Messages in this thread Patch in this message | | | From | Oded Gabbay <> | Subject | [PATCH 09/12] habanalabs: handle events during soft-reset | Date | Sun, 28 Nov 2021 21:34:32 +0200 |
| |
From: Ofir Bitton <obitton@habana.ai>
Driver should handle events during soft-reset as F/W is not going through reset and it keeps sending events towards host.
Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org> --- drivers/misc/habanalabs/common/device.c | 4 ++++ drivers/misc/habanalabs/common/habanalabs.h | 2 ++ drivers/misc/habanalabs/common/irq.c | 2 +- 3 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c index 822d9cec5aaf..720eea0b7e9c 100644 --- a/drivers/misc/habanalabs/common/device.c +++ b/drivers/misc/habanalabs/common/device.c @@ -1019,6 +1019,8 @@ int hl_device_reset(struct hl_device *hdev, u32 flags) handle_reset_trigger(hdev, flags); + hdev->is_in_soft_reset = !hard_reset; + /* This also blocks future CS/VM/JOB completion operations */ hdev->disabled = true; @@ -1171,6 +1173,7 @@ int hl_device_reset(struct hl_device *hdev, u32 flags) * is required for the initialization itself */ hdev->disabled = false; + hdev->is_in_soft_reset = false; rc = hdev->asic_funcs->hw_init(hdev); if (rc) { @@ -1242,6 +1245,7 @@ int hl_device_reset(struct hl_device *hdev, u32 flags) out_err: hdev->disabled = true; + hdev->is_in_soft_reset = false; if (hard_reset) { dev_err(hdev->dev, "Failed to reset! Device is NOT usable\n"); diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index a465b4a5f31d..c2129c9fe9e4 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -2591,6 +2591,7 @@ struct last_error_session_info { * protocol will throw an error. Relevant only for * cases where Linux was not loaded to device CPU * @supports_wait_for_multi_cs: true if wait for multi CS is supported + * @is_in_soft_reset: Device is currently in soft reset process. */ struct hl_device { struct pci_dev *pdev; @@ -2719,6 +2720,7 @@ struct hl_device { u8 device_cpu_is_halted; u8 supports_wait_for_multi_cs; u8 stream_master_qid_arr_size; + u8 is_in_soft_reset; /* Parameters for bring-up */ u64 nic_ports_mask; diff --git a/drivers/misc/habanalabs/common/irq.c b/drivers/misc/habanalabs/common/irq.c index 9fd4c18e274e..64e0d9de21bd 100644 --- a/drivers/misc/habanalabs/common/irq.c +++ b/drivers/misc/habanalabs/common/irq.c @@ -245,7 +245,7 @@ irqreturn_t hl_irq_handler_eq(int irq, void *arg) */ dma_rmb(); - if (hdev->disabled) { + if (hdev->disabled && !hdev->is_in_soft_reset) { dev_warn(hdev->dev, "Device disabled but received an EQ event\n"); goto skip_irq; } -- 2.25.1
| |