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

Pull second vfs pile from Al Viro:
 "The stuff in there: fsfreeze deadlock fixes by Jan (essentially, the
  deadlock reproduced by xfstests 068), symlink and hardlink restriction
  patches, plus assorted cleanups and fixes.

  Note that another fsfreeze deadlock (emergency thaw one) is *not*
  dealt with - the series by Fernando conflicts a lot with Jan's, breaks
  userland ABI (FIFREEZE semantics gets changed) and trades the deadlock
  for massive vfsmount leak; this is going to be handled next cycle.
  There probably will be another pull request, but that stuff won't be
  in it."

Fix up trivial conflicts due to unrelated changes next to each other in
drivers/{staging/gdm72xx/usb_boot.c, usb/gadget/storage_common.c}

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (54 commits)
  delousing target_core_file a bit
  Documentation: Correct s_umount state for freeze_fs/unfreeze_fs
  fs: Remove old freezing mechanism
  ext2: Implement freezing
  btrfs: Convert to new freezing mechanism
  nilfs2: Convert to new freezing mechanism
  ntfs: Convert to new freezing mechanism
  fuse: Convert to new freezing mechanism
  gfs2: Convert to new freezing mechanism
  ocfs2: Convert to new freezing mechanism
  xfs: Convert to new freezing code
  ext4: Convert to new freezing mechanism
  fs: Protect write paths by sb_start_write - sb_end_write
  fs: Skip atime update on frozen filesystem
  fs: Add freezing handling to mnt_want_write() / mnt_drop_write()
  fs: Improve filesystem freezing handling
  switch the protection of percpu_counter list to spinlock
  nfsd: Push mnt_want_write() outside of i_mutex
  btrfs: Push mnt_want_write() outside of i_mutex
  fat: Push mnt_want_write() outside of i_mutex
  ...

6 files changed, 151 insertions, 12 deletions

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 22f292a917a..36abf2aa7e6 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -130,6 +130,7 @@
 #define AUDIT_LAST_KERN_ANOM_MSG    1799
 #define AUDIT_ANOM_PROMISCUOUS      1700 /* Device changed promiscuous mode */
 #define AUDIT_ANOM_ABEND            1701 /* Process ended abnormally */
+#define AUDIT_ANOM_LINK		    1702 /* Suspicious use of file links */
 #define AUDIT_INTEGRITY_DATA	    1800 /* Data integrity verification */
 #define AUDIT_INTEGRITY_METADATA    1801 /* Metadata integrity verification */
 #define AUDIT_INTEGRITY_STATUS	    1802 /* Integrity enable status */
@@ -687,6 +688,8 @@ extern void		    audit_log_d_path(struct audit_buffer *ab,
 					     const struct path *path);
 extern void		    audit_log_key(struct audit_buffer *ab,
 					  char *key);
+extern void		    audit_log_link_denied(const char *operation,
+						  struct path *link);
 extern void		    audit_log_lost(const char *message);
 #ifdef CONFIG_SECURITY
 extern void 		    audit_log_secctx(struct audit_buffer *ab, u32 secid);
@@ -716,6 +719,7 @@ extern int audit_enabled;
 #define audit_log_untrustedstring(a,s) do { ; } while (0)
 #define audit_log_d_path(b, p, d) do { ; } while (0)
 #define audit_log_key(b, k) do { ; } while (0)
+#define audit_log_link_denied(o, l) do { ; } while (0)
 #define audit_log_secctx(b,s) do { ; } while (0)
 #define audit_enabled 0
 #endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4ba5c871552..38dba16c417 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -414,6 +414,7 @@ struct inodes_stat_t {
 #include <linux/shrinker.h>
 #include <linux/migrate_mode.h>
 #include <linux/uidgid.h>
+#include <linux/lockdep.h>
 
 #include <asm/byteorder.h>
 
@@ -440,6 +441,8 @@ extern unsigned long get_max_files(void);
 extern int sysctl_nr_open;
 extern struct inodes_stat_t inodes_stat;
 extern int leases_enable, lease_break_time;
+extern int sysctl_protected_symlinks;
+extern int sysctl_protected_hardlinks;
 
 struct buffer_head;
 typedef int (get_block_t)(struct inode *inode, sector_t iblock,
@@ -1445,6 +1448,8 @@ extern void f_delown(struct file *filp);
 extern pid_t f_getown(struct file *filp);
 extern int send_sigurg(struct fown_struct *fown);
 
