809 lines · 21.1 KB · C
RawDownload
// SPDX-License-Identifier: GPL-2.0-only/* *  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> * * tracefs is the file system that is used by the tracing infrastructure. */ #include <linux/module.h>#include <linux/fs.h>#include <linux/fs_context.h>#include <linux/fs_parser.h>#include <linux/kobject.h>#include <linux/namei.h>#include <linux/tracefs.h>#include <linux/fsnotify.h>#include <linux/security.h>#include <linux/seq_file.h>#include <linux/magic.h>#include <linux/slab.h>#include "internal.h" #define TRACEFS_DEFAULT_MODE	0700static struct kmem_cache *tracefs_inode_cachep __ro_after_init; static struct vfsmount *tracefs_mount;static int tracefs_mount_count;static bool tracefs_registered; /* * Keep track of all tracefs_inodes in order to update their * flags if necessary on a remount. */static DEFINE_SPINLOCK(tracefs_inode_lock);static LIST_HEAD(tracefs_inodes); static struct inode *tracefs_alloc_inode(struct super_block *sb){	struct tracefs_inode *ti;	unsigned long flags; 	ti = alloc_inode_sb(sb, tracefs_inode_cachep, GFP_KERNEL);	if (!ti)		return NULL; 	spin_lock_irqsave(&tracefs_inode_lock, flags);	list_add_rcu(&ti->list, &tracefs_inodes);	spin_unlock_irqrestore(&tracefs_inode_lock, flags); 	return &ti->vfs_inode;} static void tracefs_free_inode(struct inode *inode){	struct tracefs_inode *ti = get_tracefs(inode); 	kmem_cache_free(tracefs_inode_cachep, ti);} static void tracefs_destroy_inode(struct inode *inode){	struct tracefs_inode *ti = get_tracefs(inode);	unsigned long flags; 	spin_lock_irqsave(&tracefs_inode_lock, flags);	list_del_rcu(&ti->list);	spin_unlock_irqrestore(&tracefs_inode_lock, flags);} 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 __ro_after_init; static struct dentry *tracefs_syscall_mkdir(struct mnt_idmap *idmap,					    struct inode *inode, struct dentry *dentry,					    umode_t mode){	struct tracefs_inode *ti;	struct name_snapshot name;	int ret; 	/*	 * This is a new directory that does not take the default of	 * the rootfs. It becomes the default permissions for all the	 * files and directories underneath it.	 */	ti = get_tracefs(inode);	ti->flags |= TRACEFS_INSTANCE_INODE;	ti->private = inode; 	/*	 * 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.	 */	take_dentry_name_snapshot(&name, dentry);	inode_unlock(inode);	ret = tracefs_ops.mkdir(name.name.name);	inode_lock(inode);	release_dentry_name_snapshot(&name); 	return ERR_PTR(ret);} static int tracefs_syscall_rmdir(struct inode *inode, struct dentry *dentry){	struct name_snapshot name;	int ret; 	/*	 * 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.	 */	take_dentry_name_snapshot(&name, dentry);	inode_unlock(inode);	inode_unlock(d_inode(dentry)); 	ret = tracefs_ops.rmdir(name.name.name); 	inode_lock_nested(inode, I_MUTEX_PARENT);	inode_lock(d_inode(dentry));	release_dentry_name_snapshot(&name); 	return ret;} static void set_tracefs_inode_owner(struct inode *inode){	struct tracefs_inode *ti = get_tracefs(inode);	struct inode *root_inode = ti->private;	kuid_t uid;	kgid_t gid; 	uid = root_inode->i_uid;	gid = root_inode->i_gid; 	/*	 * If the root is not the mount point, then check the root's	 * permissions. If it was never set, then default to the	 * mount point.	 */	if (root_inode != d_inode(root_inode->i_sb->s_root)) {		struct tracefs_inode *rti; 		rti = get_tracefs(root_inode);		root_inode = d_inode(root_inode->i_sb->s_root); 		if (!(rti->flags & TRACEFS_UID_PERM_SET))			uid = root_inode->i_uid; 		if (!(rti->flags & TRACEFS_GID_PERM_SET))			gid = root_inode->i_gid;	} 	/*	 * If this inode has never been referenced, then update	 * the permissions to the superblock.	 */	if (!