diff mbox series

[v3,3/5] libnvdimm: add nd_region buffered dax_dev flag

Message ID 20190109135024.14093-4-pagupta@redhat.com (mailing list archive)
State Not Applicable
Headers show
Series kvm "virtio pmem" device | expand

Commit Message

Pankaj Gupta Jan. 9, 2019, 1:50 p.m. UTC
This patch adds 'DAXDEV_BUFFERED' flag which is set
for virtio pmem corresponding nd_region. This later
is used to disable MAP_SYNC functionality for ext4
& xfs filesystem.

Signed-off-by: Pankaj Gupta <pagupta@redhat.com>
---
 drivers/dax/super.c          | 17 +++++++++++++++++
 drivers/nvdimm/pmem.c        |  3 +++
 drivers/nvdimm/region_devs.c |  7 +++++++
 drivers/virtio/pmem.c        |  1 +
 include/linux/dax.h          |  9 +++++++++
 include/linux/libnvdimm.h    |  6 ++++++
 6 files changed, 43 insertions(+)

Comments

Dan Williams Jan. 9, 2019, 5:02 p.m. UTC | #1
On Wed, Jan 9, 2019 at 5:53 AM Pankaj Gupta <pagupta@redhat.com> wrote:
>
> This patch adds 'DAXDEV_BUFFERED' flag which is set
> for virtio pmem corresponding nd_region. This later
> is used to disable MAP_SYNC functionality for ext4
> & xfs filesystem.
>
> Signed-off-by: Pankaj Gupta <pagupta@redhat.com>
> ---
>  drivers/dax/super.c          | 17 +++++++++++++++++
>  drivers/nvdimm/pmem.c        |  3 +++
>  drivers/nvdimm/region_devs.c |  7 +++++++
>  drivers/virtio/pmem.c        |  1 +
>  include/linux/dax.h          |  9 +++++++++
>  include/linux/libnvdimm.h    |  6 ++++++
>  6 files changed, 43 insertions(+)
>
> diff --git a/drivers/dax/super.c b/drivers/dax/super.c
> index 6e928f3..9128740 100644
> --- a/drivers/dax/super.c
> +++ b/drivers/dax/super.c
> @@ -167,6 +167,8 @@ enum dax_device_flags {
>         DAXDEV_ALIVE,
>         /* gate whether dax_flush() calls the low level flush routine */
>         DAXDEV_WRITE_CACHE,
> +       /* flag to disable MAP_SYNC for virtio based host page cache flush */
> +       DAXDEV_BUFFERED,
>  };
>
>  /**
> @@ -335,6 +337,21 @@ bool dax_write_cache_enabled(struct dax_device *dax_dev)
>  }
>  EXPORT_SYMBOL_GPL(dax_write_cache_enabled);
>
> +void virtio_pmem_host_cache(struct dax_device *dax_dev, bool wc)
> +{
> +       if (wc)
> +               set_bit(DAXDEV_BUFFERED, &dax_dev->flags);
> +       else
> +               clear_bit(DAXDEV_BUFFERED, &dax_dev->flags);
> +}
> +EXPORT_SYMBOL_GPL(virtio_pmem_host_cache);

The "write_cache" property was structured this way because it can
conceivably change at runtime. The MAP_SYNC capability should be
static and never changed after init.

> +bool virtio_pmem_host_cache_enabled(struct dax_device *dax_dev)
> +{
> +       return test_bit(DAXDEV_BUFFERED, &dax_dev->flags);
> +}
> +EXPORT_SYMBOL_GPL(virtio_pmem_host_cache_enabled);

Echoing Darrick and Jan this is should be a generic property of a
dax_device and not specific to virtio. I don't like the "buffered"
designation as that's not accurate. There may be hardware reasons why
a dax_device is not synchronous, like a requirement to flush a
write-pending queue or otherwise notify the device of new writes.

