Merge branch 'linus' into core/locking

Reason: Pull in the semaphore related changes

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

36 files changed, 674 insertions, 292 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 192f88c5b0f9..c9483d8f6140 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1791,19 +1791,20 @@ out:
 }
 
 /**
- * cgroup_attach_task_current_cg - attach task 'tsk' to current task's cgroup
+ * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from'
+ * @from: attach to all cgroups of a given task
  * @tsk: the task to be attached
  */
-int cgroup_attach_task_current_cg(struct task_struct *tsk)
+int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 {
 	struct cgroupfs_root *root;
-	struct cgroup *cur_cg;
 	int retval = 0;
 
 	cgroup_lock();
 	for_each_active_root(root) {
-		cur_cg = task_cgroup_from_root(current, root);
-		retval = cgroup_attach_task(cur_cg, tsk);
+		struct cgroup *from_cg = task_cgroup_from_root(from, root);
+
+		retval = cgroup_attach_task(from_cg, tsk);
 		if (retval)
 			break;
 	}
@@ -1811,7 +1812,7 @@ int cgroup_attach_task_current_cg(struct task_struct *tsk)
 
 	return retval;
 }
-EXPORT_SYMBOL_GPL(cgroup_attach_task_current_cg);
+EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
 
 /*
  * Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex
diff --git a/kernel/compat.c b/kernel/compat.c
index e167efce8423..c9e2ec0b34a8 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -1126,3 +1126,24 @@ compat_sys_sysinfo(struct compat_sysinfo __user *info)
 
 	return 0;
 }
+
+/*
+ * Allocate user-space memory for the duration of a single system call,
+ * in order to marshall parameters inside a compat thunk.
+ */
+void __user *compat_alloc_user_space(unsigned long len)
+{
+	void __user *ptr;
+
+	/* If len would occupy more than half of the entire compat space... */
+	if (unlikely(len > (((compat_uptr_t)~0) >> 1)))
+		return NULL;
+
+	ptr = arch_compat_alloc_user_space(len);
+
+	if (unlikely(!access_ok(VERIFY_WRITE, ptr, len)))
+		return NULL;
+
+	return ptr;
+}
+EXPORT_SYMBOL_GPL(compat_alloc_user_space);
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 3c2d4972d235..de407c78178d 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -741,7 +741,7 @@ static struct console kgdbcons = {
 };
 
 #ifdef CONFIG_MAGIC_SYSRQ
-static void sysrq_handle_dbg(int key, struct tty_struct *tty)
+static void sysrq_handle_dbg(int key)
 {
 	if (!dbg_io_ops) {
 		printk(KERN_CRIT "ERROR: No KGDB I/O module available\n");
diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c
index 75bd9b3ebbb7..20059ef4459a 100644
--- a/kernel/debug/kdb/kdb_bp.c
+++ b/kernel/debug/kdb/kdb_bp.c
@@ -274,7 +274,6 @@ static int kdb_bp(int argc, const char **argv)
 	int i, bpno;
 	kdb_bp_t *bp, *bp_check;
 	int diag;
-	int free;
 	char *symname = NULL;
 	long offset = 0ul;
 	int nextarg;
@@ -305,7 +304,6 @@ static int kdb_bp(int argc, const char **argv)
 	/*
 	 * Find an empty bp structure to allocate
 	 */
-	free = KDB_MAXBPT;
 	for (bpno = 0, bp = kdb_breakpoints; bpno < KDB_MAXBPT; bpno++, bp++) {
 		if (bp->bp_free)
 			break;
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 28b844118bbd..caf057a3de0e 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1929,7 +1929,7 @@ static int kdb_sr(int argc, const char **argv)
 	if (argc != 1)
 		return KDB_ARGCOUNT;
 	kdb_trap_printk++;
-	__handle_sysrq(*argv[1], NULL, 0);
+	__handle_sysrq(*argv[1], false);
 	kdb_trap_printk--;
 
 	return 0;
diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
index c438f545a321..be775f7e81e0 100644
--- a/kernel/debug/kdb/kdb_private.h
+++ b/kernel/debug/kdb/kdb_private.h
@@ -255,7 +255,14 @@ extern void kdb_ps1(const struct task_struct *p);
 extern void kdb_print_nameval(const char *name, unsigned long val);
 extern void kdb_send_sig_info(struct task_struct *p, struct siginfo *info);
 extern void kdb_meminfo_proc_show(void);
+#ifdef CONFIG_KALLSYMS
 extern const char *kdb_walk_kallsyms(loff_t *pos);
+#else /* ! CONFIG_KALLSYMS */
+static inline const char *kdb_walk_kallsyms(loff_t *pos)
+{
+	return NULL;
+}
+#endif /* ! CONFIG_KALLSYMS */
 extern char *kdb_getstr(char *, size_t, char *);
 
 /* Defines for kdb_symbol_print */
diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
index 45344d5c53dd..6b2485dcb050 100644
--- a/kernel/debug/kdb/kdb_support.c
+++ b/kernel/debug/kdb/kdb_support.c
@@ -82,8 +82,8 @@ static char *kdb_name_table[100];	/* arbitrary size */
 int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab)
 {
 	int ret = 0;
-	unsigned long symbolsize;
-	unsigned long offset;
+	unsigned long symbolsize = 0;
+	unsigned long offset = 0;
 #define knt1_size 128		/* must be >= kallsyms table size */
 	char *knt1 = NULL;
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 671ed56e0a49..03120229db28 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1386,8 +1386,7 @@ static int wait_task_stopped(struct wait_opts *wo,
 	if (!unlikely(wo->wo_flags & WNOWAIT))
 		*p_code = 0;
 
-	/* don't need the RCU readlock here as we're holding a spinlock */
-	uid = __task_cred(p)->uid;
+	uid = task_uid(p);
 unlock_sig:
 	spin_unlock_irq(&p->sighand->siglock);
 	if (!exit_code)
@@ -1460,7 +1459,7 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
 	}
 	if (!unlikely(wo->wo_flags & WNOWAIT))
 		p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
-	uid = __task_cred(p)->uid;
+	uid = task_uid(p);
 	spin_unlock_irq(&p->sighand->siglock);
 
 	pid = task_pid_vnr(p);
diff --git a/kernel/fork.c b/kernel/fork.c
index 98b450876f93..c445f8cc408d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -300,7 +300,7 @@ out:
 #ifdef CONFIG_MMU
 static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 {
-	struct vm_area_struct *mpnt, *tmp, **pprev;
+	struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
 	struct rb_node **rb_link, *rb_parent;
 	int retval;
 	unsigned long charge;
@@ -328,6 +328,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 	if (retval)
 		goto out;
 
+	prev = NULL;
 	for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
 		struct file *file;
 
@@ -355,11 +356,11 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		if (IS_ERR(pol))
 			goto fail_nomem_policy;
 		vma_set_policy(tmp, pol);
+		tmp->vm_mm = mm;
 		if (anon_vma_fork(tmp, mpnt))
 			goto fail_nomem_anon_vma_fork;
 		tmp->vm_flags &= ~VM_LOCKED;
-		tmp->vm_mm = mm;
-		tmp->vm_next = NULL;
+		tmp->vm_next = tmp->vm_prev = NULL;
 		file = tmp->vm_file;
 		if (file) {
 			struct inode *inode = file->f_path.dentry->d_inode;
@@ -392,6 +393,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		 */
 		*pprev = tmp;
 		pprev = &tmp->vm_next;
+		tmp->vm_prev = prev;
+		prev = tmp;
 
 		__vma_link_rb(mm, tmp, rb_link, rb_parent);
 		rb_link = &tmp->vm_rb.rb_right;
@@ -752,13 +755,13 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
 	struct fs_struct *fs = current->fs;
 	if (clone_flags & CLONE_FS) {
 		/* tsk->fs is already what we want */
-		write_lock(&fs->lock);
+		spin_lock(&fs->lock);
 		if (fs->in_exec) {
-			write_unlock(&fs->lock);
+			spin_unlock(&fs->lock);
 			return -EAGAIN;
 		}
 		fs->users++;
-		write_unlock(&fs->lock);
+		spin_unlock(&fs->lock);
 		return 0;
 	}
 	tsk->fs = copy_fs_struct(fs);
@@ -1676,13 +1679,13 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 
 		if (new_fs) {
 			fs = current->fs;
-			write_lock(&fs->lock);
+			spin_lock(&fs->lock);
 			current->fs = new_fs;
 			if (--fs->users)
 				new_fs = NULL;
 			else
 				new_fs = fs;
-			write_unlock(&fs->lock);
+			spin_unlock(&fs->lock);
 		}
 
 		if (new_mm) {
diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c
index ef3c3f88a7a3..f83972b16564 100644
--- a/kernel/gcov/fs.c
+++ b/kernel/gcov/fs.c
@@ -33,10 +33,11 @@
  * @children: child nodes
  * @all: list head for list of all nodes
  * @parent: parent node
- * @info: associated profiling data structure if not a directory
- * @ghost: when an object file containing profiling data is unloaded we keep a
- *         copy of the profiling data here to allow collecting coverage data
- *         for cleanup code. Such a node is called a "ghost".
+ * @loaded_info: array of pointers to profiling data sets for loaded object
+ *   files.
+ * @num_loaded: number of profiling data sets for loaded object files.
+ * @unloaded_info: accumulated copy of profiling data sets for unloaded
+ *   object files. Used only when gcov_persist=1.
  * @dentry: main debugfs entry, either a directory or data file
  * @links: associated symbolic links
  * @name: data file basename
@@ -51,10 +52,11 @@ struct gcov_node {
 	struct list_head children;
 	struct list_head all;
 	struct gcov_node *parent;
-	struct gcov_info *info;
-	struct gcov_info *ghost;
+	struct gcov_info **loaded_info;
+	struct gcov_info *unloaded_info;
 	struct dentry *dentry;
 	struct dentry **links;
+	int num_loaded;
 	char name[0];
 };
 