+struct mm_struct;
+
 /*
  *	Umount options
  */
@@ -1458,6 +1463,31 @@ extern int send_sigurg(struct fown_struct *fown);
 extern struct list_head super_blocks;
 extern spinlock_t sb_lock;
 
+/* Possible states of 'frozen' field */
+enum {
+	SB_UNFROZEN = 0,		/* FS is unfrozen */
+	SB_FREEZE_WRITE	= 1,		/* Writes, dir ops, ioctls frozen */
+	SB_FREEZE_PAGEFAULT = 2,	/* Page faults stopped as well */
+	SB_FREEZE_FS = 3,		/* For internal FS use (e.g. to stop
+					 * internal threads if needed) */
+	SB_FREEZE_COMPLETE = 4,		/* ->freeze_fs finished successfully */
+};
+
+#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)
+
+struct sb_writers {
+	/* Counters for counting writers at each level */
+	struct percpu_counter	counter[SB_FREEZE_LEVELS];
+	wait_queue_head_t	wait;		/* queue for waiting for
+						   writers / faults to finish */
+	int			frozen;		/* Is sb frozen? */
+	wait_queue_head_t	wait_unfrozen;	/* queue for waiting for
+						   sb to be thawed */
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	lock_map[SB_FREEZE_LEVELS];
+#endif
+};
+
 struct super_block {
 	struct list_head	s_list;		/* Keep this first */
 	dev_t			s_dev;		/* search index; _not_ kdev_t */
@@ -1505,8 +1535,7 @@ struct super_block {
 	struct hlist_node	s_instances;
 	struct quota_info	s_dquot;	/* Diskquota specific options */
 
-	int			s_frozen;
-	wait_queue_head_t	s_wait_unfrozen;
+	struct sb_writers	s_writers;
 
 	char s_id[32];				/* Informational name */
 	u8 s_uuid[16];				/* UUID */
@@ -1561,14 +1590,117 @@ extern struct timespec current_fs_time(struct super_block *sb);
 /*
  * Snapshotting support.
  */
-enum {
-	SB_UNFROZEN = 0,
-	SB_FREEZE_WRITE	= 1,
-	SB_FREEZE_TRANS = 2,
-};
 
-#define vfs_check_frozen(sb, level) \
-	wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level)))
+void __sb_end_write(struct super_block *sb, int level);
+int __sb_start_write(struct super_block *sb, int level, bool wait);
+
+/**
+ * sb_end_write - drop write access to a superblock
+ * @sb: the super we wrote to
+ *
+ * Decrement number of writers to the filesystem. Wake up possible waiters
+ * wanting to freeze the filesystem.
+ */
+static inline void sb_end_write(struct super_block *sb)
+{
+	__sb_end_write(sb, SB_FREEZE_WRITE);
+}
+
+/**
+ * sb_end_pagefault - drop write access to a superblock from a page fault
+ * @sb: the super we wrote to
+ *
+ * Decrement number of processes handling write page fault to the filesystem.
+ * Wake up possible waiters wanting to freeze the filesystem.
+ */
+static inline void sb_end_pagefault(struct super_block *sb)
+{
+	__sb_end_write(sb, SB_FREEZE_PAGEFAULT);
+}
+
+/**
+ * sb_end_intwrite - drop write access to a superblock for internal fs purposes
+ * @sb: the super we wrote to
+ *
+ * Decrement fs-internal number of writers to the filesystem.  Wake up possible
+ * waiters wanting to freeze the filesystem.
+ */
+static inline void sb_end_intwrite(struct super_block *sb)
+{
+	__sb_end_write(sb, SB_FREEZE_FS);
+}
+
+/**
+ * sb_start_write - get write access to a superblock
+ * @sb: the super we write to
+ *
+ * When a process wants to write data or metadata to a file system (i.e. dirty
+ * a page or an inode), it should embed the operation in a sb_start_write() -
+ * sb_end_write() pair to get exclusion against file system freezing. This
+ * function increments number of writers preventing freezing. If the file
+ * system is already frozen, the function waits until the file system is
+ * thawed.
+ *
+ * Since freeze protection behaves as a lock, users have to preserve
+ * ordering of freeze protection and other filesystem locks. Generally,
+ * freeze protection should be the outermost lock. In particular, we have:
+ *
+ * sb_start_write
+ *   -> i_mutex			(write path, truncate, directory ops, ...)
+ *   -> s_umount		(freeze_super, thaw_super)
+ */
+static inline void sb_start_write(struct super_block *sb)
+{
+	__sb_start_write(sb, SB_FREEZE_WRITE, true);
+}
+
+static inline int sb_start_write_trylock(struct super_block *sb)
+{
+	return __sb_start_write(sb, SB_FREEZE_WRITE, false);
+}
+
+/**
+ * sb_start_pagefault - get write access to a superblock from a page fault
+ * @sb: the super we write to
+ *
+ * When a process starts handling write page fault, it should embed the
+ * operation into sb_start_pagefault() - sb_end_pagefault() pair to get
+ * exclusion against file system freezing. This is needed since the page fault
+ * is going to dirty a page. This function increments number of running page
+ * faults preventing freezing. If the file system is already frozen, the
+ * function waits until the file system is thawed.
+ *
+ * Since page fault freeze protection behaves as a lock, users have to preserve
+ * ordering of freeze protection and other filesystem locks. It is advised to
+ * put sb_start_pagefault() close to mmap_sem in lock ordering. Page fault
+ * handling code implies lock dependency:
+ *
+ * mmap_sem
+ *   -> sb_start_pagefault
+ */
+static inline void sb_start_pagefault(struct super_block *sb)
+{
+	__sb_start_write(sb, SB_FREEZE_PAGEFAULT, true);
+}
+
+/*
+ * sb_start_intwrite - get write access to a superblock for internal fs purposes
+ * @sb: the super we write to
+ *
+ * This is the third level of protection against filesystem freezing. It is
+ * free for use by a filesystem. The only requirement is that it must rank
+ * below sb_start_pagefault.
+ *
+ * For example filesystem can call sb_start_intwrite() when starting a
+ * transaction which somewhat eases handling of freezing for internal sources
+ * of filesystem changes (internal fs threads, discarding preallocation on file
+ * close, etc.).
+ */
+static inline void sb_start_intwrite(struct super_block *sb)
+{
+	__sb_start_write(sb, SB_FREEZE_FS, true);
+}
+
 
