[RFC PATCH v2 1/5] libnvdimm/dax: Add a dax flag to control synchronous fault support

["Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>]

With POWER10, architecture is adding new pmem flush and sync instructions.
The kernel should prevent the usage of MAP_SYNC if applications are not using
the new instructions on newer hardware

This patch adds a dax attribute (/sys/bus/nd/devices/region0/pfn0.1/block/pmem0/dax/sync_fault)
which can be used to control this flag. If the device supports synchronous flush
then userspace can update this attribute to enable/disable the synchronous
fault. The attribute is only visible if there is write cache enabled on the device.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 drivers/dax/super.c | 73 ++++++++++++++++++++++++++++++++++++++++++++-
 mm/Kconfig          |  3 ++
 2 files changed, 75 insertions(+), 1 deletion(-)

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 8e32345be0f7..980f7be7e56d 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -198,6 +198,12 @@ enum dax_device_flags {
 	DAXDEV_WRITE_CACHE,
 	/* flag to check if device supports synchronous flush */
 	DAXDEV_SYNC,
+	/*
+	 * flag to indicate whether synchronous flush is enabled.
+	 * Some platform may want to disable synchronous flush support
+	 * even though device supports the same.
+	 */
+	DAXDEV_SYNC_ENABLED,
 };
 
 /**
@@ -254,6 +260,60 @@ static ssize_t write_cache_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(write_cache);
 
+static bool dax_synchronous_enabled(struct dax_device *dax_dev)
+{
+	return test_bit(DAXDEV_SYNC_ENABLED, &dax_dev->flags);
+}
+
+static void set_dax_synchronous_enable(struct dax_device *dax_dev, bool enable)
+{
+	if (!test_bit(DAXDEV_SYNC, &dax_dev->flags))
+		return;
+
+	if (enable)
+		set_bit(DAXDEV_SYNC_ENABLED, &dax_dev->flags);
+	else
+		clear_bit(DAXDEV_SYNC_ENABLED, &dax_dev->flags);
+}
+
+
+static ssize_t sync_fault_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct dax_device *dax_dev = dax_get_by_host(dev_name(dev));
+	ssize_t rc;
+
+	WARN_ON_ONCE(!dax_dev);
+	if (!dax_dev)
+		return -ENXIO;
+
+	rc = sprintf(buf, "%d\n", !!__dax_synchronous(dax_dev));
+	put_dax(dax_dev);
+	return rc;
+}
+
+static ssize_t sync_fault_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	bool enable_sync;
+	int rc = strtobool(buf, &enable_sync);
+	struct dax_device *dax_dev = dax_get_by_host(dev_name(dev));
+
+	WARN_ON_ONCE(!dax_dev);
+	if (!dax_dev)
+		return -ENXIO;
+
+	if (rc)
+		len = rc;
+	else
+		set_dax_synchronous_enable(dax_dev, enable_sync);
+
+	put_dax(dax_dev);
+	return len;
+}
+
+static DEVICE_ATTR_RW(sync_fault);
+
 static umode_t dax_visible(struct kobject *kobj, struct attribute *a, int n)
 {
 	struct device *dev = container_of(kobj, typeof(*dev), kobj);
@@ -267,11 +327,18 @@ static umode_t dax_visible(struct kobject *kobj, struct attribute *a, int n)
 	if (a == &dev_attr_write_cache.attr)
 		return 0;
 #endif
+	if (a == &dev_attr_sync_fault.attr) {
+		if (dax_write_cache_enabled(dax_dev))
+			return a->mode;
+		return 0;
+	}
+
 	return a->mode;
 }
 
 static struct attribute *dax_attributes[] = {
 	&dev_attr_write_cache.attr,
+	&dev_attr_sync_fault.attr,
 	NULL,
 };
 
@@ -394,13 +461,17 @@ EXPORT_SYMBOL_GPL(dax_write_cache_enabled);
 
 bool __dax_synchronous(struct dax_device *dax_dev)
 {
-	return test_bit(DAXDEV_SYNC, &dax_dev->flags);
+	return test_bit(DAXDEV_SYNC, &dax_dev->flags) &&
+		test_bit(DAXDEV_SYNC_ENABLED, &dax_dev->flags);
 }
 EXPORT_SYMBOL_GPL(__dax_synchronous);
 
 void __set_dax_synchronous(struct dax_device *dax_dev)
 {
 	set_bit(DAXDEV_SYNC, &dax_dev->flags);
+#ifndef CONFIG_ARCH_MAP_SYNC_DISABLE
+	set_bit(DAXDEV_SYNC_ENABLED, &dax_dev->flags);
+#endif
 }
 EXPORT_SYMBOL_GPL(__set_dax_synchronous);
 
diff --git a/mm/Kconfig b/mm/Kconfig
index c1acc34c1c35..38fd7cfbfca8 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -867,4 +867,7 @@ config ARCH_HAS_HUGEPD
 config MAPPING_DIRTY_HELPERS
         bool
 
+config ARCH_MAP_SYNC_DISABLE
+	bool
+
 endmenu
-- 
2.26.2
_______________________________________________
Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org
To unsubscribe send an email to linux-nvdimm-leave@lists.01.org