19 files changed, 271 insertions, 226 deletions

diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 9e52b0626b39..f5a3b838ddb0 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -198,7 +198,8 @@ extern int buffer_heads_over_limit;
  * Generic address_space_operations implementations for buffer_head-backed
  * address_spaces.
  */
-void block_invalidatepage(struct page *page, unsigned long offset);
+void block_invalidatepage(struct page *page, unsigned int offset,
+			  unsigned int length);
 int block_write_full_page(struct page *page, get_block_t *get_block,
 				struct writeback_control *wbc);
 int block_write_full_page_endio(struct page *page, get_block_t *get_block,
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index 365f4a61bf04..fc09d7b0dacf 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -3,6 +3,7 @@
 
 #include <linux/sched.h>
 #include <linux/percpu.h>
+#include <linux/vtime.h>
 #include <asm/ptrace.h>
 
 struct context_tracking {
@@ -19,6 +20,26 @@ struct context_tracking {
 	} state;
 };
 
+static inline void __guest_enter(void)
+{
+	/*
+	 * This is running in ioctl context so we can avoid
+	 * the call to vtime_account() with its unnecessary idle check.
+	 */
+	vtime_account_system(current);
+	current->flags |= PF_VCPU;
+}
+
+static inline void __guest_exit(void)
+{
+	/*
+	 * This is running in ioctl context so we can avoid
+	 * the call to vtime_account() with its unnecessary idle check.
+	 */
+	vtime_account_system(current);
+	current->flags &= ~PF_VCPU;
+}
+
 #ifdef CONFIG_CONTEXT_TRACKING
 DECLARE_PER_CPU(struct context_tracking, context_tracking);
 
@@ -35,6 +56,9 @@ static inline bool context_tracking_active(void)
 extern void user_enter(void);
 extern void user_exit(void);
 
+extern void guest_enter(void);
+extern void guest_exit(void);
+
 static inline enum ctx_state exception_enter(void)
 {
 	enum ctx_state prev_ctx;
@@ -57,6 +81,17 @@ extern void context_tracking_task_switch(struct task_struct *prev,
 static inline bool context_tracking_in_user(void) { return false; }
 static inline void user_enter(void) { }
 static inline void user_exit(void) { }
+
+static inline void guest_enter(void)
+{
+	__guest_enter();
+}
+
+static inline void guest_exit(void)
+{
+	__guest_exit();
+}
+
 static inline enum ctx_state exception_enter(void) { return 0; }
 static inline void exception_exit(enum ctx_state prev_ctx) { }
 static inline void context_tracking_task_switch(struct task_struct *prev,
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index df6fab82f87e..383d5e39b280 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -20,8 +20,8 @@
 #define F2FS_BLKSIZE			4096	/* support only 4KB block */
 #define F2FS_MAX_EXTENSION		64	/* # of extension entries */
 
-#define NULL_ADDR		0x0U
-#define NEW_ADDR		-1U
+#define NULL_ADDR		((block_t)0)	/* used as block_t addresses */
+#define NEW_ADDR		((block_t)-1)	/* used as block_t addresses */
 
 #define F2FS_ROOT_INO(sbi)	(sbi->root_ino_num)
 #define F2FS_NODE_INO(sbi)	(sbi->node_ino_num)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 43db02e9c9fa..f8a5240541b7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -364,7 +364,7 @@ struct address_space_operations {
 
 	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
 	sector_t (*bmap)(struct address_space *, sector_t);
-	void (*invalidatepage) (struct page *, unsigned long);
+	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
 	int (*releasepage) (struct page *, gfp_t);
 	void (*freepage)(struct page *);
 	ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
@@ -1506,6 +1506,11 @@ int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
  * to have different dirent layouts depending on the binary type.
  */
 typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
+struct dir_context {
+	const filldir_t actor;
+	loff_t pos;
+};
+
 struct block_device_operations;
 
 /* These macros are for out of kernel modules to test that
@@ -1521,7 +1526,7 @@ struct file_operations {
 	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
 	ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
 	ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
-	int (*readdir) (struct file *, void *, filldir_t);
+	int (*iterate) (struct file *, struct dir_context *);
 	unsigned int (*poll) (struct file *, struct poll_table_struct *);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
@@ -2414,8 +2419,6 @@ extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
 		struct file *, loff_t *, size_t, unsigned int);
 extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
 		struct file *out, loff_t *, size_t len, unsigned int flags);
-extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
-		size_t len, unsigned int flags);
 
 extern void
 file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
@@ -2496,6 +2499,7 @@ loff_t inode_get_bytes(struct inode *inode);
 void inode_set_bytes(struct inode *inode, loff_t bytes);
 
 extern int vfs_readdir(struct file *, filldir_t, void *);
+extern int iterate_dir(struct file *, struct dir_context *);
 
