diff options
| author | Kai Ye <yekai13@huawei.com> | 2022-11-19 08:48:15 +0100 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2023-01-20 12:06:26 +0100 |
| commit | e3e289fbc0b520cf469469e8cdba84a50424eb65 (patch) | |
| tree | dacb4275ddd034fc5c657f6bc4c992f6eba584f9 /include | |
| parent | scripts/tags.sh: choose which directories to exclude from being indexed (diff) | |
| download | linux-e3e289fbc0b520cf469469e8cdba84a50424eb65.tar.xz linux-e3e289fbc0b520cf469469e8cdba84a50424eb65.zip | |
uacce: supports device isolation feature
UACCE adds the hardware error isolation feature. To improve service
reliability, some uacce devices that frequently encounter hardware
errors are isolated. Therefore, this feature is added.
Users can configure the hardware error threshold by 'isolate_strategy'
sysfs node. The user space can get the device isolated state by 'isolate'
sysfs node. If the number of device errors exceeds the configured error
threshold, the device will be isolated. It means the uacce device is
unavailable.
Signed-off-by: Kai Ye <yekai13@huawei.com>
Link: https://lore.kernel.org/r/20221119074817.12063-2-yekai13@huawei.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/uacce.h | 12 |
1 files changed, 12 insertions, 0 deletions
diff --git a/include/linux/uacce.h b/include/linux/uacce.h index 9ce88c28b0a8..0a81c3dfd26c 100644 --- a/include/linux/uacce.h +++ b/include/linux/uacce.h @@ -8,6 +8,7 @@ #define UACCE_NAME "uacce" #define UACCE_MAX_REGION 2 #define UACCE_MAX_NAME_SIZE 64 +#define UACCE_MAX_ERR_THRESHOLD 65535 struct uacce_queue; struct uacce_device; @@ -30,6 +31,9 @@ struct uacce_qfile_region { * @is_q_updated: check whether the task is finished * @mmap: mmap addresses of queue to user space * @ioctl: ioctl for user space users of the queue + * @get_isolate_state: get the device state after set the isolate strategy + * @isolate_err_threshold_write: stored the isolate error threshold to the device + * @isolate_err_threshold_read: read the isolate error threshold value from the device */ struct uacce_ops { int (*get_available_instances)(struct uacce_device *uacce); @@ -43,6 +47,9 @@ struct uacce_ops { struct uacce_qfile_region *qfr); long (*ioctl)(struct uacce_queue *q, unsigned int cmd, unsigned long arg); + enum uacce_dev_state (*get_isolate_state)(struct uacce_device *uacce); + int (*isolate_err_threshold_write)(struct uacce_device *uacce, u32 num); + u32 (*isolate_err_threshold_read)(struct uacce_device *uacce); }; /** @@ -57,6 +64,11 @@ struct uacce_interface { const struct uacce_ops *ops; }; +enum uacce_dev_state { + UACCE_DEV_NORMAL, + UACCE_DEV_ISOLATE, +}; + enum uacce_q_state { UACCE_Q_ZOMBIE = 0, UACCE_Q_INIT, |