1 files changed, 138 insertions, 103 deletions

diff --git a/drivers/accel/habanalabs/common/habanalabs_drv.c b/drivers/accel/habanalabs/common/habanalabs_drv.c
index d9df64e75f33..0035748f3228 100644
--- a/drivers/accel/habanalabs/common/habanalabs_drv.c
+++ b/drivers/accel/habanalabs/common/habanalabs_drv.c
@@ -13,6 +13,12 @@
 
 #include <linux/pci.h>
 #include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/version.h>
+
+#include <drm/drm_accel.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_ioctl.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/habanalabs.h>
@@ -26,7 +32,6 @@ MODULE_DESCRIPTION(HL_DRIVER_DESC);
 MODULE_LICENSE("GPL v2");
 
 static int hl_major;
-static struct class *hl_class;
 static DEFINE_IDR(hl_devs_idr);
 static DEFINE_MUTEX(hl_devs_idr_lock);
 
@@ -54,8 +59,6 @@ module_param(boot_error_status_mask, ulong, 0444);
 MODULE_PARM_DESC(boot_error_status_mask,
 	"Mask of the error status during device CPU boot (If bitX is cleared then error X is masked. Default all 1's)");
 
-#define PCI_VENDOR_ID_HABANALABS	0x1da3
-
 #define PCI_IDS_GOYA			0x0001
 #define PCI_IDS_GAUDI			0x1000
 #define PCI_IDS_GAUDI_SEC		0x1010
@@ -71,6 +74,41 @@ static const struct pci_device_id ids[] = {
 };
 MODULE_DEVICE_TABLE(pci, ids);
 
+static const struct drm_ioctl_desc hl_drm_ioctls[] = {
+	DRM_IOCTL_DEF_DRV(HL_INFO, hl_info_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(HL_CB, hl_cb_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(HL_CS, hl_cs_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(HL_WAIT_CS, hl_wait_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(HL_MEMORY, hl_mem_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(HL_DEBUG, hl_debug_ioctl, 0),
+};
+
+static const struct file_operations hl_fops = {
+	.owner = THIS_MODULE,
+	.open = accel_open,
+	.release = drm_release,
+	.unlocked_ioctl = drm_ioctl,
+	.compat_ioctl = drm_compat_ioctl,
+	.llseek = noop_llseek,
+	.mmap = hl_mmap
+};
+
+static const struct drm_driver hl_driver = {
+	.driver_features = DRIVER_COMPUTE_ACCEL,
+
+	.name = HL_NAME,
+	.desc = HL_DRIVER_DESC,
+	.major = LINUX_VERSION_MAJOR,
+	.minor = LINUX_VERSION_PATCHLEVEL,
+	.patchlevel = LINUX_VERSION_SUBLEVEL,
+
+	.fops = &hl_fops,
+	.open = hl_device_open,
+	.postclose = hl_device_release,
+	.ioctls = hl_drm_ioctls,
+	.num_ioctls = ARRAY_SIZE(hl_drm_ioctls)
+};
+
 /*
  * get_asic_type - translate device id to asic type
  *
@@ -102,6 +140,12 @@ static enum hl_asic_type get_asic_type(struct hl_device *hdev)
 		case REV_ID_B:
 			asic_type = ASIC_GAUDI2B;
 			break;
+		case REV_ID_C:
+			asic_type = ASIC_GAUDI2C;
+			break;
+		case REV_ID_D:
+			asic_type = ASIC_GAUDI2D;
+			break;
 		default:
 			break;
 		}
@@ -124,43 +168,28 @@ static bool is_asic_secured(enum hl_asic_type asic_type)
 }
 
 /*
- * hl_device_open - open function for habanalabs device
- *
- * @inode: pointer to inode structure
- * @filp: pointer to file structure
+ * hl_device_open() - open function for habanalabs device.
+ * @ddev: pointer to DRM device structure.
+ * @file: pointer to DRM file private data structure.
  *
  * Called when process opens an habanalabs device.
  */
-int hl_device_open(struct inode *inode, struct file *filp)
+int hl_device_open(struct drm_device *ddev, struct drm_file *file_priv)
 {
+	struct hl_device *hdev = to_hl_device(ddev);
 	enum hl_device_status status;
-	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;
-	}
-
 	hpriv = kzalloc(sizeof(*hpriv), GFP_KERNEL);
 	if (!hpriv)
 		return -ENOMEM;
 
 	hpriv->hdev = hdev;
-	filp->private_data = hpriv;
-	hpriv->filp = filp;
-
 	mutex_init(&hpriv->notifier_event.lock);
 	mutex_init(&hpriv->restore_phase_mutex);
 	mutex_init(&hpriv->ctx_lock);
 	kref_init(&hpriv->refcount);
-	nonseekable_open(inode, filp);
 
 	hl_ctx_mgr_init(&hpriv->ctx_mgr);
 	hl_mem_mgr_init(hpriv->hdev->dev, &hpriv->mem_mgr);
@@ -220,22 +249,22 @@ int hl_device_open(struct inode *inode, struct file *filp)
 
 	hl_debugfs_add_file(hpriv);
 
