/*
 *  Server-side procedures for NFSv4.
 *
 *  Copyright (c) 2002 The Regents of the University of Michigan.
 *  All rights reserved.
 *
 *  Kendrick Smith <kmsmith@umich.edu>
 *  Andy Adamson   <andros@umich.edu>
 *
 *  Redistribution and use in source and binary forms, with or without
 *  modification, are permitted provided that the following conditions
 *  are met:
 *
 *  1. Redistributions of source code must retain the above copyright
 *     notice, this list of conditions and the following disclaimer.
 *  2. Redistributions in binary form must reproduce the above copyright
 *     notice, this list of conditions and the following disclaimer in the
 *     documentation and/or other materials provided with the distribution.
 *  3. Neither the name of the University nor the names of its
 *     contributors may be used to endorse or promote products derived
 *     from this software without specific prior written permission.
 *
 *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
 *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
 *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
 *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
 *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
 *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
 *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */
#include <linux/fs_struct.h>
#include <linux/file.h>
#include <linux/falloc.h>
#include <linux/slab.h>
#include <linux/kthread.h>
#include <linux/sunrpc/addr.h>
#include <linux/nfs_ssc.h>

#include "idmap.h"
#include "cache.h"
#include "xdr4.h"
#include "vfs.h"
#include "current_stateid.h"
#include "netns.h"
#include "acl.h"
#include "pnfs.h"
#include "trace.h"

static bool inter_copy_offload_enable;
module_param(inter_copy_offload_enable, bool, 0644);
MODULE_PARM_DESC(inter_copy_offload_enable,
                 "Enable inter server to server copy offload. Default: false");

#ifdef CONFIG_NFSD_V4_2_INTER_SSC
static int nfsd4_ssc_umount_timeout = 900000;           /* default to 15 mins */
module_param(nfsd4_ssc_umount_timeout, int, 0644);
MODULE_PARM_DESC(nfsd4_ssc_umount_timeout,
                "idle msecs before unmount export from source server");
#endif

#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
#include <linux/security.h>

static inline void
nfsd4_security_inode_setsecctx(struct svc_fh *resfh, struct xdr_netobj *label, u32 *bmval)
{
        struct inode *inode = d_inode(resfh->fh_dentry);
        int status;

        inode_lock(inode);
        status = security_inode_setsecctx(resfh->fh_dentry,
                label->data, label->len);
        inode_unlock(inode);

        if (status)
                /*
                 * XXX: We should really fail the whole open, but we may
                 * already have created a new file, so it may be too
                 * late.  For now this seems the least of evils:
                 */
                bmval[2] &= ~FATTR4_WORD2_SECURITY_LABEL;

        return;
}
#else
static inline void
nfsd4_security_inode_setsecctx(struct svc_fh *resfh, struct xdr_netobj *label, u32 *bmval)
{ }
#endif

#define NFSDDBG_FACILITY                NFSDDBG_PROC

static u32 nfsd_attrmask[] = {
        NFSD_WRITEABLE_ATTRS_WORD0,
        NFSD_WRITEABLE_ATTRS_WORD1,
        NFSD_WRITEABLE_ATTRS_WORD2
};

static u32 nfsd41_ex_attrmask[] = {
        NFSD_SUPPATTR_EXCLCREAT_WORD0,
        NFSD_SUPPATTR_EXCLCREAT_WORD1,
        NFSD_SUPPATTR_EXCLCREAT_WORD2
};

static __be32
check_attr_support(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                   u32 *bmval, u32 *writable)
{
        struct dentry *dentry = cstate->current_fh.fh_dentry;
        struct svc_export *exp = cstate->current_fh.fh_export;

        if (!nfsd_attrs_supported(cstate->minorversion, bmval))
                return nfserr_attrnotsupp;
        if ((bmval[0] & FATTR4_WORD0_ACL) && !IS_POSIXACL(d_inode(dentry)))
                return nfserr_attrnotsupp;
        if ((bmval[2] & FATTR4_WORD2_SECURITY_LABEL) &&
                        !(exp->ex_flags & NFSEXP_SECURITY_LABEL))
                return nfserr_attrnotsupp;
        if (writable && !bmval_is_subset(bmval, writable))
                return nfserr_inval;
        if (writable && (bmval[2] & FATTR4_WORD2_MODE_UMASK) &&
                        (bmval[1] & FATTR4_WORD1_MODE))
                return nfserr_inval;
        return nfs_ok;
}

static __be32
nfsd4_check_open_attributes(struct svc_rqst *rqstp,
        struct nfsd4_compound_state *cstate, struct nfsd4_open *open)
{
        __be32 status = nfs_ok;

        if (open->op_create == NFS4_OPEN_CREATE) {
                if (open->op_createmode == NFS4_CREATE_UNCHECKED
                    || open->op_createmode == NFS4_CREATE_GUARDED)
                        status = check_attr_support(rqstp, cstate,
                                        open->op_bmval, nfsd_attrmask);
                else if (open->op_createmode == NFS4_CREATE_EXCLUSIVE4_1)
                        status = check_attr_support(rqstp, cstate,
                                        open->op_bmval, nfsd41_ex_attrmask);
        }

        return status;
}

static int
is_create_with_attrs(struct nfsd4_open *open)
{
        return open->op_create == NFS4_OPEN_CREATE
                && (open->op_createmode == NFS4_CREATE_UNCHECKED
                    || open->op_createmode == NFS4_CREATE_GUARDED
                    || open->op_createmode == NFS4_CREATE_EXCLUSIVE4_1);
}

/*
 * if error occurs when setting the acl, just clear the acl bit
 * in the returned attr bitmap.
 */
static void
do_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
                struct nfs4_acl *acl, u32 *bmval)
{
        __be32 status;

        status = nfsd4_set_nfs4_acl(rqstp, fhp, acl);
        if (status)
                /*
                 * We should probably fail the whole open at this point,
                 * but we've already created the file, so it's too late;
                 * So this seems the least of evils:
                 */
                bmval[0] &= ~FATTR4_WORD0_ACL;
}

static inline void
fh_dup2(struct svc_fh *dst, struct svc_fh *src)
{
        fh_put(dst);
        dget(src->fh_dentry);
        if (src->fh_export)
                exp_get(src->fh_export);
        *dst = *src;
}

static __be32
do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open, int accmode)
{
        __be32 status;

        if (open->op_truncate &&
                !(open->op_share_access & NFS4_SHARE_ACCESS_WRITE))
                return nfserr_inval;

        accmode |= NFSD_MAY_READ_IF_EXEC;

        if (open->op_share_access & NFS4_SHARE_ACCESS_READ)
                accmode |= NFSD_MAY_READ;
        if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
                accmode |= (NFSD_MAY_WRITE | NFSD_MAY_TRUNC);
        if (open->op_share_deny & NFS4_SHARE_DENY_READ)
                accmode |= NFSD_MAY_WRITE;

        status = fh_verify(rqstp, current_fh, S_IFREG, accmode);

        return status;
}

static __be32 nfsd_check_obj_isreg(struct svc_fh *fh)
{
        umode_t mode = d_inode(fh->fh_dentry)->i_mode;

        if (S_ISREG(mode))
                return nfs_ok;
        if (S_ISDIR(mode))
                return nfserr_isdir;
        /*
         * Using err_symlink as our catch-all case may look odd; but
         * there's no other obvious error for this case in 4.0, and we
         * happen to know that it will cause the linux v4 client to do
         * the right thing on attempts to open something other than a
         * regular file.
         */
        return nfserr_symlink;
}

static void nfsd4_set_open_owner_reply_cache(struct nfsd4_compound_state *cstate, struct nfsd4_open *open, struct svc_fh *resfh)
{
        if (nfsd4_has_session(cstate))
                return;
        fh_copy_shallow(&open->op_openowner->oo_owner.so_replay.rp_openfh,
                        &resfh->fh_handle);
}

static __be32
do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open, struct svc_fh **resfh)
{
        struct svc_fh *current_fh = &cstate->current_fh;
        int accmode;
        __be32 status;

