kconfig"

drivers/accel/Makefile

+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-y	+= ivpu/

drivers/accel/ivpu/Kconfig

+# SPDX-License-Identifier: GPL-2.0-only
+
+config DRM_ACCEL_IVPU
+	tristate "Intel VPU for Meteor Lake and newer"
+	depends on DRM_ACCEL
+	depends on X86_64 && !UML
+	depends on PCI && PCI_MSI
+	select FW_LOADER
+	select SHMEM
+	help
+	  Choose this option if you have a system that has an 14th generation Intel CPU
+	  or newer. VPU stands for Versatile Processing Unit and it's a CPU-integrated
+	  inference accelerator for Computer Vision and Deep Learning applications.
+
+	  If "M" is selected, the module will be called intel_vpu.

drivers/accel/ivpu/Makefile

+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2023 Intel Corporation
+
+intel_vpu-y := \
+	ivpu_drv.o \
+	ivpu_hw_mtl.o
+
+obj-$(CONFIG_DRM_ACCEL_IVPU) += intel_vpu.o
\ No newline at end of file

drivers/accel/ivpu/TODO

+- Move to threaded_irqs to mitigate potential infinite loop in ivpu_ipc_irq_handler()
+- Implement support for BLOB IDs
+- Add debugfs support to improve debugging and testing
+- Add tracing events for performance debugging
+- Implement HW based scheduling support
+- Use syncobjs for submit/sync
+- Refactor IPC protocol to improve message latency
+- Implement BO cache and MADVISE IOCTL
+- Add support for user allocated buffers using prime import and dma-buf heaps
+- Refactor struct ivpu_bo to use struct drm_gem_shmem_object
+- Add driver/device documentation

drivers/accel/ivpu/ivpu_drv.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-2023 Intel Corporation
+ */
+
+#include <linux/firmware.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include <drm/drm_accel.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_file.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_ioctl.h>
+
+#include "ivpu_drv.h"
+#include "ivpu_hw.h"
+
+#ifndef DRIVER_VERSION_STR
+#define DRIVER_VERSION_STR __stringify(DRM_IVPU_DRIVER_MAJOR) "." \
+			   __stringify(DRM_IVPU_DRIVER_MINOR) "."
+#endif
+
+static const struct drm_driver driver;
+
+int ivpu_dbg_mask;
+module_param_named(dbg_mask, ivpu_dbg_mask, int, 0644);
+MODULE_PARM_DESC(dbg_mask, "Driver debug mask. See IVPU_DBG_* macros.");
+
+u8 ivpu_pll_min_ratio;
+module_param_named(pll_min_ratio, ivpu_pll_min_ratio, byte, 0644);
+MODULE_PARM_DESC(pll_min_ratio, "Minimum PLL ratio used to set VPU frequency");
+
+u8 ivpu_pll_max_ratio = U8_MAX;
+module_param_named(pll_max_ratio, ivpu_pll_max_ratio, byte, 0644);
+MODULE_PARM_DESC(pll_max_ratio, "Maximum PLL ratio used to set VPU frequency");
+
+struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv)
+{
+	kref_get(&file_priv->ref);
+	return file_priv;
+}
+
+static void file_priv_release(struct kref *ref)
+{
+	struct ivpu_file_priv *file_priv = container_of(ref, struct ivpu_file_priv, ref);
+
+	kfree(file_priv);
+}
+
+void ivpu_file_priv_put(struct ivpu_file_priv **link)
+{
+	struct ivpu_file_priv *file_priv = *link;
+
+	WARN_ON(!file_priv);
+
+	*link = NULL;
+	kref_put(&file_priv->ref, file_priv_release);
+}
+
+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;
+	struct ivpu_device *vdev = file_priv->vdev;
+	struct pci_dev *pdev = to_pci_dev(vdev->drm.dev);
