namei: simplify the callers of follow_managed()

[karo-tx-linux.git] / fs / namei.c

/*
 *  linux/fs/namei.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

/*
 * Some corrections by tytso.
 */

/* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname
 * lookup logic.
 */
/* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture.
 */

#include <linux/init.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/fsnotify.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/ima.h>
#include <linux/syscalls.h>
#include <linux/mount.h>
#include <linux/audit.h>
#include <linux/capability.h>
#include <linux/file.h>
#include <linux/fcntl.h>
#include <linux/device_cgroup.h>
#include <linux/fs_struct.h>
#include <linux/posix_acl.h>
#include <linux/hash.h>
#include <asm/uaccess.h>

#include "internal.h"
#include "mount.h"

/* [Feb-1997 T. Schoebel-Theuer]
 * Fundamental changes in the pathname lookup mechanisms (namei)
 * were necessary because of omirr.  The reason is that omirr needs
 * to know the _real_ pathname, not the user-supplied one, in case
 * of symlinks (and also when transname replacements occur).
 *
 * The new code replaces the old recursive symlink resolution with
 * an iterative one (in case of non-nested symlink chains).  It does
 * this with calls to <fs>_follow_link().
 * As a side effect, dir_namei(), _namei() and follow_link() are now 
 * replaced with a single function lookup_dentry() that can handle all 
 * the special cases of the former code.
 *
 * With the new dcache, the pathname is stored at each inode, at least as
 * long as the refcount of the inode is positive.  As a side effect, the
 * size of the dcache depends on the inode cache and thus is dynamic.
 *
 * [29-Apr-1998 C. Scott Ananian] Updated above description of symlink
 * resolution to correspond with current state of the code.
 *
 * Note that the symlink resolution is not *completely* iterative.
 * There is still a significant amount of tail- and mid- recursion in
 * the algorithm.  Also, note that <fs>_readlink() is not used in
 * lookup_dentry(): lookup_dentry() on the result of <fs>_readlink()
 * may return different results than <fs>_follow_link().  Many virtual
 * filesystems (including /proc) exhibit this behavior.
 */

/* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation:
 * New symlink semantics: when open() is called with flags O_CREAT | O_EXCL
 * and the name already exists in form of a symlink, try to create the new
 * name indicated by the symlink. The old code always complained that the
 * name already exists, due to not following the symlink even if its target
 * is nonexistent.  The new semantics affects also mknod() and link() when
 * the name is a symlink pointing to a non-existent name.
 *
 * I don't know which semantics is the right one, since I have no access
 * to standards. But I found by trial that HP-UX 9.0 has the full "new"
 * semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the
 * "old" one. Personally, I think the new semantics is much more logical.
 * Note that "ln old new" where "new" is a symlink pointing to a non-existing
 * file does succeed in both HP-UX and SunOs, but not in Solaris
 * and in the old Linux semantics.
 */

/* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink
 * semantics.  See the comments in "open_namei" and "do_link" below.
 *
 * [10-Sep-98 Alan Modra] Another symlink change.
 */

/* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks:
 *      inside the path - always follow.
 *      in the last component in creation/removal/renaming - never follow.
 *      if LOOKUP_FOLLOW passed - follow.
 *      if the pathname has trailing slashes - follow.
 *      otherwise - don't follow.
 * (applied in that order).
 *
 * [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT
 * restored for 2.4. This is the last surviving part of old 4.2BSD bug.
 * During the 2.4 we need to fix the userland stuff depending on it -
 * hopefully we will be able to get rid of that wart in 2.5. So far only
 * XEmacs seems to be relying on it...
 */
/*
 * [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland)
 * implemented.  Let's see if raised priority of ->s_vfs_rename_mutex gives
 * any extra contention...
 */

/* In order to reduce some races, while at the same time doing additional
 * checking and hopefully speeding things up, we copy filenames to the
 * kernel data space before using them..
 *
 * POSIX.1 2.4: an empty pathname is invalid (ENOENT).
 * PATH_MAX includes the nul terminator --RR.
 */

#define EMBEDDED_NAME_MAX       (PATH_MAX - offsetof(struct filename, iname))

struct filename *
getname_flags(const char __user *filename, int flags, int *empty)
{
        struct filename *result;
        char *kname;
        int len;

        result = audit_reusename(filename);
        if (result)
                return result;

        result = __getname();
        if (unlikely(!result))
                return ERR_PTR(-ENOMEM);

        /*
         * First, try to embed the struct filename inside the names_cache
         * allocation
         */
        kname = (char *)result->iname;
        result->name = kname;

        len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX);
        if (unlikely(len < 0)) {
                __putname(result);
                return ERR_PTR(len);
        }

        /*
         * Uh-oh. We have a name that's approaching PATH_MAX. Allocate a
         * separate struct filename so we can dedicate the entire
         * names_cache allocation for the pathname, and re-do the copy from
         * userland.
         */
        if (unlikely(len == EMBEDDED_NAME_MAX)) {
                const size_t size = offsetof(struct filename, iname[1]);
                kname = (char *)result;

                /*
                 * size is chosen that way we to guarantee that
                 * result->iname[0] is within the same object and that
                 * kname can't be equal to result->iname, no matter what.
                 */
                result = kzalloc(size, GFP_KERNEL);
                if (unlikely(!result)) {
                        __putname(kname);
                        return ERR_PTR(-ENOMEM);
                }
                result->name = kname;
                len = strncpy_from_user(kname, filename, PATH_MAX);
                if (unlikely(len < 0)) {
                        __putname(kname);
                        kfree(result);
                        return ERR_PTR(len);
                }
                if (unlikely(len == PATH_MAX)) {
                        __putname(kname);
                        kfree(result);
                        return ERR_PTR(-ENAMETOOLONG);
                }
        }

        result->refcnt = 1;
        /* The empty path is special. */
        if (unlikely(!len)) {
                if (empty)
                        *empty = 1;
                if (!(flags & LOOKUP_EMPTY)) {
                        putname(result);
                        return ERR_PTR(-ENOENT);
                }
        }

        result->uptr = filename;
        result->aname = NULL;
        audit_getname(result);
        return result;
}

struct filename *
getname(const char __user * filename)
{
        return getname_flags(filename, 0, NULL);
}

struct filename *
getname_kernel(const char * filename)
{
        struct filename *result;
        int len = strlen(filename) + 1;

        result = __getname();
        if (unlikely(!result))
                return ERR_PTR(-ENOMEM);

        if (len <= EMBEDDED_NAME_MAX) {
                result->name = (char *)result->iname;
        } else if (len <= PATH_MAX) {
                struct filename *tmp;

                tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
                if (unlikely(!tmp)) {
                        __putname(result);
                        return ERR_PTR(-ENOMEM);
                }
                tmp->name = (char *)result;
                result = tmp;
        } else {
                __putname(result);
                return ERR_PTR(-ENAMETOOLONG);
        }
        memcpy((char *)result->name, filename, len);
        result->uptr = NULL;
        result->aname = NULL;
        result->refcnt = 1;
        audit_getname(result);

        return result;
}

void putname(struct filename *name)
{
        BUG_ON(name->refcnt <= 0);

        if (--name->refcnt > 0)
                return;

        if (name->name != name->iname) {
                __putname(name->name);
                kfree(name);
        } else
                __putname(name);
}

static int check_acl(struct inode *inode, int mask)
{
#ifdef CONFIG_FS_POSIX_ACL
        struct posix_acl *acl;

        if (mask & MAY_NOT_BLOCK) {
                acl = get_cached_acl_rcu(inode, ACL_TYPE_ACCESS);
                if (!acl)
                        return -EAGAIN;
                /* no ->get_acl() calls in RCU mode... */
                if (acl == ACL_NOT_CACHED)
                        return -ECHILD;
                return posix_acl_permission(inode, acl, mask & ~MAY_NOT_BLOCK);
        }

        acl = get_acl(inode, ACL_TYPE_ACCESS);
        if (IS_ERR(acl))
                return PTR_ERR(acl);
        if (acl) {
                int error = posix_acl_permission(inode, acl, mask);
                posix_acl_release(acl);
                return error;
        }
#endif

        return -EAGAIN;
}

/*
 * This does the basic permission checking
 */
static int acl_permission_check(struct inode *inode, int mask)
{
        unsigned int mode = inode->i_mode;

        if (likely(uid_eq(current_fsuid(), inode->i_uid)))
                mode >>= 6;
        else {
                if (IS_POSIXACL(inode) && (mode & S_IRWXG)) {
                        int error = check_acl(inode, mask);
                        if (error != -EAGAIN)
                                return error;
                }

                if (in_group_p(inode->i_gid))
                        mode >>= 3;
        }

        /*
         * If the DACs are ok we don't need any capability check.
         */
        if ((mask & ~mode & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0)
                return 0;
        return -EACCES;
}

/**
 * generic_permission -  check for access rights on a Posix-like filesystem
 * @inode:      inode to check access rights for
 * @mask:       right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, ...)
 *
 * Used to check for read/write/execute permissions on a file.
 * We use "fsuid" for this, letting us set arbitrary permissions
 * for filesystem access without changing the "normal" uids which
 * are used for other things.
 *
 * generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk
 * request cannot be satisfied (eg. requires blocking or too much complexity).
 * It would then be called again in ref-walk mode.
 */
int generic_permission(struct inode *inode, int mask)
{
        int ret;

        /*
         * Do the basic permission checks.
         */
        ret = acl_permission_check(inode, mask);
        if (ret != -EACCES)
                return ret;

        if (S_ISDIR(inode->i_mode)) {
                /* DACs are overridable for directories */
                if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
                        return 0;
                if (!(mask & MAY_WRITE))
                        if (capable_wrt_inode_uidgid(inode,
                                                     CAP_DAC_READ_SEARCH))
                                return 0;
                return -EACCES;
        }
        /*
         * Read/write DACs are always overridable.
         * Executable DACs are overridable when there is
         * at least one exec bit set.
         */
        if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
                if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
                        return 0;

        /*
         * Searching includes executable on directories, else just read.
         */
        mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
        if (mask == MAY_READ)
                if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH))
                        return 0;

        return -EACCES;
}
EXPORT_SYMBOL(generic_permission);

/*
 * We _really_ want to just do "generic_permission()" without
 * even looking at the inode->i_op values. So we keep a cache
 * flag in inode->i_opflags, that says "this has not special
 * permission function, use the fast case".
 */
static inline int do_inode_permission(struct inode *inode, int mask)
{
        if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) {
                if (likely(inode->i_op->permission))
                        return inode->i_op->permission(inode, mask);

                /* This gets set once for the inode lifetime */
                spin_lock(&inode->i_lock);
                inode->i_opflags |= IOP_FASTPERM;
                spin_unlock(&inode->i_lock);
        }
        return generic_permission(inode, mask);
}

/**
 * __inode_permission - Check for access rights to a given inode
 * @inode: Inode to check permission on
 * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
 *
 * Check for read/write/execute permissions on an inode.
 *
 * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask.
 *
 * This does not check for a read-only file system.  You probably want
 * inode_permission().
 */
int __inode_permission(struct inode *inode, int mask)
{
        int retval;

        if (unlikely(mask & MAY_WRITE)) {
                /*
                 * Nobody gets write access to an immutable file.
                 */
                if (IS_IMMUTABLE(inode))
                        return -EACCES;
        }

        retval = do_inode_permission(inode, mask);
        if (retval)
                return retval;

        retval = devcgroup_inode_permission(inode, mask);
        if (retval)
                return retval;

        return security_inode_permission(inode, mask);
}
EXPORT_SYMBOL(__inode_permission);

/**
 * sb_permission - Check superblock-level permissions
 * @sb: Superblock of inode to check permission on
 * @inode: Inode to check permission on
 * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
 *
 * Separate out file-system wide checks from inode-specific permission checks.
 */
static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
{
        if (unlikely(mask & MAY_WRITE)) {
                umode_t mode = inode->i_mode;

                /* Nobody gets write access to a read-only fs. */
                if ((sb->s_flags & MS_RDONLY) &&
                    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
                        return -EROFS;
        }
        return 0;
}

/**
 * inode_permission - Check for access rights to a given inode
 * @inode: Inode to check permission on
 * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
 *
 * Check for read/write/execute permissions on an inode.  We use fs[ug]id for
 * this, letting us set arbitrary permissions for filesystem access without
 * changing the "normal" UIDs which are used for other things.
 *
 * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask.
 */
int inode_permission(struct inode *inode, int mask)
{
        int retval;

        retval = sb_permission(inode->i_sb, inode, mask);
        if (retval)
                return retval;
        return __inode_permission(inode, mask);
}
EXPORT_SYMBOL(inode_permission);

/**
 * path_get - get a reference to a path
 * @path: path to get the reference to
 *
 * Given a path increment the reference count to the dentry and the vfsmount.
 */
void path_get(const struct path *path)
{
        mntget(path->mnt);
        dget(path->dentry);
}
EXPORT_SYMBOL(path_get);

/**
 * path_put - put a reference to a path
 * @path: path to put the reference to
 *
 * Given a path decrement the reference count to the dentry and the vfsmount.
 */
void path_put(const struct path *path)
{
        dput(path->dentry);
        mntput(path->mnt);
}
EXPORT_SYMBOL(path_put);

#define EMBEDDED_LEVELS 2
struct nameidata {
        struct path     path;
        union {
                struct qstr     last;
                struct path     link;
        };
        struct path     root;
        struct inode    *inode; /* path.dentry.d_inode */
        unsigned int    flags;
        unsigned        seq, m_seq;
        int             last_type;
        unsigned        depth;
        int             total_link_count;
        struct file     *base;
        struct saved {
                struct path link;
                void *cookie;
                const char *name;
        } *stack, internal[EMBEDDED_LEVELS];
};

static struct nameidata *set_nameidata(struct nameidata *p)
{
        struct nameidata *old = current->nameidata;
        p->stack = p->internal;
        p->total_link_count = old ? old->total_link_count : 0;
        current->nameidata = p;
        return old;
}

static void restore_nameidata(struct nameidata *old)
{
        struct nameidata *now = current->nameidata;

        current->nameidata = old;
        if (old)
                old->total_link_count = now->total_link_count;
        if (now->stack != now->internal) {
                kfree(now->stack);
                now->stack = now->internal;
        }
}

static int __nd_alloc_stack(struct nameidata *nd)
{
        struct saved *p = kmalloc(MAXSYMLINKS * sizeof(struct saved),
                                  GFP_KERNEL);
        if (unlikely(!p))
                return -ENOMEM;
        memcpy(p, nd->internal, sizeof(nd->internal));
        nd->stack = p;
        return 0;
}

static inline int nd_alloc_stack(struct nameidata *nd)
{
        if (likely(nd->depth != EMBEDDED_LEVELS))
                return 0;
        if (likely(nd->stack != nd->internal))
                return 0;
        return __nd_alloc_stack(nd);
}

/*
 * Path walking has 2 modes, rcu-walk and ref-walk (see
 * Documentation/filesystems/path-lookup.txt).  In situations when we can't
 * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab
 * normal reference counts on dentries and vfsmounts to transition to rcu-walk
 * mode.  Refcounts are grabbed at the last known good point before rcu-walk
 * got stuck, so ref-walk may continue from there. If this is not successful
 * (eg. a seqcount has changed), then failure is returned and it's up to caller
 * to restart the path walk from the beginning in ref-walk mode.
 */

/**
 * unlazy_walk - try to switch to ref-walk mode.
 * @nd: nameidata pathwalk data
 * @dentry: child of nd->path.dentry or NULL
 * Returns: 0 on success, -ECHILD on failure
 *
 * unlazy_walk attempts to legitimize the current nd->path, nd->root and dentry
 * for ref-walk mode.  @dentry must be a path found by a do_lookup call on
 * @nd or NULL.  Must be called from rcu-walk context.
 */
static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
{
        struct fs_struct *fs = current->fs;
        struct dentry *parent = nd->path.dentry;

        BUG_ON(!(nd->flags & LOOKUP_RCU));

