Merge tag 'v4.0-rc1' into patchwork

Linux 34.0-rc1

* tag 'v4.0-rc1': (8947 commits)
  Linux 4.0-rc1
  autofs4 copy_dev_ioctl(): keep the value of ->size we'd used for allocation
  procfs: fix race between symlink removals and traversals
  debugfs: leave freeing a symlink body until inode eviction
  Documentation/filesystems/Locking: ->get_sb() is long gone
  trylock_super(): replacement for grab_super_passive()
  fanotify: Fix up scripted S_ISDIR/S_ISREG/S_ISLNK conversions
  Cachefiles: Fix up scripted S_ISDIR/S_ISREG/S_ISLNK conversions
  VFS: (Scripted) Convert S_ISLNK/DIR/REG(dentry->d_inode) to d_is_*(dentry)
  SELinux: Use d_is_positive() rather than testing dentry->d_inode
  Smack: Use d_is_positive() rather than testing dentry->d_inode
  TOMOYO: Use d_is_dir() rather than d_inode and S_ISDIR()
  Apparmor: Use d_is_positive/negative() rather than testing dentry->d_inode
  Apparmor: mediated_filesystem() should use dentry->d_sb not inode->i_sb
  VFS: Split DCACHE_FILE_TYPE into regular and special types
  VFS: Add a fallthrough flag for marking virtual dentries
  VFS: Add a whiteout dentry type
  VFS: Introduce inode-getting helpers for layered/unioned fs environments
  kernel: make READ_ONCE() valid on const arguments
  blk-throttle: check stats_cpu before reading it from sysfs
  ...

1 files changed, 112 insertions, 49 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 42efe13077b6..b4d71b5e1ff2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -34,6 +34,7 @@
 #include <asm/byteorder.h>
 #include <uapi/linux/fs.h>
 
+struct backing_dev_info;
 struct export_operations;
 struct hd_geometry;
 struct iovec;
@@ -50,6 +51,7 @@ struct swap_info_struct;
 struct seq_file;
 struct workqueue_struct;
 struct iov_iter;
+struct vm_fault;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -360,8 +362,6 @@ struct address_space_operations {
         int (*releasepage) (struct page *, gfp_t);
         void (*freepage)(struct page *);
         ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
-        int (*get_xip_mem)(struct address_space *, pgoff_t, int,
-                                                void **, unsigned long *);
         /*
          * migrate the contents of a page to the specified target. If
          * migrate_mode is MIGRATE_ASYNC, it must not block.
@@ -394,14 +394,12 @@ int pagecache_write_end(struct file *, struct address_space *mapping,
                                 loff_t pos, unsigned len, unsigned copied,
                                 struct page *page, void *fsdata);
 
-struct backing_dev_info;
 struct address_space {
         struct inode            *host;          /* owner: inode, block_device */
         struct radix_tree_root  page_tree;      /* radix tree of all pages */
         spinlock_t              tree_lock;      /* and lock protecting it */
         atomic_t                i_mmap_writable;/* count VM_SHARED mappings */
         struct rb_root          i_mmap;         /* tree of private and shared mappings */
-        struct list_head        i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
         struct rw_semaphore     i_mmap_rwsem;   /* protect tree, count, list */
         /* Protected by tree_lock together with the radix tree */
         unsigned long           nrpages;        /* number of total pages */
@@ -409,7 +407,6 @@ struct address_space {
         pgoff_t                 writeback_index;/* writeback starts here */
         const struct address_space_operations *a_ops;   /* methods */
         unsigned long           flags;          /* error bits/gfp mask */
-        struct backing_dev_info *backing_dev_info; /* device readahead, etc */
         spinlock_t              private_lock;   /* for use by the address_space */
         struct list_head        private_list;   /* ditto */
         void                    *private_data;  /* ditto */
@@ -493,8 +490,7 @@ static inline void i_mmap_unlock_read(struct address_space *mapping)
  */
 static inline int mapping_mapped(struct address_space *mapping)
 {
-        return  !RB_EMPTY_ROOT(&mapping->i_mmap) ||
-                !list_empty(&mapping->i_mmap_nonlinear);
+        return  !RB_EMPTY_ROOT(&mapping->i_mmap);
 }
 
 /*
@@ -625,7 +621,7 @@ struct inode {
         atomic_t                i_readcount; /* struct files open RO */
 #endif
         const struct file_operations    *i_fop; /* former ->i_op->default_file_ops */
-        struct file_lock        *i_flock;
+        struct file_lock_context        *i_flctx;
         struct address_space    i_data;
         struct list_head        i_devices;
         union {
@@ -875,6 +871,7 @@ static inline struct file *get_file(struct file *f)
 #define FL_DOWNGRADE_PENDING    256 /* Lease is being downgraded */
 #define FL_UNLOCK_PENDING       512 /* Lease is being broken */
 #define FL_OFDLCK       1024    /* lock is "owned" by struct file */
+#define FL_LAYOUT       2048    /* outstanding pNFS layout */
 
