[v4,3/3] dax: add a sysfs knob to control memmap_on_memory behavior

Message ID 20231212-vv-dax_abi-v4-3-1351758f0c92@intel.com
State New
Headers
Series Add DAX ABI for memmap_on_memory |

Commit Message

Verma, Vishal L Dec. 12, 2023, 7:08 p.m. UTC
  Add a sysfs knob for dax devices to control the memmap_on_memory setting
if the dax device were to be hotplugged as system memory.

The default memmap_on_memory setting for dax devices originating via
pmem or hmem is set to 'false' - i.e. no memmap_on_memory semantics, to
preserve legacy behavior. For dax devices via CXL, the default is on.
The sysfs control allows the administrator to override the above
defaults if needed.

Cc: David Hildenbrand <david@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Tested-by: Li Zhijian <lizhijian@fujitsu.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
---
 drivers/dax/bus.c                       | 32 ++++++++++++++++++++++++++++++++
 Documentation/ABI/testing/sysfs-bus-dax | 17 +++++++++++++++++
 2 files changed, 49 insertions(+)
  

Comments

Huang, Ying Dec. 13, 2023, 1:10 a.m. UTC | #1
Vishal Verma <vishal.l.verma@intel.com> writes:

> Add a sysfs knob for dax devices to control the memmap_on_memory setting
> if the dax device were to be hotplugged as system memory.
>
> The default memmap_on_memory setting for dax devices originating via
> pmem or hmem is set to 'false' - i.e. no memmap_on_memory semantics, to
> preserve legacy behavior. For dax devices via CXL, the default is on.
> The sysfs control allows the administrator to override the above
> defaults if needed.
>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: Dan Williams <dan.j.williams@intel.com>
> Cc: Dave Jiang <dave.jiang@intel.com>
> Cc: Dave Hansen <dave.hansen@linux.intel.com>
> Cc: Huang Ying <ying.huang@intel.com>
> Tested-by: Li Zhijian <lizhijian@fujitsu.com>
> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
> Reviewed-by: David Hildenbrand <david@redhat.com>
> Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
> ---
>  drivers/dax/bus.c                       | 32 ++++++++++++++++++++++++++++++++
>  Documentation/ABI/testing/sysfs-bus-dax | 17 +++++++++++++++++
>  2 files changed, 49 insertions(+)
>
> diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
> index ce1356ac6dc2..423adee6f802 100644
> --- a/drivers/dax/bus.c
> +++ b/drivers/dax/bus.c
> @@ -1245,6 +1245,37 @@ static ssize_t numa_node_show(struct device *dev,
>  }
>  static DEVICE_ATTR_RO(numa_node);
>  
> +static ssize_t memmap_on_memory_show(struct device *dev,
> +				     struct device_attribute *attr, char *buf)
> +{
> +	struct dev_dax *dev_dax = to_dev_dax(dev);
> +
> +	return sprintf(buf, "%d\n", dev_dax->memmap_on_memory);
> +}
> +
> +static ssize_t memmap_on_memory_store(struct device *dev,
> +				      struct device_attribute *attr,
> +				      const char *buf, size_t len)
> +{
> +	struct dax_device_driver *dax_drv = to_dax_drv(dev->driver);
> +	struct dev_dax *dev_dax = to_dev_dax(dev);
> +	ssize_t rc;
> +	bool val;
> +
> +	rc = kstrtobool(buf, &val);
> +	if (rc)
> +		return rc;
> +
> +	guard(device)(dev);
> +	if (dev_dax->memmap_on_memory != val &&
> +	    dax_drv->type == DAXDRV_KMEM_TYPE)

Should we check "dev->driver != NULL" here, and should we move

        dax_drv = to_dax_drv(dev->driver);

here with device lock held?

