11 files changed, 77 insertions, 134 deletions

diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index ce12a2b06f8f..cca8eef736fc 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -759,12 +759,6 @@ extern unsigned afs_debug;
 #define dbgprintk(FMT,...) \
         printk("[%-6.6s] "FMT"\n", current->comm ,##__VA_ARGS__)
 
-/* make sure we maintain the format strings, even when debugging is disabled */
-static inline __attribute__((format(printf,1,2)))
-void _dbprintk(const char *fmt, ...)
-{
-}
-
 #define kenter(FMT,...) dbgprintk("==> %s("FMT")",__func__ ,##__VA_ARGS__)
 #define kleave(FMT,...) dbgprintk("<== %s()"FMT"",__func__ ,##__VA_ARGS__)
 #define kdebug(FMT,...) dbgprintk("    "FMT ,##__VA_ARGS__)
@@ -799,9 +793,9 @@ do {							\
 } while (0)
 
 #else
-#define _enter(FMT,...) _dbprintk("==> %s("FMT")",__func__ ,##__VA_ARGS__)
-#define _leave(FMT,...) _dbprintk("<== %s()"FMT"",__func__ ,##__VA_ARGS__)
-#define _debug(FMT,...) _dbprintk("    "FMT ,##__VA_ARGS__)
+#define _enter(FMT,...) no_printk("==> %s("FMT")",__func__ ,##__VA_ARGS__)
+#define _leave(FMT,...) no_printk("<== %s()"FMT"",__func__ ,##__VA_ARGS__)
+#define _debug(FMT,...) no_printk("    "FMT ,##__VA_ARGS__)
 #endif
 
 /*
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index a8cd821226da..bd6bc1bde2d7 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -267,13 +267,6 @@ do {									\
 #define dbgprintk(FMT, ...) \
         printk(KERN_DEBUG "[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__)
 
-/* make sure we maintain the format strings, even when debugging is disabled */
-static inline void _dbprintk(const char *fmt, ...)
-        __attribute__((format(printf, 1, 2)));
-static inline void _dbprintk(const char *fmt, ...)
-{
-}
-
 #define kenter(FMT, ...) dbgprintk("==> %s("FMT")", __func__, ##__VA_ARGS__)
 #define kleave(FMT, ...) dbgprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
 #define kdebug(FMT, ...) dbgprintk(FMT, ##__VA_ARGS__)
@@ -304,9 +297,9 @@ do {							\
 } while (0)
 
 #else
-#define _enter(FMT, ...) _dbprintk("==> %s("FMT")", __func__, ##__VA_ARGS__)
-#define _leave(FMT, ...) _dbprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
-#define _debug(FMT, ...) _dbprintk(FMT, ##__VA_ARGS__)
+#define _enter(FMT, ...) no_printk("==> %s("FMT")", __func__, ##__VA_ARGS__)
+#define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
+#define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__)
 #endif
 
 #if 1 /* defined(__KDEBUGALL) */
diff --git a/fs/file_table.c b/fs/file_table.c
index 2fc3b3c08911..edecd36fed9b 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -230,15 +230,6 @@ static void __fput(struct file *file)
         might_sleep();
 
         fsnotify_close(file);
-
-        /*
-         * fsnotify_create_event may have taken one or more references on this
-         * file.  If it did so it left one reference for us to drop to make sure
-         * its calls to fput could not prematurely destroy the file.
-         */
-        if (atomic_long_read(&file->f_count))
-                return fput(file);
-
         /*
          * The function eventpoll_release() should be the first called
          * in the file cleanup chain.
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 2f76c4a081a2..7d9d06ba184b 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -68,7 +68,7 @@ int nr_pdflush_threads;
  */
 int writeback_in_progress(struct backing_dev_info *bdi)
 {
-        return !list_empty(&bdi->work_list);
+        return test_bit(BDI_writeback_running, &bdi->state);
 }
 
 static void bdi_queue_work(struct backing_dev_info *bdi,
@@ -249,10 +249,18 @@ static void move_expired_inodes(struct list_head *delaying_queue,
 
 /*
  * Queue all expired dirty inodes for io, eldest first.
+ * Before
+ *         newly dirtied     b_dirty    b_io    b_more_io
+ *         =============>    gf         edc     BA
+ * After
+ *         newly dirtied     b_dirty    b_io    b_more_io
+ *         =============>    g          fBAedc
+ *                                           |
+ *                                           +--> dequeue for IO
  */
 static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
 {
-        list_splice_init(&wb->b_more_io, wb->b_io.prev);
+        list_splice_init(&wb->b_more_io, &wb->b_io);
         move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
 }
 
