For device specific memory space, when we move these area of pfn to
memory zone, we will set the page reserved flag at that time, some of
these reserved for device mmio, and some of these are not, such as
NVDIMM pmem.
Now, we map these dev_dax or fs_dax pages to kvm for DIMM/NVDIMM
backend, since these pages are reserved. the check of
kvm_is_reserved_pfn() misconceives those pages as MMIO. Therefor, we
introduce 2 page map types, MEMORY_DEVICE_FS_DAX/MEMORY_DEVICE_DEV_DAX,
to indentify these pages are from NVDIMM pmem. and let kvm treat these
as normal pages.
Without this patch, Many operations will be missed due to this
mistreatment to pmem pages. For example, a page may not have chance to
be unpinned for KVM guest(in kvm_release_pfn_clean); not able to be
marked as dirty/accessed(in kvm_set_pfn_dirty/accessed) etc.
V1:
https://lkml.org/lkml/2018/7/4/91
V2:
https://lkml.org/lkml/2018/7/10/135
V3:
https://lkml.org/lkml/2018/8/9/17
V4:
[PATCH V3 1/4] Added "Reviewed-by: David / Acked-by: Pankaj"
[PATCH V3 2/4] Added "Reviewed-by: Jan"
[PATCH V3 3/4] Added "Acked-by: Jan"
[PATCH V3 4/4] Fix several typos
Zhang Yi (4):
kvm: remove redundant reserved page check
mm: introduce memory type MEMORY_DEVICE_DEV_DAX
mm: add a function to differentiate the pages is from DAX device
memory
kvm: add a check if pfn is from NVDIMM pmem.
drivers/dax/pmem.c | 1 +
include/linux/memremap.h | 8 ++++++++
include/linux/mm.h | 12 ++++++++++++
virt/kvm/kvm_main.c | 16 ++++++++--------
4 files changed, 29 insertions(+), 8 deletions(-)
--
2.7.4
PageReserved() is already checked inside kvm_is_reserved_pfn(),
remove it from kvm_set_pfn_dirty().
Signed-off-by: Zhang Yi <[email protected]>
Signed-off-by: Zhang Yu <[email protected]>
Reviewed-by: David Hildenbrand <[email protected]>
Acked-by: Pankaj Gupta <[email protected]>
---
virt/kvm/kvm_main.c | 8 ++------
1 file changed, 2 insertions(+), 6 deletions(-)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 8b47507f..c44c406 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1690,12 +1690,8 @@ EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);
void kvm_set_pfn_dirty(kvm_pfn_t pfn)
{
- if (!kvm_is_reserved_pfn(pfn)) {
- struct page *page = pfn_to_page(pfn);
-
- if (!PageReserved(page))
- SetPageDirty(page);
- }
+ if (!kvm_is_reserved_pfn(pfn))
+ SetPageDirty(pfn_to_page(pfn));
}
EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
--
2.7.4
DAX driver hotplug the device memory and move it to memory zone, these
pages will be marked reserved flag, however, some other kernel componet
will misconceive these pages are reserved mmio (ex: we map these dev_dax
or fs_dax pages to kvm for DIMM/NVDIMM backend). Together with the type
MEMORY_DEVICE_FS_DAX, we can use is_dax_page() to differentiate the pages
is DAX device memory or not.
Signed-off-by: Zhang Yi <[email protected]>
Signed-off-by: Zhang Yu <[email protected]>
Acked-by: Jan Kara <[email protected]>
---
include/linux/mm.h | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 68a5121..de5cbc3 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -889,6 +889,13 @@ static inline bool is_device_public_page(const struct page *page)
page->pgmap->type == MEMORY_DEVICE_PUBLIC;
}
+static inline bool is_dax_page(const struct page *page)
+{
+ return is_zone_device_page(page) &&
+ (page->pgmap->type == MEMORY_DEVICE_FS_DAX ||
+ page->pgmap->type == MEMORY_DEVICE_DEV_DAX);
+}
+
#else /* CONFIG_DEV_PAGEMAP_OPS */
static inline void dev_pagemap_get_ops(void)
{
@@ -912,6 +919,11 @@ static inline bool is_device_public_page(const struct page *page)
{
return false;
}
+
+static inline bool is_dax_page(const struct page *page)
+{
+ return false;
+}
#endif /* CONFIG_DEV_PAGEMAP_OPS */
static inline void get_page(struct page *page)
--
2.7.4
For device specific memory space, when we move these area of pfn to
memory zone, we will set the page reserved flag at that time, some of
these reserved for device mmio, and some of these are not, such as
NVDIMM pmem.