I would just have a dax_synchronous() helper and a DAXDEV_SYNC flag. I
would also modify alloc_dax() to take a flags argument so that the
capability can be instantiated when the dax_device is allocated.
Pankaj Gupta Jan. 9, 2019, 6:21 p.m. UTC | #2
> >
> > This patch adds 'DAXDEV_BUFFERED' flag which is set
> > for virtio pmem corresponding nd_region. This later
> > is used to disable MAP_SYNC functionality for ext4
> > & xfs filesystem.
> >
> > Signed-off-by: Pankaj Gupta <pagupta@redhat.com>
> > ---
> >  drivers/dax/super.c          | 17 +++++++++++++++++
> >  drivers/nvdimm/pmem.c        |  3 +++
> >  drivers/nvdimm/region_devs.c |  7 +++++++
> >  drivers/virtio/pmem.c        |  1 +
> >  include/linux/dax.h          |  9 +++++++++
> >  include/linux/libnvdimm.h    |  6 ++++++
> >  6 files changed, 43 insertions(+)
> >
> > diff --git a/drivers/dax/super.c b/drivers/dax/super.c
> > index 6e928f3..9128740 100644
> > --- a/drivers/dax/super.c
> > +++ b/drivers/dax/super.c
> > @@ -167,6 +167,8 @@ enum dax_device_flags {
> >         DAXDEV_ALIVE,
> >         /* gate whether dax_flush() calls the low level flush routine */
> >         DAXDEV_WRITE_CACHE,
> > +       /* flag to disable MAP_SYNC for virtio based host page cache flush
> > */
> > +       DAXDEV_BUFFERED,
> >  };
> >
> >  /**
> > @@ -335,6 +337,21 @@ bool dax_write_cache_enabled(struct dax_device
> > *dax_dev)
> >  }
> >  EXPORT_SYMBOL_GPL(dax_write_cache_enabled);
> >
> > +void virtio_pmem_host_cache(struct dax_device *dax_dev, bool wc)
> > +{
> > +       if (wc)
> > +               set_bit(DAXDEV_BUFFERED, &dax_dev->flags);
> > +       else
> > +               clear_bit(DAXDEV_BUFFERED, &dax_dev->flags);
> > +}
> > +EXPORT_SYMBOL_GPL(virtio_pmem_host_cache);
> 
> The "write_cache" property was structured this way because it can
> conceivably change at runtime. The MAP_SYNC capability should be
> static and never changed after init.

o.k. Will change.

> 
> > +bool virtio_pmem_host_cache_enabled(struct dax_device *dax_dev)
> > +{
> > +       return test_bit(DAXDEV_BUFFERED, &dax_dev->flags);
> > +}
> > +EXPORT_SYMBOL_GPL(virtio_pmem_host_cache_enabled);
> 
> Echoing Darrick and Jan this is should be a generic property of a
> dax_device and not specific to virtio. I don't like the "buffered"
> designation as that's not accurate. There may be hardware reasons why
> a dax_device is not synchronous, like a requirement to flush a
> write-pending queue or otherwise notify the device of new writes.

Agree.

> 
> I would just have a dax_synchronous() helper and a DAXDEV_SYNC flag. I
> would also modify alloc_dax() to take a flags argument so that the
> capability can be instantiated when the dax_device is allocated.

o.k. Will make the change.

Thanks,
Pankaj
>
diff mbox series

Patch

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 6e928f3..9128740 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -167,6 +167,8 @@  enum dax_device_flags {
 	DAXDEV_ALIVE,
 	/* gate whether dax_flush() calls the low level flush routine */
 	DAXDEV_WRITE_CACHE,
+	/* flag to disable MAP_SYNC for virtio based host page cache flush */
+	DAXDEV_BUFFERED,
 };
 
 /**
@@ -335,6 +337,21 @@  bool dax_write_cache_enabled(struct dax_device *dax_dev)
 }
 EXPORT_SYMBOL_GPL(dax_write_cache_enabled);
 
