Merge tag 'trace-4.1-tracefs' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull tracefs from Steven Rostedt:
"This adds the new tracefs file system.
This has been in linux-next for more than one release, as I had it
ready for the 4.0 merge window, but a last minute thing that needed to
go into Linux first had to be done. That was that perf hard coded the
file system number when reading /sys/kernel/debugfs/tracing directory
making sure that the path had the debugfs mount # before it would
parse the tracing file. This broke other use cases of perf, and the
check is removed.
Now when mounting /sys/kernel/debug, tracefs is automatically mounted
in /sys/kernel/debug/tracing such that old tools will still see that
path as expected. But now system admins can mount tracefs directly
and not need to mount debugfs, which can expose security issues. A
new directory is created when tracefs is configured such that system
admins can now mount it separately (/sys/kernel/tracing)"
* tag 'trace-4.1-tracefs' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
tracing: Have mkdir and rmdir be part of tracefs
tracefs: Add directory /sys/kernel/tracing
tracing: Automatically mount tracefs on debugfs/tracing
tracing: Convert the tracing facility over to use tracefs
tracefs: Add new tracefs file system
tracing: Create cmdline tracer options on tracing fs init
tracing: Only create tracer options files if directory exists
debugfs: Provide a file creation function that also takes an initial size
diff --git a/fs/Makefile b/fs/Makefile
index a88ac48..cb92fd4 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -118,6 +118,7 @@
obj-$(CONFIG_HPPFS) += hppfs/
obj-$(CONFIG_CACHEFILES) += cachefiles/
obj-$(CONFIG_DEBUG_FS) += debugfs/
+obj-$(CONFIG_TRACING) += tracefs/
obj-$(CONFIG_OCFS2_FS) += ocfs2/
obj-$(CONFIG_BTRFS_FS) += btrfs/
obj-$(CONFIG_GFS2_FS) += gfs2/
diff --git a/fs/tracefs/Makefile b/fs/tracefs/Makefile
new file mode 100644
index 0000000..82fa35b
--- /dev/null
+++ b/fs/tracefs/Makefile
@@ -0,0 +1,4 @@
+tracefs-objs := inode.o
+
+obj-$(CONFIG_TRACING) += tracefs.o
+
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
new file mode 100644
index 0000000..d92bdf3
--- /dev/null
+++ b/fs/tracefs/inode.c
@@ -0,0 +1,650 @@
+/*
+ * inode.c - part of tracefs, a pseudo file system for activating tracing
+ *
+ * Based on debugfs by: Greg Kroah-Hartman <greg@kroah.com>
+ *
+ * Copyright (C) 2014 Red Hat Inc, author: Steven Rostedt <srostedt@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * tracefs is the file system that is used by the tracing infrastructure.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/kobject.h>
+#include <linux/namei.h>
+#include <linux/tracefs.h>
+#include <linux/fsnotify.h>
+#include <linux/seq_file.h>
+#include <linux/parser.h>
+#include <linux/magic.h>
+#include <linux/slab.h>
+
+#define TRACEFS_DEFAULT_MODE 0700
+
+static struct vfsmount *tracefs_mount;
+static int tracefs_mount_count;
+static bool tracefs_registered;
+
+static ssize_t default_read_file(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ return 0;
+}
+
+static ssize_t default_write_file(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ return count;
+}
+
+static const struct file_operations tracefs_file_operations = {
+ .read = default_read_file,
+ .write = default_write_file,
+ .open = simple_open,
+ .llseek = noop_llseek,
+};
+
+static struct tracefs_dir_ops {
+ int (*mkdir)(const char *name);
+ int (*rmdir)(const char *name);
+} tracefs_ops;
+
+static char *get_dname(struct dentry *dentry)
+{
+ const char *dname;
+ char *name;
+ int len = dentry->d_name.len;
+
+ dname = dentry->d_name.name;
+ name = kmalloc(len + 1, GFP_KERNEL);
+ if (!name)
+ return NULL;
+ memcpy(name, dname, len);
+ name[len] = 0;
+ return name;
+}
+
+static int tracefs_syscall_mkdir(struct inode *inode, struct dentry *dentry, umode_t mode)
+{
+ char *name;
+ int ret;
+
+ name = get_dname(dentry);
+ if (!name)
+ return -ENOMEM;
+
+ /*
+ * The mkdir call can call the generic functions that create
+ * the files within the tracefs system. It is up to the individual
+ * mkdir routine to handle races.
+ */
+ mutex_unlock(&inode->i_mutex);
+ ret = tracefs_ops.mkdir(name);
+ mutex_lock(&inode->i_mutex);
+
+ kfree(name);
+
+ return ret;
+}
+
+static int tracefs_syscall_rmdir(struct inode *inode, struct dentry *dentry)
+{
+ char *name;
+ int ret;
+
+ name = get_dname(dentry);
+ if (!name)
+ return -ENOMEM;
+
+ /*
+ * The rmdir call can call the generic functions that create
+ * the files within the tracefs system. It is up to the individual
+ * rmdir routine to handle races.
+ * This time we need to unlock not only the parent (inode) but
+ * also the directory that is being deleted.