        /*
         * After legitimizing the bastards, terminate_walk()
         * will do the right thing for non-RCU mode, and all our
         * subsequent exit cases should rcu_read_unlock()
         * before returning.  Do vfsmount first; if dentry
         * can't be legitimized, just set nd->path.dentry to NULL
         * and rely on dput(NULL) being a no-op.
         */
        if (!legitimize_mnt(nd->path.mnt, nd->m_seq))
                return -ECHILD;
        nd->flags &= ~LOOKUP_RCU;

        if (!lockref_get_not_dead(&parent->d_lockref)) {
                nd->path.dentry = NULL; 
                goto out;
        }

        /*
         * For a negative lookup, the lookup sequence point is the parents
         * sequence point, and it only needs to revalidate the parent dentry.
         *
         * For a positive lookup, we need to move both the parent and the
         * dentry from the RCU domain to be properly refcounted. And the
         * sequence number in the dentry validates *both* dentry counters,
         * since we checked the sequence number of the parent after we got
         * the child sequence number. So we know the parent must still
         * be valid if the child sequence number is still valid.
         */
        if (!dentry) {
                if (read_seqcount_retry(&parent->d_seq, nd->seq))
                        goto out;
                BUG_ON(nd->inode != parent->d_inode);
        } else {
                if (!lockref_get_not_dead(&dentry->d_lockref))
                        goto out;
                if (read_seqcount_retry(&dentry->d_seq, nd->seq))
                        goto drop_dentry;
        }

        /*
         * Sequence counts matched. Now make sure that the root is
         * still valid and get it if required.
         */
        if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
                spin_lock(&fs->lock);
                if (nd->root.mnt != fs->root.mnt || nd->root.dentry != fs->root.dentry)
                        goto unlock_and_drop_dentry;
                path_get(&nd->root);
                spin_unlock(&fs->lock);
        }

        rcu_read_unlock();
        return 0;

unlock_and_drop_dentry:
        spin_unlock(&fs->lock);
drop_dentry:
        rcu_read_unlock();
        dput(dentry);
        goto drop_root_mnt;
out:
        rcu_read_unlock();
drop_root_mnt:
        if (!(nd->flags & LOOKUP_ROOT))
                nd->root.mnt = NULL;
        return -ECHILD;
}

static inline int d_revalidate(struct dentry *dentry, unsigned int flags)
{
        return dentry->d_op->d_revalidate(dentry, flags);
}

/**
 * complete_walk - successful completion of path walk
 * @nd:  pointer nameidata
 *
 * If we had been in RCU mode, drop out of it and legitimize nd->path.
 * Revalidate the final result, unless we'd already done that during
 * the path walk or the filesystem doesn't ask for it.  Return 0 on
 * success, -error on failure.  In case of failure caller does not
 * need to drop nd->path.
 */
static int complete_walk(struct nameidata *nd)
{
        struct dentry *dentry = nd->path.dentry;
        int status;

        if (nd->flags & LOOKUP_RCU) {
                nd->flags &= ~LOOKUP_RCU;
                if (!(nd->flags & LOOKUP_ROOT))
                        nd->root.mnt = NULL;

                if (!legitimize_mnt(nd->path.mnt, nd->m_seq)) {
                        rcu_read_unlock();
                        return -ECHILD;
                }
                if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) {
                        rcu_read_unlock();
                        mntput(nd->path.mnt);
                        return -ECHILD;
                }
                if (read_seqcount_retry(&dentry->d_seq, nd->seq)) {
                        rcu_read_unlock();
                        dput(dentry);
                        mntput(nd->path.mnt);
                        return -ECHILD;
                }
                rcu_read_unlock();
        }

        if (likely(!(nd->flags & LOOKUP_JUMPED)))
                return 0;

        if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE)))
                return 0;

        status = dentry->d_op->d_weak_revalidate(dentry, nd->flags);
        if (status > 0)
                return 0;

        if (!status)
                status = -ESTALE;

        path_put(&nd->path);
        return status;
}

static __always_inline void set_root(struct nameidata *nd)
{
        get_fs_root(current->fs, &nd->root);
}

static __always_inline unsigned set_root_rcu(struct nameidata *nd)
{
        struct fs_struct *fs = current->fs;
        unsigned seq, res;

        do {
                seq = read_seqcount_begin(&fs->seq);
                nd->root = fs->root;
                res = __read_seqcount_begin(&nd->root.dentry->d_seq);
        } while (read_seqcount_retry(&fs->seq, seq));
        return res;
}

static void path_put_conditional(struct path *path, struct nameidata *nd)
{
        dput(path->dentry);
        if (path->mnt != nd->path.mnt)
                mntput(path->mnt);
}

static inline void path_to_nameidata(const struct path *path,
                                        struct nameidata *nd)
{
        if (!(nd->flags & LOOKUP_RCU)) {
                dput(nd->path.dentry);
                if (nd->path.mnt != path->mnt)
                        mntput(nd->path.mnt);
        }
        nd->path.mnt = path->mnt;
        nd->path.dentry = path->dentry;
}

/*
 * Helper to directly jump to a known parsed path from ->follow_link,
 * caller must have taken a reference to path beforehand.
 */
void nd_jump_link(struct nameidata *nd, struct path *path)
{
        path_put(&nd->path);

        nd->path = *path;
        nd->inode = nd->path.dentry->d_inode;
        nd->flags |= LOOKUP_JUMPED;
}

static inline void put_link(struct nameidata *nd)
{
        struct saved *last = nd->stack + --nd->depth;
        struct inode *inode = last->link.dentry->d_inode;
        if (last->cookie && inode->i_op->put_link)
                inode->i_op->put_link(last->link.dentry, last->cookie);
        path_put(&last->link);
}

int sysctl_protected_symlinks __read_mostly = 0;
int sysctl_protected_hardlinks __read_mostly = 0;

/**
 * may_follow_link - Check symlink following for unsafe situations
 * @link: The path of the symlink
 * @nd: nameidata pathwalk data
 *
 * In the case of the sysctl_protected_symlinks sysctl being enabled,
 * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is
 * in a sticky world-writable directory. This is to protect privileged
 * processes from failing races against path names that may change out
 * from under them by way of other users creating malicious symlinks.
 * It will permit symlinks to be followed only when outside a sticky
 * world-writable directory, or when the uid of the symlink and follower
 * match, or when the directory owner matches the symlink's owner.
 *
 * Returns 0 if following the symlink is allowed, -ve on error.
 */
static inline int may_follow_link(struct path *link, struct nameidata *nd)
{
        const struct inode *inode;
        const struct inode *parent;

        if (!sysctl_protected_symlinks)
                return 0;

        /* Allowed if owner and follower match. */
        inode = link->dentry->d_inode;
        if (uid_eq(current_cred()->fsuid, inode->i_uid))
                return 0;

        /* Allowed if parent directory not sticky and world-writable. */
        parent = nd->path.dentry->d_inode;
        if ((parent->i_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH))
                return 0;

        /* Allowed if parent directory and link owner match. */
        if (uid_eq(parent->i_uid, inode->i_uid))
                return 0;

        audit_log_link_denied("follow_link", link);
        path_put_conditional(link, nd);
        path_put(&nd->path);
        return -EACCES;
}

/**
 * safe_hardlink_source - Check for safe hardlink conditions
 * @inode: the source inode to hardlink from
 *
 * Return false if at least one of the following conditions:
 *    - inode is not a regular file
 *    - inode is setuid
 *    - inode is setgid and group-exec
 *    - access failure for read and write
 *
 * Otherwise returns true.
 */
static bool safe_hardlink_source(struct inode *inode)
{
        umode_t mode = inode->i_mode;

        /* Special files should not get pinned to the filesystem. */
        if (!S_ISREG(mode))
                return false;

        /* Setuid files should not get pinned to the filesystem. */
        if (mode & S_ISUID)
                return false;

        /* Executable setgid files should not get pinned to the filesystem. */
        if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP))
                return false;

        /* Hardlinking to unreadable or unwritable sources is dangerous. */
        if (inode_permission(inode, MAY_READ | MAY_WRITE))
                return false;

        return true;
}

/**
 * may_linkat - Check permissions for creating a hardlink
 * @link: the source to hardlink from
 *
 * Block hardlink when all of:
 *  - sysctl_protected_hardlinks enabled
 *  - fsuid does not match inode
 *  - hardlink source is unsafe (see safe_hardlink_source() above)
 *  - not CAP_FOWNER
 *
 * Returns 0 if successful, -ve on error.
 */
static int may_linkat(struct path *link)
{
        const struct cred *cred;
        struct inode *inode;

        if (!sysctl_protected_hardlinks)
                return 0;

        cred = current_cred();
        inode = link->dentry->d_inode;

        /* Source inode owner (or CAP_FOWNER) can hardlink all they like,
         * otherwise, it must be a safe source.
         */
        if (uid_eq(cred->fsuid, inode->i_uid) || safe_hardlink_source(inode) ||
            capable(CAP_FOWNER))
                return 0;

        audit_log_link_denied("linkat", link);
        return -EPERM;
}

static __always_inline
const char *get_link(struct nameidata *nd)
{
        struct saved *last = nd->stack + nd->depth;
        struct dentry *dentry = nd->link.dentry;
        struct inode *inode = dentry->d_inode;
        int error;
        const char *res;

        BUG_ON(nd->flags & LOOKUP_RCU);

        if (nd->link.mnt == nd->path.mnt)
                mntget(nd->link.mnt);

        last->link = nd->link;
        last->cookie = NULL;

        cond_resched();

        touch_atime(&last->link);

        error = security_inode_follow_link(dentry);
        res = ERR_PTR(error);
        if (error)
                goto out;

        nd->last_type = LAST_BIND;
        res = inode->i_link;
        if (!res) {
                res = inode->i_op->follow_link(dentry, &last->cookie, nd);
                if (IS_ERR(res)) {
out:
                        path_put(&last->link);
                        return res;
                }
        }
        nd->depth++;
        return res;
}

static int follow_up_rcu(struct path *path)
{
        struct mount *mnt = real_mount(path->mnt);
        struct mount *parent;
        struct dentry *mountpoint;

        parent = mnt->mnt_parent;
        if (&parent->mnt == path->mnt)
                return 0;
        mountpoint = mnt->mnt_mountpoint;
        path->dentry = mountpoint;
        path->mnt = &parent->mnt;
        return 1;
}

/*
 * follow_up - Find the mountpoint of path's vfsmount
 *
 * Given a path, find the mountpoint of its source file system.
 * Replace @path with the path of the mountpoint in the parent mount.
 * Up is towards /.
 *
 * Return 1 if we went up a level and 0 if we were already at the
 * root.
 */
int follow_up(struct path *path)
{
        struct mount *mnt = real_mount(path->mnt);
        struct mount *parent;
        struct dentry *mountpoint;

        read_seqlock_excl(&mount_lock);
        parent = mnt->mnt_parent;
        if (parent == mnt) {
                read_sequnlock_excl(&mount_lock);
                return 0;
        }
        mntget(&parent->mnt);
        mountpoint = dget(mnt->mnt_mountpoint);
        read_sequnlock_excl(&mount_lock);
        dput(path->dentry);
        path->dentry = mountpoint;
        mntput(path->mnt);
        path->mnt = &parent->mnt;
        return 1;
}
EXPORT_SYMBOL(follow_up);

/*
 * Perform an automount
 * - return -EISDIR to tell follow_managed() to stop and return the path we
 *   were called with.
 */
static int follow_automount(struct path *path, struct nameidata *nd,
                            bool *need_mntput)
{
        struct vfsmount *mnt;
        int err;

        if (!path->dentry->d_op || !path->dentry->d_op->d_automount)
                return -EREMOTE;

        /* We don't want to mount if someone's just doing a stat -
         * unless they're stat'ing a directory and appended a '/' to
         * the name.
         *
         * We do, however, want to mount if someone wants to open or
         * create a file of any type under the mountpoint, wants to
         * traverse through the mountpoint or wants to open the
         * mounted directory.  Also, autofs may mark negative dentries
         * as being automount points.  These will need the attentions
         * of the daemon to instantiate them before they can be used.
         */
        if (!(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
                           LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
            path->dentry->d_inode)
                return -EISDIR;

        nd->total_link_count++;
        if (nd->total_link_count >= 40)
                return -ELOOP;

        mnt = path->dentry->d_op->d_automount(path);
        if (IS_ERR(mnt)) {
                /*
                 * The filesystem is allowed to return -EISDIR here to indicate
                 * it doesn't want to automount.  For instance, autofs would do
                 * this so that its userspace daemon can mount on this dentry.
                 *
                 * However, we can only permit this if it's a terminal point in
                 * the path being looked up; if it wasn't then the remainder of
                 * the path is inaccessible and we should say so.
                 */
                if (PTR_ERR(mnt) == -EISDIR && (nd->flags & LOOKUP_PARENT))
                        return -EREMOTE;
                return PTR_ERR(mnt);
        }

        if (!mnt) /* mount collision */
                return 0;

        if (!*need_mntput) {
                /* lock_mount() may release path->mnt on error */
                mntget(path->mnt);
                *need_mntput = true;
        }
        err = finish_automount(mnt, path);

        switch (err) {
        case -EBUSY:
                /* Someone else made a mount here whilst we were busy */
                return 0;
        case 0:
                path_put(path);
                path->mnt = mnt;
                path->dentry = dget(mnt->mnt_root);
                return 0;
        default:
                return err;
        }

}

/*
 * Handle a dentry that is managed in some way.
 * - Flagged for transit management (autofs)
 * - Flagged as mountpoint
 * - Flagged as automount point
 *
 * This may only be called in refwalk mode.
 *
 * Serialization is taken care of in namespace.c
 */
static int follow_managed(struct path *path, struct nameidata *nd)
{
        struct vfsmount *mnt = path->mnt; /* held by caller, must be left alone */
        unsigned managed;
        bool need_mntput = false;
        int ret = 0;

        /* Given that we're not holding a lock here, we retain the value in a
         * local variable for each dentry as we look at it so that we don't see
         * the components of that value change under us */
        while (managed = ACCESS_ONCE(path->dentry->d_flags),
               managed &= DCACHE_MANAGED_DENTRY,
               unlikely(managed != 0)) {
                /* Allow the filesystem to manage the transit without i_mutex
                 * being held. */
                if (managed & DCACHE_MANAGE_TRANSIT) {
                        BUG_ON(!path->dentry->d_op);
                        BUG_ON(!path->dentry->d_op->d_manage);
                        ret = path->dentry->d_op->d_manage(path->dentry, false);
                        if (ret < 0)
                                break;
                }

                /* Transit to a mounted filesystem. */
                if (managed & DCACHE_MOUNTED) {
                        struct vfsmount *mounted = lookup_mnt(path);
                        if (mounted) {
                                dput(path->dentry);
                                if (need_mntput)
                                        mntput(path->mnt);
                                path->mnt = mounted;
                                path->dentry = dget(mounted->mnt_root);
                                need_mntput = true;
                                continue;
                        }

                        /* Something is mounted on this dentry in another
                         * namespace and/or whatever was mounted there in this
                         * namespace got unmounted before lookup_mnt() could
                         * get it */
                }

                /* Handle an automount point */
                if (managed & DCACHE_NEED_AUTOMOUNT) {
                        ret = follow_automount(path, nd, &need_mntput);
                        if (ret < 0)
                                break;
                        continue;
                }

                /* We didn't change the current path point */
                break;
        }

        if (need_mntput && path->mnt == mnt)
                mntput(path->mnt);
        if (ret == -EISDIR)
                ret = 0;
        if (need_mntput)
                nd->flags |= LOOKUP_JUMPED;
        if (unlikely(ret < 0))
                path_put_conditional(path, nd);
        return ret;
}

int follow_down_one(struct path *path)
{
        struct vfsmount *mounted;

        mounted = lookup_mnt(path);
        if (mounted) {
                dput(path->dentry);
                mntput(path->mnt);
                path->mnt = mounted;
                path->dentry = dget(mounted->mnt_root);
                return 1;
        }
        return 0;
}
EXPORT_SYMBOL(follow_down_one);

static inline int managed_dentry_rcu(struct dentry *dentry)
{
        return (dentry->d_flags & DCACHE_MANAGE_TRANSIT) ?
                dentry->d_op->d_manage(dentry, true) : 0;
}