@@ -136,16 +138,37 @@ static const struct seq_operations gcov_seq_ops = {
 };
 
 /*
- * Return the profiling data set for a given node. This can either be the
- * original profiling data structure or a duplicate (also called "ghost")
- * in case the associated object file has been unloaded.
+ * Return a profiling data set associated with the given node. This is
+ * either a data set for a loaded object file or a data set copy in case
+ * all associated object files have been unloaded.
  */
 static struct gcov_info *get_node_info(struct gcov_node *node)
 {
-	if (node->info)
-		return node->info;
+	if (node->num_loaded > 0)
+		return node->loaded_info[0];
 
-	return node->ghost;
+	return node->unloaded_info;
+}
+
+/*
+ * Return a newly allocated profiling data set which contains the sum of
+ * all profiling data associated with the given node.
+ */
+static struct gcov_info *get_accumulated_info(struct gcov_node *node)
+{
+	struct gcov_info *info;
+	int i = 0;
+
+	if (node->unloaded_info)
+		info = gcov_info_dup(node->unloaded_info);
+	else
+		info = gcov_info_dup(node->loaded_info[i++]);
+	if (!info)
+		return NULL;
+	for (; i < node->num_loaded; i++)
+		gcov_info_add(info, node->loaded_info[i]);
+
+	return info;
 }
 
 /*
@@ -163,9 +186,10 @@ static int gcov_seq_open(struct inode *inode, struct file *file)
 	mutex_lock(&node_lock);
 	/*
 	 * Read from a profiling data copy to minimize reference tracking
-	 * complexity and concurrent access.
+	 * complexity and concurrent access and to keep accumulating multiple
+	 * profiling data sets associated with one node simple.
 	 */
-	info = gcov_info_dup(get_node_info(node));
+	info = get_accumulated_info(node);
 	if (!info)
 		goto out_unlock;
 	iter = gcov_iter_new(info);
@@ -225,12 +249,25 @@ static struct gcov_node *get_node_by_name(const char *name)
 	return NULL;
 }
 
+/*
+ * Reset all profiling data associated with the specified node.
+ */
+static void reset_node(struct gcov_node *node)
+{
+	int i;
+
+	if (node->unloaded_info)
+		gcov_info_reset(node->unloaded_info);
+	for (i = 0; i < node->num_loaded; i++)
+		gcov_info_reset(node->loaded_info[i]);
+}
+
 static void remove_node(struct gcov_node *node);
 
 /*
  * write() implementation for gcov data files. Reset profiling data for the
- * associated file. If the object file has been unloaded (i.e. this is
- * a "ghost" node), remove the debug fs node as well.
+ * corresponding file. If all associated object files have been unloaded,
+ * remove the debug fs node as well.
  */
 static ssize_t gcov_seq_write(struct file *file, const char __user *addr,
 			      size_t len, loff_t *pos)
@@ -245,10 +282,10 @@ static ssize_t gcov_seq_write(struct file *file, const char __user *addr,
 	node = get_node_by_name(info->filename);
 	if (node) {
 		/* Reset counts or remove node for unloaded modules. */
-		if (node->ghost)
+		if (node->num_loaded == 0)
 			remove_node(node);
 		else
-			gcov_info_reset(node->info);
+			reset_node(node);
 	}
 	/* Reset counts for open file. */
 	gcov_info_reset(info);
@@ -378,7 +415,10 @@ static void init_node(struct gcov_node *node, struct gcov_info *info,
 	INIT_LIST_HEAD(&node->list);
 	INIT_LIST_HEAD(&node->children);
 	INIT_LIST_HEAD(&node->all);
-	node->info = info;
+	if (node->loaded_info) {
+		node->loaded_info[0] = info;
+		node->num_loaded = 1;
+	}
 	node->parent = parent;
 	if (name)
 		strcpy(node->name, name);
@@ -394,9 +434,13 @@ static struct gcov_node *new_node(struct gcov_node *parent,
 	struct gcov_node *node;
 
 	node = kzalloc(sizeof(struct gcov_node) + strlen(name) + 1, GFP_KERNEL);
-	if (!node) {
-		pr_warning("out of memory\n");
-		return NULL;
+	if (!node)
+		goto err_nomem;
+	if (info) {
+		node->loaded_info = kcalloc(1, sizeof(struct gcov_info *),
+					   GFP_KERNEL);
+		if (!node->loaded_info)
+			goto err_nomem;
 	}
 	init_node(node, info, name, parent);
 	/* Differentiate between gcov data file nodes and directory nodes. */
@@ -416,6 +460,11 @@ static struct gcov_node *new_node(struct gcov_node *parent,
 	list_add(&node->all, &all_head);
 
 	return node;
+
+err_nomem:
+	kfree(node);
+	pr_warning("out of memory\n");
+	return NULL;
 }
 
 /* Remove symbolic links associated with node. */
@@ -441,8 +490,9 @@ static void release_node(struct gcov_node *node)
 	list_del(&node->all);
 	debugfs_remove(node->dentry);
 	remove_links(node);
-	if (node->ghost)
-		gcov_info_free(node->ghost);
+	kfree(node->loaded_info);
+	if (node->unloaded_info)
+		gcov_info_free(node->unloaded_info);
 	kfree(node);
 }
 
@@ -477,7 +527,7 @@ static struct gcov_node *get_child_by_name(struct gcov_node *parent,
 
 /*
  * write() implementation for reset file. Reset all profiling data to zero
- * and remove ghost nodes.
+ * and remove nodes for which all associated object files are unloaded.
  */
 static ssize_t reset_write(struct file *file, const char __user *addr,
 			   size_t len, loff_t *pos)
@@ -487,8 +537,8 @@ static ssize_t reset_write(struct file *file, const char __user *addr,
 	mutex_lock(&node_lock);
 restart:
 	list_for_each_entry(node, &all_head, all) {
-		if (node->info)
-			gcov_info_reset(node->info);
+		if (node->num_loaded > 0)
+			reset_node(node);
 		else if (list_empty(&node->children)) {
 			remove_node(node);
 			/* Several nodes may have gone - restart loop. */
@@ -564,37 +614,115 @@ err_remove:
 }
 
 /*
- * The profiling data set associated with this node is being unloaded. Store a
- * copy of the profiling data and turn this node into a "ghost".
+ * Associate a profiling data set with an existing node. Needs to be called
+ * with node_lock held.
  */
-static int ghost_node(struct gcov_node *node)
+static void add_info(struct gcov_node *node, struct gcov_info *info)
 {
-	node->ghost = gcov_info_dup(node->info);
-	if (!node->ghost) {
-		pr_warning("could not save data for '%s' (out of memory)\n",
-			   node->info->filename);
-		return -ENOMEM;
+	struct gcov_info **loaded_info;
+	int num = node->num_loaded;
+
+	/*
+	 * Prepare new array. This is done first to simplify cleanup in
+	 * case the new data set is incompatible, the node only contains
+	 * unloaded data sets and there's not enough memory for the array.
+	 */
+	loaded_info = kcalloc(num + 1, sizeof(struct gcov_info *), GFP_KERNEL);
+	if (!loaded_info) {
+		pr_warning("could not add '%s' (out of memory)\n",
+			   info->filename);
+		return;
+	}
+	memcpy(loaded_info, node->loaded_info,
+	       num * sizeof(struct gcov_info *));
+	loaded_info[num] = info;
+	/* Check if the new data set is compatible. */
+	if (num == 0) {
+		/*
+		 * A module was unloaded, modified and reloaded. The new
+		 * data set replaces the copy of the last one.
+		 */
+		if (!gcov_info_is_compatible(node->unloaded_info, info)) {
+			pr_warning("discarding saved data for %s "
+				   "(incompatible version)\n", info->filename);
+			gcov_info_free(node->unloaded_info);
+			node->unloaded_info = NULL;
+		}
+	} else {
+		/*
+		 * Two different versions of the same object file are loaded.
+		 * The initial one takes precedence.
+		 */
+		if (!gcov_info_is_compatible(node->loaded_info[0], info)) {
+			pr_warning("could not add '%s' (incompatible "
+				   "version)\n", info->filename);
+			kfree(loaded_info);
+			return;
+		}
 	}
-	node->info = NULL;
+	/* Overwrite previous array. */
+	kfree(node->loaded_info);
+	node->loaded_info = loaded_info;
+	node->num_loaded = num + 1;
+}
 
