[v5,2/2] dax/kmem: allow kmem to add memory with memmap_on_memory
Commit Message
Large amounts of memory managed by the kmem driver may come in via CXL,
and it is often desirable to have the memmap for this memory on the new
memory itself.
Enroll kmem-managed memory for memmap_on_memory semantics if the dax
region originates via CXL. For non-CXL dax regions, retain the existing
default behavior of hot adding without memmap_on_memory semantics.
Add a sysfs override under the dax device to control this behavior and
override either default.
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
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.h | 1 +
drivers/dax/dax-private.h | 1 +
drivers/dax/bus.c | 38 ++++++++++++++++++++++++++++++++++++++
drivers/dax/cxl.c | 1 +
drivers/dax/hmem/hmem.c | 1 +
drivers/dax/kmem.c | 8 +++++++-
drivers/dax/pmem.c | 1 +
7 files changed, 50 insertions(+), 1 deletion(-)
Comments
Vishal Verma wrote:
> Large amounts of memory managed by the kmem driver may come in via CXL,
> and it is often desirable to have the memmap for this memory on the new
> memory itself.
>
> Enroll kmem-managed memory for memmap_on_memory semantics if the dax
> region originates via CXL. For non-CXL dax regions, retain the existing
> default behavior of hot adding without memmap_on_memory semantics.
>
> Add a sysfs override under the dax device to control this behavior and
> override either default.
>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: Michal Hocko <mhocko@suse.com>
> Cc: Oscar Salvador <osalvador@suse.de>
> 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.h | 1 +
> drivers/dax/dax-private.h | 1 +
> drivers/dax/bus.c | 38 ++++++++++++++++++++++++++++++++++++++
> drivers/dax/cxl.c | 1 +
> drivers/dax/hmem/hmem.c | 1 +
> drivers/dax/kmem.c | 8 +++++++-
> drivers/dax/pmem.c | 1 +
> 7 files changed, 50 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h
> index 1ccd23360124..cbbf64443098 100644
> --- a/drivers/dax/bus.h
> +++ b/drivers/dax/bus.h
> @@ -23,6 +23,7 @@ struct dev_dax_data {
> struct dev_pagemap *pgmap;
> resource_size_t size;
> int id;
> + bool memmap_on_memory;
> };
>
> struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data);
> diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
> index 27cf2daaaa79..446617b73aea 100644
> --- a/drivers/dax/dax-private.h
> +++ b/drivers/dax/dax-private.h
> @@ -70,6 +70,7 @@ struct dev_dax {
> struct ida ida;
> struct device dev;
> struct dev_pagemap *pgmap;
> + bool memmap_on_memory;
> int nr_range;
> struct dev_dax_range {
> unsigned long pgoff;
> diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
> index 0ee96e6fc426..43be95a231c9 100644
> --- a/drivers/dax/bus.c
> +++ b/drivers/dax/bus.c
> @@ -367,6 +367,7 @@ static ssize_t create_store(struct device *dev, struct device_attribute *attr,
> .dax_region = dax_region,
> .size = 0,
> .id = -1,
> + .memmap_on_memory = false,
> };
> struct dev_dax *dev_dax = devm_create_dev_dax(&data);
>
> @@ -1269,6 +1270,40 @@ 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;
Perhaps:
if (dev_dax->memmap_on_memory == val)
return len;
...and skip the check below when it is going to be a nop
> +
> + device_lock(dax_region->dev);
> + if (!dax_region->dev->driver) {
Is the polarity backwards here? I.e. if the device is already attached to
the kmem driver it is too late to modify memmap_on_memory policy.
> + device_unlock(dax_region->dev);
> + return -ENXIO;
I would expect -EBUSY since disabling the device allows the property to be
set and -ENXIO implies a more permanent error.
> + }
> +
> + dev_dax->memmap_on_memory = val;
> +
> + device_unlock(dax_region->dev);
> + return len;
> +}
> +static DEVICE_ATTR_RW(memmap_on_memory);
This new attribute needs a new Documentation/ABI/ entry... in fact all of
these attributes need Documentation/ entries. I can help with that base
document to get things started.
Perhaps split this sysfs ABI into its own patch and, depending on how fast
we can pull the Documentation together, start with the
region-driver-conveyed approach in the meantime.
