d91389bc83
This patch add the sysfs and hwmon entries that are exposed by the driver. Goya has several sensors, from various categories such as temperature, voltage, current, etc. The driver exposes those sensors in the standard hwmon mechanism. In addition, the driver exposes a couple of interfaces in sysfs, both for configuration and for providing status of the device or driver. The configuration attributes is for Power Management: - Automatic or manual - Frequency value when moving to high frequency mode - Maximum power the device is allowed to consume The rest of the attributes are read-only and provide the following information: - Versions of the various firmwares running on the device - Contents of the device's EEPROM - The device type (currently only Goya is supported) - PCI address of the device (to allow user-space to connect between /dev/hlX to PCI address) - Status of the device (operational, malfunction, in_reset) - How many processes are open on the device's file Reviewed-by: Mike Rapoport <rppt@linux.ibm.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
425 lines
8.6 KiB
C
425 lines
8.6 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
|
|
/*
|
|
* Copyright 2016-2019 HabanaLabs, Ltd.
|
|
* All Rights Reserved.
|
|
*
|
|
*/
|
|
|
|
#include "habanalabs.h"
|
|
|
|
#include <linux/pci.h>
|
|
#include <linux/module.h>
|
|
|
|
#define HL_DRIVER_AUTHOR "HabanaLabs Kernel Driver Team"
|
|
|
|
#define HL_DRIVER_DESC "Driver for HabanaLabs's AI Accelerators"
|
|
|
|
MODULE_AUTHOR(HL_DRIVER_AUTHOR);
|
|
MODULE_DESCRIPTION(HL_DRIVER_DESC);
|
|
MODULE_LICENSE("GPL v2");
|
|
|
|
static int hl_major;
|
|
static struct class *hl_class;
|
|
DEFINE_IDR(hl_devs_idr);
|
|
DEFINE_MUTEX(hl_devs_idr_lock);
|
|
|
|
#define PCI_VENDOR_ID_HABANALABS 0x1da3
|
|
|
|
#define PCI_IDS_GOYA 0x0001
|
|
|
|
static const struct pci_device_id ids[] = {
|
|
{ PCI_DEVICE(PCI_VENDOR_ID_HABANALABS, PCI_IDS_GOYA), },
|
|
{ 0, }
|
|
};
|
|
MODULE_DEVICE_TABLE(pci, ids);
|
|
|
|
/*
|
|
* get_asic_type - translate device id to asic type
|
|
*
|
|
* @device: id of the PCI device
|
|
*
|
|
* Translate device id to asic type.
|
|
* In case of unidentified device, return -1
|
|
*/
|
|
static enum hl_asic_type get_asic_type(u16 device)
|
|
{
|
|
enum hl_asic_type asic_type;
|
|
|
|
switch (device) {
|
|
case PCI_IDS_GOYA:
|
|
asic_type = ASIC_GOYA;
|
|
break;
|
|
default:
|
|
asic_type = ASIC_INVALID;
|
|
break;
|
|
}
|
|
|
|
return asic_type;
|
|
}
|
|
|
|
/*
|
|
* hl_device_open - open function for habanalabs device
|
|
*
|
|
* @inode: pointer to inode structure
|
|
* @filp: pointer to file structure
|
|
*
|
|
* Called when process opens an habanalabs device.
