Re: [PATCH v6 6/9] nfsd: use the getattr operation to fetch i_version

[Chuck Lever III <chuck.lever@oracle.com>]

> On Sep 30, 2022, at 7:18 AM, Jeff Layton <jlayton@kernel.org> wrote:
> 
> Now that we can call into vfs_getattr to get the i_version field, use
> that facility to fetch it instead of doing it in nfsd4_change_attribute.
> 
> Neil also pointed out recently that IS_I_VERSION directory operations
> are always logged,

^logged^synchronous maybe?

> and so we only need to mitigate the rollback problem
> on regular files. Also, we don't need to factor in the ctime when
> reexporting NFS or Ceph.
> 
> Set the STATX_VERSION (and BTIME) bits in the request when we're dealing
> with a v4 request. Then, instead of looking at IS_I_VERSION when
> generating the change attr, look at the result mask and only use it if
> STATX_VERSION is set. With this change, we can drop the fetch_iversion
> export operation as well.
> 
> Move nfsd4_change_attribute into nfsfh.c, and change it to only factor
> in the ctime if it's a regular file and the fs doesn't advertise
> STATX_ATTR_VERSION_MONOTONIC.

This patch is doing some heavy lifting. I'd prefer to see it split
up to improve bisectability:

1. Move nfsd4_change_attribute() to fs/nfsd/nfsfh.c -- no functional changes

2. Change nfsd4_change_attribute() and vfs_getattr() call sites

3. Eliminate .fetch_iversion


> Signed-off-by: Jeff Layton <jlayton@kernel.org>
> ---
> fs/nfs/export.c          |  7 -------
> fs/nfsd/nfs4xdr.c        |  4 +++-
> fs/nfsd/nfsfh.c          | 40 ++++++++++++++++++++++++++++++++++++++++
> fs/nfsd/nfsfh.h          | 29 +----------------------------
> fs/nfsd/vfs.h            |  7 ++++++-
> include/linux/exportfs.h |  1 -
> 6 files changed, 50 insertions(+), 38 deletions(-)
> 
> diff --git a/fs/nfs/export.c b/fs/nfs/export.c
> index 01596f2d0a1e..1a9d5aa51dfb 100644
> --- a/fs/nfs/export.c
> +++ b/fs/nfs/export.c
> @@ -145,17 +145,10 @@ nfs_get_parent(struct dentry *dentry)
> 	return parent;
> }
> 
> -static u64 nfs_fetch_iversion(struct inode *inode)
> -{
> -	nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE);
> -	return inode_peek_iversion_raw(inode);
> -}
> -
> const struct export_operations nfs_export_ops = {
> 	.encode_fh = nfs_encode_fh,
> 	.fh_to_dentry = nfs_fh_to_dentry,
> 	.get_parent = nfs_get_parent,
> -	.fetch_iversion = nfs_fetch_iversion,
> 	.flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK|
> 		EXPORT_OP_CLOSE_BEFORE_UNLINK|EXPORT_OP_REMOTE_FS|
> 		EXPORT_OP_NOATOMIC_ATTR,
> diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
> index 1e9690a061ec..779c009314c6 100644
> --- a/fs/nfsd/nfs4xdr.c
> +++ b/fs/nfsd/nfs4xdr.c
> @@ -2869,7 +2869,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
> 			goto out;
> 	}
> 
> -	err = vfs_getattr(&path, &stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
> +	err = vfs_getattr(&path, &stat,
> +			  STATX_BASIC_STATS | STATX_BTIME | STATX_VERSION,
> +			  AT_STATX_SYNC_AS_STAT);
> 	if (err)
> 		goto out_nfserr;
> 	if (!(stat.result_mask & STATX_BTIME))
> diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
> index a5b71526cee0..9168bc657378 100644
> --- a/fs/nfsd/nfsfh.c
> +++ b/fs/nfsd/nfsfh.c
> @@ -634,6 +634,10 @@ void fh_fill_pre_attrs(struct svc_fh *fhp)
> 		stat.mtime = inode->i_mtime;
> 		stat.ctime = inode->i_ctime;
> 		stat.size  = inode->i_size;
> +		if (v4 && IS_I_VERSION(inode)) {
> +			stat.version = inode_query_iversion(inode);
> +			stat.result_mask |= STATX_VERSION;
> +		}
> 	}
> 	if (v4)
> 		fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode);
> @@ -665,6 +669,8 @@ void fh_fill_post_attrs(struct svc_fh *fhp)
> 	if (err) {
> 		fhp->fh_post_saved = false;
> 		fhp->fh_post_attr.ctime = inode->i_ctime;
> +		if (v4 && IS_I_VERSION(inode))
> +			fhp->fh_post_attr.version = inode_query_iversion(inode);

Since fh_fill_post_attrs() calls nfsd4_change_attribute() as its
next step, don't you need to set STATX_VERSION here too?

I kind of hate the way we're handling both NFSv3 and NFSv4 post_attr
here, it's pretty difficult to reason about.


