/*
 *  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 Hewlett-Packard Development Company, L.P.
 *              Paul Moore <paul.moore@hp.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/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/swap.h>
#include <linux/spinlock.h>
#include <linux/syscalls.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/proc_fs.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/tcp.h>            /* struct or_callable used in sock_rcv_skb */
#include <net/net_namespace.h>
#include <net/netlabel.h>
#include <linux/uaccess.h>
#include <asm/ioctls.h>
#include <asm/atomic.h>
#include <linux/bitops.h>
#include <linux/interrupt.h>
#include <linux/netdevice.h>    /* for network interface checks */
#include <linux/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/sysctl.h>
#include <linux/audit.h>
#include <linux/string.h>
#include <linux/selinux.h>
#include <linux/mutex.h>
#include <linux/posix-timers.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"

#define XATTR_SELINUX_SUFFIX "selinux"
#define XATTR_NAME_SELINUX XATTR_SECURITY_PREFIX XATTR_SELINUX_SUFFIX

#define NUM_SEL_MNT_OPTS 4

extern unsigned int policydb_loaded_version;
extern int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm);
extern int selinux_compat_net;
extern struct security_operations *security_ops;

/* SECMARK reference count */
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 (!strict_strtoul(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 (!strict_strtoul(str, 0, &enabled))
                selinux_enabled = enabled ? 1 : 0;
        return 1;
}
__setup("selinux=", selinux_enabled_setup);
#else
int selinux_enabled = 1;
#endif


/*
 * Minimal support for a secondary security module,
 * just to allow the use of the capability module.
 */
static struct security_operations *secondary_ops;

/* Lists of inode and superblock security structures initialized
   before the policy was loaded. */
static LIST_HEAD(superblock_security_head);
static DEFINE_SPINLOCK(sb_security_lock);

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.
 *
 */
static int selinux_secmark_enabled(void)
{
        return (atomic_read(&selinux_secmark_refcount) > 0);
}

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

static int task_alloc_security(struct task_struct *task)
{
        struct task_security_struct *tsec;

        tsec = kzalloc(sizeof(struct task_security_struct), GFP_KERNEL);
        if (!tsec)
                return -ENOMEM;

        tsec->osid = tsec->sid = SECINITSID_UNLABELED;
        task->security = tsec;

        return 0;
}

static void task_free_security(struct task_struct *task)
{
        struct task_security_struct *tsec = task->security;
        task->security = NULL;
        kfree(tsec);
}

static int inode_alloc_security(struct inode *inode)
{
        struct task_security_struct *tsec = current->security;
        struct inode_security_struct *isec;

        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 = tsec->sid;
        inode->i_security = isec;

        return 0;
}

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);

        inode->i_security = NULL;
        kmem_cache_free(sel_inode_cache, isec);
}

static int file_alloc_security(struct file *file)
{
        struct task_security_struct *tsec = current->security;
        struct file_security_struct *fsec;

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

        fsec->sid = tsec->sid;
        fsec->fown_sid = tsec->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->list);
        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;

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

        sb->s_security = NULL;
        kfree(sbsec);
}

static int sk_alloc_security(struct sock *sk, int family, gfp_t priority)
{
        struct sk_security_struct *ssec;

        ssec = kzalloc(sizeof(*ssec), priority);
        if (!ssec)
                return -ENOMEM;

        ssec->peer_sid = SECINITSID_UNLABELED;
        ssec->sid = SECINITSID_UNLABELED;
        sk->sk_security = ssec;

        selinux_netlbl_sk_security_reset(ssec, family);

        return 0;
}

static void sk_free_security(struct sock *sk)
{
        struct sk_security_struct *ssec = sk->sk_security;

        sk->sk_security = NULL;
        selinux_netlbl_sk_security_free(ssec);
        kfree(ssec);
}

/* The security server must be initialized before
   any labeling or access decisions can be provided. */
extern int ss_initialized;

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

static char *labeling_behaviors[6] = {
        "uses xattr",
        "uses transition SIDs",
        "uses task SIDs",
        "uses genfs_contexts",
        "not configured for labeling",
        "uses mountpoint 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,
};