        *resfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL);
        if (!*resfh)
                return nfserr_jukebox;
        fh_init(*resfh, NFS4_FHSIZE);
        open->op_truncate = false;

        if (open->op_create) {
                /* FIXME: check session persistence and pnfs flags.
                 * The nfsv4.1 spec requires the following semantics:
                 *
                 * Persistent   | pNFS   | Server REQUIRED | Client Allowed
                 * Reply Cache  | server |                 |
                 * -------------+--------+-----------------+--------------------
                 * no           | no     | EXCLUSIVE4_1    | EXCLUSIVE4_1
                 *              |        |                 | (SHOULD)
                 *              |        | and EXCLUSIVE4  | or EXCLUSIVE4
                 *              |        |                 | (SHOULD NOT)
                 * no           | yes    | EXCLUSIVE4_1    | EXCLUSIVE4_1
                 * yes          | no     | GUARDED4        | GUARDED4
                 * yes          | yes    | GUARDED4        | GUARDED4
                 */

                /*
                 * Note: create modes (UNCHECKED,GUARDED...) are the same
                 * in NFSv4 as in v3 except EXCLUSIVE4_1.
                 */
                current->fs->umask = open->op_umask;
                status = do_nfsd_create(rqstp, current_fh, open->op_fname,
                                        open->op_fnamelen, &open->op_iattr,
                                        *resfh, open->op_createmode,
                                        (u32 *)open->op_verf.data,
                                        &open->op_truncate, &open->op_created);
                current->fs->umask = 0;

                if (!status && open->op_label.len)
                        nfsd4_security_inode_setsecctx(*resfh, &open->op_label, open->op_bmval);

                /*
                 * Following rfc 3530 14.2.16, and rfc 5661 18.16.4
                 * use the returned bitmask to indicate which attributes
                 * we used to store the verifier:
                 */
                if (nfsd_create_is_exclusive(open->op_createmode) && status == 0)
                        open->op_bmval[1] |= (FATTR4_WORD1_TIME_ACCESS |
                                                FATTR4_WORD1_TIME_MODIFY);
        } else
                /*
                 * Note this may exit with the parent still locked.
                 * We will hold the lock until nfsd4_open's final
                 * lookup, to prevent renames or unlinks until we've had
                 * a chance to an acquire a delegation if appropriate.
                 */
                status = nfsd_lookup(rqstp, current_fh,
                                     open->op_fname, open->op_fnamelen, *resfh);
        if (status)
                goto out;
        status = nfsd_check_obj_isreg(*resfh);
        if (status)
                goto out;

        if (is_create_with_attrs(open) && open->op_acl != NULL)
                do_set_nfs4_acl(rqstp, *resfh, open->op_acl, open->op_bmval);

        nfsd4_set_open_owner_reply_cache(cstate, open, *resfh);
        accmode = NFSD_MAY_NOP;
        if (open->op_created ||
                        open->op_claim_type == NFS4_OPEN_CLAIM_DELEGATE_CUR)
                accmode |= NFSD_MAY_OWNER_OVERRIDE;
        status = do_open_permission(rqstp, *resfh, open, accmode);
        set_change_info(&open->op_cinfo, current_fh);
out:
        return status;
}

static __be32
do_open_fhandle(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open)
{
        struct svc_fh *current_fh = &cstate->current_fh;
        __be32 status;
        int accmode = 0;

        /* We don't know the target directory, and therefore can not
        * set the change info
        */

        memset(&open->op_cinfo, 0, sizeof(struct nfsd4_change_info));

        nfsd4_set_open_owner_reply_cache(cstate, open, current_fh);

        open->op_truncate = (open->op_iattr.ia_valid & ATTR_SIZE) &&
                (open->op_iattr.ia_size == 0);
        /*
         * In the delegation case, the client is telling us about an
         * open that it *already* performed locally, some time ago.  We
         * should let it succeed now if possible.
         *
         * In the case of a CLAIM_FH open, on the other hand, the client
         * may be counting on us to enforce permissions (the Linux 4.1
         * client uses this for normal opens, for example).
         */
        if (open->op_claim_type == NFS4_OPEN_CLAIM_DELEG_CUR_FH)
                accmode = NFSD_MAY_OWNER_OVERRIDE;

        status = do_open_permission(rqstp, current_fh, open, accmode);

        return status;
}

static void
copy_clientid(clientid_t *clid, struct nfsd4_session *session)
{
        struct nfsd4_sessionid *sid =
                        (struct nfsd4_sessionid *)session->se_sessionid.data;

        clid->cl_boot = sid->clientid.cl_boot;
        clid->cl_id = sid->clientid.cl_id;
}

static __be32
nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
           union nfsd4_op_u *u)
{
        struct nfsd4_open *open = &u->open;
        __be32 status;
        struct svc_fh *resfh = NULL;
        struct net *net = SVC_NET(rqstp);
        struct nfsd_net *nn = net_generic(net, nfsd_net_id);
        bool reclaim = false;

        dprintk("NFSD: nfsd4_open filename %.*s op_openowner %p\n",
                (int)open->op_fnamelen, open->op_fname,
                open->op_openowner);

        /* This check required by spec. */
        if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL)
                return nfserr_inval;

        open->op_created = false;
        /*
         * RFC5661 18.51.3
         * Before RECLAIM_COMPLETE done, server should deny new lock
         */
        if (nfsd4_has_session(cstate) &&
            !test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &cstate->clp->cl_flags) &&
            open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
                return nfserr_grace;

        if (nfsd4_has_session(cstate))
                copy_clientid(&open->op_clientid, cstate->session);

        /* check seqid for replay. set nfs4_owner */
        status = nfsd4_process_open1(cstate, open, nn);
        if (status == nfserr_replay_me) {
                struct nfs4_replay *rp = &open->op_openowner->oo_owner.so_replay;
                fh_put(&cstate->current_fh);
                fh_copy_shallow(&cstate->current_fh.fh_handle,
                                &rp->rp_openfh);
                status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
                if (status)
                        dprintk("nfsd4_open: replay failed"
                                " restoring previous filehandle\n");
                else
                        status = nfserr_replay_me;
        }
        if (status)
                goto out;
        if (open->op_xdr_error) {
                status = open->op_xdr_error;
                goto out;
        }

        status = nfsd4_check_open_attributes(rqstp, cstate, open);
        if (status)
                goto out;

        /* Openowner is now set, so sequence id will get bumped.  Now we need
         * these checks before we do any creates: */
        status = nfserr_grace;
        if (opens_in_grace(net) && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
                goto out;
        status = nfserr_no_grace;
        if (!opens_in_grace(net) && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
                goto out;

        switch (open->op_claim_type) {
                case NFS4_OPEN_CLAIM_DELEGATE_CUR:
                case NFS4_OPEN_CLAIM_NULL:
                        status = do_open_lookup(rqstp, cstate, open, &resfh);
                        if (status)
                                goto out;
                        break;
                case NFS4_OPEN_CLAIM_PREVIOUS:
                        status = nfs4_check_open_reclaim(cstate->clp);
                        if (status)
                                goto out;
                        open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
                        reclaim = true;
                        fallthrough;
                case NFS4_OPEN_CLAIM_FH:
                case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
                        status = do_open_fhandle(rqstp, cstate, open);
                        if (status)
                                goto out;
                        resfh = &cstate->current_fh;
                        break;
                case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
                case NFS4_OPEN_CLAIM_DELEGATE_PREV:
                        dprintk("NFSD: unsupported OPEN claim type %d\n",
                                open->op_claim_type);
                        status = nfserr_notsupp;
                        goto out;
                default:
                        dprintk("NFSD: Invalid OPEN claim type %d\n",
                                open->op_claim_type);
                        status = nfserr_inval;
                        goto out;
        }
        /*
         * nfsd4_process_open2() does the actual opening of the file.  If
         * successful, it (1) truncates the file if open->op_truncate was
         * set, (2) sets open->op_stateid, (3) sets open->op_delegation.
         */
        status = nfsd4_process_open2(rqstp, resfh, open);
        WARN(status && open->op_created,
             "nfsd4_process_open2 failed to open newly-created file! status=%u\n",
             be32_to_cpu(status));
        if (reclaim && !status)
                nn->somebody_reclaimed = true;
out:
        if (resfh && resfh != &cstate->current_fh) {
                fh_dup2(&cstate->current_fh, resfh);
                fh_put(resfh);
                kfree(resfh);
        }
        nfsd4_cleanup_open_state(cstate, open);
        nfsd4_bump_seqid(cstate, status);
        return status;
}