 extern int vfs_stat(const char __user *, struct kstat *);
 extern int vfs_lstat(const char __user *, struct kstat *);
@@ -2526,7 +2530,7 @@ extern void iterate_supers_type(struct file_system_type *,
 extern int dcache_dir_open(struct inode *, struct file *);
 extern int dcache_dir_close(struct inode *, struct file *);
 extern loff_t dcache_dir_lseek(struct file *, loff_t, int);
-extern int dcache_readdir(struct file *, void *, filldir_t);
+extern int dcache_readdir(struct file *, struct dir_context *);
 extern int simple_setattr(struct dentry *, struct iattr *);
 extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 extern int simple_statfs(struct dentry *, struct kstatfs *);
@@ -2690,4 +2694,41 @@ static inline void inode_has_no_xattr(struct inode *inode)
 		inode->i_flags |= S_NOSEC;
 }
 
+static inline bool dir_emit(struct dir_context *ctx,
+			    const char *name, int namelen,
+			    u64 ino, unsigned type)
+{
+	return ctx->actor(ctx, name, namelen, ctx->pos, ino, type) == 0;
+}
+static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx)
+{
+	return ctx->actor(ctx, ".", 1, ctx->pos,
+			  file->f_path.dentry->d_inode->i_ino, DT_DIR) == 0;
+}
+static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx)
+{
+	return ctx->actor(ctx, "..", 2, ctx->pos,
+			  parent_ino(file->f_path.dentry), DT_DIR) == 0;
+}
+static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx)
+{
+	if (ctx->pos == 0) {
+		if (!dir_emit_dot(file, ctx))
+			return false;
+		ctx->pos = 1;
+	}
+	if (ctx->pos == 1) {
+		if (!dir_emit_dotdot(file, ctx))
+			return false;
+		ctx->pos = 2;
+	}
+	return true;
+}
+static inline bool dir_relax(struct inode *inode)
+{
+	mutex_unlock(&inode->i_mutex);
+	mutex_lock(&inode->i_mutex);
+	return !IS_DEADDIR(inode);
+}
+
 #endif /* _LINUX_FS_H */
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 52bd03b38962..637fa71de0c7 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -44,7 +44,7 @@ struct vlan_hdr {
  *	struct vlan_ethhdr - vlan ethernet header (ethhdr + vlan_hdr)
  *	@h_dest: destination ethernet address
  *	@h_source: source ethernet address
- *	@h_vlan_proto: ethernet protocol (always 0x8100)
+ *	@h_vlan_proto: ethernet protocol
  *	@h_vlan_TCI: priority and VLAN ID
  *	@h_vlan_encapsulated_proto: packet type ID or len
  */
diff --git a/include/linux/jbd.h b/include/linux/jbd.h
index 7e0b622503c4..8685d1be12c7 100644
--- a/include/linux/jbd.h
+++ b/include/linux/jbd.h
@@ -27,7 +27,6 @@
 #include <linux/buffer_head.h>
 #include <linux/journal-head.h>
 #include <linux/stddef.h>
-#include <linux/bit_spinlock.h>
 #include <linux/mutex.h>
 #include <linux/timer.h>
 #include <linux/lockdep.h>
@@ -244,6 +243,31 @@ typedef struct journal_superblock_s
 
 #include <linux/fs.h>
 #include <linux/sched.h>
+
+enum jbd_state_bits {
+	BH_JBD			/* Has an attached ext3 journal_head */
+	  = BH_PrivateStart,
+	BH_JWrite,		/* Being written to log (@@@ DEBUGGING) */
+	BH_Freed,		/* Has been freed (truncated) */
+	BH_Revoked,		/* Has been revoked from the log */
+	BH_RevokeValid,		/* Revoked flag is valid */
+	BH_JBDDirty,		/* Is dirty but journaled */
+	BH_State,		/* Pins most journal_head state */
+	BH_JournalHead,		/* Pins bh->b_private and jh->b_bh */
+	BH_Unshadow,		/* Dummy bit, for BJ_Shadow wakeup filtering */
+	BH_JBDPrivateStart,	/* First bit available for private use by FS */
+};
+
+BUFFER_FNS(JBD, jbd)
+BUFFER_FNS(JWrite, jwrite)
+BUFFER_FNS(JBDDirty, jbddirty)
+TAS_BUFFER_FNS(JBDDirty, jbddirty)
+BUFFER_FNS(Revoked, revoked)
+TAS_BUFFER_FNS(Revoked, revoked)
+BUFFER_FNS(RevokeValid, revokevalid)
+TAS_BUFFER_FNS(RevokeValid, revokevalid)
+BUFFER_FNS(Freed, freed)
+
 #include <linux/jbd_common.h>
 
