Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

 * Fix include order for bison/flex-generated C files, from Ben Hutchings

 * Build fixes and documentation corrections from David Ahern

 * Group parsing support, from Jiri Olsa

 * UI/gtk refactorings and improvements from Namhyung Kim

 * NULL deref fix for perf script, from Namhyung Kim

 * Assorted cleanups from Robert Richter

 * Let O= makes handle relative paths, from Steven Rostedt

 * perf script python fixes, from Feng Tang.

 * Improve 'perf lock' error message when the needed tracepoints
   are not present, from David Ahern.

 * Initial bash completion support, from Frederic Weisbecker

 * Allow building without libelf, from Namhyung Kim.

 * Support DWARF CFI based unwind to have callchains when %bp
   based unwinding is not possible, from Jiri Olsa.

 * Symbol resolution fixes, while fixing support PPC64 files with an .opt ELF
   section was the end goal, several fixes for code that handles all
   architectures and cleanups are included, from Cody Schafer.

 * Add a description for the JIT interface, from Andi Kleen.

 * Assorted fixes for Documentation and build in 32 bit, from Robert Richter

 * Add support for non-tracepoint events in perf script python, from Feng Tang

 * Cache the libtraceevent event_format associated to each evsel early, so that we
   avoid relookups, i.e. calling pevent_find_event repeatedly when processing
   tracepoint events.

   [ This is to reduce the surface contact with libtraceevents and make clear what
     is that the perf tools needs from that lib: so far parsing the common and per
     event fields. ]

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 166 insertions, 126 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index 1e4a5fe3d7b..4d31f73e256 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -283,24 +283,22 @@ static int mnt_is_readonly(struct vfsmount *mnt)
 }
 
 /*
- * Most r/o checks on a fs are for operations that take
- * discrete amounts of time, like a write() or unlink().
- * We must keep track of when those operations start
- * (for permission checks) and when they end, so that
- * we can determine when writes are able to occur to
- * a filesystem.
+ * Most r/o & frozen checks on a fs are for operations that take discrete
+ * amounts of time, like a write() or unlink().  We must keep track of when
+ * those operations start (for permission checks) and when they end, so that we
+ * can determine when writes are able to occur to a filesystem.
  */
 /**
- * mnt_want_write - get write access to a mount
+ * __mnt_want_write - get write access to a mount without freeze protection
  * @m: the mount on which to take a write
  *
- * This tells the low-level filesystem that a write is
- * about to be performed to it, and makes sure that
- * writes are allowed before returning success.  When
- * the write operation is finished, mnt_drop_write()
- * must be called.  This is effectively a refcount.
+ * This tells the low-level filesystem that a write is about to be performed to
+ * it, and makes sure that writes are allowed (mnt it read-write) before
+ * returning success. This operation does not protect against filesystem being
+ * frozen. When the write operation is finished, __mnt_drop_write() must be
+ * called. This is effectively a refcount.
  */
-int mnt_want_write(struct vfsmount *m)
+int __mnt_want_write(struct vfsmount *m)
 {
 	struct mount *mnt = real_mount(m);
 	int ret = 0;
@@ -326,6 +324,27 @@ int mnt_want_write(struct vfsmount *m)
 		ret = -EROFS;
 	}
 	preempt_enable();
+
+	return ret;
+}
+
+/**
+ * mnt_want_write - get write access to a mount
+ * @m: the mount on which to take a write
+ *
+ * This tells the low-level filesystem that a write is about to be performed to
+ * it, and makes sure that writes are allowed (mount is read-write, filesystem
+ * is not frozen) before returning success.  When the write operation is
+ * finished, mnt_drop_write() must be called.  This is effectively a refcount.
+ */
+int mnt_want_write(struct vfsmount *m)
+{
+	int ret;
+
+	sb_start_write(m->mnt_sb);
+	ret = __mnt_want_write(m);
+	if (ret)
+		sb_end_write(m->mnt_sb);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(mnt_want_write);
@@ -355,38 +374,76 @@ int mnt_clone_write(struct vfsmount *mnt)
 EXPORT_SYMBOL_GPL(mnt_clone_write);
 