+	struct drm_ivpu_param *args = data;
+	int ret = 0;
+
+	switch (args->param) {
+	case DRM_IVPU_PARAM_DEVICE_ID:
+		args->value = pdev->device;
+		break;
+	case DRM_IVPU_PARAM_DEVICE_REVISION:
+		args->value = pdev->revision;
+		break;
+	case DRM_IVPU_PARAM_PLATFORM_TYPE:
+		args->value = vdev->platform;
+		break;
+	case DRM_IVPU_PARAM_CORE_CLOCK_RATE:
+		args->value = ivpu_hw_reg_pll_freq_get(vdev);
+		break;
+	case DRM_IVPU_PARAM_NUM_CONTEXTS:
+		args->value = ivpu_get_context_count(vdev);
+		break;
+	case DRM_IVPU_PARAM_CONTEXT_BASE_ADDRESS:
+		args->value = vdev->hw->ranges.user_low.start;
+		break;
+	case DRM_IVPU_PARAM_CONTEXT_PRIORITY:
+		args->value = file_priv->priority;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static int ivpu_set_param_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct ivpu_file_priv *file_priv = file->driver_priv;
+	struct drm_ivpu_param *args = data;
+	int ret = 0;
+
+	switch (args->param) {
+	case DRM_IVPU_PARAM_CONTEXT_PRIORITY:
+		if (args->value <= DRM_IVPU_CONTEXT_PRIORITY_REALTIME)
+			file_priv->priority = args->value;
+		else
+			ret = -EINVAL;
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static int ivpu_open(struct drm_device *dev, struct drm_file *file)
+{
+	struct ivpu_device *vdev = to_ivpu_device(dev);
+	struct ivpu_file_priv *file_priv;
+
+	file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
+	if (!file_priv)
+		return -ENOMEM;
+
+	file_priv->vdev = vdev;
+	file_priv->priority = DRM_IVPU_CONTEXT_PRIORITY_NORMAL;
+	kref_init(&file_priv->ref);
+
+	file->driver_priv = file_priv;
+	return 0;
+}
+
+static void ivpu_postclose(struct drm_device *dev, struct drm_file *file)
+{
+	struct ivpu_file_priv *file_priv = file->driver_priv;
+
+	ivpu_file_priv_put(&file_priv);
+}
+
+static const struct drm_ioctl_desc ivpu_drm_ioctls[] = {
+	DRM_IOCTL_DEF_DRV(IVPU_GET_PARAM, ivpu_get_param_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(IVPU_SET_PARAM, ivpu_set_param_ioctl, 0),
+};
+
+int ivpu_shutdown(struct ivpu_device *vdev)
+{
+	int ret;
+
+	ivpu_hw_irq_disable(vdev);
+
+	ret = ivpu_hw_power_down(vdev);
+	if (ret)
+		ivpu_warn(vdev, "Failed to power down HW: %d\n", ret);
+
+	return ret;
+}
+
+static const struct file_operations ivpu_fops = {
+	.owner		= THIS_MODULE,
+	.mmap           = drm_gem_mmap,
+	DRM_ACCEL_FOPS,
+};
+
+static const struct drm_driver driver = {
+	.driver_features = DRIVER_GEM | DRIVER_COMPUTE_ACCEL,
+
+	.open = ivpu_open,
+	.postclose = ivpu_postclose,
+
+	.ioctls = ivpu_drm_ioctls,
+	.num_ioctls = ARRAY_SIZE(ivpu_drm_ioctls),
+	.fops = &ivpu_fops,
+
+	.name = DRIVER_NAME,
+	.desc = DRIVER_DESC,
+	.date = DRIVER_DATE,
+	.major = DRM_IVPU_DRIVER_MAJOR,
+	.minor = DRM_IVPU_DRIVER_MINOR,
+};
+
+static int ivpu_irq_init(struct ivpu_device *vdev)
+{
+	struct pci_dev *pdev = to_pci_dev(vdev->drm.dev);
+	int ret;
+
+	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI | PCI_IRQ_MSIX);
+	if (ret < 0) {
+		ivpu_err(vdev, "Failed to allocate a MSI IRQ: %d\n", ret);
+		return ret;
+	}
+
+	vdev->irq = pci_irq_vector(pdev, 0);
+
+	ret = devm_request_irq(vdev->drm.dev, vdev->irq, vdev->hw->ops->irq_handler,
+			       IRQF_NO_AUTOEN, DRIVER_NAME, vdev);
