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, 76 insertions, 22 deletions

diff --git a/include/linux/filelock.h b/include/linux/filelock.h
index c2ce8ba05d06..54b824c05299 100644
--- a/include/linux/filelock.h
+++ b/include/linux/filelock.h
@@ -159,6 +159,8 @@ int fcntl_setlk64(unsigned int, struct file *, unsigned int,
 
 int fcntl_setlease(unsigned int fd, struct file *filp, int arg);
 int fcntl_getlease(struct file *filp);
+int fcntl_setdeleg(unsigned int fd, struct file *filp, struct delegation *deleg);
+int fcntl_getdeleg(struct file *filp, struct delegation *deleg);
 
 static inline bool lock_is_unlock(struct file_lock *fl)
 {
@@ -212,7 +214,14 @@ int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl);
 void locks_init_lease(struct file_lease *);
 void locks_free_lease(struct file_lease *fl);
 struct file_lease *locks_alloc_lease(void);
-int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
+
+#define LEASE_BREAK_LEASE		BIT(0)	// break leases and delegations
+#define LEASE_BREAK_DELEG		BIT(1)	// break delegations only
+#define LEASE_BREAK_LAYOUT		BIT(2)	// break layouts only
+#define LEASE_BREAK_NONBLOCK		BIT(3)	// non-blocking break
+#define LEASE_BREAK_OPEN_RDONLY		BIT(4)	// readonly open event
+
+int __break_lease(struct inode *inode, unsigned int flags);
 void lease_get_mtime(struct inode *, struct timespec64 *time);
 int generic_setlease(struct file *, int, struct file_lease **, void **priv);
 int kernel_setlease(struct file *, int, struct file_lease **, void **);
@@ -271,6 +280,16 @@ static inline int fcntl_getlease(struct file *filp)
 	return F_UNLCK;
 }
 
+static inline int fcntl_setdeleg(unsigned int fd, struct file *filp, struct delegation *deleg)
+{
+	return -EINVAL;
+}
+
+static inline int fcntl_getdeleg(struct file *filp, struct delegation *deleg)
+{
+	return -EINVAL;
+}
+
 static inline bool lock_is_unlock(struct file_lock *fl)
 {
 	return false;
@@ -367,7 +386,7 @@ static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *f
 	return -ENOLCK;
 }
 
-static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
+static inline int __break_lease(struct inode *inode, unsigned int flags)
 {
 	return 0;
 }
@@ -428,6 +447,17 @@ static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
 }
 
 #ifdef CONFIG_FILE_LOCKING
+static inline unsigned int openmode_to_lease_flags(unsigned int mode)
+{
+	unsigned int flags = 0;
+
+	if ((mode & O_ACCMODE) == O_RDONLY)
+		flags |= LEASE_BREAK_OPEN_RDONLY;
+	if (mode & O_NONBLOCK)
+		flags |= LEASE_BREAK_NONBLOCK;
+	return flags;
+}
+
 static inline int break_lease(struct inode *inode, unsigned int mode)
 {
 	struct file_lock_context *flctx;
@@ -443,11 +473,11 @@ static inline int break_lease(struct inode *inode, unsigned int mode)
 		return 0;
 	smp_mb();
 	if (!list_empty_careful(&flctx->flc_lease))
-		return __break_lease(inode, mode, FL_LEASE);
+		return __break_lease(inode, LEASE_BREAK_LEASE | openmode_to_lease_flags(mode));
 	return 0;
 }
 
-static inline int break_deleg(struct inode *inode, unsigned int mode)
+static inline int break_deleg(struct inode *inode, unsigned int flags)
 {
 	struct file_lock_context *flctx;
 
@@ -461,60 +491,84 @@ static inline int break_deleg(struct inode *inode, unsigned int mode)
 	if (!flctx)
 		return 0;
 	smp_mb();
-	if (!list_empty_careful(&flctx->flc_lease))
-		return __break_lease(inode, mode, FL_DELEG);
+	if (!list_empty_careful(&flctx->flc_lease)) {
+		flags |= LEASE_BREAK_DELEG;
+		return __break_lease(inode, flags);
+	}
 	return 0;
 }
 
-static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode)
+struct delegated_inode {
+	struct inode *di_inode;
+};
+
+static inline bool is_delegated(struct delegated_inode *di)
+{
+	return di->di_inode;
+}
+
+static inline int try_break_deleg(struct inode *inode,
+				  struct delegated_inode *di)
 {
 	int ret;
 
-	ret = break_deleg(inode, O_WRONLY|O_NONBLOCK);
-	if (ret == -EWOULDBLOCK && delegated_inode) {
-		*delegated_inode = inode;
+	ret = break_deleg(inode, LEASE_BREAK_NONBLOCK);
+	if (ret == -EWOULDBLOCK && di) {
+		di->di_inode = inode;
 		ihold(inode);
 	}
 	return ret;
 }
 
-static inline int break_deleg_wait(struct inode **delegated_inode)
+static inline int break_deleg_wait(struct delegated_inode *di)
 {
 	int ret;
 
-	ret = break_deleg(*delegated_inode, O_WRONLY);
-	iput(*delegated_inode);
-	*delegated_inode = NULL;
+	ret = break_deleg(di->di_inode, 0);
+	iput(di->di_inode);
+	di->di_inode = NULL;
 	return ret;
 }
 
 static inline int break_layout(struct inode *inode, bool wait)
 {
 	smp_mb();
-	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
-		return __break_lease(inode,
-				wait ? O_WRONLY : O_WRONLY | O_NONBLOCK,
-				FL_LAYOUT);
+	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) {
+		unsigned int flags = LEASE_BREAK_LAYOUT;
+
+		if (!wait)
+			flags |= LEASE_BREAK_NONBLOCK;
+
+		return __break_lease(inode, flags);
+	}
 	return 0;
 }
 
 #else /* !CONFIG_FILE_LOCKING */
-static inline int break_lease(struct inode *inode, unsigned int mode)
+struct delegated_inode { };
+
+static inline bool is_delegated(struct delegated_inode *di)
+{
+	return false;
+}
+
+static inline int break_lease(struct inode *inode, bool wait)
 {
 	return 0;
 }
 
-static inline int break_deleg(struct inode *inode, unsigned int mode)
+static inline int break_deleg(struct inode *inode, unsigned int flags)
 {
 	return 0;
 }
 
-static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode)
+static inline int try_break_deleg(struct inode *inode,
+				  struct delegated_inode *delegated_inode)
 {
 	return 0;
 }
 
-static inline int break_deleg_wait(struct inode **delegated_inode)
+static inline int break_deleg_wait(struct delegated_inode *delegated_inode)
 {
 	BUG();
 	return 0;