 #define J_ASSERT(assert)	BUG_ON(!(assert))
@@ -840,7 +864,7 @@ extern void	 journal_release_buffer (handle_t *, struct buffer_head *);
 extern int	 journal_forget (handle_t *, struct buffer_head *);
 extern void	 journal_sync_buffer (struct buffer_head *);
 extern void	 journal_invalidatepage(journal_t *,
-				struct page *, unsigned long);
+				struct page *, unsigned int, unsigned int);
 extern int	 journal_try_to_free_buffers(journal_t *, struct page *, gfp_t);
 extern int	 journal_stop(handle_t *);
 extern int	 journal_flush (journal_t *);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 6e051f472edb..d5b50a19463c 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -26,7 +26,6 @@
 #include <linux/buffer_head.h>
 #include <linux/journal-head.h>
 #include <linux/stddef.h>
-#include <linux/bit_spinlock.h>
 #include <linux/mutex.h>
 #include <linux/timer.h>
 #include <linux/slab.h>
@@ -57,17 +56,13 @@
  */
 #define JBD2_EXPENSIVE_CHECKING
 extern ushort jbd2_journal_enable_debug;
+void __jbd2_debug(int level, const char *file, const char *func,
+		  unsigned int line, const char *fmt, ...);
 
-#define jbd_debug(n, f, a...)						\
-	do {								\
-		if ((n) <= jbd2_journal_enable_debug) {			\
-			printk (KERN_DEBUG "(%s, %d): %s: ",		\
-				__FILE__, __LINE__, __func__);	\
-			printk (f, ## a);				\
-		}							\
-	} while (0)
+#define jbd_debug(n, fmt, a...) \
+	__jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a)
 #else
-#define jbd_debug(f, a...)	/**/
+#define jbd_debug(n, fmt, a...)    /**/
 #endif
 
 extern void *jbd2_alloc(size_t size, gfp_t flags);
@@ -302,6 +297,34 @@ typedef struct journal_superblock_s
 
 #include <linux/fs.h>
 #include <linux/sched.h>
+
+enum jbd_state_bits {
+	BH_JBD			/* Has an attached ext3 journal_head */
+	  = BH_PrivateStart,
+	BH_JWrite,		/* Being written to log (@@@ DEBUGGING) */
+	BH_Freed,		/* Has been freed (truncated) */
+	BH_Revoked,		/* Has been revoked from the log */
+	BH_RevokeValid,		/* Revoked flag is valid */
+	BH_JBDDirty,		/* Is dirty but journaled */
+	BH_State,		/* Pins most journal_head state */
+	BH_JournalHead,		/* Pins bh->b_private and jh->b_bh */
+	BH_Shadow,		/* IO on shadow buffer is running */
+	BH_Verified,		/* Metadata block has been verified ok */
+	BH_JBDPrivateStart,	/* First bit available for private use by FS */
+};
+
+BUFFER_FNS(JBD, jbd)
+BUFFER_FNS(JWrite, jwrite)
+BUFFER_FNS(JBDDirty, jbddirty)
+TAS_BUFFER_FNS(JBDDirty, jbddirty)
+BUFFER_FNS(Revoked, revoked)
+TAS_BUFFER_FNS(Revoked, revoked)
+BUFFER_FNS(RevokeValid, revokevalid)
+TAS_BUFFER_FNS(RevokeValid, revokevalid)
+BUFFER_FNS(Freed, freed)
+BUFFER_FNS(Shadow, shadow)
+BUFFER_FNS(Verified, verified)
+
 #include <linux/jbd_common.h>
 
 #define J_ASSERT(assert)	BUG_ON(!(assert))
@@ -382,8 +405,15 @@ struct jbd2_revoke_table_s;
 
 struct jbd2_journal_handle
 {
-	/* Which compound transaction is this update a part of? */
-	transaction_t		*h_transaction;
+	union {
+		/* Which compound transaction is this update a part of? */
+		transaction_t	*h_transaction;
+		/* Which journal handle belongs to - used iff h_reserved set */
+		journal_t	*h_journal;
+	};
+
+	/* Handle reserved for finishing the logical operation */
+	handle_t		*h_rsv_handle;
 
 	/* Number of remaining buffers we are allowed to dirty: */
 	int			h_buffer_credits;
@@ -398,6 +428,7 @@ struct jbd2_journal_handle
 	/* Flags [no locking] */
 	unsigned int	h_sync:		1;	/* sync-on-close */
 	unsigned int	h_jdata:	1;	/* force data journaling */
+	unsigned int	h_reserved:	1;	/* handle with reserved credits */
 	unsigned int	h_aborted:	1;	/* fatal error on handle */
 	unsigned int	h_type:		8;	/* for handle statistics */
 	unsigned int	h_line_no:	16;	/* for handle statistics */
@@ -524,12 +555,6 @@ struct transaction_s
 	struct journal_head	*t_checkpoint_io_list;
 