+	if (ret)
+		ivpu_err(vdev, "Failed to request an IRQ %d\n", ret);
+
+	return ret;
+}
+
+static int ivpu_pci_init(struct ivpu_device *vdev)
+{
+	struct pci_dev *pdev = to_pci_dev(vdev->drm.dev);
+	struct resource *bar0 = &pdev->resource[0];
+	struct resource *bar4 = &pdev->resource[4];
+	int ret;
+
+	ivpu_dbg(vdev, MISC, "Mapping BAR0 (RegV) %pR\n", bar0);
+	vdev->regv = devm_ioremap_resource(vdev->drm.dev, bar0);
+	if (IS_ERR(vdev->regv)) {
+		ivpu_err(vdev, "Failed to map bar 0: %pe\n", vdev->regv);
+		return PTR_ERR(vdev->regv);
+	}
+
+	ivpu_dbg(vdev, MISC, "Mapping BAR4 (RegB) %pR\n", bar4);
+	vdev->regb = devm_ioremap_resource(vdev->drm.dev, bar4);
+	if (IS_ERR(vdev->regb)) {
+		ivpu_err(vdev, "Failed to map bar 4: %pe\n", vdev->regb);
+		return PTR_ERR(vdev->regb);
+	}
+
+	ret = dma_set_mask_and_coherent(vdev->drm.dev, DMA_BIT_MASK(38));
+	if (ret) {
+		ivpu_err(vdev, "Failed to set DMA mask: %d\n", ret);
+		return ret;
+	}
+
+	/* Clear any pending errors */
+	pcie_capability_clear_word(pdev, PCI_EXP_DEVSTA, 0x3f);
+
+	ret = pcim_enable_device(pdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to enable PCI device: %d\n", ret);
+		return ret;
+	}
+
+	pci_set_master(pdev);
+
+	return 0;
+}
+
+static int ivpu_dev_init(struct ivpu_device *vdev)
+{
+	int ret;
+
+	vdev->hw = drmm_kzalloc(&vdev->drm, sizeof(*vdev->hw), GFP_KERNEL);
+	if (!vdev->hw)
+		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;
+	vdev->context_xa_limit.max = IVPU_CONTEXT_LIMIT;
+	xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC);
+
+	ret = ivpu_pci_init(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to initialize PCI device: %d\n", ret);
+		goto err_xa_destroy;
+	}
+
+	ret = ivpu_irq_init(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to initialize IRQs: %d\n", ret);
+		goto err_xa_destroy;
+	}
+
+	/* Init basic HW info based on buttress registers which are accessible before power up */
+	ret = ivpu_hw_info_init(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to initialize HW info: %d\n", ret);
+		goto err_xa_destroy;
+	}
+
+	/* Power up early so the rest of init code can access VPU registers */
+	ret = ivpu_hw_power_up(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to power up HW: %d\n", ret);
+		goto err_xa_destroy;
+	}
+
+	return 0;
+
+err_xa_destroy:
+	xa_destroy(&vdev->context_xa);
+	return ret;
+}
+
+static void ivpu_dev_fini(struct ivpu_device *vdev)
+{
+	ivpu_shutdown(vdev);
+
+	drm_WARN_ON(&vdev->drm, !xa_empty(&vdev->context_xa));
+	xa_destroy(&vdev->context_xa);
+}
+
+static struct pci_device_id ivpu_pci_ids[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_MTL) },
+	{ }
+};
+MODULE_DEVICE_TABLE(pci, ivpu_pci_ids);
+
+static int ivpu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct ivpu_device *vdev;
+	int ret;
+
+	vdev = devm_drm_dev_alloc(&pdev->dev, &driver, struct ivpu_device, drm);
+	if (IS_ERR(vdev))
+		return PTR_ERR(vdev);
+
+	pci_set_drvdata(pdev, vdev);
+
+	ret = ivpu_dev_init(vdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to initialize VPU device: %d\n", ret);
+		return ret;
+	}
+
+	ret = drm_dev_register(&vdev->drm, 0);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to register DRM device: %d\n", ret);