/*
 * Try to skip to top of mountpoint pile in rcuwalk mode.  Fail if
 * we meet a managed dentry that would need blocking.
 */
static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
                               struct inode **inode)
{
        for (;;) {
                struct mount *mounted;
                /*
                 * Don't forget we might have a non-mountpoint managed dentry
                 * that wants to block transit.
                 */
                switch (managed_dentry_rcu(path->dentry)) {
                case -ECHILD:
                default:
                        return false;
                case -EISDIR:
                        return true;
                case 0:
                        break;
                }

                if (!d_mountpoint(path->dentry))
                        return !(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT);

                mounted = __lookup_mnt(path->mnt, path->dentry);
                if (!mounted)
                        break;
                path->mnt = &mounted->mnt;
                path->dentry = mounted->mnt.mnt_root;
                nd->flags |= LOOKUP_JUMPED;
                nd->seq = read_seqcount_begin(&path->dentry->d_seq);
                /*
                 * Update the inode too. We don't need to re-check the
                 * dentry sequence number here after this d_inode read,
                 * because a mount-point is always pinned.
                 */
                *inode = path->dentry->d_inode;
        }
        return !read_seqretry(&mount_lock, nd->m_seq) &&
                !(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT);
}

static int follow_dotdot_rcu(struct nameidata *nd)
{
        struct inode *inode = nd->inode;
        if (!nd->root.mnt)
                set_root_rcu(nd);

        while (1) {
                if (nd->path.dentry == nd->root.dentry &&
                    nd->path.mnt == nd->root.mnt) {
                        break;
                }
                if (nd->path.dentry != nd->path.mnt->mnt_root) {
                        struct dentry *old = nd->path.dentry;
                        struct dentry *parent = old->d_parent;
                        unsigned seq;

                        inode = parent->d_inode;
                        seq = read_seqcount_begin(&parent->d_seq);
                        if (read_seqcount_retry(&old->d_seq, nd->seq))
                                goto failed;
                        nd->path.dentry = parent;
                        nd->seq = seq;
                        break;
                }
                if (!follow_up_rcu(&nd->path))
                        break;
                inode = nd->path.dentry->d_inode;
                nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
        }
        while (d_mountpoint(nd->path.dentry)) {
                struct mount *mounted;
                mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry);
                if (!mounted)
                        break;
                nd->path.mnt = &mounted->mnt;
                nd->path.dentry = mounted->mnt.mnt_root;
                inode = nd->path.dentry->d_inode;
                nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
                if (read_seqretry(&mount_lock, nd->m_seq))
                        goto failed;
        }
        nd->inode = inode;
        return 0;

failed:
        return -ECHILD;
}

/*
 * Follow down to the covering mount currently visible to userspace.  At each
 * point, the filesystem owning that dentry may be queried as to whether the
 * caller is permitted to proceed or not.
 */
int follow_down(struct path *path)
{
        unsigned managed;
        int ret;

        while (managed = ACCESS_ONCE(path->dentry->d_flags),
               unlikely(managed & DCACHE_MANAGED_DENTRY)) {
                /* Allow the filesystem to manage the transit without i_mutex
                 * being held.
                 *
                 * We indicate to the filesystem if someone is trying to mount
                 * something here.  This gives autofs the chance to deny anyone
                 * other than its daemon the right to mount on its
                 * superstructure.
                 *
                 * The filesystem may sleep at this point.
                 */
                if (managed & DCACHE_MANAGE_TRANSIT) {
                        BUG_ON(!path->dentry->d_op);
                        BUG_ON(!path->dentry->d_op->d_manage);
                        ret = path->dentry->d_op->d_manage(
                                path->dentry, false);
                        if (ret < 0)
                                return ret == -EISDIR ? 0 : ret;
                }

                /* Transit to a mounted filesystem. */
                if (managed & DCACHE_MOUNTED) {
                        struct vfsmount *mounted = lookup_mnt(path);
                        if (!mounted)
                                break;
                        dput(path->dentry);
                        mntput(path->mnt);
                        path->mnt = mounted;
                        path->dentry = dget(mounted->mnt_root);
                        continue;
                }

                /* Don't handle automount points here */
                break;
        }
        return 0;
}
EXPORT_SYMBOL(follow_down);

/*
 * Skip to top of mountpoint pile in refwalk mode for follow_dotdot()
 */
static void follow_mount(struct path *path)
{
        while (d_mountpoint(path->dentry)) {
                struct vfsmount *mounted = lookup_mnt(path);
                if (!mounted)
                        break;
                dput(path->dentry);
                mntput(path->mnt);
                path->mnt = mounted;
                path->dentry = dget(mounted->mnt_root);
        }
}

static void follow_dotdot(struct nameidata *nd)
{
        if (!nd->root.mnt)
                set_root(nd);

        while(1) {
                struct dentry *old = nd->path.dentry;

                if (nd->path.dentry == nd->root.dentry &&
                    nd->path.mnt == nd->root.mnt) {
                        break;
                }
                if (nd->path.dentry != nd->path.mnt->mnt_root) {
                        /* rare case of legitimate dget_parent()... */
                        nd->path.dentry = dget_parent(nd->path.dentry);
                        dput(old);
                        break;
                }
                if (!follow_up(&nd->path))
                        break;
        }
        follow_mount(&nd->path);
        nd->inode = nd->path.dentry->d_inode;
}

/*
 * This looks up the name in dcache, possibly revalidates the old dentry and
 * allocates a new one if not found or not valid.  In the need_lookup argument
 * returns whether i_op->lookup is necessary.
 *
 * dir->d_inode->i_mutex must be held
 */
static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir,
                                    unsigned int flags, bool *need_lookup)
{
        struct dentry *dentry;
        int error;

        *need_lookup = false;
        dentry = d_lookup(dir, name);
        if (dentry) {
                if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
                        error = d_revalidate(dentry, flags);
                        if (unlikely(error <= 0)) {
                                if (error < 0) {
                                        dput(dentry);
                                        return ERR_PTR(error);
                                } else {
                                        d_invalidate(dentry);
                                        dput(dentry);
                                        dentry = NULL;
                                }
                        }
                }
        }

        if (!dentry) {
                dentry = d_alloc(dir, name);
                if (unlikely(!dentry))
                        return ERR_PTR(-ENOMEM);

                *need_lookup = true;
        }
        return dentry;
}

/*
 * Call i_op->lookup on the dentry.  The dentry must be negative and
 * unhashed.
 *
 * dir->d_inode->i_mutex must be held
 */
static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry,
                                  unsigned int flags)
{
        struct dentry *old;

        /* Don't create child dentry for a dead directory. */
        if (unlikely(IS_DEADDIR(dir))) {
                dput(dentry);
                return ERR_PTR(-ENOENT);
        }

        old = dir->i_op->lookup(dir, dentry, flags);
        if (unlikely(old)) {
                dput(dentry);
                dentry = old;
        }
        return dentry;
}

static struct dentry *__lookup_hash(struct qstr *name,
                struct dentry *base, unsigned int flags)
{
        bool need_lookup;
        struct dentry *dentry;

        dentry = lookup_dcache(name, base, flags, &need_lookup);
        if (!need_lookup)
                return dentry;

        return lookup_real(base->d_inode, dentry, flags);
}

/*
 *  It's more convoluted than I'd like it to be, but... it's still fairly
 *  small and for now I'd prefer to have fast path as straight as possible.
 *  It _is_ time-critical.
 */
static int lookup_fast(struct nameidata *nd,
                       struct path *path, struct inode **inode)
{
        struct vfsmount *mnt = nd->path.mnt;
        struct dentry *dentry, *parent = nd->path.dentry;
        int need_reval = 1;
        int status = 1;
        int err;

        /*
         * Rename seqlock is not required here because in the off chance
         * of a false negative due to a concurrent rename, we're going to
         * do the non-racy lookup, below.
         */
        if (nd->flags & LOOKUP_RCU) {
                unsigned seq;
                bool negative;
                dentry = __d_lookup_rcu(parent, &nd->last, &seq);
                if (!dentry)
                        goto unlazy;

                /*
                 * This sequence count validates that the inode matches
                 * the dentry name information from lookup.
                 */
                *inode = dentry->d_inode;
                negative = d_is_negative(dentry);
                if (read_seqcount_retry(&dentry->d_seq, seq))
                        return -ECHILD;
                if (negative)
                        return -ENOENT;

                /*
                 * This sequence count validates that the parent had no
                 * changes while we did the lookup of the dentry above.
                 *
                 * The memory barrier in read_seqcount_begin of child is
                 *  enough, we can use __read_seqcount_retry here.
                 */
                if (__read_seqcount_retry(&parent->d_seq, nd->seq))
                        return -ECHILD;
                nd->seq = seq;

                if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
                        status = d_revalidate(dentry, nd->flags);
                        if (unlikely(status <= 0)) {
                                if (status != -ECHILD)
                                        need_reval = 0;
                                goto unlazy;
                        }
                }
                path->mnt = mnt;
                path->dentry = dentry;
                if (likely(__follow_mount_rcu(nd, path, inode)))
                        return 0;
unlazy:
                if (unlazy_walk(nd, dentry))
                        return -ECHILD;
        } else {
                dentry = __d_lookup(parent, &nd->last);
        }

        if (unlikely(!dentry))
                goto need_lookup;

        if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval)
                status = d_revalidate(dentry, nd->flags);
        if (unlikely(status <= 0)) {
                if (status < 0) {
                        dput(dentry);
                        return status;
                }
                d_invalidate(dentry);
                dput(dentry);
                goto need_lookup;
        }

        if (unlikely(d_is_negative(dentry))) {
                dput(dentry);
                return -ENOENT;
        }
        path->mnt = mnt;
        path->dentry = dentry;
        err = follow_managed(path, nd);
        if (likely(!err))
                *inode = path->dentry->d_inode;
        return err;

need_lookup:
        return 1;
}

/* Fast lookup failed, do it the slow way */
static int lookup_slow(struct nameidata *nd, struct path *path)
{
        struct dentry *dentry, *parent;

        parent = nd->path.dentry;
        BUG_ON(nd->inode != parent->d_inode);

        mutex_lock(&parent->d_inode->i_mutex);
        dentry = __lookup_hash(&nd->last, parent, nd->flags);
        mutex_unlock(&parent->d_inode->i_mutex);
        if (IS_ERR(dentry))
                return PTR_ERR(dentry);
        path->mnt = nd->path.mnt;
        path->dentry = dentry;
        return follow_managed(path, nd);
}

static inline int may_lookup(struct nameidata *nd)
{
        if (nd->flags & LOOKUP_RCU) {
                int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
                if (err != -ECHILD)
                        return err;
                if (unlazy_walk(nd, NULL))
                        return -ECHILD;
        }
        return inode_permission(nd->inode, MAY_EXEC);
}

static inline int handle_dots(struct nameidata *nd, int type)
{
        if (type == LAST_DOTDOT) {
                if (nd->flags & LOOKUP_RCU) {
                        return follow_dotdot_rcu(nd);
                } else
                        follow_dotdot(nd);
        }
        return 0;
}

static void terminate_walk(struct nameidata *nd)
{
        if (!(nd->flags & LOOKUP_RCU)) {
                path_put(&nd->path);
        } else {
                nd->flags &= ~LOOKUP_RCU;
                if (!(nd->flags & LOOKUP_ROOT))
                        nd->root.mnt = NULL;
                rcu_read_unlock();
        }
        while (unlikely(nd->depth))
                put_link(nd);
}

static int pick_link(struct nameidata *nd, struct path *link)
{
        int error;
        if (unlikely(nd->total_link_count++ >= MAXSYMLINKS)) {
                path_to_nameidata(link, nd);
                return -ELOOP;
        }
        if (nd->flags & LOOKUP_RCU) {
                if (unlikely(nd->path.mnt != link->mnt ||
                             unlazy_walk(nd, link->dentry))) {
                        return -ECHILD;
                }
        }
        error = nd_alloc_stack(nd);
        if (unlikely(error)) {
                path_to_nameidata(link, nd);
                return error;
        }

        nd->link = *link;
        return 1;
}

/*
 * Do we need to follow links? We _really_ want to be able
 * to do this check without having to look at inode->i_op,
 * so we keep a cache of "no, this doesn't need follow_link"
 * for the common case.
 */
static inline int should_follow_link(struct nameidata *nd, struct path *link, int follow)
{
        if (likely(!d_is_symlink(link->dentry)))
                return 0;
        if (!follow)
                return 0;
        return pick_link(nd, link);
}

enum {WALK_GET = 1, WALK_PUT = 2};

static int walk_component(struct nameidata *nd, int flags)
{
        struct path path;
        struct inode *inode;
        int err;
        /*
         * "." and ".." are special - ".." especially so because it has
         * to be able to know about the current root directory and
         * parent relationships.
         */
        if (unlikely(nd->last_type != LAST_NORM)) {
                err = handle_dots(nd, nd->last_type);
                if (flags & WALK_PUT)
                        put_link(nd);
                return err;
        }
        err = lookup_fast(nd, &path, &inode);
        if (unlikely(err)) {
                if (err < 0)
                        return err;

                err = lookup_slow(nd, &path);
                if (err < 0)
                        return err;

                inode = path.dentry->d_inode;
                err = -ENOENT;
                if (d_is_negative(path.dentry))
                        goto out_path_put;
        }

        if (flags & WALK_PUT)
                put_link(nd);
        err = should_follow_link(nd, &path, flags & WALK_GET);
        if (unlikely(err))
                return err;
        path_to_nameidata(&path, nd);
        nd->inode = inode;
        return 0;

out_path_put:
        path_to_nameidata(&path, nd);
        return err;
}

/*
 * We can do the critical dentry name comparison and hashing
 * operations one word at a time, but we are limited to:
 *
 * - Architectures with fast unaligned word accesses. We could
 *   do a "get_unaligned()" if this helps and is sufficiently
 *   fast.
 *
 * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we
 *   do not trap on the (extremely unlikely) case of a page
 *   crossing operation.
 *
 * - Furthermore, we need an efficient 64-bit compile for the
 *   64-bit case in order to generate the "number of bytes in
 *   the final mask". Again, that could be replaced with a
 *   efficient population count instruction or similar.
 */
#ifdef CONFIG_DCACHE_WORD_ACCESS

#include <asm/word-at-a-time.h>

#ifdef CONFIG_64BIT

static inline unsigned int fold_hash(unsigned long hash)
{
        return hash_64(hash, 32);
}

#else   /* 32-bit case */

#define fold_hash(x) (x)

#endif

unsigned int full_name_hash(const unsigned char *name, unsigned int len)
{
        unsigned long a, mask;
        unsigned long hash = 0;

        for (;;) {
                a = load_unaligned_zeropad(name);
                if (len < sizeof(unsigned long))
                        break;
                hash += a;
                hash *= 9;
                name += sizeof(unsigned long);
                len -= sizeof(unsigned long);
                if (!len)
                        goto done;
        }
        mask = bytemask_from_count(len);
        hash += mask & a;
done:
        return fold_hash(hash);
}
EXPORT_SYMBOL(full_name_hash);

/*
 * Calculate the length and hash of the path component, and
 * return the "hash_len" as the result.
 */
static inline u64 hash_name(const char *name)
{
        unsigned long a, b, adata, bdata, mask, hash, len;
        const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;

        hash = a = 0;
        len = -sizeof(unsigned long);
        do {
                hash = (hash + a) * 9;
                len += sizeof(unsigned long);
                a = load_unaligned_zeropad(name+len);
                b = a ^ REPEAT_BYTE('/');
        } while (!(has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants)));

        adata = prep_zero_mask(a, adata, &constants);
        bdata = prep_zero_mask(b, bdata, &constants);

        mask = create_zero_mask(adata | bdata);

        hash += a & zero_bytemask(mask);
        len += find_zero(mask);
        return hashlen_create(fold_hash(hash), len);
}

#else

unsigned int full_name_hash(const unsigned char *name, unsigned int len)
{
        unsigned long hash = init_name_hash();
        while (len--)
                hash = partial_name_hash(*name++, hash);
        return end_name_hash(hash);
}
EXPORT_SYMBOL(full_name_hash);