+void virtio_pmem_host_cache(struct dax_device *dax_dev, bool wc)
+{
+	if (wc)
+		set_bit(DAXDEV_BUFFERED, &dax_dev->flags);
+	else
+		clear_bit(DAXDEV_BUFFERED, &dax_dev->flags);
+}
+EXPORT_SYMBOL_GPL(virtio_pmem_host_cache);
+
+bool virtio_pmem_host_cache_enabled(struct dax_device *dax_dev)
+{
+	return test_bit(DAXDEV_BUFFERED, &dax_dev->flags);
+}
+EXPORT_SYMBOL_GPL(virtio_pmem_host_cache_enabled);
+
 bool dax_alive(struct dax_device *dax_dev)
 {
 	lockdep_assert_held(&dax_srcu);
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index fe1217b..8d190a3 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -472,6 +472,9 @@  static int pmem_attach_disk(struct device *dev,
 		return -ENOMEM;
 	}
 	dax_write_cache(dax_dev, nvdimm_has_cache(nd_region));
+
+	/* Set buffered bit in 'dax_dev' for virtio pmem */
+	virtio_pmem_host_cache(dax_dev, nvdimm_is_buffered(nd_region));
 	pmem->dax_dev = dax_dev;
 
 	gendev = disk_to_dev(disk);
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index f8218b4..1f8b2be 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -1264,6 +1264,13 @@  int nd_region_conflict(struct nd_region *nd_region, resource_size_t start,
 	return device_for_each_child(&nvdimm_bus->dev, &ctx, region_conflict);
 }
 
+int nvdimm_is_buffered(struct nd_region *nd_region)
+{
+	return is_nd_pmem(&nd_region->dev) &&
+		test_bit(ND_REGION_BUFFERED, &nd_region->flags);
+}
+EXPORT_SYMBOL_GPL(nvdimm_is_buffered);
+
 void __exit nd_region_devs_exit(void)
 {
 	ida_destroy(&region_ida);
diff --git a/drivers/virtio/pmem.c b/drivers/virtio/pmem.c
index 51f5349..901767b 100644
--- a/drivers/virtio/pmem.c
+++ b/drivers/virtio/pmem.c
@@ -81,6 +81,7 @@  static int virtio_pmem_probe(struct virtio_device *vdev)
 	ndr_desc.numa_node = nid;
 	ndr_desc.flush = virtio_pmem_flush;
 	set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
+	set_bit(ND_REGION_BUFFERED, &ndr_desc.flags);
 	nd_region = nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc);
 	nd_region->provider_data =  dev_to_virtio
 					(nd_region->dev.parent->parent);
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 0dd316a..d16e03e 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -37,6 +37,8 @@  void put_dax(struct dax_device *dax_dev);
 void kill_dax(struct dax_device *dax_dev);
 void dax_write_cache(struct dax_device *dax_dev, bool wc);
 bool dax_write_cache_enabled(struct dax_device *dax_dev);
+void virtio_pmem_host_cache(struct dax_device *dax_dev, bool wc);
+bool virtio_pmem_host_cache_enabled(struct dax_device *dax_dev);
 #else
 static inline struct dax_device *dax_get_by_host(const char *host)
 {
@@ -64,6 +66,13 @@  static inline bool dax_write_cache_enabled(struct dax_device *dax_dev)
 {
 	return false;
 }
+static inline void virtio_pmem_host_cache(struct dax_device *dax_dev, bool wc)
+{
+}
+static inline bool virtio_pmem_host_cache_enabled(struct dax_device *dax_dev)
+{
+	return false;
+}
 #endif
 
 struct writeback_control;
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index ca8bc07..94616f1 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -64,6 +64,11 @@  enum {
 	 */
 	ND_REGION_PERSIST_MEMCTRL = 2,
 
+	/* provides virtio based asynchronous flush mechanism for buffered
+	 * host page cache.
+	 */
+	ND_REGION_BUFFERED = 3,
+
 	/* mark newly adjusted resources as requiring a label update */
 	DPA_RESOURCE_ADJUSTED = 1 << 0,
 };
@@ -265,6 +270,7 @@  int generic_nvdimm_flush(struct nd_region *nd_region);
 int nvdimm_has_flush(struct nd_region *nd_region);
 int nvdimm_has_cache(struct nd_region *nd_region);
 int nvdimm_in_overwrite(struct nvdimm *nvdimm);
+int nvdimm_is_buffered(struct nd_region *nd_region);
 
 static inline int nvdimm_ctl(struct nvdimm *nvdimm, unsigned int cmd, void *buf,
 		unsigned int buf_len, int *cmd_rc)