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>

1 files changed, 50 insertions, 0 deletions

diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c
index 905eff1f840ed..d3a217929a248 100644
--- a/drivers/misc/uacce/uacce.c
+++ b/drivers/misc/uacce/uacce.c
@@ -363,12 +363,52 @@ static ssize_t region_dus_size_show(struct device *dev,
 		       uacce->qf_pg_num[UACCE_QFRT_DUS] << PAGE_SHIFT);
 }
 
+static ssize_t isolate_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct uacce_device *uacce = to_uacce_device(dev);
+
+	return sysfs_emit(buf, "%d\n", uacce->ops->get_isolate_state(uacce));
+}
+
+static ssize_t isolate_strategy_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct uacce_device *uacce = to_uacce_device(dev);
+	u32 val;
+
+	val = uacce->ops->isolate_err_threshold_read(uacce);
+
+	return sysfs_emit(buf, "%u\n", val);
+}
+
+static ssize_t isolate_strategy_store(struct device *dev, struct device_attribute *attr,
+				   const char *buf, size_t count)
+{
+	struct uacce_device *uacce = to_uacce_device(dev);
+	unsigned long val;
+	int ret;
+
+	if (kstrtoul(buf, 0, &val) < 0)
+		return -EINVAL;
+
+	if (val > UACCE_MAX_ERR_THRESHOLD)
+		return -EINVAL;
+
+	ret = uacce->ops->isolate_err_threshold_write(uacce, val);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
 static DEVICE_ATTR_RO(api);
 static DEVICE_ATTR_RO(flags);
 static DEVICE_ATTR_RO(available_instances);
 static DEVICE_ATTR_RO(algorithms);
 static DEVICE_ATTR_RO(region_mmio_size);
 static DEVICE_ATTR_RO(region_dus_size);
+static DEVICE_ATTR_RO(isolate);
+static DEVICE_ATTR_RW(isolate_strategy);
 
 static struct attribute *uacce_dev_attrs[] = {
 	&dev_attr_api.attr,
@@ -377,6 +417,8 @@ static struct attribute *uacce_dev_attrs[] = {
 	&dev_attr_algorithms.attr,
 	&dev_attr_region_mmio_size.attr,
 	&dev_attr_region_dus_size.attr,
+	&dev_attr_isolate.attr,
+	&dev_attr_isolate_strategy.attr,
 	NULL,
 };
 
@@ -392,6 +434,14 @@ static umode_t uacce_dev_is_visible(struct kobject *kobj,
 	    (!uacce->qf_pg_num[UACCE_QFRT_DUS])))
 		return 0;
 
+	if (attr == &dev_attr_isolate_strategy.attr &&
+	    (!uacce->ops->isolate_err_threshold_read &&
+	     !uacce->ops->isolate_err_threshold_write))
+		return 0;
+
+	if (attr == &dev_attr_isolate.attr && !uacce->ops->get_isolate_state)
+		return 0;
+
 	return attr->mode;
 }