 extern bool inode_owner_or_capable(const struct inode *inode);
 
@@ -1892,6 +2024,7 @@ struct file_system_type {
 	struct lock_class_key s_lock_key;
 	struct lock_class_key s_umount_key;
 	struct lock_class_key s_vfs_rename_key;
+	struct lock_class_key s_writers_key[SB_FREEZE_LEVELS];
 
 	struct lock_class_key i_lock_key;
 	struct lock_class_key i_mutex_key;
@@ -2334,9 +2467,6 @@ static inline void i_readcount_inc(struct inode *inode)
 }
 #endif
 extern int do_pipe_flags(int *, int);
-extern struct file *create_read_pipe(struct file *f, int flags);
-extern struct file *create_write_pipe(int flags);
-extern void free_write_pipe(struct file *);
 
 extern int kernel_read(struct file *, loff_t, char *, unsigned long);
 extern struct file * open_exec(const char *);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bd079a1b0fd..311be906b57 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1441,6 +1441,7 @@ extern void truncate_inode_pages_range(struct address_space *,
 
 /* generic vm_area_ops exported for stackable file systems */
 extern int filemap_fault(struct vm_area_struct *, struct vm_fault *);
+extern int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 
 /* mm/page-writeback.c */
 int write_one_page(struct page *page, int wait);
diff --git a/include/linux/namei.h b/include/linux/namei.h
index d2ef8b34b96..4bf19d8174e 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -67,6 +67,7 @@ extern int kern_path(const char *, unsigned, struct path *);
 
 extern struct dentry *kern_path_create(int, const char *, struct path *, int);
 extern struct dentry *user_path_create(int, const char __user *, struct path *, int);
+extern void done_path_create(struct path *, struct dentry *);
 extern struct dentry *kern_path_locked(const char *, struct path *);
 extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 			   const char *, unsigned int, struct path *);
diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h
index ce4743a2601..fa63048fecf 100644
--- a/include/linux/nfsd/nfsfh.h
+++ b/include/linux/nfsd/nfsfh.h
@@ -143,6 +143,7 @@ typedef struct svc_fh {
 	int			fh_maxsize;	/* max size for fh_handle */
 
 	unsigned char		fh_locked;	/* inode locked by us */
+	unsigned char		fh_want_write;	/* remount protection taken */
 
 #ifdef CONFIG_NFSD_V3
 	unsigned char		fh_post_saved;	/* post-op attrs saved */
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index e11d1c0fc60..ad1a427b526 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -160,4 +160,6 @@ void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
 long pipe_fcntl(struct file *, unsigned int, unsigned long arg);
 struct pipe_inode_info *get_pipe_info(struct file *file);
 
+int create_pipe_files(struct file **, int);
+
 #endif