 	/*
-	 * Doubly-linked circular list of temporary buffers currently undergoing
-	 * IO in the log [j_list_lock]
-	 */
-	struct journal_head	*t_iobuf_list;
-
-	/*
 	 * Doubly-linked circular list of metadata buffers being shadowed by log
 	 * IO.  The IO buffers on the iobuf list and the shadow buffers on this
 	 * list match each other one for one at all times. [j_list_lock]
@@ -537,12 +562,6 @@ struct transaction_s
 	struct journal_head	*t_shadow_list;
 
 	/*
-	 * Doubly-linked circular list of control buffers being written to the
-	 * log. [j_list_lock]
-	 */
-	struct journal_head	*t_log_list;
-
-	/*
 	 * List of inodes whose data we've modified in data=ordered mode.
 	 * [j_list_lock]
 	 */
@@ -671,11 +690,10 @@ jbd2_time_diff(unsigned long start, unsigned long end)
  *  waiting for checkpointing
  * @j_wait_transaction_locked: Wait queue for waiting for a locked transaction
  *  to start committing, or for a barrier lock to be released
- * @j_wait_logspace: Wait queue for waiting for checkpointing to complete
  * @j_wait_done_commit: Wait queue for waiting for commit to complete
- * @j_wait_checkpoint:  Wait queue to trigger checkpointing
  * @j_wait_commit: Wait queue to trigger commit
  * @j_wait_updates: Wait queue to wait for updates to complete
+ * @j_wait_reserved: Wait queue to wait for reserved buffer credits to drop
  * @j_checkpoint_mutex: Mutex for locking against concurrent checkpoints
  * @j_head: Journal head - identifies the first unused block in the journal
  * @j_tail: Journal tail - identifies the oldest still-used block in the
@@ -689,6 +707,7 @@ jbd2_time_diff(unsigned long start, unsigned long end)
  *     journal
  * @j_fs_dev: Device which holds the client fs.  For internal journal this will
  *     be equal to j_dev
+ * @j_reserved_credits: Number of buffers reserved from the running transaction
  * @j_maxlen: Total maximum capacity of the journal region on disk.
  * @j_list_lock: Protects the buffer lists and internal buffer state.
  * @j_inode: Optional inode where we store the journal.  If present, all journal
@@ -778,21 +797,18 @@ struct journal_s
 	 */
 	wait_queue_head_t	j_wait_transaction_locked;
 
-	/* Wait queue for waiting for checkpointing to complete */
-	wait_queue_head_t	j_wait_logspace;
-
 	/* Wait queue for waiting for commit to complete */
 	wait_queue_head_t	j_wait_done_commit;
 
-	/* Wait queue to trigger checkpointing */
-	wait_queue_head_t	j_wait_checkpoint;
-
 	/* Wait queue to trigger commit */
 	wait_queue_head_t	j_wait_commit;
 
 	/* Wait queue to wait for updates to complete */
 	wait_queue_head_t	j_wait_updates;
 
+	/* Wait queue to wait for reserved buffer credits to drop */
+	wait_queue_head_t	j_wait_reserved;
+
 	/* Semaphore for locking against concurrent checkpoints */
 	struct mutex		j_checkpoint_mutex;
 
@@ -847,6 +863,9 @@ struct journal_s
 	/* Total maximum capacity of the journal region on disk. */
 	unsigned int		j_maxlen;
 
+	/* Number of buffers reserved from the running transaction */
+	atomic_t		j_reserved_credits;
+
 	/*
 	 * Protects the buffer lists and internal buffer state.
 	 */
@@ -991,9 +1010,17 @@ extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, i
 extern void __journal_free_buffer(struct journal_head *bh);
 extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int);
 extern void __journal_clean_data_list(transaction_t *transaction);
+static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh)
+{
+	list_add_tail(&bh->b_assoc_buffers, head);
+}
+static inline void jbd2_unfile_log_bh(struct buffer_head *bh)
+{
+	list_del_init(&bh->b_assoc_buffers);
+}
 
 /* Log buffer allocation */
-extern struct journal_head * jbd2_journal_get_descriptor_buffer(journal_t *);
+struct buffer_head *jbd2_journal_get_descriptor_buffer(journal_t *journal);
 int jbd2_journal_next_log_block(journal_t *, unsigned long long *);
 int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid,
 			      unsigned long *block);
@@ -1039,11 +1066,10 @@ extern void jbd2_buffer_abort_trigger(struct journal_head *jh,
 				      struct jbd2_buffer_trigger_type *triggers);
 
 /* Buffer IO */
-extern int
-jbd2_journal_write_metadata_buffer(transaction_t	  *transaction,
-			      struct journal_head  *jh_in,
-			      struct journal_head **jh_out,
-			      unsigned long long   blocknr);
+extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
+					      struct journal_head *jh_in,
+					      struct buffer_head **bh_out,
+					      sector_t blocknr);
 