-	return 0;
+/*
+ * Return the index of a profiling data set associated with a node.
+ */
+static int get_info_index(struct gcov_node *node, struct gcov_info *info)
+{
+	int i;
+
+	for (i = 0; i < node->num_loaded; i++) {
+		if (node->loaded_info[i] == info)
+			return i;
+	}
+	return -ENOENT;
 }
 
 /*
- * Profiling data for this node has been loaded again. Add profiling data
- * from previous instantiation and turn this node into a regular node.
+ * Save the data of a profiling data set which is being unloaded.
  */
-static void revive_node(struct gcov_node *node, struct gcov_info *info)
+static void save_info(struct gcov_node *node, struct gcov_info *info)
 {
-	if (gcov_info_is_compatible(node->ghost, info))
-		gcov_info_add(info, node->ghost);
+	if (node->unloaded_info)
+		gcov_info_add(node->unloaded_info, info);
 	else {
-		pr_warning("discarding saved data for '%s' (version changed)\n",
+		node->unloaded_info = gcov_info_dup(info);
+		if (!node->unloaded_info) {
+			pr_warning("could not save data for '%s' "
+				   "(out of memory)\n", info->filename);
+		}
+	}
+}
+
+/*
+ * Disassociate a profiling data set from a node. Needs to be called with
+ * node_lock held.
+ */
+static void remove_info(struct gcov_node *node, struct gcov_info *info)
+{
+	int i;
+
+	i = get_info_index(node, info);
+	if (i < 0) {
+		pr_warning("could not remove '%s' (not found)\n",
 			   info->filename);
+		return;
 	}
-	gcov_info_free(node->ghost);
-	node->ghost = NULL;
-	node->info = info;
+	if (gcov_persist)
+		save_info(node, info);
+	/* Shrink array. */
+	node->loaded_info[i] = node->loaded_info[node->num_loaded - 1];
+	node->num_loaded--;
+	if (node->num_loaded > 0)
+		return;
+	/* Last loaded data set was removed. */
+	kfree(node->loaded_info);
+	node->loaded_info = NULL;
+	node->num_loaded = 0;
+	if (!node->unloaded_info)
+		remove_node(node);
 }
 
 /*
@@ -609,30 +737,18 @@ void gcov_event(enum gcov_action action, struct gcov_info *info)
 	node = get_node_by_name(info->filename);
 	switch (action) {
 	case GCOV_ADD:
-		/* Add new node or revive ghost. */
-		if (!node) {
+		if (node)
+			add_info(node, info);
+		else
 			add_node(info);
-			break;
-		}
-		if (gcov_persist)
-			revive_node(node, info);
-		else {
-			pr_warning("could not add '%s' (already exists)\n",
-				   info->filename);
-		}
 		break;
 	case GCOV_REMOVE:
-		/* Remove node or turn into ghost. */
-		if (!node) {
+		if (node)
+			remove_info(node, info);
+		else {
 			pr_warning("could not remove '%s' (not found)\n",
 				   info->filename);
-			break;
 		}
-		if (gcov_persist) {
-			if (!ghost_node(node))
-				break;
-		}
-		remove_node(node);
 		break;
 	}
 	mutex_unlock(&node_lock);
diff --git a/kernel/groups.c b/kernel/groups.c
index 53b1916c9492..253dc0f35cf4 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -143,10 +143,9 @@ int groups_search(const struct group_info *group_info, gid_t grp)
 	right = group_info->ngroups;
 	while (left < right) {
 		unsigned int mid = (left+right)/2;
-		int cmp = grp - GROUP_AT(group_info, mid);
-		if (cmp > 0)
+		if (grp > GROUP_AT(group_info, mid))
 			left = mid + 1;
-		else if (cmp < 0)
+		else if (grp < GROUP_AT(group_info, mid))
 			right = mid;
 		else
 			return 1;
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index ce669174f355..1decafbb6b1a 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1091,11 +1091,10 @@ EXPORT_SYMBOL_GPL(hrtimer_cancel);
  */
 ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
 {
-	struct hrtimer_clock_base *base;
 	unsigned long flags;
 	ktime_t rem;
 
-	base = lock_hrtimer_base(timer, &flags);
+	lock_hrtimer_base(timer, &flags);
 	rem = hrtimer_expires_remaining(timer);
 	unlock_hrtimer_base(timer, &flags);
 
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index d71a987fd2bf..c7c2aed9e2dc 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -433,7 +433,8 @@ register_user_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered,
 			    struct task_struct *tsk)
 {
-	return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered);
+	return perf_event_create_kernel_counter(attr, -1, task_pid_vnr(tsk),
+						triggered);
 }
 EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
 
diff --git a/kernel/kfifo.c b/kernel/kfifo.c
index 4502604ecadf..01a0700e873f 100644
--- a/kernel/kfifo.c
+++ b/kernel/kfifo.c
@@ -365,8 +365,6 @@ static unsigned int setup_sgl(struct __kfifo *fifo, struct scatterlist *sgl,
 	n = setup_sgl_buf(sgl, fifo->data + off, nents, l);
 	n += setup_sgl_buf(sgl + n, fifo->data, nents - n, len - l);
 
-	if (n)
-		sg_mark_end(sgl + n - 1);
 	return n;
 }
 
@@ -503,6 +501,15 @@ unsigned int __kfifo_out_r(struct __kfifo *fifo, void *buf,
 }
 EXPORT_SYMBOL(__kfifo_out_r);
 
+void __kfifo_skip_r(struct __kfifo *fifo, size_t recsize)
+{
+	unsigned int n;
+
+	n = __kfifo_peek_n(fifo, recsize);
+	fifo->out += n + recsize;
+}
+EXPORT_SYMBOL(__kfifo_skip_r);
+
 int __kfifo_from_user_r(struct __kfifo *fifo, const void __user *from,
 	unsigned long len, unsigned int *copied, size_t recsize)
 {
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 6e9b19667a8d..9cd0591c96a2 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -153,7 +153,9 @@ static int ____call_usermodehelper(void *data)
 			goto fail;
 	}
 
-	retval = kernel_execve(sub_info->path, sub_info->argv, sub_info->envp);
+	retval = kernel_execve(sub_info->path,
+			       (const char *const *)sub_info->argv,
+			       (const char *const *)sub_info->envp);
 
 	/* Exec failed? */
 fail:
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 4c0b7b3e6d2e..200407c1502f 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -36,15 +36,6 @@
 # include <asm/mutex.h>
 #endif
 
-/***
- * mutex_init - initialize the mutex
- * @lock: the mutex to be initialized
- * @key: the lock_class_key for the class; used by mutex lock debugging
- *
- * Initialize the mutex to unlocked state.
- *
- * It is not allowed to initialize an already locked mutex.
- */
 void
 __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 {
@@ -68,7 +59,7 @@ EXPORT_SYMBOL(__mutex_init);
 static __used noinline void __sched
 __mutex_lock_slowpath(atomic_t *lock_count);
 
-/***
+/**
  * mutex_lock - acquire the mutex
  * @lock: the mutex to be acquired
  *
@@ -105,7 +96,7 @@ EXPORT_SYMBOL(mutex_lock);
 
 static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
 
-/***
+/**
  * mutex_unlock - release the mutex
  * @lock: the mutex to be released
  *
@@ -364,8 +355,8 @@ __mutex_lock_killable_slowpath(atomic_t *lock_count);
 static noinline int __sched
 __mutex_lock_interruptible_slowpath(atomic_t *lock_count);
 
-/***
- * mutex_lock_interruptible - acquire the mutex, interruptable
+/**
+ * mutex_lock_interruptible - acquire the mutex, interruptible
  * @lock: the mutex to be acquired
  *
  * Lock the mutex like mutex_lock(), and return 0 if the mutex has
@@ -456,15 +447,15 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count)
 	return prev == 1;
 }
 
-/***
- * mutex_trylock - try acquire the mutex, without waiting
+/**
+ * mutex_trylock - try to acquire the mutex, without waiting
  * @lock: the mutex to be acquired
  *
  * Try to acquire the mutex atomically. Returns 1 if the mutex
  * has been acquired successfully, and 0 on contention.
  *
  * NOTE: this function follows the spin_trylock() convention, so
- * it is negated to the down_trylock() return values! Be careful
+ * it is negated from the down_trylock() return values! Be careful
  * about this when converting semaphore users to mutexes.
  *
  * This function must not be used in interrupt context. The
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 403d1804b198..db5b56064687 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -402,11 +402,31 @@ static void perf_group_detach(struct perf_event *event)
 	}
 }
 