/*
 * We know there's a real path component here of at least
 * one character.
 */
static inline u64 hash_name(const char *name)
{
        unsigned long hash = init_name_hash();
        unsigned long len = 0, c;

        c = (unsigned char)*name;
        do {
                len++;
                hash = partial_name_hash(c, hash);
                c = (unsigned char)name[len];
        } while (c && c != '/');
        return hashlen_create(end_name_hash(hash), len);
}

#endif

/*
 * Name resolution.
 * This is the basic name resolution function, turning a pathname into
 * the final dentry. We expect 'base' to be positive and a directory.
 *
 * Returns 0 and nd will have valid dentry and mnt on success.
 * Returns error and drops reference to input namei data on failure.
 */
static int link_path_walk(const char *name, struct nameidata *nd)
{
        int err;

        while (*name=='/')
                name++;
        if (!*name)
                return 0;

        /* At this point we know we have a real path component. */
        for(;;) {
                u64 hash_len;
                int type;

                err = may_lookup(nd);
                if (err)
                        break;

                hash_len = hash_name(name);

                type = LAST_NORM;
                if (name[0] == '.') switch (hashlen_len(hash_len)) {
                        case 2:
                                if (name[1] == '.') {
                                        type = LAST_DOTDOT;
                                        nd->flags |= LOOKUP_JUMPED;
                                }
                                break;
                        case 1:
                                type = LAST_DOT;
                }
                if (likely(type == LAST_NORM)) {
                        struct dentry *parent = nd->path.dentry;
                        nd->flags &= ~LOOKUP_JUMPED;
                        if (unlikely(parent->d_flags & DCACHE_OP_HASH)) {
                                struct qstr this = { { .hash_len = hash_len }, .name = name };
                                err = parent->d_op->d_hash(parent, &this);
                                if (err < 0)
                                        break;
                                hash_len = this.hash_len;
                                name = this.name;
                        }
                }

                nd->last.hash_len = hash_len;
                nd->last.name = name;
                nd->last_type = type;

                name += hashlen_len(hash_len);
                if (!*name)
                        goto OK;
                /*
                 * If it wasn't NUL, we know it was '/'. Skip that
                 * slash, and continue until no more slashes.
                 */
                do {
                        name++;
                } while (unlikely(*name == '/'));
                if (unlikely(!*name)) {
OK:
                        /* called from path_init(), done */
                        if (!nd->depth)
                                return 0;
                        name = nd->stack[nd->depth - 1].name;
                        /* called from trailing_symlink(), done */
                        if (!name)
                                return 0;
                        /* last component of nested symlink */
                        err = walk_component(nd, WALK_GET | WALK_PUT);
                } else {
                        err = walk_component(nd, WALK_GET);
                }
                if (err < 0)
                        break;

                if (err) {
                        const char *s = get_link(nd);

                        if (unlikely(IS_ERR(s))) {
                                err = PTR_ERR(s);
                                break;
                        }
                        err = 0;
                        if (unlikely(!s)) {
                                /* jumped */
                                put_link(nd);
                        } else {
                                if (*s == '/') {
                                        if (!nd->root.mnt)
                                                set_root(nd);
                                        path_put(&nd->path);
                                        nd->path = nd->root;
                                        path_get(&nd->root);
                                        nd->flags |= LOOKUP_JUMPED;
                                        while (unlikely(*++s == '/'))
                                                ;
                                }
                                nd->inode = nd->path.dentry->d_inode;
                                nd->stack[nd->depth - 1].name = name;
                                if (!*s)
                                        goto OK;
                                name = s;
                                continue;
                        }
                }
                if (!d_can_lookup(nd->path.dentry)) {
                        err = -ENOTDIR;
                        break;
                }
        }
        terminate_walk(nd);
        return err;
}

static int path_init(int dfd, const struct filename *name, unsigned int flags,
                     struct nameidata *nd)
{
        int retval = 0;
        const char *s = name->name;

        nd->last_type = LAST_ROOT; /* if there are only slashes... */
        nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
        nd->depth = 0;
        nd->base = NULL;
        if (flags & LOOKUP_ROOT) {
                struct dentry *root = nd->root.dentry;
                struct inode *inode = root->d_inode;
                if (*s) {
                        if (!d_can_lookup(root))
                                return -ENOTDIR;
                        retval = inode_permission(inode, MAY_EXEC);
                        if (retval)
                                return retval;
                }
                nd->path = nd->root;
                nd->inode = inode;
                if (flags & LOOKUP_RCU) {
                        rcu_read_lock();
                        nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
                        nd->m_seq = read_seqbegin(&mount_lock);
                } else {
                        path_get(&nd->path);
                }
                goto done;
        }

        nd->root.mnt = NULL;

        nd->m_seq = read_seqbegin(&mount_lock);
        if (*s == '/') {
                if (flags & LOOKUP_RCU) {
                        rcu_read_lock();
                        nd->seq = set_root_rcu(nd);
                } else {
                        set_root(nd);
                        path_get(&nd->root);
                }
                nd->path = nd->root;
        } else if (dfd == AT_FDCWD) {
                if (flags & LOOKUP_RCU) {
                        struct fs_struct *fs = current->fs;
                        unsigned seq;

                        rcu_read_lock();

                        do {
                                seq = read_seqcount_begin(&fs->seq);
                                nd->path = fs->pwd;
                                nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
                        } while (read_seqcount_retry(&fs->seq, seq));
                } else {
                        get_fs_pwd(current->fs, &nd->path);
                }
        } else {
                /* Caller must check execute permissions on the starting path component */
                struct fd f = fdget_raw(dfd);
                struct dentry *dentry;

                if (!f.file)
                        return -EBADF;

                dentry = f.file->f_path.dentry;

                if (*s) {
                        if (!d_can_lookup(dentry)) {
                                fdput(f);
                                return -ENOTDIR;
                        }
                }

                nd->path = f.file->f_path;
                if (flags & LOOKUP_RCU) {
                        if (f.flags & FDPUT_FPUT)
                                nd->base = f.file;
                        nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
                        rcu_read_lock();
                } else {
                        path_get(&nd->path);
                        fdput(f);
                }
        }

        nd->inode = nd->path.dentry->d_inode;
        if (!(flags & LOOKUP_RCU))
                goto done;
        if (likely(!read_seqcount_retry(&nd->path.dentry->d_seq, nd->seq)))
                goto done;
        if (!(nd->flags & LOOKUP_ROOT))
                nd->root.mnt = NULL;
        rcu_read_unlock();
        return -ECHILD;
done:
        nd->total_link_count = 0;
        return link_path_walk(s, nd);
}

static void path_cleanup(struct nameidata *nd)
{
        if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
                path_put(&nd->root);
                nd->root.mnt = NULL;
        }
        if (unlikely(nd->base))
                fput(nd->base);
}

static int trailing_symlink(struct nameidata *nd)
{
        const char *s;
        int error = may_follow_link(&nd->link, nd);
        if (unlikely(error))
                return error;
        nd->flags |= LOOKUP_PARENT;
        s = get_link(nd);
        if (unlikely(IS_ERR(s))) {
                terminate_walk(nd);
                return PTR_ERR(s);
        }
        if (unlikely(!s))
                return 0;
        if (*s == '/') {
                if (!nd->root.mnt)
                        set_root(nd);
                path_put(&nd->path);
                nd->path = nd->root;
                path_get(&nd->root);
                nd->flags |= LOOKUP_JUMPED;
        }
        nd->inode = nd->path.dentry->d_inode;
        nd->stack[0].name = NULL;
        return link_path_walk(s, nd);
}

static inline int lookup_last(struct nameidata *nd)
{
        int err;
        if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len])
                nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;

        nd->flags &= ~LOOKUP_PARENT;
        err = walk_component(nd,
                        nd->flags & LOOKUP_FOLLOW
                                ? nd->depth
                                        ? WALK_PUT | WALK_GET
                                        : WALK_GET
                                : 0);
        if (err < 0)
                terminate_walk(nd);
        return err;
}

/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
static int path_lookupat(int dfd, const struct filename *name,
                                unsigned int flags, struct nameidata *nd)
{
        int err;

        /*
         * Path walking is largely split up into 2 different synchronisation
         * schemes, rcu-walk and ref-walk (explained in
         * Documentation/filesystems/path-lookup.txt). These share much of the
         * path walk code, but some things particularly setup, cleanup, and
         * following mounts are sufficiently divergent that functions are
         * duplicated. Typically there is a function foo(), and its RCU
         * analogue, foo_rcu().
         *
         * -ECHILD is the error number of choice (just to avoid clashes) that
         * is returned if some aspect of an rcu-walk fails. Such an error must
         * be handled by restarting a traditional ref-walk (which will always
         * be able to complete).
         */
        err = path_init(dfd, name, flags, nd);
        if (!err && !(flags & LOOKUP_PARENT)) {
                while ((err = lookup_last(nd)) > 0) {
                        err = trailing_symlink(nd);
                        if (err)
                                break;
                }
        }

        if (!err)
                err = complete_walk(nd);

        if (!err && nd->flags & LOOKUP_DIRECTORY) {
                if (!d_can_lookup(nd->path.dentry)) {
                        path_put(&nd->path);
                        err = -ENOTDIR;
                }
        }

        path_cleanup(nd);
        return err;
}

static int filename_lookup(int dfd, struct filename *name,
                                unsigned int flags, struct nameidata *nd)
{
        int retval;
        struct nameidata *saved_nd = set_nameidata(nd);

        retval = path_lookupat(dfd, name, flags | LOOKUP_RCU, nd);
        if (unlikely(retval == -ECHILD))
                retval = path_lookupat(dfd, name, flags, nd);
        if (unlikely(retval == -ESTALE))
                retval = path_lookupat(dfd, name, flags | LOOKUP_REVAL, nd);

        if (likely(!retval))
                audit_inode(name, nd->path.dentry, flags & LOOKUP_PARENT);
        restore_nameidata(saved_nd);
        return retval;
}

/* does lookup, returns the object with parent locked */
struct dentry *kern_path_locked(const char *name, struct path *path)
{
        struct filename *filename = getname_kernel(name);
        struct nameidata nd;
        struct dentry *d;
        int err;

        if (IS_ERR(filename))
                return ERR_CAST(filename);

        err = filename_lookup(AT_FDCWD, filename, LOOKUP_PARENT, &nd);
        if (err) {
                d = ERR_PTR(err);
                goto out;
        }
        if (nd.last_type != LAST_NORM) {
                path_put(&nd.path);
                d = ERR_PTR(-EINVAL);
                goto out;
        }
        mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
        d = __lookup_hash(&nd.last, nd.path.dentry, 0);
        if (IS_ERR(d)) {
                mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
                path_put(&nd.path);
                goto out;
        }
        *path = nd.path;
out:
        putname(filename);
        return d;
}

int kern_path(const char *name, unsigned int flags, struct path *path)
{
        struct nameidata nd;
        struct filename *filename = getname_kernel(name);
        int res = PTR_ERR(filename);

        if (!IS_ERR(filename)) {
                res = filename_lookup(AT_FDCWD, filename, flags, &nd);
                putname(filename);
                if (!res)
                        *path = nd.path;
        }
        return res;
}
EXPORT_SYMBOL(kern_path);

/**
 * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair
 * @dentry:  pointer to dentry of the base directory
 * @mnt: pointer to vfs mount of the base directory
 * @name: pointer to file name
 * @flags: lookup flags
 * @path: pointer to struct path to fill
 */
int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
                    const char *name, unsigned int flags,
                    struct path *path)
{
        struct filename *filename = getname_kernel(name);
        int err = PTR_ERR(filename);

        BUG_ON(flags & LOOKUP_PARENT);

        /* the first argument of filename_lookup() is ignored with LOOKUP_ROOT */
        if (!IS_ERR(filename)) {
                struct nameidata nd;
                nd.root.dentry = dentry;
                nd.root.mnt = mnt;
                err = filename_lookup(AT_FDCWD, filename,
                                      flags | LOOKUP_ROOT, &nd);
                if (!err)
                        *path = nd.path;
                putname(filename);
        }
        return err;
}
EXPORT_SYMBOL(vfs_path_lookup);

/**
 * lookup_one_len - filesystem helper to lookup single pathname component
 * @name:       pathname component to lookup
 * @base:       base directory to lookup from
 * @len:        maximum length @len should be interpreted to
 *
 * Note that this routine is purely a helper for filesystem usage and should
 * not be called by generic code.
 */
struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
{
        struct qstr this;
        unsigned int c;
        int err;

        WARN_ON_ONCE(!mutex_is_locked(&base->d_inode->i_mutex));

        this.name = name;
        this.len = len;
        this.hash = full_name_hash(name, len);
        if (!len)
                return ERR_PTR(-EACCES);

        if (unlikely(name[0] == '.')) {
                if (len < 2 || (len == 2 && name[1] == '.'))
                        return ERR_PTR(-EACCES);
        }

        while (len--) {
                c = *(const unsigned char *)name++;
                if (c == '/' || c == '\0')
                        return ERR_PTR(-EACCES);
        }
        /*
         * See if the low-level filesystem might want
         * to use its own hash..
         */
        if (base->d_flags & DCACHE_OP_HASH) {
                int err = base->d_op->d_hash(base, &this);
                if (err < 0)
                        return ERR_PTR(err);
        }

        err = inode_permission(base->d_inode, MAY_EXEC);
        if (err)
                return ERR_PTR(err);

        return __lookup_hash(&this, base, 0);
}
EXPORT_SYMBOL(lookup_one_len);

int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
                 struct path *path, int *empty)
{
        struct nameidata nd;
        struct filename *tmp = getname_flags(name, flags, empty);
        int err = PTR_ERR(tmp);
        if (!IS_ERR(tmp)) {

                BUG_ON(flags & LOOKUP_PARENT);

                err = filename_lookup(dfd, tmp, flags, &nd);
                putname(tmp);
                if (!err)
                        *path = nd.path;
        }
        return err;
}

int user_path_at(int dfd, const char __user *name, unsigned flags,
                 struct path *path)
{
        return user_path_at_empty(dfd, name, flags, path, NULL);
}
EXPORT_SYMBOL(user_path_at);

/*
 * NB: most callers don't do anything directly with the reference to the
 *     to struct filename, but the nd->last pointer points into the name string
 *     allocated by getname. So we must hold the reference to it until all
 *     path-walking is complete.
 */
static struct filename *
user_path_parent(int dfd, const char __user *path,
                 struct path *parent,
                 struct qstr *last,
                 int *type,
                 unsigned int flags)
{
        struct nameidata nd;
        struct filename *s = getname(path);
        int error;

        /* only LOOKUP_REVAL is allowed in extra flags */
        flags &= LOOKUP_REVAL;

        if (IS_ERR(s))
                return s;

        error = filename_lookup(dfd, s, flags | LOOKUP_PARENT, &nd);
        if (error) {
                putname(s);
                return ERR_PTR(error);
        }
        *parent = nd.path;
        *last = nd.last;
        *type = nd.last_type;

        return s;
}

/**
 * mountpoint_last - look up last component for umount
 * @nd:   pathwalk nameidata - currently pointing at parent directory of "last"
 * @path: pointer to container for result
 *
 * This is a special lookup_last function just for umount. In this case, we
 * need to resolve the path without doing any revalidation.
 *
 * The nameidata should be the result of doing a LOOKUP_PARENT pathwalk. Since
 * mountpoints are always pinned in the dcache, their ancestors are too. Thus,
 * in almost all cases, this lookup will be served out of the dcache. The only
 * cases where it won't are if nd->last refers to a symlink or the path is
 * bogus and it doesn't exist.
 *
 * Returns:
 * -error: if there was an error during lookup. This includes -ENOENT if the
 *         lookup found a negative dentry. The nd->path reference will also be
 *         put in this case.
 *
 * 0:      if we successfully resolved nd->path and found it to not to be a
 *         symlink that needs to be followed. "path" will also be populated.
 *         The nd->path reference will also be put.
 *
 * 1:      if we successfully resolved nd->last and found it to be a symlink
 *         that needs to be followed. "path" will be populated with the path
 *         to the link, and nd->path will *not* be put.
 */
static int
mountpoint_last(struct nameidata *nd, struct path *path)
{
        int error = 0;
        struct dentry *dentry;
        struct dentry *dir = nd->path.dentry;