 /* Transaction locking */
 extern void		__wait_on_journal (journal_t *);
@@ -1076,10 +1102,14 @@ static inline handle_t *journal_current_handle(void)
  */
 
 extern handle_t *jbd2_journal_start(journal_t *, int nblocks);
-extern handle_t *jbd2__journal_start(journal_t *, int nblocks, gfp_t gfp_mask,
-				     unsigned int type, unsigned int line_no);
+extern handle_t *jbd2__journal_start(journal_t *, int blocks, int rsv_blocks,
+				     gfp_t gfp_mask, unsigned int type,
+				     unsigned int line_no);
 extern int	 jbd2_journal_restart(handle_t *, int nblocks);
 extern int	 jbd2__journal_restart(handle_t *, int nblocks, gfp_t gfp_mask);
+extern int	 jbd2_journal_start_reserved(handle_t *handle,
+				unsigned int type, unsigned int line_no);
+extern void	 jbd2_journal_free_reserved(handle_t *handle);
 extern int	 jbd2_journal_extend (handle_t *, int nblocks);
 extern int	 jbd2_journal_get_write_access(handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_get_create_access (handle_t *, struct buffer_head *);
@@ -1090,7 +1120,7 @@ extern int	 jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_forget (handle_t *, struct buffer_head *);
 extern void	 journal_sync_buffer (struct buffer_head *);
 extern int	 jbd2_journal_invalidatepage(journal_t *,
-				struct page *, unsigned long);
+				struct page *, unsigned int, unsigned int);
 extern int	 jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t);
 extern int	 jbd2_journal_stop(handle_t *);
 extern int	 jbd2_journal_flush (journal_t *);
@@ -1125,6 +1155,7 @@ extern void	   jbd2_journal_ack_err    (journal_t *);
 extern int	   jbd2_journal_clear_err  (journal_t *);
 extern int	   jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *);
 extern int	   jbd2_journal_force_commit(journal_t *);
+extern int	   jbd2_journal_force_commit_nested(journal_t *);
 extern int	   jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *inode);
 extern int	   jbd2_journal_begin_ordered_truncate(journal_t *journal,
 				struct jbd2_inode *inode, loff_t new_size);
@@ -1178,8 +1209,10 @@ extern int	   jbd2_journal_init_revoke_caches(void);
 extern void	   jbd2_journal_destroy_revoke(journal_t *);
 extern int	   jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *);
 extern int	   jbd2_journal_cancel_revoke(handle_t *, struct journal_head *);
-extern void	   jbd2_journal_write_revoke_records(journal_t *,
-						     transaction_t *, int);
+extern void	   jbd2_journal_write_revoke_records(journal_t *journal,
+						     transaction_t *transaction,
+						     struct list_head *log_bufs,
+						     int write_op);
 
 /* Recovery revoke support */
 extern int	jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t);
@@ -1195,11 +1228,9 @@ extern void	jbd2_clear_buffer_revoked_flags(journal_t *journal);
  * transitions on demand.
  */
 
-int __jbd2_log_space_left(journal_t *); /* Called with journal locked */
 int jbd2_log_start_commit(journal_t *journal, tid_t tid);
 int __jbd2_log_start_commit(journal_t *journal, tid_t tid);
 int jbd2_journal_start_commit(journal_t *journal, tid_t *tid);
-int jbd2_journal_force_commit_nested(journal_t *journal);
 int jbd2_log_wait_commit(journal_t *journal, tid_t tid);
 int jbd2_complete_transaction(journal_t *journal, tid_t tid);
 int jbd2_log_do_checkpoint(journal_t *journal);
@@ -1235,7 +1266,7 @@ static inline int is_journal_aborted(journal_t *journal)
 
 static inline int is_handle_aborted(handle_t *handle)
 {
-	if (handle->h_aborted)
+	if (handle->h_aborted || !handle->h_transaction)
 		return 1;
 	return is_journal_aborted(handle->h_transaction->t_journal);
 }
@@ -1266,16 +1297,37 @@ extern int jbd2_journal_blocks_per_page(struct inode *inode);
 extern size_t journal_tag_bytes(journal_t *journal);
 
 /*
+ * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for
+ * transaction control blocks.
+ */
+#define JBD2_CONTROL_BLOCKS_SHIFT 5
+
+/*
  * Return the minimum number of blocks which must be free in the journal
  * before a new transaction may be started.  Must be called under j_state_lock.
  */
-static inline int jbd_space_needed(journal_t *journal)
+static inline int jbd2_space_needed(journal_t *journal)
 {
 	int nblocks = journal->j_max_transaction_buffers;
-	if (journal->j_committing_transaction)
-		nblocks += atomic_read(&journal->j_committing_transaction->
-				       t_outstanding_credits);
-	return nblocks;
+	return nblocks + (nblocks >> JBD2_CONTROL_BLOCKS_SHIFT);
+}
+
+/*
+ * Return number of free blocks in the log. Must be called under j_state_lock.
+ */
+static inline unsigned long jbd2_log_space_left(journal_t *journal)
+{
+	/* Allow for rounding errors */
+	unsigned long free = journal->j_free - 32;
+
+	if (journal->j_committing_transaction) {
+		unsigned long committing = atomic_read(&journal->
+			j_committing_transaction->t_outstanding_credits);
+
+		/* Transaction + control blocks */
+		free -= committing + (committing >> JBD2_CONTROL_BLOCKS_SHIFT);
+	}
+	return free;
 }
 