+		ivpu_dev_fini(vdev);
+	}
+
+	return ret;
+}
+
+static void ivpu_remove(struct pci_dev *pdev)
+{
+	struct ivpu_device *vdev = pci_get_drvdata(pdev);
+
+	drm_dev_unregister(&vdev->drm);
+	ivpu_dev_fini(vdev);
+}
+
+static struct pci_driver ivpu_pci_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = ivpu_pci_ids,
+	.probe = ivpu_probe,
+	.remove = ivpu_remove,
+};
+
+module_pci_driver(ivpu_pci_driver);
+
+MODULE_AUTHOR("Intel Corporation");
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL and additional rights");
+MODULE_VERSION(DRIVER_VERSION_STR);

drivers/accel/ivpu/ivpu_drv.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020-2023 Intel Corporation
+ */
+
+#ifndef __IVPU_DRV_H__
+#define __IVPU_DRV_H__
+
+#include <drm/drm_device.h>
+#include <drm/drm_managed.h>
+#include <drm/drm_mm.h>
+#include <drm/drm_print.h>
+
+#include <linux/pci.h>
+#include <linux/xarray.h>
+#include <uapi/drm/ivpu_accel.h>
+
+#define DRIVER_NAME "intel_vpu"
+#define DRIVER_DESC "Driver for Intel Versatile Processing Unit (VPU)"
+#define DRIVER_DATE "20230117"
+
+#define PCI_DEVICE_ID_MTL   0x7d1d
+
+#define IVPU_GLOBAL_CONTEXT_MMU_SSID 0
+#define IVPU_CONTEXT_LIMIT	     64
+#define IVPU_NUM_ENGINES	     2
+
+#define IVPU_PLATFORM_SILICON 0
+#define IVPU_PLATFORM_SIMICS  2
+#define IVPU_PLATFORM_FPGA    3
+#define IVPU_PLATFORM_INVALID 8
+
+#define IVPU_DBG_REG	 BIT(0)
+#define IVPU_DBG_IRQ	 BIT(1)
+#define IVPU_DBG_MMU	 BIT(2)
+#define IVPU_DBG_FILE	 BIT(3)
+#define IVPU_DBG_MISC	 BIT(4)
+#define IVPU_DBG_FW_BOOT BIT(5)
+#define IVPU_DBG_PM	 BIT(6)
+#define IVPU_DBG_IPC	 BIT(7)
+#define IVPU_DBG_BO	 BIT(8)
+#define IVPU_DBG_JOB	 BIT(9)
+#define IVPU_DBG_JSM	 BIT(10)
+#define IVPU_DBG_KREF	 BIT(11)
+#define IVPU_DBG_RPM	 BIT(12)
+
+#define ivpu_err(vdev, fmt, ...) \
+	drm_err(&(vdev)->drm, "%s(): " fmt, __func__, ##__VA_ARGS__)
+
+#define ivpu_err_ratelimited(vdev, fmt, ...) \
+	drm_err_ratelimited(&(vdev)->drm, "%s(): " fmt, __func__, ##__VA_ARGS__)
+
+#define ivpu_warn(vdev, fmt, ...) \
+	drm_warn(&(vdev)->drm, "%s(): " fmt, __func__, ##__VA_ARGS__)
+
+#define ivpu_warn_ratelimited(vdev, fmt, ...) \
+	drm_err_ratelimited(&(vdev)->drm, "%s(): " fmt, __func__, ##__VA_ARGS__)
+
+#define ivpu_info(vdev, fmt, ...) drm_info(&(vdev)->drm, fmt, ##__VA_ARGS__)
+
+#define ivpu_dbg(vdev, type, fmt, args...) do {                                \
+	if (unlikely(IVPU_DBG_##type & ivpu_dbg_mask))                         \
+		dev_dbg((vdev)->drm.dev, "[%s] " fmt, #type, ##args);          \
+} while (0)
+
+#define IVPU_WA(wa_name) (vdev->wa.wa_name)
+
+struct ivpu_wa_table {
+	bool punit_disabled;
+	bool clear_runtime_mem;
+};
+
+struct ivpu_hw_info;
+
+struct ivpu_device {
+	struct drm_device drm;
+	void __iomem *regb;
+	void __iomem *regv;
+	u32 platform;
+	u32 irq;
+
+	struct ivpu_wa_table wa;
+	struct ivpu_hw_info *hw;
+
+	struct xarray context_xa;
+	struct xa_limit context_xa_limit;
+
+	struct {
+		int boot;
+		int jsm;
+		int tdr;
+		int reschedule_suspend;
+	} timeout;
+};
+
+/*
+ * file_priv has its own refcount (ref) that allows user space to close the fd
+ * without blocking even if VPU is still processing some jobs.
