This is a note to let you know that I've just added the patch titled
NFSD: Refactor NFSv4 OPEN(CREATE)
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
nfsd-refactor-nfsv4-open-create.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 4befa50217a197e21ef0954f555ce8ea941ff131
Author: Chuck Lever <chuck.lever@xxxxxxxxxx>
Date: Mon Mar 28 14:47:34 2022 -0400
NFSD: Refactor NFSv4 OPEN(CREATE)
[ Upstream commit 254454a5aa4a9f696d6bae080c08d5863e650f49 ]
Copy do_nfsd_create() to nfs4proc.c and remove NFSv3-specific logic.
Signed-off-by: Chuck Lever <chuck.lever@xxxxxxxxxx>
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 73c62561580a1..489cdcd8f8c9a 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -37,6 +37,8 @@
#include <linux/falloc.h>
#include <linux/slab.h>
#include <linux/kthread.h>
+#include <linux/namei.h>
+
#include <linux/sunrpc/addr.h>
#include <linux/nfs_ssc.h>
@@ -235,6 +237,154 @@ static void nfsd4_set_open_owner_reply_cache(struct nfsd4_compound_state *cstate
&resfh->fh_handle);
}
+static inline bool nfsd4_create_is_exclusive(int createmode)
+{
+ return createmode == NFS4_CREATE_EXCLUSIVE ||
+ createmode == NFS4_CREATE_EXCLUSIVE4_1;
+}
+
+/*
+ * Implement NFSv4's unchecked, guarded, and exclusive create
+ * semantics for regular files. Open state for this new file is
+ * subsequently fabricated in nfsd4_process_open2().
+ *
+ * Upon return, caller must release @fhp and @resfhp.
+ */
+static __be32
+nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ struct svc_fh *resfhp, struct nfsd4_open *open)
+{
+ struct iattr *iap = &open->op_iattr;
+ struct dentry *parent, *child;
+ __u32 v_mtime, v_atime;
+ struct inode *inode;
+ __be32 status;
+ int host_err;
+
+ if (isdotent(open->op_fname, open->op_fnamelen))
+ return nfserr_exist;
+ if (!(iap->ia_valid & ATTR_MODE))
+ iap->ia_mode = 0;
+
+ status = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
+ if (status != nfs_ok)
+ return status;
+ parent = fhp->fh_dentry;
+ inode = d_inode(parent);
+
+ host_err = fh_want_write(fhp);
+ if (host_err)
+ return nfserrno(host_err);
+
+ fh_lock_nested(fhp, I_MUTEX_PARENT);
+
+ child = lookup_one_len(open->op_fname, parent, open->op_fnamelen);
+ if (IS_ERR(child)) {
+ status = nfserrno(PTR_ERR(child));
+ goto out;
+ }
+
+ if (d_really_is_negative(child)) {
+ status = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE);
+ if (status != nfs_ok)
+ goto out;
+ }
+
+ status = fh_compose(resfhp, fhp->fh_export, child, fhp);
+ if (status != nfs_ok)
+ goto out;
+
+ v_mtime = 0;
+ v_atime = 0;
+ if (nfsd4_create_is_exclusive(open->op_createmode)) {
+ u32 *verifier = (u32 *)open->op_verf.data;
+
+ /*
+ * Solaris 7 gets confused (bugid 4218508) if these have
+ * the high bit set, as do xfs filesystems without the
+ * "bigtime" feature. So just clear the high bits. If this
+ * is ever changed to use different attrs for storing the
+ * verifier, then do_open_lookup() will also need to be
+ * fixed accordingly.
+ */
+ v_mtime = verifier[0] & 0x7fffffff;
+ v_atime = verifier[1] & 0x7fffffff;
+ }
+
+ if (d_really_is_positive(child)) {
+ status = nfs_ok;
+
+ switch (open->op_createmode) {
+ case NFS4_CREATE_UNCHECKED:
+ if (!d_is_reg(child))
+ break;
+
+ /*
+ * In NFSv4, we don't want to truncate the file
+ * now. This would be wrong if the OPEN fails for
+ * some other reason. Furthermore, if the size is
+ * nonzero, we should ignore it according to spec!
+ */
+ open->op_truncate = (iap->ia_valid & ATTR_SIZE) &&
+ !iap->ia_size;
+ break;
+ case NFS4_CREATE_GUARDED:
+ status = nfserr_exist;
+ break;
+ case NFS4_CREATE_EXCLUSIVE:
+ if (d_inode(child)->i_mtime.tv_sec == v_mtime &&
+ d_inode(child)->i_atime.tv_sec == v_atime &&
+ d_inode(child)->i_size == 0) {
+ open->op_created = true;
+ break; /* subtle */
+ }
+ status = nfserr_exist;
+ break;
+ case NFS4_CREATE_EXCLUSIVE4_1:
+ if (d_inode(child)->i_mtime.tv_sec == v_mtime &&
+ d_inode(child)->i_atime.tv_sec == v_atime &&
+ d_inode(child)->i_size == 0) {
+ open->op_created = true;
+ goto set_attr; /* subtle */
+ }
+ status = nfserr_exist;
+ }
+ goto out;
+ }
+
+ if (!IS_POSIXACL(inode))
+ iap->ia_mode &= ~current_umask();
+
+ host_err = vfs_create(&init_user_ns, inode, child, iap->ia_mode, true);
+ if (host_err < 0) {
+ status = nfserrno(host_err);
+ goto out;
+ }
+ open->op_created = true;
+
+ /* A newly created file already has a file size of zero. */
+ if ((iap->ia_valid & ATTR_SIZE) && (iap->ia_size == 0))
+ iap->ia_valid &= ~ATTR_SIZE;
+ if (nfsd4_create_is_exclusive(open->op_createmode)) {
+ iap->ia_valid = ATTR_MTIME | ATTR_ATIME |
+ ATTR_MTIME_SET|ATTR_ATIME_SET;
+ iap->ia_mtime.tv_sec = v_mtime;
+ iap->ia_atime.tv_sec = v_atime;
+ iap->ia_mtime.tv_nsec = 0;
+ iap->ia_atime.tv_nsec = 0;
+ }
+
+set_attr:
+ status = nfsd_create_setattr(rqstp, fhp, resfhp, iap);
+
+out:
+ fh_unlock(fhp);
+ if (child && !IS_ERR(child))
+ dput(child);
+ fh_drop_write(fhp);
+ return status;
+}
+
static __be32
do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open, struct svc_fh **resfh)
{
@@ -264,16 +414,8 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru
* yes | yes | GUARDED4 | GUARDED4
*/
- /*
- * Note: create modes (UNCHECKED,GUARDED...) are the same
- * in NFSv4 as in v3 except EXCLUSIVE4_1.
- */
current->fs->umask = open->op_umask;
- status = do_nfsd_create(rqstp, current_fh, open->op_fname,
- open->op_fnamelen, &open->op_iattr,
- *resfh, open->op_createmode,
- (u32 *)open->op_verf.data,
- &open->op_truncate, &open->op_created);
+ status = nfsd4_create_file(rqstp, current_fh, *resfh, open);
current->fs->umask = 0;
if (!status && open->op_label.len)
@@ -284,7 +426,7 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru
* use the returned bitmask to indicate which attributes
* we used to store the verifier:
*/
- if (nfsd_create_is_exclusive(open->op_createmode) && status == 0)
+ if (nfsd4_create_is_exclusive(open->op_createmode) && status == 0)
open->op_bmval[1] |= (FATTR4_WORD1_TIME_ACCESS |
FATTR4_WORD1_TIME_MODIFY);
} else