+ */
+ mutex_unlock(&inode->i_mutex);
+ mutex_unlock(&dentry->d_inode->i_mutex);
+
+ ret = tracefs_ops.rmdir(name);
+
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
+ mutex_lock(&dentry->d_inode->i_mutex);
+
+ kfree(name);
+
+ return ret;
+}
+
+static const struct inode_operations tracefs_dir_inode_operations = {
+ .lookup = simple_lookup,
+ .mkdir = tracefs_syscall_mkdir,
+ .rmdir = tracefs_syscall_rmdir,
+};
+
+static struct inode *tracefs_get_inode(struct super_block *sb)
+{
+ struct inode *inode = new_inode(sb);
+ if (inode) {
+ inode->i_ino = get_next_ino();
+ inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ }
+ return inode;
+}
+
+struct tracefs_mount_opts {
+ kuid_t uid;
+ kgid_t gid;
+ umode_t mode;
+};
+
+enum {
+ Opt_uid,
+ Opt_gid,
+ Opt_mode,
+ Opt_err
+};
+
+static const match_table_t tokens = {
+ {Opt_uid, "uid=%u"},
+ {Opt_gid, "gid=%u"},
+ {Opt_mode, "mode=%o"},
+ {Opt_err, NULL}
+};
+
+struct tracefs_fs_info {
+ struct tracefs_mount_opts mount_opts;
+};
+
+static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts)
+{
+ substring_t args[MAX_OPT_ARGS];
+ int option;
+ int token;
+ kuid_t uid;
+ kgid_t gid;
+ char *p;
+
+ opts->mode = TRACEFS_DEFAULT_MODE;
+
+ while ((p = strsep(&data, ",")) != NULL) {
+ if (!*p)
+ continue;
+
+ token = match_token(p, tokens, args);
+ switch (token) {
+ case Opt_uid:
+ if (match_int(&args[0], &option))
+ return -EINVAL;
+ uid = make_kuid(current_user_ns(), option);
+ if (!uid_valid(uid))
+ return -EINVAL;
+ opts->uid = uid;
+ break;
+ case Opt_gid:
+ if (match_int(&args[0], &option))
+ return -EINVAL;
+ gid = make_kgid(current_user_ns(), option);
+ if (!gid_valid(gid))
+ return -EINVAL;
+ opts->gid = gid;
+ break;
+ case Opt_mode:
+ if (match_octal(&args[0], &option))
+ return -EINVAL;
+ opts->mode = option & S_IALLUGO;
+ break;
+ /*
+ * We might like to report bad mount options here;
+ * but traditionally tracefs has ignored all mount options
+ */
+ }
+ }
+
+ return 0;
+}
+
+static int tracefs_apply_options(struct super_block *sb)
+{
+ struct tracefs_fs_info *fsi = sb->s_fs_info;
+ struct inode *inode = sb->s_root->d_inode;
+ struct tracefs_mount_opts *opts = &fsi->mount_opts;
+
+ inode->i_mode &= ~S_IALLUGO;
+ inode->i_mode |= opts->mode;
+
+ inode->i_uid = opts->uid;
+ inode->i_gid = opts->gid;
+
+ return 0;
+}
+
+static int tracefs_remount(struct super_block *sb, int *flags, char *data)
+{
+ int err;
+ struct tracefs_fs_info *fsi = sb->s_fs_info;
+
+ sync_filesystem(sb);
+ err = tracefs_parse_options(data, &fsi->mount_opts);
+ if (err)
+ goto fail;
+
+ tracefs_apply_options(sb);
+
+fail:
+ return err;
+}
+
+static int tracefs_show_options(struct seq_file *m, struct dentry *root)
+{
+ struct tracefs_fs_info *fsi = root->d_sb->s_fs_info;
+ struct tracefs_mount_opts *opts = &fsi->mount_opts;
+
+ if (!uid_eq(opts->uid, GLOBAL_ROOT_UID))
+ seq_printf(m, ",uid=%u",
+ from_kuid_munged(&init_user_ns, opts->uid));
+ if (!gid_eq(opts->gid, GLOBAL_ROOT_GID))
+ seq_printf(m, ",gid=%u",
+ from_kgid_munged(&init_user_ns, opts->gid));
+ if (opts->mode != TRACEFS_DEFAULT_MODE)
+ seq_printf(m, ",mode=%o", opts->mode);
+
+ return 0;
+}
+
+static const struct super_operations tracefs_super_operations = {
+ .statfs = simple_statfs,
+ .remount_fs = tracefs_remount,
+ .show_options = tracefs_show_options,
+};
+
+static int trace_fill_super(struct super_block *sb, void *data, int silent)
+{
+ static struct tree_descr trace_files[] = {{""}};
+ struct tracefs_fs_info *fsi;
+ int err;
+
+ save_mount_options(sb, data);
+
+ fsi = kzalloc(sizeof(struct tracefs_fs_info), GFP_KERNEL);
+ sb->s_fs_info = fsi;
+ if (!fsi) {
+ err = -ENOMEM;
+ goto fail;
+ }
+
+ err = tracefs_parse_options(data, &fsi->mount_opts);
+ if (err)
+ goto fail;
+
+ err = simple_fill_super(sb, TRACEFS_MAGIC, trace_files);
+ if (err)
+ goto fail;
+
+ sb->s_op = &tracefs_super_operations;
+
+ tracefs_apply_options(sb);
+
+ return 0;
+
+fail:
+ kfree(fsi);
+ sb->s_fs_info = NULL;
+ return err;
+}
+
+static struct dentry *trace_mount(struct file_system_type *fs_type,
+ int flags, const char *dev_name,
+ void *data)
+{
+ return mount_single(fs_type, flags, data, trace_fill_super);
+}
+
+static struct file_system_type trace_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "tracefs",
+ .mount = trace_mount,
+ .kill_sb = kill_litter_super,
+};
+MODULE_ALIAS_FS("tracefs");
+
+static struct dentry *start_creating(const char *name, struct dentry *parent)
+{
+ struct dentry *dentry;
+ int error;
+
+ pr_debug("tracefs: creating file '%s'\n",name);
+
+ error = simple_pin_fs(&trace_fs_type, &tracefs_mount,
+ &tracefs_mount_count);
+ if (error)
+ return ERR_PTR(error);
+
+ /* If the parent is not specified, we create it in the root.