 /**
- * mnt_want_write_file - get write access to a file's mount
+ * __mnt_want_write_file - get write access to a file's mount
  * @file: the file who's mount on which to take a write
  *
- * This is like mnt_want_write, but it takes a file and can
+ * This is like __mnt_want_write, but it takes a file and can
  * do some optimisations if the file is open for write already
  */
-int mnt_want_write_file(struct file *file)
+int __mnt_want_write_file(struct file *file)
 {
 	struct inode *inode = file->f_dentry->d_inode;
+
 	if (!(file->f_mode & FMODE_WRITE) || special_file(inode->i_mode))
-		return mnt_want_write(file->f_path.mnt);
+		return __mnt_want_write(file->f_path.mnt);
 	else
 		return mnt_clone_write(file->f_path.mnt);
 }
+
+/**
+ * mnt_want_write_file - get write access to a file's mount
+ * @file: the file who's mount on which to take a write
+ *
+ * This is like mnt_want_write, but it takes a file and can
+ * do some optimisations if the file is open for write already
+ */
+int mnt_want_write_file(struct file *file)
+{
+	int ret;
+
+	sb_start_write(file->f_path.mnt->mnt_sb);
+	ret = __mnt_want_write_file(file);
+	if (ret)
+		sb_end_write(file->f_path.mnt->mnt_sb);
+	return ret;
+}
 EXPORT_SYMBOL_GPL(mnt_want_write_file);
 
 /**
- * mnt_drop_write - give up write access to a mount
+ * __mnt_drop_write - give up write access to a mount
  * @mnt: the mount on which to give up write access
  *
  * Tells the low-level filesystem that we are done
  * performing writes to it.  Must be matched with
- * mnt_want_write() call above.
+ * __mnt_want_write() call above.
  */
-void mnt_drop_write(struct vfsmount *mnt)
+void __mnt_drop_write(struct vfsmount *mnt)
 {
 	preempt_disable();
 	mnt_dec_writers(real_mount(mnt));
 	preempt_enable();
 }
+
+/**
+ * mnt_drop_write - give up write access to a mount
+ * @mnt: the mount on which to give up write access
+ *
+ * Tells the low-level filesystem that we are done performing writes to it and
+ * also allows filesystem to be frozen again.  Must be matched with
+ * mnt_want_write() call above.
+ */
+void mnt_drop_write(struct vfsmount *mnt)
+{
+	__mnt_drop_write(mnt);
+	sb_end_write(mnt->mnt_sb);
+}
 EXPORT_SYMBOL_GPL(mnt_drop_write);
 
+void __mnt_drop_write_file(struct file *file)
+{
+	__mnt_drop_write(file->f_path.mnt);
+}
+
 void mnt_drop_write_file(struct file *file)
 {
 	mnt_drop_write(file->f_path.mnt);
@@ -515,8 +572,20 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry,
 }
 
 /*
- * lookup_mnt increments the ref count before returning
- * the vfsmount struct.
+ * lookup_mnt - Return the first child mount mounted at path
+ *
+ * "First" means first mounted chronologically.  If you create the
+ * following mounts:
+ *
+ * mount /dev/sda1 /mnt
+ * mount /dev/sda2 /mnt
+ * mount /dev/sda3 /mnt
+ *
+ * Then lookup_mnt() on the base /mnt dentry in the root mount will
+ * return successively the root dentry and vfsmount of /dev/sda1, then
+ * /dev/sda2, then /dev/sda3, then NULL.
+ *
+ * lookup_mnt takes a reference to the found vfsmount.
  */
 struct vfsmount *lookup_mnt(struct path *path)
 {
@@ -621,21 +690,6 @@ static void attach_mnt(struct mount *mnt, struct path *path)
 	list_add_tail(&mnt->mnt_child, &real_mount(path->mnt)->mnt_mounts);
 }
 
-static inline void __mnt_make_longterm(struct mount *mnt)
-{
-#ifdef CONFIG_SMP
-	atomic_inc(&mnt->mnt_longterm);
-#endif
-}
-
-/* needs vfsmount lock for write */
-static inline void __mnt_make_shortterm(struct mount *mnt)
-{
-#ifdef CONFIG_SMP
-	atomic_dec(&mnt->mnt_longterm);
-#endif
-}
-
 /*
  * vfsmount lock must be held for write
  */
@@ -649,10 +703,8 @@ static void commit_tree(struct mount *mnt)
 	BUG_ON(parent == mnt);
 
 	list_add_tail(&head, &mnt->mnt_list);
-	list_for_each_entry(m, &head, mnt_list) {
+	list_for_each_entry(m, &head, mnt_list)
 		m->mnt_ns = n;
-		__mnt_make_longterm(m);
-	}
 
 	list_splice(&head, n->list.prev);
 