On Thu, 2023-10-05 at 14:16 -0700, Dan Williams wrote:
> Vishal Verma wrote:
> >
<..>
> > +
> > + rc = kstrtobool(buf, &val);
> > + if (rc)
> > + return rc;
>
> Perhaps:
>
> if (dev_dax->memmap_on_memory == val)
> return len;
>
> ...and skip the check below when it is going to be a nop
>
> > +
> > + device_lock(dax_region->dev);
> > + if (!dax_region->dev->driver) {
>
> Is the polarity backwards here? I.e. if the device is already attached to
> the kmem driver it is too late to modify memmap_on_memory policy.
Hm this sounded logical until I tried it. After a reconfigure-device to
devdax (i.e. detach kmem), I get the -EBUSY if I invert this check.
>
> > + device_unlock(dax_region->dev);
> > + return -ENXIO;
>
> I would expect -EBUSY since disabling the device allows the property to be
> set and -ENXIO implies a more permanent error.
>
> > + }
> > +
> > + dev_dax->memmap_on_memory = val;
> > +
> > + device_unlock(dax_region->dev);
> > + return len;
> > +}
> > +static DEVICE_ATTR_RW(memmap_on_memory);
>
> This new attribute needs a new Documentation/ABI/ entry... in fact all of
> these attributes need Documentation/ entries. I can help with that base
> document to get things started.
>
> Perhaps split this sysfs ABI into its own patch and, depending on how fast
> we can pull the Documentation together, start with the
> region-driver-conveyed approach in the meantime.
Yep I'll split this out and I can do a separate series to add the ABI
docs for /sys/bus/dax, and include this new ABI in that as well.
Agreed with all other comments.
"Verma, Vishal L" <vishal.l.verma@intel.com> writes:
> On Thu, 2023-10-05 at 14:16 -0700, Dan Williams wrote:
>> Vishal Verma wrote:
>> >
> <..>
>
>> > +
>> > + rc = kstrtobool(buf, &val);
>> > + if (rc)
>> > + return rc;
>>
>> Perhaps:
>>
>> if (dev_dax->memmap_on_memory == val)
>> return len;
>>
>> ...and skip the check below when it is going to be a nop
>>
>> > +
>> > + device_lock(dax_region->dev);
>> > + if (!dax_region->dev->driver) {
>>
>> Is the polarity backwards here? I.e. if the device is already attached to
>> the kmem driver it is too late to modify memmap_on_memory policy.
>
> Hm this sounded logical until I tried it. After a reconfigure-device to
> devdax (i.e. detach kmem), I get the -EBUSY if I invert this check.
Can you try to unbind the device via sysfs by hand and retry?
--
Best Regards,
Huang, Ying
>>
>> > + device_unlock(dax_region->dev);
>> > + return -ENXIO;
>>
[snip]
On Tue, 2023-10-17 at 13:18 +0800, Huang, Ying wrote:
> "Verma, Vishal L" <vishal.l.verma@intel.com> writes:
>
> > On Thu, 2023-10-05 at 14:16 -0700, Dan Williams wrote:
> > > Vishal Verma wrote:
> > > >
> > <..>
> >
> > > > +
> > > > + rc = kstrtobool(buf, &val);
> > > > + if (rc)
> > > > + return rc;
> > >
> > > Perhaps:
> > >
> > > if (dev_dax->memmap_on_memory == val)
> > > return len;
> > >
> > > ...and skip the check below when it is going to be a nop
> > >
> > > > +
> > > > + device_lock(dax_region->dev);
> > > > + if (!dax_region->dev->driver) {
> > >
> > > Is the polarity backwards here? I.e. if the device is already
> > > attached to
> > > the kmem driver it is too late to modify memmap_on_memory policy.
> >
> > Hm this sounded logical until I tried it. After a reconfigure-
> > device to
> > devdax (i.e. detach kmem), I get the -EBUSY if I invert this check.
>
> Can you try to unbind the device via sysfs by hand and retry?
>
I think what is happening maybe is while kmem gets detached, the device
goes back to another dax driver (hmem in my tests). So either way, the
check for if (driver) or if (!driver) won't distinguish between kmem
vs. something else.
Maybe we just remove this check? Or add an explicit kmem check somehow?
"Verma, Vishal L" <vishal.l.verma@intel.com> writes:
> On Tue, 2023-10-17 at 13:18 +0800, Huang, Ying wrote:
>> "Verma, Vishal L" <vishal.l.verma@intel.com> writes:
>>
>> > On Thu, 2023-10-05 at 14:16 -0700, Dan Williams wrote:
>> > > Vishal Verma wrote:
>> > > >
>> > <..>
>> >
>> > > > +
>> > > > + rc = kstrtobool(buf, &val);
>> > > > + if (rc)
>> > > > + return rc;
>> > >
>> > > Perhaps:
>> > >
>> > > if (dev_dax->memmap_on_memory == val)
>> > > return len;
>> > >
>> > > ...and skip the check below when it is going to be a nop
>> > >
>> > > > +
>> > > > + device_lock(dax_region->dev);
>> > > > + if (!dax_region->dev->driver) {
>> > >
>> > > Is the polarity backwards here? I.e. if the device is already
>> > > attached to
>> > > the kmem driver it is too late to modify memmap_on_memory policy.