/*
 * OPEN is the only seqid-mutating operation whose decoding can fail
 * with a seqid-mutating error (specifically, decoding of user names in
 * the attributes).  Therefore we have to do some processing to look up
 * the stateowner so that we can bump the seqid.
 */
static __be32 nfsd4_open_omfg(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_op *op)
{
        struct nfsd4_open *open = &op->u.open;

        if (!seqid_mutating_err(ntohl(op->status)))
                return op->status;
        if (nfsd4_has_session(cstate))
                return op->status;
        open->op_xdr_error = op->status;
        return nfsd4_open(rqstp, cstate, &op->u);
}

/*
 * filehandle-manipulating ops.
 */
static __be32
nfsd4_getfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
            union nfsd4_op_u *u)
{
        u->getfh = &cstate->current_fh;
        return nfs_ok;
}

static __be32
nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
            union nfsd4_op_u *u)
{
        struct nfsd4_putfh *putfh = &u->putfh;
        __be32 ret;

        fh_put(&cstate->current_fh);
        cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen;
        memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval,
               putfh->pf_fhlen);
        ret = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_BYPASS_GSS);
#ifdef CONFIG_NFSD_V4_2_INTER_SSC
        if (ret == nfserr_stale && putfh->no_verify) {
                SET_FH_FLAG(&cstate->current_fh, NFSD4_FH_FOREIGN);
                ret = 0;
        }
#endif
        return ret;
}

static __be32
nfsd4_putrootfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                union nfsd4_op_u *u)
{
        __be32 status;

        fh_put(&cstate->current_fh);
        status = exp_pseudoroot(rqstp, &cstate->current_fh);
        return status;
}

static __be32
nfsd4_restorefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                union nfsd4_op_u *u)
{
        if (!cstate->save_fh.fh_dentry)
                return nfserr_restorefh;

        fh_dup2(&cstate->current_fh, &cstate->save_fh);
        if (HAS_CSTATE_FLAG(cstate, SAVED_STATE_ID_FLAG)) {
                memcpy(&cstate->current_stateid, &cstate->save_stateid, sizeof(stateid_t));
                SET_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG);
        }
        return nfs_ok;
}

static __be32
nfsd4_savefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
             union nfsd4_op_u *u)
{
        fh_dup2(&cstate->save_fh, &cstate->current_fh);
        if (HAS_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG)) {
                memcpy(&cstate->save_stateid, &cstate->current_stateid, sizeof(stateid_t));
                SET_CSTATE_FLAG(cstate, SAVED_STATE_ID_FLAG);
        }
        return nfs_ok;
}

/*
 * misc nfsv4 ops
 */
static __be32
nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
             union nfsd4_op_u *u)
{
        struct nfsd4_access *access = &u->access;
        u32 access_full;

        access_full = NFS3_ACCESS_FULL;
        if (cstate->minorversion >= 2)
                access_full |= NFS4_ACCESS_XALIST | NFS4_ACCESS_XAREAD |
                               NFS4_ACCESS_XAWRITE;

        if (access->ac_req_access & ~access_full)
                return nfserr_inval;

        access->ac_resp_access = access->ac_req_access;
        return nfsd_access(rqstp, &cstate->current_fh, &access->ac_resp_access,
                           &access->ac_supported);
}

static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net)
{
        __be32 *verf = (__be32 *)verifier->data;

        BUILD_BUG_ON(2*sizeof(*verf) != sizeof(verifier->data));

        nfsd_copy_boot_verifier(verf, net_generic(net, nfsd_net_id));
}

static __be32
nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
             union nfsd4_op_u *u)
{
        struct nfsd4_commit *commit = &u->commit;

        return nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset,
                             commit->co_count,
                             (__be32 *)commit->co_verf.data);
}

static __be32
nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
             union nfsd4_op_u *u)
{
        struct nfsd4_create *create = &u->create;
        struct svc_fh resfh;
        __be32 status;
        dev_t rdev;

        fh_init(&resfh, NFS4_FHSIZE);

        status = fh_verify(rqstp, &cstate->current_fh, S_IFDIR, NFSD_MAY_NOP);
        if (status)
                return status;

        status = check_attr_support(rqstp, cstate, create->cr_bmval,
                                    nfsd_attrmask);
        if (status)
                return status;

        current->fs->umask = create->cr_umask;
        switch (create->cr_type) {
        case NF4LNK:
                status = nfsd_symlink(rqstp, &cstate->current_fh,
                                      create->cr_name, create->cr_namelen,
                                      create->cr_data, &resfh);
                break;

        case NF4BLK:
                status = nfserr_inval;
                rdev = MKDEV(create->cr_specdata1, create->cr_specdata2);
                if (MAJOR(rdev) != create->cr_specdata1 ||
                    MINOR(rdev) != create->cr_specdata2)
                        goto out_umask;
                status = nfsd_create(rqstp, &cstate->current_fh,
                                     create->cr_name, create->cr_namelen,
                                     &create->cr_iattr, S_IFBLK, rdev, &resfh);
                break;

        case NF4CHR:
                status = nfserr_inval;
                rdev = MKDEV(create->cr_specdata1, create->cr_specdata2);
                if (MAJOR(rdev) != create->cr_specdata1 ||
                    MINOR(rdev) != create->cr_specdata2)
                        goto out_umask;
                status = nfsd_create(rqstp, &cstate->current_fh,
                                     create->cr_name, create->cr_namelen,
                                     &create->cr_iattr,S_IFCHR, rdev, &resfh);
                break;

        case NF4SOCK:
                status = nfsd_create(rqstp, &cstate->current_fh,
                                     create->cr_name, create->cr_namelen,
                                     &create->cr_iattr, S_IFSOCK, 0, &resfh);
                break;

        case NF4FIFO:
                status = nfsd_create(rqstp, &cstate->current_fh,
                                     create->cr_name, create->cr_namelen,
                                     &create->cr_iattr, S_IFIFO, 0, &resfh);
                break;

        case NF4DIR:
                create->cr_iattr.ia_valid &= ~ATTR_SIZE;
                status = nfsd_create(rqstp, &cstate->current_fh,
                                     create->cr_name, create->cr_namelen,
                                     &create->cr_iattr, S_IFDIR, 0, &resfh);
                break;

        default:
                status = nfserr_badtype;
        }

        if (status)
                goto out;

        if (create->cr_label.len)
                nfsd4_security_inode_setsecctx(&resfh, &create->cr_label, create->cr_bmval);

        if (create->cr_acl != NULL)
                do_set_nfs4_acl(rqstp, &resfh, create->cr_acl,
                                create->cr_bmval);

        fh_unlock(&cstate->current_fh);
        set_change_info(&create->cr_cinfo, &cstate->current_fh);
        fh_dup2(&cstate->current_fh, &resfh);
out:
        fh_put(&resfh);
out_umask:
        current->fs->umask = 0;
        return status;
}

static __be32
nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
              union nfsd4_op_u *u)
{
        struct nfsd4_getattr *getattr = &u->getattr;
        __be32 status;

        status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
        if (status)
                return status;

        if (getattr->ga_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1)
                return nfserr_inval;

        getattr->ga_bmval[0] &= nfsd_suppattrs[cstate->minorversion][0];
        getattr->ga_bmval[1] &= nfsd_suppattrs[cstate->minorversion][1];
        getattr->ga_bmval[2] &= nfsd_suppattrs[cstate->minorversion][2];

        getattr->ga_fhp = &cstate->current_fh;
        return nfs_ok;
}

static __be32
nfsd4_link(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
           union nfsd4_op_u *u)
{
        struct nfsd4_link *link = &u->link;
        __be32 status;

        status = nfsd_link(rqstp, &cstate->current_fh,
                           link->li_name, link->li_namelen, &cstate->save_fh);
        if (!status)
                set_change_info(&link->li_cinfo, &cstate->current_fh);
        return status;
}

