diff options
| author | Oded Gabbay <ogabbay@kernel.org> | 2021-02-16 22:46:17 +0200 |
|---|---|---|
| committer | Oded Gabbay <ogabbay@kernel.org> | 2021-04-09 14:09:22 +0300 |
| commit | 23c3efd1fb0eb19b9e39eeb07515b167f6d4517a (patch) | |
| tree | 37ca8c1c03e69d456213d106e0b1fe1d283bc289 /drivers/misc | |
| parent | 35862d1c99471e3a03175e94d267815a0921e9ca (diff) | |
habanalabs: fail reset if device is not idle
After any reset (soft or hard) the device (the engines/QMANs) should
be idle. If they are not idle, fail the reset. If it is soft-reset,
the driver will try to do hard-reset automatically. If it is hard-reset,
the driver will make the device non-operational.
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Diffstat (limited to 'drivers/misc')
| -rw-r--r-- | drivers/misc/habanalabs/common/device.c | 26 |
1 files changed, 12 insertions, 14 deletions
diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c index cba23e5f1bb3..1d18c41d331a 100644 --- a/drivers/misc/habanalabs/common/device.c +++ b/drivers/misc/habanalabs/common/device.c @@ -71,21 +71,8 @@ static void hpriv_release(struct kref *ref) kfree(hpriv); - if (hdev->reset_upon_device_release) { - u64 idle_mask[HL_BUSY_ENGINES_MASK_EXT_SIZE] = {0}; - - /* We try soft reset first */ + if (hdev->reset_upon_device_release) hl_device_reset(hdev, false, false); - - /* If device is not idle perform hard reset */ - if (!hdev->asic_funcs->is_device_idle(hdev, idle_mask, - HL_BUSY_ENGINES_MASK_EXT_SIZE, NULL)) { - dev_info(hdev->dev, - "device is not idle (mask %#llx %#llx) after soft reset, performing hard reset", - idle_mask[0], idle_mask[1]); - hl_device_reset(hdev, true, false); - } - } } void hl_hpriv_get(struct hl_fpriv *hpriv) @@ -948,6 +935,7 @@ static void device_disable_open_processes(struct hl_device *hdev) int hl_device_reset(struct hl_device *hdev, bool hard_reset, bool from_hard_reset_thread) { + u64 idle_mask[HL_BUSY_ENGINES_MASK_EXT_SIZE] = {0}; int i, rc; if (!hdev->init_done) { @@ -1167,6 +1155,16 @@ kill_processes: goto out_err; } + /* If device is not idle fail the reset process */ + if (!hdev->asic_funcs->is_device_idle(hdev, idle_mask, + HL_BUSY_ENGINES_MASK_EXT_SIZE, NULL)) { + dev_err(hdev->dev, + "device is not idle (mask %#llx %#llx) after reset\n", + idle_mask[0], idle_mask[1]); + rc = -EIO; + goto out_err; + } + /* Check that the communication with the device is working */ rc = hdev->asic_funcs->test_queues(hdev); if (rc) { |