security/selinux/hooks.c

/*
 *  NSA Security-Enhanced Linux (SELinux) security module
 *
 *  This file contains the SELinux hook function implementations.
 *
 *  Authors:  Stephen Smalley, <sds@epoch.ncsc.mil>
 *	      Chris Vance, <cvance@nai.com>
 *	      Wayne Salamon, <wsalamon@nai.com>
 *	      James Morris <jmorris@redhat.com>
 *
 *  Copyright (C) 2001,2002 Networks Associates Technology, Inc.
 *  Copyright (C) 2003-2008 Red Hat, Inc., James Morris <jmorris@redhat.com>
 *					   Eric Paris <eparis@redhat.com>
 *  Copyright (C) 2004-2005 Trusted Computer Solutions, Inc.
 *			    <dgoeddel@trustedcs.com>
 *  Copyright (C) 2006, 2007, 2009 Hewlett-Packard Development Company, L.P.
 *	Paul Moore <paul@paul-moore.com>
 *  Copyright (C) 2007 Hitachi Software Engineering Co., Ltd.
 *		       Yuichi Nakamura <ynakam@hitachisoft.jp>
 *
 *	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.
 */

#include <linux/init.h>
#include <linux/kd.h>
#include <linux/kernel.h>
#include <linux/tracehook.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/security.h>
#include <linux/xattr.h>
#include <linux/capability.h>
#include <linux/unistd.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/proc_fs.h>
#include <linux/swap.h>
#include <linux/spinlock.h>
#include <linux/syscalls.h>
#include <linux/dcache.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_ipv6.h>
#include <linux/tty.h>
#include <net/icmp.h>
#include <net/ip.h>		/* for local_port_range[] */
#include <net/sock.h>
#include <net/tcp.h>		/* struct or_callable used in sock_rcv_skb */
#include <net/inet_connection_sock.h>
#include <net/net_namespace.h>
#include <net/netlabel.h>
#include <linux/uaccess.h>
#include <asm/ioctls.h>
#include <linux/atomic.h>
#include <linux/bitops.h>
#include <linux/interrupt.h>
#include <linux/netdevice.h>	/* for network interface checks */
#include <net/netlink.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/dccp.h>
#include <linux/quota.h>
#include <linux/un.h>		/* for Unix socket types */
#include <net/af_unix.h>	/* for Unix socket types */
#include <linux/parser.h>
#include <linux/nfs_mount.h>
#include <net/ipv6.h>
#include <linux/hugetlb.h>
#include <linux/personality.h>
#include <linux/audit.h>
#include <linux/string.h>
#include <linux/selinux.h>
#include <linux/mutex.h>
#include <linux/posix-timers.h>
#include <linux/syslog.h>
#include <linux/user_namespace.h>
#include <linux/export.h>
#include <linux/msg.h>
#include <linux/shm.h>

#include "avc.h"
#include "objsec.h"
#include "netif.h"
#include "netnode.h"
#include "netport.h"
#include "xfrm.h"
#include "netlabel.h"
#include "audit.h"
#include "avc_ss.h"

extern struct security_operations *security_ops;

/* SECMARK reference count */
static atomic_t selinux_secmark_refcount = ATOMIC_INIT(0);

#ifdef CONFIG_SECURITY_SELINUX_DEVELOP
int selinux_enforcing;

static int __init enforcing_setup(char *str)
{
	unsigned long enforcing;
	if (!kstrtoul(str, 0, &enforcing))
		selinux_enforcing = enforcing ? 1 : 0;
	return 1;
}
__setup("enforcing=", enforcing_setup);
#endif

#ifdef CONFIG_SECURITY_SELINUX_BOOTPARAM
int selinux_enabled = CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE;

static int __init selinux_enabled_setup(char *str)
{
	unsigned long enabled;
	if (!kstrtoul(str, 0, &enabled))
		selinux_enabled = enabled ? 1 : 0;
	return 1;
}
__setup("selinux=", selinux_enabled_setup);
#else
int selinux_enabled = 1;
#endif

static struct kmem_cache *sel_inode_cache;

/**
 * selinux_secmark_enabled - Check to see if SECMARK is currently enabled
 *
 * Description:
 * This function checks the SECMARK reference counter to see if any SECMARK
 * targets are currently configured, if the reference counter is greater than
 * zero SECMARK is considered to be enabled.  Returns true (1) if SECMARK is
 * enabled, false (0) if SECMARK is disabled.  If the always_check_network
 * policy capability is enabled, SECMARK is always considered enabled.
 *
 */
static int selinux_secmark_enabled(void)
{
	return (selinux_policycap_alwaysnetwork || atomic_read(&selinux_secmark_refcount));
}

/**
 * selinux_peerlbl_enabled - Check to see if peer labeling is currently enabled
 *
 * Description:
 * This function checks if NetLabel or labeled IPSEC is enabled.  Returns true
 * (1) if any are enabled or false (0) if neither are enabled.  If the
 * always_check_network policy capability is enabled, peer labeling
 * is always considered enabled.
 *
 */
static int selinux_peerlbl_enabled(void)
{
	return (selinux_policycap_alwaysnetwork || netlbl_enabled() || selinux_xfrm_enabled());
}

static int selinux_netcache_avc_callback(u32 event)
{
	if (event == AVC_CALLBACK_RESET) {
		sel_netif_flush();
		sel_netnode_flush();
		sel_netport_flush();
		synchronize_net();
	}
	return 0;
}

/*
 * initialise the security for the init task
 */
static void cred_init_security(void)
{
	struct cred *cred = (struct cred *) current->real_cred;
	struct task_security_struct *tsec;

	tsec = kzalloc(sizeof(struct task_security_struct), GFP_KERNEL);
	if (!tsec)
		panic("SELinux:  Failed to initialize initial task.\n");

	tsec->osid = tsec->sid = SECINITSID_KERNEL;
	cred->security = tsec;
}

/*
 * get the security ID of a set of credentials
 */
static inline u32 cred_sid(const struct cred *cred)
{
	const struct task_security_struct *tsec;

	tsec = cred->security;
	return tsec->sid;
}

/*
 * get the objective security ID of a task
 */
static inline u32 task_sid(const struct task_struct *task)
{
	u32 sid;

	rcu_read_lock();
	sid = cred_sid(__task_cred(task));
	rcu_read_unlock();
	return sid;
}

/*
 * get the subjective security ID of the current task
 */
static inline u32 current_sid(void)
{
	const struct task_security_struct *tsec = current_security();

	return tsec->sid;
}

/* Allocate and free functions for each kind of security blob. */

static int inode_alloc_security(struct inode *inode)
{
	struct inode_security_struct *isec;
	u32 sid = current_sid();

	isec = kmem_cache_zalloc(sel_inode_cache, GFP_NOFS);
	if (!isec)
		return -ENOMEM;

	mutex_init(&isec->lock);
	INIT_LIST_HEAD(&isec->list);
	isec->inode = inode;
	isec->sid = SECINITSID_UNLABELED;
	isec->sclass = SECCLASS_FILE;
	isec->task_sid = sid;
	inode->i_security = isec;

	return 0;
}

static void inode_free_rcu(struct rcu_head *head)
{
	struct inode_security_struct *isec;

	isec = container_of(head, struct inode_security_struct, rcu);
	kmem_cache_free(sel_inode_cache, isec);
}

static void inode_free_security(struct inode *inode)
{
	struct inode_security_struct *isec = inode->i_security;
	struct superblock_security_struct *sbsec = inode->i_sb->s_security;

	spin_lock(&sbsec->isec_lock);
	if (!list_empty(&isec->list))
		list_del_init(&isec->list);
	spin_unlock(&sbsec->isec_lock);

	/*
	 * The inode may still be referenced in a path walk and
	 * a call to selinux_inode_permission() can be made
	 * after inode_free_security() is called. Ideally, the VFS
	 * wouldn't do this, but fixing that is a much harder
	 * job. For now, simply free the i_security via RCU, and
	 * leave the current inode->i_security pointer intact.
	 * The inode will be freed after the RCU grace period too.
	 */
	call_rcu(&isec->rcu, inode_free_rcu);
}

static int file_alloc_security(struct file *file)
{
	struct file_security_struct *fsec;
	u32 sid = current_sid();

	fsec = kzalloc(sizeof(struct file_security_struct), GFP_KERNEL);
	if (!fsec)
		return -ENOMEM;

	fsec->sid = sid;
	fsec->fown_sid = sid;
	file->f_security = fsec;

	return 0;
}

static void file_free_security(struct file *file)
{
	struct file_security_struct *fsec = file->f_security;
	file->f_security = NULL;
	kfree(fsec);
}

static int superblock_alloc_security(struct super_block *sb)
{
	struct superblock_security_struct *sbsec;

	sbsec = kzalloc(sizeof(struct superblock_security_struct), GFP_KERNEL);
	if (!sbsec)
		return -ENOMEM;

	mutex_init(&sbsec->lock);
	INIT_LIST_HEAD(&sbsec->isec_head);
	spin_lock_init(&sbsec->isec_lock);
	sbsec->sb = sb;
	sbsec->sid = SECINITSID_UNLABELED;
	sbsec->def_sid = SECINITSID_FILE;
	sbsec->mntpoint_sid = SECINITSID_UNLABELED;
	sb->s_security = sbsec;

	return 0;
}

static void superblock_free_security(struct super_block *sb)
{
	struct superblock_security_struct *sbsec = sb->s_security;
	sb->s_security = NULL;
	kfree(sbsec);
}

/* The file system's label must be initialized prior to use. */

static const char *labeling_behaviors[7] = {
	"uses xattr",
	"uses transition SIDs",
	"uses task SIDs",
	"uses genfs_contexts",
	"not configured for labeling",
	"uses mountpoint labeling",
	"uses native labeling",
};

static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry);

static inline int inode_doinit(struct inode *inode)
{
	return inode_doinit_with_dentry(inode, NULL);
}

enum {
	Opt_error = -1,
	Opt_context = 1,
	Opt_fscontext = 2,
	Opt_defcontext = 3,
	Opt_rootcontext = 4,
	Opt_labelsupport = 5,
	Opt_nextmntopt = 6,
};

#define NUM_SEL_MNT_OPTS	(Opt_nextmntopt - 1)

static const match_table_t tokens = {
	{Opt_context, CONTEXT_STR "%s"},
	{Opt_fscontext, FSCONTEXT_STR "%s"},
	{Opt_defcontext, DEFCONTEXT_STR "%s"},
	{Opt_rootcontext, ROOTCONTEXT_STR "%s"},
	{Opt_labelsupport, LABELSUPP_STR},
	{Opt_error, NULL},
};

#define SEL_MOUNT_FAIL_MSG "SELinux:  duplicate or incompatible mount options\n"

static int may_context_mount_sb_relabel(u32 sid,
			struct superblock_security_struct *sbsec,
			const struct cred *cred)
{
	const struct task_security_struct *tsec = cred->security;
	int rc;

	rc = avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM,
			  FILESYSTEM__RELABELFROM, NULL);
	if (rc)
		return rc;

	rc = avc_has_perm(tsec->sid, sid, SECCLASS_FILESYSTEM,
			  FILESYSTEM__RELABELTO, NULL);
	return rc;
}

static int may_context_mount_inode_relabel(u32 sid,
			struct superblock_security_struct *sbsec,
			const struct cred *cred)
{
	const struct task_security_struct *tsec = cred->security;
	int rc;
	rc = avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM,
			  FILESYSTEM__RELABELFROM, NULL);
	if (rc)
		return rc;

	rc = avc_has_perm(sid, sbsec->sid, SECCLASS_FILESYSTEM,
			  FILESYSTEM__ASSOCIATE, NULL);
	return rc;
}

static int selinux_is_sblabel_mnt(struct super_block *sb)
{
	struct superblock_security_struct *sbsec = sb->s_security;

	if (sbsec->behavior == SECURITY_FS_USE_XATTR ||
	    sbsec->behavior == SECURITY_FS_USE_TRANS ||
	    sbsec->behavior == SECURITY_FS_USE_TASK)
		return 1;