@@ -725,56 +777,60 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 					int flag)
 {
 	struct super_block *sb = old->mnt.mnt_sb;
-	struct mount *mnt = alloc_vfsmnt(old->mnt_devname);
+	struct mount *mnt;
+	int err;
 
-	if (mnt) {
-		if (flag & (CL_SLAVE | CL_PRIVATE))
-			mnt->mnt_group_id = 0; /* not a peer of original */
-		else
-			mnt->mnt_group_id = old->mnt_group_id;
-
-		if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) {
-			int err = mnt_alloc_group_id(mnt);
-			if (err)
-				goto out_free;
-		}
+	mnt = alloc_vfsmnt(old->mnt_devname);
+	if (!mnt)
+		return ERR_PTR(-ENOMEM);
 
-		mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD;
-		atomic_inc(&sb->s_active);
-		mnt->mnt.mnt_sb = sb;
-		mnt->mnt.mnt_root = dget(root);
-		mnt->mnt_mountpoint = mnt->mnt.mnt_root;
-		mnt->mnt_parent = mnt;
-		br_write_lock(&vfsmount_lock);
-		list_add_tail(&mnt->mnt_instance, &sb->s_mounts);
-		br_write_unlock(&vfsmount_lock);
+	if (flag & (CL_SLAVE | CL_PRIVATE))
+		mnt->mnt_group_id = 0; /* not a peer of original */
+	else
+		mnt->mnt_group_id = old->mnt_group_id;
 
-		if (flag & CL_SLAVE) {
-			list_add(&mnt->mnt_slave, &old->mnt_slave_list);
-			mnt->mnt_master = old;
-			CLEAR_MNT_SHARED(mnt);
-		} else if (!(flag & CL_PRIVATE)) {
-			if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old))
-				list_add(&mnt->mnt_share, &old->mnt_share);
-			if (IS_MNT_SLAVE(old))
-				list_add(&mnt->mnt_slave, &old->mnt_slave);
-			mnt->mnt_master = old->mnt_master;
-		}
-		if (flag & CL_MAKE_SHARED)
-			set_mnt_shared(mnt);
-
-		/* stick the duplicate mount on the same expiry list
-		 * as the original if that was on one */
-		if (flag & CL_EXPIRE) {
-			if (!list_empty(&old->mnt_expire))
-				list_add(&mnt->mnt_expire, &old->mnt_expire);
-		}
+	if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) {
+		err = mnt_alloc_group_id(mnt);
+		if (err)
+			goto out_free;
+	}
+
+	mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD;
+	atomic_inc(&sb->s_active);
+	mnt->mnt.mnt_sb = sb;
+	mnt->mnt.mnt_root = dget(root);
+	mnt->mnt_mountpoint = mnt->mnt.mnt_root;
+	mnt->mnt_parent = mnt;
+	br_write_lock(&vfsmount_lock);
+	list_add_tail(&mnt->mnt_instance, &sb->s_mounts);
+	br_write_unlock(&vfsmount_lock);
+
+	if (flag & CL_SLAVE) {
+		list_add(&mnt->mnt_slave, &old->mnt_slave_list);
+		mnt->mnt_master = old;
+		CLEAR_MNT_SHARED(mnt);
+	} else if (!(flag & CL_PRIVATE)) {
+		if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old))
+			list_add(&mnt->mnt_share, &old->mnt_share);
+		if (IS_MNT_SLAVE(old))
+			list_add(&mnt->mnt_slave, &old->mnt_slave);
+		mnt->mnt_master = old->mnt_master;
+	}
+	if (flag & CL_MAKE_SHARED)
+		set_mnt_shared(mnt);
+
+	/* stick the duplicate mount on the same expiry list
+	 * as the original if that was on one */
+	if (flag & CL_EXPIRE) {
+		if (!list_empty(&old->mnt_expire))
+			list_add(&mnt->mnt_expire, &old->mnt_expire);
 	}
+
 	return mnt;
 