Now, we map these dev_dax or fs_dax pages to kvm for DIMM/NVDIMM
backend, since these pages are reserved, the check of
kvm_is_reserved_pfn() misconceives those pages as MMIO. Therefor, we
introduce 2 page map types, MEMORY_DEVICE_FS_DAX/MEMORY_DEVICE_DEV_DAX,
to identify these pages are from NVDIMM pmem and let kvm treat these
as normal pages.
Without this patch, many operations will be missed due to this
mistreatment to pmem pages, for example, a page may not have chance to
be unpinned for KVM guest(in kvm_release_pfn_clean), not able to be
marked as dirty/accessed(in kvm_set_pfn_dirty/accessed) etc.
Signed-off-by: Zhang Yi <[email protected]>
---
virt/kvm/kvm_main.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index c44c406..969b6ca 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -147,8 +147,12 @@ __weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
{
- if (pfn_valid(pfn))
- return PageReserved(pfn_to_page(pfn));
+ struct page *page;
+
+ if (pfn_valid(pfn)) {
+ page = pfn_to_page(pfn);
+ return PageReserved(page) && !is_dax_page(page);
+ }
return true;
}
--
2.7.4
Currently, NVDIMM pages will be marked 'PageReserved'. However, unlike
other reserved PFNs, pages on NVDIMM shall still behave like normal ones
in many cases, i.e. when used as backend memory of KVM guest. This patch
introduces a new memory type, MEMORY_DEVICE_DEV_DAX. And set this flag
while dax driver hotplug the device memory.
Signed-off-by: Zhang Yi <[email protected]>
Signed-off-by: Zhang Yu <[email protected]>
Reviewed-by: Jan Kara <[email protected]>
---
drivers/dax/pmem.c | 1 +
include/linux/memremap.h | 8 ++++++++
2 files changed, 9 insertions(+)
diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index fd49b24..fb3f363 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -111,6 +111,7 @@ static int dax_pmem_probe(struct device *dev)
return rc;
dax_pmem->pgmap.ref = &dax_pmem->ref;
+ dax_pmem->pgmap.type = MEMORY_DEVICE_DEV_DAX;
addr = devm_memremap_pages(dev, &dax_pmem->pgmap);
if (IS_ERR(addr))
return PTR_ERR(addr);
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index f91f9e7..cd07ca8 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -53,11 +53,19 @@ struct vmem_altmap {
* wakeup event whenever a page is unpinned and becomes idle. This
* wakeup is used to coordinate physical address space management (ex:
* fs truncate/hole punch) vs pinned pages (ex: device dma).
+ *
+ * MEMORY_DEVICE_DEV_DAX:
+ * Device memory that support raw access to persistent memory. Without need
+ * of an intervening filesystem, it could be directed mapped via an mmap
+ * capable character device. Together with the type MEMORY_DEVICE_FS_DAX,
+ * we could distinguish the persistent memory pages from normal ZONE_DEVICE
+ * pages.
*/
enum memory_type {
MEMORY_DEVICE_PRIVATE = 1,
MEMORY_DEVICE_PUBLIC,
MEMORY_DEVICE_FS_DAX,
+ MEMORY_DEVICE_DEV_DAX,
};
/*
--
2.7.4
>
> For device specific memory space, when we move these area of pfn to
> memory zone, we will set the page reserved flag at that time, some of
> these reserved for device mmio, and some of these are not, such as
> NVDIMM pmem.
>
> Now, we map these dev_dax or fs_dax pages to kvm for DIMM/NVDIMM
> backend, since these pages are reserved, the check of
> kvm_is_reserved_pfn() misconceives those pages as MMIO. Therefor, we
> introduce 2 page map types, MEMORY_DEVICE_FS_DAX/MEMORY_DEVICE_DEV_DAX,
> to identify these pages are from NVDIMM pmem and let kvm treat these
> as normal pages.