+static inline int
+event_filter_match(struct perf_event *event)
+{
+	return event->cpu == -1 || event->cpu == smp_processor_id();
+}
+
 static void
 event_sched_out(struct perf_event *event,
 		  struct perf_cpu_context *cpuctx,
 		  struct perf_event_context *ctx)
 {
+	u64 delta;
+	/*
+	 * An event which could not be activated because of
+	 * filter mismatch still needs to have its timings
+	 * maintained, otherwise bogus information is return
+	 * via read() for time_enabled, time_running:
+	 */
+	if (event->state == PERF_EVENT_STATE_INACTIVE
+	    && !event_filter_match(event)) {
+		delta = ctx->time - event->tstamp_stopped;
+		event->tstamp_running += delta;
+		event->tstamp_stopped = ctx->time;
+	}
+
 	if (event->state != PERF_EVENT_STATE_ACTIVE)
 		return;
 
@@ -432,9 +452,7 @@ group_sched_out(struct perf_event *group_event,
 		struct perf_event_context *ctx)
 {
 	struct perf_event *event;
-
-	if (group_event->state != PERF_EVENT_STATE_ACTIVE)
-		return;
+	int state = group_event->state;
 
 	event_sched_out(group_event, cpuctx, ctx);
 
@@ -444,7 +462,7 @@ group_sched_out(struct perf_event *group_event,
 	list_for_each_entry(event, &group_event->sibling_list, group_entry)
 		event_sched_out(event, cpuctx, ctx);
 
-	if (group_event->attr.exclusive)
+	if (state == PERF_EVENT_STATE_ACTIVE && group_event->attr.exclusive)
 		cpuctx->exclusive = 0;
 }
 
@@ -5743,15 +5761,15 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long)hcpu;
 
-	switch (action) {
+	switch (action & ~CPU_TASKS_FROZEN) {
 
 	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
+	case CPU_DOWN_FAILED:
 		perf_event_init_cpu(cpu);
 		break;
 
+	case CPU_UP_CANCELED:
 	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
 		perf_event_exit_cpu(cpu);
 		break;
 
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index 996a4dec5f96..645e541a45f6 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -212,15 +212,17 @@ EXPORT_SYMBOL_GPL(pm_qos_request_active);
 
 /**
  * pm_qos_add_request - inserts new qos request into the list
- * @pm_qos_class: identifies which list of qos request to us
+ * @dep: pointer to a preallocated handle
+ * @pm_qos_class: identifies which list of qos request to use
  * @value: defines the qos request
  *
  * This function inserts a new entry in the pm_qos_class list of requested qos
  * performance characteristics.  It recomputes the aggregate QoS expectations
- * for the pm_qos_class of parameters, and returns the pm_qos_request list
- * element as a handle for use in updating and removal.  Call needs to save
- * this handle for later use.
+ * for the pm_qos_class of parameters and initializes the pm_qos_request_list
+ * handle.  Caller needs to save this handle for later use in updates and
+ * removal.
  */
+
 void pm_qos_add_request(struct pm_qos_request_list *dep,
 			int pm_qos_class, s32 value)
 {
@@ -348,7 +350,7 @@ static int pm_qos_power_open(struct inode *inode, struct file *filp)
 
 	pm_qos_class = find_pm_qos_object_by_minor(iminor(inode));
 	if (pm_qos_class >= 0) {
-		struct pm_qos_request_list *req = kzalloc(GFP_KERNEL, sizeof(*req));
+               struct pm_qos_request_list *req = kzalloc(sizeof(*req), GFP_KERNEL);
 		if (!req)
 			return -ENOMEM;
 
@@ -387,10 +389,12 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
 	} else if (count == 11) { /* len('0x12345678/0') */
 		if (copy_from_user(ascii_value, buf, 11))
 			return -EFAULT;
+		if (strlen(ascii_value) != 10)
+			return -EINVAL;
 		x = sscanf(ascii_value, "%x", &value);
 		if (x != 1)
 			return -EINVAL;
-		pr_debug(KERN_ERR "%s, %d, 0x%x\n", ascii_value, x, value);
+		pr_debug("%s, %d, 0x%x\n", ascii_value, x, value);
 	} else
 		return -EINVAL;
 
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index c77963938bca..8dc31e02ae12 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -338,7 +338,6 @@ int hibernation_snapshot(int platform_mode)
 		goto Close;
 
 	suspend_console();
-	hibernation_freeze_swap();
 	saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
 	error = dpm_suspend_start(PMSG_FREEZE);
 	if (error)
diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c
index e8b337006276..d52359374e85 100644
--- a/kernel/power/poweroff.c
+++ b/kernel/power/poweroff.c
@@ -24,7 +24,7 @@ static void do_poweroff(struct work_struct *dummy)
 
 static DECLARE_WORK(poweroff_work, do_poweroff);
 
-static void handle_poweroff(int key, struct tty_struct *tty)
+static void handle_poweroff(int key)
 {
 	/* run sysrq poweroff on boot cpu */
 	schedule_work_on(cpumask_first(cpu_online_mask), &poweroff_work);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 5e7edfb05e66..d3f795f01bbc 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1086,7 +1086,6 @@ void swsusp_free(void)
 	buffer = NULL;
 	alloc_normal = 0;
 	alloc_highmem = 0;
-	hibernation_thaw_swap();
 }
 
 /* Helper functions used for the shrinking of memory. */
@@ -1122,9 +1121,19 @@ static unsigned long preallocate_image_pages(unsigned long nr_pages, gfp_t mask)
 	return nr_alloc;
 }
 
-static unsigned long preallocate_image_memory(unsigned long nr_pages)
+static unsigned long preallocate_image_memory(unsigned long nr_pages,
+					      unsigned long avail_normal)
 {
-	return preallocate_image_pages(nr_pages, GFP_IMAGE);
+	unsigned long alloc;
+
+	if (avail_normal <= alloc_normal)
+		return 0;
+
+	alloc = avail_normal - alloc_normal;
+	if (nr_pages < alloc)
+		alloc = nr_pages;
+
+	return preallocate_image_pages(alloc, GFP_IMAGE);
 }
 
 #ifdef CONFIG_HIGHMEM
@@ -1170,15 +1179,22 @@ static inline unsigned long preallocate_highmem_fraction(unsigned long nr_pages,
  */
 static void free_unnecessary_pages(void)
 {
-	unsigned long save_highmem, to_free_normal, to_free_highmem;
+	unsigned long save, to_free_normal, to_free_highmem;
 
-	to_free_normal = alloc_normal - count_data_pages();
-	save_highmem = count_highmem_pages();
-	if (alloc_highmem > save_highmem) {
-		to_free_highmem = alloc_highmem - save_highmem;
+	save = count_data_pages();
+	if (alloc_normal >= save) {
+		to_free_normal = alloc_normal - save;
+		save = 0;
+	} else {
+		to_free_normal = 0;
+		save -= alloc_normal;
+	}
+	save += count_highmem_pages();
+	if (alloc_highmem >= save) {
+		to_free_highmem = alloc_highmem - save;
 	} else {
 		to_free_highmem = 0;
-		to_free_normal -= save_highmem - alloc_highmem;
+		to_free_normal -= save - alloc_highmem;
 	}
 
 	memory_bm_position_reset(&copy_bm);
@@ -1259,7 +1275,7 @@ int hibernate_preallocate_memory(void)
 {
 	struct zone *zone;
 	unsigned long saveable, size, max_size, count, highmem, pages = 0;
-	unsigned long alloc, save_highmem, pages_highmem;
+	unsigned long alloc, save_highmem, pages_highmem, avail_normal;
 	struct timeval start, stop;
 	int error;
 
@@ -1296,6 +1312,7 @@ int hibernate_preallocate_memory(void)
 		else
 			count += zone_page_state(zone, NR_FREE_PAGES);
 	}
+	avail_normal = count;
 	count += highmem;
 	count -= totalreserve_pages;
 
@@ -1310,12 +1327,21 @@ int hibernate_preallocate_memory(void)
 	 */
 	if (size >= saveable) {
 		pages = preallocate_image_highmem(save_highmem);
-		pages += preallocate_image_memory(saveable - pages);
+		pages += preallocate_image_memory(saveable - pages, avail_normal);
 		goto out;
 	}
 
 	/* Estimate the minimum size of the image. */
 	pages = minimum_image_size(saveable);
+	/*
+	 * To avoid excessive pressure on the normal zone, leave room in it to
+	 * accommodate an image of the minimum size (unless it's already too
+	 * small, in which case don't preallocate pages from it at all).
+	 */
+	if (avail_normal > pages)
+		avail_normal -= pages;
+	else
+		avail_normal = 0;
 	if (size < pages)
 		size = min_t(unsigned long, pages, max_size);
 