|
|
*/
|
|
int hl_device_open(struct inode *inode, struct file *filp)
|
|
{
|
|
struct hl_device *hdev;
|
|
struct hl_fpriv *hpriv;
|
|
int rc;
|
|
|
|
mutex_lock(&hl_devs_idr_lock);
|
|
hdev = idr_find(&hl_devs_idr, iminor(inode));
|
|
mutex_unlock(&hl_devs_idr_lock);
|
|
|
|
if (!hdev) {
|
|
pr_err("Couldn't find device %d:%d\n",
|
|
imajor(inode), iminor(inode));
|
|
return -ENXIO;
|
|
}
|
|
|
|
mutex_lock(&hdev->fd_open_cnt_lock);
|
|
|
|
if (hdev->disabled) {
|
|
dev_err_ratelimited(hdev->dev,
|
|
"Can't open %s because it is disabled\n",
|
|
dev_name(hdev->dev));
|
|
mutex_unlock(&hdev->fd_open_cnt_lock);
|
|
return -EPERM;
|
|
}
|
|
|
|
if (atomic_read(&hdev->fd_open_cnt)) {
|
|
dev_info_ratelimited(hdev->dev,
|
|
"Device %s is already attached to application\n",
|
|
dev_name(hdev->dev));
|
|
mutex_unlock(&hdev->fd_open_cnt_lock);
|
|
return -EBUSY;
|
|
}
|
|
|
|
atomic_inc(&hdev->fd_open_cnt);
|
|
|
|
mutex_unlock(&hdev->fd_open_cnt_lock);
|
|
|
|
hpriv = kzalloc(sizeof(*hpriv), GFP_KERNEL);
|
|
if (!hpriv) {
|
|
rc = -ENOMEM;
|
|
goto close_device;
|
|
}
|
|
|
|
hpriv->hdev = hdev;
|
|
filp->private_data = hpriv;
|
|
hpriv->filp = filp;
|
|
kref_init(&hpriv->refcount);
|
|
nonseekable_open(inode, filp);
|
|
|
|
hl_cb_mgr_init(&hpriv->cb_mgr);
|
|
hl_ctx_mgr_init(&hpriv->ctx_mgr);
|
|
|
|
rc = hl_ctx_create(hdev, hpriv);
|
|
if (rc) {
|
|
dev_err(hdev->dev, "Failed to open FD (CTX fail)\n");
|
|
goto out_err;
|
|
}
|
|
|
|
hpriv->taskpid = find_get_pid(current->pid);
|
|
|
|
/*
|
|
* Device is IDLE at this point so it is legal to change PLLs. There
|
|
* is no need to check anything because if the PLL is already HIGH, the
|
|
* set function will return without doing anything
|
|
*/
|
|
hl_device_set_frequency(hdev, PLL_HIGH);
|
|
|
|
return 0;
|
|
|
|
out_err:
|
|
filp->private_data = NULL;
|
|
hl_ctx_mgr_fini(hpriv->hdev, &hpriv->ctx_mgr);
|
|
hl_cb_mgr_fini(hpriv->hdev, &hpriv->cb_mgr);
|
|
kfree(hpriv);
|
|
|
|
close_device:
|
|
atomic_dec(&hdev->fd_open_cnt);
|
|
return rc;
|
|
}
|
|
|
|
/*
|
|
* create_hdev - create habanalabs device instance
|
|
*
|
|
* @dev: will hold the pointer to the new habanalabs device structure
|
|
* @pdev: pointer to the pci device
|
|
* @asic_type: in case of simulator device, which device is it
|
|
* @minor: in case of simulator device, the minor of the device
|
|
*
|
|
* Allocate memory for habanalabs device and initialize basic fields
|
|
* Identify the ASIC type
|
|
* Allocate ID (minor) for the device (only for real devices)
|
|
*/
|
|
int create_hdev(struct hl_device **dev, struct pci_dev *pdev,
|
|
enum hl_asic_type asic_type, int minor)
|
|
{
|
|
struct hl_device *hdev;
|
|
int rc;
|
|
|
|
*dev = NULL;
|
|
|
|
hdev = kzalloc(sizeof(*hdev), GFP_KERNEL);
|
|
if (!hdev)
|
|
return -ENOMEM;
|
|
|
|
hdev->major = hl_major;
|
|
|
|
