Re: [PATCH v5 03/13] mm/shmem: Support memfile_notifier
On Tue, Apr 19, 2022 at 03:40:09PM -0700, Vishal Annapurve wrote:
> On Thu, Mar 10, 2022 at 6:10 AM Chao Peng wrote:
> >
> > From: "Kirill A. Shutemov"
> >
> > It maintains a memfile_notifier list in shmem_inode_info structure and
> > implements memfile_pfn_ops callbacks defined by memfile_notifier. It
> > then exposes them to memfile_notifier via
> > shmem_get_memfile_notifier_info.
> >
> > We use SGP_NOALLOC in shmem_get_lock_pfn since the pages should be
> > allocated by userspace for private memory. If there is no pages
> > allocated at the offset then error should be returned so KVM knows that
> > the memory is not private memory.
> >
> > Signed-off-by: Kirill A. Shutemov
> > Signed-off-by: Chao Peng
> > ---
> > include/linux/shmem_fs.h | 4 +++
> > mm/shmem.c | 76
> > 2 files changed, 80 insertions(+)
> >
> > diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
> > index 2dde843f28ef..7bb16f2d2825 100644
> > --- a/include/linux/shmem_fs.h
> > +++ b/include/linux/shmem_fs.h
> > @@ -9,6 +9,7 @@
> > #include
> > #include
> > #include
> > +#include
> >
> > /* inode in-kernel data */
> >
> > @@ -28,6 +29,9 @@ struct shmem_inode_info {
> > struct simple_xattrsxattrs; /* list of xattrs */
> > atomic_tstop_eviction; /* hold when working on
> > inode */
> > unsigned intxflags; /* shmem extended flags */
> > +#ifdef CONFIG_MEMFILE_NOTIFIER
> > + struct memfile_notifier_list memfile_notifiers;
> > +#endif
> > struct inodevfs_inode;
> > };
> >
> > diff --git a/mm/shmem.c b/mm/shmem.c
> > index 9b31a7056009..7b43e274c9a2 100644
> > --- a/mm/shmem.c
> > +++ b/mm/shmem.c
> > @@ -903,6 +903,28 @@ static struct folio *shmem_get_partial_folio(struct
> > inode *inode, pgoff_t index)
> > return page ? page_folio(page) : NULL;
> > }
> >
> > +static void notify_fallocate(struct inode *inode, pgoff_t start, pgoff_t
> > end)
> > +{
> > +#ifdef CONFIG_MEMFILE_NOTIFIER
> > + struct shmem_inode_info *info = SHMEM_I(inode);
> > +
> > + memfile_notifier_fallocate(>memfile_notifiers, start, end);
> > +#endif
> > +}
> > +
> > +static void notify_invalidate_page(struct inode *inode, struct folio
> > *folio,
> > + pgoff_t start, pgoff_t end)
> > +{
> > +#ifdef CONFIG_MEMFILE_NOTIFIER
> > + struct shmem_inode_info *info = SHMEM_I(inode);
> > +
> > + start = max(start, folio->index);
> > + end = min(end, folio->index + folio_nr_pages(folio));
> > +
> > + memfile_notifier_invalidate(>memfile_notifiers, start, end);
> > +#endif
> > +}
> > +
> > /*
> > * Remove range of pages and swap entries from page cache, and free them.
> > * If !unfalloc, truncate or punch hole; if unfalloc, undo failed
> > fallocate.
> > @@ -946,6 +968,8 @@ static void shmem_undo_range(struct inode *inode,
> > loff_t lstart, loff_t lend,
> > }
> > index += folio_nr_pages(folio) - 1;
> >
> > + notify_invalidate_page(inode, folio, start, end);
> > +
> > if (!unfalloc || !folio_test_uptodate(folio))
> > truncate_inode_folio(mapping, folio);
> > folio_unlock(folio);
> > @@ -1019,6 +1043,9 @@ static void shmem_undo_range(struct inode *inode,
> > loff_t lstart, loff_t lend,
> > index--;
> > break;
> > }
> > +
> > + notify_invalidate_page(inode, folio, start,
> > end);
> > +
>
> Should this be done in batches or done once for all of range [start, end)?