+ * We need the root dentry to do this, which is in the super
+ * block. A pointer to that is in the struct vfsmount that we
+ * have around.
+ */
+ if (!parent)
+ parent = tracefs_mount->mnt_root;
+
+ mutex_lock(&parent->d_inode->i_mutex);
+ dentry = lookup_one_len(name, parent, strlen(name));
+ if (!IS_ERR(dentry) && dentry->d_inode) {
+ dput(dentry);
+ dentry = ERR_PTR(-EEXIST);
+ }
+ if (IS_ERR(dentry))
+ mutex_unlock(&parent->d_inode->i_mutex);
+ return dentry;
+}
+
+static struct dentry *failed_creating(struct dentry *dentry)
+{
+ mutex_unlock(&dentry->d_parent->d_inode->i_mutex);
+ dput(dentry);
+ simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+ return NULL;
+}
+
+static struct dentry *end_creating(struct dentry *dentry)
+{
+ mutex_unlock(&dentry->d_parent->d_inode->i_mutex);
+ return dentry;
+}
+
+/**
+ * tracefs_create_file - create a file in the tracefs filesystem
+ * @name: a pointer to a string containing the name of the file to create.
+ * @mode: the permission that the file should have.
+ * @parent: a pointer to the parent dentry for this file. This should be a
+ * directory dentry if set. If this parameter is NULL, then the
+ * file will be created in the root of the tracefs filesystem.
+ * @data: a pointer to something that the caller will want to get to later
+ * on. The inode.i_private pointer will point to this value on
+ * the open() call.
+ * @fops: a pointer to a struct file_operations that should be used for
+ * this file.
+ *
+ * This is the basic "create a file" function for tracefs. It allows for a
+ * wide range of flexibility in creating a file, or a directory (if you want
+ * to create a directory, the tracefs_create_dir() function is
+ * recommended to be used instead.)
+ *
+ * This function will return a pointer to a dentry if it succeeds. This
+ * pointer must be passed to the tracefs_remove() function when the file is
+ * to be removed (no automatic cleanup happens if your module is unloaded,
+ * you are responsible here.) If an error occurs, %NULL will be returned.
+ *
+ * If tracefs is not enabled in the kernel, the value -%ENODEV will be
+ * returned.
+ */
+struct dentry *tracefs_create_file(const char *name, umode_t mode,
+ struct dentry *parent, void *data,
+ const struct file_operations *fops)
+{
+ struct dentry *dentry;
+ struct inode *inode;
+
+ if (!(mode & S_IFMT))
+ mode |= S_IFREG;
+ BUG_ON(!S_ISREG(mode));
+ dentry = start_creating(name, parent);
+
+ if (IS_ERR(dentry))
+ return NULL;
+
+ inode = tracefs_get_inode(dentry->d_sb);
+ if (unlikely(!inode))
+ return failed_creating(dentry);
+
+ inode->i_mode = mode;
+ inode->i_fop = fops ? fops : &tracefs_file_operations;
+ inode->i_private = data;
+ d_instantiate(dentry, inode);
+ fsnotify_create(dentry->d_parent->d_inode, dentry);
+ return end_creating(dentry);
+}
+
+static struct dentry *__create_dir(const char *name, struct dentry *parent,
+ const struct inode_operations *ops)
+{
+ struct dentry *dentry = start_creating(name, parent);
+ struct inode *inode;
+
+ if (IS_ERR(dentry))
+ return NULL;
+
+ inode = tracefs_get_inode(dentry->d_sb);
+ if (unlikely(!inode))
+ return failed_creating(dentry);
+
+ inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
+ inode->i_op = ops;
+ inode->i_fop = &simple_dir_operations;
+
+ /* directory inodes start off with i_nlink == 2 (for "." entry) */
+ inc_nlink(inode);
+ d_instantiate(dentry, inode);
+ inc_nlink(dentry->d_parent->d_inode);
+ fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
+ return end_creating(dentry);
+}
+
+/**
+ * tracefs_create_dir - create a directory in the tracefs filesystem
+ * @name: a pointer to a string containing the name of the directory to
+ * create.
+ * @parent: a pointer to the parent dentry for this file. This should be a
+ * directory dentry if set. If this parameter is NULL, then the
+ * directory will be created in the root of the tracefs filesystem.
+ *
+ * This function creates a directory in tracefs with the given name.
+ *
+ * This function will return a pointer to a dentry if it succeeds. This
+ * pointer must be passed to the tracefs_remove() function when the file is
+ * to be removed. If an error occurs, %NULL will be returned.
+ *
+ * If tracing is not enabled in the kernel, the value -%ENODEV will be
+ * returned.
+ */
+struct dentry *tracefs_create_dir(const char *name, struct dentry *parent)
+{
+ return __create_dir(name, parent, &simple_dir_inode_operations);
+}
+
+/**
+ * tracefs_create_instance_dir - create the tracing instances directory
+ * @name: The name of the instances directory to create
+ * @parent: The parent directory that the instances directory will exist
+ * @mkdir: The function to call when a mkdir is performed.
+ * @rmdir: The function to call when a rmdir is performed.
+ *
+ * Only one instances directory is allowed.
+ *
+ * The instances directory is special as it allows for mkdir and rmdir to
+ * to be done by userspace. When a mkdir or rmdir is performed, the inode
+ * locks are released and the methhods passed in (@mkdir and @rmdir) are
+ * called without locks and with the name of the directory being created
+ * within the instances directory.
+ *
+ * Returns the dentry of the instances directory.