  out_free:
 	free_vfsmnt(mnt);
-	return NULL;
+	return ERR_PTR(err);
 }
 
 static inline void mntfree(struct mount *mnt)
@@ -804,7 +860,8 @@ static void mntput_no_expire(struct mount *mnt)
 put_again:
 #ifdef CONFIG_SMP
 	br_read_lock(&vfsmount_lock);
-	if (likely(atomic_read(&mnt->mnt_longterm))) {
+	if (likely(mnt->mnt_ns)) {
+		/* shouldn't be the last one */
 		mnt_add_count(mnt, -1);
 		br_read_unlock(&vfsmount_lock);
 		return;
@@ -939,7 +996,7 @@ EXPORT_SYMBOL(replace_mount_options);
 /* iterator; we want it to have access to namespace_sem, thus here... */
 static void *m_start(struct seq_file *m, loff_t *pos)
 {
-	struct proc_mounts *p = container_of(m, struct proc_mounts, m);
+	struct proc_mounts *p = proc_mounts(m);
 
 	down_read(&namespace_sem);
 	return seq_list_start(&p->ns->list, *pos);
@@ -947,7 +1004,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 
 static void *m_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct proc_mounts *p = container_of(m, struct proc_mounts, m);
+	struct proc_mounts *p = proc_mounts(m);
 
 	return seq_list_next(v, &p->ns->list, pos);
 }
@@ -959,7 +1016,7 @@ static void m_stop(struct seq_file *m, void *v)
 
 static int m_show(struct seq_file *m, void *v)
 {
-	struct proc_mounts *p = container_of(m, struct proc_mounts, m);
+	struct proc_mounts *p = proc_mounts(m);
 	struct mount *r = list_entry(v, struct mount, mnt_list);
 	return p->show(m, &r->mnt);
 }
@@ -1074,8 +1131,6 @@ void umount_tree(struct mount *mnt, int propagate, struct list_head *kill)
 		list_del_init(&p->mnt_expire);
 		list_del_init(&p->mnt_list);
 		__touch_mnt_namespace(p->mnt_ns);
-		if (p->mnt_ns)
-			__mnt_make_shortterm(p);
 		p->mnt_ns = NULL;
 		list_del_init(&p->mnt_child);
 		if (mnt_has_parent(p)) {
@@ -1260,11 +1315,12 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 	struct path path;
 
 	if (!(flag & CL_COPY_ALL) && IS_MNT_UNBINDABLE(mnt))
-		return NULL;
+		return ERR_PTR(-EINVAL);
 
 	res = q = clone_mnt(mnt, dentry, flag);
-	if (!q)
-		goto Enomem;
+	if (IS_ERR(q))
+		return q;
+
 	q->mnt_mountpoint = mnt->mnt_mountpoint;
 
 	p = mnt;
@@ -1286,8 +1342,8 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 			path.mnt = &q->mnt;
 			path.dentry = p->mnt_mountpoint;
 			q = clone_mnt(p, p->mnt.mnt_root, flag);
-			if (!q)
-				goto Enomem;
+			if (IS_ERR(q))
+				goto out;
 			br_write_lock(&vfsmount_lock);
 			list_add_tail(&q->mnt_list, &res->mnt_list);
 			attach_mnt(q, &path);
@@ -1295,7 +1351,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 		}
 	}
 	return res;
-Enomem:
+out:
 	if (res) {
 		LIST_HEAD(umount_list);
 		br_write_lock(&vfsmount_lock);
@@ -1303,9 +1359,11 @@ Enomem:
 		br_write_unlock(&vfsmount_lock);
 		release_mounts(&umount_list);
 	}
-	return NULL;
+	return q;
 }
 