 /*
  * Special return value from posix_lock_file() and vfs_lock_file() for
@@ -885,6 +882,8 @@ static inline struct file *get_file(struct file *f)
 /* legacy typedef, should eventually be removed */
 typedef void *fl_owner_t;
 
+struct file_lock;
+
 struct file_lock_operations {
         void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
         void (*fl_release_private)(struct file_lock *);
@@ -898,7 +897,7 @@ struct lock_manager_operations {
         void (*lm_notify)(struct file_lock *);  /* unblock callback */
         int (*lm_grant)(struct file_lock *, int);
         bool (*lm_break)(struct file_lock *);
-        int (*lm_change)(struct file_lock **, int, struct list_head *);
+        int (*lm_change)(struct file_lock *, int, struct list_head *);
         void (*lm_setup)(struct file_lock *, void **);
 };
 
@@ -923,17 +922,17 @@ int locks_in_grace(struct net *);
  * FIXME: should we create a separate "struct lock_request" to help distinguish
  * these two uses?
  *
- * The i_flock list is ordered by:
+ * The varous i_flctx lists are ordered by:
  *
- * 1) lock type -- FL_LEASEs first, then FL_FLOCK, and finally FL_POSIX
- * 2) lock owner
- * 3) lock range start
- * 4) lock range end
+ * 1) lock owner
+ * 2) lock range start
+ * 3) lock range end
  *
  * Obviously, the last two criteria only matter for POSIX locks.
  */
 struct file_lock {
         struct file_lock *fl_next;      /* singly linked list for this inode  */
+        struct list_head fl_list;       /* link into file_lock_context */
         struct hlist_node fl_link;      /* node in global lists */
         struct list_head fl_block;      /* circular list of blocked processes */
         fl_owner_t fl_owner;
@@ -964,6 +963,13 @@ struct file_lock {
         } fl_u;
 };
 
+struct file_lock_context {
+        spinlock_t              flc_lock;
+        struct list_head        flc_flock;
+        struct list_head        flc_posix;
+        struct list_head        flc_lease;
+};
+
 /* The following constant reflects the upper bound of the file/locking space */
 #ifndef OFFSET_MAX
 #define INT_LIMIT(x)    (~((x)1 << (sizeof(x)*8 - 1)))
@@ -990,6 +996,7 @@ extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg);
 extern int fcntl_getlease(struct file *filp);
 
 /* fs/locks.c */
+void locks_free_lock_context(struct file_lock_context *ctx);
 void locks_free_lock(struct file_lock *fl);
 extern void locks_init_lock(struct file_lock *);
 extern struct file_lock * locks_alloc_lock(void);
@@ -1010,7 +1017,7 @@ extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int t
 extern void lease_get_mtime(struct inode *, struct timespec *time);
 extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
 extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
-extern int lease_modify(struct file_lock **, int, struct list_head *);
+extern int lease_modify(struct file_lock *, int, struct list_head *);
 #else /* !CONFIG_FILE_LOCKING */
 static inline int fcntl_getlk(struct file *file, unsigned int cmd,
                               struct flock __user *user)
@@ -1047,6 +1054,11 @@ static inline int fcntl_getlease(struct file *filp)
         return F_UNLCK;
 }
 
+static inline void
+locks_free_lock_context(struct file_lock_context *ctx)
+{
+}
+
 static inline void locks_init_lock(struct file_lock *fl)
 {
         return;
@@ -1137,7 +1149,7 @@ static inline int vfs_setlease(struct file *filp, long arg,
         return -EINVAL;
 }
 
-static inline int lease_modify(struct file_lock **before, int arg,
+static inline int lease_modify(struct file_lock *fl, int arg,
                                struct list_head *dispose)
 {
         return -EINVAL;
@@ -1184,8 +1196,6 @@ struct mm_struct;
 #define UMOUNT_NOFOLLOW 0x00000008      /* Don't follow symlink on umount */
 #define UMOUNT_UNUSED   0x80000000      /* Flag guaranteed to be unused */
 
-extern struct list_head super_blocks;
-extern spinlock_t sb_lock;
 
 /* Possible states of 'frozen' field */
 enum {
@@ -1502,6 +1512,26 @@ struct block_device_operations;
 #define HAVE_COMPAT_IOCTL 1
 #define HAVE_UNLOCKED_IOCTL 1
 