-	memset(&hdev->captured_err_info, 0, sizeof(hdev->captured_err_info));
-	atomic_set(&hdev->captured_err_info.cs_timeout.write_enable, 1);
-	hdev->captured_err_info.undef_opcode.write_enable = true;
+	hl_enable_err_info_capture(&hdev->captured_err_info);
 
 	hdev->open_counter++;
 	hdev->last_successful_open_jif = jiffies;
 	hdev->last_successful_open_ktime = ktime_get();
 
+	file_priv->driver_priv = hpriv;
+	hpriv->file_priv = file_priv;
+
 	return 0;
 
 out_err:
 	mutex_unlock(&hdev->fpriv_list_lock);
-	hl_mem_mgr_fini(&hpriv->mem_mgr);
+	hl_mem_mgr_fini(&hpriv->mem_mgr, NULL);
 	hl_mem_mgr_idr_destroy(&hpriv->mem_mgr);
 	hl_ctx_mgr_fini(hpriv->hdev, &hpriv->ctx_mgr);
-	filp->private_data = NULL;
 	mutex_destroy(&hpriv->ctx_lock);
 	mutex_destroy(&hpriv->restore_phase_mutex);
 	mutex_destroy(&hpriv->notifier_event.lock);
@@ -271,9 +300,7 @@ int hl_device_open_ctrl(struct inode *inode, struct file *filp)
 	 */
 	hpriv->hdev = hdev;
 	filp->private_data = hpriv;
-	hpriv->filp = filp;
 
-	mutex_init(&hpriv->notifier_event.lock);
 	nonseekable_open(inode, filp);
 
 	hpriv->taskpid = get_task_pid(current, PIDTYPE_PID);
@@ -307,7 +334,6 @@ static void set_driver_behavior_per_device(struct hl_device *hdev)
 {
 	hdev->nic_ports_mask = 0;
 	hdev->fw_components = FW_TYPE_ALL_TYPES;
-	hdev->mmu_enable = MMU_EN_ALL;
 	hdev->cpu_queues_enable = 1;
 	hdev->pldm = 0;
 	hdev->hard_reset_on_fw_events = 1;
@@ -321,7 +347,6 @@ static void copy_kernel_module_params_to_device(struct hl_device *hdev)
 	hdev->asic_prop.fw_security_enabled = is_asic_secured(hdev->asic_type);
 
 	hdev->major = hl_major;
-	hdev->hclass = hl_class;
 	hdev->memory_scrub = memory_scrub;
 	hdev->reset_on_lockup = reset_on_lockup;
 	hdev->boot_error_status_mask = boot_error_status_mask;
@@ -336,8 +361,7 @@ static void fixup_device_params_per_asic(struct hl_device *hdev, int timeout)
 		 * a different default timeout for Gaudi
 		 */
 		if (timeout == HL_DEFAULT_TIMEOUT_LOCKED)
-			hdev->timeout_jiffies = msecs_to_jiffies(GAUDI_DEFAULT_TIMEOUT_LOCKED *
-										MSEC_PER_SEC);
+			hdev->timeout_jiffies = secs_to_jiffies(GAUDI_DEFAULT_TIMEOUT_LOCKED);
 
 		hdev->reset_upon_device_release = 0;
 		break;
@@ -362,7 +386,7 @@ static int fixup_device_params(struct hl_device *hdev)
 	hdev->fw_comms_poll_interval_usec = HL_FW_STATUS_POLL_INTERVAL_USEC;
 
 	if (tmp_timeout)
-		hdev->timeout_jiffies = msecs_to_jiffies(tmp_timeout * MSEC_PER_SEC);
+		hdev->timeout_jiffies = secs_to_jiffies(tmp_timeout);
 	else
 		hdev->timeout_jiffies = MAX_SCHEDULE_TIMEOUT;
 
