iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

habanalabs/gaudi: invoke device reset from one code block

Browse Source 
[ Upstream commit be572e67dafbf8004d46a2c9d97338c107efb60e ]

In order to prepare the driver code for device reset event
notification, change the event handler function flow to call
device reset from one code block.

In addition, the commit fixes an issue that reset was performed
w/o checking the 'hard_reset_on_fw_event' state and w/o setting
the HL_DRV_RESET_DELAY flag.

Signed-off-by: Tal Cohen <talcohen@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
Tal Cohen 2022-06-08 16:02:09 +03:00 committed by Greg Kroah-Hartman
parent fb806b52ac
commit 6a4aa11781
1 changed files with 16 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
drivers/misc/habanalabs/gaudi/gaudi.c
View File

@ -7717,10 +7717,10 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
struct gaudi_device *gaudi = hdev->asic_specific;
u64 data = le64_to_cpu(eq_entry->data[0]);
u32 ctl = le32_to_cpu(eq_entry->hdr.ctl);
u32 fw_fatal_err_flag = 0;
u32 fw_fatal_err_flag = 0, flags = 0;
u16 event_type = ((ctl & EQ_CTL_EVENT_TYPE_MASK)
>> EQ_CTL_EVENT_TYPE_SHIFT);
bool reset_required;
bool reset_required, reset_direct = false;
u8 cause;
int rc;
@ -7808,7 +7808,8 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
dev_err(hdev->dev, "reset required due to %s\n",
gaudi_irq_map_table[event_type].name);
hl_device_reset(hdev, 0);
reset_direct = true;
goto reset_device;
} else {
hl_fw_unmask_irq(hdev, event_type);
}
@ -7830,7 +7831,8 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
dev_err(hdev->dev, "reset required due to %s\n",
gaudi_irq_map_table[event_type].name);
hl_device_reset(hdev, 0);
reset_direct = true;
goto reset_device;
} else {
hl_fw_unmask_irq(hdev, event_type);
}
@ -7981,12 +7983,17 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
return;
reset_device:
if (hdev->asic_prop.fw_security_enabled)
hl_device_reset(hdev, HL_DRV_RESET_HARD
| HL_DRV_RESET_BYPASS_REQ_TO_FW
| fw_fatal_err_flag);
reset_required = true;
if (hdev->asic_prop.fw_security_enabled && !reset_direct)
flags = HL_DRV_RESET_HARD | HL_DRV_RESET_BYPASS_REQ_TO_FW | fw_fatal_err_flag;
else if (hdev->hard_reset_on_fw_events)
hl_device_reset(hdev, HL_DRV_RESET_HARD | HL_DRV_RESET_DELAY | fw_fatal_err_flag);
flags = HL_DRV_RESET_HARD | HL_DRV_RESET_DELAY | fw_fatal_err_flag;
else
reset_required = false;
if (reset_required)
hl_device_reset(hdev, flags);
else
hl_fw_unmask_irq(hdev, event_type);
}