	/* Special handling for sysfs. Is genfs but also has setxattr handler*/
	if (strncmp(sb->s_type->name, "sysfs", sizeof("sysfs")) == 0)
		return 1;

	/*
	 * Special handling for rootfs. Is genfs but supports
	 * setting SELinux context on in-core inodes.
	 */
	if (strncmp(sb->s_type->name, "rootfs", sizeof("rootfs")) == 0)
		return 1;

	return 0;
}

static int sb_finish_set_opts(struct super_block *sb)
{
	struct superblock_security_struct *sbsec = sb->s_security;
	struct dentry *root = sb->s_root;
	struct inode *root_inode = root->d_inode;
	int rc = 0;

	if (sbsec->behavior == SECURITY_FS_USE_XATTR) {
		/* Make sure that the xattr handler exists and that no
		   error other than -ENODATA is returned by getxattr on
		   the root directory.  -ENODATA is ok, as this may be
		   the first boot of the SELinux kernel before we have
		   assigned xattr values to the filesystem. */
		if (!root_inode->i_op->getxattr) {
			printk(KERN_WARNING "SELinux: (dev %s, type %s) has no "
			       "xattr support\n", sb->s_id, sb->s_type->name);
			rc = -EOPNOTSUPP;
			goto out;
		}
		rc = root_inode->i_op->getxattr(root, XATTR_NAME_SELINUX, NULL, 0);
		if (rc < 0 && rc != -ENODATA) {
			if (rc == -EOPNOTSUPP)
				printk(KERN_WARNING "SELinux: (dev %s, type "
				       "%s) has no security xattr handler\n",
				       sb->s_id, sb->s_type->name);
			else
				printk(KERN_WARNING "SELinux: (dev %s, type "
				       "%s) getxattr errno %d\n", sb->s_id,
				       sb->s_type->name, -rc);
			goto out;
		}
	}

	if (sbsec->behavior > ARRAY_SIZE(labeling_behaviors))
		printk(KERN_ERR "SELinux: initialized (dev %s, type %s), unknown behavior\n",
		       sb->s_id, sb->s_type->name);
	else
		printk(KERN_DEBUG "SELinux: initialized (dev %s, type %s), %s\n",
		       sb->s_id, sb->s_type->name,
		       labeling_behaviors[sbsec->behavior-1]);

	sbsec->flags |= SE_SBINITIALIZED;
	if (selinux_is_sblabel_mnt(sb))
		sbsec->flags |= SBLABEL_MNT;

	/* Initialize the root inode. */
	rc = inode_doinit_with_dentry(root_inode, root);

	/* Initialize any other inodes associated with the superblock, e.g.
	   inodes created prior to initial policy load or inodes created
	   during get_sb by a pseudo filesystem that directly
	   populates itself. */
	spin_lock(&sbsec->isec_lock);
next_inode:
	if (!list_empty(&sbsec->isec_head)) {
		struct inode_security_struct *isec =
				list_entry(sbsec->isec_head.next,
					   struct inode_security_struct, list);
		struct inode *inode = isec->inode;
		spin_unlock(&sbsec->isec_lock);
		inode = igrab(inode);
		if (inode) {
			if (!IS_PRIVATE(inode))
				inode_doinit(inode);
			iput(inode);
		}
		spin_lock(&sbsec->isec_lock);
		list_del_init(&isec->list);
		goto next_inode;
	}
	spin_unlock(&sbsec->isec_lock);
out:
	return rc;
}

/*
 * This function should allow an FS to ask what it's mount security
 * options were so it can use those later for submounts, displaying
 * mount options, or whatever.
 */
static int selinux_get_mnt_opts(const struct super_block *sb,
				struct security_mnt_opts *opts)
{
	int rc = 0, i;
	struct superblock_security_struct *sbsec = sb->s_security;
	char *context = NULL;
	u32 len;
	char tmp;

	security_init_mnt_opts(opts);

	if (!(sbsec->flags & SE_SBINITIALIZED))
		return -EINVAL;

	if (!ss_initialized)
		return -EINVAL;

	/* make sure we always check enough bits to cover the mask */
	BUILD_BUG_ON(SE_MNTMASK >= (1 << NUM_SEL_MNT_OPTS));

	tmp = sbsec->flags & SE_MNTMASK;
	/* count the number of mount options for this sb */
	for (i = 0; i < NUM_SEL_MNT_OPTS; i++) {
		if (tmp & 0x01)
			opts->num_mnt_opts++;
		tmp >>= 1;
	}
	/* Check if the Label support flag is set */
	if (sbsec->flags & SBLABEL_MNT)
		opts->num_mnt_opts++;

	opts->mnt_opts = kcalloc(opts->num_mnt_opts, sizeof(char *), GFP_ATOMIC);
	if (!opts->mnt_opts) {
		rc = -ENOMEM;
		goto out_free;
	}

	opts->mnt_opts_flags = kcalloc(opts->num_mnt_opts, sizeof(int), GFP_ATOMIC);
	if (!opts->mnt_opts_flags) {
		rc = -ENOMEM;
		goto out_free;
	}

	i = 0;
	if (sbsec->flags & FSCONTEXT_MNT) {
		rc = security_sid_to_context(sbsec->sid, &context, &len);
		if (rc)
			goto out_free;
		opts->mnt_opts[i] = context;
		opts->mnt_opts_flags[i++] = FSCONTEXT_MNT;
	}
	if (sbsec->flags & CONTEXT_MNT) {
		rc = security_sid_to_context(sbsec->mntpoint_sid, &context, &len);
		if (rc)
			goto out_free;
		opts->mnt_opts[i] = context;
		opts->mnt_opts_flags[i++] = CONTEXT_MNT;
	}
	if (sbsec->flags & DEFCONTEXT_MNT) {
		rc = security_sid_to_context(sbsec->def_sid, &context, &len);
		if (rc)
			goto out_free;
		opts->mnt_opts[i] = context;
		opts->mnt_opts_flags[i++] = DEFCONTEXT_MNT;
	}
	if (sbsec->flags & ROOTCONTEXT_MNT) {
		struct inode *root = sbsec->sb->s_root->d_inode;
		struct inode_security_struct *isec = root->i_security;

		rc = security_sid_to_context(isec->sid, &context, &len);
		if (rc)
			goto out_free;
		opts->mnt_opts[i] = context;
		opts->mnt_opts_flags[i++] = ROOTCONTEXT_MNT;
	}
	if (sbsec->flags & SBLABEL_MNT) {
		opts->mnt_opts[i] = NULL;
		opts->mnt_opts_flags[i++] = SBLABEL_MNT;
	}

	BUG_ON(i != opts->num_mnt_opts);

	return 0;

out_free:
	security_free_mnt_opts(opts);
	return rc;
}

static int bad_option(struct superblock_security_struct *sbsec, char flag,
		      u32 old_sid, u32 new_sid)
{
	char mnt_flags = sbsec->flags & SE_MNTMASK;

	/* check if the old mount command had the same options */
	if (sbsec->flags & SE_SBINITIALIZED)
		if (!(sbsec->flags & flag) ||
		    (old_sid != new_sid))
			return 1;

	/* check if we were passed the same options twice,
	 * aka someone passed context=a,context=b
	 */
	if (!(sbsec->flags & SE_SBINITIALIZED))
		if (mnt_flags & flag)
			return 1;
	return 0;
}

/*
 * Allow filesystems with binary mount data to explicitly set mount point
 * labeling information.
 */
static int selinux_set_mnt_opts(struct super_block *sb,
				struct security_mnt_opts *opts,
				unsigned long kern_flags,
				unsigned long *set_kern_flags)
{
	const struct cred *cred = current_cred();
	int rc = 0, i;
	struct superblock_security_struct *sbsec = sb->s_security;
	const char *name = sb->s_type->name;
	struct inode *inode = sbsec->sb->s_root->d_inode;
	struct inode_security_struct *root_isec = inode->i_security;
	u32 fscontext_sid = 0, context_sid = 0, rootcontext_sid = 0;
	u32 defcontext_sid = 0;
	char **mount_options = opts->mnt_opts;
	int *flags = opts->mnt_opts_flags;
	int num_opts = opts->num_mnt_opts;

	mutex_lock(&sbsec->lock);

	if (!ss_initialized) {
		if (!num_opts) {
			/* Defer initialization until selinux_complete_init,
			   after the initial policy is loaded and the security
			   server is ready to handle calls. */
			goto out;
		}
		rc = -EINVAL;
		printk(KERN_WARNING "SELinux: Unable to set superblock options "
			"before the security server is initialized\n");
		goto out;
	}
	if (kern_flags && !set_kern_flags) {
		/* Specifying internal flags without providing a place to
		 * place the results is not allowed */
		rc = -EINVAL;
		goto out;
	}

	/*
	 * Binary mount data FS will come through this function twice.  Once
	 * from an explicit call and once from the generic calls from the vfs.
	 * Since the generic VFS calls will not contain any security mount data
	 * we need to skip the double mount verification.
	 *
	 * This does open a hole in which we will not notice if the first
	 * mount using this sb set explict options and a second mount using
	 * this sb does not set any security options.  (The first options
	 * will be used for both mounts)
	 */
	if ((sbsec->flags & SE_SBINITIALIZED) && (sb->s_type->fs_flags & FS_BINARY_MOUNTDATA)
	    && (num_opts == 0))
		goto out;

	/*
	 * parse the mount options, check if they are valid sids.
	 * also check if someone is trying to mount the same sb more
	 * than once with different security options.
	 */
	for (i = 0; i < num_opts; i++) {
		u32 sid;

		if (flags[i] == SBLABEL_MNT)
			continue;
		rc = security_context_to_sid(mount_options[i],
					     strlen(mount_options[i]), &sid, GFP_KERNEL);
		if (rc) {
			printk(KERN_WARNING "SELinux: security_context_to_sid"
			       "(%s) failed for (dev %s, type %s) errno=%d\n",
			       mount_options[i], sb->s_id, name, rc);
			goto out;
		}
		switch (flags[i]) {
		case FSCONTEXT_MNT:
			fscontext_sid = sid;

			if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid,
					fscontext_sid))
				goto out_double_mount;

			sbsec->flags |= FSCONTEXT_MNT;
			break;
		case CONTEXT_MNT:
			context_sid = sid;

			if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid,
					context_sid))
				goto out_double_mount;

			sbsec->flags |= CONTEXT_MNT;
			break;
		case ROOTCONTEXT_MNT:
			rootcontext_sid = sid;

			if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid,
					rootcontext_sid))
				goto out_double_mount;

			sbsec->flags |= ROOTCONTEXT_MNT;

			break;
		case DEFCONTEXT_MNT:
			defcontext_sid = sid;

			if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid,
					defcontext_sid))
				goto out_double_mount;

			sbsec->flags |= DEFCONTEXT_MNT;

			break;
		default:
			rc = -EINVAL;
			goto out;
		}
	}

	if (sbsec->flags & SE_SBINITIALIZED) {
		/* previously mounted with options, but not on this attempt? */
		if ((sbsec->flags & SE_MNTMASK) && !num_opts)
			goto out_double_mount;
		rc = 0;
		goto out;
	}

	if (strcmp(sb->s_type->name, "proc") == 0)
		sbsec->flags |= SE_SBPROC;

	if (!sbsec->behavior) {
		/*
		 * Determine the labeling behavior to use for this
		 * filesystem type.
		 */
		rc = security_fs_use(sb);
		if (rc) {
			printk(KERN_WARNING
				"%s: security_fs_use(%s) returned %d\n",
					__func__, sb->s_type->name, rc);
			goto out;
		}
	}
	/* sets the context of the superblock for the fs being mounted. */
	if (fscontext_sid) {
		rc = may_context_mount_sb_relabel(fscontext_sid, sbsec, cred);
		if (rc)
			goto out;