Batching is definitely prefered. Will look at that.
Thanks,
Chao
>
> > VM_BUG_ON_FOLIO(folio_test_writeback(folio),
> > folio);
> > truncate_inode_folio(mapping, folio);
> > @@ -2279,6 +2306,9 @@ static struct inode *shmem_get_inode(struct
> > super_block *sb, const struct inode
> > info->flags = flags & VM_NORESERVE;
> > INIT_LIST_HEAD(>shrinklist);
> > INIT_LIST_HEAD(>swaplist);
> > +#ifdef CONFIG_MEMFILE_NOTIFIER
> > + memfile_notifier_list_init(>memfile_notifiers);
> > +#endif
> > simple_xattrs_init(>xattrs);
> > cache_no_acl(inode);
> > mapping_set_large_folios(inode->i_mapping);
> > @@ -2802,6 +2832,7 @@ static long shmem_fallocate(struct file *file, int
> > mode, loff_t offset,
> > if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
> > i_size_write(inode, offset + len);
> > inode->i_ctime = current_time(inode);
> > + notify_fallocate(inode, start, end);
> > undone:
> >
Re: [PATCH v5 03/13] mm/shmem: Support memfile_notifier
On Thu, Mar 10, 2022 at 6:10 AM Chao Peng wrote:
>
> From: "Kirill A. Shutemov"
>
> It maintains a memfile_notifier list in shmem_inode_info structure and
> implements memfile_pfn_ops callbacks defined by memfile_notifier. It
> then exposes them to memfile_notifier via
> shmem_get_memfile_notifier_info.
>
> We use SGP_NOALLOC in shmem_get_lock_pfn since the pages should be
> allocated by userspace for private memory. If there is no pages
> allocated at the offset then error should be returned so KVM knows that
> the memory is not private memory.
>
> Signed-off-by: Kirill A. Shutemov
> Signed-off-by: Chao Peng
> ---
> include/linux/shmem_fs.h | 4 +++
> mm/shmem.c | 76
> 2 files changed, 80 insertions(+)
>
> diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
> index 2dde843f28ef..7bb16f2d2825 100644
> --- a/include/linux/shmem_fs.h
> +++ b/include/linux/shmem_fs.h
> @@ -9,6 +9,7 @@
> #include
> #include
> #include
> +#include
>
> /* inode in-kernel data */
>
> @@ -28,6 +29,9 @@ struct shmem_inode_info {
> struct simple_xattrsxattrs; /* list of xattrs */
> atomic_tstop_eviction; /* hold when working on inode
> */
> unsigned intxflags; /* shmem extended flags */
> +#ifdef CONFIG_MEMFILE_NOTIFIER
> + struct memfile_notifier_list memfile_notifiers;
> +#endif
> struct inodevfs_inode;
> };
>
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 9b31a7056009..7b43e274c9a2 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -903,6 +903,28 @@ static struct folio *shmem_get_partial_folio(struct
> inode *inode, pgoff_t index)
> return page ? page_folio(page) : NULL;
> }
>
> +static void notify_fallocate(struct inode *inode, pgoff_t start, pgoff_t end)
> +{
> +#ifdef CONFIG_MEMFILE_NOTIFIER
> + struct shmem_inode_info *info = SHMEM_I(inode);
> +
> + memfile_notifier_fallocate(>memfile_notifiers, start, end);
> +#endif
> +}
> +
> +static void notify_invalidate_page(struct inode *inode, struct folio *folio,
> + pgoff_t start, pgoff_t end)
> +{
> +#ifdef CONFIG_MEMFILE_NOTIFIER
> + struct shmem_inode_info *info = SHMEM_I(inode);
> +
> + start = max(start, folio->index);
> + end = min(end, folio->index + folio_nr_pages(folio));
> +
> + memfile_notifier_invalidate(>memfile_notifiers, start, end);
> +#endif
> +}
> +
> /*
> * Remove range of pages and swap entries from page cache, and free them.
> * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate.
> @@ -946,6 +968,8 @@ static void shmem_undo_range(struct inode *inode, loff_t
> lstart, loff_t lend,
> }
> index += folio_nr_pages(folio) - 1;
>
> + notify_invalidate_page(inode, folio, start, end);
> +
> if (!unfalloc || !folio_test_uptodate(folio))
> truncate_inode_folio(mapping, folio);
> folio_unlock(folio);
> @@ -1019,6 +1043,9 @@ static void shmem_undo_range(struct inode *inode,
> loff_t lstart, loff_t lend,
> index--;
> break;
> }
> +
> + notify_invalidate_page(inode, folio, start,
> end);
> +
Should this be done in batches or done once for all of range [start, end)?
> VM_BUG_ON_FOLIO(folio_test_writeback(folio),
> folio);
> truncate_inode_folio(mapping, folio);
> @@ -2279,6 +2306,9 @@ static struct inode *shmem_get_inode(struct super_block
> *sb, const struct inode
> info->flags = flags & VM_NORESERVE;
> INIT_LIST_HEAD(>shrinklist);
> INIT_LIST_HEAD(>swaplist);
> +#ifdef CONFIG_MEMFILE_NOTIFIER
> + memfile_notifier_list_init(>memfile_notifiers);
> +#endif
> simple_xattrs_init(>xattrs);
> cache_no_acl(inode);
> mapping_set_large_folios(inode->i_mapping);
> @@ -2802,6 +2832,7 @@ static long shmem_fallocate(struct file *file, int
> mode, loff_t offset,
> if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
> i_size_write(inode, offset + len);
> inode->i_ctime = current_time(inode);
> + notify_fallocate(inode, start, end);
> undone:
> spin_lock(>i_lock);
> inode->i_private = NULL;
> @@ -3909,6 +3940,47 @@ static struct file_system_type shmem_fs_type = {
> .fs_flags = FS_USERNS_MOUNT,
> };
>
> +#ifdef CONFIG_MEMFILE_NOTIFIER
> +static long shmem_get_lock_pfn(struct inode *inode, pgoff_t offset, int
> *order)
> +{
> + struct page *page;
> + int ret;
> +
> + ret = shmem_getpage(inode,
Re: [PATCH v5 03/13] mm/shmem: Support memfile_notifier
On Mon, Apr 11, 2022 at 06:26:47PM +0300, Kirill A. Shutemov wrote:
> On Thu, Mar 10, 2022 at 10:09:01PM +0800, Chao Peng wrote:
> > diff --git a/mm/shmem.c b/mm/shmem.c
> > index 9b31a7056009..7b43e274c9a2 100644
> > --- a/mm/shmem.c
> > +++ b/mm/shmem.c
> > @@ -903,6 +903,28 @@ static struct folio *shmem_get_partial_folio(struct
> > inode *inode, pgoff_t index)
> > return page ? page_folio(page) : NULL;
> > }
> >
> > +static void notify_fallocate(struct inode *inode, pgoff_t start, pgoff_t
> > end)
> > +{
> > +#ifdef CONFIG_MEMFILE_NOTIFIER
> > + struct shmem_inode_info *info = SHMEM_I(inode);
> > +
> > + memfile_notifier_fallocate(>memfile_notifiers, start, end);
> > +#endif
>
> All these #ifdefs look ugly. Could you provide dummy memfile_* for
> !MEMFILE_NOTIFIER case?
Sure.
Chao
>
> --
> Kirill A. Shutemov
Re: [PATCH v5 03/13] mm/shmem: Support memfile_notifier
On Thu, Mar 10, 2022 at 10:09:01PM +0800, Chao Peng wrote:
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 9b31a7056009..7b43e274c9a2 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -903,6 +903,28 @@ static struct folio *shmem_get_partial_folio(struct
> inode *inode, pgoff_t index)
> return page ? page_folio(page) : NULL;
> }
>
> +static void notify_fallocate(struct inode *inode, pgoff_t start, pgoff_t end)
> +{
> +#ifdef CONFIG_MEMFILE_NOTIFIER
> + struct shmem_inode_info *info = SHMEM_I(inode);
> +
> + memfile_notifier_fallocate(>memfile_notifiers, start, end);
> +#endif
All these #ifdefs look ugly. Could you provide dummy memfile_* for
!MEMFILE_NOTIFIER case?