+ */
+struct ivpu_file_priv {
+	struct kref ref;
+	struct ivpu_device *vdev;
+	u32 priority;
+};
+
+extern int ivpu_dbg_mask;
+extern u8 ivpu_pll_min_ratio;
+extern u8 ivpu_pll_max_ratio;
+
+struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv);
+void ivpu_file_priv_put(struct ivpu_file_priv **link);
+int ivpu_shutdown(struct ivpu_device *vdev);
+
+static inline bool ivpu_is_mtl(struct ivpu_device *vdev)
+{
+	return to_pci_dev(vdev->drm.dev)->device == PCI_DEVICE_ID_MTL;
+}
+
+static inline u8 ivpu_revision(struct ivpu_device *vdev)
+{
+	return to_pci_dev(vdev->drm.dev)->revision;
+}
+
+static inline u16 ivpu_device_id(struct ivpu_device *vdev)
+{
+	return to_pci_dev(vdev->drm.dev)->device;
+}
+
+static inline struct ivpu_device *to_ivpu_device(struct drm_device *dev)
+{
+	return container_of(dev, struct ivpu_device, drm);
+}
+
+static inline u32 ivpu_get_context_count(struct ivpu_device *vdev)
+{
+	struct xa_limit ctx_limit = vdev->context_xa_limit;
+
+	return (ctx_limit.max - ctx_limit.min + 1);
+}
+
+static inline u32 ivpu_get_platform(struct ivpu_device *vdev)
+{
+	WARN_ON_ONCE(vdev->platform == IVPU_PLATFORM_INVALID);
+	return vdev->platform;
+}
+
+static inline bool ivpu_is_silicon(struct ivpu_device *vdev)
+{
+	return ivpu_get_platform(vdev) == IVPU_PLATFORM_SILICON;
+}
+
+static inline bool ivpu_is_simics(struct ivpu_device *vdev)
+{
+	return ivpu_get_platform(vdev) == IVPU_PLATFORM_SIMICS;
+}
+
+static inline bool ivpu_is_fpga(struct ivpu_device *vdev)
+{
+	return ivpu_get_platform(vdev) == IVPU_PLATFORM_FPGA;
+}
+
+#endif /* __IVPU_DRV_H__ */

drivers/accel/ivpu/ivpu_hw.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020-2023 Intel Corporation
+ */
+
+#ifndef __IVPU_HW_H__
+#define __IVPU_HW_H__
+
+#include "ivpu_drv.h"
+
+struct ivpu_hw_ops {
+	int (*info_init)(struct ivpu_device *vdev);
+	int (*power_up)(struct ivpu_device *vdev);
+	int (*boot_fw)(struct ivpu_device *vdev);
+	int (*power_down)(struct ivpu_device *vdev);
+	bool (*is_idle)(struct ivpu_device *vdev);
+	void (*wdt_disable)(struct ivpu_device *vdev);
+	void (*diagnose_failure)(struct ivpu_device *vdev);
+	u32 (*reg_pll_freq_get)(struct ivpu_device *vdev);
+	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);
+	void (*reg_db_set)(struct ivpu_device *vdev, u32 db_id);
+	u32 (*reg_ipc_rx_addr_get)(struct ivpu_device *vdev);
+	u32 (*reg_ipc_rx_count_get)(struct ivpu_device *vdev);
+	void (*reg_ipc_tx_set)(struct ivpu_device *vdev, u32 vpu_addr);
+	void (*irq_clear)(struct ivpu_device *vdev);
+	void (*irq_enable)(struct ivpu_device *vdev);
+	void (*irq_disable)(struct ivpu_device *vdev);
+	irqreturn_t (*irq_handler)(int irq, void *ptr);
+};
+
+struct ivpu_addr_range {
+	resource_size_t start;
+	resource_size_t end;
+};
+
+struct ivpu_hw_info {
+	const struct ivpu_hw_ops *ops;
+	struct {
+		struct ivpu_addr_range global_low;
+		struct ivpu_addr_range global_high;
+		struct ivpu_addr_range user_low;
+		struct ivpu_addr_range user_high;
+		struct ivpu_addr_range global_aliased_pio;
+	} ranges;
+	struct {
+		u8 min_ratio;
+		u8 max_ratio;
+		/*
+		 * Pll ratio for the efficiency frequency. The VPU has optimum
+		 * performance to power ratio at this frequency.