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_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,
                        struct task_security_struct *tsec)
{
        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,
                        struct task_security_struct *tsec)
{
        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 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;
                }
        }

        sbsec->initialized = 1;

        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]);

        /* 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->initialized)
                return -EINVAL;

        if (!ss_initialized)
                return -EINVAL;

        /*
         * if we ever use sbsec flags for anything other than tracking mount
         * settings this is going to need a mask
         */
        tmp = sbsec->flags;
        /* count the number of mount options for this sb */
        for (i = 0; i < 8; i++) {
                if (tmp & 0x01)
                        opts->num_mnt_opts++;
                tmp >>= 1;
        }

        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;
        }

        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)
{
        /* check if the old mount command had the same options */
        if (sbsec->initialized)
                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->initialized)
                if (sbsec->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)
{
        int rc = 0, i;
        struct task_security_struct *tsec = current->security;
        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. */
                        spin_lock(&sb_security_lock);
                        if (list_empty(&sbsec->list))
                                list_add(&sbsec->list, &superblock_security_head);
                        spin_unlock(&sb_security_lock);
                        goto out;
                }
                rc = -EINVAL;
                printk(KERN_WARNING "SELinux: Unable to set superblock options "
                        "before the security server is initialized\n");
                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->initialized && (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;
                rc = security_context_to_sid(mount_options[i],
                                             strlen(mount_options[i]), &sid);
                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->initialized) {
                /* previously mounted with options, but not on this attempt? */
                if (sbsec->flags && !num_opts)
                        goto out_double_mount;
                rc = 0;
                goto out;
        }

        if (strcmp(sb->s_type->name, "proc") == 0)
                sbsec->proc = 1;

        /* Determine the labeling behavior to use for this filesystem type. */
        rc = security_fs_use(sb->s_type->name, &sbsec->behavior, &sbsec->sid);
        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, tsec);
                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 (context_sid) {
                if (!fscontext_sid) {
                        rc = may_context_mount_sb_relabel(context_sid, sbsec, tsec);
                        if (rc)
                                goto out;
                        sbsec->sid = context_sid;
                } else {
                        rc = may_context_mount_inode_relabel(context_sid, sbsec, tsec);
                        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, tsec);
                if (rc)
                        goto out;

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

        if (defcontext_sid) {
                if (sbsec->behavior != SECURITY_FS_USE_XATTR) {
                        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, tsec);
                        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 void 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 put this sb on the list and deal
         * with it later
         */
        if (!ss_initialized) {
                spin_lock(&sb_security_lock);
                if (list_empty(&newsbsec->list))
                        list_add(&newsbsec->list, &superblock_security_head);
                spin_unlock(&sb_security_lock);
                return;
        }

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

        /* if fs is reusing a sb, just let its options stand... */
        if (newsbsec->initialized)
                return;

        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);
}

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;

                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);

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 = strchr(opts->mnt_opts[i], ',');

                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;
                default:
                        BUG();
                };
                /* 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_INET_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 proc_dir_entry *de,
                                u16 tclass,
                                u32 *sid)
{
        int buflen, rc;
        char *buffer, *path, *end;

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

        buflen = PAGE_SIZE;
        end = buffer+buflen;
        *--end = '\0';
        buflen--;
        path = end-1;
        *path = '/';
        while (de && de != de->parent) {
                buflen -= de->namelen + 1;
                if (buflen < 0)
                        break;
                end -= de->namelen;
                memcpy(end, de->name, de->namelen);
                *--end = '/';
                path = end;
                de = de->parent;
        }
        rc = security_genfs_sid("proc", path, tclass, sid);
        free_page((unsigned long)buffer);
        return rc;
}
#else
static int selinux_proc_get_sid(struct proc_dir_entry *de,
                                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->initialized) {
                /* 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_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) {
                        printk(KERN_WARNING "SELinux: %s:  no dentry for dev=%s "
                               "ino=%ld\n", __func__, inode->i_sb->s_id,
                               inode->i_ino);
                        goto out_unlock;
                }

