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>
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 | 40 +++++++++++++++++++++++++++++++++
Documentation/ABI/testing/sysfs-bus-dax | 13 +++++++++++
2 files changed, 53 insertions(+)
diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 1ff1ab5fa105..11abb57cc031 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -1270,6 +1270,45 @@ 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 dev_dax *dev_dax = to_dev_dax(dev);
+ struct dax_region *dax_region = dev_dax->region;
+ ssize_t rc;
+ bool val;
+
+ rc = kstrtobool(buf, &val);
+ if (rc)
+ return rc;
+
+ if (dev_dax->memmap_on_memory == val)
+ return len;
+
+ device_lock(dax_region->dev);
+ if (!dax_region->dev->driver) {
+ device_unlock(dax_region->dev);
+ return -ENXIO;
+ }
+
+ device_lock(dev);
+ dev_dax->memmap_on_memory = val;
+ device_unlock(dev);
+
+ device_unlock(dax_region->dev);
+ return rc == 0 ? len : rc;
+}
+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);
@@ -1296,6 +1335,7 @@ 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..bb063a004e41 100644
--- a/Documentation/ABI/testing/sysfs-bus-dax
+++ b/Documentation/ABI/testing/sysfs-bus-dax
@@ -149,3 +149,16 @@ 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).
--
2.41.0On 07.12.23 05:36, Vishal Verma wrote:
> 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>
> 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 | 40 +++++++++++++++++++++++++++++++++
> Documentation/ABI/testing/sysfs-bus-dax | 13 +++++++++++
> 2 files changed, 53 insertions(+)
>
> diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
> index 1ff1ab5fa105..11abb57cc031 100644
> --- a/drivers/dax/bus.c
> +++ b/drivers/dax/bus.c
> @@ -1270,6 +1270,45 @@ 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 dev_dax *dev_dax = to_dev_dax(dev);
> + struct dax_region *dax_region = dev_dax->region;
> + ssize_t rc;
> + bool val;
> +
> + rc = kstrtobool(buf, &val);
> + if (rc)
> + return rc;
> +
> + if (dev_dax->memmap_on_memory == val)
> + return len;
> +
> + device_lock(dax_region->dev);
> + if (!dax_region->dev->driver) {
> + device_unlock(dax_region->dev);
> + return -ENXIO;
> + }
> +
> + device_lock(dev);
> + dev_dax->memmap_on_memory = val;
> + device_unlock(dev);
> +
> + device_unlock(dax_region->dev);
> + return rc == 0 ? len : rc;
> +}
> +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);
> @@ -1296,6 +1335,7 @@ 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..bb063a004e41 100644
> --- a/Documentation/ABI/testing/sysfs-bus-dax
> +++ b/Documentation/ABI/testing/sysfs-bus-dax
> @@ -149,3 +149,16 @@ 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).
>
Should we note the dependency on other factors as given in
mhp_supports_memmap_on_memory(), especially, the system-wide setting and
some weird kernel configurations?
--
Cheers,
David / dhildenb
On Fri, 2023-12-08 at 12:36 +0100, David Hildenbrand wrote: > On 07.12.23 05:36, Vishal Verma wrote: [..] > > > > + > > +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). > > > > Should we note the dependency on other factors as given in > mhp_supports_memmap_on_memory(), especially, the system-wide setting and > some weird kernel configurations? > Yep good idea, I'll make a note of those for v3.
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>
> 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 | 40 +++++++++++++++++++++++++++++++++
> Documentation/ABI/testing/sysfs-bus-dax | 13 +++++++++++
> 2 files changed, 53 insertions(+)
>
> diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
> index 1ff1ab5fa105..11abb57cc031 100644
> --- a/drivers/dax/bus.c
> +++ b/drivers/dax/bus.c
> @@ -1270,6 +1270,45 @@ 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 dev_dax *dev_dax = to_dev_dax(dev);
> + struct dax_region *dax_region = dev_dax->region;
> + ssize_t rc;
> + bool val;
> +
> + rc = kstrtobool(buf, &val);
> + if (rc)
> + return rc;
> +
> + if (dev_dax->memmap_on_memory == val)
> + return len;
> +
> + device_lock(dax_region->dev);
> + if (!dax_region->dev->driver) {
This still doesn't look right. Can we check whether the current driver
is kmem? And only allow change if it's not kmem?
--
Best Regards,
Huang, Ying
> + device_unlock(dax_region->dev);
> + return -ENXIO;
> + }
> +
> + device_lock(dev);
> + dev_dax->memmap_on_memory = val;
> + device_unlock(dev);
> +
> + device_unlock(dax_region->dev);
> + return rc == 0 ? len : rc;
> +}
> +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);
> @@ -1296,6 +1335,7 @@ 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..bb063a004e41 100644
> --- a/Documentation/ABI/testing/sysfs-bus-dax
> +++ b/Documentation/ABI/testing/sysfs-bus-dax
> @@ -149,3 +149,16 @@ 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).
On Fri, 2023-12-08 at 11:13 +0800, Huang, Ying wrote:
> Vishal Verma <vishal.l.verma@intel.com> writes:
>
[..]