+/*
+ * These flags let !MMU mmap() govern direct device mapping vs immediate
+ * copying more easily for MAP_PRIVATE, especially for ROM filesystems.
+ *
+ * NOMMU_MAP_COPY:      Copy can be mapped (MAP_PRIVATE)
+ * NOMMU_MAP_DIRECT:    Can be mapped directly (MAP_SHARED)
+ * NOMMU_MAP_READ:      Can be mapped for reading
+ * NOMMU_MAP_WRITE:     Can be mapped for writing
+ * NOMMU_MAP_EXEC:      Can be mapped for execution
+ */
+#define NOMMU_MAP_COPY          0x00000001
+#define NOMMU_MAP_DIRECT        0x00000008
+#define NOMMU_MAP_READ          VM_MAYREAD
+#define NOMMU_MAP_WRITE         VM_MAYWRITE
+#define NOMMU_MAP_EXEC          VM_MAYEXEC
+
+#define NOMMU_VMFLAGS \
+        (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC)
+
+
 struct iov_iter;
 
 struct file_operations {
@@ -1536,6 +1566,9 @@ struct file_operations {
         long (*fallocate)(struct file *file, int mode, loff_t offset,
                           loff_t len);
         void (*show_fdinfo)(struct seq_file *m, struct file *f);
+#ifndef CONFIG_MMU
+        unsigned (*mmap_capabilities)(struct file *);
+#endif
 };
 
 struct inode_operations {
@@ -1618,8 +1651,10 @@ struct super_operations {
         struct dquot **(*get_dquots)(struct inode *);
 #endif
         int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
-        long (*nr_cached_objects)(struct super_block *, int);
-        long (*free_cached_objects)(struct super_block *, long, int);
+        long (*nr_cached_objects)(struct super_block *,
+                                  struct shrink_control *);
+        long (*free_cached_objects)(struct super_block *,
+                                    struct shrink_control *);
 };
 
 /*
@@ -1638,6 +1673,11 @@ struct super_operations {
 #define S_IMA           1024    /* Inode has an associated IMA struct */
 #define S_AUTOMOUNT     2048    /* Automount/referral quasi-directory */
 #define S_NOSEC         4096    /* no suid or xattr security attributes */
+#ifdef CONFIG_FS_DAX
+#define S_DAX           8192    /* Direct Access, avoiding the page cache */
+#else
+#define S_DAX           0       /* Make all the DAX code disappear */
+#endif
 
 /*
  * Note that nosuid etc flags are inode-specific: setting some file-system
@@ -1675,6 +1715,7 @@ struct super_operations {
 #define IS_IMA(inode)           ((inode)->i_flags & S_IMA)
 #define IS_AUTOMOUNT(inode)     ((inode)->i_flags & S_AUTOMOUNT)
 #define IS_NOSEC(inode)         ((inode)->i_flags & S_NOSEC)
+#define IS_DAX(inode)           ((inode)->i_flags & S_DAX)
 
 #define IS_WHITEOUT(inode)      (S_ISCHR(inode->i_mode) && \
                                  (inode)->i_rdev == WHITEOUT_DEV)
@@ -1746,8 +1787,12 @@ struct super_operations {
 #define __I_DIO_WAKEUP          9
 #define I_DIO_WAKEUP            (1 << I_DIO_WAKEUP)
 #define I_LINKABLE              (1 << 10)
+#define I_DIRTY_TIME            (1 << 11)
+#define __I_DIRTY_TIME_EXPIRED  12
+#define I_DIRTY_TIME_EXPIRED    (1 << __I_DIRTY_TIME_EXPIRED)
 
 #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
+#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
 
 extern void __mark_inode_dirty(struct inode *, int);
 static inline void mark_inode_dirty(struct inode *inode)
@@ -1910,6 +1955,7 @@ extern int current_umask(void);
 
 extern void ihold(struct inode * inode);
 extern void iput(struct inode *);
+extern int generic_update_time(struct inode *, struct timespec *, int);
 
 static inline struct inode *file_inode(const struct file *f)
 {
@@ -1959,7 +2005,7 @@ static inline int locks_verify_truncate(struct inode *inode,
                                     struct file *filp,
                                     loff_t size)
 {
-        if (inode->i_flock && mandatory_lock(inode))
+        if (inode->i_flctx && mandatory_lock(inode))
                 return locks_mandatory_area(
                         FLOCK_VERIFY_WRITE, inode, filp,
                         size < inode->i_size ? size : inode->i_size,
@@ -1973,11 +2019,12 @@ static inline int break_lease(struct inode *inode, unsigned int mode)
 {
         /*
          * Since this check is lockless, we must ensure that any refcounts
-         * taken are done before checking inode->i_flock. Otherwise, we could
-         * end up racing with tasks trying to set a new lease on this file.
+         * taken are done before checking i_flctx->flc_lease. Otherwise, we
+         * could end up racing with tasks trying to set a new lease on this
+         * file.
          */
         smp_mb();
-        if (inode->i_flock)
+        if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
                 return __break_lease(inode, mode, FL_LEASE);
         return 0;
 }
@@ -1986,11 +2033,12 @@ static inline int break_deleg(struct inode *inode, unsigned int mode)
 {
         /*
          * Since this check is lockless, we must ensure that any refcounts
-         * taken are done before checking inode->i_flock. Otherwise, we could
-         * end up racing with tasks trying to set a new lease on this file.
+         * taken are done before checking i_flctx->flc_lease. Otherwise, we
+         * could end up racing with tasks trying to set a new lease on this
+         * file.
          */
         smp_mb();
-        if (inode->i_flock)
+        if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
                 return __break_lease(inode, mode, FL_DELEG);
         return 0;
 }
@@ -2017,6 +2065,16 @@ static inline int break_deleg_wait(struct inode **delegated_inode)
         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);
+        return 0;
+}
+
 #else /* !CONFIG_FILE_LOCKING */
 static inline int locks_mandatory_locked(struct file *file)
 {
@@ -2072,6 +2130,11 @@ static inline int break_deleg_wait(struct inode **delegated_inode)
         return 0;
 }
 