>
> Without this patch, many operations will be missed due to this
> mistreatment to pmem pages, for example, a page may not have chance to
> be unpinned for KVM guest(in kvm_release_pfn_clean), not able to be
> marked as dirty/accessed(in kvm_set_pfn_dirty/accessed) etc.
>
> Signed-off-by: Zhang Yi <[email protected]>
> ---
> virt/kvm/kvm_main.c | 8 ++++++--
> 1 file changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index c44c406..969b6ca 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -147,8 +147,12 @@ __weak void
> kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
>
> bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
> {
> - if (pfn_valid(pfn))
> - return PageReserved(pfn_to_page(pfn));
> + struct page *page;
> +
> + if (pfn_valid(pfn)) {
> + page = pfn_to_page(pfn);
> + return PageReserved(page) && !is_dax_page(page);
> + }
>
> return true;
> }
Acked-by: Pankaj Gupta <[email protected]>
> --
> 2.7.4
>
>
On 2018-08-29 at 06:15:48 -0400, Pankaj Gupta wrote:
>
> >
> > For device specific memory space, when we move these area of pfn to
> > memory zone, we will set the page reserved flag at that time, some of
> > these reserved for device mmio, and some of these are not, such as
> > NVDIMM pmem.
> >
> > Now, we map these dev_dax or fs_dax pages to kvm for DIMM/NVDIMM
> > backend, since these pages are reserved, the check of
> > kvm_is_reserved_pfn() misconceives those pages as MMIO. Therefor, we
> > introduce 2 page map types, MEMORY_DEVICE_FS_DAX/MEMORY_DEVICE_DEV_DAX,
> > to identify these pages are from NVDIMM pmem and let kvm treat these
> > as normal pages.
> >
> > Without this patch, many operations will be missed due to this
> > mistreatment to pmem pages, for example, a page may not have chance to
> > be unpinned for KVM guest(in kvm_release_pfn_clean), not able to be
> > marked as dirty/accessed(in kvm_set_pfn_dirty/accessed) etc.
> >
> > Signed-off-by: Zhang Yi <[email protected]>
> > ---
> > virt/kvm/kvm_main.c | 8 ++++++--
> > 1 file changed, 6 insertions(+), 2 deletions(-)
> >
> > diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> > index c44c406..969b6ca 100644
> > --- a/virt/kvm/kvm_main.c
> > +++ b/virt/kvm/kvm_main.c
> > @@ -147,8 +147,12 @@ __weak void
> > kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
> >
> > bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
> > {
> > - if (pfn_valid(pfn))
> > - return PageReserved(pfn_to_page(pfn));
> > + struct page *page;
> > +
> > + if (pfn_valid(pfn)) {
> > + page = pfn_to_page(pfn);
> > + return PageReserved(page) && !is_dax_page(page);
> > + }
> >
> > return true;
> > }
>
> Acked-by: Pankaj Gupta <[email protected]>
Thanks for your kindly review, Pankaj, as all the patch [1,2,3,4]/4 got
the reviewed[acked]-by, can we Queue this by now?
>
> > --
> > 2.7.4
> >
> >
On 08/22/2018 03:58 AM, Zhang Yi wrote:
> bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
> {
> - if (pfn_valid(pfn))
> - return PageReserved(pfn_to_page(pfn));
> + struct page *page;
> +
> + if (pfn_valid(pfn)) {
> + page = pfn_to_page(pfn);
> + return PageReserved(page) && !is_dax_page(page);
> + }
This is in desperate need of commenting about what it is doing and why.
The changelog alone doesn't cut it.
On 2018-08-30 at 12:07:11 -0700, Dave Hansen wrote:
> On 08/22/2018 03:58 AM, Zhang Yi wrote:
> > bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
> > {
> > - if (pfn_valid(pfn))
> > - return PageReserved(pfn_to_page(pfn));
> > + struct page *page;
> > +
> > + if (pfn_valid(pfn)) {
> > + page = pfn_to_page(pfn);
> > + return PageReserved(page) && !is_dax_page(page);
> > + }
>
> This is in desperate need of commenting about what it is doing and why.
>
> The changelog alone doesn't cut it.