		sbsec->sid = fscontext_sid;
	}

	/*
	 * Switch to using mount point labeling behavior.
	 * sets the label used on all file below the mountpoint, and will set
	 * the superblock context if not already set.
	 */
	if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !context_sid) {
		sbsec->behavior = SECURITY_FS_USE_NATIVE;
		*set_kern_flags |= SECURITY_LSM_NATIVE_LABELS;
	}

	if (context_sid) {
		if (!fscontext_sid) {
			rc = may_context_mount_sb_relabel(context_sid, sbsec,
							  cred);
			if (rc)
				goto out;
			sbsec->sid = context_sid;
		} else {
			rc = may_context_mount_inode_relabel(context_sid, sbsec,
							     cred);
			if (rc)
				goto out;
		}
		if (!rootcontext_sid)
			rootcontext_sid = context_sid;

		sbsec->mntpoint_sid = context_sid;
		sbsec->behavior = SECURITY_FS_USE_MNTPOINT;
	}

	if (rootcontext_sid) {
		rc = may_context_mount_inode_relabel(rootcontext_sid, sbsec,
						     cred);
		if (rc)
			goto out;

		root_isec->sid = rootcontext_sid;
		root_isec->initialized = 1;
	}

	if (defcontext_sid) {
		if (sbsec->behavior != SECURITY_FS_USE_XATTR &&
			sbsec->behavior != SECURITY_FS_USE_NATIVE) {
			rc = -EINVAL;
			printk(KERN_WARNING "SELinux: defcontext option is "
			       "invalid for this filesystem type\n");
			goto out;
		}

		if (defcontext_sid != sbsec->def_sid) {
			rc = may_context_mount_inode_relabel(defcontext_sid,
							     sbsec, cred);
			if (rc)
				goto out;
		}

		sbsec->def_sid = defcontext_sid;
	}

	rc = sb_finish_set_opts(sb);
out:
	mutex_unlock(&sbsec->lock);
	return rc;
out_double_mount:
	rc = -EINVAL;
	printk(KERN_WARNING "SELinux: mount invalid.  Same superblock, different "
	       "security settings for (dev %s, type %s)\n", sb->s_id, name);
	goto out;
}

static int selinux_cmp_sb_context(const struct super_block *oldsb,
				    const struct super_block *newsb)
{
	struct superblock_security_struct *old = oldsb->s_security;
	struct superblock_security_struct *new = newsb->s_security;
	char oldflags = old->flags & SE_MNTMASK;
	char newflags = new->flags & SE_MNTMASK;

	if (oldflags != newflags)
		goto mismatch;
	if ((oldflags & FSCONTEXT_MNT) && old->sid != new->sid)
		goto mismatch;
	if ((oldflags & CONTEXT_MNT) && old->mntpoint_sid != new->mntpoint_sid)
		goto mismatch;
	if ((oldflags & DEFCONTEXT_MNT) && old->def_sid != new->def_sid)
		goto mismatch;
	if (oldflags & ROOTCONTEXT_MNT) {
		struct inode_security_struct *oldroot = oldsb->s_root->d_inode->i_security;
		struct inode_security_struct *newroot = newsb->s_root->d_inode->i_security;
		if (oldroot->sid != newroot->sid)
			goto mismatch;
	}
	return 0;
mismatch:
	printk(KERN_WARNING "SELinux: mount invalid.  Same superblock, "
			    "different security settings for (dev %s, "
			    "type %s)\n", newsb->s_id, newsb->s_type->name);
	return -EBUSY;
}

static int selinux_sb_clone_mnt_opts(const struct super_block *oldsb,
					struct super_block *newsb)
{
	const struct superblock_security_struct *oldsbsec = oldsb->s_security;
	struct superblock_security_struct *newsbsec = newsb->s_security;

	int set_fscontext =	(oldsbsec->flags & FSCONTEXT_MNT);
	int set_context =	(oldsbsec->flags & CONTEXT_MNT);
	int set_rootcontext =	(oldsbsec->flags & ROOTCONTEXT_MNT);

	/*
	 * if the parent was able to be mounted it clearly had no special lsm
	 * mount options.  thus we can safely deal with this superblock later
	 */
	if (!ss_initialized)
		return 0;

	/* how can we clone if the old one wasn't set up?? */
	BUG_ON(!(oldsbsec->flags & SE_SBINITIALIZED));

	/* if fs is reusing a sb, make sure that the contexts match */
	if (newsbsec->flags & SE_SBINITIALIZED)
		return selinux_cmp_sb_context(oldsb, newsb);

	mutex_lock(&newsbsec->lock);

	newsbsec->flags = oldsbsec->flags;

	newsbsec->sid = oldsbsec->sid;
	newsbsec->def_sid = oldsbsec->def_sid;
	newsbsec->behavior = oldsbsec->behavior;

	if (set_context) {
		u32 sid = oldsbsec->mntpoint_sid;

		if (!set_fscontext)
			newsbsec->sid = sid;
		if (!set_rootcontext) {
			struct inode *newinode = newsb->s_root->d_inode;
			struct inode_security_struct *newisec = newinode->i_security;
			newisec->sid = sid;
		}
		newsbsec->mntpoint_sid = sid;
	}
	if (set_rootcontext) {
		const struct inode *oldinode = oldsb->s_root->d_inode;
		const struct inode_security_struct *oldisec = oldinode->i_security;
		struct inode *newinode = newsb->s_root->d_inode;
		struct inode_security_struct *newisec = newinode->i_security;

		newisec->sid = oldisec->sid;
	}

	sb_finish_set_opts(newsb);
	mutex_unlock(&newsbsec->lock);
	return 0;
}

static int selinux_parse_opts_str(char *options,
				  struct security_mnt_opts *opts)
{
	char *p;
	char *context = NULL, *defcontext = NULL;
	char *fscontext = NULL, *rootcontext = NULL;
	int rc, num_mnt_opts = 0;

	opts->num_mnt_opts = 0;

	/* Standard string-based options. */
	while ((p = strsep(&options, "|")) != NULL) {
		int token;
		substring_t args[MAX_OPT_ARGS];

		if (!*p)
			continue;

		token = match_token(p, tokens, args);

		switch (token) {
		case Opt_context:
			if (context || defcontext) {
				rc = -EINVAL;
				printk(KERN_WARNING SEL_MOUNT_FAIL_MSG);
				goto out_err;
			}
			context = match_strdup(&args[0]);
			if (!context) {
				rc = -ENOMEM;
				goto out_err;
			}
			break;

		case Opt_fscontext:
			if (fscontext) {
				rc = -EINVAL;
				printk(KERN_WARNING SEL_MOUNT_FAIL_MSG);
				goto out_err;
			}
			fscontext = match_strdup(&args[0]);
			if (!fscontext) {
				rc = -ENOMEM;
				goto out_err;
			}
			break;

		case Opt_rootcontext:
			if (rootcontext) {
				rc = -EINVAL;
				printk(KERN_WARNING SEL_MOUNT_FAIL_MSG);
				goto out_err;
			}
			rootcontext = match_strdup(&args[0]);
			if (!rootcontext) {
				rc = -ENOMEM;
				goto out_err;
			}
			break;

		case Opt_defcontext:
			if (context || defcontext) {
				rc = -EINVAL;
				printk(KERN_WARNING SEL_MOUNT_FAIL_MSG);
				goto out_err;
			}
			defcontext = match_strdup(&args[0]);
			if (!defcontext) {
				rc = -ENOMEM;
				goto out_err;
			}
			break;
		case Opt_labelsupport:
			break;
		default:
			rc = -EINVAL;
			printk(KERN_WARNING "SELinux:  unknown mount option\n");
			goto out_err;

		}
	}

	rc = -ENOMEM;
	opts->mnt_opts = kcalloc(NUM_SEL_MNT_OPTS, sizeof(char *), GFP_ATOMIC);
	if (!opts->mnt_opts)
		goto out_err;

	opts->mnt_opts_flags = kcalloc(NUM_SEL_MNT_OPTS, sizeof(int), GFP_ATOMIC);
	if (!opts->mnt_opts_flags) {
		kfree(opts->mnt_opts);
		goto out_err;
	}

	if (fscontext) {
		opts->mnt_opts[num_mnt_opts] = fscontext;
		opts->mnt_opts_flags[num_mnt_opts++] = FSCONTEXT_MNT;
	}
	if (context) {
		opts->mnt_opts[num_mnt_opts] = context;
		opts->mnt_opts_flags[num_mnt_opts++] = CONTEXT_MNT;
	}
	if (rootcontext) {
		opts->mnt_opts[num_mnt_opts] = rootcontext;
		opts->mnt_opts_flags[num_mnt_opts++] = ROOTCONTEXT_MNT;
	}
	if (defcontext) {
		opts->mnt_opts[num_mnt_opts] = defcontext;
		opts->mnt_opts_flags[num_mnt_opts++] = DEFCONTEXT_MNT;
	}

	opts->num_mnt_opts = num_mnt_opts;
	return 0;

out_err:
	kfree(context);
	kfree(defcontext);
	kfree(fscontext);
	kfree(rootcontext);
	return rc;
}
/*
 * string mount options parsing and call set the sbsec
 */
static int superblock_doinit(struct super_block *sb, void *data)
{
	int rc = 0;
	char *options = data;
	struct security_mnt_opts opts;

	security_init_mnt_opts(&opts);

	if (!data)
		goto out;

	BUG_ON(sb->s_type->fs_flags & FS_BINARY_MOUNTDATA);

	rc = selinux_parse_opts_str(options, &opts);
	if (rc)
		goto out_err;

out:
	rc = selinux_set_mnt_opts(sb, &opts, 0, NULL);

out_err:
	security_free_mnt_opts(&opts);
	return rc;
}

static void selinux_write_opts(struct seq_file *m,
			       struct security_mnt_opts *opts)
{
	int i;
	char *prefix;

	for (i = 0; i < opts->num_mnt_opts; i++) {
		char *has_comma;

		if (opts->mnt_opts[i])
			has_comma = strchr(opts->mnt_opts[i], ',');
		else
			has_comma = NULL;

		switch (opts->mnt_opts_flags[i]) {
		case CONTEXT_MNT:
			prefix = CONTEXT_STR;
			break;
		case FSCONTEXT_MNT:
			prefix = FSCONTEXT_STR;
			break;
		case ROOTCONTEXT_MNT:
			prefix = ROOTCONTEXT_STR;
			break;
		case DEFCONTEXT_MNT:
			prefix = DEFCONTEXT_STR;
			break;
		case SBLABEL_MNT:
			seq_putc(m, ',');
			seq_puts(m, LABELSUPP_STR);
			continue;
		default:
			BUG();
			return;
		};
		/* we need a comma before each option */
		seq_putc(m, ',');
		seq_puts(m, prefix);
		if (has_comma)
			seq_putc(m, '\"');
		seq_puts(m, opts->mnt_opts[i]);
		if (has_comma)
			seq_putc(m, '\"');
	}
}

static int selinux_sb_show_options(struct seq_file *m, struct super_block *sb)
{
	struct security_mnt_opts opts;
	int rc;

	rc = selinux_get_mnt_opts(sb, &opts);
	if (rc) {
		/* before policy load we may get EINVAL, don't show anything */
		if (rc == -EINVAL)
			rc = 0;
		return rc;
	}

	selinux_write_opts(m, &opts);

	security_free_mnt_opts(&opts);

	return rc;
}

static inline u16 inode_mode_to_security_class(umode_t mode)
{
	switch (mode & S_IFMT) {
	case S_IFSOCK:
		return SECCLASS_SOCK_FILE;
	case S_IFLNK:
		return SECCLASS_LNK_FILE;
	case S_IFREG:
		return SECCLASS_FILE;
	case S_IFBLK:
		return SECCLASS_BLK_FILE;
	case S_IFDIR:
		return SECCLASS_DIR;
	case S_IFCHR:
		return SECCLASS_CHR_FILE;
	case S_IFIFO:
		return SECCLASS_FIFO_FILE;

