Re: [PATCH v4 01/19] fs: new API for handling inode->i_version

[Jeff Layton <jlayton@kernel.org>]

On Sat, 2017-12-23 at 10:14 +1100, NeilBrown wrote:
> On Fri, Dec 22 2017, Jeff Layton wrote:
> 
> > From: Jeff Layton <jlayton@redhat.com>
> > 
> > Add a documentation blob that explains what the i_version field is, how
> > it is expected to work, and how it is currently implemented by various
> > filesystems.
> > 
> > We already have inode_inc_iversion. Add several other functions for
> > manipulating and accessing the i_version counter. For now, the
> > implementation is trivial and basically works the way that all of the
> > open-coded i_version accesses work today.
> > 
> > Future patches will convert existing users of i_version to use the new
> > API, and then convert the backend implementation to do things more
> > efficiently.
> > 
> > Signed-off-by: Jeff Layton <jlayton@redhat.com>
> > ---
> >  fs/btrfs/file.c          |   1 +
> >  fs/btrfs/inode.c         |   1 +
> >  fs/btrfs/ioctl.c         |   1 +
> >  fs/btrfs/xattr.c         |   1 +
> >  fs/ext4/inode.c          |   1 +
> >  fs/ext4/namei.c          |   1 +
> >  fs/inode.c               |   1 +
> >  include/linux/fs.h       |  15 ----
> >  include/linux/iversion.h | 205 +++++++++++++++++++++++++++++++++++++++++++++++
> >  9 files changed, 212 insertions(+), 15 deletions(-)
> >  create mode 100644 include/linux/iversion.h
> > 
> > diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
> > index eb1bac7c8553..c95d7b2efefb 100644
> > --- a/fs/btrfs/file.c
> > +++ b/fs/btrfs/file.c
> > @@ -31,6 +31,7 @@
> >  #include <linux/slab.h>
> >  #include <linux/btrfs.h>
> >  #include <linux/uio.h>
> > +#include <linux/iversion.h>
> >  #include "ctree.h"
> >  #include "disk-io.h"
> >  #include "transaction.h"
> > diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
> > index e1a7f3cb5be9..27f008b33fc1 100644
> > --- a/fs/btrfs/inode.c
> > +++ b/fs/btrfs/inode.c
> > @@ -43,6 +43,7 @@
> >  #include <linux/posix_acl_xattr.h>
> >  #include <linux/uio.h>
> >  #include <linux/magic.h>
> > +#include <linux/iversion.h>
> >  #include "ctree.h"
> >  #include "disk-io.h"
> >  #include "transaction.h"
> > diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
> > index 2ef8acaac688..aa452c9e2eff 100644
> > --- a/fs/btrfs/ioctl.c
> > +++ b/fs/btrfs/ioctl.c
> > @@ -43,6 +43,7 @@
> >  #include <linux/uuid.h>
> >  #include <linux/btrfs.h>
> >  #include <linux/uaccess.h>
> > +#include <linux/iversion.h>
> >  #include "ctree.h"
> >  #include "disk-io.h"
> >  #include "transaction.h"
> > diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
> > index 2c7e53f9ff1b..5258c1714830 100644
> > --- a/fs/btrfs/xattr.c
> > +++ b/fs/btrfs/xattr.c
> > @@ -23,6 +23,7 @@
> >  #include <linux/xattr.h>
> >  #include <linux/security.h>
> >  #include <linux/posix_acl_xattr.h>
> > +#include <linux/iversion.h>
> >  #include "ctree.h"
> >  #include "btrfs_inode.h"
> >  #include "transaction.h"
> > diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> > index 7df2c5644e59..fa5d8bc52d2d 100644
> > --- a/fs/ext4/inode.c
> > +++ b/fs/ext4/inode.c
> > @@ -39,6 +39,7 @@
> >  #include <linux/slab.h>
> >  #include <linux/bitops.h>
> >  #include <linux/iomap.h>
> > +#include <linux/iversion.h>
> >  
> >  #include "ext4_jbd2.h"
> >  #include "xattr.h"
> > diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
> > index 798b3ac680db..bcf0dff517be 100644
> > --- a/fs/ext4/namei.c
> > +++ b/fs/ext4/namei.c
> > @@ -34,6 +34,7 @@
> >  #include <linux/quotaops.h>
> >  #include <linux/buffer_head.h>
> >  #include <linux/bio.h>
> > +#include <linux/iversion.h>
> >  #include "ext4.h"
> >  #include "ext4_jbd2.h"
> >  
> > diff --git a/fs/inode.c b/fs/inode.c
> > index 03102d6ef044..19e72f500f71 100644
> > --- a/fs/inode.c
> > +++ b/fs/inode.c
> > @@ -18,6 +18,7 @@
> >  #include <linux/buffer_head.h> /* for inode_has_buffers */
> >  #include <linux/ratelimit.h>
> >  #include <linux/list_lru.h>
> > +#include <linux/iversion.h>
> >  #include <trace/events/writeback.h>
> >  #include "internal.h"
> >  
> > diff --git a/include/linux/fs.h b/include/linux/fs.h
> > index 511fbaabf624..76382c24e9d0 100644
> > --- a/include/linux/fs.h
> > +++ b/include/linux/fs.h
> > @@ -2036,21 +2036,6 @@ static inline void inode_dec_link_count(struct inode *inode)
> >  	mark_inode_dirty(inode);
> >  }
> >  
> > -/**
> > - * inode_inc_iversion - increments i_version
> > - * @inode: inode that need to be updated
> > - *
> > - * Every time the inode is modified, the i_version field will be incremented.
> > - * The filesystem has to be mounted with i_version flag
> > - */
> > -
> > -static inline void inode_inc_iversion(struct inode *inode)
> > -{
> > -       spin_lock(&inode->i_lock);
> > -       inode->i_version++;
> > -       spin_unlock(&inode->i_lock);
> > -}
> > -
> >  enum file_time_flags {
> >  	S_ATIME = 1,
> >  	S_MTIME = 2,
> > diff --git a/include/linux/iversion.h b/include/linux/iversion.h
> > new file mode 100644
> > index 000000000000..bb50d27c71f9
> > --- /dev/null
> > +++ b/include/linux/iversion.h
> > @@ -0,0 +1,205 @@
> > +/* SPDX-License-Identifier: GPL-2.0 */
> > +#ifndef _LINUX_IVERSION_H
> > +#define _LINUX_IVERSION_H
> > +
> > +#include <linux/fs.h>
> > +
> > +/*
> > + * The change attribute (i_version) is mandated by NFSv4 and is mostly for
> > + * knfsd, but is also used for other purposes (e.g. IMA). The i_version must
> > + * appear different to observers if there was a change to the inode's data or
> > + * metadata since it was last queried.
> > + *
> > + * It should be considered an opaque value by observers. If it remains the same
> 
>                                  ^^^^^^^^^^^^
> 
> You keep using that word ... I don't think it means what you think it
> means.
> Change that sentence to:
> 
>     Observers see i_version as a 64 number which never decreases.
> 
> and the rest still makes perfect sense.
> 