static __be32 nfsd4_do_lookupp(struct svc_rqst *rqstp, struct svc_fh *fh)
{
        struct svc_fh tmp_fh;
        __be32 ret;

        fh_init(&tmp_fh, NFS4_FHSIZE);
        ret = exp_pseudoroot(rqstp, &tmp_fh);
        if (ret)
                return ret;
        if (tmp_fh.fh_dentry == fh->fh_dentry) {
                fh_put(&tmp_fh);
                return nfserr_noent;
        }
        fh_put(&tmp_fh);
        return nfsd_lookup(rqstp, fh, "..", 2, fh);
}

static __be32
nfsd4_lookupp(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
              union nfsd4_op_u *u)
{
        return nfsd4_do_lookupp(rqstp, &cstate->current_fh);
}

static __be32
nfsd4_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
             union nfsd4_op_u *u)
{
        return nfsd_lookup(rqstp, &cstate->current_fh,
                           u->lookup.lo_name, u->lookup.lo_len,
                           &cstate->current_fh);
}

static __be32
nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
           union nfsd4_op_u *u)
{
        struct nfsd4_read *read = &u->read;
        __be32 status;

        read->rd_nf = NULL;
        if (read->rd_offset >= OFFSET_MAX)
                return nfserr_inval;

        trace_nfsd_read_start(rqstp, &cstate->current_fh,
                              read->rd_offset, read->rd_length);

        /*
         * If we do a zero copy read, then a client will see read data
         * that reflects the state of the file *after* performing the
         * following compound.
         *
         * To ensure proper ordering, we therefore turn off zero copy if
         * the client wants us to do more in this compound:
         */
        if (!nfsd4_last_compound_op(rqstp))
                clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);

        /* check stateid */
        status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
                                        &read->rd_stateid, RD_STATE,
                                        &read->rd_nf, NULL);
        if (status) {
                dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
                goto out;
        }
        status = nfs_ok;
out:
        read->rd_rqstp = rqstp;
        read->rd_fhp = &cstate->current_fh;
        return status;
}


static void
nfsd4_read_release(union nfsd4_op_u *u)
{
        if (u->read.rd_nf)
                nfsd_file_put(u->read.rd_nf);
        trace_nfsd_read_done(u->read.rd_rqstp, u->read.rd_fhp,
                             u->read.rd_offset, u->read.rd_length);
}

static __be32
nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
              union nfsd4_op_u *u)
{
        struct nfsd4_readdir *readdir = &u->readdir;
        u64 cookie = readdir->rd_cookie;
        static const nfs4_verifier zeroverf;

        /* no need to check permission - this will be done in nfsd_readdir() */

        if (readdir->rd_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1)
                return nfserr_inval;

        readdir->rd_bmval[0] &= nfsd_suppattrs[cstate->minorversion][0];
        readdir->rd_bmval[1] &= nfsd_suppattrs[cstate->minorversion][1];
        readdir->rd_bmval[2] &= nfsd_suppattrs[cstate->minorversion][2];

        if ((cookie == 1) || (cookie == 2) ||
            (cookie == 0 && memcmp(readdir->rd_verf.data, zeroverf.data, NFS4_VERIFIER_SIZE)))
                return nfserr_bad_cookie;

        readdir->rd_rqstp = rqstp;
        readdir->rd_fhp = &cstate->current_fh;
        return nfs_ok;
}

static __be32
nfsd4_readlink(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
               union nfsd4_op_u *u)
{
        u->readlink.rl_rqstp = rqstp;
        u->readlink.rl_fhp = &cstate->current_fh;
        return nfs_ok;
}

static __be32
nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
             union nfsd4_op_u *u)
{
        struct nfsd4_remove *remove = &u->remove;
        __be32 status;

        if (opens_in_grace(SVC_NET(rqstp)))
                return nfserr_grace;
        status = nfsd_unlink(rqstp, &cstate->current_fh, 0,
                             remove->rm_name, remove->rm_namelen);
        if (!status) {
                fh_unlock(&cstate->current_fh);
                set_change_info(&remove->rm_cinfo, &cstate->current_fh);
        }
        return status;
}

static __be32
nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
             union nfsd4_op_u *u)
{
        struct nfsd4_rename *rename = &u->rename;
        __be32 status;

        if (opens_in_grace(SVC_NET(rqstp)))
                return nfserr_grace;
        status = nfsd_rename(rqstp, &cstate->save_fh, rename->rn_sname,
                             rename->rn_snamelen, &cstate->current_fh,
                             rename->rn_tname, rename->rn_tnamelen);
        if (status)
                return status;
        set_change_info(&rename->rn_sinfo, &cstate->current_fh);
        set_change_info(&rename->rn_tinfo, &cstate->save_fh);
        return nfs_ok;
}

static __be32
nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
              union nfsd4_op_u *u)
{
        struct nfsd4_secinfo *secinfo = &u->secinfo;
        struct svc_export *exp;
        struct dentry *dentry;
        __be32 err;

        err = fh_verify(rqstp, &cstate->current_fh, S_IFDIR, NFSD_MAY_EXEC);
        if (err)
                return err;
        err = nfsd_lookup_dentry(rqstp, &cstate->current_fh,
                                    secinfo->si_name, secinfo->si_namelen,
                                    &exp, &dentry);
        if (err)
                return err;
        fh_unlock(&cstate->current_fh);
        if (d_really_is_negative(dentry)) {
                exp_put(exp);
                err = nfserr_noent;
        } else
                secinfo->si_exp = exp;
        dput(dentry);
        if (cstate->minorversion)
                /* See rfc 5661 section 2.6.3.1.1.8 */
                fh_put(&cstate->current_fh);
        return err;
}

static __be32
nfsd4_secinfo_no_name(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                union nfsd4_op_u *u)
{
        __be32 err;

        switch (u->secinfo_no_name.sin_style) {
        case NFS4_SECINFO_STYLE4_CURRENT_FH:
                break;
        case NFS4_SECINFO_STYLE4_PARENT:
                err = nfsd4_do_lookupp(rqstp, &cstate->current_fh);
                if (err)
                        return err;
                break;
        default:
                return nfserr_inval;
        }

        u->secinfo_no_name.sin_exp = exp_get(cstate->current_fh.fh_export);
        fh_put(&cstate->current_fh);
        return nfs_ok;
}

static void
nfsd4_secinfo_release(union nfsd4_op_u *u)
{
        if (u->secinfo.si_exp)
                exp_put(u->secinfo.si_exp);
}

static void
nfsd4_secinfo_no_name_release(union nfsd4_op_u *u)
{
        if (u->secinfo_no_name.sin_exp)
                exp_put(u->secinfo_no_name.sin_exp);
}

static __be32
nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
              union nfsd4_op_u *u)
{
        struct nfsd4_setattr *setattr = &u->setattr;
        __be32 status = nfs_ok;
        int err;

        if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
                status = nfs4_preprocess_stateid_op(rqstp, cstate,
                                &cstate->current_fh, &setattr->sa_stateid,
                                WR_STATE, NULL, NULL);
                if (status) {
                        dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n");
                        return status;
                }
        }
        err = fh_want_write(&cstate->current_fh);
        if (err)
                return nfserrno(err);
        status = nfs_ok;

        status = check_attr_support(rqstp, cstate, setattr->sa_bmval,
                                    nfsd_attrmask);
        if (status)
                goto out;

        if (setattr->sa_acl != NULL)
                status = nfsd4_set_nfs4_acl(rqstp, &cstate->current_fh,
                                            setattr->sa_acl);
        if (status)
                goto out;
        if (setattr->sa_label.len)
                status = nfsd4_set_nfs4_label(rqstp, &cstate->current_fh,
                                &setattr->sa_label);

        if (status)
                goto out;
        status = nfsd_setattr(rqstp, &cstate->current_fh, &setattr->sa_iattr,
                                0, (time64_t)0);
out:
        fh_drop_write(&cstate->current_fh);
        return status;
}

static __be32
nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
            union nfsd4_op_u *u)
{
        struct nfsd4_write *write = &u->write;
        stateid_t *stateid = &write->wr_stateid;
        struct nfsd_file *nf = NULL;
        __be32 status = nfs_ok;
        unsigned long cnt;
        int nvecs;