@@ -1336,16 +1362,34 @@ int hibernate_preallocate_memory(void)
 	 */
 	pages_highmem = preallocate_image_highmem(highmem / 2);
 	alloc = (count - max_size) - pages_highmem;
-	pages = preallocate_image_memory(alloc);
-	if (pages < alloc)
-		goto err_out;
-	size = max_size - size;
-	alloc = size;
-	size = preallocate_highmem_fraction(size, highmem, count);
-	pages_highmem += size;
-	alloc -= size;
-	pages += preallocate_image_memory(alloc);
-	pages += pages_highmem;
+	pages = preallocate_image_memory(alloc, avail_normal);
+	if (pages < alloc) {
+		/* We have exhausted non-highmem pages, try highmem. */
+		alloc -= pages;
+		pages += pages_highmem;
+		pages_highmem = preallocate_image_highmem(alloc);
+		if (pages_highmem < alloc)
+			goto err_out;
+		pages += pages_highmem;
+		/*
+		 * size is the desired number of saveable pages to leave in
+		 * memory, so try to preallocate (all memory - size) pages.
+		 */
+		alloc = (count - pages) - size;
+		pages += preallocate_image_highmem(alloc);
+	} else {
+		/*
+		 * There are approximately max_size saveable pages at this point
+		 * and we want to reduce this number down to size.
+		 */
+		alloc = max_size - size;
+		size = preallocate_highmem_fraction(alloc, highmem, count);
+		pages_highmem += size;
+		alloc -= size;
+		size = preallocate_image_memory(alloc, avail_normal);
+		pages_highmem += preallocate_image_highmem(alloc - size);
+		pages += pages_highmem + size;
+	}
 
 	/*
 	 * We only need as many page frames for the image as there are saveable
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 5d0059eed3e4..e6a5bdf61a37 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -136,10 +136,10 @@ sector_t alloc_swapdev_block(int swap)
 {
 	unsigned long offset;
 
-	offset = swp_offset(get_swap_for_hibernation(swap));
+	offset = swp_offset(get_swap_page_of_type(swap));
 	if (offset) {
 		if (swsusp_extents_insert(offset))
-			swap_free_for_hibernation(swp_entry(swap, offset));
+			swap_free(swp_entry(swap, offset));
 		else
 			return swapdev_block(swap, offset);
 	}
@@ -163,7 +163,7 @@ void free_all_swap_pages(int swap)
 		ext = container_of(node, struct swsusp_extent, node);
 		rb_erase(node, &swsusp_extents);
 		for (offset = ext->start; offset <= ext->end; offset++)
-			swap_free_for_hibernation(swp_entry(swap, offset));
+			swap_free(swp_entry(swap, offset));
 
 		kfree(ext);
 	}
diff --git a/kernel/sched.c b/kernel/sched.c
index 41541d79e3c8..dc85ceb90832 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1294,6 +1294,10 @@ static void resched_task(struct task_struct *p)
 static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
 {
 }
+
+static void sched_avg_update(struct rq *rq)
+{
+}
 #endif /* CONFIG_SMP */
 
 #if BITS_PER_LONG == 32
@@ -3182,6 +3186,8 @@ static void update_cpu_load(struct rq *this_rq)
 
 		this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
 	}
+
+	sched_avg_update(this_rq);
 }
 
 static void update_cpu_load_active(struct rq *this_rq)
@@ -3507,9 +3513,9 @@ void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
 
 	if (total) {
-		u64 temp;
+		u64 temp = rtime;
 
-		temp = (u64)(rtime * utime);
+		temp *= utime;
 		do_div(temp, total);
 		utime = (cputime_t)temp;
 	} else
@@ -3540,9 +3546,9 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
 
 	if (total) {
-		u64 temp;
+		u64 temp = rtime;
 
-		temp = (u64)(rtime * cputime.utime);
+		temp *= cputime.utime;
 		do_div(temp, total);
 		utime = (cputime_t)temp;
 	} else
@@ -3865,8 +3871,16 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
 		/*
 		 * Owner changed, break to re-assess state.
 		 */
-		if (lock->owner != owner)
+		if (lock->owner != owner) {
+			/*
+			 * If the lock has switched to a different owner,
+			 * we likely have heavy contention. Return 0 to quit
+			 * optimistic spinning and not contend further:
+			 */
+			if (lock->owner)
+				return 0;
 			break;
+		}
 
 		/*
 		 * Is that owner really running on that cpu?
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 806d1b227a21..db3f674ca49d 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -54,13 +54,13 @@ enum sched_tunable_scaling sysctl_sched_tunable_scaling
  * Minimal preemption granularity for CPU-bound tasks:
  * (default: 2 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
-unsigned int sysctl_sched_min_granularity = 2000000ULL;
-unsigned int normalized_sysctl_sched_min_granularity = 2000000ULL;
+unsigned int sysctl_sched_min_granularity = 750000ULL;
+unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;
 
 /*
  * is kept at sysctl_sched_latency / sysctl_sched_min_granularity
  */
-static unsigned int sched_nr_latency = 3;
+static unsigned int sched_nr_latency = 8;
 
 /*
  * After fork, child runs first. If set to 0 (default) then
@@ -1313,7 +1313,7 @@ static struct sched_group *
 find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		  int this_cpu, int load_idx)
 {
-	struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups;
+	struct sched_group *idlest = NULL, *group = sd->groups;
 	unsigned long min_load = ULONG_MAX, this_load = 0;
 	int imbalance = 100 + (sd->imbalance_pct-100)/2;
 
@@ -1348,7 +1348,6 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 
 		if (local_group) {
 			this_load = avg_load;
-			this = group;
 		} else if (avg_load < min_load) {
 			min_load = avg_load;
 			idlest = group;
@@ -2268,8 +2267,6 @@ unsigned long scale_rt_power(int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	u64 total, available;
 
-	sched_avg_update(rq);
-
 	total = sched_avg_period() + (rq->clock - rq->age_stamp);
 	available = total - rq->rt_avg;
 
@@ -3633,7 +3630,7 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)
 	if (time_before(now, nohz.next_balance))
 		return 0;
 
-	if (!rq->nr_running)
+	if (rq->idle_at_tick)
 		return 0;
 
 	first_pick_cpu = atomic_read(&nohz.first_pick_cpu);
@@ -3752,6 +3749,8 @@ static void task_fork_fair(struct task_struct *p)
 
 	raw_spin_lock_irqsave(&rq->lock, flags);
 
+	update_rq_clock(rq);
+
 	if (unlikely(task_cpu(p) != this_cpu))
 		__set_task_cpu(p, this_cpu);
 
diff --git a/kernel/sys.c b/kernel/sys.c
index e9ad44489828..7f5a0cd296a9 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -931,6 +931,7 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
 		pgid = pid;
 	if (pgid < 0)
 		return -EINVAL;
+	rcu_read_lock();
 
 	/* From this point forward we keep holding onto the tasklist lock
 	 * so that our parent does not change from under us. -DaveM
@@ -984,6 +985,7 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
 out:
 	/* All paths lead to here, thus we are safe. -DaveM */
 	write_unlock_irq(&tasklist_lock);
+	rcu_read_unlock();
 	return err;
 }
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index ca38e8e3e907..f88552c6d227 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1713,10 +1713,7 @@ static __init int sysctl_init(void)
 {
 	sysctl_set_parent(NULL, root_table);
 #ifdef CONFIG_SYSCTL_SYSCALL_CHECK
-	{
-		int err;
-		err = sysctl_check_table(current->nsproxy, root_table);
-	}
+	sysctl_check_table(current->nsproxy, root_table);
 #endif
 	return 0;
 }
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0d88ce9b9fb8..fa7ece649fe1 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -381,12 +381,19 @@ static int function_stat_show(struct seq_file *m, void *v)
 {
 	struct ftrace_profile *rec = v;
 	char str[KSYM_SYMBOL_LEN];
+	int ret = 0;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	static DEFINE_MUTEX(mutex);
 	static struct trace_seq s;
 	unsigned long long avg;
 	unsigned long long stddev;
 #endif
+	mutex_lock(&ftrace_profile_lock);
+
+	/* we raced with function_profile_reset() */
+	if (unlikely(rec->counter == 0)) {
+		ret = -EBUSY;
+		goto out;
+	}
 
 	kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
 	seq_printf(m, "  %-30.30s  %10lu", str, rec->counter);
@@ -408,7 +415,6 @@ static int function_stat_show(struct seq_file *m, void *v)
 		do_div(stddev, (rec->counter - 1) * 1000);
 	}
 
-	mutex_lock(&mutex);
 	trace_seq_init(&s);
 	trace_print_graph_duration(rec->time, &s);
 	trace_seq_puts(&s, "    ");
@@ -416,11 +422,12 @@ static int function_stat_show(struct seq_file *m, void *v)
 	trace_seq_puts(&s, "    ");
 	trace_print_graph_duration(stddev, &s);
 	trace_print_seq(m, &s);
-	mutex_unlock(&mutex);
 #endif
 	seq_putc(m, '\n');
+out:
+	mutex_unlock(&ftrace_profile_lock);
 