        /* If we're in rcuwalk, drop out of it to handle last component */
        if (nd->flags & LOOKUP_RCU) {
                if (unlazy_walk(nd, NULL)) {
                        error = -ECHILD;
                        goto out;
                }
        }

        nd->flags &= ~LOOKUP_PARENT;

        if (unlikely(nd->last_type != LAST_NORM)) {
                error = handle_dots(nd, nd->last_type);
                if (error)
                        goto out;
                dentry = dget(nd->path.dentry);
                goto done;
        }

        mutex_lock(&dir->d_inode->i_mutex);
        dentry = d_lookup(dir, &nd->last);
        if (!dentry) {
                /*
                 * No cached dentry. Mounted dentries are pinned in the cache,
                 * so that means that this dentry is probably a symlink or the
                 * path doesn't actually point to a mounted dentry.
                 */
                dentry = d_alloc(dir, &nd->last);
                if (!dentry) {
                        error = -ENOMEM;
                        mutex_unlock(&dir->d_inode->i_mutex);
                        goto out;
                }
                dentry = lookup_real(dir->d_inode, dentry, nd->flags);
                error = PTR_ERR(dentry);
                if (IS_ERR(dentry)) {
                        mutex_unlock(&dir->d_inode->i_mutex);
                        goto out;
                }
        }
        mutex_unlock(&dir->d_inode->i_mutex);

done:
        if (d_is_negative(dentry)) {
                error = -ENOENT;
                dput(dentry);
                goto out;
        }
        if (nd->depth)
                put_link(nd);
        path->dentry = dentry;
        path->mnt = nd->path.mnt;
        error = should_follow_link(nd, path, nd->flags & LOOKUP_FOLLOW);
        if (unlikely(error)) {
                if (error < 0)
                        goto out;
                return error;
        }
        mntget(path->mnt);
        follow_mount(path);
        error = 0;
out:
        terminate_walk(nd);
        return error;
}

/**
 * path_mountpoint - look up a path to be umounted
 * @dfd:        directory file descriptor to start walk from
 * @name:       full pathname to walk
 * @path:       pointer to container for result
 * @flags:      lookup flags
 *
 * Look up the given name, but don't attempt to revalidate the last component.
 * Returns 0 and "path" will be valid on success; Returns error otherwise.
 */
static int
path_mountpoint(int dfd, const struct filename *name, struct path *path,
                struct nameidata *nd, unsigned int flags)
{
        int err = path_init(dfd, name, flags, nd);
        if (unlikely(err))
                goto out;

        while ((err = mountpoint_last(nd, path)) > 0) {
                err = trailing_symlink(nd);
                if (err)
                        break;
        }
out:
        path_cleanup(nd);
        return err;
}

static int
filename_mountpoint(int dfd, struct filename *name, struct path *path,
                        unsigned int flags)
{
        struct nameidata nd, *saved;
        int error;
        if (IS_ERR(name))
                return PTR_ERR(name);
        saved = set_nameidata(&nd);
        error = path_mountpoint(dfd, name, path, &nd, flags | LOOKUP_RCU);
        if (unlikely(error == -ECHILD))
                error = path_mountpoint(dfd, name, path, &nd, flags);
        if (unlikely(error == -ESTALE))
                error = path_mountpoint(dfd, name, path, &nd, flags | LOOKUP_REVAL);
        if (likely(!error))
                audit_inode(name, path->dentry, 0);
        restore_nameidata(saved);
        putname(name);
        return error;
}

/**
 * user_path_mountpoint_at - lookup a path from userland in order to umount it
 * @dfd:        directory file descriptor
 * @name:       pathname from userland
 * @flags:      lookup flags
 * @path:       pointer to container to hold result
 *
 * A umount is a special case for path walking. We're not actually interested
 * in the inode in this situation, and ESTALE errors can be a problem. We
 * simply want track down the dentry and vfsmount attached at the mountpoint
 * and avoid revalidating the last component.
 *
 * Returns 0 and populates "path" on success.
 */
int
user_path_mountpoint_at(int dfd, const char __user *name, unsigned int flags,
                        struct path *path)
{
        return filename_mountpoint(dfd, getname(name), path, flags);
}

int
kern_path_mountpoint(int dfd, const char *name, struct path *path,
                        unsigned int flags)
{
        return filename_mountpoint(dfd, getname_kernel(name), path, flags);
}
EXPORT_SYMBOL(kern_path_mountpoint);

int __check_sticky(struct inode *dir, struct inode *inode)
{
        kuid_t fsuid = current_fsuid();

        if (uid_eq(inode->i_uid, fsuid))
                return 0;
        if (uid_eq(dir->i_uid, fsuid))
                return 0;
        return !capable_wrt_inode_uidgid(inode, CAP_FOWNER);
}
EXPORT_SYMBOL(__check_sticky);

/*
 *      Check whether we can remove a link victim from directory dir, check
 *  whether the type of victim is right.
 *  1. We can't do it if dir is read-only (done in permission())
 *  2. We should have write and exec permissions on dir
 *  3. We can't remove anything from append-only dir
 *  4. We can't do anything with immutable dir (done in permission())
 *  5. If the sticky bit on dir is set we should either
 *      a. be owner of dir, or
 *      b. be owner of victim, or
 *      c. have CAP_FOWNER capability
 *  6. If the victim is append-only or immutable we can't do antyhing with
 *     links pointing to it.
 *  7. If we were asked to remove a directory and victim isn't one - ENOTDIR.
 *  8. If we were asked to remove a non-directory and victim isn't one - EISDIR.
 *  9. We can't remove a root or mountpoint.
 * 10. We don't allow removal of NFS sillyrenamed files; it's handled by
 *     nfs_async_unlink().
 */
static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
{
        struct inode *inode = victim->d_inode;
        int error;

        if (d_is_negative(victim))
                return -ENOENT;
        BUG_ON(!inode);

        BUG_ON(victim->d_parent->d_inode != dir);
        audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);

        error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
        if (error)
                return error;
        if (IS_APPEND(dir))
                return -EPERM;

        if (check_sticky(dir, inode) || IS_APPEND(inode) ||
            IS_IMMUTABLE(inode) || IS_SWAPFILE(inode))
                return -EPERM;
        if (isdir) {
                if (!d_is_dir(victim))
                        return -ENOTDIR;
                if (IS_ROOT(victim))
                        return -EBUSY;
        } else if (d_is_dir(victim))
                return -EISDIR;
        if (IS_DEADDIR(dir))
                return -ENOENT;
        if (victim->d_flags & DCACHE_NFSFS_RENAMED)
                return -EBUSY;
        return 0;
}

/*      Check whether we can create an object with dentry child in directory
 *  dir.
 *  1. We can't do it if child already exists (open has special treatment for
 *     this case, but since we are inlined it's OK)
 *  2. We can't do it if dir is read-only (done in permission())
 *  3. We should have write and exec permissions on dir
 *  4. We can't do it if dir is immutable (done in permission())
 */
static inline int may_create(struct inode *dir, struct dentry *child)
{
        audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE);
        if (child->d_inode)
                return -EEXIST;
        if (IS_DEADDIR(dir))
                return -ENOENT;
        return inode_permission(dir, MAY_WRITE | MAY_EXEC);
}

/*
 * p1 and p2 should be directories on the same fs.
 */
struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
{
        struct dentry *p;

        if (p1 == p2) {
                mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
                return NULL;
        }

        mutex_lock(&p1->d_inode->i_sb->s_vfs_rename_mutex);

        p = d_ancestor(p2, p1);
        if (p) {
                mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT);
                mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_CHILD);
                return p;
        }

        p = d_ancestor(p1, p2);
        if (p) {
                mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
                mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD);
                return p;
        }

        mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
        mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT2);
        return NULL;
}
EXPORT_SYMBOL(lock_rename);

void unlock_rename(struct dentry *p1, struct dentry *p2)
{
        mutex_unlock(&p1->d_inode->i_mutex);
        if (p1 != p2) {
                mutex_unlock(&p2->d_inode->i_mutex);
                mutex_unlock(&p1->d_inode->i_sb->s_vfs_rename_mutex);
        }
}
EXPORT_SYMBOL(unlock_rename);

int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
                bool want_excl)
{
        int error = may_create(dir, dentry);
        if (error)
                return error;

        if (!dir->i_op->create)
                return -EACCES; /* shouldn't it be ENOSYS? */
        mode &= S_IALLUGO;
        mode |= S_IFREG;
        error = security_inode_create(dir, dentry, mode);
        if (error)
                return error;
        error = dir->i_op->create(dir, dentry, mode, want_excl);
        if (!error)
                fsnotify_create(dir, dentry);
        return error;
}
EXPORT_SYMBOL(vfs_create);

static int may_open(struct path *path, int acc_mode, int flag)
{
        struct dentry *dentry = path->dentry;
        struct inode *inode = dentry->d_inode;
        int error;

        /* O_PATH? */
        if (!acc_mode)
                return 0;

        if (!inode)
                return -ENOENT;

        switch (inode->i_mode & S_IFMT) {
        case S_IFLNK:
                return -ELOOP;
        case S_IFDIR:
                if (acc_mode & MAY_WRITE)
                        return -EISDIR;
                break;
        case S_IFBLK:
        case S_IFCHR:
                if (path->mnt->mnt_flags & MNT_NODEV)
                        return -EACCES;
                /*FALLTHRU*/
        case S_IFIFO:
        case S_IFSOCK:
                flag &= ~O_TRUNC;
                break;
        }

        error = inode_permission(inode, acc_mode);
        if (error)
                return error;

        /*
         * An append-only file must be opened in append mode for writing.
         */
        if (IS_APPEND(inode)) {
                if  ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND))
                        return -EPERM;
                if (flag & O_TRUNC)
                        return -EPERM;
        }

        /* O_NOATIME can only be set by the owner or superuser */
        if (flag & O_NOATIME && !inode_owner_or_capable(inode))
                return -EPERM;

        return 0;
}

static int handle_truncate(struct file *filp)
{
        struct path *path = &filp->f_path;
        struct inode *inode = path->dentry->d_inode;
        int error = get_write_access(inode);
        if (error)
                return error;
        /*
         * Refuse to truncate files with mandatory locks held on them.
         */
        error = locks_verify_locked(filp);
        if (!error)
                error = security_path_truncate(path);
        if (!error) {
                error = do_truncate(path->dentry, 0,
                                    ATTR_MTIME|ATTR_CTIME|ATTR_OPEN,
                                    filp);
        }
        put_write_access(inode);
        return error;
}

static inline int open_to_namei_flags(int flag)
{
        if ((flag & O_ACCMODE) == 3)
                flag--;
        return flag;
}

static int may_o_create(struct path *dir, struct dentry *dentry, umode_t mode)
{
        int error = security_path_mknod(dir, dentry, mode, 0);
        if (error)
                return error;

        error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC);
        if (error)
                return error;

        return security_inode_create(dir->dentry->d_inode, dentry, mode);
}

/*
 * Attempt to atomically look up, create and open a file from a negative
 * dentry.
 *
 * Returns 0 if successful.  The file will have been created and attached to
 * @file by the filesystem calling finish_open().
 *
 * Returns 1 if the file was looked up only or didn't need creating.  The
 * caller will need to perform the open themselves.  @path will have been
 * updated to point to the new dentry.  This may be negative.
 *
 * Returns an error code otherwise.
 */
static int atomic_open(struct nameidata *nd, struct dentry *dentry,
                        struct path *path, struct file *file,
                        const struct open_flags *op,
                        bool got_write, bool need_lookup,
                        int *opened)
{
        struct inode *dir =  nd->path.dentry->d_inode;
        unsigned open_flag = open_to_namei_flags(op->open_flag);
        umode_t mode;
        int error;
        int acc_mode;
        int create_error = 0;
        struct dentry *const DENTRY_NOT_SET = (void *) -1UL;
        bool excl;

        BUG_ON(dentry->d_inode);

        /* Don't create child dentry for a dead directory. */
        if (unlikely(IS_DEADDIR(dir))) {
                error = -ENOENT;
                goto out;
        }

        mode = op->mode;
        if ((open_flag & O_CREAT) && !IS_POSIXACL(dir))
                mode &= ~current_umask();

        excl = (open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT);
        if (excl)
                open_flag &= ~O_TRUNC;

        /*
         * Checking write permission is tricky, bacuse we don't know if we are
         * going to actually need it: O_CREAT opens should work as long as the
         * file exists.  But checking existence breaks atomicity.  The trick is
         * to check access and if not granted clear O_CREAT from the flags.
         *
         * Another problem is returing the "right" error value (e.g. for an
         * O_EXCL open we want to return EEXIST not EROFS).
         */
        if (((open_flag & (O_CREAT | O_TRUNC)) ||
            (open_flag & O_ACCMODE) != O_RDONLY) && unlikely(!got_write)) {
                if (!(open_flag & O_CREAT)) {
                        /*
                         * No O_CREATE -> atomicity not a requirement -> fall
                         * back to lookup + open
                         */
                        goto no_open;
                } else if (open_flag & (O_EXCL | O_TRUNC)) {
                        /* Fall back and fail with the right error */
                        create_error = -EROFS;
                        goto no_open;
                } else {
                        /* No side effects, safe to clear O_CREAT */
                        create_error = -EROFS;
                        open_flag &= ~O_CREAT;
                }
        }

        if (open_flag & O_CREAT) {
                error = may_o_create(&nd->path, dentry, mode);
                if (error) {
                        create_error = error;
                        if (open_flag & O_EXCL)
                                goto no_open;
                        open_flag &= ~O_CREAT;
                }
        }

        if (nd->flags & LOOKUP_DIRECTORY)
                open_flag |= O_DIRECTORY;

        file->f_path.dentry = DENTRY_NOT_SET;
        file->f_path.mnt = nd->path.mnt;
        error = dir->i_op->atomic_open(dir, dentry, file, open_flag, mode,
                                      opened);
        if (error < 0) {
                if (create_error && error == -ENOENT)
                        error = create_error;
                goto out;
        }

        if (error) {    /* returned 1, that is */
                if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
                        error = -EIO;
                        goto out;
                }
                if (file->f_path.dentry) {
                        dput(dentry);
                        dentry = file->f_path.dentry;
                }
                if (*opened & FILE_CREATED)
                        fsnotify_create(dir, dentry);
                if (!dentry->d_inode) {
                        WARN_ON(*opened & FILE_CREATED);
                        if (create_error) {
                                error = create_error;
                                goto out;
                        }
                } else {
                        if (excl && !(*opened & FILE_CREATED)) {
                                error = -EEXIST;
                                goto out;
                        }
                }
                goto looked_up;
        }

        /*
         * We didn't have the inode before the open, so check open permission
         * here.
         */
        acc_mode = op->acc_mode;
        if (*opened & FILE_CREATED) {
                WARN_ON(!(open_flag & O_CREAT));
                fsnotify_create(dir, dentry);
                acc_mode = MAY_OPEN;
        }
        error = may_open(&file->f_path, acc_mode, open_flag);
        if (error)
                fput(file);

out:
        dput(dentry);
        return error;

no_open:
        if (need_lookup) {
                dentry = lookup_real(dir, dentry, nd->flags);
                if (IS_ERR(dentry))
                        return PTR_ERR(dentry);

                if (create_error) {
                        int open_flag = op->open_flag;

                        error = create_error;
                        if ((open_flag & O_EXCL)) {
                                if (!dentry->d_inode)
                                        goto out;
                        } else if (!dentry->d_inode) {
                                goto out;
                        } else if ((open_flag & O_TRUNC) &&
                                   d_is_reg(dentry)) {
                                goto out;
                        }
                        /* will fail later, go on to get the right error */
                }
        }
looked_up:
        path->dentry = dentry;
        path->mnt = nd->path.mnt;
        return 1;
}