        if (write->wr_offset >= OFFSET_MAX)
                return nfserr_inval;

        cnt = write->wr_buflen;
        trace_nfsd_write_start(rqstp, &cstate->current_fh,
                               write->wr_offset, cnt);
        status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
                                                stateid, WR_STATE, &nf, NULL);
        if (status) {
                dprintk("NFSD: nfsd4_write: couldn't process stateid!\n");
                return status;
        }

        write->wr_how_written = write->wr_stable_how;

        nvecs = svc_fill_write_vector(rqstp, write->wr_payload.pages,
                                      write->wr_payload.head, write->wr_buflen);
        WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec));

        status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf,
                                write->wr_offset, rqstp->rq_vec, nvecs, &cnt,
                                write->wr_how_written,
                                (__be32 *)write->wr_verifier.data);
        nfsd_file_put(nf);

        write->wr_bytes_written = cnt;
        trace_nfsd_write_done(rqstp, &cstate->current_fh,
                              write->wr_offset, cnt);
        return status;
}

static __be32
nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                  stateid_t *src_stateid, struct nfsd_file **src,
                  stateid_t *dst_stateid, struct nfsd_file **dst)
{
        __be32 status;

        if (!cstate->save_fh.fh_dentry)
                return nfserr_nofilehandle;

        status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh,
                                            src_stateid, RD_STATE, src, NULL);
        if (status) {
                dprintk("NFSD: %s: couldn't process src stateid!\n", __func__);
                goto out;
        }

        status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
                                            dst_stateid, WR_STATE, dst, NULL);
        if (status) {
                dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__);
                goto out_put_src;
        }

        /* fix up for NFS-specific error code */
        if (!S_ISREG(file_inode((*src)->nf_file)->i_mode) ||
            !S_ISREG(file_inode((*dst)->nf_file)->i_mode)) {
                status = nfserr_wrong_type;
                goto out_put_dst;
        }

out:
        return status;
out_put_dst:
        nfsd_file_put(*dst);
out_put_src:
        nfsd_file_put(*src);
        goto out;
}

static __be32
nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                union nfsd4_op_u *u)
{
        struct nfsd4_clone *clone = &u->clone;
        struct nfsd_file *src, *dst;
        __be32 status;

        status = nfsd4_verify_copy(rqstp, cstate, &clone->cl_src_stateid, &src,
                                   &clone->cl_dst_stateid, &dst);
        if (status)
                goto out;

        status = nfsd4_clone_file_range(src, clone->cl_src_pos,
                        dst, clone->cl_dst_pos, clone->cl_count,
                        EX_ISSYNC(cstate->current_fh.fh_export));

        nfsd_file_put(dst);
        nfsd_file_put(src);
out:
        return status;
}

void nfs4_put_copy(struct nfsd4_copy *copy)
{
        if (!refcount_dec_and_test(&copy->refcount))
                return;
        kfree(copy);
}

static bool
check_and_set_stop_copy(struct nfsd4_copy *copy)
{
        bool value;

        spin_lock(&copy->cp_clp->async_lock);
        value = copy->stopped;
        if (!copy->stopped)
                copy->stopped = true;
        spin_unlock(&copy->cp_clp->async_lock);
        return value;
}

static void nfsd4_stop_copy(struct nfsd4_copy *copy)
{
        /* only 1 thread should stop the copy */
        if (!check_and_set_stop_copy(copy))
                kthread_stop(copy->copy_task);
        nfs4_put_copy(copy);
}

static struct nfsd4_copy *nfsd4_get_copy(struct nfs4_client *clp)
{
        struct nfsd4_copy *copy = NULL;

        spin_lock(&clp->async_lock);
        if (!list_empty(&clp->async_copies)) {
                copy = list_first_entry(&clp->async_copies, struct nfsd4_copy,
                                        copies);
                refcount_inc(&copy->refcount);
        }
        spin_unlock(&clp->async_lock);
        return copy;
}

void nfsd4_shutdown_copy(struct nfs4_client *clp)
{
        struct nfsd4_copy *copy;

        while ((copy = nfsd4_get_copy(clp)) != NULL)
                nfsd4_stop_copy(copy);
}
#ifdef CONFIG_NFSD_V4_2_INTER_SSC

extern struct file *nfs42_ssc_open(struct vfsmount *ss_mnt,
                                   struct nfs_fh *src_fh,
                                   nfs4_stateid *stateid);
extern void nfs42_ssc_close(struct file *filep);

extern void nfs_sb_deactive(struct super_block *sb);

#define NFSD42_INTERSSC_MOUNTOPS "vers=4.2,addr=%s,sec=sys"

/*
 * setup a work entry in the ssc delayed unmount list.
 */
static __be32 nfsd4_ssc_setup_dul(struct nfsd_net *nn, char *ipaddr,
                struct nfsd4_ssc_umount_item **retwork, struct vfsmount **ss_mnt)
{
        struct nfsd4_ssc_umount_item *ni = 0;
        struct nfsd4_ssc_umount_item *work = NULL;
        struct nfsd4_ssc_umount_item *tmp;
        DEFINE_WAIT(wait);

        *ss_mnt = NULL;
        *retwork = NULL;
        work = kzalloc(sizeof(*work), GFP_KERNEL);
try_again:
        spin_lock(&nn->nfsd_ssc_lock);
        list_for_each_entry_safe(ni, tmp, &nn->nfsd_ssc_mount_list, nsui_list) {
                if (strncmp(ni->nsui_ipaddr, ipaddr, sizeof(ni->nsui_ipaddr)))
                        continue;
                /* found a match */
                if (ni->nsui_busy) {
                        /*  wait - and try again */
                        prepare_to_wait(&nn->nfsd_ssc_waitq, &wait,
                                TASK_INTERRUPTIBLE);
                        spin_unlock(&nn->nfsd_ssc_lock);

                        /* allow 20secs for mount/unmount for now - revisit */
                        if (signal_pending(current) ||
                                        (schedule_timeout(20*HZ) == 0)) {
                                kfree(work);
                                return nfserr_eagain;
                        }
                        finish_wait(&nn->nfsd_ssc_waitq, &wait);
                        goto try_again;
                }
                *ss_mnt = ni->nsui_vfsmount;
                refcount_inc(&ni->nsui_refcnt);
                spin_unlock(&nn->nfsd_ssc_lock);
                kfree(work);

                /* return vfsmount in ss_mnt */
                return 0;
        }
        if (work) {
                strncpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr));
                refcount_set(&work->nsui_refcnt, 2);
                work->nsui_busy = true;
                list_add_tail(&work->nsui_list, &nn->nfsd_ssc_mount_list);
                *retwork = work;
        }
        spin_unlock(&nn->nfsd_ssc_lock);
        return 0;
}

static void nfsd4_ssc_update_dul_work(struct nfsd_net *nn,
                struct nfsd4_ssc_umount_item *work, struct vfsmount *ss_mnt)
{
        /* set nsui_vfsmount, clear busy flag and wakeup waiters */
        spin_lock(&nn->nfsd_ssc_lock);
        work->nsui_vfsmount = ss_mnt;
        work->nsui_busy = false;
        wake_up_all(&nn->nfsd_ssc_waitq);
        spin_unlock(&nn->nfsd_ssc_lock);
}

static void nfsd4_ssc_cancel_dul_work(struct nfsd_net *nn,
                struct nfsd4_ssc_umount_item *work)
{
        spin_lock(&nn->nfsd_ssc_lock);
        list_del(&work->nsui_list);
        wake_up_all(&nn->nfsd_ssc_waitq);
        spin_unlock(&nn->nfsd_ssc_lock);
        kfree(work);
}