-	return 0;
+	return ret;
 }
 
 static void ftrace_profile_reset(struct ftrace_profile_stat *stat)
@@ -1503,6 +1510,8 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 		if (*pos > 0)
 			return t_hash_start(m, pos);
 		iter->flags |= FTRACE_ITER_PRINTALL;
+		/* reset in case of seek/pread */
+		iter->flags &= ~FTRACE_ITER_HASH;
 		return iter;
 	}
 
@@ -2409,7 +2418,7 @@ static const struct file_operations ftrace_filter_fops = {
 	.open = ftrace_filter_open,
 	.read = seq_read,
 	.write = ftrace_filter_write,
-	.llseek = ftrace_regex_lseek,
+	.llseek = no_llseek,
 	.release = ftrace_filter_release,
 };
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 3632ce87674f..492197e2f86c 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2985,13 +2985,11 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
 
 static void rb_advance_iter(struct ring_buffer_iter *iter)
 {
-	struct ring_buffer *buffer;
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event;
 	unsigned length;
 
 	cpu_buffer = iter->cpu_buffer;
-	buffer = cpu_buffer->buffer;
 
 	/*
 	 * Check if we are at the end of the buffer.
@@ -3846,6 +3844,9 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 			rpos = reader->read;
 			pos += size;
 
+			if (rpos >= commit)
+				break;
+
 			event = rb_reader_event(cpu_buffer);
 			size = rb_event_length(event);
 		} while (len > size);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ba14a22be4cc..9ec59f541156 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3463,6 +3463,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 					size_t cnt, loff_t *fpos)
 {
 	char *buf;
+	size_t written;
 
 	if (tracing_disabled)
 		return -EINVAL;
@@ -3484,11 +3485,15 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	} else
 		buf[cnt] = '\0';
 
-	cnt = mark_printk("%s", buf);
+	written = mark_printk("%s", buf);
 	kfree(buf);
-	*fpos += cnt;
+	*fpos += written;
 
-	return cnt;
+	/* don't tell userspace we wrote more - it might confuse them */
+	if (written > cnt)
+		written = cnt;
+
+	return written;
 }
 
 static int tracing_clock_show(struct seq_file *m, void *v)
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 000e6e85b445..31cc4cb0dbf2 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -91,6 +91,8 @@ int perf_trace_init(struct perf_event *p_event)
 		    tp_event->class && tp_event->class->reg &&
 		    try_module_get(tp_event->mod)) {
 			ret = perf_trace_event_init(tp_event, p_event);
+			if (ret)
+				module_put(tp_event->mod);
 			break;
 		}
 	}
@@ -146,6 +148,7 @@ void perf_trace_destroy(struct perf_event *p_event)
 		}
 	}
 out:
+	module_put(tp_event->mod);
 	mutex_unlock(&event_mutex);
 }
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 09b4fa6e4d3b..4c758f146328 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -598,88 +598,165 @@ out:
 	return ret;
 }
 
-static void print_event_fields(struct trace_seq *s, struct list_head *head)
+enum {
+	FORMAT_HEADER		= 1,
+	FORMAT_PRINTFMT		= 2,
+};
+
+static void *f_next(struct seq_file *m, void *v, loff_t *pos)
 {
+	struct ftrace_event_call *call = m->private;
 	struct ftrace_event_field *field;
+	struct list_head *head;
 
-	list_for_each_entry_reverse(field, head, link) {
-		/*
-		 * Smartly shows the array type(except dynamic array).
-		 * Normal:
-		 *	field:TYPE VAR
-		 * If TYPE := TYPE[LEN], it is shown:
-		 *	field:TYPE VAR[LEN]
-		 */
-		const char *array_descriptor = strchr(field->type, '[');
+	(*pos)++;
 
-		if (!strncmp(field->type, "__data_loc", 10))
-			array_descriptor = NULL;
+	switch ((unsigned long)v) {
+	case FORMAT_HEADER:
+		head = &ftrace_common_fields;
 
-		if (!array_descriptor) {
-			trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;"
-					"\tsize:%u;\tsigned:%d;\n",
-					field->type, field->name, field->offset,
-					field->size, !!field->is_signed);
-		} else {
-			trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;"
-					"\tsize:%u;\tsigned:%d;\n",
-					(int)(array_descriptor - field->type),
-					field->type, field->name,
-					array_descriptor, field->offset,
-					field->size, !!field->is_signed);
-		}
+		if (unlikely(list_empty(head)))
+			return NULL;
+
+		field = list_entry(head->prev, struct ftrace_event_field, link);
+		return field;
+
+	case FORMAT_PRINTFMT:
+		/* all done */
+		return NULL;
+	}
+
+	head = trace_get_fields(call);
+
+	/*
+	 * To separate common fields from event fields, the
+	 * LSB is set on the first event field. Clear it in case.
+	 */
+	v = (void *)((unsigned long)v & ~1L);
+
+	field = v;
+	/*
+	 * If this is a common field, and at the end of the list, then
+	 * continue with main list.
+	 */
+	if (field->link.prev == &ftrace_common_fields) {
+		if (unlikely(list_empty(head)))
+			return NULL;
+		field = list_entry(head->prev, struct ftrace_event_field, link);
+		/* Set the LSB to notify f_show to print an extra newline */
+		field = (struct ftrace_event_field *)
+			((unsigned long)field | 1);
+		return field;
 	}
+
+	/* If we are done tell f_show to print the format */
+	if (field->link.prev == head)
+		return (void *)FORMAT_PRINTFMT;
+
+	field = list_entry(field->link.prev, struct ftrace_event_field, link);
+
+	return field;
 }
 
-static ssize_t
-event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
-		  loff_t *ppos)
+static void *f_start(struct seq_file *m, loff_t *pos)
 {
-	struct ftrace_event_call *call = filp->private_data;
-	struct list_head *head;
-	struct trace_seq *s;
-	char *buf;
-	int r;
+	loff_t l = 0;
+	void *p;
 
-	if (*ppos)
+	/* Start by showing the header */
+	if (!*pos)
+		return (void *)FORMAT_HEADER;
+
+	p = (void *)FORMAT_HEADER;
+	do {
+		p = f_next(m, p, &l);
+	} while (p && l < *pos);
+
+	return p;
+}
+
+static int f_show(struct seq_file *m, void *v)
+{
+	struct ftrace_event_call *call = m->private;
+	struct ftrace_event_field *field;
+	const char *array_descriptor;
+
+	switch ((unsigned long)v) {
+	case FORMAT_HEADER:
+		seq_printf(m, "name: %s\n", call->name);
+		seq_printf(m, "ID: %d\n", call->event.type);
+		seq_printf(m, "format:\n");
 		return 0;
 
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
-	if (!s)
-		return -ENOMEM;
+	case FORMAT_PRINTFMT:
+		seq_printf(m, "\nprint fmt: %s\n",
+			   call->print_fmt);
+		return 0;
+	}
 
-	trace_seq_init(s);
+	/*
+	 * To separate common fields from event fields, the
+	 * LSB is set on the first event field. Clear it and
+	 * print a newline if it is set.
+	 */
+	if ((unsigned long)v & 1) {
+		seq_putc(m, '\n');
+		v = (void *)((unsigned long)v & ~1L);
+	}
 
-	trace_seq_printf(s, "name: %s\n", call->name);
-	trace_seq_printf(s, "ID: %d\n", call->event.type);
-	trace_seq_printf(s, "format:\n");
+	field = v;
 
-	/* print common fields */
-	print_event_fields(s, &ftrace_common_fields);
+	/*
+	 * Smartly shows the array type(except dynamic array).
+	 * Normal:
+	 *	field:TYPE VAR
+	 * If TYPE := TYPE[LEN], it is shown:
+	 *	field:TYPE VAR[LEN]
+	 */
+	array_descriptor = strchr(field->type, '[');
 
-	trace_seq_putc(s, '\n');
+	if (!strncmp(field->type, "__data_loc", 10))
+		array_descriptor = NULL;
 
-	/* print event specific fields */
-	head = trace_get_fields(call);
-	print_event_fields(s, head);
+	if (!array_descriptor)
+		seq_printf(m, "\tfield:%s %s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+			   field->type, field->name, field->offset,
+			   field->size, !!field->is_signed);
+	else
+		seq_printf(m, "\tfield:%.*s %s%s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+			   (int)(array_descriptor - field->type),
+			   field->type, field->name,
+			   array_descriptor, field->offset,
+			   field->size, !!field->is_signed);
 
-	r = trace_seq_printf(s, "\nprint fmt: %s\n", call->print_fmt);
+	return 0;
+}
 
-	if (!r) {
-		/*
-		 * ug!  The format output is bigger than a PAGE!!
-		 */
-		buf = "FORMAT TOO BIG\n";
-		r = simple_read_from_buffer(ubuf, cnt, ppos,
-					      buf, strlen(buf));
-		goto out;
-	}
+static void f_stop(struct seq_file *m, void *p)
+{
+}
 