> >
> > +
> > +static ssize_t memmap_on_memory_store(struct device *dev,
> > + struct device_attribute *attr,
> > + const char *buf, size_t len)
> > +{
> > + struct dev_dax *dev_dax = to_dev_dax(dev);
> > + struct dax_region *dax_region = dev_dax->region;
> > + ssize_t rc;
> > + bool val;
> > +
> > + rc = kstrtobool(buf, &val);
> > + if (rc)
> > + return rc;
> > +
> > + if (dev_dax->memmap_on_memory == val)
> > + return len;
> > +
> > + device_lock(dax_region->dev);
> > + if (!dax_region->dev->driver) {
>
> This still doesn't look right. Can we check whether the current driver
> is kmem? And only allow change if it's not kmem?
Ah yes I lost track of this todo between revisions when I split this
out. Let me fix that for the next revision.
Hi Vishal,
On 07/12/2023 12:36, Vishal Verma wrote:
> +
> +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
s/memmap_on+memory=1/memmap_on_memory=1
I have a question here
What relationship about memmap_on_memory and 'ndctl-create-namespace -M' option which
specifies where is the vmemmap backed memory.
I'm confused that memmap_on_memory=1 and '-M dev' are the same for nvdimm devdax mode ?
ndctl-create-namespace
...
-M, --map=
A pmem namespace in "fsdax" or "devdax" mode requires allocation of per-page metadata. The allocation
can be drawn from either:
• "mem": typical system memory
• "dev": persistent memory reserved from the namespace :: Given relative capacities of "Persistent
Memory" to "System RAM" the allocation defaults to reserving space out of the namespace directly
("--map=dev"). The overhead is 64-bytes per 4K (16GB per 1TB) on x86.
Thanks
Zhijian
> + placed on regular memory (memmap_on_memory=0). This attribute
> + must be set before the device is handed over to the 'kmem'
On Thu, 2023-12-07 at 08:29 +0000, Zhijian Li (Fujitsu) wrote: > Hi Vishal, > > > On 07/12/2023 12:36, Vishal Verma wrote: > > + > > +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 > > s/memmap_on+memory=1/memmap_on_memory=1 Thanks, will fix. > > > I have a question here > > What relationship about memmap_on_memory and 'ndctl-create-namespace > -M' option which > specifies where is the vmemmap backed memory. > I'm confused that memmap_on_memory=1 and '-M dev' are the same for > nvdimm devdax mode ? > The main difference is that memory that comes from non-nvdimm sources, such as hmem, or cxl, doesn't have a chance to set up the altmaps as pmem can with '-M dev'. For these, memmap_on_memory does this as part of the memory hotplug.
On 08/12/2023 03:25, Verma, Vishal L wrote: > On Thu, 2023-12-07 at 08:29 +0000, Zhijian Li (Fujitsu) wrote: >> Hi Vishal, >> >> >> On 07/12/2023 12:36, Vishal Verma wrote: >>> + >>> +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 >> >> s/memmap_on+memory=1/memmap_on_memory=1 > > Thanks, will fix. >> >> >> I have a question here >> >> What relationship about memmap_on_memory and 'ndctl-create-namespace >> -M' option which >> specifies where is the vmemmap backed memory. >> I'm confused that memmap_on_memory=1 and '-M dev' are the same for >> nvdimm devdax mode ? >> > The main difference is that memory that comes from non-nvdimm sources, > such as hmem, or cxl, doesn't have a chance to set up the altmaps as > pmem can with '-M dev'. For these, memmap_on_memory does this as part > of the memory hotplug. Thanks for your explanation. (I wrongly thought nvdimm.kmem was also controlled by '-M dev' before) feel free add: Tested-by: Li Zhijian <lizhijian@fujitsu.com>
On Fri, 2023-12-08 at 09:20 +0000, Zhijian Li (Fujitsu) wrote: > > > On 08/12/2023 03:25, Verma, Vishal L wrote: > > On Thu, 2023-12-07 at 08:29 +0000, Zhijian Li (Fujitsu) wrote: > > > Hi Vishal, > > > > > > > > > On 07/12/2023 12:36, Vishal Verma wrote: > > > > + > > > > +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 > > > > > > s/memmap_on+memory=1/memmap_on_memory=1 > > > > Thanks, will fix. > > > > > > > > > I have a question here > > > > > > What relationship about memmap_on_memory and 'ndctl-create-namespace > > > -M' option which > > > specifies where is the vmemmap backed memory. > > > I'm confused that memmap_on_memory=1 and '-M dev' are the same for > > > nvdimm devdax mode ? > > > > > The main difference is that memory that comes from non-nvdimm sources, > > such as hmem, or cxl, doesn't have a chance to set up the altmaps as > > pmem can with '-M dev'. For these, memmap_on_memory does this as part > > of the memory hotplug. > > Thanks for your explanation. > (I wrongly thought nvdimm.kmem was also controlled by '-M dev' before) > > feel free add: > Tested-by: Li Zhijian <lizhijian@fujitsu.com> Thank you Zhijian!
© 2016 - 2025 Red Hat, Inc.