--
Kirill A. Shutemov
Re: [PATCH v5 03/13] mm/shmem: Support memfile_notifier
On Fri, Mar 11, 2022 at 10:08:22AM +1100, Dave Chinner wrote:
> On Thu, Mar 10, 2022 at 10:09:01PM +0800, Chao Peng wrote:
> > From: "Kirill A. Shutemov"
> >
> > It maintains a memfile_notifier list in shmem_inode_info structure and
> > implements memfile_pfn_ops callbacks defined by memfile_notifier. It
> > then exposes them to memfile_notifier via
> > shmem_get_memfile_notifier_info.
> >
> > We use SGP_NOALLOC in shmem_get_lock_pfn since the pages should be
> > allocated by userspace for private memory. If there is no pages
> > allocated at the offset then error should be returned so KVM knows that
> > the memory is not private memory.
> >
> > Signed-off-by: Kirill A. Shutemov
> > Signed-off-by: Chao Peng
> > ---
> > include/linux/shmem_fs.h | 4 +++
> > mm/shmem.c | 76
> > 2 files changed, 80 insertions(+)
> >
> > diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
> > index 2dde843f28ef..7bb16f2d2825 100644
> > --- a/include/linux/shmem_fs.h
> > +++ b/include/linux/shmem_fs.h
> > @@ -9,6 +9,7 @@
> > #include
> > #include
> > #include
> > +#include
> >
> > /* inode in-kernel data */
> >
> > @@ -28,6 +29,9 @@ struct shmem_inode_info {
> > struct simple_xattrsxattrs; /* list of xattrs */
> > atomic_tstop_eviction; /* hold when working on inode */
> > unsigned intxflags; /* shmem extended flags */
> > +#ifdef CONFIG_MEMFILE_NOTIFIER
> > + struct memfile_notifier_list memfile_notifiers;
> > +#endif
> > struct inodevfs_inode;
> > };
> >
> > diff --git a/mm/shmem.c b/mm/shmem.c
> > index 9b31a7056009..7b43e274c9a2 100644
> > --- a/mm/shmem.c
> > +++ b/mm/shmem.c
> > @@ -903,6 +903,28 @@ static struct folio *shmem_get_partial_folio(struct
> > inode *inode, pgoff_t index)
> > return page ? page_folio(page) : NULL;
> > }
> >
> > +static void notify_fallocate(struct inode *inode, pgoff_t start, pgoff_t
> > end)
> > +{
> > +#ifdef CONFIG_MEMFILE_NOTIFIER
> > + struct shmem_inode_info *info = SHMEM_I(inode);
> > +
> > + memfile_notifier_fallocate(>memfile_notifiers, start, end);
> > +#endif
> > +}
>
> *notify_populate(), not fallocate. This is a notification that a
> range has been populated, not that the fallocate() syscall was run
> to populate the backing store of a file.
>
> i.e. fallocate is the name of a userspace filesystem API that can
> be used to manipulate the backing store of a file in various ways.
> It can both populate and punch away the backing store of a file, and
> some operations that fallocate() can run will do both (e.g.
> FALLOC_FL_ZERO_RANGE) and so could generate both
> notify_invalidate() and a notify_populate() events.
Yes, I fully agreed fallocate syscall has both populating and hole
punching semantics so notify_fallocate can be misleading since we
actually mean populate here.
>
> Hence "fallocate" as an internal mm namespace or operation does not
> belong anywhere in core MM infrastructure - it should never get used
> anywhere other than the VFS/filesystem layers that implement the
> fallocate() syscall or use it directly.
Will use your suggestion through the series where applied. Thanks for
your suggestion.
Chao
>
> Cheers,
>
> Dave.