(ti->flags & TRACEFS_UID_PERM_SET))		inode->i_uid = uid; 	if (!(ti->flags & TRACEFS_GID_PERM_SET))		inode->i_gid = gid;} static int tracefs_permission(struct mnt_idmap *idmap,			      struct inode *inode, int mask){	set_tracefs_inode_owner(inode);	return generic_permission(idmap, inode, mask);} static int tracefs_getattr(struct mnt_idmap *idmap,			   const struct path *path, struct kstat *stat,			   u32 request_mask, unsigned int flags){	struct inode *inode = d_backing_inode(path->dentry); 	set_tracefs_inode_owner(inode);	generic_fillattr(idmap, request_mask, inode, stat);	return 0;} static int tracefs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,			   struct iattr *attr){	unsigned int ia_valid = attr->ia_valid;	struct inode *inode = d_inode(dentry);	struct tracefs_inode *ti = get_tracefs(inode); 	if (ia_valid & ATTR_UID)		ti->flags |= TRACEFS_UID_PERM_SET; 	if (ia_valid & ATTR_GID)		ti->flags |= TRACEFS_GID_PERM_SET; 	return simple_setattr(idmap, dentry, attr);} static const struct inode_operations tracefs_instance_dir_inode_operations = {	.lookup		= simple_lookup,	.mkdir		= tracefs_syscall_mkdir,	.rmdir		= tracefs_syscall_rmdir,	.permission	= tracefs_permission,	.getattr	= tracefs_getattr,	.setattr	= tracefs_setattr,}; static const struct inode_operations tracefs_dir_inode_operations = {	.lookup		= simple_lookup,	.permission	= tracefs_permission,	.getattr	= tracefs_getattr,	.setattr	= tracefs_setattr,}; static const struct inode_operations tracefs_file_inode_operations = {	.permission	= tracefs_permission,	.getattr	= tracefs_getattr,	.setattr	= tracefs_setattr,}; struct inode *tracefs_get_inode(struct super_block *sb){	struct inode *inode = new_inode(sb);	if (inode) {		inode->i_ino = get_next_ino();		simple_inode_init_ts(inode);	}	return inode;} struct tracefs_fs_info {	kuid_t uid;	kgid_t gid;	umode_t mode;	/* Opt_* bitfield. */	unsigned int opts;}; enum {	Opt_uid,	Opt_gid,	Opt_mode,}; static const struct fs_parameter_spec tracefs_param_specs[] = {	fsparam_gid	("gid",		Opt_gid),	fsparam_u32oct	("mode",	Opt_mode),	fsparam_uid	("uid",		Opt_uid),	{}}; static int tracefs_parse_param(struct fs_context *fc, struct fs_parameter *param){	struct tracefs_fs_info *opts = fc->s_fs_info;	struct fs_parse_result result;	int opt; 	opt = fs_parse(fc, tracefs_param_specs, param, &result);	if (opt < 0)		return opt; 	switch (opt) {	case Opt_uid:		opts->uid = result.uid;		break;	case Opt_gid:		opts->gid = result.gid;		break;	case Opt_mode:		opts->mode = result.uint_32 & S_IALLUGO;		break;	/*	 * We might like to report bad mount options here;	 * but traditionally tracefs has ignored all mount options	 */	} 	opts->opts |= BIT(opt); 	return 0;} static int tracefs_apply_options(struct super_block *sb, bool remount){	struct tracefs_fs_info *fsi = sb->s_fs_info;	struct inode *inode = d_inode(sb->s_root);	struct tracefs_inode *ti;	bool update_uid, update_gid;	int srcu_idx;	umode_t tmp_mode; 	/*	 * On remount, only reset mode/uid/gid if they were provided as mount	 * options.	 */ 	if (!remount || fsi->opts & BIT(Opt_mode)) {		tmp_mode = READ_ONCE(inode->i_mode) & ~S_IALLUGO;		tmp_mode |= fsi->mode;		WRITE_ONCE(inode->i_mode, tmp_mode);	} 	if (!remount || fsi->opts & BIT(Opt_uid))		inode->i_uid = fsi->uid; 	if (!remount || fsi->opts & BIT(Opt_gid))		inode->i_gid = fsi->gid; 	if (remount && (fsi->opts & BIT(Opt_uid) || fsi->opts & BIT(Opt_gid))) { 		update_uid = fsi->opts & BIT(Opt_uid);		update_gid = fsi->opts & BIT(Opt_gid); 		srcu_idx = eventfs_remount_lock();		rcu_read_lock();		list_for_each_entry_rcu(ti, &tracefs_inodes, list) {			if (update_uid) {				ti->flags &= ~TRACEFS_UID_PERM_SET;				ti->vfs_inode.i_uid = fsi->uid;			} 			if (update_gid) {				ti->flags &= ~TRACEFS_GID_PERM_SET;				ti->vfs_inode.i_gid = fsi->gid;			} 			/*			 * Note, the above ti->vfs_inode updates are			 * used in eventfs_remount() so they must come			 * before calling it.			 */			if (ti->flags & TRACEFS_EVENT_INODE)				eventfs_remount(ti, update_uid, update_gid);		}		rcu_read_unlock();		eventfs_remount_unlock(srcu_idx);	} 	return 0;} static int tracefs_reconfigure(struct fs_context *fc){	struct super_block *sb = fc->root->d_sb;	struct tracefs_fs_info *sb_opts = sb->s_fs_info;	struct tracefs_fs_info *new_opts = fc->s_fs_info; 	if (!new_opts)		return 0; 	sync_filesystem(sb);	/* structure copy of new mount options to sb */	*sb_opts = *new_opts; 	return tracefs_apply_options(sb, true);} static int tracefs_show_options(struct seq_file *m, struct dentry *root){	struct tracefs_fs_info *fsi = root->d_sb->s_fs_info; 	if (!uid_eq(fsi->uid, GLOBAL_ROOT_UID))		seq_printf(m, ",uid=%u",			   from_kuid_munged(&init_user_ns, fsi->uid));	if (!gid_eq(fsi->gid, GLOBAL_ROOT_GID))		seq_printf(m, ",gid=%u",			   from_kgid_munged(&init_user_ns, fsi->gid));	if (fsi->mode != TRACEFS_DEFAULT_MODE)		seq_printf(m, ",mode=%o", fsi->mode); 	return 0;} static int tracefs_drop_inode(struct inode *inode){	struct tracefs_inode *ti = get_tracefs(inode); 	/*	 * This inode is being freed and cannot be used for	 * eventfs. Clear the flag so that it doesn't call into	 * eventfs during the remount flag updates. The eventfs_inode	 * gets freed after an SRCU cycle, so the content will still	 * be safe if the iteration is going on now.	 */	ti->flags &= ~TRACEFS_EVENT_INODE; 	return 1;} static const struct super_operations tracefs_super_operations = {	.alloc_inode    = tracefs_alloc_inode,	.free_inode     = tracefs_free_inode,	.destroy_inode  = tracefs_destroy_inode,	.drop_inode     = tracefs_drop_inode,	.statfs		= simple_statfs,	.show_options	= tracefs_show_options,}; /* * It would be cleaner if eventfs had its own dentry ops. * * Note that d_revalidate is called potentially under RCU, * so it can't take the eventfs mutex etc. It's fine - if * we open a file just as it's marked dead, things will * still work just fine, and just see the old stale case. */static void tracefs_d_release(struct dentry *dentry){	if (dentry->d_fsdata)		eventfs_d_release(dentry);} static int tracefs_d_revalidate(struct inode *inode, const struct qstr *name,				struct dentry *dentry, unsigned int flags){	struct eventfs_inode *ei = dentry->d_fsdata; 	return !(ei && ei->is_freed);} static int tracefs_d_delete(const struct dentry *dentry){	/*	 * We want to keep eventfs dentries around but not tracefs	 * ones. eventfs dentries have content in d_fsdata.	 * Use d_fsdata to determine if it's a eventfs dentry or not.	 */	return dentry->d_fsdata == NULL;} static const struct dentry_operations tracefs_dentry_operations = {	.d_revalidate = tracefs_d_revalidate,	.d_release = tracefs_d_release,	.d_delete = tracefs_d_delete,}; static int tracefs_fill_super(struct super_block *sb, struct fs_context *fc){	static const struct tree_descr trace_files[] = {{""}};	int err; 	err = simple_fill_super(sb, TRACEFS_MAGIC, trace_files);	if (err)		return err; 	sb->s_op = &tracefs_super_operations;	tracefs_apply_options(sb, false);	set_default_d_op(sb, &tracefs_dentry_operations); 	return 0;} static int tracefs_get_tree(struct fs_context *fc){	int err = get_tree_single(fc, tracefs_fill_super); 	if (err)		return err; 	return tracefs_reconfigure(fc);} static void tracefs_free_fc(struct fs_context *fc){	kfree(fc->s_fs_info);} static const struct fs_context_operations tracefs_context_ops = {	.free		= tracefs_free_fc,	.parse_param	= tracefs_parse_param,	.get_tree	= tracefs_get_tree,	.reconfigure	= tracefs_reconfigure,};

Lines 1–500 of 809.