/*
 * Support one copy source server for now.
 */
static __be32
nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp,
                       struct vfsmount **mount)
{
        struct file_system_type *type;
        struct vfsmount *ss_mnt;
        struct nfs42_netaddr *naddr;
        struct sockaddr_storage tmp_addr;
        size_t tmp_addrlen, match_netid_len = 3;
        char *startsep = "", *endsep = "", *match_netid = "tcp";
        char *ipaddr, *dev_name, *raw_data;
        int len, raw_len;
        __be32 status = nfserr_inval;
        struct nfsd4_ssc_umount_item *work = NULL;
        struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);

        naddr = &nss->u.nl4_addr;
        tmp_addrlen = rpc_uaddr2sockaddr(SVC_NET(rqstp), naddr->addr,
                                         naddr->addr_len,
                                         (struct sockaddr *)&tmp_addr,
                                         sizeof(tmp_addr));
        if (tmp_addrlen == 0)
                goto out_err;

        if (tmp_addr.ss_family == AF_INET6) {
                startsep = "[";
                endsep = "]";
                match_netid = "tcp6";
                match_netid_len = 4;
        }

        if (naddr->netid_len != match_netid_len ||
                strncmp(naddr->netid, match_netid, naddr->netid_len))
                goto out_err;

        /* Construct the raw data for the vfs_kern_mount call */
        len = RPC_MAX_ADDRBUFLEN + 1;
        ipaddr = kzalloc(len, GFP_KERNEL);
        if (!ipaddr)
                goto out_err;

        rpc_ntop((struct sockaddr *)&tmp_addr, ipaddr, len);

        /* 2 for ipv6 endsep and startsep. 3 for ":/" and trailing '/0'*/

        raw_len = strlen(NFSD42_INTERSSC_MOUNTOPS) + strlen(ipaddr);
        raw_data = kzalloc(raw_len, GFP_KERNEL);
        if (!raw_data)
                goto out_free_ipaddr;

        snprintf(raw_data, raw_len, NFSD42_INTERSSC_MOUNTOPS, ipaddr);

        status = nfserr_nodev;
        type = get_fs_type("nfs");
        if (!type)
                goto out_free_rawdata;

        /* Set the server:<export> for the vfs_kern_mount call */
        dev_name = kzalloc(len + 5, GFP_KERNEL);
        if (!dev_name)
                goto out_free_rawdata;
        snprintf(dev_name, len + 5, "%s%s%s:/", startsep, ipaddr, endsep);

        status = nfsd4_ssc_setup_dul(nn, ipaddr, &work, &ss_mnt);
        if (status)
                goto out_free_devname;
        if (ss_mnt)
                goto out_done;

        /* Use an 'internal' mount: SB_KERNMOUNT -> MNT_INTERNAL */
        ss_mnt = vfs_kern_mount(type, SB_KERNMOUNT, dev_name, raw_data);
        module_put(type->owner);
        if (IS_ERR(ss_mnt)) {
                status = nfserr_nodev;
                if (work)
                        nfsd4_ssc_cancel_dul_work(nn, work);
                goto out_free_devname;
        }
        if (work)
                nfsd4_ssc_update_dul_work(nn, work, ss_mnt);
out_done:
        status = 0;
        *mount = ss_mnt;

out_free_devname:
        kfree(dev_name);
out_free_rawdata:
        kfree(raw_data);
out_free_ipaddr:
        kfree(ipaddr);
out_err:
        return status;
}

static void
nfsd4_interssc_disconnect(struct vfsmount *ss_mnt)
{
        nfs_do_sb_deactive(ss_mnt->mnt_sb);
        mntput(ss_mnt);
}

/*
 * Verify COPY destination stateid.
 *
 * Connect to the source server with NFSv4.1.
 * Create the source struct file for nfsd_copy_range.
 * Called with COPY cstate:
 *    SAVED_FH: source filehandle
 *    CURRENT_FH: destination filehandle
 */
static __be32
nfsd4_setup_inter_ssc(struct svc_rqst *rqstp,
                      struct nfsd4_compound_state *cstate,
                      struct nfsd4_copy *copy, struct vfsmount **mount)
{
        struct svc_fh *s_fh = NULL;
        stateid_t *s_stid = &copy->cp_src_stateid;
        __be32 status = nfserr_inval;

        /* Verify the destination stateid and set dst struct file*/
        status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
                                            &copy->cp_dst_stateid,
                                            WR_STATE, &copy->nf_dst, NULL);
        if (status)
                goto out;

        status = nfsd4_interssc_connect(&copy->cp_src, rqstp, mount);
        if (status)
                goto out;

        s_fh = &cstate->save_fh;

        copy->c_fh.size = s_fh->fh_handle.fh_size;
        memcpy(copy->c_fh.data, &s_fh->fh_handle.fh_base, copy->c_fh.size);
        copy->stateid.seqid = cpu_to_be32(s_stid->si_generation);
        memcpy(copy->stateid.other, (void *)&s_stid->si_opaque,
               sizeof(stateid_opaque_t));

        status = 0;
out:
        return status;
}

static void
nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src,
                        struct nfsd_file *dst)
{
        bool found = false;
        long timeout;
        struct nfsd4_ssc_umount_item *tmp;
        struct nfsd4_ssc_umount_item *ni = NULL;
        struct nfsd_net *nn = net_generic(dst->nf_net, nfsd_net_id);

        nfs42_ssc_close(src->nf_file);
        nfsd_file_put(dst);
        fput(src->nf_file);

        if (!nn) {
                mntput(ss_mnt);
                return;
        }
        spin_lock(&nn->nfsd_ssc_lock);
        timeout = msecs_to_jiffies(nfsd4_ssc_umount_timeout);
        list_for_each_entry_safe(ni, tmp, &nn->nfsd_ssc_mount_list, nsui_list) {
                if (ni->nsui_vfsmount->mnt_sb == ss_mnt->mnt_sb) {
                        list_del(&ni->nsui_list);
                        /*
                         * vfsmount can be shared by multiple exports,
                         * decrement refcnt. If the count drops to 1 it
                         * will be unmounted when nsui_expire expires.
                         */
                        refcount_dec(&ni->nsui_refcnt);
                        ni->nsui_expire = jiffies + timeout;
                        list_add_tail(&ni->nsui_list, &nn->nfsd_ssc_mount_list);
                        found = true;
                        break;
                }
        }
        spin_unlock(&nn->nfsd_ssc_lock);
        if (!found) {
                mntput(ss_mnt);
                return;
        }
}

#else /* CONFIG_NFSD_V4_2_INTER_SSC */

static __be32
nfsd4_setup_inter_ssc(struct svc_rqst *rqstp,
                      struct nfsd4_compound_state *cstate,
                      struct nfsd4_copy *copy,
                      struct vfsmount **mount)
{
        *mount = NULL;
        return nfserr_inval;
}

static void
nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src,
                        struct nfsd_file *dst)
{
}

static void
nfsd4_interssc_disconnect(struct vfsmount *ss_mnt)
{
}

static struct file *nfs42_ssc_open(struct vfsmount *ss_mnt,
                                   struct nfs_fh *src_fh,
                                   nfs4_stateid *stateid)
{
        return NULL;
}
#endif /* CONFIG_NFSD_V4_2_INTER_SSC */

static __be32
nfsd4_setup_intra_ssc(struct svc_rqst *rqstp,
                      struct nfsd4_compound_state *cstate,
                      struct nfsd4_copy *copy)
{
        return nfsd4_verify_copy(rqstp, cstate, &copy->cp_src_stateid,
                                 &copy->nf_src, &copy->cp_dst_stateid,
                                 &copy->nf_dst);
}

static void
nfsd4_cleanup_intra_ssc(struct nfsd_file *src, struct nfsd_file *dst)
{
        nfsd_file_put(src);
        nfsd_file_put(dst);
}

static void nfsd4_cb_offload_release(struct nfsd4_callback *cb)
{
        struct nfsd4_copy *copy = container_of(cb, struct nfsd4_copy, cp_cb);

        nfs4_put_copy(copy);
}

static int nfsd4_cb_offload_done(struct nfsd4_callback *cb,
                                 struct rpc_task *task)
{
        return 1;
}

static const struct nfsd4_callback_ops nfsd4_cb_offload_ops = {
        .release = nfsd4_cb_offload_release,
        .done = nfsd4_cb_offload_done
};

static void nfsd4_init_copy_res(struct nfsd4_copy *copy, bool sync)
{
        copy->cp_res.wr_stable_how =
                copy->committed ? NFS_FILE_SYNC : NFS_UNSTABLE;
        copy->cp_synchronous = sync;
        gen_boot_verifier(&copy->cp_res.wr_verifier, copy->cp_clp->net);
}

static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy)
{
        ssize_t bytes_copied = 0;
        u64 bytes_total = copy->cp_count;
        u64 src_pos = copy->cp_src_pos;
        u64 dst_pos = copy->cp_dst_pos;
        __be32 status;