+		 */
+		u8 pn_ratio;
+		u32 profiling_freq;
+	} pll;
+	u32 tile_fuse;
+	u32 sku;
+	u16 config;
+};
+
+extern const struct ivpu_hw_ops ivpu_hw_mtl_ops;
+
+static inline int ivpu_hw_info_init(struct ivpu_device *vdev)
+{
+	return vdev->hw->ops->info_init(vdev);
+};
+
+static inline int ivpu_hw_power_up(struct ivpu_device *vdev)
+{
+	ivpu_dbg(vdev, PM, "HW power up\n");
+
+	return vdev->hw->ops->power_up(vdev);
+};
+
+static inline int ivpu_hw_boot_fw(struct ivpu_device *vdev)
+{
+	return vdev->hw->ops->boot_fw(vdev);
+};
+
+static inline bool ivpu_hw_is_idle(struct ivpu_device *vdev)
+{
+	return vdev->hw->ops->is_idle(vdev);
+};
+
+static inline int ivpu_hw_power_down(struct ivpu_device *vdev)
+{
+	ivpu_dbg(vdev, PM, "HW power down\n");
+
+	return vdev->hw->ops->power_down(vdev);
+};
+
+static inline void ivpu_hw_wdt_disable(struct ivpu_device *vdev)
+{
+	vdev->hw->ops->wdt_disable(vdev);
+};
+
+/* Register indirect accesses */
+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_reg_telemetry_offset_get(struct ivpu_device *vdev)
+{
+	return vdev->hw->ops->reg_telemetry_offset_get(vdev);
+};
+
+static inline u32 ivpu_hw_reg_telemetry_size_get(struct ivpu_device *vdev)
+{
+	return vdev->hw->ops->reg_telemetry_size_get(vdev);
+};
+
+static inline u32 ivpu_hw_reg_telemetry_enable_get(struct ivpu_device *vdev)
+{
+	return vdev->hw->ops->reg_telemetry_enable_get(vdev);
+};
+
+static inline void ivpu_hw_reg_db_set(struct ivpu_device *vdev, u32 db_id)
+{
+	vdev->hw->ops->reg_db_set(vdev, db_id);
+};
+
+static inline u32 ivpu_hw_reg_ipc_rx_addr_get(struct ivpu_device *vdev)
+{
+	return vdev->hw->ops->reg_ipc_rx_addr_get(vdev);
+};
+
+static inline u32 ivpu_hw_reg_ipc_rx_count_get(struct ivpu_device *vdev)
+{
+	return vdev->hw->ops->reg_ipc_rx_count_get(vdev);
+};
+
+static inline void ivpu_hw_reg_ipc_tx_set(struct ivpu_device *vdev, u32 vpu_addr)
+{
+	vdev->hw->ops->reg_ipc_tx_set(vdev, vpu_addr);
+};
+
+static inline void ivpu_hw_irq_clear(struct ivpu_device *vdev)
+{
+	vdev->hw->ops->irq_clear(vdev);
+};
+
+static inline void ivpu_hw_irq_enable(struct ivpu_device *vdev)
+{
+	vdev->hw->ops->irq_enable(vdev);
+};
+
+static inline void ivpu_hw_irq_disable(struct ivpu_device *vdev)
+{
+	vdev->hw->ops->irq_disable(vdev);
+};
+
+static inline void ivpu_hw_init_range(struct ivpu_addr_range *range, u64 start, u64 size)
+{
+	range->start = start;
+	range->end = start + size;
+}
+
+static inline u64 ivpu_hw_range_size(const struct ivpu_addr_range *range)
+{
+	return range->end - range->start;
+}
+
+static inline void ivpu_hw_diagnose_failure(struct ivpu_device *vdev)
+{
+	vdev->hw->ops->diagnose_failure(vdev);
+}
+
+#endif /* __IVPU_HW_H__ */

drivers/accel/ivpu/ivpu_hw_reg_io.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020-2023 Intel Corporation
+ */
+
+#ifndef __IVPU_HW_REG_IO_H__
+#define __IVPU_HW_REG_IO_H__
+
+#include <linux/bitfield.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+
+#include "ivpu_drv.h"
+
+#define REG_POLL_SLEEP_US 50
+#define REG_IO_ERROR      0xffffffff
+
+#define REGB_RD32(reg)          ivpu_hw_reg_rd32(vdev, vdev->regb, (reg), #reg, __func__)
+#define REGB_RD32_SILENT(reg)   readl(vdev->regb + (reg))