>> >
>> > Hm this sounded logical until I tried it. After a reconfigure-
>> > device to
>> > devdax (i.e. detach kmem), I get the -EBUSY if I invert this check.
>>
>> Can you try to unbind the device via sysfs by hand and retry?
>>
> I think what is happening maybe is while kmem gets detached, the device
> goes back to another dax driver (hmem in my tests). So either way, the
> check for if (driver) or if (!driver) won't distinguish between kmem
> vs. something else.
>
> Maybe we just remove this check? Or add an explicit kmem check somehow?
I think it's good to check kmem explicitly here.
--
Best Regards,
Huang, Ying
@@ -23,6 +23,7 @@ struct dev_dax_data {
struct dev_pagemap *pgmap;
resource_size_t size;
int id;
+ bool memmap_on_memory;
};
struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data);
@@ -70,6 +70,7 @@ struct dev_dax {
struct ida ida;
struct device dev;
struct dev_pagemap *pgmap;
+ bool memmap_on_memory;
int nr_range;
struct dev_dax_range {
unsigned long pgoff;
@@ -367,6 +367,7 @@ static ssize_t create_store(struct device *dev, struct device_attribute *attr,
.dax_region = dax_region,
.size = 0,
.id = -1,
+ .memmap_on_memory = false,
};
struct dev_dax *dev_dax = devm_create_dev_dax(&data);
@@ -1269,6 +1270,40 @@ 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;
+
+ device_lock(dax_region->dev);
+ if (!dax_region->dev->driver) {
+ device_unlock(dax_region->dev);
+ return -ENXIO;
+ }
+
+ dev_dax->memmap_on_memory = val;
+
+ device_unlock(dax_region->dev);
+ 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);
@@ -1295,6 +1330,7 @@ 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,
};
@@ -1400,6 +1436,8 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
dev_dax->align = dax_region->align;
ida_init(&dev_dax->ida);
+ dev_dax->memmap_on_memory = data->memmap_on_memory;
+
inode = dax_inode(dax_dev);
dev->devt = inode->i_rdev;
dev->bus = &dax_bus_type;
@@ -26,6 +26,7 @@ static int cxl_dax_region_probe(struct device *dev)
.dax_region = dax_region,
.id = -1,
.size = range_len(&cxlr_dax->hpa_range),
+ .memmap_on_memory = true,
};
return PTR_ERR_OR_ZERO(devm_create_dev_dax(&data));
@@ -36,6 +36,7 @@ static int dax_hmem_probe(struct platform_device *pdev)
.dax_region = dax_region,
.id = -1,
.size = region_idle ? 0 : range_len(&mri->range),
+ .memmap_on_memory = false,
};
return PTR_ERR_OR_ZERO(devm_create_dev_dax(&data));
@@ -12,6 +12,7 @@
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/memory-tiers.h>
+#include <linux/memory_hotplug.h>
#include "dax-private.h"
#include "bus.h"
@@ -56,6 +57,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
unsigned long total_len = 0;
struct dax_kmem_data *data;
int i, rc, mapped = 0;
+ mhp_t mhp_flags;
int numa_node;
/*
@@ -136,12 +138,16 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
*/
res->flags = IORESOURCE_SYSTEM_RAM;
+ mhp_flags = MHP_NID_IS_MGID;
+ if (dev_dax->memmap_on_memory)
+ mhp_flags |= MHP_MEMMAP_ON_MEMORY;
+
/*
* Ensure that future kexec'd kernels will not treat
* this as RAM automatically.
*/
rc = add_memory_driver_managed(data->mgid, range.start,
- range_len(&range), kmem_name, MHP_NID_IS_MGID);
+ range_len(&range), kmem_name, mhp_flags);
if (rc) {
dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
@@ -63,6 +63,7 @@ static struct dev_dax *__dax_pmem_probe(struct device *dev)
.id = id,
.pgmap = &pgmap,
.size = range_len(&range),
+ .memmap_on_memory = false,
};
return devm_create_dev_dax(&data);