Merge tag 'vfs-6.19-rc1.directory.delegations' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull directory delegations update from Christian Brauner:
 "This contains the work for recall-only directory delegations for
  knfsd.

  Add support for simple, recallable-only directory delegations. This
  was decided at the fall NFS Bakeathon where the NFS client and server
  maintainers discussed how to merge directory delegation support.

  The approach starts with recallable-only delegations for several reasons:

   1. RFC8881 has gaps that are being addressed in RFC8881bis. In
      particular, it requires directory position information for
      CB_NOTIFY callbacks, which is difficult to implement properly
      under Linux. The spec is being extended to allow that information
      to be omitted.

   2. Client-side support for CB_NOTIFY still lags. The client side
      involves heuristics about when to request a delegation.

   3. Early indication shows simple, recallable-only delegations can
      help performance. Anna Schumaker mentioned seeing a multi-minute
      speedup in xfstests runs with them enabled.

  With these changes, userspace can also request a read lease on a
  directory that will be recalled on conflicting accesses. This may be
  useful for applications like Samba. Users can disable leases
  altogether via the fs.leases-enable sysctl if needed.

  VFS changes:

   - Dedicated Type for Delegations

     Introduce struct delegated_inode to track inodes that may have
     delegations that need to be broken. This replaces the previous
     approach of passing raw inode pointers through the delegation
     breaking code paths, providing better type safety and clearer
     semantics for the delegation machinery.

   - Break parent directory delegations in open(..., O_CREAT) codepath

   - Allow mkdir to wait for delegation break on parent

   - Allow rmdir to wait for delegation break on parent

   - Add try_break_deleg calls for parents to vfs_link(), vfs_rename(),
     and vfs_unlink()

   - Make vfs_create(), vfs_mknod(), and vfs_symlink() break delegations
     on parent directory

   - Clean up argument list for vfs_create()

   - Expose delegation support to userland

  Filelock changes:

   - Make lease_alloc() take a flags argument

   - Rework the __break_lease API to use flags

   - Add struct delegated_inode

   - Push the S_ISREG check down to ->setlease handlers

   - Lift the ban on directory leases in generic_setlease

  NFSD changes:

   - Allow filecache to hold S_IFDIR files

   - Allow DELEGRETURN on directories

   - Wire up GET_DIR_DELEGATION handling

  Fixes:

   - Fix kernel-doc warnings in __fcntl_getlease

   - Add needed headers for new struct delegation definition"

* tag 'vfs-6.19-rc1.directory.delegations' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  vfs: add needed headers for new struct delegation definition
  filelock: __fcntl_getlease: fix kernel-doc warnings
  vfs: expose delegation support to userland
  nfsd: wire up GET_DIR_DELEGATION handling
  nfsd: allow DELEGRETURN on directories
  nfsd: allow filecache to hold S_IFDIR files
  filelock: lift the ban on directory leases in generic_setlease
  vfs: make vfs_symlink break delegations on parent dir
  vfs: make vfs_mknod break delegations on parent directory
  vfs: make vfs_create break delegations on parent directory
  vfs: clean up argument list for vfs_create()
  vfs: break parent dir delegations in open(..., O_CREAT) codepath
  vfs: allow rmdir to wait for delegation break on parent
  vfs: allow mkdir to wait for delegation break on parent
  vfs: add try_break_deleg calls for parents to vfs_{link,rename,unlink}
  filelock: push the S_ISREG check down to ->setlease handlers
  filelock: add struct delegated_inode
  filelock: rework the __break_lease API to use flags
  filelock: make lease_alloc() take a flags argument