/*
 * Look up and maybe create and open the last component.
 *
 * Must be called with i_mutex held on parent.
 *
 * Returns 0 if the file was successfully atomically created (if necessary) and
 * opened.  In this case the file will be returned attached to @file.
 *
 * Returns 1 if the file was not completely opened at this time, though lookups
 * and creations will have been performed and the dentry returned in @path will
 * be positive upon return if O_CREAT was specified.  If O_CREAT wasn't
 * specified then a negative dentry may be returned.
 *
 * An error code is returned otherwise.
 *
 * FILE_CREATE will be set in @*opened if the dentry was created and will be
 * cleared otherwise prior to returning.
 */
static int lookup_open(struct nameidata *nd, struct path *path,
                        struct file *file,
                        const struct open_flags *op,
                        bool got_write, int *opened)
{
        struct dentry *dir = nd->path.dentry;
        struct inode *dir_inode = dir->d_inode;
        struct dentry *dentry;
        int error;
        bool need_lookup;

        *opened &= ~FILE_CREATED;
        dentry = lookup_dcache(&nd->last, dir, nd->flags, &need_lookup);
        if (IS_ERR(dentry))
                return PTR_ERR(dentry);

        /* Cached positive dentry: will open in f_op->open */
        if (!need_lookup && dentry->d_inode)
                goto out_no_open;

        if ((nd->flags & LOOKUP_OPEN) && dir_inode->i_op->atomic_open) {
                return atomic_open(nd, dentry, path, file, op, got_write,
                                   need_lookup, opened);
        }

        if (need_lookup) {
                BUG_ON(dentry->d_inode);

                dentry = lookup_real(dir_inode, dentry, nd->flags);
                if (IS_ERR(dentry))
                        return PTR_ERR(dentry);
        }

        /* Negative dentry, just create the file */
        if (!dentry->d_inode && (op->open_flag & O_CREAT)) {
                umode_t mode = op->mode;
                if (!IS_POSIXACL(dir->d_inode))
                        mode &= ~current_umask();
                /*
                 * This write is needed to ensure that a
                 * rw->ro transition does not occur between
                 * the time when the file is created and when
                 * a permanent write count is taken through
                 * the 'struct file' in finish_open().
                 */
                if (!got_write) {
                        error = -EROFS;
                        goto out_dput;
                }
                *opened |= FILE_CREATED;
                error = security_path_mknod(&nd->path, dentry, mode, 0);
                if (error)
                        goto out_dput;
                error = vfs_create(dir->d_inode, dentry, mode,
                                   nd->flags & LOOKUP_EXCL);
                if (error)
                        goto out_dput;
        }
out_no_open:
        path->dentry = dentry;
        path->mnt = nd->path.mnt;
        return 1;

out_dput:
        dput(dentry);
        return error;
}

/*
 * Handle the last step of open()
 */
static int do_last(struct nameidata *nd,
                   struct file *file, const struct open_flags *op,
                   int *opened, struct filename *name)
{
        struct dentry *dir = nd->path.dentry;
        int open_flag = op->open_flag;
        bool will_truncate = (open_flag & O_TRUNC) != 0;
        bool got_write = false;
        int acc_mode = op->acc_mode;
        struct inode *inode;
        struct path save_parent = { .dentry = NULL, .mnt = NULL };
        struct path path;
        bool retried = false;
        int error;

        nd->flags &= ~LOOKUP_PARENT;
        nd->flags |= op->intent;

        if (nd->last_type != LAST_NORM) {
                error = handle_dots(nd, nd->last_type);
                if (unlikely(error)) {
                        terminate_walk(nd);
                        return error;
                }
                goto finish_open;
        }

        if (!(open_flag & O_CREAT)) {
                if (nd->last.name[nd->last.len])
                        nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
                /* we _can_ be in RCU mode here */
                error = lookup_fast(nd, &path, &inode);
                if (likely(!error))
                        goto finish_lookup;

                if (error < 0)
                        goto out;

                BUG_ON(nd->inode != dir->d_inode);
        } else {
                /* create side of things */
                /*
                 * This will *only* deal with leaving RCU mode - LOOKUP_JUMPED
                 * has been cleared when we got to the last component we are
                 * about to look up
                 */
                error = complete_walk(nd);
                if (error) {
                        if (nd->depth)
                                put_link(nd);
                        return error;
                }

                audit_inode(name, dir, LOOKUP_PARENT);
                error = -EISDIR;
                /* trailing slashes? */
                if (nd->last.name[nd->last.len])
                        goto out;
        }

retry_lookup:
        if (op->open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) {
                error = mnt_want_write(nd->path.mnt);
                if (!error)
                        got_write = true;
                /*
                 * do _not_ fail yet - we might not need that or fail with
                 * a different error; let lookup_open() decide; we'll be
                 * dropping this one anyway.
                 */
        }
        mutex_lock(&dir->d_inode->i_mutex);
        error = lookup_open(nd, &path, file, op, got_write, opened);
        mutex_unlock(&dir->d_inode->i_mutex);

        if (error <= 0) {
                if (error)
                        goto out;

                if ((*opened & FILE_CREATED) ||
                    !S_ISREG(file_inode(file)->i_mode))
                        will_truncate = false;

                audit_inode(name, file->f_path.dentry, 0);
                goto opened;
        }

        if (*opened & FILE_CREATED) {
                /* Don't check for write permission, don't truncate */
                open_flag &= ~O_TRUNC;
                will_truncate = false;
                acc_mode = MAY_OPEN;
                path_to_nameidata(&path, nd);
                goto finish_open_created;
        }

        /*
         * create/update audit record if it already exists.
         */
        if (d_is_positive(path.dentry))
                audit_inode(name, path.dentry, 0);

        /*
         * If atomic_open() acquired write access it is dropped now due to
         * possible mount and symlink following (this might be optimized away if
         * necessary...)
         */
        if (got_write) {
                mnt_drop_write(nd->path.mnt);
                got_write = false;
        }

        error = -EEXIST;
        if ((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT))
                goto exit_dput;

        error = follow_managed(&path, nd);
        if (error < 0)
                goto out;

        BUG_ON(nd->flags & LOOKUP_RCU);
        inode = path.dentry->d_inode;
        error = -ENOENT;
        if (d_is_negative(path.dentry)) {
                path_to_nameidata(&path, nd);
                goto out;
        }
finish_lookup:
        if (nd->depth)
                put_link(nd);
        error = should_follow_link(nd, &path, nd->flags & LOOKUP_FOLLOW);
        if (unlikely(error)) {
                if (error < 0)
                        goto out;
                return error;
        }

        if (unlikely(d_is_symlink(path.dentry)) && !(open_flag & O_PATH)) {
                path_to_nameidata(&path, nd);
                error = -ELOOP;
                goto out;
        }

        if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) {
                path_to_nameidata(&path, nd);
        } else {
                save_parent.dentry = nd->path.dentry;
                save_parent.mnt = mntget(path.mnt);
                nd->path.dentry = path.dentry;

        }
        nd->inode = inode;
        /* Why this, you ask?  _Now_ we might have grown LOOKUP_JUMPED... */
finish_open:
        error = complete_walk(nd);
        if (error) {
                if (nd->depth)
                        put_link(nd);
                path_put(&save_parent);
                return error;
        }
        audit_inode(name, nd->path.dentry, 0);
        error = -EISDIR;
        if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry))
                goto out;
        error = -ENOTDIR;
        if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry))
                goto out;
        if (!d_is_reg(nd->path.dentry))
                will_truncate = false;

        if (will_truncate) {
                error = mnt_want_write(nd->path.mnt);
                if (error)
                        goto out;
                got_write = true;
        }
finish_open_created:
        error = may_open(&nd->path, acc_mode, open_flag);
        if (error)
                goto out;

        BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
        error = vfs_open(&nd->path, file, current_cred());
        if (!error) {
                *opened |= FILE_OPENED;
        } else {
                if (error == -EOPENSTALE)
                        goto stale_open;
                goto out;
        }
opened:
        error = open_check_o_direct(file);
        if (error)
                goto exit_fput;
        error = ima_file_check(file, op->acc_mode, *opened);
        if (error)
                goto exit_fput;

        if (will_truncate) {
                error = handle_truncate(file);
                if (error)
                        goto exit_fput;
        }
out:
        if (got_write)
                mnt_drop_write(nd->path.mnt);
        path_put(&save_parent);
        terminate_walk(nd);
        return error;

exit_dput:
        path_put_conditional(&path, nd);
        goto out;
exit_fput:
        fput(file);
        goto out;

stale_open:
        /* If no saved parent or already retried then can't retry */
        if (!save_parent.dentry || retried)
                goto out;

        BUG_ON(save_parent.dentry != dir);
        path_put(&nd->path);
        nd->path = save_parent;
        nd->inode = dir->d_inode;
        save_parent.mnt = NULL;
        save_parent.dentry = NULL;
        if (got_write) {
                mnt_drop_write(nd->path.mnt);
                got_write = false;
        }
        retried = true;
        goto retry_lookup;
}

static int do_tmpfile(int dfd, struct filename *pathname,
                struct nameidata *nd, int flags,
                const struct open_flags *op,
                struct file *file, int *opened)
{
        static const struct qstr name = QSTR_INIT("/", 1);
        struct dentry *dentry, *child;
        struct inode *dir;
        int error = path_lookupat(dfd, pathname,
                                  flags | LOOKUP_DIRECTORY, nd);
        if (unlikely(error))
                return error;
        error = mnt_want_write(nd->path.mnt);
        if (unlikely(error))
                goto out;
        /* we want directory to be writable */
        error = inode_permission(nd->inode, MAY_WRITE | MAY_EXEC);
        if (error)
                goto out2;
        dentry = nd->path.dentry;
        dir = dentry->d_inode;
        if (!dir->i_op->tmpfile) {
                error = -EOPNOTSUPP;
                goto out2;
        }
        child = d_alloc(dentry, &name);
        if (unlikely(!child)) {
                error = -ENOMEM;
                goto out2;
        }
        nd->flags &= ~LOOKUP_DIRECTORY;
        nd->flags |= op->intent;
        dput(nd->path.dentry);
        nd->path.dentry = child;
        error = dir->i_op->tmpfile(dir, nd->path.dentry, op->mode);
        if (error)
                goto out2;
        audit_inode(pathname, nd->path.dentry, 0);
        /* Don't check for other permissions, the inode was just created */
        error = may_open(&nd->path, MAY_OPEN, op->open_flag);
        if (error)
                goto out2;
        file->f_path.mnt = nd->path.mnt;
        error = finish_open(file, nd->path.dentry, NULL, opened);
        if (error)
                goto out2;
        error = open_check_o_direct(file);
        if (error) {
                fput(file);
        } else if (!(op->open_flag & O_EXCL)) {
                struct inode *inode = file_inode(file);
                spin_lock(&inode->i_lock);
                inode->i_state |= I_LINKABLE;
                spin_unlock(&inode->i_lock);
        }
out2:
        mnt_drop_write(nd->path.mnt);
out:
        path_put(&nd->path);
        return error;
}

static struct file *path_openat(int dfd, struct filename *pathname,
                struct nameidata *nd, const struct open_flags *op, int flags)
{
        struct file *file;
        int opened = 0;
        int error;

        file = get_empty_filp();
        if (IS_ERR(file))
                return file;

        file->f_flags = op->open_flag;

        if (unlikely(file->f_flags & __O_TMPFILE)) {
                error = do_tmpfile(dfd, pathname, nd, flags, op, file, &opened);
                goto out2;
        }

        error = path_init(dfd, pathname, flags, nd);
        if (unlikely(error))
                goto out;

        while ((error = do_last(nd, file, op, &opened, pathname)) > 0) {
                nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
                error = trailing_symlink(nd);
                if (unlikely(error))
                        break;
        }
out:
        path_cleanup(nd);
out2:
        if (!(opened & FILE_OPENED)) {
                BUG_ON(!error);
                put_filp(file);
        }
        if (unlikely(error)) {
                if (error == -EOPENSTALE) {
                        if (flags & LOOKUP_RCU)
                                error = -ECHILD;
                        else
                                error = -ESTALE;
                }
                file = ERR_PTR(error);
        }
        return file;
}

struct file *do_filp_open(int dfd, struct filename *pathname,
                const struct open_flags *op)
{
        struct nameidata nd, *saved_nd = set_nameidata(&nd);
        int flags = op->lookup_flags;
        struct file *filp;

        filp = path_openat(dfd, pathname, &nd, op, flags | LOOKUP_RCU);
        if (unlikely(filp == ERR_PTR(-ECHILD)))
                filp = path_openat(dfd, pathname, &nd, op, flags);
        if (unlikely(filp == ERR_PTR(-ESTALE)))
                filp = path_openat(dfd, pathname, &nd, op, flags | LOOKUP_REVAL);
        restore_nameidata(saved_nd);
        return filp;
}

struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
                const char *name, const struct open_flags *op)
{
        struct nameidata nd, *saved_nd;
        struct file *file;
        struct filename *filename;
        int flags = op->lookup_flags | LOOKUP_ROOT;

        nd.root.mnt = mnt;
        nd.root.dentry = dentry;

        if (d_is_symlink(dentry) && op->intent & LOOKUP_OPEN)
                return ERR_PTR(-ELOOP);

        filename = getname_kernel(name);
        if (unlikely(IS_ERR(filename)))
                return ERR_CAST(filename);

        saved_nd = set_nameidata(&nd);
        file = path_openat(-1, filename, &nd, op, flags | LOOKUP_RCU);
        if (unlikely(file == ERR_PTR(-ECHILD)))
                file = path_openat(-1, filename, &nd, op, flags);
        if (unlikely(file == ERR_PTR(-ESTALE)))
                file = path_openat(-1, filename, &nd, op, flags | LOOKUP_REVAL);
        restore_nameidata(saved_nd);
        putname(filename);
        return file;
}

static struct dentry *filename_create(int dfd, struct filename *name,
                                struct path *path, unsigned int lookup_flags)
{
        struct dentry *dentry = ERR_PTR(-EEXIST);
        struct nameidata nd;
        int err2;
        int error;
        bool is_dir = (lookup_flags & LOOKUP_DIRECTORY);

        /*
         * Note that only LOOKUP_REVAL and LOOKUP_DIRECTORY matter here. Any
         * other flags passed in are ignored!
         */
        lookup_flags &= LOOKUP_REVAL;

        error = filename_lookup(dfd, name, LOOKUP_PARENT|lookup_flags, &nd);
        if (error)
                return ERR_PTR(error);

        /*
         * Yucky last component or no last component at all?
         * (foo/., foo/.., /////)
         */
        if (nd.last_type != LAST_NORM)
                goto out;
        nd.flags &= ~LOOKUP_PARENT;
        nd.flags |= LOOKUP_CREATE | LOOKUP_EXCL;

        /* don't fail immediately if it's r/o, at least try to report other errors */
        err2 = mnt_want_write(nd.path.mnt);
        /*
         * Do the final lookup.
         */
        mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
        dentry = __lookup_hash(&nd.last, nd.path.dentry, nd.flags);
        if (IS_ERR(dentry))
                goto unlock;

        error = -EEXIST;
        if (d_is_positive(dentry))
                goto fail;