-	r = simple_read_from_buffer(ubuf, cnt, ppos,
-				    s->buffer, s->len);
- out:
-	kfree(s);
-	return r;
+static const struct seq_operations trace_format_seq_ops = {
+	.start		= f_start,
+	.next		= f_next,
+	.stop		= f_stop,
+	.show		= f_show,
+};
+
+static int trace_format_open(struct inode *inode, struct file *file)
+{
+	struct ftrace_event_call *call = inode->i_private;
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, &trace_format_seq_ops);
+	if (ret < 0)
+		return ret;
+
+	m = file->private_data;
+	m->private = call;
+
+	return 0;
 }
 
 static ssize_t
@@ -877,8 +954,10 @@ static const struct file_operations ftrace_enable_fops = {
 };
 
 static const struct file_operations ftrace_event_format_fops = {
-	.open = tracing_open_generic,
-	.read = event_format_read,
+	.open = trace_format_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = seq_release,
 };
 
 static const struct file_operations ftrace_event_id_fops = {
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 6bff23625781..6f233698518e 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -507,7 +507,15 @@ get_return_for_leaf(struct trace_iterator *iter,
 			 * if the output fails.
 			 */
 			data->ent = *curr;
-			data->ret = *next;
+			/*
+			 * If the next event is not a return type, then
+			 * we only care about what type it is. Otherwise we can
+			 * safely copy the entire event.
+			 */
+			if (next->ent.type == TRACE_GRAPH_RET)
+				data->ret = *next;
+			else
+				data->ret.ent.type = next->ent.type;
 		}
 	}
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 8b27c9849b42..544301d29dee 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -514,8 +514,8 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
 static int kretprobe_dispatcher(struct kretprobe_instance *ri,
 				struct pt_regs *regs);
 
-/* Check the name is good for event/group */
-static int check_event_name(const char *name)
+/* Check the name is good for event/group/fields */
+static int is_good_name(const char *name)
 {
 	if (!isalpha(*name) && *name != '_')
 		return 0;
@@ -557,7 +557,7 @@ static struct trace_probe *alloc_trace_probe(const char *group,
 	else
 		tp->rp.kp.pre_handler = kprobe_dispatcher;
 
-	if (!event || !check_event_name(event)) {
+	if (!event || !is_good_name(event)) {
 		ret = -EINVAL;
 		goto error;
 	}
@@ -567,7 +567,7 @@ static struct trace_probe *alloc_trace_probe(const char *group,
 	if (!tp->call.name)
 		goto error;
 
-	if (!group || !check_event_name(group)) {
+	if (!group || !is_good_name(group)) {
 		ret = -EINVAL;
 		goto error;
 	}
@@ -883,7 +883,7 @@ static int create_trace_probe(int argc, char **argv)
 	int i, ret = 0;
 	int is_return = 0, is_delete = 0;
 	char *symbol = NULL, *event = NULL, *group = NULL;
-	char *arg, *tmp;
+	char *arg;
 	unsigned long offset = 0;
 	void *addr = NULL;
 	char buf[MAX_EVENT_NAME_LEN];
@@ -992,26 +992,36 @@ static int create_trace_probe(int argc, char **argv)
 	/* parse arguments */
 	ret = 0;
 	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+		/* Increment count for freeing args in error case */
+		tp->nr_args++;
+
 		/* Parse argument name */
 		arg = strchr(argv[i], '=');
-		if (arg)
+		if (arg) {
 			*arg++ = '\0';
-		else
+			tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+		} else {
 			arg = argv[i];
+			/* If argument name is omitted, set "argN" */
+			snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1);
+			tp->args[i].name = kstrdup(buf, GFP_KERNEL);
+		}
 
-		tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
 		if (!tp->args[i].name) {
-			pr_info("Failed to allocate argument%d name '%s'.\n",
-				i, argv[i]);
+			pr_info("Failed to allocate argument[%d] name.\n", i);
 			ret = -ENOMEM;
 			goto error;
 		}
-		tmp = strchr(tp->args[i].name, ':');
-		if (tmp)
-			*tmp = '_';	/* convert : to _ */
+
+		if (!is_good_name(tp->args[i].name)) {
+			pr_info("Invalid argument[%d] name: %s\n",
+				i, tp->args[i].name);
+			ret = -EINVAL;
+			goto error;
+		}
 
 		if (conflict_field_name(tp->args[i].name, tp->args, i)) {
-			pr_info("Argument%d name '%s' conflicts with "
+			pr_info("Argument[%d] name '%s' conflicts with "
 				"another field.\n", i, argv[i]);
 			ret = -EINVAL;
 			goto error;
@@ -1020,12 +1030,9 @@ static int create_trace_probe(int argc, char **argv)
 		/* Parse fetch argument */
 		ret = parse_probe_arg(arg, tp, &tp->args[i], is_return);
 		if (ret) {
-			pr_info("Parse error at argument%d. (%d)\n", i, ret);
-			kfree(tp->args[i].name);
+			pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
 			goto error;
 		}
-
-		tp->nr_args++;
 	}
 
 	ret = register_trace_probe(tp);
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 056468eae7cf..a6b7e0e0f3eb 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -249,7 +249,7 @@ static int trace_lookup_stack(struct seq_file *m, long i)
 {
 	unsigned long addr = stack_dump_trace[i];
 
-	return seq_printf(m, "%pF\n", (void *)addr);
+	return seq_printf(m, "%pS\n", (void *)addr);
 }
 
 static void print_disabled(struct seq_file *m)
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index b60e2a869bba..2feb2870d3a1 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -122,7 +122,7 @@ static void __touch_watchdog(void)
 
 void touch_softlockup_watchdog(void)
 {
-	__get_cpu_var(watchdog_touch_ts) = 0;
+	__raw_get_cpu_var(watchdog_touch_ts) = 0;
 }
 EXPORT_SYMBOL(touch_softlockup_watchdog);
 
@@ -142,7 +142,14 @@ void touch_all_softlockup_watchdogs(void)
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 void touch_nmi_watchdog(void)
 {
-	__get_cpu_var(watchdog_nmi_touch) = true;
+	if (watchdog_enabled) {
+		unsigned cpu;
+
+		for_each_present_cpu(cpu) {
+			if (per_cpu(watchdog_nmi_touch, cpu) != true)
+				per_cpu(watchdog_nmi_touch, cpu) = true;
+		}
+	}
 	touch_softlockup_watchdog();
 }
 EXPORT_SYMBOL(touch_nmi_watchdog);
@@ -206,6 +213,9 @@ static void watchdog_overflow_callback(struct perf_event *event, int nmi,
 		 struct perf_sample_data *data,
 		 struct pt_regs *regs)
 {
+	/* Ensure the watchdog never gets throttled */
+	event->hw.interrupts = 0;
+
 	if (__get_cpu_var(watchdog_nmi_touch) == true) {
 		__get_cpu_var(watchdog_nmi_touch) = false;
 		return;
@@ -430,6 +440,9 @@ static int watchdog_enable(int cpu)
 		wake_up_process(p);
 	}
 
+	/* if any cpu succeeds, watchdog is considered enabled for the system */
+	watchdog_enabled = 1;
+
 	return 0;
 }
 
@@ -452,9 +465,6 @@ static void watchdog_disable(int cpu)
 		per_cpu(softlockup_watchdog, cpu) = NULL;
 		kthread_stop(p);
 	}
-
-	/* if any cpu succeeds, watchdog is considered enabled for the system */
-	watchdog_enabled = 1;
 }
 
 static void watchdog_enable_all_cpus(void)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 2994a0e3a61c..f77afd939229 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1,19 +1,26 @@
 /*
- * linux/kernel/workqueue.c
+ * kernel/workqueue.c - generic async execution with shared worker pool
  *
- * Generic mechanism for defining kernel helper threads for running
- * arbitrary tasks in process context.
+ * Copyright (C) 2002		Ingo Molnar
  *
- * Started by Ingo Molnar, Copyright (C) 2002
+ *   Derived from the taskqueue/keventd code by:
+ *     David Woodhouse <dwmw2@infradead.org>
+ *     Andrew Morton
+ *     Kai Petzke <wpp@marie.physik.tu-berlin.de>
+ *     Theodore Ts'o <tytso@mit.edu>
  *
- * Derived from the taskqueue/keventd code by:
+ * Made to use alloc_percpu by Christoph Lameter.
  *
- *   David Woodhouse <dwmw2@infradead.org>
- *   Andrew Morton
- *   Kai Petzke <wpp@marie.physik.tu-berlin.de>
- *   Theodore Ts'o <tytso@mit.edu>
+ * Copyright (C) 2010		SUSE Linux Products GmbH
+ * Copyright (C) 2010		Tejun Heo <tj@kernel.org>
  *
- * Made to use alloc_percpu by Christoph Lameter.
+ * This is the generic async execution mechanism.  Work items as are
+ * executed in process context.  The worker pool is shared and
+ * automatically managed.  There is one worker pool for each CPU and
+ * one extra for works which are better served by workers which are
+ * not bound to any specific CPU.
+ *
+ * Please read Documentation/workqueue.txt for details.
  */
 