/* Parameters for bring-up - set them to defaults */
|
|
hdev->cpu_enable = 1;
|
|
hdev->reset_pcilink = 0;
|
|
hdev->cpu_queues_enable = 1;
|
|
hdev->fw_loading = 1;
|
|
hdev->pldm = 0;
|
|
|
|
/* If CPU is disabled, no point in loading FW */
|
|
if (!hdev->cpu_enable)
|
|
hdev->fw_loading = 0;
|
|
|
|
/* If we don't load FW, no need to initialize CPU queues */
|
|
if (!hdev->fw_loading)
|
|
hdev->cpu_queues_enable = 0;
|
|
|
|
hdev->disabled = true;
|
|
hdev->pdev = pdev; /* can be NULL in case of simulator device */
|
|
|
|
if (asic_type == ASIC_AUTO_DETECT) {
|
|
hdev->asic_type = get_asic_type(pdev->device);
|
|
if (hdev->asic_type == ASIC_INVALID) {
|
|
dev_err(&pdev->dev, "Unsupported ASIC\n");
|
|
rc = -ENODEV;
|
|
goto free_hdev;
|
|
}
|
|
} else {
|
|
hdev->asic_type = asic_type;
|
|
}
|
|
|
|
mutex_lock(&hl_devs_idr_lock);
|
|
|
|
if (minor == -1) {
|
|
rc = idr_alloc(&hl_devs_idr, hdev, 0, HL_MAX_MINORS,
|
|
GFP_KERNEL);
|
|
} else {
|
|
void *old_idr = idr_replace(&hl_devs_idr, hdev, minor);
|
|
|
|
if (IS_ERR_VALUE(old_idr)) {
|
|
rc = PTR_ERR(old_idr);
|
|
pr_err("Error %d when trying to replace minor %d\n",
|
|
rc, minor);
|
|
mutex_unlock(&hl_devs_idr_lock);
|
|
goto free_hdev;
|
|
}
|
|
rc = minor;
|
|
}
|
|
|
|
mutex_unlock(&hl_devs_idr_lock);
|
|
|
|
if (rc < 0) {
|
|
if (rc == -ENOSPC) {
|
|
pr_err("too many devices in the system\n");
|
|
rc = -EBUSY;
|
|
}
|
|
goto free_hdev;
|
|
}
|
|
|
|
hdev->id = rc;
|
|
|
|
*dev = hdev;
|
|
|
|
return 0;
|
|
|
|
free_hdev:
|
|
kfree(hdev);
|
|
return rc;
|
|
}
|
|
|
|
/*
|
|
* destroy_hdev - destroy habanalabs device instance
|
|
*
|
|
* @dev: pointer to the habanalabs device structure
|
|
*
|
|
*/
|
|
void destroy_hdev(struct hl_device *hdev)
|
|
{
|
|
/* Remove device from the device list */
|
|
mutex_lock(&hl_devs_idr_lock);
|
|
idr_remove(&hl_devs_idr, hdev->id);
|
|
mutex_unlock(&hl_devs_idr_lock);
|
|
|
|
kfree(hdev);
|
|
}
|
|
|
|
static int hl_pmops_suspend(struct device *dev)
|
|
{
|
|
struct pci_dev *pdev = to_pci_dev(dev);
|
|
struct hl_device *hdev = pci_get_drvdata(pdev);
|
|
|
|
pr_debug("Going to suspend PCI device\n");
|
|
|
|
if (!hdev) {
|
|
pr_err("device pointer is NULL in suspend\n");
|
|
return 0;
|
|
}
|
|
|
|
return hl_device_suspend(hdev);
|
|
}
|
|
|
|
static int hl_pmops_resume(struct device *dev)
|
|
{
|
|
struct pci_dev *pdev = to_pci_dev(dev);
|
|
struct hl_device *hdev = pci_get_drvdata(pdev);
|
|
|
|
pr_debug("Going to resume PCI device\n");
|
|
|
|
if (!hdev) {
|
|
pr_err("device pointer is NULL in resume\n");
|
|
return 0;
|
|
}
|
|
|
|
return hl_device_resume(hdev);
|
|
}
|
|
|
|
/*
|
|
* hl_pci_probe - probe PCI habanalabs devices
|
|
*
|
|
* @pdev: pointer to pci device
|
|
* @id: pointer to pci device id structure
|
|
*
|
|
* Standard PCI probe function for habanalabs device.