        /* See RFC 7862 p.67: */
        if (bytes_total == 0)
                bytes_total = ULLONG_MAX;
        do {
                if (kthread_should_stop())
                        break;
                bytes_copied = nfsd_copy_file_range(copy->nf_src->nf_file,
                                src_pos, copy->nf_dst->nf_file, dst_pos,
                                bytes_total);
                if (bytes_copied <= 0)
                        break;
                bytes_total -= bytes_copied;
                copy->cp_res.wr_bytes_written += bytes_copied;
                src_pos += bytes_copied;
                dst_pos += bytes_copied;
        } while (bytes_total > 0 && !copy->cp_synchronous);
        /* for a non-zero asynchronous copy do a commit of data */
        if (!copy->cp_synchronous && copy->cp_res.wr_bytes_written > 0) {
                down_write(&copy->nf_dst->nf_rwsem);
                status = vfs_fsync_range(copy->nf_dst->nf_file,
                                         copy->cp_dst_pos,
                                         copy->cp_res.wr_bytes_written, 0);
                up_write(&copy->nf_dst->nf_rwsem);
                if (!status)
                        copy->committed = true;
        }
        return bytes_copied;
}

static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, bool sync)
{
        __be32 status;
        ssize_t bytes;

        bytes = _nfsd_copy_file_range(copy);
        /* for async copy, we ignore the error, client can always retry
         * to get the error
         */
        if (bytes < 0 && !copy->cp_res.wr_bytes_written)
                status = nfserrno(bytes);
        else {
                nfsd4_init_copy_res(copy, sync);
                status = nfs_ok;
        }

        if (!copy->cp_intra) /* Inter server SSC */
                nfsd4_cleanup_inter_ssc(copy->ss_mnt, copy->nf_src,
                                        copy->nf_dst);
        else
                nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst);

        return status;
}

static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst)
{
        dst->cp_src_pos = src->cp_src_pos;
        dst->cp_dst_pos = src->cp_dst_pos;
        dst->cp_count = src->cp_count;
        dst->cp_synchronous = src->cp_synchronous;
        memcpy(&dst->cp_res, &src->cp_res, sizeof(src->cp_res));
        memcpy(&dst->fh, &src->fh, sizeof(src->fh));
        dst->cp_clp = src->cp_clp;
        dst->nf_dst = nfsd_file_get(src->nf_dst);
        dst->cp_intra = src->cp_intra;
        if (src->cp_intra) /* for inter, file_src doesn't exist yet */
                dst->nf_src = nfsd_file_get(src->nf_src);

        memcpy(&dst->cp_stateid, &src->cp_stateid, sizeof(src->cp_stateid));
        memcpy(&dst->cp_src, &src->cp_src, sizeof(struct nl4_server));
        memcpy(&dst->stateid, &src->stateid, sizeof(src->stateid));
        memcpy(&dst->c_fh, &src->c_fh, sizeof(src->c_fh));
        dst->ss_mnt = src->ss_mnt;
}

static void cleanup_async_copy(struct nfsd4_copy *copy)
{
        nfs4_free_copy_state(copy);
        nfsd_file_put(copy->nf_dst);
        if (copy->cp_intra)
                nfsd_file_put(copy->nf_src);
        spin_lock(&copy->cp_clp->async_lock);
        list_del(&copy->copies);
        spin_unlock(&copy->cp_clp->async_lock);
        nfs4_put_copy(copy);
}

static int nfsd4_do_async_copy(void *data)
{
        struct nfsd4_copy *copy = (struct nfsd4_copy *)data;
        struct nfsd4_copy *cb_copy;

        if (!copy->cp_intra) { /* Inter server SSC */
                copy->nf_src = kzalloc(sizeof(struct nfsd_file), GFP_KERNEL);
                if (!copy->nf_src) {
                        copy->nfserr = nfserr_serverfault;
                        nfsd4_interssc_disconnect(copy->ss_mnt);
                        goto do_callback;
                }
                copy->nf_src->nf_file = nfs42_ssc_open(copy->ss_mnt, &copy->c_fh,
                                              &copy->stateid);
                if (IS_ERR(copy->nf_src->nf_file)) {
                        copy->nfserr = nfserr_offload_denied;
                        nfsd4_interssc_disconnect(copy->ss_mnt);
                        goto do_callback;
                }
        }

        copy->nfserr = nfsd4_do_copy(copy, 0);
do_callback:
        cb_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL);
        if (!cb_copy)
                goto out;
        refcount_set(&cb_copy->refcount, 1);
        memcpy(&cb_copy->cp_res, &copy->cp_res, sizeof(copy->cp_res));
        cb_copy->cp_clp = copy->cp_clp;
        cb_copy->nfserr = copy->nfserr;
        memcpy(&cb_copy->fh, &copy->fh, sizeof(copy->fh));
        nfsd4_init_cb(&cb_copy->cp_cb, cb_copy->cp_clp,
                        &nfsd4_cb_offload_ops, NFSPROC4_CLNT_CB_OFFLOAD);
        trace_nfsd_cb_offload(copy->cp_clp, &copy->cp_res.cb_stateid,
                              &copy->fh, copy->cp_count, copy->nfserr);
        nfsd4_run_cb(&cb_copy->cp_cb);
out:
        if (!copy->cp_intra)
                kfree(copy->nf_src);
        cleanup_async_copy(copy);
        return 0;
}

static __be32
nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                union nfsd4_op_u *u)
{
        struct nfsd4_copy *copy = &u->copy;
        __be32 status;
        struct nfsd4_copy *async_copy = NULL;

        if (!copy->cp_intra) { /* Inter server SSC */
                if (!inter_copy_offload_enable || copy->cp_synchronous) {
                        status = nfserr_notsupp;
                        goto out;
                }
                status = nfsd4_setup_inter_ssc(rqstp, cstate, copy,
                                &copy->ss_mnt);
                if (status)
                        return nfserr_offload_denied;
        } else {
                status = nfsd4_setup_intra_ssc(rqstp, cstate, copy);
                if (status)
                        return status;
        }

        copy->cp_clp = cstate->clp;
        memcpy(&copy->fh, &cstate->current_fh.fh_handle,
                sizeof(struct knfsd_fh));
        if (!copy->cp_synchronous) {
                struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);

                status = nfserrno(-ENOMEM);
                async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL);
                if (!async_copy)
                        goto out_err;
                if (!nfs4_init_copy_state(nn, copy))
                        goto out_err;
                refcount_set(&async_copy->refcount, 1);
                memcpy(&copy->cp_res.cb_stateid, &copy->cp_stateid.stid,
                        sizeof(copy->cp_res.cb_stateid));
                dup_copy_fields(copy, async_copy);
                async_copy->copy_task = kthread_create(nfsd4_do_async_copy,
                                async_copy, "%s", "copy thread");
                if (IS_ERR(async_copy->copy_task))
                        goto out_err;
                spin_lock(&async_copy->cp_clp->async_lock);
                list_add(&async_copy->copies,
                                &async_copy->cp_clp->async_copies);
                spin_unlock(&async_copy->cp_clp->async_lock);
                wake_up_process(async_copy->copy_task);
                status = nfs_ok;
        } else {
                status = nfsd4_do_copy(copy, 1);
        }
out:
        return status;
out_err:
        if (async_copy)
                cleanup_async_copy(async_copy);
        status = nfserrno(-ENOMEM);
        if (!copy->cp_intra)
                nfsd4_interssc_disconnect(copy->ss_mnt);
        goto out;
}

struct nfsd4_copy *
find_async_copy(struct nfs4_client *clp, stateid_t *stateid)
{
        struct nfsd4_copy *copy;