 /*
@@ -1286,11 +1338,9 @@ static inline int jbd_space_needed(journal_t *journal)
 #define BJ_None		0	/* Not journaled */
 #define BJ_Metadata	1	/* Normal journaled metadata */
 #define BJ_Forget	2	/* Buffer superseded by this transaction */
-#define BJ_IO		3	/* Buffer is for temporary IO use */
-#define BJ_Shadow	4	/* Buffer contents being shadowed to the log */
-#define BJ_LogCtl	5	/* Buffer contains log descriptors */
-#define BJ_Reserved	6	/* Buffer is reserved for access by journal */
-#define BJ_Types	7
+#define BJ_Shadow	3	/* Buffer contents being shadowed to the log */
+#define BJ_Reserved	4	/* Buffer is reserved for access by journal */
+#define BJ_Types	5
 
 extern int jbd_blocks_per_page(struct inode *inode);
 
@@ -1319,6 +1369,19 @@ static inline u32 jbd2_chksum(journal_t *journal, u32 crc,
 	return *(u32 *)desc.ctx;
 }
 
+/* Return most recent uncommitted transaction */
+static inline tid_t  jbd2_get_latest_transaction(journal_t *journal)
+{
+	tid_t tid;
+
+	read_lock(&journal->j_state_lock);
+	tid = journal->j_commit_request;
+	if (journal->j_running_transaction)
+		tid = journal->j_running_transaction->t_tid;
+	read_unlock(&journal->j_state_lock);
+	return tid;
+}
+
 #ifdef __KERNEL__
 
 #define buffer_trace_init(bh)	do {} while (0)
diff --git a/include/linux/jbd_common.h b/include/linux/jbd_common.h
index 6133679bc4c0..3dc53432355f 100644
--- a/include/linux/jbd_common.h
+++ b/include/linux/jbd_common.h
@@ -1,31 +1,7 @@
 #ifndef _LINUX_JBD_STATE_H
 #define _LINUX_JBD_STATE_H
 
-enum jbd_state_bits {
-	BH_JBD			/* Has an attached ext3 journal_head */
-	  = BH_PrivateStart,
-	BH_JWrite,		/* Being written to log (@@@ DEBUGGING) */
-	BH_Freed,		/* Has been freed (truncated) */
-	BH_Revoked,		/* Has been revoked from the log */
-	BH_RevokeValid,		/* Revoked flag is valid */
-	BH_JBDDirty,		/* Is dirty but journaled */
-	BH_State,		/* Pins most journal_head state */
-	BH_JournalHead,		/* Pins bh->b_private and jh->b_bh */
-	BH_Unshadow,		/* Dummy bit, for BJ_Shadow wakeup filtering */
-	BH_Verified,		/* Metadata block has been verified ok */
-	BH_JBDPrivateStart,	/* First bit available for private use by FS */
-};
-
-BUFFER_FNS(JBD, jbd)
-BUFFER_FNS(JWrite, jwrite)
-BUFFER_FNS(JBDDirty, jbddirty)
-TAS_BUFFER_FNS(JBDDirty, jbddirty)
-BUFFER_FNS(Revoked, revoked)
-TAS_BUFFER_FNS(Revoked, revoked)
-BUFFER_FNS(RevokeValid, revokevalid)
-TAS_BUFFER_FNS(RevokeValid, revokevalid)
-BUFFER_FNS(Freed, freed)
-BUFFER_FNS(Verified, verified)
+#include <linux/bit_spinlock.h>
 
 static inline struct buffer_head *jh2bh(struct journal_head *jh)
 {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index f0eea07d2c2b..8db53cfaccdb 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -23,6 +23,7 @@
 #include <linux/ratelimit.h>
 #include <linux/err.h>
 #include <linux/irqflags.h>
+#include <linux/context_tracking.h>
 #include <asm/signal.h>
 
 #include <linux/kvm.h>
@@ -760,42 +761,6 @@ static inline int kvm_iommu_unmap_guest(struct kvm *kvm)
 }
 #endif
 