        /*
         * Special case - lookup gave negative, but... we had foo/bar/
         * From the vfs_mknod() POV we just have a negative dentry -
         * all is fine. Let's be bastards - you had / on the end, you've
         * been asking for (non-existent) directory. -ENOENT for you.
         */
        if (unlikely(!is_dir && nd.last.name[nd.last.len])) {
                error = -ENOENT;
                goto fail;
        }
        if (unlikely(err2)) {
                error = err2;
                goto fail;
        }
        *path = nd.path;
        return dentry;
fail:
        dput(dentry);
        dentry = ERR_PTR(error);
unlock:
        mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
        if (!err2)
                mnt_drop_write(nd.path.mnt);
out:
        path_put(&nd.path);
        return dentry;
}

struct dentry *kern_path_create(int dfd, const char *pathname,
                                struct path *path, unsigned int lookup_flags)
{
        struct filename *filename = getname_kernel(pathname);
        struct dentry *res;

        if (IS_ERR(filename))
                return ERR_CAST(filename);
        res = filename_create(dfd, filename, path, lookup_flags);
        putname(filename);
        return res;
}
EXPORT_SYMBOL(kern_path_create);

void done_path_create(struct path *path, struct dentry *dentry)
{
        dput(dentry);
        mutex_unlock(&path->dentry->d_inode->i_mutex);
        mnt_drop_write(path->mnt);
        path_put(path);
}
EXPORT_SYMBOL(done_path_create);

struct dentry *user_path_create(int dfd, const char __user *pathname,
                                struct path *path, unsigned int lookup_flags)
{
        struct filename *tmp = getname(pathname);
        struct dentry *res;
        if (IS_ERR(tmp))
                return ERR_CAST(tmp);
        res = filename_create(dfd, tmp, path, lookup_flags);
        putname(tmp);
        return res;
}
EXPORT_SYMBOL(user_path_create);

int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
{
        int error = may_create(dir, dentry);

        if (error)
                return error;

        if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))
                return -EPERM;

        if (!dir->i_op->mknod)
                return -EPERM;

        error = devcgroup_inode_mknod(mode, dev);
        if (error)
                return error;

        error = security_inode_mknod(dir, dentry, mode, dev);
        if (error)
                return error;

        error = dir->i_op->mknod(dir, dentry, mode, dev);
        if (!error)
                fsnotify_create(dir, dentry);
        return error;
}
EXPORT_SYMBOL(vfs_mknod);

static int may_mknod(umode_t mode)
{
        switch (mode & S_IFMT) {
        case S_IFREG:
        case S_IFCHR:
        case S_IFBLK:
        case S_IFIFO:
        case S_IFSOCK:
        case 0: /* zero mode translates to S_IFREG */
                return 0;
        case S_IFDIR:
                return -EPERM;
        default:
                return -EINVAL;
        }
}

SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode,
                unsigned, dev)
{
        struct dentry *dentry;
        struct path path;
        int error;
        unsigned int lookup_flags = 0;

        error = may_mknod(mode);
        if (error)
                return error;
retry:
        dentry = user_path_create(dfd, filename, &path, lookup_flags);
        if (IS_ERR(dentry))
                return PTR_ERR(dentry);

        if (!IS_POSIXACL(path.dentry->d_inode))
                mode &= ~current_umask();
        error = security_path_mknod(&path, dentry, mode, dev);
        if (error)
                goto out;
        switch (mode & S_IFMT) {
                case 0: case S_IFREG:
                        error = vfs_create(path.dentry->d_inode,dentry,mode,true);
                        break;
                case S_IFCHR: case S_IFBLK:
                        error = vfs_mknod(path.dentry->d_inode,dentry,mode,
                                        new_decode_dev(dev));
                        break;
                case S_IFIFO: case S_IFSOCK:
                        error = vfs_mknod(path.dentry->d_inode,dentry,mode,0);
                        break;
        }
out:
        done_path_create(&path, dentry);
        if (retry_estale(error, lookup_flags)) {
                lookup_flags |= LOOKUP_REVAL;
                goto retry;
        }
        return error;
}

SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev)
{
        return sys_mknodat(AT_FDCWD, filename, mode, dev);
}

int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
        int error = may_create(dir, dentry);
        unsigned max_links = dir->i_sb->s_max_links;

        if (error)
                return error;

        if (!dir->i_op->mkdir)
                return -EPERM;

        mode &= (S_IRWXUGO|S_ISVTX);
        error = security_inode_mkdir(dir, dentry, mode);
        if (error)
                return error;

        if (max_links && dir->i_nlink >= max_links)
                return -EMLINK;

        error = dir->i_op->mkdir(dir, dentry, mode);
        if (!error)
                fsnotify_mkdir(dir, dentry);
        return error;
}
EXPORT_SYMBOL(vfs_mkdir);

SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode)
{
        struct dentry *dentry;
        struct path path;
        int error;
        unsigned int lookup_flags = LOOKUP_DIRECTORY;

retry:
        dentry = user_path_create(dfd, pathname, &path, lookup_flags);
        if (IS_ERR(dentry))
                return PTR_ERR(dentry);

        if (!IS_POSIXACL(path.dentry->d_inode))
                mode &= ~current_umask();
        error = security_path_mkdir(&path, dentry, mode);
        if (!error)
                error = vfs_mkdir(path.dentry->d_inode, dentry, mode);
        done_path_create(&path, dentry);
        if (retry_estale(error, lookup_flags)) {
                lookup_flags |= LOOKUP_REVAL;
                goto retry;
        }
        return error;
}

SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode)
{
        return sys_mkdirat(AT_FDCWD, pathname, mode);
}

/*
 * The dentry_unhash() helper will try to drop the dentry early: we
 * should have a usage count of 1 if we're the only user of this
 * dentry, and if that is true (possibly after pruning the dcache),
 * then we drop the dentry now.
 *
 * A low-level filesystem can, if it choses, legally
 * do a
 *
 *      if (!d_unhashed(dentry))
 *              return -EBUSY;
 *
 * if it cannot handle the case of removing a directory
 * that is still in use by something else..
 */
void dentry_unhash(struct dentry *dentry)
{
        shrink_dcache_parent(dentry);
        spin_lock(&dentry->d_lock);
        if (dentry->d_lockref.count == 1)
                __d_drop(dentry);
        spin_unlock(&dentry->d_lock);
}
EXPORT_SYMBOL(dentry_unhash);

int vfs_rmdir(struct inode *dir, struct dentry *dentry)
{
        int error = may_delete(dir, dentry, 1);

        if (error)
                return error;

        if (!dir->i_op->rmdir)
                return -EPERM;

        dget(dentry);
        mutex_lock(&dentry->d_inode->i_mutex);

        error = -EBUSY;
        if (is_local_mountpoint(dentry))
                goto out;

        error = security_inode_rmdir(dir, dentry);
        if (error)
                goto out;

        shrink_dcache_parent(dentry);
        error = dir->i_op->rmdir(dir, dentry);
        if (error)
                goto out;

        dentry->d_inode->i_flags |= S_DEAD;
        dont_mount(dentry);
        detach_mounts(dentry);

out:
        mutex_unlock(&dentry->d_inode->i_mutex);
        dput(dentry);
        if (!error)
                d_delete(dentry);
        return error;
}
EXPORT_SYMBOL(vfs_rmdir);

static long do_rmdir(int dfd, const char __user *pathname)
{
        int error = 0;
        struct filename *name;
        struct dentry *dentry;
        struct path path;
        struct qstr last;
        int type;
        unsigned int lookup_flags = 0;
retry:
        name = user_path_parent(dfd, pathname,
                                &path, &last, &type, lookup_flags);
        if (IS_ERR(name))
                return PTR_ERR(name);

        switch (type) {
        case LAST_DOTDOT:
                error = -ENOTEMPTY;
                goto exit1;
        case LAST_DOT:
                error = -EINVAL;
                goto exit1;
        case LAST_ROOT:
                error = -EBUSY;
                goto exit1;
        }

        error = mnt_want_write(path.mnt);
        if (error)
                goto exit1;

        mutex_lock_nested(&path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
        dentry = __lookup_hash(&last, path.dentry, lookup_flags);
        error = PTR_ERR(dentry);
        if (IS_ERR(dentry))
                goto exit2;
        if (!dentry->d_inode) {
                error = -ENOENT;
                goto exit3;
        }
        error = security_path_rmdir(&path, dentry);
        if (error)
                goto exit3;
        error = vfs_rmdir(path.dentry->d_inode, dentry);
exit3:
        dput(dentry);
exit2:
        mutex_unlock(&path.dentry->d_inode->i_mutex);
        mnt_drop_write(path.mnt);
exit1:
        path_put(&path);
        putname(name);
        if (retry_estale(error, lookup_flags)) {
                lookup_flags |= LOOKUP_REVAL;
                goto retry;
        }
        return error;
}

SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
{
        return do_rmdir(AT_FDCWD, pathname);
}

/**
 * vfs_unlink - unlink a filesystem object
 * @dir:        parent directory
 * @dentry:     victim
 * @delegated_inode: returns victim inode, if the inode is delegated.
 *
 * The caller must hold dir->i_mutex.
 *
 * If vfs_unlink discovers a delegation, it will return -EWOULDBLOCK and
 * return a reference to the inode in delegated_inode.  The caller
 * should then break the delegation on that inode and retry.  Because
 * breaking a delegation may take a long time, the caller should drop
 * dir->i_mutex before doing so.
 *
 * Alternatively, a caller may pass NULL for delegated_inode.  This may
 * be appropriate for callers that expect the underlying filesystem not
 * to be NFS exported.
 */
int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode)
{
        struct inode *target = dentry->d_inode;
        int error = may_delete(dir, dentry, 0);

        if (error)
                return error;

        if (!dir->i_op->unlink)
                return -EPERM;

        mutex_lock(&target->i_mutex);
        if (is_local_mountpoint(dentry))
                error = -EBUSY;
        else {
                error = security_inode_unlink(dir, dentry);
                if (!error) {
                        error = try_break_deleg(target, delegated_inode);
                        if (error)
                                goto out;
                        error = dir->i_op->unlink(dir, dentry);
                        if (!error) {
                                dont_mount(dentry);
                                detach_mounts(dentry);
                        }
                }
        }
out:
        mutex_unlock(&target->i_mutex);

        /* We don't d_delete() NFS sillyrenamed files--they still exist. */
        if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) {
                fsnotify_link_count(target);
                d_delete(dentry);
        }

        return error;
}
EXPORT_SYMBOL(vfs_unlink);

/*
 * Make sure that the actual truncation of the file will occur outside its
 * directory's i_mutex.  Truncate can take a long time if there is a lot of
 * writeout happening, and we don't want to prevent access to the directory
 * while waiting on the I/O.
 */
static long do_unlinkat(int dfd, const char __user *pathname)
{
        int error;
        struct filename *name;
        struct dentry *dentry;
        struct path path;
        struct qstr last;
        int type;
        struct inode *inode = NULL;
        struct inode *delegated_inode = NULL;
        unsigned int lookup_flags = 0;
retry:
        name = user_path_parent(dfd, pathname,
                                &path, &last, &type, lookup_flags);
        if (IS_ERR(name))
                return PTR_ERR(name);

        error = -EISDIR;
        if (type != LAST_NORM)
                goto exit1;

        error = mnt_want_write(path.mnt);
        if (error)
                goto exit1;
retry_deleg:
        mutex_lock_nested(&path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
        dentry = __lookup_hash(&last, path.dentry, lookup_flags);
        error = PTR_ERR(dentry);
        if (!IS_ERR(dentry)) {
                /* Why not before? Because we want correct error value */
                if (last.name[last.len])
                        goto slashes;
                inode = dentry->d_inode;
                if (d_is_negative(dentry))
                        goto slashes;
                ihold(inode);
                error = security_path_unlink(&path, dentry);
                if (error)
                        goto exit2;
                error = vfs_unlink(path.dentry->d_inode, dentry, &delegated_inode);
exit2:
                dput(dentry);
        }
        mutex_unlock(&path.dentry->d_inode->i_mutex);
        if (inode)
                iput(inode);    /* truncate the inode here */
        inode = NULL;
        if (delegated_inode) {
                error = break_deleg_wait(&delegated_inode);
                if (!error)
                        goto retry_deleg;
        }
        mnt_drop_write(path.mnt);
exit1:
        path_put(&path);
        putname(name);
        if (retry_estale(error, lookup_flags)) {
                lookup_flags |= LOOKUP_REVAL;
                inode = NULL;
                goto retry;
        }
        return error;

slashes:
        if (d_is_negative(dentry))
                error = -ENOENT;
        else if (d_is_dir(dentry))
                error = -EISDIR;
        else
                error = -ENOTDIR;
        goto exit2;
}

SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag)
{
        if ((flag & ~AT_REMOVEDIR) != 0)
                return -EINVAL;

        if (flag & AT_REMOVEDIR)
                return do_rmdir(dfd, pathname);

        return do_unlinkat(dfd, pathname);
}

SYSCALL_DEFINE1(unlink, const char __user *, pathname)
{
        return do_unlinkat(AT_FDCWD, pathname);
}

int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
{
        int error = may_create(dir, dentry);

        if (error)
                return error;

        if (!dir->i_op->symlink)
                return -EPERM;

        error = security_inode_symlink(dir, dentry, oldname);
        if (error)
                return error;

        error = dir->i_op->symlink(dir, dentry, oldname);
        if (!error)
                fsnotify_create(dir, dentry);
        return error;
}
EXPORT_SYMBOL(vfs_symlink);

SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
                int, newdfd, const char __user *, newname)
{
        int error;
        struct filename *from;
        struct dentry *dentry;
        struct path path;
        unsigned int lookup_flags = 0;

        from = getname(oldname);
        if (IS_ERR(from))
                return PTR_ERR(from);
retry:
        dentry = user_path_create(newdfd, newname, &path, lookup_flags);
        error = PTR_ERR(dentry);
        if (IS_ERR(dentry))
                goto out_putname;

        error = security_path_symlink(&path, dentry, from->name);
        if (!error)
                error = vfs_symlink(path.dentry->d_inode, dentry, from->name);
        done_path_create(&path, dentry);
        if (retry_estale(error, lookup_flags)) {
                lookup_flags |= LOOKUP_REVAL;
                goto retry;
        }
out_putname:
        putname(from);
        return error;
}

SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname)
{
        return sys_symlinkat(oldname, AT_FDCWD, newname);
}

/**
 * vfs_link - create a new link
 * @old_dentry: object to be linked
 * @dir:        new parent
 * @new_dentry: where to create the new link
 * @delegated_inode: returns inode needing a delegation break
 *
 * The caller must hold dir->i_mutex
 *
 * If vfs_link discovers a delegation on the to-be-linked file in need
 * of breaking, it will return -EWOULDBLOCK and return a reference to the
 * inode in delegated_inode.  The caller should then break the delegation
 * and retry.  Because breaking a delegation may take a long time, the
 * caller should drop the i_mutex before doing so.
 *
 * Alternatively, a caller may pass NULL for delegated_inode.  This may
 * be appropriate for callers that expect the underlying filesystem not
 * to be NFS exported.
 */
int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode)
{
        struct inode *inode = old_dentry->d_inode;
        unsigned max_links = dir->i_sb->s_max_links;
        int error;

        if (!inode)
                return -ENOENT;

        error = may_create(dir, new_dentry);
        if (error)
                return error;

        if (dir->i_sb != inode->i_sb)
                return -EXDEV;

        /*
         * A link to an append-only or immutable file cannot be created.
         */
        if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
                return -EPERM;
        if (!dir->i_op->link)
                return -EPERM;
        if (S_ISDIR(inode->i_mode))
                return -EPERM;

        error = security_inode_link(old_dentry, dir, new_dentry);
        if (error)
                return error;

        mutex_lock(&inode->i_mutex);
        /* Make sure we don't allow creating hardlink to an unlinked file */
        if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE))
                error =  -ENOENT;
        else if (max_links && inode->i_nlink >= max_links)
                error = -EMLINK;
        else {
                error = try_break_deleg(inode, delegated_inode);
                if (!error)
                        error = dir->i_op->link(old_dentry, dir, new_dentry);
        }

        if (!error && (inode->i_state & I_LINKABLE)) {
                spin_lock(&inode->i_lock);
                inode->i_state &= ~I_LINKABLE;
                spin_unlock(&inode->i_lock);
        }
        mutex_unlock(&inode->i_mutex);
        if (!error)
                fsnotify_link(dir, inode, new_dentry);
        return error;
}
EXPORT_SYMBOL(vfs_link);