+ */
+struct dentry *tracefs_create_instance_dir(const char *name, struct dentry *parent,
+ int (*mkdir)(const char *name),
+ int (*rmdir)(const char *name))
+{
+ struct dentry *dentry;
+
+ /* Only allow one instance of the instances directory. */
+ if (WARN_ON(tracefs_ops.mkdir || tracefs_ops.rmdir))
+ return NULL;
+
+ dentry = __create_dir(name, parent, &tracefs_dir_inode_operations);
+ if (!dentry)
+ return NULL;
+
+ tracefs_ops.mkdir = mkdir;
+ tracefs_ops.rmdir = rmdir;
+
+ return dentry;
+}
+
+static inline int tracefs_positive(struct dentry *dentry)
+{
+ return dentry->d_inode && !d_unhashed(dentry);
+}
+
+static int __tracefs_remove(struct dentry *dentry, struct dentry *parent)
+{
+ int ret = 0;
+
+ if (tracefs_positive(dentry)) {
+ if (dentry->d_inode) {
+ dget(dentry);
+ switch (dentry->d_inode->i_mode & S_IFMT) {
+ case S_IFDIR:
+ ret = simple_rmdir(parent->d_inode, dentry);
+ break;
+ default:
+ simple_unlink(parent->d_inode, dentry);
+ break;
+ }
+ if (!ret)
+ d_delete(dentry);
+ dput(dentry);
+ }
+ }
+ return ret;
+}
+
+/**
+ * tracefs_remove - removes a file or directory from the tracefs filesystem
+ * @dentry: a pointer to a the dentry of the file or directory to be
+ * removed.
+ *
+ * This function removes a file or directory in tracefs that was previously
+ * created with a call to another tracefs function (like
+ * tracefs_create_file() or variants thereof.)
+ */
+void tracefs_remove(struct dentry *dentry)
+{
+ struct dentry *parent;
+ int ret;
+
+ if (IS_ERR_OR_NULL(dentry))
+ return;
+
+ parent = dentry->d_parent;
+ if (!parent || !parent->d_inode)
+ return;
+
+ mutex_lock(&parent->d_inode->i_mutex);
+ ret = __tracefs_remove(dentry, parent);
+ mutex_unlock(&parent->d_inode->i_mutex);
+ if (!ret)
+ simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+}
+
+/**
+ * tracefs_remove_recursive - recursively removes a directory
+ * @dentry: a pointer to a the dentry of the directory to be removed.
+ *
+ * This function recursively removes a directory tree in tracefs that
+ * was previously created with a call to another tracefs function
+ * (like tracefs_create_file() or variants thereof.)
+ */
+void tracefs_remove_recursive(struct dentry *dentry)
+{
+ struct dentry *child, *parent;
+
+ if (IS_ERR_OR_NULL(dentry))
+ return;
+
+ parent = dentry->d_parent;
+ if (!parent || !parent->d_inode)
+ return;
+
+ parent = dentry;
+ down:
+ mutex_lock(&parent->d_inode->i_mutex);
+ loop:
+ /*
+ * The parent->d_subdirs is protected by the d_lock. Outside that
+ * lock, the child can be unlinked and set to be freed which can
+ * use the d_u.d_child as the rcu head and corrupt this list.
+ */
+ spin_lock(&parent->d_lock);
+ list_for_each_entry(child, &parent->d_subdirs, d_child) {
+ if (!tracefs_positive(child))
+ continue;
+
+ /* perhaps simple_empty(child) makes more sense */
+ if (!list_empty(&child->d_subdirs)) {
+ spin_unlock(&parent->d_lock);
+ mutex_unlock(&parent->d_inode->i_mutex);
+ parent = child;
+ goto down;
+ }
+
+ spin_unlock(&parent->d_lock);
+
+ if (!__tracefs_remove(child, parent))
+ simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+
+ /*
+ * The parent->d_lock protects agaist child from unlinking
+ * from d_subdirs. When releasing the parent->d_lock we can
+ * no longer trust that the next pointer is valid.
+ * Restart the loop. We'll skip this one with the
+ * tracefs_positive() check.
+ */
+ goto loop;
+ }
+ spin_unlock(&parent->d_lock);
+
+ mutex_unlock(&parent->d_inode->i_mutex);
+ child = parent;
+ parent = parent->d_parent;
+ mutex_lock(&parent->d_inode->i_mutex);
+
+ if (child != dentry)
+ /* go up */
+ goto loop;
+
+ if (!__tracefs_remove(child, parent))
+ simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+ mutex_unlock(&parent->d_inode->i_mutex);
+}
+
+/**
+ * tracefs_initialized - Tells whether tracefs has been registered
+ */
+bool tracefs_initialized(void)
+{
+ return tracefs_registered;
+}
+
+static struct kobject *trace_kobj;
+
+static int __init tracefs_init(void)
+{
+ int retval;
+
+ trace_kobj = kobject_create_and_add("tracing", kernel_kobj);
+ if (!trace_kobj)
+ return -EINVAL;
+
+ retval = register_filesystem(&trace_fs_type);
+ if (!retval)
+ tracefs_registered = true;
+
+ return retval;
+}
+core_initcall(tracefs_init);
diff --git a/include/linux/tracefs.h b/include/linux/tracefs.h
new file mode 100644
index 0000000..5b727a1
--- /dev/null
+++ b/include/linux/tracefs.h
@@ -0,0 +1,45 @@
+/*
+ * tracefs.h - a pseudo file system for activating tracing
+ *
+ * Based on debugfs by: 2004 Greg Kroah-Hartman <greg@kroah.com>
+ *
+ * Copyright (C) 2014 Red Hat Inc, author: Steven Rostedt <srostedt@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * tracefs is the file system that is used by the tracing infrastructure.