-static inline void __guest_enter(void)
-{
-	/*
-	 * This is running in ioctl context so we can avoid
-	 * the call to vtime_account() with its unnecessary idle check.
-	 */
-	vtime_account_system(current);
-	current->flags |= PF_VCPU;
-}
-
-static inline void __guest_exit(void)
-{
-	/*
-	 * This is running in ioctl context so we can avoid
-	 * the call to vtime_account() with its unnecessary idle check.
-	 */
-	vtime_account_system(current);
-	current->flags &= ~PF_VCPU;
-}
-
-#ifdef CONFIG_CONTEXT_TRACKING
-extern void guest_enter(void);
-extern void guest_exit(void);
-
-#else /* !CONFIG_CONTEXT_TRACKING */
-static inline void guest_enter(void)
-{
-	__guest_enter();
-}
-
-static inline void guest_exit(void)
-{
-	__guest_exit();
-}
-#endif /* !CONFIG_CONTEXT_TRACKING */
-
 static inline void kvm_guest_enter(void)
 {
 	unsigned long flags;
diff --git a/include/linux/loop.h b/include/linux/loop.h
deleted file mode 100644
index 460b60fa7adf..000000000000
--- a/include/linux/loop.h
+++ /dev/null
@@ -1,85 +0,0 @@
-/*
- * include/linux/loop.h
- *
- * Written by Theodore Ts'o, 3/29/93.
- *
- * Copyright 1993 by Theodore Ts'o.  Redistribution of this file is
- * permitted under the GNU General Public License.
- */
-#ifndef _LINUX_LOOP_H
-#define _LINUX_LOOP_H
-
-#include <linux/bio.h>
-#include <linux/blkdev.h>
-#include <linux/spinlock.h>
-#include <linux/mutex.h>
-#include <uapi/linux/loop.h>
-
-/* Possible states of device */
-enum {
-	Lo_unbound,
-	Lo_bound,
-	Lo_rundown,
-};
-
-struct loop_func_table;
-
-struct loop_device {
-	int		lo_number;
-	int		lo_refcnt;
-	loff_t		lo_offset;
-	loff_t		lo_sizelimit;
-	int		lo_flags;
-	int		(*transfer)(struct loop_device *, int cmd,
-				    struct page *raw_page, unsigned raw_off,
-				    struct page *loop_page, unsigned loop_off,
-				    int size, sector_t real_block);
-	char		lo_file_name[LO_NAME_SIZE];
-	char		lo_crypt_name[LO_NAME_SIZE];
-	char		lo_encrypt_key[LO_KEY_SIZE];
-	int		lo_encrypt_key_size;
-	struct loop_func_table *lo_encryption;
-	__u32           lo_init[2];
-	kuid_t		lo_key_owner;	/* Who set the key */
-	int		(*ioctl)(struct loop_device *, int cmd, 
-				 unsigned long arg); 
-
-	struct file *	lo_backing_file;
-	struct block_device *lo_device;
-	unsigned	lo_blocksize;
-	void		*key_data; 
-
-	gfp_t		old_gfp_mask;
-
-	spinlock_t		lo_lock;
-	struct bio_list		lo_bio_list;
-	unsigned int		lo_bio_count;
-	int			lo_state;
-	struct mutex		lo_ctl_mutex;
-	struct task_struct	*lo_thread;
-	wait_queue_head_t	lo_event;
-	/* wait queue for incoming requests */
-	wait_queue_head_t	lo_req_wait;
-
-	struct request_queue	*lo_queue;
-	struct gendisk		*lo_disk;
-};
-
-/* Support for loadable transfer modules */
-struct loop_func_table {
-	int number;	/* filter type */ 
-	int (*transfer)(struct loop_device *lo, int cmd,
-			struct page *raw_page, unsigned raw_off,
-			struct page *loop_page, unsigned loop_off,
-			int size, sector_t real_block);
-	int (*init)(struct loop_device *, const struct loop_info64 *); 
-	/* release is called from loop_unregister_transfer or clr_fd */
-	int (*release)(struct loop_device *); 
-	int (*ioctl)(struct loop_device *, int cmd, unsigned long arg);
-	struct module *owner;
-}; 
-
-int loop_register_transfer(struct loop_func_table *funcs);
-int loop_unregister_transfer(int number); 
-
-#endif
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e0c8528a41a4..66d881f1d576 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1041,7 +1041,8 @@ int get_kernel_page(unsigned long start, int write, struct page **pages);
 struct page *get_dump_page(unsigned long addr);
 
 extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
-extern void do_invalidatepage(struct page *page, unsigned long offset);
+extern void do_invalidatepage(struct page *page, unsigned int offset,
+			      unsigned int length);
 
 int __set_page_dirty_nobuffers(struct page *page);
 int __set_page_dirty_no_writeback(struct page *page);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 60584b185a0c..96e4c21e15e0 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1695,6 +1695,7 @@ extern int		init_dummy_netdev(struct net_device *dev);
 extern struct net_device	*dev_get_by_index(struct net *net, int ifindex);
 extern struct net_device	*__dev_get_by_index(struct net *net, int ifindex);
 extern struct net_device	*dev_get_by_index_rcu(struct net *net, int ifindex);
+extern int		netdev_get_name(struct net *net, char *name, int ifindex);
 extern int		dev_restart(struct net_device *dev);
 #ifdef CONFIG_NETPOLL_TRAP
 extern int		netpoll_trap(void);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f463a46424e2..c5b6dbf9c2fc 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -389,8 +389,7 @@ struct perf_event {
 	/* mmap bits */
 	struct mutex			mmap_mutex;
 	atomic_t			mmap_count;
-	int				mmap_locked;
-	struct user_struct		*mmap_user;
+
 	struct ring_buffer		*rb;
 	struct list_head		rb_entry;
 