@@ -363,62 +371,35 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
         spin_lock(&inode_lock);
         inode->i_state &= ~I_SYNC;
         if (!(inode->i_state & I_FREEING)) {
-                if ((inode->i_state & I_DIRTY_PAGES) && wbc->for_kupdate) {
-                        /*
-                         * More pages get dirtied by a fast dirtier.
-                         */
-                        goto select_queue;
-                } else if (inode->i_state & I_DIRTY) {
-                        /*
-                         * At least XFS will redirty the inode during the
-                         * writeback (delalloc) and on io completion (isize).
-                         */
-                        redirty_tail(inode);
-                } else if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+                if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
                         /*
                          * We didn't write back all the pages.  nfs_writepages()
-                         * sometimes bales out without doing anything. Redirty
-                         * the inode; Move it from b_io onto b_more_io/b_dirty.
+                         * sometimes bales out without doing anything.
                          */
-                        /*
-                         * akpm: if the caller was the kupdate function we put
-                         * this inode at the head of b_dirty so it gets first
-                         * consideration.  Otherwise, move it to the tail, for
-                         * the reasons described there.  I'm not really sure
-                         * how much sense this makes.  Presumably I had a good
-                         * reasons for doing it this way, and I'd rather not
-                         * muck with it at present.
-                         */
-                        if (wbc->for_kupdate) {
+                        inode->i_state |= I_DIRTY_PAGES;
+                        if (wbc->nr_to_write <= 0) {
                                 /*
-                                 * For the kupdate function we move the inode
-                                 * to b_more_io so it will get more writeout as
-                                 * soon as the queue becomes uncongested.
+                                 * slice used up: queue for next turn
                                  */
-                                inode->i_state |= I_DIRTY_PAGES;
-select_queue:
-                                if (wbc->nr_to_write <= 0) {
-                                        /*
-                                         * slice used up: queue for next turn
-                                         */
-                                        requeue_io(inode);
-                                } else {
-                                        /*
-                                         * somehow blocked: retry later
-                                         */
-                                        redirty_tail(inode);
-                                }
+                                requeue_io(inode);
                         } else {
                                 /*
-                                 * Otherwise fully redirty the inode so that
-                                 * other inodes on this superblock will get some
-                                 * writeout.  Otherwise heavy writing to one
-                                 * file would indefinitely suspend writeout of
-                                 * all the other files.
+                                 * Writeback blocked by something other than
+                                 * congestion. Delay the inode for some time to
+                                 * avoid spinning on the CPU (100% iowait)
+                                 * retrying writeback of the dirty page/inode
+                                 * that cannot be performed immediately.
                                  */
-                                inode->i_state |= I_DIRTY_PAGES;
                                 redirty_tail(inode);
                         }
+                } else if (inode->i_state & I_DIRTY) {
+                        /*
+                         * Filesystems can dirty the inode during writeback
+                         * operations, such as delayed allocation during
+                         * submission or metadata updates after data IO
+                         * completion.
+                         */
+                        redirty_tail(inode);
                 } else if (atomic_read(&inode->i_count)) {
                         /*
                          * The inode is clean, inuse
@@ -590,7 +571,7 @@ static inline bool over_bground_thresh(void)
 {
         unsigned long background_thresh, dirty_thresh;
 
-        get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
+        global_dirty_limits(&background_thresh, &dirty_thresh);
 
         return (global_page_state(NR_FILE_DIRTY) +
                 global_page_state(NR_UNSTABLE_NFS) >= background_thresh);
@@ -759,6 +740,7 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
         struct wb_writeback_work *work;
         long wrote = 0;
 
+        set_bit(BDI_writeback_running, &wb->bdi->state);
         while ((work = get_next_work_item(bdi)) != NULL) {
                 /*
                  * Override sync mode, in case we must wait for completion
@@ -785,6 +767,7 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
          * Check for periodic writeback, kupdated() style
          */
         wrote += wb_check_old_data_flush(wb);
+        clear_bit(BDI_writeback_running, &wb->bdi->state);
 
         return wrote;
 }
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index 6a026441c5a6..f6aad48d38a8 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -321,17 +321,11 @@ void fscache_put_context(struct fscache_cookie *cookie, void *context)
 #define dbgprintk(FMT, ...) \
         printk(KERN_DEBUG "[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__)
 
-/* make sure we maintain the format strings, even when debugging is disabled */
-static inline __attribute__((format(printf, 1, 2)))
-void _dbprintk(const char *fmt, ...)
-{
-}
-
 #define kenter(FMT, ...) dbgprintk("==> %s("FMT")", __func__, ##__VA_ARGS__)
 #define kleave(FMT, ...) dbgprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
 #define kdebug(FMT, ...) dbgprintk(FMT, ##__VA_ARGS__)
 
