diff options
| author | Oded Gabbay <oded.gabbay@gmail.com> | 2019-02-16 00:39:21 +0200 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2019-02-18 09:46:45 +0100 |
| commit | eff6f4a0e70b7bcf4674f471a768860a74e638a6 (patch) | |
| tree | e39e2436c9022aa993d935e37507dece50a5e8e4 /drivers/misc/habanalabs/habanalabs_drv.c | |
| parent | f8c8c7d5f1b0ea85fe6b4fe2dc63d72774a29184 (diff) | |
| download | linux-eff6f4a0e70b7bcf4674f471a768860a74e638a6.tar.bz2 | |
habanalabs: add command submission module
This patch adds the main flow for the user to submit work to the device.
Each work is described by a command submission object (CS). The CS contains
3 arrays of command buffers: One for execution, and two for context-switch
(store and restore).
For each CB, the user specifies on which queue to put that CB. In case of
an internal queue, the entry doesn't contain a pointer to the CB but the
address in the on-chip memory that the CB resides at.
The driver parses some of the CBs to enforce security restrictions.
The user receives a sequence number that represents the CS object. The user
can then query the driver regarding the status of the CS, using that
sequence number.
In case the CS doesn't finish before the timeout expires, the driver will
perform a soft-reset of the device.
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>
Diffstat (limited to 'drivers/misc/habanalabs/habanalabs_drv.c')
| -rw-r--r-- | drivers/misc/habanalabs/habanalabs_drv.c | 20 |
1 files changed, 20 insertions, 0 deletions
diff --git a/drivers/misc/habanalabs/habanalabs_drv.c b/drivers/misc/habanalabs/habanalabs_drv.c index b0bf77af1e40..77a1cc85e530 100644 --- a/drivers/misc/habanalabs/habanalabs_drv.c +++ b/drivers/misc/habanalabs/habanalabs_drv.c @@ -24,6 +24,17 @@ static struct class *hl_class; DEFINE_IDR(hl_devs_idr); DEFINE_MUTEX(hl_devs_idr_lock); +static int timeout_locked = 5; +static int reset_on_lockup = 1; + +module_param(timeout_locked, int, 0444); +MODULE_PARM_DESC(timeout_locked, + "Device lockup timeout in seconds (0 = disabled, default 5s)"); + +module_param(reset_on_lockup, int, 0444); +MODULE_PARM_DESC(reset_on_lockup, + "Do device reset on lockup (0 = no, 1 = yes, default yes)"); + #define PCI_VENDOR_ID_HABANALABS 0x1da3 #define PCI_IDS_GOYA 0x0001 @@ -113,6 +124,7 @@ int hl_device_open(struct inode *inode, struct file *filp) hpriv->hdev = hdev; filp->private_data = hpriv; hpriv->filp = filp; + mutex_init(&hpriv->restore_phase_mutex); kref_init(&hpriv->refcount); nonseekable_open(inode, filp); @@ -140,6 +152,7 @@ out_err: filp->private_data = NULL; hl_ctx_mgr_fini(hpriv->hdev, &hpriv->ctx_mgr); hl_cb_mgr_fini(hpriv->hdev, &hpriv->cb_mgr); + mutex_destroy(&hpriv->restore_phase_mutex); kfree(hpriv); close_device: @@ -172,8 +185,10 @@ int create_hdev(struct hl_device **dev, struct pci_dev *pdev, return -ENOMEM; hdev->major = hl_major; + hdev->reset_on_lockup = reset_on_lockup; /* Parameters for bring-up - set them to defaults */ + hdev->mmu_enable = 0; hdev->cpu_enable = 1; hdev->reset_pcilink = 0; hdev->cpu_queues_enable = 1; @@ -193,6 +208,11 @@ int create_hdev(struct hl_device **dev, struct pci_dev *pdev, if (!hdev->cpu_queues_enable) hdev->heartbeat = 0; + if (timeout_locked) + hdev->timeout_jiffies = msecs_to_jiffies(timeout_locked * 1000); + else + hdev->timeout_jiffies = MAX_SCHEDULE_TIMEOUT; + hdev->disabled = true; hdev->pdev = pdev; /* can be NULL in case of simulator device */ |