Thanks! Fixed in my tree. I'll not resend the set just for that though.

> > + * since it was last checked, then nothing has changed in the inode. If it's
> > + * different then something has changed. Observers cannot infer anything about
> > + * the nature or magnitude of the changes from the value, only that the inode
> > + * has changed in some fashion.
> > + *
> > + * Not all filesystems properly implement the i_version counter. Subsystems that
> > + * want to use i_version field on an inode should first check whether the
> > + * filesystem sets the SB_I_VERSION flag (usually via the IS_I_VERSION macro).
> > + *
> > + * Those that set SB_I_VERSION will automatically have their i_version counter
> > + * incremented on writes to normal files. If the SB_I_VERSION is not set, then
> > + * the VFS will not touch it on writes, and the filesystem can use it how it
> > + * wishes. Note that the filesystem is always responsible for updating the
> > + * i_version on namespace changes in directories (mkdir, rmdir, unlink, etc.).
> > + * We consider these sorts of filesystems to have a kernel-managed i_version.
> > + *
> > + * Note that some filesystems (e.g. NFS and AFS) just use the field to store
> > + * a server-provided value (for the most part). For that reason, those
> > + * filesystems do not set SB_I_VERSION. These filesystems are considered to
> > + * have a self-managed i_version.
> > + */
> > +
> > +/**
> > + * inode_set_iversion_raw - set i_version to the specified raw value
> > + * @inode: inode to set
> > + * @new: new i_version value to set
> > + *
> > + * Set @inode's i_version field to @new. This function is for use by
> > + * filesystems that self-manage the i_version.
> > + *
> > + * For example, the NFS client stores its NFSv4 change attribute in this way,
> > + * and the AFS client stores the data_version from the server here.
> > + */
> > +static inline void
> > +inode_set_iversion_raw(struct inode *inode, const u64 new)
> > +{
> > +	inode->i_version = new;
> > +}
> > +
> > +/**
> > + * inode_set_iversion - set i_version to a particular value
> > + * @inode: inode to set
> > + * @new: new i_version value to set
> > + *
> > + * Set @inode's i_version field to @new. This function is for filesystems with
> > + * a kernel-managed i_version.
> > + *
> > + * For now, this just does the same thing as the _raw variant.
> > + */
> > +static inline void
> > +inode_set_iversion(struct inode *inode, const u64 new)
> > +{
> > +	inode_set_iversion_raw(inode, new);
> > +}
> > +
> > +/**
> > + * inode_set_iversion_queried - set i_version to a particular value and set
> > + *                              flag to indicate that it has been viewed
> > + * @inode: inode to set
> > + * @new: new i_version value to set
> > + *
> > + * When loading in an i_version value from a backing store, we typically don't
> > + * know whether it was previously viewed before being stored or not. Thus, we
> > + * must assume that it was, to ensure that any changes will result in the
> > + * value changing.
> > + *
> > + * This function will set the inode's i_version, and possibly flag the value
> > + * as if it has already been viewed at least once.
> > + *
> > + * For now, this just does what inode_set_iversion does.
> > + */
> > +static inline void
> > +inode_set_iversion_queried(struct inode *inode, const u64 new)
> > +{
> > +	inode_set_iversion(inode, new);
> > +}
> > +
> > +/**
> > + * inode_maybe_inc_iversion - increments i_version
> > + * @inode: inode with the i_version that should be updated
> > + * @force: increment the counter even if it's not necessary
> > + *
> > + * Every time the inode is modified, the i_version field must be seen to have
> > + * changed by any observer.
> > + *