-#define kjournal(FMT, ...) _dbprintk(FMT, ##__VA_ARGS__)
+#define kjournal(FMT, ...) no_printk(FMT, ##__VA_ARGS__)
 
 #ifdef __KDEBUG
 #define _enter(FMT, ...) kenter(FMT, ##__VA_ARGS__)
@@ -358,9 +352,9 @@ do {						\
 } while (0)
 
 #else
-#define _enter(FMT, ...) _dbprintk("==> %s("FMT")", __func__, ##__VA_ARGS__)
-#define _leave(FMT, ...) _dbprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
-#define _debug(FMT, ...) _dbprintk(FMT, ##__VA_ARGS__)
+#define _enter(FMT, ...) no_printk("==> %s("FMT")", __func__, ##__VA_ARGS__)
+#define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
+#define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__)
 #endif
 
 /*
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 36dfdae95123..e17b49e2eabd 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -45,7 +45,7 @@ unsigned short nfs_callback_tcpport;
 unsigned short nfs_callback_tcpport6;
 #define NFS_CALLBACK_MAXPORTNR (65535U)
 
-static int param_set_portnr(const char *val, struct kernel_param *kp)
+static int param_set_portnr(const char *val, const struct kernel_param *kp)
 {
         unsigned long num;
         int ret;
@@ -58,11 +58,10 @@ static int param_set_portnr(const char *val, struct kernel_param *kp)
         *((unsigned int *)kp->arg) = num;
         return 0;
 }
-
-static int param_get_portnr(char *buffer, struct kernel_param *kp)
-{
-        return param_get_uint(buffer, kp);
-}
+static struct kernel_param_ops param_ops_portnr = {
+        .set = param_set_portnr,
+        .get = param_get_uint,
+};
 #define param_check_portnr(name, p) __param_check(name, p, unsigned int);
 
 module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644);
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index eb8f73c9c131..756566fe8449 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -17,9 +17,9 @@ static bool should_merge(struct fsnotify_event *old, struct fsnotify_event *new)
             old->data_type == new->data_type &&
             old->tgid == new->tgid) {
                 switch (old->data_type) {
-                case (FSNOTIFY_EVENT_FILE):
-                        if ((old->file->f_path.mnt == new->file->f_path.mnt) &&
-                            (old->file->f_path.dentry == new->file->f_path.dentry))
+                case (FSNOTIFY_EVENT_PATH):
+                        if ((old->path.mnt == new->path.mnt) &&
+                            (old->path.dentry == new->path.dentry))
                                 return true;
                 case (FSNOTIFY_EVENT_NONE):
                         return true;
@@ -174,7 +174,7 @@ static bool fanotify_should_send_event(struct fsnotify_group *group,
                 return false;
 
         /* if we don't have enough info to send an event to userspace say no */
-        if (data_type != FSNOTIFY_EVENT_FILE)
+        if (data_type != FSNOTIFY_EVENT_PATH)
                 return false;
 
         if (inode_mark && vfsmnt_mark) {
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 25a3b4dfcf61..032b837fcd11 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -65,7 +65,7 @@ static int create_fd(struct fsnotify_group *group, struct fsnotify_event *event)
         if (client_fd < 0)
                 return client_fd;
 
-        if (event->data_type != FSNOTIFY_EVENT_FILE) {
+        if (event->data_type != FSNOTIFY_EVENT_PATH) {
                 WARN_ON(1);
                 put_unused_fd(client_fd);
                 return -EINVAL;
@@ -75,8 +75,8 @@ static int create_fd(struct fsnotify_group *group, struct fsnotify_event *event)
          * we need a new file handle for the userspace program so it can read even if it was
          * originally opened O_WRONLY.
          */
-        dentry = dget(event->file->f_path.dentry);
-        mnt = mntget(event->file->f_path.mnt);
+        dentry = dget(event->path.dentry);
+        mnt = mntget(event->path.mnt);
         /* it's possible this event was an overflow event.  in that case dentry and mnt
          * are NULL;  That's fine, just don't call dentry open */
         if (dentry && mnt)
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 4d2a82c1ceb1..3970392b2722 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -84,7 +84,7 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
 }
 
 /* Notify this dentry's parent about a child's events. */
-void __fsnotify_parent(struct file *file, struct dentry *dentry, __u32 mask)
+void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
 {
         struct dentry *parent;
         struct inode *p_inode;
@@ -92,7 +92,7 @@ void __fsnotify_parent(struct file *file, struct dentry *dentry, __u32 mask)
         bool should_update_children = false;
 
         if (!dentry)
-                dentry = file->f_path.dentry;
+                dentry = path->dentry;
 
         if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED))
                 return;
@@ -124,8 +124,8 @@ void __fsnotify_parent(struct file *file, struct dentry *dentry, __u32 mask)
                  * specifies these are events which came from a child. */
                 mask |= FS_EVENT_ON_CHILD;
 
