Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull second set of VFS changes from Al Viro:
 "Assorted f_pos race fixes, making do_splice_direct() safe to call with
  i_mutex on parent, O_TMPFILE support, Jeff's locks.c series,
  ->d_hash/->d_compare calling conventions changes from Linus, misc
  stuff all over the place."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (63 commits)
  Document ->tmpfile()
  ext4: ->tmpfile() support
  vfs: export lseek_execute() to modules
  lseek_execute() doesn't need an inode passed to it
  block_dev: switch to fixed_size_llseek()
  cpqphp_sysfs: switch to fixed_size_llseek()
  tile-srom: switch to fixed_size_llseek()
  proc_powerpc: switch to fixed_size_llseek()
  ubi/cdev: switch to fixed_size_llseek()
  pci/proc: switch to fixed_size_llseek()
  isapnp: switch to fixed_size_llseek()
  lpfc: switch to fixed_size_llseek()
  locks: give the blocked_hash its own spinlock
  locks: add a new "lm_owner_key" lock operation
  locks: turn the blocked_list into a hashtable
  locks: convert fl_link to a hlist_node
  locks: avoid taking global lock if possible when waking up blocked waiters
  locks: protect most of the file_lock handling with i_lock
  locks: encapsulate the fl_link list handling
  locks: make "added" in __posix_lock_file a bool
  ...

2 files changed, 37 insertions, 22 deletions

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 9858f337529c..fe7afe225381 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -11,10 +11,8 @@ be able to use diff(1).
 prototypes:
         int (*d_revalidate)(struct dentry *, unsigned int);
         int (*d_weak_revalidate)(struct dentry *, unsigned int);
-        int (*d_hash)(const struct dentry *, const struct inode *,
-                        struct qstr *);
-        int (*d_compare)(const struct dentry *, const struct inode *,
-                        const struct dentry *, const struct inode *,
+        int (*d_hash)(const struct dentry *, struct qstr *);
+        int (*d_compare)(const struct dentry *, const struct dentry *,
                         unsigned int, const char *, const struct qstr *);
         int (*d_delete)(struct dentry *);
         void (*d_release)(struct dentry *);
@@ -66,6 +64,7 @@ prototypes:
         int (*atomic_open)(struct inode *, struct dentry *,
                                 struct file *, unsigned open_flag,
                                 umode_t create_mode, int *opened);
+        int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 
 locking rules:
         all may block
@@ -93,6 +92,7 @@ removexattr:	yes
 fiemap:         no
 update_time:    no
 atomic_open:    yes
+tmpfile:        no
 
         Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
 victim.
@@ -344,25 +344,38 @@ prototypes:
 
 
 locking rules:
-                        file_lock_lock  may block
+                        inode->i_lock   may block
 fl_copy_lock:           yes             no
 fl_release_private:     maybe           no
 
 ----------------------- lock_manager_operations ---------------------------
 prototypes:
         int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
+        unsigned long (*lm_owner_key)(struct file_lock *);
         void (*lm_notify)(struct file_lock *);  /* unblock callback */
         int (*lm_grant)(struct file_lock *, struct file_lock *, int);
         void (*lm_break)(struct file_lock *); /* break_lease callback */
         int (*lm_change)(struct file_lock **, int);
 
 locking rules:
-                        file_lock_lock  may block
-lm_compare_owner:       yes             no
-lm_notify:              yes             no
-lm_grant:               no              no
-lm_break:               yes             no
-lm_change               yes             no
+
+                        inode->i_lock   blocked_lock_lock       may block
+lm_compare_owner:       yes[1]          maybe                   no
+lm_owner_key            yes[1]          yes                     no
+lm_notify:              yes             yes                     no
+lm_grant:               no              no                      no
+lm_break:               yes             no                      no
+lm_change               yes             no                      no
+
+[1]:    ->lm_compare_owner and ->lm_owner_key are generally called with
+*an* inode->i_lock held. It may not be the i_lock of the inode
+associated with either file_lock argument! This is the case with deadlock
+detection, since the code has to chase down the owners of locks that may
+be entirely unrelated to the one on which the lock is being acquired.
+For deadlock detection however, the blocked_lock_lock is also held. The
+fact that these locks are held ensures that the file_locks do not
+disappear out from under you while doing the comparison or generating an
+owner key.
 
 --------------------------- buffer_head -----------------------------------
 prototypes:
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index e6bd1ffd821e..1f0ba30ae47e 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -360,6 +360,8 @@ struct inode_operations {
         int (*removexattr) (struct dentry *, const char *);
         void (*update_time)(struct inode *, struct timespec *, int);
         int (*atomic_open)(struct inode *, struct dentry *,
+        int (*tmpfile) (struct inode *, struct dentry *, umode_t);
+} ____cacheline_aligned;
                                 struct file *, unsigned open_flag,
                                 umode_t create_mode, int *opened);
 };
@@ -472,6 +474,9 @@ otherwise noted.
         component is negative or needs lookup.  Cached positive dentries are
         still handled by f_op->open().
 
+  tmpfile: called in the end of O_TMPFILE open().  Optional, equivalent to
+        atomically creating, opening and unlinking a file in given directory.
+
 The Address Space Object
 ========================
 
@@ -901,10 +906,8 @@ defined:
 struct dentry_operations {
         int (*d_revalidate)(struct dentry *, unsigned int);
         int (*d_weak_revalidate)(struct dentry *, unsigned int);
-        int (*d_hash)(const struct dentry *, const struct inode *,
-                        struct qstr *);
-        int (*d_compare)(const struct dentry *, const struct inode *,
-                        const struct dentry *, const struct inode *,
+        int (*d_hash)(const struct dentry *, struct qstr *);
+        int (*d_compare)(const struct dentry *, const struct dentry *,
                         unsigned int, const char *, const struct qstr *);
         int (*d_delete)(const struct dentry *);
         void (*d_release)(struct dentry *);
@@ -949,25 +952,24 @@ struct dentry_operations {
 
   d_hash: called when the VFS adds a dentry to the hash table. The first
         dentry passed to d_hash is the parent directory that the name is
-        to be hashed into. The inode is the dentry's inode.
+        to be hashed into.
 
         Same locking and synchronisation rules as d_compare regarding
         what is safe to dereference etc.
 
   d_compare: called to compare a dentry name with a given name. The first
         dentry is the parent of the dentry to be compared, the second is
-        the parent's inode, then the dentry and inode (may be NULL) of the
-        child dentry. len and name string are properties of the dentry to be
-        compared. qstr is the name to compare it with.
+        the child dentry. len and name string are properties of the dentry
+        to be compared. qstr is the name to compare it with.
 
         Must be constant and idempotent, and should not take locks if
-        possible, and should not or store into the dentry or inodes.
-        Should not dereference pointers outside the dentry or inodes without
+        possible, and should not or store into the dentry.
+        Should not dereference pointers outside the dentry without
         lots of care (eg.  d_parent, d_inode, d_name should not be used).
 
         However, our vfsmount is pinned, and RCU held, so the dentries and
         inodes won't disappear, neither will our sb or filesystem module.
-        ->i_sb and ->d_sb may be used.
+        ->d_sb may be used.
 
         It is a tricky calling convention because it needs to be called under
         "rcu-walk", ie. without any locks or references on things.