+#define REGB_RD64(reg)          ivpu_hw_reg_rd64(vdev, vdev->regb, (reg), #reg, __func__)
+#define REGB_WR32(reg, val)     ivpu_hw_reg_wr32(vdev, vdev->regb, (reg), (val), #reg, __func__)
+#define REGB_WR64(reg, val)     ivpu_hw_reg_wr64(vdev, vdev->regb, (reg), (val), #reg, __func__)
+
+#define REGV_RD32(reg)          ivpu_hw_reg_rd32(vdev, vdev->regv, (reg), #reg, __func__)
+#define REGV_RD32_SILENT(reg)   readl(vdev->regv + (reg))
+#define REGV_RD64(reg)          ivpu_hw_reg_rd64(vdev, vdev->regv, (reg), #reg, __func__)
+#define REGV_WR32(reg, val)     ivpu_hw_reg_wr32(vdev, vdev->regv, (reg), (val), #reg, __func__)
+#define REGV_WR64(reg, val)     ivpu_hw_reg_wr64(vdev, vdev->regv, (reg), (val), #reg, __func__)
+
+#define REGV_WR32I(reg, stride, index, val) \
+	ivpu_hw_reg_wr32_index(vdev, vdev->regv, (reg), (stride), (index), (val), #reg, __func__)
+
+#define REG_FLD(REG, FLD) \
+	(REG##_##FLD##_MASK)
+#define REG_FLD_NUM(REG, FLD, num) \
+	FIELD_PREP(REG##_##FLD##_MASK, num)
+#define REG_GET_FLD(REG, FLD, val) \
+	FIELD_GET(REG##_##FLD##_MASK, val)
+#define REG_CLR_FLD(REG, FLD, val) \
+	((val) & ~(REG##_##FLD##_MASK))
+#define REG_SET_FLD(REG, FLD, val) \
+	((val) | (REG##_##FLD##_MASK))
+#define REG_SET_FLD_NUM(REG, FLD, num, val) \
+	(((val) & ~(REG##_##FLD##_MASK)) | FIELD_PREP(REG##_##FLD##_MASK, num))
+#define REG_TEST_FLD(REG, FLD, val) \
+	((REG##_##FLD##_MASK) == ((val) & (REG##_##FLD##_MASK)))
+#define REG_TEST_FLD_NUM(REG, FLD, num, val) \
+	((num) == FIELD_GET(REG##_##FLD##_MASK, val))
+
+#define REGB_POLL(reg, var, cond, timeout_us) \
+	read_poll_timeout(REGB_RD32_SILENT, var, cond, REG_POLL_SLEEP_US, timeout_us, false, reg)
+
+#define REGV_POLL(reg, var, cond, timeout_us) \
+	read_poll_timeout(REGV_RD32_SILENT, var, cond, REG_POLL_SLEEP_US, timeout_us, false, reg)
+
+#define REGB_POLL_FLD(reg, fld, val, timeout_us) \
+({ \
+	u32 var; \
+	REGB_POLL(reg, var, (FIELD_GET(reg##_##fld##_MASK, var) == (val)), timeout_us); \
+})
+
+#define REGV_POLL_FLD(reg, fld, val, timeout_us) \
+({ \
+	u32 var; \
+	REGV_POLL(reg, var, (FIELD_GET(reg##_##fld##_MASK, var) == (val)), timeout_us); \
+})
+
+static inline u32
+ivpu_hw_reg_rd32(struct ivpu_device *vdev, void __iomem *base, u32 reg,
+		 const char *name, const char *func)
+{
+	u32 val = readl(base + reg);
+
+	ivpu_dbg(vdev, REG, "%s RD: %s (0x%08x) => 0x%08x\n", func, name, reg, val);
+	return val;
+}
+
+static inline u64
+ivpu_hw_reg_rd64(struct ivpu_device *vdev, void __iomem *base, u32 reg,
+		 const char *name, const char *func)
+{
+	u64 val = readq(base + reg);
+
+	ivpu_dbg(vdev, REG, "%s RD: %s (0x%08x) => 0x%016llx\n", func, name, reg, val);
+	return val;
+}
+
+static inline void
+ivpu_hw_reg_wr32(struct ivpu_device *vdev, void __iomem *base, u32 reg, u32 val,
+		 const char *name, const char *func)
+{
+	ivpu_dbg(vdev, REG, "%s WR: %s (0x%08x) <= 0x%08x\n", func, name, reg, val);
+	writel(val, base + reg);
+}
+
+static inline void
+ivpu_hw_reg_wr64(struct ivpu_device *vdev, void __iomem *base, u32 reg, u64 val,
+		 const char *name, const char *func)
+{
+	ivpu_dbg(vdev, REG, "%s WR: %s (0x%08x) <= 0x%016llx\n", func, name, reg, val);