|
|
* Create a new habanalabs device and initialize it according to the
|
|
* device's type
|
|
*/
|
|
static int hl_pci_probe(struct pci_dev *pdev,
|
|
const struct pci_device_id *id)
|
|
{
|
|
struct hl_device *hdev;
|
|
int rc;
|
|
|
|
dev_info(&pdev->dev, HL_NAME
|
|
" device found [%04x:%04x] (rev %x)\n",
|
|
(int)pdev->vendor, (int)pdev->device, (int)pdev->revision);
|
|
|
|
rc = create_hdev(&hdev, pdev, ASIC_AUTO_DETECT, -1);
|
|
if (rc)
|
|
return rc;
|
|
|
|
pci_set_drvdata(pdev, hdev);
|
|
|
|
rc = hl_device_init(hdev, hl_class);
|
|
if (rc) {
|
|
dev_err(&pdev->dev, "Fatal error during habanalabs device init\n");
|
|
rc = -ENODEV;
|
|
goto disable_device;
|
|
}
|
|
|
|
return 0;
|
|
|
|
disable_device:
|
|
pci_set_drvdata(pdev, NULL);
|
|
destroy_hdev(hdev);
|
|
|
|
return rc;
|
|
}
|
|
|
|
/*
|
|
* hl_pci_remove - remove PCI habanalabs devices
|
|
*
|
|
* @pdev: pointer to pci device
|
|
*
|
|
* Standard PCI remove function for habanalabs device
|
|
*/
|
|
static void hl_pci_remove(struct pci_dev *pdev)
|
|
{
|
|
struct hl_device *hdev;
|
|
|
|
hdev = pci_get_drvdata(pdev);
|
|
if (!hdev)
|
|
return;
|
|
|
|
hl_device_fini(hdev);
|
|
pci_set_drvdata(pdev, NULL);
|
|
|
|
destroy_hdev(hdev);
|
|
}
|
|
|
|
static const struct dev_pm_ops hl_pm_ops = {
|
|
.suspend = hl_pmops_suspend,
|
|
.resume = hl_pmops_resume,
|
|
};
|
|
|
|
static struct pci_driver hl_pci_driver = {
|
|
.name = HL_NAME,
|
|
.id_table = ids,
|
|
.probe = hl_pci_probe,
|
|
.remove = hl_pci_remove,
|
|
.driver.pm = &hl_pm_ops,
|
|
};
|
|
|
|
/*
|
|
* hl_init - Initialize the habanalabs kernel driver
|
|
*/
|
|
static int __init hl_init(void)
|
|
{
|
|
int rc;
|
|
dev_t dev;
|
|
|
|
pr_info("loading driver\n");
|
|
|
|
rc = alloc_chrdev_region(&dev, 0, HL_MAX_MINORS, HL_NAME);
|
|
if (rc < 0) {
|
|
pr_err("unable to get major\n");
|
|
return rc;
|
|
}
|
|
|
|
hl_major = MAJOR(dev);
|
|
|
|
hl_class = class_create(THIS_MODULE, HL_NAME);
|
|
if (IS_ERR(hl_class)) {
|
|
pr_err("failed to allocate class\n");
|
|
rc = PTR_ERR(hl_class);
|
|
goto remove_major;
|
|
}
|
|
|
|
rc = pci_register_driver(&hl_pci_driver);
|
|
if (rc) {
|
|
pr_err("failed to register pci device\n");
|
|
goto remove_class;
|
|
}
|
|
|
|
pr_debug("driver loaded\n");
|
|
|
|
return 0;
|
|
|
|
remove_class:
|
|
class_destroy(hl_class);
|
|
remove_major:
|
|
unregister_chrdev_region(MKDEV(hl_major, 0), HL_MAX_MINORS);
|
|
return rc;
|
|
}
|
|
|
|
/*
|
|
* hl_exit - Release all resources of the habanalabs kernel driver
|
|
*/
|
|
static void __exit hl_exit(void)
|
|
{
|
|
pci_unregister_driver(&hl_pci_driver);
|
|
|
|
class_destroy(hl_class);
|
|
unregister_chrdev_region(MKDEV(hl_major, 0), HL_MAX_MINORS);
|
|
|
|
idr_destroy(&hl_devs_idr);
|
|
|
|
pr_debug("driver removed\n");
|
|
}
|
|
|
|
module_init(hl_init);
|
|
module_exit(hl_exit);
|