+ *
+ */
+
+#ifndef _TRACEFS_H_
+#define _TRACEFS_H_
+
+#include <linux/fs.h>
+#include <linux/seq_file.h>
+
+#include <linux/types.h>
+
+struct file_operations;
+
+#ifdef CONFIG_TRACING
+
+struct dentry *tracefs_create_file(const char *name, umode_t mode,
+ struct dentry *parent, void *data,
+ const struct file_operations *fops);
+
+struct dentry *tracefs_create_dir(const char *name, struct dentry *parent);
+
+void tracefs_remove(struct dentry *dentry);
+void tracefs_remove_recursive(struct dentry *dentry);
+
+struct dentry *tracefs_create_instance_dir(const char *name, struct dentry *parent,
+ int (*mkdir)(const char *name),
+ int (*rmdir)(const char *name));
+
+bool tracefs_initialized(void);
+
+#endif /* CONFIG_TRACING */
+
+#endif
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index 7d664ea..7b1425a 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -58,6 +58,8 @@
#define STACK_END_MAGIC 0x57AC6E9D
+#define TRACEFS_MAGIC 0x74726163
+
#define V9FS_MAGIC 0x01021997
#define BDEVFS_MAGIC 0x62646576
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4f22802..5a2e0b5 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -18,7 +18,7 @@
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
#include <linux/suspend.h>
-#include <linux/debugfs.h>
+#include <linux/tracefs.h>
#include <linux/hardirq.h>
#include <linux/kthread.h>
#include <linux/uaccess.h>
@@ -1008,7 +1008,7 @@
.stat_show = function_stat_show
};
-static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
+static __init void ftrace_profile_tracefs(struct dentry *d_tracer)
{
struct ftrace_profile_stat *stat;
struct dentry *entry;
@@ -1044,15 +1044,15 @@
}
}
- entry = debugfs_create_file("function_profile_enabled", 0644,
+ entry = tracefs_create_file("function_profile_enabled", 0644,
d_tracer, NULL, &ftrace_profile_fops);
if (!entry)
- pr_warning("Could not create debugfs "
+ pr_warning("Could not create tracefs "
"'function_profile_enabled' entry\n");
}
#else /* CONFIG_FUNCTION_PROFILER */
-static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
+static __init void ftrace_profile_tracefs(struct dentry *d_tracer)
{
}
#endif /* CONFIG_FUNCTION_PROFILER */
@@ -4712,7 +4712,7 @@
mutex_unlock(&ftrace_lock);
}
-static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
+static __init int ftrace_init_dyn_tracefs(struct dentry *d_tracer)
{
trace_create_file("available_filter_functions", 0444,
@@ -5020,7 +5020,7 @@
}
core_initcall(ftrace_nodyn_init);
-static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
+static inline int ftrace_init_dyn_tracefs(struct dentry *d_tracer) { return 0; }
static inline void ftrace_startup_enable(int command) { }
static inline void ftrace_startup_all(int command) { }
/* Keep as macros so we do not need to define the commands */
@@ -5473,7 +5473,7 @@
.release = ftrace_pid_release,
};
-static __init int ftrace_init_debugfs(void)
+static __init int ftrace_init_tracefs(void)
{
struct dentry *d_tracer;
@@ -5481,16 +5481,16 @@
if (IS_ERR(d_tracer))
return 0;
- ftrace_init_dyn_debugfs(d_tracer);
+ ftrace_init_dyn_tracefs(d_tracer);
trace_create_file("set_ftrace_pid", 0644, d_tracer,
NULL, &ftrace_pid_fops);
- ftrace_profile_debugfs(d_tracer);
+ ftrace_profile_tracefs(d_tracer);
return 0;
}
-fs_initcall(ftrace_init_debugfs);
+fs_initcall(ftrace_init_tracefs);
/**
* ftrace_kill - kill ftrace
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 62c6506..bcfa2ad 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -20,6 +20,7 @@
#include <linux/notifier.h>
#include <linux/irqflags.h>
#include <linux/debugfs.h>
+#include <linux/tracefs.h>
#include <linux/pagemap.h>
#include <linux/hardirq.h>
#include <linux/linkage.h>
@@ -31,6 +32,7 @@
#include <linux/splice.h>
#include <linux/kdebug.h>
#include <linux/string.h>
+#include <linux/mount.h>
#include <linux/rwsem.h>
#include <linux/slab.h>
#include <linux/ctype.h>
@@ -4105,9 +4107,24 @@
tr->current_trace = &nop_trace;
}
-static int tracing_set_tracer(struct trace_array *tr, const char *buf)
+static void update_tracer_options(struct trace_array *tr, struct tracer *t)
{
static struct trace_option_dentry *topts;
+
+ /* Only enable if the directory has been created already. */
+ if (!tr->dir)
+ return;
+
+ /* Currently, only the top instance has options */
+ if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL))
+ return;
+
+ destroy_trace_option_files(topts);
+ topts = create_trace_option_files(tr, t);
+}
+
+static int tracing_set_tracer(struct trace_array *tr, const char *buf)
+{
struct tracer *t;
#ifdef CONFIG_TRACER_MAX_TRACE
bool had_max_tr;
@@ -4172,11 +4189,7 @@
free_snapshot(tr);
}
#endif
- /* Currently, only the top instance has options */
- if (tr->flags & TRACE_ARRAY_FL_GLOBAL) {
- destroy_trace_option_files(topts);
- topts = create_trace_option_files(tr, t);
- }