	}

	return SECCLASS_FILE;
}

static inline int default_protocol_stream(int protocol)
{
	return (protocol == IPPROTO_IP || protocol == IPPROTO_TCP);
}

static inline int default_protocol_dgram(int protocol)
{
	return (protocol == IPPROTO_IP || protocol == IPPROTO_UDP);
}

static inline u16 socket_type_to_security_class(int family, int type, int protocol)
{
	switch (family) {
	case PF_UNIX:
		switch (type) {
		case SOCK_STREAM:
		case SOCK_SEQPACKET:
			return SECCLASS_UNIX_STREAM_SOCKET;
		case SOCK_DGRAM:
			return SECCLASS_UNIX_DGRAM_SOCKET;
		}
		break;
	case PF_INET:
	case PF_INET6:
		switch (type) {
		case SOCK_STREAM:
			if (default_protocol_stream(protocol))
				return SECCLASS_TCP_SOCKET;
			else
				return SECCLASS_RAWIP_SOCKET;
		case SOCK_DGRAM:
			if (default_protocol_dgram(protocol))
				return SECCLASS_UDP_SOCKET;
			else
				return SECCLASS_RAWIP_SOCKET;
		case SOCK_DCCP:
			return SECCLASS_DCCP_SOCKET;
		default:
			return SECCLASS_RAWIP_SOCKET;
		}
		break;
	case PF_NETLINK:
		switch (protocol) {
		case NETLINK_ROUTE:
			return SECCLASS_NETLINK_ROUTE_SOCKET;
		case NETLINK_FIREWALL:
			return SECCLASS_NETLINK_FIREWALL_SOCKET;
		case NETLINK_SOCK_DIAG:
			return SECCLASS_NETLINK_TCPDIAG_SOCKET;
		case NETLINK_NFLOG:
			return SECCLASS_NETLINK_NFLOG_SOCKET;
		case NETLINK_XFRM:
			return SECCLASS_NETLINK_XFRM_SOCKET;
		case NETLINK_SELINUX:
			return SECCLASS_NETLINK_SELINUX_SOCKET;
		case NETLINK_AUDIT:
			return SECCLASS_NETLINK_AUDIT_SOCKET;
		case NETLINK_IP6_FW:
			return SECCLASS_NETLINK_IP6FW_SOCKET;
		case NETLINK_DNRTMSG:
			return SECCLASS_NETLINK_DNRT_SOCKET;
		case NETLINK_KOBJECT_UEVENT:
			return SECCLASS_NETLINK_KOBJECT_UEVENT_SOCKET;
		default:
			return SECCLASS_NETLINK_SOCKET;
		}
	case PF_PACKET:
		return SECCLASS_PACKET_SOCKET;
	case PF_KEY:
		return SECCLASS_KEY_SOCKET;
	case PF_APPLETALK:
		return SECCLASS_APPLETALK_SOCKET;
	}

	return SECCLASS_SOCKET;
}

#ifdef CONFIG_PROC_FS
static int selinux_proc_get_sid(struct dentry *dentry,
				u16 tclass,
				u32 *sid)
{
	int rc;
	char *buffer, *path;

	buffer = (char *)__get_free_page(GFP_KERNEL);
	if (!buffer)
		return -ENOMEM;

	path = dentry_path_raw(dentry, buffer, PAGE_SIZE);
	if (IS_ERR(path))
		rc = PTR_ERR(path);
	else {
		/* each process gets a /proc/PID/ entry. Strip off the
		 * PID part to get a valid selinux labeling.
		 * e.g. /proc/1/net/rpc/nfs -> /net/rpc/nfs */
		while (path[1] >= '0' && path[1] <= '9') {
			path[1] = '/';
			path++;
		}
		rc = security_genfs_sid("proc", path, tclass, sid);
	}
	free_page((unsigned long)buffer);
	return rc;
}
#else
static int selinux_proc_get_sid(struct dentry *dentry,
				u16 tclass,
				u32 *sid)
{
	return -EINVAL;
}
#endif

/* The inode's security attributes must be initialized before first use. */
static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry)
{
	struct superblock_security_struct *sbsec = NULL;
	struct inode_security_struct *isec = inode->i_security;
	u32 sid;
	struct dentry *dentry;
#define INITCONTEXTLEN 255
	char *context = NULL;
	unsigned len = 0;
	int rc = 0;

	if (isec->initialized)
		goto out;

	mutex_lock(&isec->lock);
	if (isec->initialized)
		goto out_unlock;

	sbsec = inode->i_sb->s_security;
	if (!(sbsec->flags & SE_SBINITIALIZED)) {
		/* Defer initialization until selinux_complete_init,
		   after the initial policy is loaded and the security
		   server is ready to handle calls. */
		spin_lock(&sbsec->isec_lock);
		if (list_empty(&isec->list))
			list_add(&isec->list, &sbsec->isec_head);
		spin_unlock(&sbsec->isec_lock);
		goto out_unlock;
	}

	switch (sbsec->behavior) {
	case SECURITY_FS_USE_NATIVE:
		break;
	case SECURITY_FS_USE_XATTR:
		if (!inode->i_op->getxattr) {
			isec->sid = sbsec->def_sid;
			break;
		}

		/* Need a dentry, since the xattr API requires one.
		   Life would be simpler if we could just pass the inode. */
		if (opt_dentry) {
			/* Called from d_instantiate or d_splice_alias. */
			dentry = dget(opt_dentry);
		} else {
			/* Called from selinux_complete_init, try to find a dentry. */
			dentry = d_find_alias(inode);
		}
		if (!dentry) {
			/*
			 * this is can be hit on boot when a file is accessed
			 * before the policy is loaded.  When we load policy we
			 * may find inodes that have no dentry on the
			 * sbsec->isec_head list.  No reason to complain as these
			 * will get fixed up the next time we go through
			 * inode_doinit with a dentry, before these inodes could
			 * be used again by userspace.
			 */
			goto out_unlock;
		}

		len = INITCONTEXTLEN;
		context = kmalloc(len+1, GFP_NOFS);
		if (!context) {
			rc = -ENOMEM;
			dput(dentry);
			goto out_unlock;
		}
		context[len] = '\0';
		rc = inode->i_op->getxattr(dentry, XATTR_NAME_SELINUX,
					   context, len);
		if (rc == -ERANGE) {
			kfree(context);

			/* Need a larger buffer.  Query for the right size. */
			rc = inode->i_op->getxattr(dentry, XATTR_NAME_SELINUX,
						   NULL, 0);
			if (rc < 0) {
				dput(dentry);
				goto out_unlock;
			}
			len = rc;
			context = kmalloc(len+1, GFP_NOFS);
			if (!context) {
				rc = -ENOMEM;
				dput(dentry);
				goto out_unlock;
			}
			context[len] = '\0';
			rc = inode->i_op->getxattr(dentry,
						   XATTR_NAME_SELINUX,
						   context, len);
		}
		dput(dentry);
		if (rc < 0) {
			if (rc != -ENODATA) {
				printk(KERN_WARNING "SELinux: %s:  getxattr returned "
				       "%d for dev=%s ino=%ld\n", __func__,
				       -rc, inode->i_sb->s_id, inode->i_ino);
				kfree(context);
				goto out_unlock;
			}
			/* Map ENODATA to the default file SID */
			sid = sbsec->def_sid;
			rc = 0;
		} else {
			rc = security_context_to_sid_default(context, rc, &sid,
							     sbsec->def_sid,
							     GFP_NOFS);
			if (rc) {
				char *dev = inode->i_sb->s_id;
				unsigned long ino = inode->i_ino;

				if (rc == -EINVAL) {
					if (printk_ratelimit())
						printk(KERN_NOTICE "SELinux: inode=%lu on dev=%s was found to have an invalid "
							"context=%s.  This indicates you may need to relabel the inode or the "
							"filesystem in question.\n", ino, dev, context);
				} else {
					printk(KERN_WARNING "SELinux: %s:  context_to_sid(%s) "
					       "returned %d for dev=%s ino=%ld\n",
					       __func__, context, -rc, dev, ino);
				}
				kfree(context);
				/* Leave with the unlabeled SID */
				rc = 0;
				break;
			}
		}
		kfree(context);
		isec->sid = sid;
		break;
	case SECURITY_FS_USE_TASK:
		isec->sid = isec->task_sid;
		break;
	case SECURITY_FS_USE_TRANS:
		/* Default to the fs SID. */
		isec->sid = sbsec->sid;

		/* Try to obtain a transition SID. */
		isec->sclass = inode_mode_to_security_class(inode->i_mode);
		rc = security_transition_sid(isec->task_sid, sbsec->sid,
					     isec->sclass, NULL, &sid);
		if (rc)
			goto out_unlock;
		isec->sid = sid;
		break;
	case SECURITY_FS_USE_MNTPOINT:
		isec->sid = sbsec->mntpoint_sid;
		break;
	default:
		/* Default to the fs superblock SID. */
		isec->sid = sbsec->sid;

		if ((sbsec->flags & SE_SBPROC) && !S_ISLNK(inode->i_mode)) {
			/* We must have a dentry to determine the label on
			 * procfs inodes */
			if (opt_dentry)
				/* Called from d_instantiate or
				 * d_splice_alias. */
				dentry = dget(opt_dentry);
			else
				/* Called from selinux_complete_init, try to
				 * find a dentry. */
				dentry = d_find_alias(inode);
			/*
			 * This can be hit on boot when a file is accessed
			 * before the policy is loaded.  When we load policy we
			 * may find inodes that have no dentry on the
			 * sbsec->isec_head list.  No reason to complain as
			 * these will get fixed up the next time we go through
			 * inode_doinit() with a dentry, before these inodes
			 * could be used again by userspace.
			 */
			if (!dentry)
				goto out_unlock;
			isec->sclass = inode_mode_to_security_class(inode->i_mode);
			rc = selinux_proc_get_sid(dentry, isec->sclass, &sid);
			dput(dentry);
			if (rc)
				goto out_unlock;
			isec->sid = sid;
		}
		break;
	}

	isec->initialized = 1;

out_unlock:
	mutex_unlock(&isec->lock);
out:
	if (isec->sclass == SECCLASS_FILE)
		isec->sclass = inode_mode_to_security_class(inode->i_mode);
	return rc;
}

/* Convert a Linux signal to an access vector. */
static inline u32 signal_to_av(int sig)
{
	u32 perm = 0;

	switch (sig) {
	case SIGCHLD:
		/* Commonly granted from child to parent. */
		perm = PROCESS__SIGCHLD;
		break;
	case SIGKILL:
		/* Cannot be caught or ignored */
		perm = PROCESS__SIGKILL;
		break;
	case SIGSTOP:
		/* Cannot be caught or ignored */
		perm = PROCESS__SIGSTOP;
		break;
	default:
		/* All other signals. */
		perm = PROCESS__SIGNAL;
		break;
	}

	return perm;
}

/*
 * Check permission between a pair of credentials
 * fork check, ptrace check, etc.
 */
static int cred_has_perm(const struct cred *actor,
			 const struct cred *target,
			 u32 perms)
{
	u32 asid = cred_sid(actor), tsid = cred_sid(target);

	return avc_has_perm(asid, tsid, SECCLASS_PROCESS, perms, NULL);
}

/*
 * Check permission between a pair of tasks, e.g. signal checks,
 * fork check, ptrace check, etc.
 * tsk1 is the actor and tsk2 is the target
 * - this uses the default subjective creds of tsk1
 */
static int task_has_perm(const struct task_struct *tsk1,
			 const struct task_struct *tsk2,
			 u32 perms)
{
	const struct task_security_struct *__tsec1, *__tsec2;
	u32 sid1, sid2;

	rcu_read_lock();
	__tsec1 = __task_cred(tsk1)->security;	sid1 = __tsec1->sid;
	__tsec2 = __task_cred(tsk2)->security;	sid2 = __tsec2->sid;
	rcu_read_unlock();
	return avc_has_perm(sid1, sid2, SECCLASS_PROCESS, perms, NULL);
}