>
> --
> Dave Chinner
> da...@fromorbit.com
Re: [PATCH v5 03/13] mm/shmem: Support memfile_notifier
On Thu, Mar 10, 2022 at 10:09:01PM +0800, Chao Peng wrote:
> From: "Kirill A. Shutemov"
>
> It maintains a memfile_notifier list in shmem_inode_info structure and
> implements memfile_pfn_ops callbacks defined by memfile_notifier. It
> then exposes them to memfile_notifier via
> shmem_get_memfile_notifier_info.
>
> We use SGP_NOALLOC in shmem_get_lock_pfn since the pages should be
> allocated by userspace for private memory. If there is no pages
> allocated at the offset then error should be returned so KVM knows that
> the memory is not private memory.
>
> Signed-off-by: Kirill A. Shutemov
> Signed-off-by: Chao Peng
> ---
> include/linux/shmem_fs.h | 4 +++
> mm/shmem.c | 76
> 2 files changed, 80 insertions(+)
>
> diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
> index 2dde843f28ef..7bb16f2d2825 100644
> --- a/include/linux/shmem_fs.h
> +++ b/include/linux/shmem_fs.h
> @@ -9,6 +9,7 @@
> #include
> #include
> #include
> +#include
>
> /* inode in-kernel data */
>
> @@ -28,6 +29,9 @@ struct shmem_inode_info {
> struct simple_xattrsxattrs; /* list of xattrs */
> atomic_tstop_eviction; /* hold when working on inode */
> unsigned intxflags; /* shmem extended flags */
> +#ifdef CONFIG_MEMFILE_NOTIFIER
> + struct memfile_notifier_list memfile_notifiers;
> +#endif
> struct inodevfs_inode;
> };
>
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 9b31a7056009..7b43e274c9a2 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -903,6 +903,28 @@ static struct folio *shmem_get_partial_folio(struct
> inode *inode, pgoff_t index)
> return page ? page_folio(page) : NULL;
> }
>
> +static void notify_fallocate(struct inode *inode, pgoff_t start, pgoff_t end)
> +{
> +#ifdef CONFIG_MEMFILE_NOTIFIER
> + struct shmem_inode_info *info = SHMEM_I(inode);
> +
> + memfile_notifier_fallocate(>memfile_notifiers, start, end);
> +#endif
> +}
*notify_populate(), not fallocate. This is a notification that a
range has been populated, not that the fallocate() syscall was run
to populate the backing store of a file.
i.e. fallocate is the name of a userspace filesystem API that can
be used to manipulate the backing store of a file in various ways.
It can both populate and punch away the backing store of a file, and
some operations that fallocate() can run will do both (e.g.
FALLOC_FL_ZERO_RANGE) and so could generate both
notify_invalidate() and a notify_populate() events.
Hence "fallocate" as an internal mm namespace or operation does not
belong anywhere in core MM infrastructure - it should never get used
anywhere other than the VFS/filesystem layers that implement the
fallocate() syscall or use it directly.
Cheers,
Dave.
--
Dave Chinner
da...@fromorbit.com
[PATCH v5 03/13] mm/shmem: Support memfile_notifier
From: "Kirill A. Shutemov"
It maintains a memfile_notifier list in shmem_inode_info structure and
implements memfile_pfn_ops callbacks defined by memfile_notifier. It
then exposes them to memfile_notifier via
shmem_get_memfile_notifier_info.
We use SGP_NOALLOC in shmem_get_lock_pfn since the pages should be
allocated by userspace for private memory. If there is no pages
allocated at the offset then error should be returned so KVM knows that
the memory is not private memory.