+ update_tracer_options(tr, t);
#ifdef CONFIG_TRACER_MAX_TRACE
if (t->use_max_tr && !had_max_tr) {
@@ -5817,6 +5830,14 @@
static struct dentry *tracing_get_dentry(struct trace_array *tr)
{
+ if (WARN_ON(!tr->dir))
+ return ERR_PTR(-ENODEV);
+
+ /* Top directory uses NULL as the parent */
+ if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
+ return NULL;
+
+ /* All sub buffers have a descriptor */
return tr->dir;
}
@@ -5831,10 +5852,10 @@
if (IS_ERR(d_tracer))
return NULL;
- tr->percpu_dir = debugfs_create_dir("per_cpu", d_tracer);
+ tr->percpu_dir = tracefs_create_dir("per_cpu", d_tracer);
WARN_ONCE(!tr->percpu_dir,
- "Could not create debugfs directory 'per_cpu/%d'\n", cpu);
+ "Could not create tracefs directory 'per_cpu/%d'\n", cpu);
return tr->percpu_dir;
}
@@ -5851,7 +5872,7 @@
}
static void
-tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
+tracing_init_tracefs_percpu(struct trace_array *tr, long cpu)
{
struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu);
struct dentry *d_cpu;
@@ -5861,9 +5882,9 @@
return;
snprintf(cpu_dir, 30, "cpu%ld", cpu);
- d_cpu = debugfs_create_dir(cpu_dir, d_percpu);
+ d_cpu = tracefs_create_dir(cpu_dir, d_percpu);
if (!d_cpu) {
- pr_warning("Could not create debugfs '%s' entry\n", cpu_dir);
+ pr_warning("Could not create tracefs '%s' entry\n", cpu_dir);
return;
}
@@ -6015,9 +6036,9 @@
{
struct dentry *ret;
- ret = debugfs_create_file(name, mode, parent, data, fops);
+ ret = tracefs_create_file(name, mode, parent, data, fops);
if (!ret)
- pr_warning("Could not create debugfs '%s' entry\n", name);
+ pr_warning("Could not create tracefs '%s' entry\n", name);
return ret;
}
@@ -6034,9 +6055,9 @@
if (IS_ERR(d_tracer))
return NULL;
- tr->options = debugfs_create_dir("options", d_tracer);
+ tr->options = tracefs_create_dir("options", d_tracer);
if (!tr->options) {
- pr_warning("Could not create debugfs directory 'options'\n");
+ pr_warning("Could not create tracefs directory 'options'\n");
return NULL;
}
@@ -6105,7 +6126,7 @@
return;
for (cnt = 0; topts[cnt].opt; cnt++)
- debugfs_remove(topts[cnt].entry);
+ tracefs_remove(topts[cnt].entry);
kfree(topts);
}
@@ -6194,7 +6215,7 @@
struct dentry *trace_instance_dir;
static void
-init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer);
+init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer);
static int
allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size)
@@ -6271,7 +6292,7 @@
#endif
}
-static int new_instance_create(const char *name)
+static int instance_mkdir(const char *name)
{
struct trace_array *tr;
int ret;
@@ -6310,17 +6331,17 @@
if (allocate_trace_buffers(tr, trace_buf_size) < 0)
goto out_free_tr;
- tr->dir = debugfs_create_dir(name, trace_instance_dir);
+ tr->dir = tracefs_create_dir(name, trace_instance_dir);
if (!tr->dir)
goto out_free_tr;
ret = event_trace_add_tracer(tr->dir, tr);
if (ret) {
- debugfs_remove_recursive(tr->dir);
+ tracefs_remove_recursive(tr->dir);
goto out_free_tr;
}
- init_tracer_debugfs(tr, tr->dir);
+ init_tracer_tracefs(tr, tr->dir);
list_add(&tr->list, &ftrace_trace_arrays);
@@ -6341,7 +6362,7 @@
}
-static int instance_delete(const char *name)
+static int instance_rmdir(const char *name)
{
struct trace_array *tr;
int found = 0;
@@ -6382,82 +6403,17 @@
return ret;
}
-static int instance_mkdir (struct inode *inode, struct dentry *dentry, umode_t mode)
-{
- struct dentry *parent;
- int ret;
-
- /* Paranoid: Make sure the parent is the "instances" directory */
- parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
- if (WARN_ON_ONCE(parent != trace_instance_dir))
- return -ENOENT;
-
- /*
- * The inode mutex is locked, but debugfs_create_dir() will also
- * take the mutex. As the instances directory can not be destroyed
- * or changed in any other way, it is safe to unlock it, and
- * let the dentry try. If two users try to make the same dir at
- * the same time, then the new_instance_create() will determine the
- * winner.
- */
- mutex_unlock(&inode->i_mutex);
-
- ret = new_instance_create(dentry->d_iname);
-
- mutex_lock(&inode->i_mutex);
-
- return ret;
-}
-
-static int instance_rmdir(struct inode *inode, struct dentry *dentry)
-{
- struct dentry *parent;
- int ret;
-
- /* Paranoid: Make sure the parent is the "instances" directory */
- parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
- if (WARN_ON_ONCE(parent != trace_instance_dir))
- return -ENOENT;
-
- /* The caller did a dget() on dentry */
- mutex_unlock(&dentry->d_inode->i_mutex);
-
- /*
- * The inode mutex is locked, but debugfs_create_dir() will also
- * take the mutex. As the instances directory can not be destroyed
- * or changed in any other way, it is safe to unlock it, and
- * let the dentry try. If two users try to make the same dir at
- * the same time, then the instance_delete() will determine the
- * winner.