/*
 * Check permission between current and another task, e.g. signal checks,
 * fork check, ptrace check, etc.
 * current is the actor and tsk2 is the target
 * - this uses current's subjective creds
 */
static int current_has_perm(const struct task_struct *tsk,
			    u32 perms)
{
	u32 sid, tsid;

	sid = current_sid();
	tsid = task_sid(tsk);
	return avc_has_perm(sid, tsid, SECCLASS_PROCESS, perms, NULL);
}

#if CAP_LAST_CAP > 63
#error Fix SELinux to handle capabilities > 63.
#endif

/* Check whether a task is allowed to use a capability. */
static int cred_has_capability(const struct cred *cred,
			       int cap, int audit)
{
	struct common_audit_data ad;
	struct av_decision avd;
	u16 sclass;
	u32 sid = cred_sid(cred);
	u32 av = CAP_TO_MASK(cap);
	int rc;

	ad.type = LSM_AUDIT_DATA_CAP;
	ad.u.cap = cap;

	switch (CAP_TO_INDEX(cap)) {
	case 0:
		sclass = SECCLASS_CAPABILITY;
		break;
	case 1:
		sclass = SECCLASS_CAPABILITY2;
		break;
	default:
		printk(KERN_ERR
		       "SELinux:  out of range capability %d\n", cap);
		BUG();
		return -EINVAL;
	}

	rc = avc_has_perm_noaudit(sid, sid, sclass, av, 0, &avd);
	if (audit == SECURITY_CAP_AUDIT) {
		int rc2 = avc_audit(sid, sid, sclass, av, &avd, rc, &ad);
		if (rc2)
			return rc2;
	}
	return rc;
}

/* Check whether a task is allowed to use a system operation. */
static int task_has_system(struct task_struct *tsk,
			   u32 perms)
{
	u32 sid = task_sid(tsk);

	return avc_has_perm(sid, SECINITSID_KERNEL,
			    SECCLASS_SYSTEM, perms, NULL);
}

/* Check whether a task has a particular permission to an inode.
   The 'adp' parameter is optional and allows other audit
   data to be passed (e.g. the dentry). */
static int inode_has_perm(const struct cred *cred,
			  struct inode *inode,
			  u32 perms,
			  struct common_audit_data *adp)
{
	struct inode_security_struct *isec;
	u32 sid;

	validate_creds(cred);

	if (unlikely(IS_PRIVATE(inode)))
		return 0;

	sid = cred_sid(cred);
	isec = inode->i_security;

	return avc_has_perm(sid, isec->sid, isec->sclass, perms, adp);
}

/* Same as inode_has_perm, but pass explicit audit data containing
   the dentry to help the auditing code to more easily generate the
   pathname if needed. */
static inline int dentry_has_perm(const struct cred *cred,
				  struct dentry *dentry,
				  u32 av)
{
	struct inode *inode = dentry->d_inode;
	struct common_audit_data ad;

	ad.type = LSM_AUDIT_DATA_DENTRY;
	ad.u.dentry = dentry;
	return inode_has_perm(cred, inode, av, &ad);
}

/* Same as inode_has_perm, but pass explicit audit data containing
   the path to help the auditing code to more easily generate the
   pathname if needed. */
static inline int path_has_perm(const struct cred *cred,
				struct path *path,
				u32 av)
{
	struct inode *inode = path->dentry->d_inode;
	struct common_audit_data ad;

	ad.type = LSM_AUDIT_DATA_PATH;
	ad.u.path = *path;
	return inode_has_perm(cred, inode, av, &ad);
}

/* Same as path_has_perm, but uses the inode from the file struct. */
static inline int file_path_has_perm(const struct cred *cred,
				     struct file *file,
				     u32 av)
{
	struct common_audit_data ad;

	ad.type = LSM_AUDIT_DATA_PATH;
	ad.u.path = file->f_path;
	return inode_has_perm(cred, file_inode(file), av, &ad);
}

/* Check whether a task can use an open file descriptor to
   access an inode in a given way.  Check access to the
   descriptor itself, and then use dentry_has_perm to
   check a particular permission to the file.
   Access to the descriptor is implicitly granted if it
   has the same SID as the process.  If av is zero, then
   access to the file is not checked, e.g. for cases
   where only the descriptor is affected like seek. */
static int file_has_perm(const struct cred *cred,
			 struct file *file,
			 u32 av)
{
	struct file_security_struct *fsec = file->f_security;
	struct inode *inode = file_inode(file);
	struct common_audit_data ad;
	u32 sid = cred_sid(cred);
	int rc;

	ad.type = LSM_AUDIT_DATA_PATH;
	ad.u.path = file->f_path;

	if (sid != fsec->sid) {
		rc = avc_has_perm(sid, fsec->sid,
				  SECCLASS_FD,
				  FD__USE,
				  &ad);
		if (rc)
			goto out;
	}

	/* av is zero if only checking access to the descriptor. */
	rc = 0;
	if (av)
		rc = inode_has_perm(cred, inode, av, &ad);

out:
	return rc;
}

/* Check whether a task can create a file. */
static int may_create(struct inode *dir,
		      struct dentry *dentry,
		      u16 tclass)
{
	const struct task_security_struct *tsec = current_security();
	struct inode_security_struct *dsec;
	struct superblock_security_struct *sbsec;
	u32 sid, newsid;
	struct common_audit_data ad;
	int rc;

	dsec = dir->i_security;
	sbsec = dir->i_sb->s_security;

	sid = tsec->sid;
	newsid = tsec->create_sid;

	ad.type = LSM_AUDIT_DATA_DENTRY;
	ad.u.dentry = dentry;

	rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR,
			  DIR__ADD_NAME | DIR__SEARCH,
			  &ad);
	if (rc)
		return rc;

	if (!newsid || !(sbsec->flags & SBLABEL_MNT)) {
		rc = security_transition_sid(sid, dsec->sid, tclass,
					     &dentry->d_name, &newsid);
		if (rc)
			return rc;
	}

	rc = avc_has_perm(sid, newsid, tclass, FILE__CREATE, &ad);
	if (rc)
		return rc;

	return avc_has_perm(newsid, sbsec->sid,
			    SECCLASS_FILESYSTEM,
			    FILESYSTEM__ASSOCIATE, &ad);
}

/* Check whether a task can create a key. */
static int may_create_key(u32 ksid,
			  struct task_struct *ctx)
{
	u32 sid = task_sid(ctx);

	return avc_has_perm(sid, ksid, SECCLASS_KEY, KEY__CREATE, NULL);
}

#define MAY_LINK	0
#define MAY_UNLINK	1
#define MAY_RMDIR	2

/* Check whether a task can link, unlink, or rmdir a file/directory. */
static int may_link(struct inode *dir,
		    struct dentry *dentry,
		    int kind)

{
	struct inode_security_struct *dsec, *isec;
	struct common_audit_data ad;
	u32 sid = current_sid();
	u32 av;
	int rc;

	dsec = dir->i_security;
	isec = dentry->d_inode->i_security;

	ad.type = LSM_AUDIT_DATA_DENTRY;
	ad.u.dentry = dentry;

	av = DIR__SEARCH;
	av |= (kind ? DIR__REMOVE_NAME : DIR__ADD_NAME);
	rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR, av, &ad);
	if (rc)
		return rc;

	switch (kind) {
	case MAY_LINK:
		av = FILE__LINK;
		break;
	case MAY_UNLINK:
		av = FILE__UNLINK;
		break;
	case MAY_RMDIR:
		av = DIR__RMDIR;
		break;
	default:
		printk(KERN_WARNING "SELinux: %s:  unrecognized kind %d\n",
			__func__, kind);
		return 0;
	}

	rc = avc_has_perm(sid, isec->sid, isec->sclass, av, &ad);
	return rc;
}

static inline int may_rename(struct inode *old_dir,
			     struct dentry *old_dentry,
			     struct inode *new_dir,
			     struct dentry *new_dentry)
{
	struct inode_security_struct *old_dsec, *new_dsec, *old_isec, *new_isec;
	struct common_audit_data ad;
	u32 sid = current_sid();
	u32 av;
	int old_is_dir, new_is_dir;
	int rc;

	old_dsec = old_dir->i_security;
	old_isec = old_dentry->d_inode->i_security;
	old_is_dir = S_ISDIR(old_dentry->d_inode->i_mode);
	new_dsec = new_dir->i_security;

	ad.type = LSM_AUDIT_DATA_DENTRY;

	ad.u.dentry = old_dentry;
	rc = avc_has_perm(sid, old_dsec->sid, SECCLASS_DIR,
			  DIR__REMOVE_NAME | DIR__SEARCH, &ad);
	if (rc)
		return rc;
	rc = avc_has_perm(sid, old_isec->sid,
			  old_isec->sclass, FILE__RENAME, &ad);
	if (rc)
		return rc;
	if (old_is_dir && new_dir != old_dir) {
		rc = avc_has_perm(sid, old_isec->sid,
				  old_isec->sclass, DIR__REPARENT, &ad);
		if (rc)
			return rc;
	}

	ad.u.dentry = new_dentry;
	av = DIR__ADD_NAME | DIR__SEARCH;
	if (new_dentry->d_inode)
		av |= DIR__REMOVE_NAME;
	rc = avc_has_perm(sid, new_dsec->sid, SECCLASS_DIR, av, &ad);
	if (rc)
		return rc;
	if (new_dentry->d_inode) {
		new_isec = new_dentry->d_inode->i_security;
		new_is_dir = S_ISDIR(new_dentry->d_inode->i_mode);
		rc = avc_has_perm(sid, new_isec->sid,
				  new_isec->sclass,
				  (new_is_dir ? DIR__RMDIR : FILE__UNLINK), &ad);
		if (rc)
			return rc;
	}

	return 0;
}

/* Check whether a task can perform a filesystem operation. */
static int superblock_has_perm(const struct cred *cred,
			       struct super_block *sb,
			       u32 perms,
			       struct common_audit_data *ad)
{
	struct superblock_security_struct *sbsec;
	u32 sid = cred_sid(cred);

	sbsec = sb->s_security;
	return avc_has_perm(sid, sbsec->sid, SECCLASS_FILESYSTEM, perms, ad);
}

/* Convert a Linux mode and permission mask to an access vector. */
static inline u32 file_mask_to_av(int mode, int mask)
{
	u32 av = 0;

	if (!S_ISDIR(mode)) {
		if (mask & MAY_EXEC)
			av |= FILE__EXECUTE;
		if (mask & MAY_READ)
			av |= FILE__READ;

		if (mask & MAY_APPEND)
			av |= FILE__APPEND;
		else if (mask & MAY_WRITE)
			av |= FILE__WRITE;