+static inline int break_layout(struct inode *inode, bool wait)
+{
+        return 0;
+}
+
 #endif /* CONFIG_FILE_LOCKING */
 
 /* fs/open.c */
@@ -2080,6 +2143,7 @@ struct filename {
         const char              *name;  /* pointer to actual string */
         const __user char       *uptr;  /* original userland pointer */
         struct audit_names      *aname;
+        int                     refcnt;
         bool                    separate; /* should "name" be freed? */
 };
 
@@ -2101,6 +2165,7 @@ extern int filp_close(struct file *, fl_owner_t id);
 extern struct filename *getname_flags(const char __user *, int, int *);
 extern struct filename *getname(const char __user *);
 extern struct filename *getname_kernel(const char *);
+extern void putname(struct filename *name);
 
 enum {
         FILE_CREATED = 1,
@@ -2121,15 +2186,8 @@ extern void __init vfs_caches_init(unsigned long);
 
 extern struct kmem_cache *names_cachep;
 
-extern void final_putname(struct filename *name);
-
 #define __getname()             kmem_cache_alloc(names_cachep, GFP_KERNEL)
 #define __putname(name)         kmem_cache_free(names_cachep, (void *)(name))
-#ifndef CONFIG_AUDITSYSCALL
-#define putname(name)           final_putname(name)
-#else
-extern void putname(struct filename *name);
-#endif
 
 #ifdef CONFIG_BLOCK
 extern int register_blkdev(unsigned int, const char *);
@@ -2436,6 +2494,11 @@ extern struct inode *ilookup(struct super_block *sb, unsigned long ino);
 
 extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *);
 extern struct inode * iget_locked(struct super_block *, unsigned long);
+extern struct inode *find_inode_nowait(struct super_block *,
+                                       unsigned long,
+                                       int (*match)(struct inode *,
+                                                    unsigned long, void *),
+                                       void *data);
 extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
 extern int insert_inode_locked(struct inode *);
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -2481,8 +2544,6 @@ extern int sb_min_blocksize(struct super_block *, int);
 
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
-extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr,
-                unsigned long size, pgoff_t pgoff);
 int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
 extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
@@ -2494,6 +2555,9 @@ extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t l
 extern ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
 extern ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
 
+ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos);
+ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos);
+
 /* fs/block_dev.c */
 extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to);
 extern ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from);
@@ -2527,19 +2591,13 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 
-#ifdef CONFIG_FS_XIP
-extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len,
-                             loff_t *ppos);
-extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma);
-extern ssize_t xip_file_write(struct file *filp, const char __user *buf,
-                              size_t len, loff_t *ppos);
-extern int xip_truncate_page(struct address_space *mapping, loff_t from);
-#else
-static inline int xip_truncate_page(struct address_space *mapping, loff_t from)
-{
-        return 0;
-}
-#endif
+ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *,
+                loff_t, get_block_t, dio_iodone_t, int flags);
+int dax_clear_blocks(struct inode *, sector_t block, long size);
+int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
+int dax_truncate_page(struct inode *, loff_t from, get_block_t);
+int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
+#define dax_mkwrite(vma, vmf, gb)       dax_fault(vma, vmf, gb)
 
 #ifdef CONFIG_BLOCK
 typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
@@ -2696,6 +2754,11 @@ extern int generic_show_options(struct seq_file *m, struct dentry *root);
 extern void save_mount_options(struct super_block *sb, char *options);
 extern void replace_mount_options(struct super_block *sb, char *options);
 
+static inline bool io_is_direct(struct file *filp)
+{
+        return (filp->f_flags & O_DIRECT) || IS_DAX(file_inode(filp));
+}
+
 static inline ino_t parent_ino(struct dentry *dentry)
 {
         ino_t res;