> 	} else
> 		fhp->fh_post_saved = true;
> 	if (v4)
> @@ -754,3 +760,37 @@ enum fsid_source fsid_source(const struct svc_fh *fhp)
> 		return FSIDSOURCE_UUID;
> 	return FSIDSOURCE_DEV;
> }
> +
> +/*
> + * We could use i_version alone as the change attribute.  However, i_version
> + * can go backwards on a regular file after an unclean shutdown.  On its own
> + * that doesn't necessarily cause a problem, but if i_version goes backwards
> + * and then is incremented again it could reuse a value that was previously
> + * used before boot, and a client who queried the two values might incorrectly
> + * assume nothing changed.
> + *
> + * By using both ctime and the i_version counter we guarantee that as long as
> + * time doesn't go backwards we never reuse an old value. If the filesystem
> + * advertises STATX_ATTR_VERSION_MONOTONIC, then this mitigation is not needed.
> + *
> + * We only need to do this for regular files as well. For directories, we
> + * assume that the new change attr is always logged to stable storage in some
> + * fashion before the results can be seen.
> + */

Let's make this a kdoc-style comment. Thanks!


> +u64 nfsd4_change_attribute(struct kstat *stat, struct inode *inode)

I'd prefer to use "const" pointers for both function parameters.


> +{
> +	u64 chattr;
> +
> +	if (stat->result_mask & STATX_VERSION) {
> +		chattr = stat->version;
> +
> +		if (S_ISREG(inode->i_mode) &&
> +		    !(stat->attributes & STATX_ATTR_VERSION_MONOTONIC)) {
> +			chattr += (u64)stat->ctime.tv_sec << 30;
> +			chattr += stat->ctime.tv_nsec;
> +		}
> +	} else {
> +		chattr = time_to_chattr(&stat->ctime);
> +	}
> +	return chattr;
> +}
> diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
> index c3ae6414fc5c..4c223a7a91d4 100644
> --- a/fs/nfsd/nfsfh.h
> +++ b/fs/nfsd/nfsfh.h
> @@ -291,34 +291,7 @@ static inline void fh_clear_pre_post_attrs(struct svc_fh *fhp)
> 	fhp->fh_pre_saved = false;
> }
> 
> -/*
> - * We could use i_version alone as the change attribute.  However,
> - * i_version can go backwards after a reboot.  On its own that doesn't
> - * necessarily cause a problem, but if i_version goes backwards and then
> - * is incremented again it could reuse a value that was previously used
> - * before boot, and a client who queried the two values might
> - * incorrectly assume nothing changed.
> - *
> - * By using both ctime and the i_version counter we guarantee that as
> - * long as time doesn't go backwards we never reuse an old value.
> - */
> -static inline u64 nfsd4_change_attribute(struct kstat *stat,
> -					 struct inode *inode)
> -{
> -	if (inode->i_sb->s_export_op->fetch_iversion)
> -		return inode->i_sb->s_export_op->fetch_iversion(inode);
> -	else if (IS_I_VERSION(inode)) {
> -		u64 chattr;
> -
> -		chattr =  stat->ctime.tv_sec;
> -		chattr <<= 30;
> -		chattr += stat->ctime.tv_nsec;
> -		chattr += inode_query_iversion(inode);
> -		return chattr;
> -	} else
> -		return time_to_chattr(&stat->ctime);
> -}
> -
> +u64 nfsd4_change_attribute(struct kstat *stat, struct inode *inode);
> extern void fh_fill_pre_attrs(struct svc_fh *fhp);
> extern void fh_fill_post_attrs(struct svc_fh *fhp);
> extern void fh_fill_both_attrs(struct svc_fh *fhp);
> diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
> index c95cd414b4bb..a905f59481ee 100644
> --- a/fs/nfsd/vfs.h
> +++ b/fs/nfsd/vfs.h
> @@ -168,9 +168,14 @@ static inline void fh_drop_write(struct svc_fh *fh)
> 
> static inline __be32 fh_getattr(const struct svc_fh *fh, struct kstat *stat)
> {
> +	u32 request_mask = STATX_BASIC_STATS;

Reverse christmas tree, please.


> 	struct path p = {.mnt = fh->fh_export->ex_path.mnt,
> 			 .dentry = fh->fh_dentry};
> -	return nfserrno(vfs_getattr(&p, stat, STATX_BASIC_STATS,
> +
> +	if (fh->fh_maxsize == NFS4_FHSIZE)

Would it hurt to set BTIME and VERSION unconditionally?


> +		request_mask |= (STATX_BTIME | STATX_VERSION);
> +
> +	return nfserrno(vfs_getattr(&p, stat, request_mask,
> 				    AT_STATX_SYNC_AS_STAT));
> }
> 
> diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
> index fe848901fcc3..9f4d4bcbf251 100644
> --- a/include/linux/exportfs.h
> +++ b/include/linux/exportfs.h
> @@ -213,7 +213,6 @@ struct export_operations {
> 			  bool write, u32 *device_generation);
> 	int (*commit_blocks)(struct inode *inode, struct iomap *iomaps,
> 			     int nr_iomaps, struct iattr *iattr);
> -	u64 (*fetch_iversion)(struct inode *);
> #define	EXPORT_OP_NOWCC			(0x1) /* don't collect v3 wcc data */
> #define	EXPORT_OP_NOSUBTREECHK		(0x2) /* no subtree checking */
> #define	EXPORT_OP_CLOSE_BEFORE_UNLINK	(0x4) /* close files before unlink */
> -- 
> 2.37.3
> 

--
Chuck Lever