	} else {
		if (mask & MAY_EXEC)
			av |= DIR__SEARCH;
		if (mask & MAY_WRITE)
			av |= DIR__WRITE;
		if (mask & MAY_READ)
			av |= DIR__READ;
	}

	return av;
}

/* Convert a Linux file to an access vector. */
static inline u32 file_to_av(struct file *file)
{
	u32 av = 0;

	if (file->f_mode & FMODE_READ)
		av |= FILE__READ;
	if (file->f_mode & FMODE_WRITE) {
		if (file->f_flags & O_APPEND)
			av |= FILE__APPEND;
		else
			av |= FILE__WRITE;
	}
	if (!av) {
		/*
		 * Special file opened with flags 3 for ioctl-only use.
		 */
		av = FILE__IOCTL;
	}

	return av;
}

/*
 * Convert a file to an access vector and include the correct open
 * open permission.
 */
static inline u32 open_file_to_av(struct file *file)
{
	u32 av = file_to_av(file);

	if (selinux_policycap_openperm)
		av |= FILE__OPEN;

	return av;
}

/* Hook functions begin here. */

static int selinux_ptrace_access_check(struct task_struct *child,
				     unsigned int mode)
{
	int rc;

	rc = cap_ptrace_access_check(child, mode);
	if (rc)
		return rc;

	if (mode & PTRACE_MODE_READ) {
		u32 sid = current_sid();
		u32 csid = task_sid(child);
		return avc_has_perm(sid, csid, SECCLASS_FILE, FILE__READ, NULL);
	}

	return current_has_perm(child, PROCESS__PTRACE);
}

static int selinux_ptrace_traceme(struct task_struct *parent)
{
	int rc;

	rc = cap_ptrace_traceme(parent);
	if (rc)
		return rc;

	return task_has_perm(parent, current, PROCESS__PTRACE);
}

static int selinux_capget(struct task_struct *target, kernel_cap_t *effective,
			  kernel_cap_t *inheritable, kernel_cap_t *permitted)
{
	int error;

	error = current_has_perm(target, PROCESS__GETCAP);
	if (error)
		return error;

	return cap_capget(target, effective, inheritable, permitted);
}

static int selinux_capset(struct cred *new, const struct cred *old,
			  const kernel_cap_t *effective,
			  const kernel_cap_t *inheritable,
			  const kernel_cap_t *permitted)
{
	int error;

	error = cap_capset(new, old,
				      effective, inheritable, permitted);
	if (error)
		return error;

	return cred_has_perm(old, new, PROCESS__SETCAP);
}

/*
 * (This comment used to live with the selinux_task_setuid hook,
 * which was removed).
 *
 * Since setuid only affects the current process, and since the SELinux
 * controls are not based on the Linux identity attributes, SELinux does not
 * need to control this operation.  However, SELinux does control the use of
 * the CAP_SETUID and CAP_SETGID capabilities using the capable hook.
 */

static int selinux_capable(const struct cred *cred, struct user_namespace *ns,
			   int cap, int audit)
{
	int rc;

	rc = cap_capable(cred, ns, cap, audit);
	if (rc)
		return rc;

	return cred_has_capability(cred, cap, audit);
}

static int selinux_quotactl(int cmds, int type, int id, struct super_block *sb)
{
	const struct cred *cred = current_cred();
	int rc = 0;

	if (!sb)
		return 0;

	switch (cmds) {
	case Q_SYNC:
	case Q_QUOTAON:
	case Q_QUOTAOFF:
	case Q_SETINFO:
	case Q_SETQUOTA:
		rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAMOD, NULL);
		break;
	case Q_GETFMT:
	case Q_GETINFO:
	case Q_GETQUOTA:
		rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAGET, NULL);
		break;
	default:
		rc = 0;  /* let the kernel handle invalid cmds */
		break;
	}
	return rc;
}

static int selinux_quota_on(struct dentry *dentry)
{
	const struct cred *cred = current_cred();

	return dentry_has_perm(cred, dentry, FILE__QUOTAON);
}

static int selinux_syslog(int type)
{
	int rc;

	switch (type) {
	case SYSLOG_ACTION_READ_ALL:	/* Read last kernel messages */
	case SYSLOG_ACTION_SIZE_BUFFER:	/* Return size of the log buffer */
		rc = task_has_system(current, SYSTEM__SYSLOG_READ);
		break;
	case SYSLOG_ACTION_CONSOLE_OFF:	/* Disable logging to console */
	case SYSLOG_ACTION_CONSOLE_ON:	/* Enable logging to console */
	/* Set level of messages printed to console */
	case SYSLOG_ACTION_CONSOLE_LEVEL:
		rc = task_has_system(current, SYSTEM__SYSLOG_CONSOLE);
		break;
	case SYSLOG_ACTION_CLOSE:	/* Close log */
	case SYSLOG_ACTION_OPEN:	/* Open log */
	case SYSLOG_ACTION_READ:	/* Read from log */
	case SYSLOG_ACTION_READ_CLEAR:	/* Read/clear last kernel messages */
	case SYSLOG_ACTION_CLEAR:	/* Clear ring buffer */
	default:
		rc = task_has_system(current, SYSTEM__SYSLOG_MOD);
		break;
	}
	return rc;
}

/*
 * Check that a process has enough memory to allocate a new virtual
 * mapping. 0 means there is enough memory for the allocation to
 * succeed and -ENOMEM implies there is not.
 *
 * Do not audit the selinux permission check, as this is applied to all
 * processes that allocate mappings.
 */
static int selinux_vm_enough_memory(struct mm_struct *mm, long pages)
{
	int rc, cap_sys_admin = 0;

	rc = selinux_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN,
			     SECURITY_CAP_NOAUDIT);
	if (rc == 0)
		cap_sys_admin = 1;

	return __vm_enough_memory(mm, pages, cap_sys_admin);
}

/* binprm security operations */

static int selinux_bprm_set_creds(struct linux_binprm *bprm)
{
	const struct task_security_struct *old_tsec;
	struct task_security_struct *new_tsec;
	struct inode_security_struct *isec;
	struct common_audit_data ad;
	struct inode *inode = file_inode(bprm->file);
	int rc;

	rc = cap_bprm_set_creds(bprm);
	if (rc)
		return rc;

	/* SELinux context only depends on initial program or script and not
	 * the script interpreter */
	if (bprm->cred_prepared)
		return 0;

	old_tsec = current_security();
	new_tsec = bprm->cred->security;
	isec = inode->i_security;

	/* Default to the current task SID. */
	new_tsec->sid = old_tsec->sid;
	new_tsec->osid = old_tsec->sid;

	/* Reset fs, key, and sock SIDs on execve. */
	new_tsec->create_sid = 0;
	new_tsec->keycreate_sid = 0;
	new_tsec->sockcreate_sid = 0;

	if (old_tsec->exec_sid) {
		new_tsec->sid = old_tsec->exec_sid;
		/* Reset exec SID on execve. */
		new_tsec->exec_sid = 0;

		/*
		 * Minimize confusion: if no_new_privs or nosuid and a
		 * transition is explicitly requested, then fail the exec.
		 */
		if (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)
			return -EPERM;
		if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)
			return -EACCES;
	} else {
		/* Check for a default transition on this program. */
		rc = security_transition_sid(old_tsec->sid, isec->sid,
					     SECCLASS_PROCESS, NULL,
					     &new_tsec->sid);
		if (rc)
			return rc;
	}

	ad.type = LSM_AUDIT_DATA_PATH;
	ad.u.path = bprm->file->f_path;

	if ((bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) ||
	    (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS))
		new_tsec->sid = old_tsec->sid;

	if (new_tsec->sid == old_tsec->sid) {
		rc = avc_has_perm(old_tsec->sid, isec->sid,
				  SECCLASS_FILE, FILE__EXECUTE_NO_TRANS, &ad);
		if (rc)
			return rc;
	} else {
		/* Check permissions for the transition. */
		rc = avc_has_perm(old_tsec->sid, new_tsec->sid,
				  SECCLASS_PROCESS, PROCESS__TRANSITION, &ad);
		if (rc)
			return rc;

		rc = avc_has_perm(new_tsec->sid, isec->sid,
				  SECCLASS_FILE, FILE__ENTRYPOINT, &ad);
		if (rc)
			return rc;

		/* Check for shared state */
		if (bprm->unsafe & LSM_UNSAFE_SHARE) {
			rc = avc_has_perm(old_tsec->sid, new_tsec->sid,
					  SECCLASS_PROCESS, PROCESS__SHARE,
					  NULL);
			if (rc)
				return -EPERM;
		}

		/* Make sure that anyone attempting to ptrace over a task that
		 * changes its SID has the appropriate permit */
		if (bprm->unsafe &
		    (LSM_UNSAFE_PTRACE | LSM_UNSAFE_PTRACE_CAP)) {
			struct task_struct *tracer;
			struct task_security_struct *sec;
			u32 ptsid = 0;

			rcu_read_lock();
			tracer = ptrace_parent(current);
			if (likely(tracer != NULL)) {
				sec = __task_cred(tracer)->security;
				ptsid = sec->sid;
			}
			rcu_read_unlock();

			if (ptsid != 0) {
				rc = avc_has_perm(ptsid, new_tsec->sid,
						  SECCLASS_PROCESS,
						  PROCESS__PTRACE, NULL);
				if (rc)
					return -EPERM;
			}
		}

		/* Clear any possibly unsafe personality bits on exec: */
		bprm->per_clear |= PER_CLEAR_ON_SETID;
	}

	return 0;
}

static int selinux_bprm_secureexec(struct linux_binprm *bprm)
{
	const struct task_security_struct *tsec = current_security();
	u32 sid, osid;
	int atsecure = 0;

	sid = tsec->sid;
	osid = tsec->osid;

	if (osid != sid) {
		/* Enable secure mode for SIDs transitions unless
		   the noatsecure permission is granted between
		   the two SIDs, i.e. ahp returns 0. */
		atsecure = avc_has_perm(osid, sid,
					SECCLASS_PROCESS,
					PROCESS__NOATSECURE, NULL);
	}

	return (atsecure || cap_bprm_secureexec(bprm));
}

static int match_file(const void *p, struct file *file, unsigned fd)
{
	return file_has_perm(p, file, file_to_av(file)) ? fd + 1 : 0;
}

/* Derived from fs/exec.c:flush_old_files. */
static inline void flush_unauthorized_files(const struct cred *cred,
					    struct files_struct *files)
{
	struct file *file, *devnull = NULL;
	struct tty_struct *tty;
	int drop_tty = 0;
	unsigned n;

	tty = get_current_tty();
	if (tty) {
		spin_lock(&tty_files_lock);
		if (!list_empty(&tty->tty_files)) {
			struct tty_file_private *file_priv;

			/* Revalidate access to controlling tty.
			   Use file_path_has_perm on the tty path directly
			   rather than using file_has_perm, as this particular
			   open file may belong to another process and we are
			   only interested in the inode-based check here. */
			file_priv = list_first_entry(&tty->tty_files,
						struct tty_file_private, list);
			file = file_priv->file;
			if (file_path_has_perm(cred, file, FILE__READ | FILE__WRITE))
				drop_tty = 1;
		}
		spin_unlock(&tty_files_lock);
		tty_kref_put(tty);
	}
	/* Reset controlling tty. */
	if (drop_tty)
		no_tty();

	/* Revalidate access to inherited open files. */
	n = iterate_fd(files, 0, match_file, cred);
	if (!n) /* none found? */
		return;

	devnull = dentry_open(&selinux_null, O_RDWR, cred);
	if (IS_ERR(devnull))
		devnull = NULL;
	/* replace all the matching ones with this */
	do {
		replace_fd(n - 1, devnull, 0);
	} while ((n = iterate_fd(files, n, match_file, cred)) != 0);
	if (devnull)
		fput(devnull);
}

/*
 * Prepare a process for imminent new credential changes due to exec
 */
static void selinux_bprm_committing_creds(struct linux_binprm *bprm)
{
	struct task_security_struct *new_tsec;
	struct rlimit *rlim, *initrlim;
	int rc, i;

	new_tsec = bprm->cred->security;
	if (new_tsec->sid == new_tsec->osid)
		return;

	/* Close files for which the new task SID is not authorized. */
	flush_unauthorized_files(bprm->cred, current->files);

	/* Always clear parent death signal on SID transitions. */
	current->pdeath_signal = 0;