- */
- mutex_unlock(&inode->i_mutex);
-
- ret = instance_delete(dentry->d_iname);
-
- mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
- mutex_lock(&dentry->d_inode->i_mutex);
-
- return ret;
-}
-
-static const struct inode_operations instance_dir_inode_operations = {
- .lookup = simple_lookup,
- .mkdir = instance_mkdir,
- .rmdir = instance_rmdir,
-};
-
static __init void create_trace_instances(struct dentry *d_tracer)
{
- trace_instance_dir = debugfs_create_dir("instances", d_tracer);
+ trace_instance_dir = tracefs_create_instance_dir("instances", d_tracer,
+ instance_mkdir,
+ instance_rmdir);
if (WARN_ON(!trace_instance_dir))
return;
-
- /* Hijack the dir inode operations, to allow mkdir */
- trace_instance_dir->d_inode->i_op = &instance_dir_inode_operations;
}
static void
-init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
+init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
{
int cpu;
@@ -6511,10 +6467,32 @@
#endif
for_each_tracing_cpu(cpu)
- tracing_init_debugfs_percpu(tr, cpu);
+ tracing_init_tracefs_percpu(tr, cpu);
}
+static struct vfsmount *trace_automount(void *ingore)
+{
+ struct vfsmount *mnt;
+ struct file_system_type *type;
+
+ /*
+ * To maintain backward compatibility for tools that mount
+ * debugfs to get to the tracing facility, tracefs is automatically
+ * mounted to the debugfs/tracing directory.
+ */
+ type = get_fs_type("tracefs");
+ if (!type)
+ return NULL;
+ mnt = vfs_kern_mount(type, 0, "tracefs", NULL);
+ put_filesystem(type);
+ if (IS_ERR(mnt))
+ return NULL;
+ mntget(mnt);
+
+ return mnt;
+}
+
/**
* tracing_init_dentry - initialize top level trace array
*
@@ -6526,23 +6504,30 @@
{
struct trace_array *tr = &global_trace;
+ /* The top level trace array uses NULL as parent */
if (tr->dir)
- return tr->dir;
+ return NULL;
if (WARN_ON(!debugfs_initialized()))
return ERR_PTR(-ENODEV);
- tr->dir = debugfs_create_dir("tracing", NULL);
-
+ /*
+ * As there may still be users that expect the tracing
+ * files to exist in debugfs/tracing, we must automount
+ * the tracefs file system there, so older tools still
+ * work with the newer kerenl.
+ */
+ tr->dir = debugfs_create_automount("tracing", NULL,
+ trace_automount, NULL);
if (!tr->dir) {
pr_warn_once("Could not create debugfs directory 'tracing'\n");
return ERR_PTR(-ENOMEM);
}
- return tr->dir;
+ return NULL;
}
-static __init int tracer_init_debugfs(void)
+static __init int tracer_init_tracefs(void)
{
struct dentry *d_tracer;
@@ -6552,7 +6537,7 @@
if (IS_ERR(d_tracer))
return 0;
- init_tracer_debugfs(&global_trace, d_tracer);
+ init_tracer_tracefs(&global_trace, d_tracer);
trace_create_file("tracing_thresh", 0644, d_tracer,
&global_trace, &tracing_thresh_fops);
@@ -6575,6 +6560,10 @@
create_trace_options_dir(&global_trace);
+ /* If the tracer was started via cmdline, create options for it here */
+ if (global_trace.current_trace != &nop_trace)
+ update_tracer_options(&global_trace, global_trace.current_trace);
+
return 0;
}
@@ -6910,5 +6899,5 @@
return 0;
}
-fs_initcall(tracer_init_debugfs);
+fs_initcall(tracer_init_tracefs);
late_initcall(clear_boot_tracer);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index dd8205a..d951ded 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -334,7 +334,7 @@
/**
- * struct tracer - a specific tracer and its callbacks to interact with debugfs
+ * struct tracer - a specific tracer and its callbacks to interact with tracefs
* @name: the name chosen to select it on the available_tracers file
* @init: called when one switches to this tracer (echo name > current_tracer)
* @reset: called when one switches to another tracer
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index db54dda..0d2e473 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -13,7 +13,7 @@
#include <linux/workqueue.h>
#include <linux/spinlock.h>
#include <linux/kthread.h>
-#include <linux/debugfs.h>
+#include <linux/tracefs.h>
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/ctype.h>
@@ -480,7 +480,7 @@
return;
if (!--dir->nr_events) {
- debugfs_remove_recursive(dir->entry);
+ tracefs_remove_recursive(dir->entry);
list_del(&dir->list);
__put_system_dir(dir);
}
@@ -499,7 +499,7 @@
}
spin_unlock(&dir->d_lock);
- debugfs_remove_recursive(dir);
+ tracefs_remove_recursive(dir);
}
list_del(&file->list);
@@ -1526,7 +1526,7 @@
} else
__get_system(system);
- dir->entry = debugfs_create_dir(name, parent);
+ dir->entry = tracefs_create_dir(name, parent);
if (!dir->entry) {
pr_warn("Failed to create system directory %s\n", name);
__put_system(system);
@@ -1539,12 +1539,12 @@
dir->subsystem = system;
file->system = dir;
- entry = debugfs_create_file("filter", 0644, dir->entry, dir,
+ entry = tracefs_create_file("filter", 0644, dir->entry, dir,
&ftrace_subsystem_filter_fops);
if (!entry) {
kfree(system->filter);
system->filter = NULL;
- pr_warn("Could not create debugfs '%s/filter' entry\n", name);
+ pr_warn("Could not create tracefs '%s/filter' entry\n", name);
}
trace_create_file("enable", 0644, dir->entry, dir,
@@ -1585,9 +1585,9 @@
d_events = parent;
name = ftrace_event_name(call);
- file->dir = debugfs_create_dir(name, d_events);
+ file->dir = tracefs_create_dir(name, d_events);
if (!file->dir) {
- pr_warn("Could not create debugfs '%s' directory\n", name);
+ pr_warn("Could not create tracefs '%s' directory\n", name);
return -1;
}
@@ -2228,7 +2228,7 @@
/*
* The top level array has already had its ftrace_event_file
* descriptors created in order to allow for early events to
- * be recorded. This function is called after the debugfs has been
+ * be recorded. This function is called after the tracefs has been
* initialized, and we now have to create the files associated
* to the events.