@@ -382,12 +406,36 @@ static int fixup_device_params(struct hl_device *hdev)
 	/* If CPU queues not enabled, no way to do heartbeat */
 	if (!hdev->cpu_queues_enable)
 		hdev->heartbeat = 0;
-
 	fixup_device_params_per_asic(hdev, tmp_timeout);
 
 	return 0;
 }
 
+static int allocate_device_id(struct hl_device *hdev)
+{
+	int id;
+
+	mutex_lock(&hl_devs_idr_lock);
+	id = idr_alloc(&hl_devs_idr, hdev, 0, HL_MAX_MINORS, GFP_KERNEL);
+	mutex_unlock(&hl_devs_idr_lock);
+
+	if (id < 0) {
+		if (id == -ENOSPC)
+			pr_err("too many devices in the system\n");
+		return -EBUSY;
+	}
+
+	hdev->id = id;
+
+	/*
+	 * Firstly initialized with the internal device ID.
+	 * Will be updated later after the DRM device registration to hold the minor ID.
+	 */
+	hdev->cdev_idx = hdev->id;
+
+	return 0;
+}
+
 /**
  * create_hdev - create habanalabs device instance
  *
@@ -400,27 +448,29 @@ static int fixup_device_params(struct hl_device *hdev)
  */
 static int create_hdev(struct hl_device **dev, struct pci_dev *pdev)
 {
-	int main_id, ctrl_id = 0, rc = 0;
 	struct hl_device *hdev;
+	int rc;
 
 	*dev = NULL;
 
-	hdev = kzalloc(sizeof(*hdev), GFP_KERNEL);
-	if (!hdev)
-		return -ENOMEM;
+	hdev = devm_drm_dev_alloc(&pdev->dev, &hl_driver, struct hl_device, drm);
+	if (IS_ERR(hdev))
+		return PTR_ERR(hdev);
+
+	hdev->dev = hdev->drm.dev;
 
 	/* Will be NULL in case of simulator device */
 	hdev->pdev = pdev;
 
 	/* Assign status description string */
-	strncpy(hdev->status[HL_DEVICE_STATUS_OPERATIONAL], "operational", HL_STR_MAX);
-	strncpy(hdev->status[HL_DEVICE_STATUS_IN_RESET], "in reset", HL_STR_MAX);
-	strncpy(hdev->status[HL_DEVICE_STATUS_MALFUNCTION], "disabled", HL_STR_MAX);
-	strncpy(hdev->status[HL_DEVICE_STATUS_NEEDS_RESET], "needs reset", HL_STR_MAX);
-	strncpy(hdev->status[HL_DEVICE_STATUS_IN_DEVICE_CREATION],
-					"in device creation", HL_STR_MAX);
-	strncpy(hdev->status[HL_DEVICE_STATUS_IN_RESET_AFTER_DEVICE_RELEASE],
-					"in reset after device release", HL_STR_MAX);
+	strscpy(hdev->status[HL_DEVICE_STATUS_OPERATIONAL], "operational", HL_STR_MAX);
+	strscpy(hdev->status[HL_DEVICE_STATUS_IN_RESET], "in reset", HL_STR_MAX);
+	strscpy(hdev->status[HL_DEVICE_STATUS_MALFUNCTION], "disabled", HL_STR_MAX);
+	strscpy(hdev->status[HL_DEVICE_STATUS_NEEDS_RESET], "needs reset", HL_STR_MAX);
+	strscpy(hdev->status[HL_DEVICE_STATUS_IN_DEVICE_CREATION],
+				"in device creation", HL_STR_MAX);
+	strscpy(hdev->status[HL_DEVICE_STATUS_IN_RESET_AFTER_DEVICE_RELEASE],
+				"in reset after device release", HL_STR_MAX);
 
 
 	/* First, we must find out which ASIC are we handling. This is needed
@@ -430,7 +480,7 @@ static int create_hdev(struct hl_device **dev, struct pci_dev *pdev)
 	if (hdev->asic_type == ASIC_INVALID) {
 		dev_err(&pdev->dev, "Unsupported ASIC\n");
 		rc = -ENODEV;
-		goto free_hdev;
+		goto out_err;
 	}
 
 	copy_kernel_module_params_to_device(hdev);
@@ -439,42 +489,15 @@ static int create_hdev(struct hl_device **dev, struct pci_dev *pdev)
 
 	fixup_device_params(hdev);
 