	/* Check whether the new SID can inherit resource limits from the old
	 * SID.  If not, reset all soft limits to the lower of the current
	 * task's hard limit and the init task's soft limit.
	 *
	 * Note that the setting of hard limits (even to lower them) can be
	 * controlled by the setrlimit check.  The inclusion of the init task's
	 * soft limit into the computation is to avoid resetting soft limits
	 * higher than the default soft limit for cases where the default is
	 * lower than the hard limit, e.g. RLIMIT_CORE or RLIMIT_STACK.
	 */
	rc = avc_has_perm(new_tsec->osid, new_tsec->sid, SECCLASS_PROCESS,
			  PROCESS__RLIMITINH, NULL);
	if (rc) {
		/* protect against do_prlimit() */
		task_lock(current);
		for (i = 0; i < RLIM_NLIMITS; i++) {
			rlim = current->signal->rlim + i;
			initrlim = init_task.signal->rlim + i;
			rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur);
		}
		task_unlock(current);
		update_rlimit_cpu(current, rlimit(RLIMIT_CPU));
	}
}

/*
 * Clean up the process immediately after the installation of new credentials
 * due to exec
 */
static void selinux_bprm_committed_creds(struct linux_binprm *bprm)
{
	const struct task_security_struct *tsec = current_security();
	struct itimerval itimer;
	u32 osid, sid;
	int rc, i;

	osid = tsec->osid;
	sid = tsec->sid;

	if (sid == osid)
		return;

	/* Check whether the new SID can inherit signal state from the old SID.
	 * If not, clear itimers to avoid subsequent signal generation and
	 * flush and unblock signals.
	 *
	 * This must occur _after_ the task SID has been updated so that any
	 * kill done after the flush will be checked against the new SID.
	 */
	rc = avc_has_perm(osid, sid, SECCLASS_PROCESS, PROCESS__SIGINH, NULL);
	if (rc) {
		memset(&itimer, 0, sizeof itimer);
		for (i = 0; i < 3; i++)
			do_setitimer(i, &itimer, NULL);
		spin_lock_irq(&current->sighand->siglock);
		if (!(current->signal->flags & SIGNAL_GROUP_EXIT)) {
			__flush_signals(current);
			flush_signal_handlers(current, 1);
			sigemptyset(&current->blocked);
		}
		spin_unlock_irq(&current->sighand->siglock);
	}

	/* Wake up the parent if it is waiting so that it can recheck
	 * wait permission to the new task SID. */
	read_lock(&tasklist_lock);
	__wake_up_parent(current, current->real_parent);
	read_unlock(&tasklist_lock);
}

/* superblock security operations */

static int selinux_sb_alloc_security(struct super_block *sb)
{
	return superblock_alloc_security(sb);
}

static void selinux_sb_free_security(struct super_block *sb)
{
	superblock_free_security(sb);
}

static inline int match_prefix(char *prefix, int plen, char *option, int olen)
{
	if (plen > olen)
		return 0;

	return !memcmp(prefix, option, plen);
}

static inline int selinux_option(char *option, int len)
{
	return (match_prefix(CONTEXT_STR, sizeof(CONTEXT_STR)-1, option, len) ||
		match_prefix(FSCONTEXT_STR, sizeof(FSCONTEXT_STR)-1, option, len) ||
		match_prefix(DEFCONTEXT_STR, sizeof(DEFCONTEXT_STR)-1, option, len) ||
		match_prefix(ROOTCONTEXT_STR, sizeof(ROOTCONTEXT_STR)-1, option, len) ||
		match_prefix(LABELSUPP_STR, sizeof(LABELSUPP_STR)-1, option, len));
}

static inline void take_option(char **to, char *from, int *first, int len)
{
	if (!*first) {
		**to = ',';
		*to += 1;
	} else
		*first = 0;
	memcpy(*to, from, len);
	*to += len;
}

static inline void take_selinux_option(char **to, char *from, int *first,
				       int len)
{
	int current_size = 0;

	if (!*first) {
		**to = '|';
		*to += 1;
	} else
		*first = 0;

	while (current_size < len) {
		if (*from != '"') {
			**to = *from;
			*to += 1;
		}
		from += 1;
		current_size += 1;
	}
}

static int selinux_sb_copy_data(char *orig, char *copy)
{
	int fnosec, fsec, rc = 0;
	char *in_save, *in_curr, *in_end;
	char *sec_curr, *nosec_save, *nosec;
	int open_quote = 0;

	in_curr = orig;
	sec_curr = copy;

	nosec = (char *)get_zeroed_page(GFP_KERNEL);
	if (!nosec) {
		rc = -ENOMEM;
		goto out;
	}

	nosec_save = nosec;
	fnosec = fsec = 1;
	in_save = in_end = orig;

	do {
		if (*in_end == '"')
			open_quote = !open_quote;
		if ((*in_end == ',' && open_quote == 0) ||
				*in_end == '\0') {
			int len = in_end - in_curr;

			if (selinux_option(in_curr, len))
				take_selinux_option(&sec_curr, in_curr, &fsec, len);
			else
				take_option(&nosec, in_curr, &fnosec, len);

			in_curr = in_end + 1;
		}
	} while (*in_end++);

	strcpy(in_save, nosec_save);
	free_page((unsigned long)nosec_save);
out:
	return rc;
}

static int selinux_sb_remount(struct super_block *sb, void *data)
{
	int rc, i, *flags;
	struct security_mnt_opts opts;
	char *secdata, **mount_options;
	struct superblock_security_struct *sbsec = sb->s_security;

	if (!(sbsec->flags & SE_SBINITIALIZED))
		return 0;

	if (!data)
		return 0;

	if (sb->s_type->fs_flags & FS_BINARY_MOUNTDATA)
		return 0;

	security_init_mnt_opts(&opts);
	secdata = alloc_secdata();
	if (!secdata)
		return -ENOMEM;
	rc = selinux_sb_copy_data(data, secdata);
	if (rc)
		goto out_free_secdata;

	rc = selinux_parse_opts_str(secdata, &opts);
	if (rc)
		goto out_free_secdata;

	mount_options = opts.mnt_opts;
	flags = opts.mnt_opts_flags;

	for (i = 0; i < opts.num_mnt_opts; i++) {
		u32 sid;
		size_t len;

		if (flags[i] == SBLABEL_MNT)
			continue;
		len = strlen(mount_options[i]);
		rc = security_context_to_sid(mount_options[i], len, &sid,
					     GFP_KERNEL);
		if (rc) {
			printk(KERN_WARNING "SELinux: security_context_to_sid"
			       "(%s) failed for (dev %s, type %s) errno=%d\n",
			       mount_options[i], sb->s_id, sb->s_type->name, rc);
			goto out_free_opts;
		}
		rc = -EINVAL;
		switch (flags[i]) {
		case FSCONTEXT_MNT:
			if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, sid))
				goto out_bad_option;
			break;
		case CONTEXT_MNT:
			if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, sid))
				goto out_bad_option;
			break;
		case ROOTCONTEXT_MNT: {
			struct inode_security_struct *root_isec;
			root_isec = sb->s_root->d_inode->i_security;

			if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, sid))
				goto out_bad_option;
			break;
		}
		case DEFCONTEXT_MNT:
			if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, sid))
				goto out_bad_option;
			break;
		default:
			goto out_free_opts;
		}
	}

	rc = 0;
out_free_opts:
	security_free_mnt_opts(&opts);
out_free_secdata:
	free_secdata(secdata);
	return rc;
out_bad_option:
	printk(KERN_WARNING "SELinux: unable to change security options "
	       "during remount (dev %s, type=%s)\n", sb->s_id,
	       sb->s_type->name);
	goto out_free_opts;
}

static int selinux_sb_kern_mount(struct super_block *sb, int flags, void *data)
{
	const struct cred *cred = current_cred();
	struct common_audit_data ad;
	int rc;

	rc = superblock_doinit(sb, data);
	if (rc)
		return rc;

	/* Allow all mounts performed by the kernel */
	if (flags & MS_KERNMOUNT)
		return 0;

	ad.type = LSM_AUDIT_DATA_DENTRY;
	ad.u.dentry = sb->s_root;
	return superblock_has_perm(cred, sb, FILESYSTEM__MOUNT, &ad);
}

static int selinux_sb_statfs(struct dentry *dentry)
{
	const struct cred *cred = current_cred();
	struct common_audit_data ad;

	ad.type = LSM_AUDIT_DATA_DENTRY;
	ad.u.dentry = dentry->d_sb->s_root;
	return superblock_has_perm(cred, dentry->d_sb, FILESYSTEM__GETATTR, &ad);
}

static int selinux_mount(const char *dev_name,
			 struct path *path,
			 const char *type,
			 unsigned long flags,
			 void *data)
{
	const struct cred *cred = current_cred();

	if (flags & MS_REMOUNT)
		return superblock_has_perm(cred, path->dentry->d_sb,
					   FILESYSTEM__REMOUNT, NULL);
	else
		return path_has_perm(cred, path, FILE__MOUNTON);
}

static int selinux_umount(struct vfsmount *mnt, int flags)
{
	const struct cred *cred = current_cred();

	return superblock_has_perm(cred, mnt->mnt_sb,
				   FILESYSTEM__UNMOUNT, NULL);
}

/* inode security operations */

static int selinux_inode_alloc_security(struct inode *inode)
{
	return inode_alloc_security(inode);
}

static void selinux_inode_free_security(struct inode *inode)
{
	inode_free_security(inode);
}

static int selinux_dentry_init_security(struct dentry *dentry, int mode,
					struct qstr *name, void **ctx,
					u32 *ctxlen)
{
	const struct cred *cred = current_cred();
	struct task_security_struct *tsec;
	struct inode_security_struct *dsec;
	struct superblock_security_struct *sbsec;
	struct inode *dir = dentry->d_parent->d_inode;
	u32 newsid;
	int rc;

	tsec = cred->security;
	dsec = dir->i_security;
	sbsec = dir->i_sb->s_security;

	if (tsec->create_sid && sbsec->behavior != SECURITY_FS_USE_MNTPOINT) {
		newsid = tsec->create_sid;
	} else {
		rc = security_transition_sid(tsec->sid, dsec->sid,
					     inode_mode_to_security_class(mode),
					     name,
					     &newsid);
		if (rc) {
			printk(KERN_WARNING
				"%s: security_transition_sid failed, rc=%d\n",
			       __func__, -rc);
			return rc;
		}
	}

	return security_sid_to_context(newsid, (char **)ctx, ctxlen);
}

static int selinux_inode_init_security(struct inode *inode, struct inode *dir,
				       const struct qstr *qstr,
				       const char **name,
				       void **value, size_t *len)
{
	const struct task_security_struct *tsec = current_security();
	struct inode_security_struct *dsec;
	struct superblock_security_struct *sbsec;
	u32 sid, newsid, clen;
	int rc;
	char *context;

	dsec = dir->i_security;
	sbsec = dir->i_sb->s_security;

	sid = tsec->sid;
	newsid = tsec->create_sid;

	if ((sbsec->flags & SE_SBINITIALIZED) &&
	    (sbsec->behavior == SECURITY_FS_USE_MNTPOINT))
		newsid = sbsec->mntpoint_sid;
	else if (!newsid || !(sbsec->flags & SBLABEL_MNT)) {
		rc = security_transition_sid(sid, dsec->sid,
					     inode_mode_to_security_class(inode->i_mode),
					     qstr, &newsid);
		if (rc) {
			printk(KERN_WARNING "%s:  "
			       "security_transition_sid failed, rc=%d (dev=%s "
			       "ino=%ld)\n",
			       __func__,
			       -rc, inode->i_sb->s_id, inode->i_ino);
			return rc;
		}
	}