--
Best Regards,
Huang, Ying

> +		return -EBUSY;
> +	dev_dax->memmap_on_memory = val;
> +
> +	return len;
> +}
> +static DEVICE_ATTR_RW(memmap_on_memory);
> +
>  static umode_t dev_dax_visible(struct kobject *kobj, struct attribute *a, int n)
>  {
>  	struct device *dev = container_of(kobj, struct device, kobj);
> @@ -1271,6 +1302,7 @@ static struct attribute *dev_dax_attributes[] = {
>  	&dev_attr_align.attr,
>  	&dev_attr_resource.attr,
>  	&dev_attr_numa_node.attr,
> +	&dev_attr_memmap_on_memory.attr,
>  	NULL,
>  };
>  
> diff --git a/Documentation/ABI/testing/sysfs-bus-dax b/Documentation/ABI/testing/sysfs-bus-dax
> index a61a7b186017..b1fd8bf8a7de 100644
> --- a/Documentation/ABI/testing/sysfs-bus-dax
> +++ b/Documentation/ABI/testing/sysfs-bus-dax
> @@ -149,3 +149,20 @@ KernelVersion:	v5.1
>  Contact:	nvdimm@lists.linux.dev
>  Description:
>  		(RO) The id attribute indicates the region id of a dax region.
> +
> +What:		/sys/bus/dax/devices/daxX.Y/memmap_on_memory
> +Date:		October, 2023
> +KernelVersion:	v6.8
> +Contact:	nvdimm@lists.linux.dev
> +Description:
> +		(RW) Control the memmap_on_memory setting if the dax device
> +		were to be hotplugged as system memory. This determines whether
> +		the 'altmap' for the hotplugged memory will be placed on the
> +		device being hotplugged (memmap_on_memory=1) or if it will be
> +		placed on regular memory (memmap_on_memory=0). This attribute
> +		must be set before the device is handed over to the 'kmem'
> +		driver (i.e.  hotplugged into system-ram). Additionally, this
> +		depends on CONFIG_MHP_MEMMAP_ON_MEMORY, and a globally enabled
> +		memmap_on_memory parameter for memory_hotplug. This is
> +		typically set on the kernel command line -
> +		memory_hotplug.memmap_on_memory set to 'true' or 'force'."
  

Patch

diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index ce1356ac6dc2..423adee6f802 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -1245,6 +1245,37 @@  static ssize_t numa_node_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(numa_node);
 
+static ssize_t memmap_on_memory_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct dev_dax *dev_dax = to_dev_dax(dev);
+
+	return sprintf(buf, "%d\n", dev_dax->memmap_on_memory);
+}
+
+static ssize_t memmap_on_memory_store(struct device *dev,
+				      struct device_attribute *attr,
+				      const char *buf, size_t len)
+{
+	struct dax_device_driver *dax_drv = to_dax_drv(dev->driver);
+	struct dev_dax *dev_dax = to_dev_dax(dev);
+	ssize_t rc;
+	bool val;
+
+	rc = kstrtobool(buf, &val);
+	if (rc)
+		return rc;
+
+	guard(device)(dev);
+	if (dev_dax->memmap_on_memory != val &&
+	    dax_drv->type == DAXDRV_KMEM_TYPE)
+		return -EBUSY;
+	dev_dax->memmap_on_memory = val;
+
+	return len;
+}
+static DEVICE_ATTR_RW(memmap_on_memory);
+
 static umode_t dev_dax_visible(struct kobject *kobj, struct attribute *a, int n)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
@@ -1271,6 +1302,7 @@  static struct attribute *dev_dax_attributes[] = {
 	&dev_attr_align.attr,
 	&dev_attr_resource.attr,
 	&dev_attr_numa_node.attr,
+	&dev_attr_memmap_on_memory.attr,
 	NULL,
 };
 
diff --git a/Documentation/ABI/testing/sysfs-bus-dax b/Documentation/ABI/testing/sysfs-bus-dax
index a61a7b186017..b1fd8bf8a7de 100644
--- a/Documentation/ABI/testing/sysfs-bus-dax
+++ b/Documentation/ABI/testing/sysfs-bus-dax
@@ -149,3 +149,20 @@  KernelVersion:	v5.1
 Contact:	nvdimm@lists.linux.dev
 Description:
 		(RO) The id attribute indicates the region id of a dax region.
+
+What:		/sys/bus/dax/devices/daxX.Y/memmap_on_memory
+Date:		October, 2023
+KernelVersion:	v6.8
+Contact:	nvdimm@lists.linux.dev
+Description:
+		(RW) Control the memmap_on_memory setting if the dax device
+		were to be hotplugged as system memory. This determines whether
+		the 'altmap' for the hotplugged memory will be placed on the
+		device being hotplugged (memmap_on_memory=1) or if it will be
+		placed on regular memory (memmap_on_memory=0). This attribute
+		must be set before the device is handed over to the 'kmem'
+		driver (i.e.  hotplugged into system-ram). Additionally, this
+		depends on CONFIG_MHP_MEMMAP_ON_MEMORY, and a globally enabled
+		memmap_on_memory parameter for memory_hotplug. This is
+		typically set on the kernel command line -
+		memory_hotplug.memmap_on_memory set to 'true' or 'force'."