                len = INITCONTEXTLEN;
                context = kmalloc(len, GFP_NOFS);
                if (!context) {
                        rc = -ENOMEM;
                        dput(dentry);
                        goto out_unlock;
                }
                rc = inode->i_op->getxattr(dentry, XATTR_NAME_SELINUX,
                                           context, len);
                if (rc == -ERANGE) {
                        /* 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;
                        }
                        kfree(context);
                        len = rc;
                        context = kmalloc(len, GFP_NOFS);
                        if (!context) {
                                rc = -ENOMEM;
                                dput(dentry);
                                goto out_unlock;
                        }
                        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) {
                                printk(KERN_WARNING "SELinux: %s:  context_to_sid(%s) "
                                       "returned %d for dev=%s ino=%ld\n",
                                       __func__, context, -rc,
                                       inode->i_sb->s_id, inode->i_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,
                                             &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->proc && !S_ISLNK(inode->i_mode)) {
                        struct proc_inode *proci = PROC_I(inode);
                        if (proci->pde) {
                                isec->sclass = inode_mode_to_security_class(inode->i_mode);
                                rc = selinux_proc_get_sid(proci->pde,
                                                          isec->sclass,
                                                          &sid);
                                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 betweeen a pair of tasks, e.g. signal checks,
   fork check, ptrace check, etc. */
static int task_has_perm(struct task_struct *tsk1,
                         struct task_struct *tsk2,
                         u32 perms)
{
        struct task_security_struct *tsec1, *tsec2;

        tsec1 = tsk1->security;
        tsec2 = tsk2->security;
        return avc_has_perm(tsec1->sid, tsec2->sid,
                            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 task_has_capability(struct task_struct *tsk,
                               int cap)
{
        struct task_security_struct *tsec;
        struct avc_audit_data ad;
        u16 sclass;
        u32 av = CAP_TO_MASK(cap);

        tsec = tsk->security;

        AVC_AUDIT_DATA_INIT(&ad, CAP);
        ad.tsk = tsk;
        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 avc_has_perm(tsec->sid, tsec->sid, sclass, av, &ad);
}

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

        tsec = tsk->security;

        return avc_has_perm(tsec->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(struct task_struct *tsk,
                          struct inode *inode,
                          u32 perms,
                          struct avc_audit_data *adp)
{
        struct task_security_struct *tsec;
        struct inode_security_struct *isec;
        struct avc_audit_data ad;

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

        tsec = tsk->security;
        isec = inode->i_security;

        if (!adp) {
                adp = &ad;
                AVC_AUDIT_DATA_INIT(&ad, FS);
                ad.u.fs.inode = inode;
        }

        return avc_has_perm(tsec->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(struct task_struct *tsk,
                                  struct vfsmount *mnt,
                                  struct dentry *dentry,
                                  u32 av)
{
        struct inode *inode = dentry->d_inode;
        struct avc_audit_data ad;
        AVC_AUDIT_DATA_INIT(&ad, FS);
        ad.u.fs.path.mnt = mnt;
        ad.u.fs.path.dentry = dentry;
        return inode_has_perm(tsk, inode, 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(struct task_struct *tsk,
                                struct file *file,
                                u32 av)
{
        struct task_security_struct *tsec = tsk->security;
        struct file_security_struct *fsec = file->f_security;
        struct inode *inode = file->f_path.dentry->d_inode;
        struct avc_audit_data ad;
        int rc;

        AVC_AUDIT_DATA_INIT(&ad, FS);
        ad.u.fs.path = file->f_path;

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

        /* av is zero if only checking access to the descriptor. */
        if (av)
                return inode_has_perm(tsk, inode, av, &ad);

        return 0;
}

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

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

        AVC_AUDIT_DATA_INIT(&ad, FS);
        ad.u.fs.path.dentry = dentry;

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

        if (tsec->create_sid && sbsec->behavior != SECURITY_FS_USE_MNTPOINT) {
                newsid = tsec->create_sid;
        } else {
                rc = security_transition_sid(tsec->sid, dsec->sid, tclass,
                                             &newsid);
                if (rc)
                        return rc;
        }

        rc = avc_has_perm(tsec->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)
{
        struct task_security_struct *tsec;

        tsec = ctx->security;

        return avc_has_perm(tsec->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 task_security_struct *tsec;
        struct inode_security_struct *dsec, *isec;
        struct avc_audit_data ad;
        u32 av;
        int rc;

        tsec = current->security;
        dsec = dir->i_security;
        isec = dentry->d_inode->i_security;