	/* Possibly defer initialization to selinux_complete_init. */
	if (sbsec->flags & SE_SBINITIALIZED) {
		struct inode_security_struct *isec = inode->i_security;
		isec->sclass = inode_mode_to_security_class(inode->i_mode);
		isec->sid = newsid;
		isec->initialized = 1;
	}

	if (!ss_initialized || !(sbsec->flags & SBLABEL_MNT))
		return -EOPNOTSUPP;

	if (name)
		*name = XATTR_SELINUX_SUFFIX;

	if (value && len) {
		rc = security_sid_to_context_force(newsid, &context, &clen);
		if (rc)
			return rc;
		*value = context;
		*len = clen;
	}

	return 0;
}

static int selinux_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode)
{
	return may_create(dir, dentry, SECCLASS_FILE);
}

static int selinux_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry)
{
	return may_link(dir, old_dentry, MAY_LINK);
}

static int selinux_inode_unlink(struct inode *dir, struct dentry *dentry)
{
	return may_link(dir, dentry, MAY_UNLINK);
}

static int selinux_inode_symlink(struct inode *dir, struct dentry *dentry, const char *name)
{
	return may_create(dir, dentry, SECCLASS_LNK_FILE);
}

static int selinux_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mask)
{
	return may_create(dir, dentry, SECCLASS_DIR);
}

static int selinux_inode_rmdir(struct inode *dir, struct dentry *dentry)
{
	return may_link(dir, dentry, MAY_RMDIR);
}

static int selinux_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
{
	return may_create(dir, dentry, inode_mode_to_security_class(mode));
}

static int selinux_inode_rename(struct inode *old_inode, struct dentry *old_dentry,
				struct inode *new_inode, struct dentry *new_dentry)
{
	return may_rename(old_inode, old_dentry, new_inode, new_dentry);
}

static int selinux_inode_readlink(struct dentry *dentry)
{
	const struct cred *cred = current_cred();

	return dentry_has_perm(cred, dentry, FILE__READ);
}

static int selinux_inode_follow_link(struct dentry *dentry, struct nameidata *nameidata)
{
	const struct cred *cred = current_cred();

	return dentry_has_perm(cred, dentry, FILE__READ);
}

static noinline int audit_inode_permission(struct inode *inode,
					   u32 perms, u32 audited, u32 denied,
					   int result,
					   unsigned flags)
{
	struct common_audit_data ad;
	struct inode_security_struct *isec = inode->i_security;
	int rc;

	ad.type = LSM_AUDIT_DATA_INODE;
	ad.u.inode = inode;

	rc = slow_avc_audit(current_sid(), isec->sid, isec->sclass, perms,
			    audited, denied, result, &ad, flags);
	if (rc)
		return rc;
	return 0;
}

static int selinux_inode_permission(struct inode *inode, int mask)
{
	const struct cred *cred = current_cred();
	u32 perms;
	bool from_access;
	unsigned flags = mask & MAY_NOT_BLOCK;
	struct inode_security_struct *isec;
	u32 sid;
	struct av_decision avd;
	int rc, rc2;
	u32 audited, denied;

	from_access = mask & MAY_ACCESS;
	mask &= (MAY_READ|MAY_WRITE|MAY_EXEC|MAY_APPEND);

	/* No permission to check.  Existence test. */
	if (!mask)
		return 0;

	validate_creds(cred);

	if (unlikely(IS_PRIVATE(inode)))
		return 0;

	perms = file_mask_to_av(inode->i_mode, mask);

	sid = cred_sid(cred);
	isec = inode->i_security;

	rc = avc_has_perm_noaudit(sid, isec->sid, isec->sclass, perms, 0, &avd);
	audited = avc_audit_required(perms, &avd, rc,
				     from_access ? FILE__AUDIT_ACCESS : 0,
				     &denied);
	if (likely(!audited))
		return rc;

	rc2 = audit_inode_permission(inode, perms, audited, denied, rc, flags);
	if (rc2)
		return rc2;
	return rc;
}

static int selinux_inode_setattr(struct dentry *dentry, struct iattr *iattr)
{
	const struct cred *cred = current_cred();
	unsigned int ia_valid = iattr->ia_valid;
	__u32 av = FILE__WRITE;

	/* ATTR_FORCE is just used for ATTR_KILL_S[UG]ID. */
	if (ia_valid & ATTR_FORCE) {
		ia_valid &= ~(ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_MODE |
			      ATTR_FORCE);
		if (!ia_valid)
			return 0;
	}

	if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID |
			ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_TIMES_SET))
		return dentry_has_perm(cred, dentry, FILE__SETATTR);

	if (selinux_policycap_openperm && (ia_valid & ATTR_SIZE))
		av |= FILE__OPEN;

	return dentry_has_perm(cred, dentry, av);
}

static int selinux_inode_getattr(struct vfsmount *mnt, struct dentry *dentry)
{
	const struct cred *cred = current_cred();
	struct path path;

	path.dentry = dentry;
	path.mnt = mnt;

	return path_has_perm(cred, &path, FILE__GETATTR);
}

static int selinux_inode_setotherxattr(struct dentry *dentry, const char *name)
{
	const struct cred *cred = current_cred();

	if (!strncmp(name, XATTR_SECURITY_PREFIX,
		     sizeof XATTR_SECURITY_PREFIX - 1)) {
		if (!strcmp(name, XATTR_NAME_CAPS)) {
			if (!capable(CAP_SETFCAP))
				return -EPERM;
		} else if (!capable(CAP_SYS_ADMIN)) {
			/* A different attribute in the security namespace.
			   Restrict to administrator. */
			return -EPERM;
		}
	}

	/* Not an attribute we recognize, so just check the
	   ordinary setattr permission. */
	return dentry_has_perm(cred, dentry, FILE__SETATTR);
}

static int selinux_inode_setxattr(struct dentry *dentry, const char *name,
				  const void *value, size_t size, int flags)
{
	struct inode *inode = dentry->d_inode;
	struct inode_security_struct *isec = inode->i_security;
	struct superblock_security_struct *sbsec;
	struct common_audit_data ad;
	u32 newsid, sid = current_sid();
	int rc = 0;

	if (strcmp(name, XATTR_NAME_SELINUX))
		return selinux_inode_setotherxattr(dentry, name);

	sbsec = inode->i_sb->s_security;
	if (!(sbsec->flags & SBLABEL_MNT))
		return -EOPNOTSUPP;

	if (!inode_owner_or_capable(inode))
		return -EPERM;

	ad.type = LSM_AUDIT_DATA_DENTRY;
	ad.u.dentry = dentry;

	rc = avc_has_perm(sid, isec->sid, isec->sclass,
			  FILE__RELABELFROM, &ad);
	if (rc)
		return rc;

	rc = security_context_to_sid(value, size, &newsid, GFP_KERNEL);
	if (rc == -EINVAL) {
		if (!capable(CAP_MAC_ADMIN)) {
			struct audit_buffer *ab;
			size_t audit_size;
			const char *str;

			/* We strip a nul only if it is at the end, otherwise the
			 * context contains a nul and we should audit that */
			if (value) {
				str = value;
				if (str[size - 1] == '\0')
					audit_size = size - 1;
				else
					audit_size = size;
			} else {
				str = "";
				audit_size = 0;
			}
			ab = audit_log_start(current->audit_context, GFP_ATOMIC, AUDIT_SELINUX_ERR);
			audit_log_format(ab, "op=setxattr invalid_context=");
			audit_log_n_untrustedstring(ab, value, audit_size);
			audit_log_end(ab);

			return rc;
		}
		rc = security_context_to_sid_force(value, size, &newsid);
	}
	if (rc)
		return rc;

	rc = avc_has_perm(sid, newsid, isec->sclass,
			  FILE__RELABELTO, &ad);
	if (rc)
		return rc;

	rc = security_validate_transition(isec->sid, newsid, sid,
					  isec->sclass);
	if (rc)
		return rc;

	return avc_has_perm(newsid,
			    sbsec->sid,
			    SECCLASS_FILESYSTEM,
			    FILESYSTEM__ASSOCIATE,
			    &ad);
}

static void selinux_inode_post_setxattr(struct dentry *dentry, const char *name,
					const void *value, size_t size,
					int flags)
{
	struct inode *inode = dentry->d_inode;
	struct inode_security_struct *isec = inode->i_security;
	u32 newsid;
	int rc;

	if (strcmp(name, XATTR_NAME_SELINUX)) {
		/* Not an attribute we recognize, so nothing to do. */
		return;
	}

	rc = security_context_to_sid_force(value, size, &newsid);
	if (rc) {
		printk(KERN_ERR "SELinux:  unable to map context to SID"
		       "for (%s, %lu), rc=%d\n",
		       inode->i_sb->s_id, inode->i_ino, -rc);
		return;
	}

	isec->sclass = inode_mode_to_security_class(inode->i_mode);
	isec->sid = newsid;
	isec->initialized = 1;

	return;
}

static int selinux_inode_getxattr(struct dentry *dentry, const char *name)
{
	const struct cred *cred = current_cred();

	return dentry_has_perm(cred, dentry, FILE__GETATTR);
}

static int selinux_inode_listxattr(struct dentry *dentry)
{
	const struct cred *cred = current_cred();

	return dentry_has_perm(cred, dentry, FILE__GETATTR);
}

static int selinux_inode_removexattr(struct dentry *dentry, const char *name)
{
	if (strcmp(name, XATTR_NAME_SELINUX))
		return selinux_inode_setotherxattr(dentry, name);

	/* No one is allowed to remove a SELinux security label.
	   You can change the label, but all data must be labeled. */
	return -EACCES;
}

/*
 * Copy the inode security context value to the user.
 *
 * Permission check is handled by selinux_inode_getxattr hook.
 */
static int selinux_inode_getsecurity(const struct inode *inode, const char *name, void **buffer, bool alloc)
{
	u32 size;
	int error;
	char *context = NULL;
	struct inode_security_struct *isec = inode->i_security;

	if (strcmp(name, XATTR_SELINUX_SUFFIX))
		return -EOPNOTSUPP;

	/*
	 * If the caller has CAP_MAC_ADMIN, then get the raw context
	 * value even if it is not defined by current policy; otherwise,
	 * use the in-core value under current policy.
	 * Use the non-auditing forms of the permission checks since
	 * getxattr may be called by unprivileged processes commonly
	 * and lack of permission just means that we fall back to the
	 * in-core context value, not a denial.
	 */
	error = selinux_capable(current_cred(), &init_user_ns, CAP_MAC_ADMIN,
				SECURITY_CAP_NOAUDIT);
	if (!error)
		error = security_sid_to_context_force(isec->sid, &context,
						      &size);
	else
		error = security_sid_to_context(isec->sid, &context, &size);
	if (error)
		return error;
	error = size;
	if (alloc) {
		*buffer = context;
		goto out_nofree;
	}
	kfree(context);
out_nofree:
	return error;
}

static int selinux_inode_setsecurity(struct inode *inode, const char *name,
				     const void *value, size_t size, int flags)
{
	struct inode_security_struct *isec = inode->i_security;
	u32 newsid;
	int rc;

	if (strcmp(name, XATTR_SELINUX_SUFFIX))
		return -EOPNOTSUPP;

	if (!value || !size)
		return -EACCES;

	rc = security_context_to_sid((void *)value, size, &newsid, GFP_KERNEL);
	if (rc)
		return rc;

	isec->sclass = inode_mode_to_security_class(inode->i_mode);
	isec->sid = newsid;
	isec->initialized = 1;
	return 0;
}

static int selinux_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size)
{
	const int len = sizeof(XATTR_NAME_SELINUX);
	if (buffer && len <= buffer_size)
		memcpy(buffer, XATTR_NAME_SELINUX, len);
	return len;
}

static void selinux_inode_getsecid(const struct inode *inode, u32 *secid)
{
	struct inode_security_struct *isec = inode->i_security;
	*secid = isec->sid;
}

/* file security operations */

static int selinux_revalidate_file_permission(struct file *file, int mask)
{
	const struct cred *cred = current_cred();
	struct inode *inode = file_inode(file);

	/* file_mask_to_av won't add FILE__WRITE if MAY_APPEND is set */
	if ((file->f_flags & O_APPEND) && (mask & MAY_WRITE))
		mask |= MAY_APPEND;

	return file_has_perm(cred, file,
			     file_mask_to_av(inode->i_mode, mask));
}

static int selinux_file_permission(struct file *file, int mask)