+/* Caller should check returned pointer for errors */
+
 struct vfsmount *collect_mounts(struct path *path)
 {
 	struct mount *tree;
@@ -1313,7 +1371,9 @@ struct vfsmount *collect_mounts(struct path *path)
 	tree = copy_tree(real_mount(path->mnt), path->dentry,
 			 CL_COPY_ALL | CL_PRIVATE);
 	up_write(&namespace_sem);
-	return tree ? &tree->mnt : NULL;
+	if (IS_ERR(tree))
+		return NULL;
+	return &tree->mnt;
 }
 
 void drop_collected_mounts(struct vfsmount *mnt)
@@ -1608,14 +1668,15 @@ static int do_loopback(struct path *path, char *old_name,
 	if (!check_mnt(real_mount(path->mnt)) || !check_mnt(old))
 		goto out2;
 
-	err = -ENOMEM;
 	if (recurse)
 		mnt = copy_tree(old, old_path.dentry, 0);
 	else
 		mnt = clone_mnt(old, old_path.dentry, 0);
 
-	if (!mnt)
-		goto out2;
+	if (IS_ERR(mnt)) {
+		err = PTR_ERR(mnt);
+		goto out;
+	}
 
 	err = graft_tree(mnt, path);
 	if (err) {
@@ -2209,23 +2270,6 @@ static struct mnt_namespace *alloc_mnt_ns(void)
 	return new_ns;
 }
 
-void mnt_make_longterm(struct vfsmount *mnt)
-{
-	__mnt_make_longterm(real_mount(mnt));
-}
-
-void mnt_make_shortterm(struct vfsmount *m)
-{
-#ifdef CONFIG_SMP
-	struct mount *mnt = real_mount(m);
-	if (atomic_add_unless(&mnt->mnt_longterm, -1, 1))
-		return;
-	br_write_lock(&vfsmount_lock);
-	atomic_dec(&mnt->mnt_longterm);
-	br_write_unlock(&vfsmount_lock);
-#endif
-}
-
 /*
  * Allocate a new namespace structure and populate it with contents
  * copied from the namespace of the passed in task structure.
@@ -2246,10 +2290,10 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 	down_write(&namespace_sem);
 	/* First pass: copy the tree topology */
 	new = copy_tree(old, old->mnt.mnt_root, CL_COPY_ALL | CL_EXPIRE);
-	if (!new) {
+	if (IS_ERR(new)) {
 		up_write(&namespace_sem);
 		kfree(new_ns);
-		return ERR_PTR(-ENOMEM);
+		return ERR_CAST(new);
 	}
 	new_ns->root = new;
 	br_write_lock(&vfsmount_lock);
@@ -2265,18 +2309,13 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 	q = new;
 	while (p) {
 		q->mnt_ns = new_ns;
-		__mnt_make_longterm(q);
 		if (fs) {
 			if (&p->mnt == fs->root.mnt) {
 				fs->root.mnt = mntget(&q->mnt);
-				__mnt_make_longterm(q);
-				mnt_make_shortterm(&p->mnt);
 				rootmnt = &p->mnt;
 			}
 			if (&p->mnt == fs->pwd.mnt) {
 				fs->pwd.mnt = mntget(&q->mnt);
-				__mnt_make_longterm(q);
-				mnt_make_shortterm(&p->mnt);
 				pwdmnt = &p->mnt;
 			}
 		}
@@ -2320,7 +2359,6 @@ static struct mnt_namespace *create_mnt_ns(struct vfsmount *m)
 	if (!IS_ERR(new_ns)) {
 		struct mount *mnt = real_mount(m);
 		mnt->mnt_ns = new_ns;
-		__mnt_make_longterm(mnt);
 		new_ns->root = mnt;
 		list_add(&new_ns->list, &mnt->mnt_list);
 	} else {
@@ -2615,7 +2653,7 @@ struct vfsmount *kern_mount_data(struct file_system_type *type, void *data)
 		 * it is a longterm mount, don't release mnt until
 		 * we unmount before file sys is unregistered
 		*/
-		mnt_make_longterm(mnt);
+		real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL;
 	}
 	return mnt;
 }
@@ -2625,7 +2663,9 @@ void kern_unmount(struct vfsmount *mnt)
 {
 	/* release long term mount so mount point can be released */
 	if (!IS_ERR_OR_NULL(mnt)) {
-		mnt_make_shortterm(mnt);
+		br_write_lock(&vfsmount_lock);
+		real_mount(mnt)->mnt_ns = NULL;
+		br_write_unlock(&vfsmount_lock);
 		mntput(mnt);
 	}
 }