        AVC_AUDIT_DATA_INIT(&ad, FS);
        ad.u.fs.path.dentry = dentry;

        av = DIR__SEARCH;
        av |= (kind ? DIR__REMOVE_NAME : DIR__ADD_NAME);
        rc = avc_has_perm(tsec->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(tsec->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 task_security_struct *tsec;
        struct inode_security_struct *old_dsec, *new_dsec, *old_isec, *new_isec;
        struct avc_audit_data ad;
        u32 av;
        int old_is_dir, new_is_dir;
        int rc;

        tsec = current->security;
        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;

        AVC_AUDIT_DATA_INIT(&ad, FS);

        ad.u.fs.path.dentry = old_dentry;
        rc = avc_has_perm(tsec->sid, old_dsec->sid, SECCLASS_DIR,
                          DIR__REMOVE_NAME | DIR__SEARCH, &ad);
        if (rc)
                return rc;
        rc = avc_has_perm(tsec->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(tsec->sid, old_isec->sid,
                                  old_isec->sclass, DIR__REPARENT, &ad);
                if (rc)
                        return rc;
        }

        ad.u.fs.path.dentry = new_dentry;
        av = DIR__ADD_NAME | DIR__SEARCH;
        if (new_dentry->d_inode)
                av |= DIR__REMOVE_NAME;
        rc = avc_has_perm(tsec->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(tsec->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(struct task_struct *tsk,
                               struct super_block *sb,
                               u32 perms,
                               struct avc_audit_data *ad)
{
        struct task_security_struct *tsec;
        struct superblock_security_struct *sbsec;

        tsec = tsk->security;
        sbsec = sb->s_security;
        return avc_has_perm(tsec->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 ((mode & S_IFMT) != S_IFDIR) {
                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 file mask to an access vector and include the correct open
 * open permission.
 */
static inline u32 open_file_mask_to_av(int mode, int mask)
{
        u32 av = file_mask_to_av(mode, mask);

        if (selinux_policycap_openperm) {
                /*
                 * lnk files and socks do not really have an 'open'
                 */
                if (S_ISREG(mode))
                        av |= FILE__OPEN;
                else if (S_ISCHR(mode))
                        av |= CHR_FILE__OPEN;
                else if (S_ISBLK(mode))
                        av |= BLK_FILE__OPEN;
                else if (S_ISFIFO(mode))
                        av |= FIFO_FILE__OPEN;
                else if (S_ISDIR(mode))
                        av |= DIR__OPEN;
                else
                        printk(KERN_ERR "SELinux: WARNING: inside %s with "
                                "unknown mode:%x\n", __func__, mode);
        }
        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;
}

/* Hook functions begin here. */

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

        rc = secondary_ops->ptrace_may_access(child, mode);
        if (rc)
                return rc;

        if (mode == PTRACE_MODE_READ) {
                struct task_security_struct *tsec = current->security;
                struct task_security_struct *csec = child->security;
                return avc_has_perm(tsec->sid, csec->sid,
                                    SECCLASS_FILE, FILE__READ, NULL);
        }

        return task_has_perm(current, child, PROCESS__PTRACE);
}

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

        rc = secondary_ops->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 = task_has_perm(current, target, PROCESS__GETCAP);
        if (error)
                return error;

        return secondary_ops->capget(target, effective, inheritable, permitted);
}

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

        error = secondary_ops->capset_check(target, effective, inheritable, permitted);
        if (error)
                return error;

        return task_has_perm(current, target, PROCESS__SETCAP);
}

static void selinux_capset_set(struct task_struct *target, kernel_cap_t *effective,
                               kernel_cap_t *inheritable, kernel_cap_t *permitted)
{
        secondary_ops->capset_set(target, effective, inheritable, permitted);
}

static int selinux_capable(struct task_struct *tsk, int cap)
{
        int rc;

        rc = secondary_ops->capable(tsk, cap);
        if (rc)
                return rc;

        return task_has_capability(tsk, cap);
}

static int selinux_sysctl_get_sid(ctl_table *table, u16 tclass, u32 *sid)
{
        int buflen, rc;
        char *buffer, *path, *end;

        rc = -ENOMEM;
        buffer = (char *)__get_free_page(GFP_KERNEL);
        if (!buffer)
                goto out;

        buflen = PAGE_SIZE;
        end = buffer+buflen;
        *--end = '\0';
        buflen--;
        path = end-1;
        *path = '/';
        while (table) {
                const char *name = table->procname;
                size_t namelen = strlen(name);
                buflen -= namelen + 1;
                if (buflen < 0)
                        goto out_free;
                end -= namelen;
                memcpy(end, name, namelen);
                *--end = '/';
                path = end;
                table = table->parent;
        }
        buflen -= 4;
        if (buflen < 0)
                goto out_free;
        end -= 4;
        memcpy(end, "/sys", 4);
        path = end;
        rc = security_genfs_sid("proc", path, tclass, sid);
out_free:
        free_page((unsigned long)buffer);
out:
        return rc;
}

static int selinux_sysctl(ctl_table *table, int op)
{
        int error = 0;
        u32 av;
        struct task_security_struct *tsec;
        u32 tsid;
        int rc;

        rc = secondary_ops->sysctl(table, op);
        if (rc)
                return rc;

        tsec = current->security;

        rc = selinux_sysctl_get_sid(table, (op == 0001) ?
                                    SECCLASS_DIR : SECCLASS_FILE, &tsid);
        if (rc) {
                /* Default to the well-defined sysctl SID. */
                tsid = SECINITSID_SYSCTL;
        }

        /* The op values are "defined" in sysctl.c, thereby creating
         * a bad coupling between this module and sysctl.c */
        if (op == 001) {
                error = avc_has_perm(tsec->sid, tsid,
                                     SECCLASS_DIR, DIR__SEARCH, NULL);
        } else {
                av = 0;
                if (op & 004)
                        av |= FILE__READ;
                if (op & 002)
                        av |= FILE__WRITE;
                if (av)
                        error = avc_has_perm(tsec->sid, tsid,
                                             SECCLASS_FILE, av, NULL);
        }

        return error;
}

static int selinux_quotactl(int cmds, int type, int id, struct super_block *sb)
{
        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(current, sb, FILESYSTEM__QUOTAMOD,
                                         NULL);
                break;
        case Q_GETFMT:
        case Q_GETINFO:
        case Q_GETQUOTA:
                rc = superblock_has_perm(current, 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)
{
        return dentry_has_perm(current, NULL, dentry, FILE__QUOTAON);
}

static int selinux_syslog(int type)
{
        int rc;

        rc = secondary_ops->syslog(type);
        if (rc)
                return rc;

        switch (type) {
        case 3:         /* Read last kernel messages */
        case 10:        /* Return size of the log buffer */
                rc = task_has_system(current, SYSTEM__SYSLOG_READ);
                break;
        case 6:         /* Disable logging to console */
        case 7:         /* Enable logging to console */
        case 8:         /* Set level of messages printed to console */
                rc = task_has_system(current, SYSTEM__SYSLOG_CONSOLE);
                break;
        case 0:         /* Close log */
        case 1:         /* Open log */
        case 2:         /* Read from log */
        case 4:         /* Read/clear last kernel messages */
        case 5:         /* 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.
 *
 * Note that secondary_ops->capable and task_has_perm_noaudit return 0
 * if the capability is granted, but __vm_enough_memory requires 1 if
 * the capability is granted.
 *
 * 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;
        struct task_security_struct *tsec = current->security;

        rc = secondary_ops->capable(current, CAP_SYS_ADMIN);
        if (rc == 0)
                rc = avc_has_perm_noaudit(tsec->sid, tsec->sid,
                                          SECCLASS_CAPABILITY,
                                          CAP_TO_MASK(CAP_SYS_ADMIN),
                                          0,
                                          NULL);

        if (rc == 0)
                cap_sys_admin = 1;

        return __vm_enough_memory(mm, pages, cap_sys_admin);
}

/* binprm security operations */

static int selinux_bprm_alloc_security(struct linux_binprm *bprm)
{
        struct bprm_security_struct *bsec;

        bsec = kzalloc(sizeof(struct bprm_security_struct), GFP_KERNEL);
        if (!bsec)
                return -ENOMEM;