        spin_lock(&clp->async_lock);
        list_for_each_entry(copy, &clp->async_copies, copies) {
                if (memcmp(&copy->cp_stateid.stid, stateid, NFS4_STATEID_SIZE))
                        continue;
                refcount_inc(&copy->refcount);
                spin_unlock(&clp->async_lock);
                return copy;
        }
        spin_unlock(&clp->async_lock);
        return NULL;
}

static __be32
nfsd4_offload_cancel(struct svc_rqst *rqstp,
                     struct nfsd4_compound_state *cstate,
                     union nfsd4_op_u *u)
{
        struct nfsd4_offload_status *os = &u->offload_status;
        struct nfsd4_copy *copy;
        struct nfs4_client *clp = cstate->clp;

        copy = find_async_copy(clp, &os->stateid);
        if (!copy) {
                struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);

                return manage_cpntf_state(nn, &os->stateid, clp, NULL);
        } else
                nfsd4_stop_copy(copy);

        return nfs_ok;
}

static __be32
nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                  union nfsd4_op_u *u)
{
        struct nfsd4_copy_notify *cn = &u->copy_notify;
        __be32 status;
        struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
        struct nfs4_stid *stid;
        struct nfs4_cpntf_state *cps;
        struct nfs4_client *clp = cstate->clp;

        status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
                                        &cn->cpn_src_stateid, RD_STATE, NULL,
                                        &stid);
        if (status)
                return status;

        cn->cpn_sec = nn->nfsd4_lease;
        cn->cpn_nsec = 0;

        status = nfserrno(-ENOMEM);
        cps = nfs4_alloc_init_cpntf_state(nn, stid);
        if (!cps)
                goto out;
        memcpy(&cn->cpn_cnr_stateid, &cps->cp_stateid.stid, sizeof(stateid_t));
        memcpy(&cps->cp_p_stateid, &stid->sc_stateid, sizeof(stateid_t));
        memcpy(&cps->cp_p_clid, &clp->cl_clientid, sizeof(clientid_t));

        /* For now, only return one server address in cpn_src, the
         * address used by the client to connect to this server.
         */
        cn->cpn_src.nl4_type = NL4_NETADDR;
        status = nfsd4_set_netaddr((struct sockaddr *)&rqstp->rq_daddr,
                                 &cn->cpn_src.u.nl4_addr);
        WARN_ON_ONCE(status);
        if (status) {
                nfs4_put_cpntf_state(nn, cps);
                goto out;
        }
out:
        nfs4_put_stid(stid);
        return status;
}

static __be32
nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                struct nfsd4_fallocate *fallocate, int flags)
{
        __be32 status;
        struct nfsd_file *nf;

        status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
                                            &fallocate->falloc_stateid,
                                            WR_STATE, &nf, NULL);
        if (status != nfs_ok) {
                dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n");
                return status;
        }

        status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, nf->nf_file,
                                     fallocate->falloc_offset,
                                     fallocate->falloc_length,
                                     flags);
        nfsd_file_put(nf);
        return status;
}
static __be32
nfsd4_offload_status(struct svc_rqst *rqstp,
                     struct nfsd4_compound_state *cstate,
                     union nfsd4_op_u *u)
{
        struct nfsd4_offload_status *os = &u->offload_status;
        __be32 status = 0;
        struct nfsd4_copy *copy;
        struct nfs4_client *clp = cstate->clp;

        copy = find_async_copy(clp, &os->stateid);
        if (copy) {
                os->count = copy->cp_res.wr_bytes_written;
                nfs4_put_copy(copy);
        } else
                status = nfserr_bad_stateid;

        return status;
}

static __be32
nfsd4_allocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
               union nfsd4_op_u *u)
{
        return nfsd4_fallocate(rqstp, cstate, &u->allocate, 0);
}

static __be32
nfsd4_deallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                 union nfsd4_op_u *u)
{
        return nfsd4_fallocate(rqstp, cstate, &u->deallocate,
                               FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE);
}

static __be32
nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
           union nfsd4_op_u *u)
{
        struct nfsd4_seek *seek = &u->seek;
        int whence;
        __be32 status;
        struct nfsd_file *nf;

        status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
                                            &seek->seek_stateid,
                                            RD_STATE, &nf, NULL);
        if (status) {
                dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n");
                return status;
        }

        switch (seek->seek_whence) {
        case NFS4_CONTENT_DATA:
                whence = SEEK_DATA;
                break;
        case NFS4_CONTENT_HOLE:
                whence = SEEK_HOLE;
                break;
        default:
                status = nfserr_union_notsupp;
                goto out;
        }

        /*
         * Note:  This call does change file->f_pos, but nothing in NFSD
         *        should ever file->f_pos.
         */
        seek->seek_pos = vfs_llseek(nf->nf_file, seek->seek_offset, whence);
        if (seek->seek_pos < 0)
                status = nfserrno(seek->seek_pos);
        else if (seek->seek_pos >= i_size_read(file_inode(nf->nf_file)))
                seek->seek_eof = true;

out:
        nfsd_file_put(nf);
        return status;
}

/* This routine never returns NFS_OK!  If there are no other errors, it
 * will return NFSERR_SAME or NFSERR_NOT_SAME depending on whether the
 * attributes matched.  VERIFY is implemented by mapping NFSERR_SAME
 * to NFS_OK after the call; NVERIFY by mapping NFSERR_NOT_SAME to NFS_OK.
 */
static __be32
_nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
             struct nfsd4_verify *verify)
{
        __be32 *buf, *p;
        int count;
        __be32 status;

        status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
        if (status)
                return status;

        status = check_attr_support(rqstp, cstate, verify->ve_bmval, NULL);
        if (status)
                return status;

        if ((verify->ve_bmval[0] & FATTR4_WORD0_RDATTR_ERROR)
            || (verify->ve_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1))
                return nfserr_inval;
        if (verify->ve_attrlen & 3)
                return nfserr_inval;

        /* count in words:
         *   bitmap_len(1) + bitmap(2) + attr_len(1) = 4
         */
        count = 4 + (verify->ve_attrlen >> 2);
        buf = kmalloc(count << 2, GFP_KERNEL);
        if (!buf)
                return nfserr_jukebox;

        p = buf;
        status = nfsd4_encode_fattr_to_buf(&p, count, &cstate->current_fh,
                                    cstate->current_fh.fh_export,
                                    cstate->current_fh.fh_dentry,
                                    verify->ve_bmval,
                                    rqstp, 0);
        /*
         * If nfsd4_encode_fattr() ran out of space, assume that's because
         * the attributes are longer (hence different) than those given:
         */
        if (status == nfserr_resource)
                status = nfserr_not_same;
        if (status)
                goto out_kfree;

        /* skip bitmap */
        p = buf + 1 + ntohl(buf[0]);
        status = nfserr_not_same;
        if (ntohl(*p++) != verify->ve_attrlen)
                goto out_kfree;
        if (!memcmp(p, verify->ve_attrval, verify->ve_attrlen))
                status = nfserr_same;

out_kfree:
        kfree(buf);
        return status;
}

static __be32
nfsd4_nverify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
              union nfsd4_op_u *u)
{
        __be32 status;

        status = _nfsd4_verify(rqstp, cstate, &u->verify);
        return status == nfserr_not_same ? nfs_ok : status;
}

static __be32
nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
             union nfsd4_op_u *u)
{
        __be32 status;

        status = _nfsd4_verify(rqstp, cstate, &u->nverify);
        return status == nfserr_same ? nfs_ok : status;
}

#ifdef CONFIG_NFSD_PNFS
static const struct nfsd4_layout_ops *
nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type)
{
        if (!exp->ex_layout_types) {
                dprintk("%s: export does not support pNFS\n", __func__);
                return NULL;
        }

        if (layout_type >= LAYOUT_TYPE_MAX ||
            !(exp->ex_layout_types & (1 << layout_type))) {
                dprintk("%s: layout type %d not supported\n",
                        __func__, layout_type);
                return NULL;
        }

        return nfsd4_layout_ops[layout_type];
}

static __be32
nfsd4_getdeviceinfo(struct svc_rqst *rqstp,
                struct nfsd4_compound_state *cstate, union nfsd4_op_u *u)
{