 #include <linux/module.h>
@@ -35,6 +42,9 @@
 #include <linux/lockdep.h>
 #include <linux/idr.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/workqueue.h>
+
 #include "workqueue_sched.h"
 
 enum {
@@ -87,7 +97,8 @@ enum {
 /*
  * Structure fields follow one of the following exclusion rules.
  *
- * I: Set during initialization and read-only afterwards.
+ * I: Modifiable by initialization/destruction paths and read-only for
+ *    everyone else.
  *
  * P: Preemption protected.  Disabling preemption is enough and should
  *    only be modified and accessed from the local cpu.
@@ -195,7 +206,7 @@ typedef cpumask_var_t mayday_mask_t;
 	cpumask_test_and_set_cpu((cpu), (mask))
 #define mayday_clear_cpu(cpu, mask)		cpumask_clear_cpu((cpu), (mask))
 #define for_each_mayday_cpu(cpu, mask)		for_each_cpu((cpu), (mask))
-#define alloc_mayday_mask(maskp, gfp)		alloc_cpumask_var((maskp), (gfp))
+#define alloc_mayday_mask(maskp, gfp)		zalloc_cpumask_var((maskp), (gfp))
 #define free_mayday_mask(mask)			free_cpumask_var((mask))
 #else
 typedef unsigned long mayday_mask_t;
@@ -940,10 +951,14 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
 	struct global_cwq *gcwq;
 	struct cpu_workqueue_struct *cwq;
 	struct list_head *worklist;
+	unsigned int work_flags;
 	unsigned long flags;
 
 	debug_work_activate(work);
 
+	if (WARN_ON_ONCE(wq->flags & WQ_DYING))
+		return;
+
 	/* determine gcwq to use */
 	if (!(wq->flags & WQ_UNBOUND)) {
 		struct global_cwq *last_gcwq;
@@ -986,14 +1001,17 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
 	BUG_ON(!list_empty(&work->entry));
 
 	cwq->nr_in_flight[cwq->work_color]++;
+	work_flags = work_color_to_flags(cwq->work_color);
 
 	if (likely(cwq->nr_active < cwq->max_active)) {
 		cwq->nr_active++;
 		worklist = gcwq_determine_ins_pos(gcwq, cwq);
-	} else
+	} else {
+		work_flags |= WORK_STRUCT_DELAYED;
 		worklist = &cwq->delayed_works;
+	}
 
-	insert_work(cwq, work, worklist, work_color_to_flags(cwq->work_color));
+	insert_work(cwq, work, worklist, work_flags);
 
 	spin_unlock_irqrestore(&gcwq->lock, flags);
 }
@@ -1212,6 +1230,7 @@ static void worker_leave_idle(struct worker *worker)
  * bound), %false if offline.
  */
 static bool worker_maybe_bind_and_lock(struct worker *worker)
+__acquires(&gcwq->lock)
 {
 	struct global_cwq *gcwq = worker->gcwq;
 	struct task_struct *task = worker->task;
@@ -1485,6 +1504,8 @@ static void gcwq_mayday_timeout(unsigned long __gcwq)
  * otherwise.
  */
 static bool maybe_create_worker(struct global_cwq *gcwq)
+__releases(&gcwq->lock)
+__acquires(&gcwq->lock)
 {
 	if (!need_to_create_worker(gcwq))
 		return false;
@@ -1659,6 +1680,7 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq)
 	struct list_head *pos = gcwq_determine_ins_pos(cwq->gcwq, cwq);
 
 	move_linked_works(work, pos, NULL);
+	__clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work));
 	cwq->nr_active++;
 }
 
@@ -1666,6 +1688,7 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq)
  * cwq_dec_nr_in_flight - decrement cwq's nr_in_flight
  * @cwq: cwq of interest
  * @color: color of work which left the queue
+ * @delayed: for a delayed work
  *
  * A work either has completed or is removed from pending queue,
  * decrement nr_in_flight of its cwq and handle workqueue flushing.
@@ -1673,19 +1696,22 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq)
  * CONTEXT:
  * spin_lock_irq(gcwq->lock).
  */
-static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color)
+static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color,
+				 bool delayed)
 {
 	/* ignore uncolored works */
 	if (color == WORK_NO_COLOR)
 		return;
 
 	cwq->nr_in_flight[color]--;
-	cwq->nr_active--;
 
-	if (!list_empty(&cwq->delayed_works)) {
-		/* one down, submit a delayed one */
-		if (cwq->nr_active < cwq->max_active)
-			cwq_activate_first_delayed(cwq);
+	if (!delayed) {
+		cwq->nr_active--;
+		if (!list_empty(&cwq->delayed_works)) {
+			/* one down, submit a delayed one */
+			if (cwq->nr_active < cwq->max_active)
+				cwq_activate_first_delayed(cwq);
+		}
 	}
 
 	/* is flush in progress and are we at the flushing tip? */
@@ -1722,6 +1748,8 @@ static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color)
  * spin_lock_irq(gcwq->lock) which is released and regrabbed.
  */
 static void process_one_work(struct worker *worker, struct work_struct *work)
+__releases(&gcwq->lock)
+__acquires(&gcwq->lock)
 {
 	struct cpu_workqueue_struct *cwq = get_work_cwq(work);
 	struct global_cwq *gcwq = cwq->gcwq;
@@ -1790,7 +1818,13 @@ static void process_one_work(struct worker *worker, struct work_struct *work)
 	work_clear_pending(work);
 	lock_map_acquire(&cwq->wq->lockdep_map);
 	lock_map_acquire(&lockdep_map);
+	trace_workqueue_execute_start(work);
 	f(work);
+	/*
+	 * While we must be careful to not use "work" after this, the trace
+	 * point will only record its address.
+	 */
+	trace_workqueue_execute_end(work);
 	lock_map_release(&lockdep_map);
 	lock_map_release(&cwq->wq->lockdep_map);
 
@@ -1814,7 +1848,7 @@ static void process_one_work(struct worker *worker, struct work_struct *work)
 	hlist_del_init(&worker->hentry);
 	worker->current_work = NULL;
 	worker->current_cwq = NULL;
-	cwq_dec_nr_in_flight(cwq, work_color);
+	cwq_dec_nr_in_flight(cwq, work_color, false);
 }
 
 /**
@@ -2379,7 +2413,8 @@ static int try_to_grab_pending(struct work_struct *work)
 			debug_work_deactivate(work);
 			list_del_init(&work->entry);
 			cwq_dec_nr_in_flight(get_work_cwq(work),
-					     get_work_color(work));
+				get_work_color(work),
+				*work_data_bits(work) & WORK_STRUCT_DELAYED);
 			ret = 1;
 		}
 	}
@@ -2782,7 +2817,6 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name,
 		if (IS_ERR(rescuer->task))
 			goto err;
 
-		wq->rescuer = rescuer;
 		rescuer->task->flags |= PF_THREAD_BOUND;
 		wake_up_process(rescuer->task);
 	}
@@ -2824,6 +2858,7 @@ void destroy_workqueue(struct workqueue_struct *wq)
 {
 	unsigned int cpu;
 
+	wq->flags |= WQ_DYING;
 	flush_workqueue(wq);
 
 	/*
@@ -2848,6 +2883,7 @@ void destroy_workqueue(struct workqueue_struct *wq)
 	if (wq->flags & WQ_RESCUER) {
 		kthread_stop(wq->rescuer->task);
 		free_mayday_mask(wq->mayday_mask);
+		kfree(wq->rescuer);
 	}
 
 	free_cwqs(wq);
@@ -3230,6 +3266,8 @@ static int __cpuinit trustee_thread(void *__gcwq)
  * multiple times.  To be used by cpu_callback.
  */
 static void __cpuinit wait_trustee_state(struct global_cwq *gcwq, int state)
+__releases(&gcwq->lock)
+__acquires(&gcwq->lock)
 {
 	if (!(gcwq->trustee_state == state ||
 	      gcwq->trustee_state == TRUSTEE_DONE)) {
@@ -3536,8 +3574,7 @@ static int __init init_workqueues(void)
 		spin_lock_init(&gcwq->lock);
 		INIT_LIST_HEAD(&gcwq->worklist);
 		gcwq->cpu = cpu;
-		if (cpu == WORK_CPU_UNBOUND)
-			gcwq->flags |= GCWQ_DISASSOCIATED;
+		gcwq->flags |= GCWQ_DISASSOCIATED;
 
 		INIT_LIST_HEAD(&gcwq->idle_list);
 		for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++)
@@ -3561,6 +3598,8 @@ static int __init init_workqueues(void)
 		struct global_cwq *gcwq = get_gcwq(cpu);
 		struct worker *worker;
 
+		if (cpu != WORK_CPU_UNBOUND)
+			gcwq->flags &= ~GCWQ_DISASSOCIATED;
 		worker = create_worker(gcwq, true);
 		BUG_ON(!worker);
 		spin_lock_irq(&gcwq->lock);