+	writeq(val, base + reg);
+}
+
+static inline void
+ivpu_hw_reg_wr32_index(struct ivpu_device *vdev, void __iomem *base, u32 reg,
+		       u32 stride, u32 index, u32 val, const char *name,
+		       const char *func)
+{
+	reg += index * stride;
+
+	ivpu_dbg(vdev, REG, "%s WR: %s_%d (0x%08x) <= 0x%08x\n", func, name, index, reg, val);
+	writel(val, base + reg);
+}
+
+#endif /* __IVPU_HW_REG_IO_H__ */

include/uapi/drm/ivpu_accel.h

+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2020-2023 Intel Corporation
+ */
+
+#ifndef __UAPI_IVPU_DRM_H__
+#define __UAPI_IVPU_DRM_H__
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_IVPU_DRIVER_MAJOR 1
+#define DRM_IVPU_DRIVER_MINOR 0
+
+#define DRM_IVPU_GET_PARAM		  0x00
+#define DRM_IVPU_SET_PARAM		  0x01
+
+#define DRM_IOCTL_IVPU_GET_PARAM                                               \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_IVPU_GET_PARAM, struct drm_ivpu_param)
+
+#define DRM_IOCTL_IVPU_SET_PARAM                                               \
+	DRM_IOW(DRM_COMMAND_BASE + DRM_IVPU_SET_PARAM, struct drm_ivpu_param)
+
+/**
+ * DOC: contexts
+ *
+ * VPU contexts have private virtual address space, job queues and priority.
+ * Each context is identified by an unique ID. Context is created on open().
+ */
+
+#define DRM_IVPU_PARAM_DEVICE_ID	    0
+#define DRM_IVPU_PARAM_DEVICE_REVISION	    1
+#define DRM_IVPU_PARAM_PLATFORM_TYPE	    2
+#define DRM_IVPU_PARAM_CORE_CLOCK_RATE	    3
+#define DRM_IVPU_PARAM_NUM_CONTEXTS	    4
+#define DRM_IVPU_PARAM_CONTEXT_BASE_ADDRESS 5
+#define DRM_IVPU_PARAM_CONTEXT_PRIORITY	    6
+
+#define DRM_IVPU_PLATFORM_TYPE_SILICON	    0
+
+#define DRM_IVPU_CONTEXT_PRIORITY_IDLE	    0
+#define DRM_IVPU_CONTEXT_PRIORITY_NORMAL    1
+#define DRM_IVPU_CONTEXT_PRIORITY_FOCUS	    2
+#define DRM_IVPU_CONTEXT_PRIORITY_REALTIME  3
+
+/**
+ * struct drm_ivpu_param - Get/Set VPU parameters
+ */
+struct drm_ivpu_param {
+	/**
+	 * @param:
+	 *
+	 * Supported params:
+	 *
+	 * %DRM_IVPU_PARAM_DEVICE_ID:
+	 * PCI Device ID of the VPU device (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_DEVICE_REVISION:
+	 * VPU device revision (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_PLATFORM_TYPE:
+	 * Returns %DRM_IVPU_PLATFORM_TYPE_SILICON on real hardware or device specific
+	 * platform type when executing on a simulator or emulator (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_CORE_CLOCK_RATE:
+	 * Current PLL frequency (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_NUM_CONTEXTS:
+	 * Maximum number of simultaneously existing contexts (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_CONTEXT_BASE_ADDRESS:
+	 * Lowest VPU virtual address available in the current context (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_CONTEXT_PRIORITY:
+	 * Value of current context scheduling priority (read-write).
+	 * See DRM_IVPU_CONTEXT_PRIORITY_* for possible values.
+	 *
+	 */
+	__u32 param;
+
+	/** @index: Index for params that have multiple instances */
+	__u32 index;
+
+	/** @value: Param value */
+	__u64 value;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* __UAPI_IVPU_DRM_H__ */