Signed-off-by: Kirill A. Shutemov
Signed-off-by: Chao Peng
---
include/linux/shmem_fs.h | 4 +++
mm/shmem.c | 76
2 files changed, 80 insertions(+)
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 2dde843f28ef..7bb16f2d2825 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -9,6 +9,7 @@
#include
#include
#include
+#include
/* inode in-kernel data */
@@ -28,6 +29,9 @@ struct shmem_inode_info {
struct simple_xattrsxattrs; /* list of xattrs */
atomic_tstop_eviction; /* hold when working on inode */
unsigned intxflags; /* shmem extended flags */
+#ifdef CONFIG_MEMFILE_NOTIFIER
+ struct memfile_notifier_list memfile_notifiers;
+#endif
struct inodevfs_inode;
};
diff --git a/mm/shmem.c b/mm/shmem.c
index 9b31a7056009..7b43e274c9a2 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -903,6 +903,28 @@ static struct folio *shmem_get_partial_folio(struct inode
*inode, pgoff_t index)
return page ? page_folio(page) : NULL;
}
+static void notify_fallocate(struct inode *inode, pgoff_t start, pgoff_t end)
+{
+#ifdef CONFIG_MEMFILE_NOTIFIER
+ struct shmem_inode_info *info = SHMEM_I(inode);
+
+ memfile_notifier_fallocate(>memfile_notifiers, start, end);
+#endif
+}
+
+static void notify_invalidate_page(struct inode *inode, struct folio *folio,
+ pgoff_t start, pgoff_t end)
+{
+#ifdef CONFIG_MEMFILE_NOTIFIER
+ struct shmem_inode_info *info = SHMEM_I(inode);
+
+ start = max(start, folio->index);
+ end = min(end, folio->index + folio_nr_pages(folio));
+
+ memfile_notifier_invalidate(>memfile_notifiers, start, end);
+#endif
+}
+
/*
* Remove range of pages and swap entries from page cache, and free them.
* If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate.
@@ -946,6 +968,8 @@ static void shmem_undo_range(struct inode *inode, loff_t
lstart, loff_t lend,
}
index += folio_nr_pages(folio) - 1;
+ notify_invalidate_page(inode, folio, start, end);
+
if (!unfalloc || !folio_test_uptodate(folio))
truncate_inode_folio(mapping, folio);
folio_unlock(folio);
@@ -1019,6 +1043,9 @@ static void shmem_undo_range(struct inode *inode, loff_t
lstart, loff_t lend,
index--;
break;
}
+
+ notify_invalidate_page(inode, folio, start,
end);
+
VM_BUG_ON_FOLIO(folio_test_writeback(folio),
folio);
truncate_inode_folio(mapping, folio);
@@ -2279,6 +2306,9 @@ static struct inode *shmem_get_inode(struct super_block
*sb, const struct inode
info->flags = flags & VM_NORESERVE;
INIT_LIST_HEAD(>shrinklist);
INIT_LIST_HEAD(>swaplist);
+#ifdef CONFIG_MEMFILE_NOTIFIER
+ memfile_notifier_list_init(>memfile_notifiers);
+#endif
simple_xattrs_init(>xattrs);
cache_no_acl(inode);
mapping_set_large_folios(inode->i_mapping);
@@ -2802,6 +2832,7 @@ static long shmem_fallocate(struct file *file, int mode,
loff_t offset,
if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
i_size_write(inode, offset + len);
inode->i_ctime = current_time(inode);
+ notify_fallocate(inode, start, end);
undone:
spin_lock(>i_lock);
inode->i_private = NULL;
@@ -3909,6 +3940,47 @@ static struct file_system_type shmem_fs_type = {
.fs_flags = FS_USERNS_MOUNT,
};
+#ifdef CONFIG_MEMFILE_NOTIFIER
+static long shmem_get_lock_pfn(struct inode *inode, pgoff_t offset, int *order)
+{
+ struct page *page;
+ int ret;
+
+ ret = shmem_getpage(inode, offset, , SGP_NOALLOC);
+ if (ret)
+ return ret;
+
+ *order = thp_order(compound_head(page));
+
+ return page_to_pfn(page);
+}
+
+static void shmem_put_unlock_pfn(unsigned long pfn)
+{
+ struct page *page = pfn_to_page(pfn);
+
+ VM_BUG_ON_PAGE(!PageLocked(page), page);
+
+ set_page_dirty(page);
+ unlock_page(page);
+