Thanks, Dave, Will add some comments
>
> Currently, NVDIMM pages will be marked 'PageReserved'. However, unlike
> other reserved PFNs, pages on NVDIMM shall still behave like normal ones
> in many cases, i.e. when used as backend memory of KVM guest. This patch
> introduces a new memory type, MEMORY_DEVICE_DEV_DAX. And set this flag
> while dax driver hotplug the device memory.
>
> Signed-off-by: Zhang Yi <[email protected]>
> Signed-off-by: Zhang Yu <[email protected]>
> Reviewed-by: Jan Kara suse.cz>
> ---
> drivers/dax/pmem.c | 1 +
> include/linux/memremap.h | 8 ++++++++
> 2 files changed, 9 insertions(+)
>
> diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
> index fd49b24..fb3f363 100644
> --- a/drivers/dax/pmem.c
> +++ b/drivers/dax/pmem.c
> @@ -111,6 +111,7 @@ static int dax_pmem_probe(struct device *dev)
> return rc;
>
> dax_pmem->pgmap.ref = &dax_pmem->ref;
> + dax_pmem->pgmap.type = MEMORY_DEVICE_DEV_DAX;
> addr = devm_memremap_pages(dev, &dax_pmem->pgmap);
> if (IS_ERR(addr))
> return PTR_ERR(addr);
> diff --git a/include/linux/memremap.h b/include/linux/memremap.h
> index f91f9e7..cd07ca8 100644
> --- a/include/linux/memremap.h
> +++ b/include/linux/memremap.h
> @@ -53,11 +53,19 @@ struct vmem_altmap {
> * wakeup event whenever a page is unpinned and becomes idle. This
> * wakeup is used to coordinate physical address space management (ex:
> * fs truncate/hole punch) vs pinned pages (ex: device dma).
> + *
> + * MEMORY_DEVICE_DEV_DAX:
> + * Device memory that support raw access to persistent memory. Without need
> + * of an intervening filesystem, it could be directed mapped via an mmap
> + * capable character device. Together with the type MEMORY_DEVICE_FS_DAX,
> + * we could distinguish the persistent memory pages from normal ZONE_DEVICE
> + * pages.
> */
> enum memory_type {
> MEMORY_DEVICE_PRIVATE = 1,
> MEMORY_DEVICE_PUBLIC,
> MEMORY_DEVICE_FS_DAX,
> + MEMORY_DEVICE_DEV_DAX,
> };
>
> /*
> --
Reviewed-by: Pankaj Gupta <[email protected]>
> 2.7.4
>
>
>
> DAX driver hotplug the device memory and move it to memory zone, these
> pages will be marked reserved flag, however, some other kernel componet
> will misconceive these pages are reserved mmio (ex: we map these dev_dax
> or fs_dax pages to kvm for DIMM/NVDIMM backend). Together with the type
> MEMORY_DEVICE_FS_DAX, we can use is_dax_page() to differentiate the pages
> is DAX device memory or not.
>
> Signed-off-by: Zhang Yi <[email protected]>
> Signed-off-by: Zhang Yu <[email protected]>
> Acked-by: Jan Kara <[email protected]>
> ---
> include/linux/mm.h | 12 ++++++++++++
> 1 file changed, 12 insertions(+)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 68a5121..de5cbc3 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -889,6 +889,13 @@ static inline bool is_device_public_page(const struct
> page *page)
> page->pgmap->type == MEMORY_DEVICE_PUBLIC;
> }
>
> +static inline bool is_dax_page(const struct page *page)
> +{
> + return is_zone_device_page(page) &&
> + (page->pgmap->type == MEMORY_DEVICE_FS_DAX ||
> + page->pgmap->type == MEMORY_DEVICE_DEV_DAX);
> +}
> +
> #else /* CONFIG_DEV_PAGEMAP_OPS */
> static inline void dev_pagemap_get_ops(void)
> {
> @@ -912,6 +919,11 @@ static inline bool is_device_public_page(const struct
> page *page)
> {
> return false;
> }
> +
> +static inline bool is_dax_page(const struct page *page)
> +{
> + return false;
> +}
> #endif /* CONFIG_DEV_PAGEMAP_OPS */
>
> static inline void get_page(struct page *page)
> --
Reviewed-by: Pankaj Gupta <[email protected]>
> 2.7.4
>
>