-                if (file)
-                        fsnotify(p_inode, mask, file, FSNOTIFY_EVENT_FILE,
+                if (path)
+                        fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH,
                                  dentry->d_name.name, 0);
                 else
                         fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE,
@@ -217,8 +217,8 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
         /* global tests shouldn't care about events on child only the specific event */
         __u32 test_mask = (mask & ~FS_EVENT_ON_CHILD);
 
-        if (data_is == FSNOTIFY_EVENT_FILE)
-                mnt = ((struct file *)data)->f_path.mnt;
+        if (data_is == FSNOTIFY_EVENT_PATH)
+                mnt = ((struct path *)data)->mnt;
         else
                 mnt = NULL;
 
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 5e73eeb2c697..a91b69a6a291 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -52,9 +52,9 @@ static bool event_compare(struct fsnotify_event *old, struct fsnotify_event *new
                             !strcmp(old->file_name, new->file_name))
                                 return true;
                         break;
-                case (FSNOTIFY_EVENT_FILE):
-                        if ((old->file->f_path.mnt == new->file->f_path.mnt) &&
-                            (old->file->f_path.dentry == new->file->f_path.dentry))
+                case (FSNOTIFY_EVENT_PATH):
+                        if ((old->path.mnt == new->path.mnt) &&
+                            (old->path.dentry == new->path.dentry))
                                 return true;
                         break;
                 case (FSNOTIFY_EVENT_NONE):
@@ -147,10 +147,10 @@ static bool inotify_should_send_event(struct fsnotify_group *group, struct inode
                                       __u32 mask, void *data, int data_type)
 {
         if ((inode_mark->mask & FS_EXCL_UNLINK) &&
-            (data_type == FSNOTIFY_EVENT_FILE)) {
-                struct file *file  = data;
+            (data_type == FSNOTIFY_EVENT_PATH)) {
+                struct path *path = data;
 
-                if (d_unlinked(file->f_path.dentry))
+                if (d_unlinked(path->dentry))
                         return false;
         }
 
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index d6c435adc7a2..f39260f8f865 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -31,7 +31,6 @@
  * allocated and used.
  */
 
-#include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -90,8 +89,8 @@ void fsnotify_put_event(struct fsnotify_event *event)
         if (atomic_dec_and_test(&event->refcnt)) {
                 pr_debug("%s: event=%p\n", __func__, event);
 
-                if (event->data_type == FSNOTIFY_EVENT_FILE)
-                        fput(event->file);
+                if (event->data_type == FSNOTIFY_EVENT_PATH)
+                        path_put(&event->path);
 
                 BUG_ON(!list_empty(&event->private_data_list));
 
@@ -376,8 +375,8 @@ struct fsnotify_event *fsnotify_clone_event(struct fsnotify_event *old_event)
                 }
         }
         event->tgid = get_pid(old_event->tgid);
-        if (event->data_type == FSNOTIFY_EVENT_FILE)
-                get_file(event->file);
+        if (event->data_type == FSNOTIFY_EVENT_PATH)
+                path_get(&event->path);
 
         return event;
 }
@@ -424,22 +423,11 @@ struct fsnotify_event *fsnotify_create_event(struct inode *to_tell, __u32 mask,
         event->data_type = data_type;
 
         switch (data_type) {
-        case FSNOTIFY_EVENT_FILE: {
-                event->file = data;
-                /*
-                 * if this file is about to disappear hold an extra reference
-                 * until we return to __fput so we don't have to worry about
-                 * future get/put destroying the file under us or generating
-                 * additional events.  Notice that we change f_mode without
-                 * holding f_lock.  This is safe since this is the only possible
-                 * reference to this object in the kernel (it was about to be
-                 * freed, remember?)
-                 */
-                if (!atomic_long_read(&event->file->f_count)) {
-                        event->file->f_mode |= FMODE_NONOTIFY;
-                        get_file(event->file);
-                }
-                get_file(event->file);
+        case FSNOTIFY_EVENT_PATH: {
+                struct path *path = data;
+                event->path.dentry = path->dentry;
+                event->path.mnt = path->mnt;
+                path_get(&event->path);
                 break;
         }
         case FSNOTIFY_EVENT_INODE:
@@ -447,7 +435,8 @@ struct fsnotify_event *fsnotify_create_event(struct inode *to_tell, __u32 mask,
                 break;
         case FSNOTIFY_EVENT_NONE:
                 event->inode = NULL;
-                event->file = NULL;
+                event->path.dentry = NULL;
+                event->path.mnt = NULL;
                 break;
         default:
                 BUG();