/*
 * Hardlinks are often used in delicate situations.  We avoid
 * security-related surprises by not following symlinks on the
 * newname.  --KAB
 *
 * We don't follow them on the oldname either to be compatible
 * with linux 2.0, and to avoid hard-linking to directories
 * and other special files.  --ADM
 */
SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
                int, newdfd, const char __user *, newname, int, flags)
{
        struct dentry *new_dentry;
        struct path old_path, new_path;
        struct inode *delegated_inode = NULL;
        int how = 0;
        int error;

        if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
                return -EINVAL;
        /*
         * To use null names we require CAP_DAC_READ_SEARCH
         * This ensures that not everyone will be able to create
         * handlink using the passed filedescriptor.
         */
        if (flags & AT_EMPTY_PATH) {
                if (!capable(CAP_DAC_READ_SEARCH))
                        return -ENOENT;
                how = LOOKUP_EMPTY;
        }

        if (flags & AT_SYMLINK_FOLLOW)
                how |= LOOKUP_FOLLOW;
retry:
        error = user_path_at(olddfd, oldname, how, &old_path);
        if (error)
                return error;

        new_dentry = user_path_create(newdfd, newname, &new_path,
                                        (how & LOOKUP_REVAL));
        error = PTR_ERR(new_dentry);
        if (IS_ERR(new_dentry))
                goto out;

        error = -EXDEV;
        if (old_path.mnt != new_path.mnt)
                goto out_dput;
        error = may_linkat(&old_path);
        if (unlikely(error))
                goto out_dput;
        error = security_path_link(old_path.dentry, &new_path, new_dentry);
        if (error)
                goto out_dput;
        error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode);
out_dput:
        done_path_create(&new_path, new_dentry);
        if (delegated_inode) {
                error = break_deleg_wait(&delegated_inode);
                if (!error) {
                        path_put(&old_path);
                        goto retry;
                }
        }
        if (retry_estale(error, how)) {
                path_put(&old_path);
                how |= LOOKUP_REVAL;
                goto retry;
        }
out:
        path_put(&old_path);

        return error;
}

SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname)
{
        return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
}

/**
 * vfs_rename - rename a filesystem object
 * @old_dir:    parent of source
 * @old_dentry: source
 * @new_dir:    parent of destination
 * @new_dentry: destination
 * @delegated_inode: returns an inode needing a delegation break
 * @flags:      rename flags
 *
 * The caller must hold multiple mutexes--see lock_rename()).
 *
 * If vfs_rename discovers a delegation in need of breaking at either
 * the source or destination, it will return -EWOULDBLOCK and return a
 * reference to the inode in delegated_inode.  The caller should then
 * break the delegation and retry.  Because breaking a delegation may
 * take a long time, the caller should drop all locks before doing
 * so.
 *
 * Alternatively, a caller may pass NULL for delegated_inode.  This may
 * be appropriate for callers that expect the underlying filesystem not
 * to be NFS exported.
 *
 * The worst of all namespace operations - renaming directory. "Perverted"
 * doesn't even start to describe it. Somebody in UCB had a heck of a trip...
 * Problems:
 *      a) we can get into loop creation.
 *      b) race potential - two innocent renames can create a loop together.
 *         That's where 4.4 screws up. Current fix: serialization on
 *         sb->s_vfs_rename_mutex. We might be more accurate, but that's another
 *         story.
 *      c) we have to lock _four_ objects - parents and victim (if it exists),
 *         and source (if it is not a directory).
 *         And that - after we got ->i_mutex on parents (until then we don't know
 *         whether the target exists).  Solution: try to be smart with locking
 *         order for inodes.  We rely on the fact that tree topology may change
 *         only under ->s_vfs_rename_mutex _and_ that parent of the object we
 *         move will be locked.  Thus we can rank directories by the tree
 *         (ancestors first) and rank all non-directories after them.
 *         That works since everybody except rename does "lock parent, lookup,
 *         lock child" and rename is under ->s_vfs_rename_mutex.
 *         HOWEVER, it relies on the assumption that any object with ->lookup()
 *         has no more than 1 dentry.  If "hybrid" objects will ever appear,
 *         we'd better make sure that there's no link(2) for them.
 *      d) conversion from fhandle to dentry may come in the wrong moment - when
 *         we are removing the target. Solution: we will have to grab ->i_mutex
 *         in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on
 *         ->i_mutex on parents, which works but leads to some truly excessive
 *         locking].
 */
int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
               struct inode *new_dir, struct dentry *new_dentry,
               struct inode **delegated_inode, unsigned int flags)
{
        int error;
        bool is_dir = d_is_dir(old_dentry);
        const unsigned char *old_name;
        struct inode *source = old_dentry->d_inode;
        struct inode *target = new_dentry->d_inode;
        bool new_is_dir = false;
        unsigned max_links = new_dir->i_sb->s_max_links;

        if (source == target)
                return 0;

        error = may_delete(old_dir, old_dentry, is_dir);
        if (error)
                return error;

        if (!target) {
                error = may_create(new_dir, new_dentry);
        } else {
                new_is_dir = d_is_dir(new_dentry);

                if (!(flags & RENAME_EXCHANGE))
                        error = may_delete(new_dir, new_dentry, is_dir);
                else
                        error = may_delete(new_dir, new_dentry, new_is_dir);
        }
        if (error)
                return error;

        if (!old_dir->i_op->rename && !old_dir->i_op->rename2)
                return -EPERM;

        if (flags && !old_dir->i_op->rename2)
                return -EINVAL;

        /*
         * If we are going to change the parent - check write permissions,
         * we'll need to flip '..'.
         */
        if (new_dir != old_dir) {
                if (is_dir) {
                        error = inode_permission(source, MAY_WRITE);
                        if (error)
                                return error;
                }
                if ((flags & RENAME_EXCHANGE) && new_is_dir) {
                        error = inode_permission(target, MAY_WRITE);
                        if (error)
                                return error;
                }
        }

        error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry,
                                      flags);
        if (error)
                return error;

        old_name = fsnotify_oldname_init(old_dentry->d_name.name);
        dget(new_dentry);
        if (!is_dir || (flags & RENAME_EXCHANGE))
                lock_two_nondirectories(source, target);
        else if (target)
                mutex_lock(&target->i_mutex);

        error = -EBUSY;
        if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry))
                goto out;

        if (max_links && new_dir != old_dir) {
                error = -EMLINK;
                if (is_dir && !new_is_dir && new_dir->i_nlink >= max_links)
                        goto out;
                if ((flags & RENAME_EXCHANGE) && !is_dir && new_is_dir &&
                    old_dir->i_nlink >= max_links)
                        goto out;
        }
        if (is_dir && !(flags & RENAME_EXCHANGE) && target)
                shrink_dcache_parent(new_dentry);
        if (!is_dir) {
                error = try_break_deleg(source, delegated_inode);
                if (error)
                        goto out;
        }
        if (target && !new_is_dir) {
                error = try_break_deleg(target, delegated_inode);
                if (error)
                        goto out;
        }
        if (!old_dir->i_op->rename2) {
                error = old_dir->i_op->rename(old_dir, old_dentry,
                                              new_dir, new_dentry);
        } else {
                WARN_ON(old_dir->i_op->rename != NULL);
                error = old_dir->i_op->rename2(old_dir, old_dentry,
                                               new_dir, new_dentry, flags);
        }
        if (error)
                goto out;

        if (!(flags & RENAME_EXCHANGE) && target) {
                if (is_dir)
                        target->i_flags |= S_DEAD;
                dont_mount(new_dentry);
                detach_mounts(new_dentry);
        }
        if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) {
                if (!(flags & RENAME_EXCHANGE))
                        d_move(old_dentry, new_dentry);
                else
                        d_exchange(old_dentry, new_dentry);
        }
out:
        if (!is_dir || (flags & RENAME_EXCHANGE))
                unlock_two_nondirectories(source, target);
        else if (target)
                mutex_unlock(&target->i_mutex);
        dput(new_dentry);
        if (!error) {
                fsnotify_move(old_dir, new_dir, old_name, is_dir,
                              !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry);
                if (flags & RENAME_EXCHANGE) {
                        fsnotify_move(new_dir, old_dir, old_dentry->d_name.name,
                                      new_is_dir, NULL, new_dentry);
                }
        }
        fsnotify_oldname_free(old_name);

        return error;
}
EXPORT_SYMBOL(vfs_rename);

SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
                int, newdfd, const char __user *, newname, unsigned int, flags)
{
        struct dentry *old_dentry, *new_dentry;
        struct dentry *trap;
        struct path old_path, new_path;
        struct qstr old_last, new_last;
        int old_type, new_type;
        struct inode *delegated_inode = NULL;
        struct filename *from;
        struct filename *to;
        unsigned int lookup_flags = 0, target_flags = LOOKUP_RENAME_TARGET;
        bool should_retry = false;
        int error;

        if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
                return -EINVAL;

        if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) &&
            (flags & RENAME_EXCHANGE))
                return -EINVAL;

        if ((flags & RENAME_WHITEOUT) && !capable(CAP_MKNOD))
                return -EPERM;

        if (flags & RENAME_EXCHANGE)
                target_flags = 0;

retry:
        from = user_path_parent(olddfd, oldname,
                                &old_path, &old_last, &old_type, lookup_flags);
        if (IS_ERR(from)) {
                error = PTR_ERR(from);
                goto exit;
        }

        to = user_path_parent(newdfd, newname,
                                &new_path, &new_last, &new_type, lookup_flags);
        if (IS_ERR(to)) {
                error = PTR_ERR(to);
                goto exit1;
        }

        error = -EXDEV;
        if (old_path.mnt != new_path.mnt)
                goto exit2;

        error = -EBUSY;
        if (old_type != LAST_NORM)
                goto exit2;

        if (flags & RENAME_NOREPLACE)
                error = -EEXIST;
        if (new_type != LAST_NORM)
                goto exit2;

        error = mnt_want_write(old_path.mnt);
        if (error)
                goto exit2;

retry_deleg:
        trap = lock_rename(new_path.dentry, old_path.dentry);

        old_dentry = __lookup_hash(&old_last, old_path.dentry, lookup_flags);
        error = PTR_ERR(old_dentry);
        if (IS_ERR(old_dentry))
                goto exit3;
        /* source must exist */
        error = -ENOENT;
        if (d_is_negative(old_dentry))
                goto exit4;
        new_dentry = __lookup_hash(&new_last, new_path.dentry, lookup_flags | target_flags);
        error = PTR_ERR(new_dentry);
        if (IS_ERR(new_dentry))
                goto exit4;
        error = -EEXIST;
        if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry))
                goto exit5;
        if (flags & RENAME_EXCHANGE) {
                error = -ENOENT;
                if (d_is_negative(new_dentry))
                        goto exit5;

                if (!d_is_dir(new_dentry)) {
                        error = -ENOTDIR;
                        if (new_last.name[new_last.len])
                                goto exit5;
                }
        }
        /* unless the source is a directory trailing slashes give -ENOTDIR */
        if (!d_is_dir(old_dentry)) {
                error = -ENOTDIR;
                if (old_last.name[old_last.len])
                        goto exit5;
                if (!(flags & RENAME_EXCHANGE) && new_last.name[new_last.len])
                        goto exit5;
        }
        /* source should not be ancestor of target */
        error = -EINVAL;
        if (old_dentry == trap)
                goto exit5;
        /* target should not be an ancestor of source */
        if (!(flags & RENAME_EXCHANGE))
                error = -ENOTEMPTY;
        if (new_dentry == trap)
                goto exit5;

        error = security_path_rename(&old_path, old_dentry,
                                     &new_path, new_dentry, flags);
        if (error)
                goto exit5;
        error = vfs_rename(old_path.dentry->d_inode, old_dentry,
                           new_path.dentry->d_inode, new_dentry,
                           &delegated_inode, flags);
exit5:
        dput(new_dentry);
exit4:
        dput(old_dentry);
exit3:
        unlock_rename(new_path.dentry, old_path.dentry);
        if (delegated_inode) {
                error = break_deleg_wait(&delegated_inode);
                if (!error)
                        goto retry_deleg;
        }
        mnt_drop_write(old_path.mnt);
exit2:
        if (retry_estale(error, lookup_flags))
                should_retry = true;
        path_put(&new_path);
        putname(to);
exit1:
        path_put(&old_path);
        putname(from);
        if (should_retry) {
                should_retry = false;
                lookup_flags |= LOOKUP_REVAL;
                goto retry;
        }
exit:
        return error;
}

SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
                int, newdfd, const char __user *, newname)
{
        return sys_renameat2(olddfd, oldname, newdfd, newname, 0);
}

SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname)
{
        return sys_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
}

int vfs_whiteout(struct inode *dir, struct dentry *dentry)
{
        int error = may_create(dir, dentry);
        if (error)
                return error;

        if (!dir->i_op->mknod)
                return -EPERM;

        return dir->i_op->mknod(dir, dentry,
                                S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV);
}
EXPORT_SYMBOL(vfs_whiteout);

int readlink_copy(char __user *buffer, int buflen, const char *link)
{
        int len = PTR_ERR(link);
        if (IS_ERR(link))
                goto out;

        len = strlen(link);
        if (len > (unsigned) buflen)
                len = buflen;
        if (copy_to_user(buffer, link, len))
                len = -EFAULT;
out:
        return len;
}
EXPORT_SYMBOL(readlink_copy);

/*
 * A helper for ->readlink().  This should be used *ONLY* for symlinks that
 * have ->follow_link() touching nd only in nd_set_link().  Using (or not
 * using) it for any given inode is up to filesystem.
 */
int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen)
{
        void *cookie;
        const char *link = dentry->d_inode->i_link;
        int res;

        if (!link) {
                link = dentry->d_inode->i_op->follow_link(dentry, &cookie, NULL);
                if (IS_ERR(link))
                        return PTR_ERR(link);
        }
        res = readlink_copy(buffer, buflen, link);
        if (cookie && dentry->d_inode->i_op->put_link)
                dentry->d_inode->i_op->put_link(dentry, cookie);
        return res;
}
EXPORT_SYMBOL(generic_readlink);

/* get the link contents into pagecache */
static char *page_getlink(struct dentry * dentry, struct page **ppage)
{
        char *kaddr;
        struct page *page;
        struct address_space *mapping = dentry->d_inode->i_mapping;
        page = read_mapping_page(mapping, 0, NULL);
        if (IS_ERR(page))
                return (char*)page;
        *ppage = page;
        kaddr = kmap(page);
        nd_terminate_link(kaddr, dentry->d_inode->i_size, PAGE_SIZE - 1);
        return kaddr;
}

int page_readlink(struct dentry *dentry, char __user *buffer, int buflen)
{
        struct page *page = NULL;
        int res = readlink_copy(buffer, buflen, page_getlink(dentry, &page));
        if (page) {
                kunmap(page);
                page_cache_release(page);
        }
        return res;
}
EXPORT_SYMBOL(page_readlink);

const char *page_follow_link_light(struct dentry *dentry, void **cookie, struct nameidata *nd)
{
        struct page *page = NULL;
        char *res = page_getlink(dentry, &page);
        if (!IS_ERR(res))
                *cookie = page;
        return res;
}
EXPORT_SYMBOL(page_follow_link_light);

void page_put_link(struct dentry *dentry, void *cookie)
{
        struct page *page = cookie;
        kunmap(page);
        page_cache_release(page);
}
EXPORT_SYMBOL(page_put_link);

/*
 * The nofs argument instructs pagecache_write_begin to pass AOP_FLAG_NOFS
 */
int __page_symlink(struct inode *inode, const char *symname, int len, int nofs)
{
        struct address_space *mapping = inode->i_mapping;
        struct page *page;
        void *fsdata;
        int err;
        char *kaddr;
        unsigned int flags = AOP_FLAG_UNINTERRUPTIBLE;
        if (nofs)
                flags |= AOP_FLAG_NOFS;

retry:
        err = pagecache_write_begin(NULL, mapping, 0, len-1,
                                flags, &page, &fsdata);
        if (err)
                goto fail;

        kaddr = kmap_atomic(page);
        memcpy(kaddr, symname, len-1);
        kunmap_atomic(kaddr);

        err = pagecache_write_end(NULL, mapping, 0, len-1, len-1,
                                                        page, fsdata);
        if (err < 0)
                goto fail;
        if (err < len-1)
                goto retry;

        mark_inode_dirty(inode);
        return 0;
fail:
        return err;
}
EXPORT_SYMBOL(__page_symlink);

int page_symlink(struct inode *inode, const char *symname, int len)
{
        return __page_symlink(inode, symname, len,
                        !(mapping_gfp_mask(inode->i_mapping) & __GFP_FS));
}
EXPORT_SYMBOL(page_symlink);

const struct inode_operations page_symlink_inode_operations = {
        .readlink       = generic_readlink,
        .follow_link    = page_follow_link_light,
        .put_link       = page_put_link,
};
EXPORT_SYMBOL(page_symlink_inode_operations);