> > + * In this implementation, we always increment it after taking the i_lock to
> > + * ensure that we don't race with other incrementors.
> > + *
> > + * Returns true if counter was bumped, and false if it wasn't.
> > + */
> > +static inline bool
> > +inode_maybe_inc_iversion(struct inode *inode, bool force)
> > +{
> > +	spin_lock(&inode->i_lock);
> > +	inode->i_version++;
> > +	spin_unlock(&inode->i_lock);
> > +	return true;
> > +}
> > +
> > +/**
> > + * inode_inc_iversion - forcibly increment i_version
> > + * @inode: inode that needs to be updated
> > + *
> > + * Forcbily increment the i_version field. This always results in a change to
> > + * the observable value.
> > + */
> > +static inline void
> > +inode_inc_iversion(struct inode *inode)
> > +{
> > +	inode_maybe_inc_iversion(inode, true);
> > +}
> > +
> > +/**
> > + * inode_iversion_need_inc - is the i_version in need of being incremented?
> > + * @inode: inode to check
> > + *
> > + * Returns whether the inode->i_version counter needs incrementing on the next
> > + * change.
> > + *
> > + * For now, we assume that it always does.
> > + */
> > +static inline bool
> > +inode_iversion_need_inc(struct inode *inode)
> > +{
> > +	return true;
> > +}
> > +
> > +/**
> > + * inode_peek_iversion_raw - grab a "raw" iversion value
> > + * @inode: inode from which i_version should be read
> > + *
> > + * Grab a "raw" inode->i_version value and return it. The i_version is not
> > + * flagged or converted in any way. This is mostly used to access a self-managed
> > + * i_version.
> > + *
> > + * With those filesystems, we want to treat the i_version as an entirely
> > + * opaque value.
> > + */
> > +static inline u64
> > +inode_peek_iversion_raw(const struct inode *inode)
> > +{
> > +	return inode->i_version;
> > +}
> > +
> > +/**
> > + * inode_peek_iversion - read i_version without flagging it to be incremented
> > + * @inode: inode from which i_version should be read
> > + *
> > + * Read the inode i_version counter for an inode without registering it as a
> > + * query.
> > + *
> > + * This is typically used by local filesystems that need to store an i_version
> > + * on disk. In that situation, it's not necessary to flag it as having been
> > + * viewed, as the result won't be used to gauge changes from that point.
> > + */
> > +static inline u64
> > +inode_peek_iversion(const struct inode *inode)
> > +{
> > +	return inode_peek_iversion_raw(inode);
> > +}
> > +
> > +/**
> > + * inode_query_iversion - read i_version for later use
> > + * @inode: inode from which i_version should be read
> > + *
> > + * Read the inode i_version counter. This should be used by callers that wish
> > + * to store the returned i_version for later comparison. This will guarantee
> > + * that a later query of the i_version will result in a different value if
> > + * anything has changed.
> > + *
> > + * This implementation just does a peek.
> > + */
> > +static inline u64
> > +inode_query_iversion(struct inode *inode)
> > +{
> > +	return inode_peek_iversion(inode);
> > +}
> > +
> > +/**
> > + * inode_cmp_iversion - check whether the i_version counter has changed
> > + * @inode: inode to check
> > + * @old: old value to check against its i_version
> > + *
> > + * Compare an i_version counter with a previous one. Returns 0 if they are
> > + * the same or non-zero if they are different.
> > + */
> > +static inline s64
> > +inode_cmp_iversion(const struct inode *inode, const u64 old)
> > +{
> > +	return (s64)inode_peek_iversion(inode) - (s64)old;
> > +}
> > +#endif
> > -- 
> > 2.14.3
> > 
> > --
> > To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
> > the body of a message to majordomo@vger.kernel.org
> > More majordomo info at  http://vger.kernel.org/majordomo-info.html

-- 
Jeff Layton <jlayton@kernel.org>