-	mutex_lock(&hl_devs_idr_lock);
-
-	/* Always save 2 numbers, 1 for main device and 1 for control.
-	 * They must be consecutive
-	 */
-	main_id = idr_alloc(&hl_devs_idr, hdev, 0, HL_MAX_MINORS, GFP_KERNEL);
-
-	if (main_id >= 0)
-		ctrl_id = idr_alloc(&hl_devs_idr, hdev, main_id + 1,
-					main_id + 2, GFP_KERNEL);
-
-	mutex_unlock(&hl_devs_idr_lock);
-
-	if ((main_id < 0) || (ctrl_id < 0)) {
-		if ((main_id == -ENOSPC) || (ctrl_id == -ENOSPC))
-			pr_err("too many devices in the system\n");
-
-		if (main_id >= 0) {
-			mutex_lock(&hl_devs_idr_lock);
-			idr_remove(&hl_devs_idr, main_id);
-			mutex_unlock(&hl_devs_idr_lock);
-		}
-
-		rc = -EBUSY;
-		goto free_hdev;
-	}
-
-	hdev->id = main_id;
-	hdev->id_control = ctrl_id;
+	rc = allocate_device_id(hdev);
+	if (rc)
+		goto out_err;
 
 	*dev = hdev;
 
 	return 0;
 
-free_hdev:
-	kfree(hdev);
+out_err:
 	return rc;
 }
 
@@ -489,10 +512,8 @@ static 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);
-	idr_remove(&hl_devs_idr, hdev->id_control);
 	mutex_unlock(&hl_devs_idr_lock);
 
-	kfree(hdev);
 }
 
 static int hl_pmops_suspend(struct device *dev)
@@ -653,6 +674,38 @@ static pci_ers_result_t hl_pci_err_slot_reset(struct pci_dev *pdev)
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
+static void hl_pci_reset_prepare(struct pci_dev *pdev)
+{
+	struct hl_device *hdev;
+
+	hdev = pci_get_drvdata(pdev);
+	if (!hdev)
+		return;
+
+	hdev->disabled = true;
+}
+
+static void hl_pci_reset_done(struct pci_dev *pdev)
+{
+	struct hl_device *hdev;
+	u32 flags;
+
+	hdev = pci_get_drvdata(pdev);
+	if (!hdev)
+		return;
+
+	/*
+	 * Schedule a thread to trigger hard reset.
+	 * The reason for this handler, is for rare cases where the driver is up
+	 * and FLR occurs. This is valid only when working with no VM, so FW handles FLR
+	 * and resets the device. FW will go back preboot stage, so driver needs to perform
+	 * hard reset in order to load FW fit again.
+	 */
+	flags = HL_DRV_RESET_HARD | HL_DRV_RESET_BYPASS_REQ_TO_FW;
+
+	hl_device_reset(hdev, flags);
+}
+
 static const struct dev_pm_ops hl_pm_ops = {
 	.suspend = hl_pmops_suspend,
 	.resume = hl_pmops_resume,
@@ -662,6 +715,8 @@ static const struct pci_error_handlers hl_pci_err_handler = {
 	.error_detected = hl_pci_err_detected,
 	.slot_reset = hl_pci_err_slot_reset,
 	.resume = hl_pci_err_resume,
+	.reset_prepare = hl_pci_reset_prepare,
+	.reset_done = hl_pci_reset_done,
 };
 
 static struct pci_driver hl_pci_driver = {
@@ -696,28 +751,16 @@ static int __init hl_init(void)
 
 	hl_major = MAJOR(dev);
 
-	hl_class = class_create(HL_NAME);
-	if (IS_ERR(hl_class)) {
-		pr_err("failed to allocate class\n");
-		rc = PTR_ERR(hl_class);
-		goto remove_major;
-	}
-
-	hl_debugfs_init();
-
 	rc = pci_register_driver(&hl_pci_driver);
 	if (rc) {
 		pr_err("failed to register pci device\n");
-		goto remove_debugfs;
+		goto remove_major;
 	}
 
 	pr_debug("driver loaded\n");
 
 	return 0;
 
-remove_debugfs:
-	hl_debugfs_fini();
-	class_destroy(hl_class);
 remove_major:
 	unregister_chrdev_region(MKDEV(hl_major, 0), HL_MAX_MINORS);
 	return rc;
@@ -730,14 +773,6 @@ static void __exit hl_exit(void)
 {
 	pci_unregister_driver(&hl_pci_driver);
 
-	/*
-	 * Removing debugfs must be after all devices or simulator devices
-	 * have been removed because otherwise we get a bug in the
-	 * debugfs module for referencing NULL objects
-	 */
-	hl_debugfs_fini();
-
-	class_destroy(hl_class);
 	unregister_chrdev_region(MKDEV(hl_major, 0), HL_MAX_MINORS);
 
 	idr_destroy(&hl_devs_idr);