korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2025-01-08 14:54:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

accel/habanalabs/gaudi2: assume hard-reset by FW upon PCIe AXI drain

Browse Source 
When a PCIe AXI drain event happens, it is possible that the driver
cannot access the device through PCIe, and therefore cannot send a
hard-reset request to FW.
Starting from FW version 1.13, FW will initiate a hard-reset in such
a case without waiting for a reset request from the driver.

Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This commit is contained in:
Tomer Tayar 2023-10-15 14:04:53 +03:00 committed by Oded Gabbay
parent fbc2a09e09
commit c648548233
2 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
drivers/accel/habanalabs/common/habanalabs.h
View File

@ -3594,6 +3594,14 @@ static inline bool hl_is_fw_sw_ver_below(struct hl_device *hdev, u32 fw_sw_major
return false;
}
static inline bool hl_is_fw_sw_ver_equal_or_greater(struct hl_device *hdev, u32 fw_sw_major,
u32 fw_sw_minor)
{
return (hdev->fw_sw_major_ver > fw_sw_major ||
(hdev->fw_sw_major_ver == fw_sw_major &&
hdev->fw_sw_minor_ver >= fw_sw_minor));
}
/*
* Kernel module functions that can be accessed by entire module
*/

2
drivers/accel/habanalabs/gaudi2/gaudi2.c
View File

@ -10007,6 +10007,8 @@ static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_ent
error_count = gaudi2_handle_pcie_drain(hdev, &eq_entry->pcie_drain_ind_data);
reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
if (hl_is_fw_sw_ver_equal_or_greater(hdev, 1, 13))
is_critical = true;
break;
case GAUDI2_EVENT_PSOC59_RPM_ERROR_OR_DRAIN: