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
  ...

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:

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.

arch/alpha/include/uapi/asm/fcntl.h

@@ -32,6 +32,7 @@
 #define O_SYNC		(__O_SYNC|O_DSYNC)
 
 #define O_PATH		040000000
+#define O_TMPFILE	0100000000
 
 #define F_GETLK		7
 #define F_SETLK		8

arch/arc/kernel/troubleshoot.c

@@ -101,7 +101,7 @@ static void show_faulting_vma(unsigned long address, char *buf)
 		if (file) {
 			struct path *path = &file->f_path;
 			nm = d_path(path, buf, PAGE_SIZE - 1);
-			inode = vma->vm_file->f_path.dentry->d_inode;
+			inode = file_inode(vma->vm_file);
 			dev = inode->i_sb->s_dev;
 			ino = inode->i_ino;
 		}

arch/parisc/include/uapi/asm/fcntl.h

@@ -20,6 +20,7 @@
 #define O_INVISIBLE	004000000 /* invisible I/O, for DMAPI/XDSM */
 
 #define O_PATH		020000000
+#define O_TMPFILE	040000000
 
 #define F_GETLK64	8
 #define F_SETLK64	9

arch/powerpc/kernel/proc_powerpc.c

@@ -29,25 +29,9 @@
 
 #ifdef CONFIG_PPC64
 
-static loff_t page_map_seek( struct file *file, loff_t off, int whence)
+static loff_t page_map_seek(struct file *file, loff_t off, int whence)
 {
-	loff_t new;
-	switch(whence) {
-	case 0:
-		new = off;
-		break;
-	case 1:
-		new = file->f_pos + off;
-		break;
-	case 2:
-		new = PAGE_SIZE + off;
-		break;
-	default:
-		return -EINVAL;
-	}
-	if ( new < 0 || new > PAGE_SIZE )
-		return -EINVAL;
-	return (file->f_pos = new);
+	return fixed_size_llseek(file, off, whence, PAGE_SIZE);
 }
 
 static ssize_t page_map_read( struct file *file, char __user *buf, size_t nbytes,

arch/sparc/include/uapi/asm/fcntl.h

@@ -35,6 +35,7 @@
 #define O_SYNC		(__O_SYNC|O_DSYNC)
 
 #define O_PATH		0x1000000
+#define O_TMPFILE	0x2000000
 
 #define F_GETOWN	5	/*  for sockets. */
 #define F_SETOWN	6	/*  for sockets. */

drivers/char/ps3flash.c

@@ -98,32 +98,8 @@ static int ps3flash_fetch(struct ps3_storage_device *dev, u64 start_sector)
 static loff_t ps3flash_llseek(struct file *file, loff_t offset, int origin)
 {
 	struct ps3_storage_device *dev = ps3flash_dev;
-	loff_t res;
-
-	mutex_lock(&file->f_mapping->host->i_mutex);
-	switch (origin) {
-	case 0:
-		break;
-	case 1:
-		offset += file->f_pos;
-		break;
-	case 2:
-		offset += dev->regions[dev->region_idx].size*dev->blk_size;
-		break;
-	default:
-		offset = -1;
-	}
-	if (offset < 0) {
-		res = -EINVAL;
-		goto out;
-	}
-
-	file->f_pos = offset;
-	res = file->f_pos;
-
-out:
-	mutex_unlock(&file->f_mapping->host->i_mutex);
-	return res;
+	return generic_file_llseek_size(file, offset, origin, MAX_LFS_FILESIZE,
+			dev->regions[dev->region_idx].size*dev->blk_size);
 }
 
 static ssize_t ps3flash_read(char __user *userbuf, void *kernelbuf,

drivers/char/tile-srom.c

@@ -273,32 +273,10 @@ static ssize_t srom_write(struct file *filp, const char __user *buf,
 }
 
 /* Provide our own implementation so we can use srom->total_size. */
-loff_t srom_llseek(struct file *filp, loff_t offset, int origin)
+loff_t srom_llseek(struct file *file, loff_t offset, int origin)
 {
-	struct srom_dev *srom = filp->private_data;
-
-	if (mutex_lock_interruptible(&srom->lock))
-		return -ERESTARTSYS;
-
-	switch (origin) {
-	case SEEK_END:
-		offset += srom->total_size;
-		break;
-	case SEEK_CUR:
-		offset += filp->f_pos;
-		break;
-	}
-
-	if (offset < 0 || offset > srom->total_size) {
-		offset = -EINVAL;
-	} else {
-		filp->f_pos = offset;
-		filp->f_version = 0;
-	}
-
-	mutex_unlock(&srom->lock);
-
-	return offset;
+	struct srom_dev *srom = file->private_data;
+	return fixed_size_llseek(file, offset, origin, srom->total_size);
 }
 
 static ssize_t total_show(struct device *dev,

drivers/mtd/mtdchar.c

@@ -55,25 +55,7 @@ struct mtd_file_info {
 static loff_t mtdchar_lseek(struct file *file, loff_t offset, int orig)
 {
 	struct mtd_file_info *mfi = file->private_data;
-	struct mtd_info *mtd = mfi->mtd;
-
-	switch (orig) {
-	case SEEK_SET:
-		break;
-	case SEEK_CUR:
-		offset += file->f_pos;
-		break;
-	case SEEK_END:
-		offset += mtd->size;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (offset >= 0 && offset <= mtd->size)
-		return file->f_pos = offset;
-
-	return -EINVAL;
+	return fixed_size_llseek(file, offset, orig, mfi->mtd->size);
 }
 
 static int count;

drivers/mtd/ubi/cdev.c

@@ -155,38 +155,14 @@ static loff_t vol_cdev_llseek(struct file *file, loff_t offset, int origin)
 {
 	struct ubi_volume_desc *desc = file->private_data;
 	struct ubi_volume *vol = desc->vol;
-	loff_t new_offset;
 
 	if (vol->updating) {
 		/* Update is in progress, seeking is prohibited */
 		ubi_err("updating");
 		return -EBUSY;
 	}
 
-	switch (origin) {
-	case 0: /* SEEK_SET */
-		new_offset = offset;
-		break;
-	case 1: /* SEEK_CUR */
-		new_offset = file->f_pos + offset;
-		break;
-	case 2: /* SEEK_END */
-		new_offset = vol->used_bytes + offset;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (new_offset < 0 || new_offset > vol->used_bytes) {
-		ubi_err("bad seek %lld", new_offset);
-		return -EINVAL;
-	}
-
-	dbg_gen("seek volume %d, offset %lld, origin %d, new offset %lld",
-		vol->vol_id, offset, origin, new_offset);
-
-	file->f_pos = new_offset;
-	return new_offset;
+	return fixed_size_llseek(file, offset, origin, vol->used_bytes);
 }
 
 static int vol_cdev_fsync(struct file *file, loff_t start, loff_t end,

drivers/net/ethernet/brocade/bna/bnad_debugfs.c

@@ -230,32 +230,12 @@ bnad_debugfs_open_drvinfo(struct inode *inode, struct file *file)
 static loff_t
 bnad_debugfs_lseek(struct file *file, loff_t offset, int orig)
 {
-	loff_t pos = file->f_pos;
 	struct bnad_debug_info *debug = file->private_data;
 
 	if (!debug)
 		return -EINVAL;
 
-	switch (orig) {
-	case 0:
-		file->f_pos = offset;
-		break;
-	case 1:
-		file->f_pos += offset;
-		break;
-	case 2:
-		file->f_pos = debug->buffer_len + offset;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (file->f_pos < 0 || file->f_pos > debug->buffer_len) {
-		file->f_pos = pos;
-		return -EINVAL;
-	}
-
-	return file->f_pos;
+	return fixed_size_llseek(file, offset, orig, debug->buffer_len);
 }
 
 static ssize_t

drivers/net/wireless/ti/wlcore/debugfs.c

@@ -1056,7 +1056,7 @@ static ssize_t dev_mem_read(struct file *file,
 		return -EINVAL;
 
 	memset(&part, 0, sizeof(part));
-	part.mem.start = file->f_pos;
+	part.mem.start = *ppos;
 	part.mem.size = bytes;
 
 	buf = kmalloc(bytes, GFP_KERNEL);
@@ -1137,7 +1137,7 @@ static ssize_t dev_mem_write(struct file *file, const char __user *user_buf,
 		return -EINVAL;
 
 	memset(&part, 0, sizeof(part));
-	part.mem.start = file->f_pos;
+	part.mem.start = *ppos;
 	part.mem.size = bytes;
 
 	buf = kmalloc(bytes, GFP_KERNEL);