1 files changed, 43 insertions, 14 deletions

diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index a238b6725008..93798575b807 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -1086,7 +1086,7 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net,
 		     struct auth_domain *client,
 		     struct svc_fh *fhp,
 		     unsigned int may_flags, struct file *file,
-		     struct nfsd_file **pnf, bool want_gc)
+		     umode_t type, bool want_gc, struct nfsd_file **pnf)
 {
 	unsigned char need = may_flags & NFSD_FILE_MAY_MASK;
 	struct nfsd_file *new, *nf;
@@ -1097,13 +1097,13 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net,
 	int ret;
 
 retry:
-	if (rqstp) {
-		status = fh_verify(rqstp, fhp, S_IFREG,
+	if (rqstp)
+		status = fh_verify(rqstp, fhp, type,
 				   may_flags|NFSD_MAY_OWNER_OVERRIDE);
-	} else {
-		status = fh_verify_local(net, cred, client, fhp, S_IFREG,
+	else
+		status = fh_verify_local(net, cred, client, fhp, type,
 					 may_flags|NFSD_MAY_OWNER_OVERRIDE);
-	}
+
 	if (status != nfs_ok)
 		return status;
 	inode = d_inode(fhp->fh_dentry);
@@ -1176,15 +1176,18 @@ out:
 
 open_file:
 	trace_nfsd_file_alloc(nf);
-	nf->nf_mark = nfsd_file_mark_find_or_create(inode);
-	if (nf->nf_mark) {
+
+	if (type == S_IFREG)
+		nf->nf_mark = nfsd_file_mark_find_or_create(inode);
+
+	if (type != S_IFREG || nf->nf_mark) {
 		if (file) {
 			get_file(file);
 			nf->nf_file = file;
 			status = nfs_ok;
 			trace_nfsd_file_opened(nf, status);
 		} else {
-			ret = nfsd_open_verified(fhp, may_flags, &nf->nf_file);
+			ret = nfsd_open_verified(fhp, type, may_flags, &nf->nf_file);
 			if (ret == -EOPENSTALE && stale_retry) {
 				stale_retry = false;
 				nfsd_file_unhash(nf);
@@ -1246,7 +1249,7 @@ nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		     unsigned int may_flags, struct nfsd_file **pnf)
 {
 	return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL,
-				    fhp, may_flags, NULL, pnf, true);
+				    fhp, may_flags, NULL, S_IFREG, true, pnf);
 }
 
 /**
@@ -1271,7 +1274,7 @@ nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		  unsigned int may_flags, struct nfsd_file **pnf)
 {
 	return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL,
-				    fhp, may_flags, NULL, pnf, false);
+				    fhp, may_flags, NULL, S_IFREG, false, pnf);
 }
 
 /**
@@ -1314,8 +1317,8 @@ nfsd_file_acquire_local(struct net *net, struct svc_cred *cred,
 	const struct cred *save_cred = get_current_cred();
 	__be32 beres;
 
-	beres = nfsd_file_do_acquire(NULL, net, cred, client,
-				     fhp, may_flags, NULL, pnf, false);
+	beres = nfsd_file_do_acquire(NULL, net, cred, client, fhp, may_flags,
+				     NULL, S_IFREG, false, pnf);
 	put_cred(revert_creds(save_cred));
 	return beres;
 }
@@ -1344,7 +1347,33 @@ nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			 struct nfsd_file **pnf)
 {
 	return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL,
-				    fhp, may_flags, file, pnf, false);
+				    fhp, may_flags, file, S_IFREG, false, pnf);
+}
+
+/**
+ * nfsd_file_acquire_dir - Get a struct nfsd_file with an open directory
+ * @rqstp: the RPC transaction being executed
+ * @fhp: the NFS filehandle of the file to be opened
+ * @pnf: OUT: new or found "struct nfsd_file" object
+ *
+ * The nfsd_file_object returned by this API is reference-counted
+ * but not garbage-collected. The object is unhashed after the
+ * final nfsd_file_put(). This opens directories only, and only
+ * in O_RDONLY mode.
+ *
+ * Return values:
+ *   %nfs_ok - @pnf points to an nfsd_file with its reference
+ *   count boosted.
+ *
+ * On error, an nfsstat value in network byte order is returned.
+ */
+__be32
+nfsd_file_acquire_dir(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		      struct nfsd_file **pnf)
+{
+	return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL, fhp,
+				    NFSD_MAY_READ|NFSD_MAY_64BIT_COOKIE,
+				    NULL, S_IFDIR, false, pnf);
 }
 
 /*