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 87a03c746f17..f5d4723cdb3d 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -33,9 +33,25 @@ do { \
 		preempt_schedule(); \
 } while (0)
 
+#ifdef CONFIG_CONTEXT_TRACKING
+
+void preempt_schedule_context(void);
+
+#define preempt_check_resched_context() \
+do { \
+	if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) \
+		preempt_schedule_context(); \
+} while (0)
+#else
+
+#define preempt_check_resched_context() preempt_check_resched()
+
+#endif /* CONFIG_CONTEXT_TRACKING */
+
 #else /* !CONFIG_PREEMPT */
 
 #define preempt_check_resched()		do { } while (0)
+#define preempt_check_resched_context()	do { } while (0)
 
 #endif /* CONFIG_PREEMPT */
 
@@ -88,7 +104,7 @@ do { \
 do { \
 	preempt_enable_no_resched_notrace(); \
 	barrier(); \
-	preempt_check_resched(); \
+	preempt_check_resched_context(); \
 } while (0)
 
 #else /* !CONFIG_PREEMPT_COUNT */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9c676eae3968..dec1748cd002 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -627,6 +627,7 @@ static inline struct rtable *skb_rtable(const struct sk_buff *skb)
 }
 
 extern void kfree_skb(struct sk_buff *skb);
+extern void kfree_skb_list(struct sk_buff *segs);
 extern void skb_tx_error(struct sk_buff *skb);
 extern void consume_skb(struct sk_buff *skb);
 extern void	       __kfree_skb(struct sk_buff *skb);
diff --git a/include/linux/smp.h b/include/linux/smp.h
index e6564c1dc552..c8488763277f 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -11,6 +11,7 @@
 #include <linux/list.h>
 #include <linux/cpumask.h>
 #include <linux/init.h>
+#include <linux/irqflags.h>
 
 extern void cpu_idle(void);
 
@@ -139,13 +140,17 @@ static inline int up_smp_call_function(smp_call_func_t func, void *info)
 }
 #define smp_call_function(func, info, wait) \
 			(up_smp_call_function(func, info))
-#define on_each_cpu(func,info,wait)		\
-	({					\
-		local_irq_disable();		\
-		func(info);			\
-		local_irq_enable();		\
-		0;				\
-	})
+
+static inline int on_each_cpu(smp_call_func_t func, void *info, int wait)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	func(info);
+	local_irq_restore(flags);
+	return 0;
+}
+
 /*
  * Note we still need to test the mask even for UP
  * because we actually can get an empty mask from
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 09a545a7dfa3..74575cbf2d6f 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -35,6 +35,7 @@ struct splice_desc {
 		void *data;		/* cookie */
 	} u;
 	loff_t pos;			/* file position */
+	loff_t *opos;			/* sendfile: output position */
 	size_t num_spliced;		/* number of bytes already spliced */
 	bool need_wakeup;		/* need to wake up writer */
 };
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index 71a5782d8c59..b1dd2db80076 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -34,7 +34,7 @@ static inline void vtime_user_exit(struct task_struct *tsk)
 }
 extern void vtime_guest_enter(struct task_struct *tsk);
 extern void vtime_guest_exit(struct task_struct *tsk);
-extern void vtime_init_idle(struct task_struct *tsk);
+extern void vtime_init_idle(struct task_struct *tsk, int cpu);
 #else
 static inline void vtime_account_irq_exit(struct task_struct *tsk)
 {
@@ -45,7 +45,7 @@ static inline void vtime_user_enter(struct task_struct *tsk) { }
 static inline void vtime_user_exit(struct task_struct *tsk) { }
 static inline void vtime_guest_enter(struct task_struct *tsk) { }
 static inline void vtime_guest_exit(struct task_struct *tsk) { }
-static inline void vtime_init_idle(struct task_struct *tsk) { }
+static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { }
 #endif
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 579a5007c696..abfe11787af3 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -78,6 +78,7 @@ struct writeback_control {
 	unsigned tagged_writepages:1;	/* tag-and-write to avoid livelock */
 	unsigned for_reclaim:1;		/* Invoked from the page allocator */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
+	unsigned for_sync:1;		/* sync(2) WB_SYNC_ALL writeback */
 };
 
 /*