*/
@@ -2311,16 +2311,16 @@
struct dentry *d_events;
struct dentry *entry;
- entry = debugfs_create_file("set_event", 0644, parent,
+ entry = tracefs_create_file("set_event", 0644, parent,
tr, &ftrace_set_event_fops);
if (!entry) {
- pr_warn("Could not create debugfs 'set_event' entry\n");
+ pr_warn("Could not create tracefs 'set_event' entry\n");
return -ENOMEM;
}
- d_events = debugfs_create_dir("events", parent);
+ d_events = tracefs_create_dir("events", parent);
if (!d_events) {
- pr_warn("Could not create debugfs 'events' directory\n");
+ pr_warn("Could not create tracefs 'events' directory\n");
return -ENOMEM;
}
@@ -2412,7 +2412,7 @@
down_write(&trace_event_sem);
__trace_remove_event_dirs(tr);
- debugfs_remove_recursive(tr->event_dir);
+ tracefs_remove_recursive(tr->event_dir);
up_write(&trace_event_sem);
tr->event_dir = NULL;
@@ -2534,10 +2534,10 @@
if (IS_ERR(d_tracer))
return 0;
- entry = debugfs_create_file("available_events", 0444, d_tracer,
+ entry = tracefs_create_file("available_events", 0444, d_tracer,
tr, &ftrace_avail_fops);
if (!entry)
- pr_warn("Could not create debugfs 'available_events' entry\n");
+ pr_warn("Could not create tracefs 'available_events' entry\n");
if (trace_define_common_fields())
pr_warn("tracing: Failed to allocate common fields");
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 2d25ad1..9cfea4c 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -6,7 +6,6 @@
* is Copyright (c) Steven Rostedt <srostedt@redhat.com>
*
*/
-#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
#include <linux/slab.h>
@@ -151,7 +150,7 @@
* The curr_ret_stack is initialized to -1 and get increased
* in this function. So it can be less than -1 only if it was
* filtered out via ftrace_graph_notrace_addr() which can be
- * set from set_graph_notrace file in debugfs by user.
+ * set from set_graph_notrace file in tracefs by user.
*/
if (current->curr_ret_stack < -1)
return -EBUSY;
@@ -1432,7 +1431,7 @@
.llseek = generic_file_llseek,
};
-static __init int init_graph_debugfs(void)
+static __init int init_graph_tracefs(void)
{
struct dentry *d_tracer;
@@ -1445,7 +1444,7 @@
return 0;
}
-fs_initcall(init_graph_debugfs);
+fs_initcall(init_graph_tracefs);
static __init int init_graph_trace(void)
{
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index d73f565..ed998fb 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1310,7 +1310,7 @@
return ret;
}
-/* Make a debugfs interface for controlling probe points */
+/* Make a tracefs interface for controlling probe points */
static __init int init_kprobe_trace(void)
{
struct dentry *d_tracer;
@@ -1323,20 +1323,20 @@
if (IS_ERR(d_tracer))
return 0;
- entry = debugfs_create_file("kprobe_events", 0644, d_tracer,
+ entry = tracefs_create_file("kprobe_events", 0644, d_tracer,
NULL, &kprobe_events_ops);
/* Event list interface */
if (!entry)
- pr_warning("Could not create debugfs "
+ pr_warning("Could not create tracefs "
"'kprobe_events' entry\n");
/* Profile interface */
- entry = debugfs_create_file("kprobe_profile", 0444, d_tracer,
+ entry = tracefs_create_file("kprobe_profile", 0444, d_tracer,
NULL, &kprobe_profile_ops);
if (!entry)
- pr_warning("Could not create debugfs "
+ pr_warning("Could not create tracefs "
"'kprobe_profile' entry\n");
return 0;
}
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 4f815fb..19aff63 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -25,7 +25,7 @@
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/smp.h>
-#include <linux/debugfs.h>
+#include <linux/tracefs.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/ctype.h>
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 75e19e8..6cf9353 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -12,7 +12,7 @@
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
-#include <linux/debugfs.h>
+#include <linux/tracefs.h>
#include "trace_stat.h"
#include "trace.h"
@@ -65,7 +65,7 @@
static void destroy_session(struct stat_session *session)
{
- debugfs_remove(session->file);
+ tracefs_remove(session->file);
__reset_stat_session(session);
mutex_destroy(&session->stat_mutex);
kfree(session);
@@ -279,9 +279,9 @@
if (IS_ERR(d_tracing))
return 0;
- stat_dir = debugfs_create_dir("trace_stat", d_tracing);
+ stat_dir = tracefs_create_dir("trace_stat", d_tracing);
if (!stat_dir)
- pr_warning("Could not create debugfs "
+ pr_warning("Could not create tracefs "
"'trace_stat' entry\n");
return 0;
}
@@ -291,7 +291,7 @@
if (!stat_dir && tracing_stat_init())
return -ENODEV;
- session->file = debugfs_create_file(session->ts->name, 0644,
+ session->file = tracefs_create_file(session->ts->name, 0644,
stat_dir,
session, &tracing_stat_fops);
if (!session->file)