#define NFSDDBG_FACILITY NFSDDBG_FILEOP
-/* We must ignore files (but only files) which might have mandatory
- * locks on them because there is no way to know if the accesser has
- * the lock.
- */
-#define IS_ISMNDLK(i) (S_ISREG((i)->i_mode) && MANDATORY_LOCK(i))
-
/*
* This is a cache of readahead params that help us choose the proper
* readahead strategy. Initially, we set all readahead parameters to 0
{
struct svc_export *exp = *expp, *exp2 = NULL;
struct dentry *dentry = *dpp;
- struct vfsmount *mnt = mntget(exp->ex_mnt);
+ struct vfsmount *mnt = mntget(exp->ex_path.mnt);
struct dentry *mounts = dget(dentry);
int err = 0;
while (follow_down(&mnt,&mounts)&&d_mountpoint(mounts));
- exp2 = exp_get_by_name(exp->ex_client, mnt, mounts, &rqstp->rq_chandle);
+ exp2 = rqst_exp_get_by_name(rqstp, mnt, mounts);
if (IS_ERR(exp2)) {
- err = PTR_ERR(exp2);
+ if (PTR_ERR(exp2) != -ENOENT)
+ err = PTR_ERR(exp2);
dput(mounts);
mntput(mnt);
goto out;
}
- if (exp2 && ((exp->ex_flags & NFSEXP_CROSSMOUNT) || EX_NOHIDE(exp2))) {
+ if ((exp->ex_flags & NFSEXP_CROSSMOUNT) || EX_NOHIDE(exp2)) {
/* successfully crossed mount point */
exp_put(exp);
*expp = exp2;
dput(dentry);
*dpp = mounts;
} else {
- if (exp2) exp_put(exp2);
+ exp_put(exp2);
dput(mounts);
}
mntput(mnt);
return err;
}
-/*
- * Look up one component of a pathname.
- * N.B. After this call _both_ fhp and resfh need an fh_put
- *
- * If the lookup would cross a mountpoint, and the mounted filesystem
- * is exported to the client with NFSEXP_NOHIDE, then the lookup is
- * accepted as it stands and the mounted directory is
- * returned. Otherwise the covered directory is returned.
- * NOTE: this mountpoint crossing is not supported properly by all
- * clients and is explicitly disallowed for NFSv3
- * NeilBrown <neilb@cse.unsw.edu.au>
- */
__be32
-nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
- int len, struct svc_fh *resfh)
+nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ const char *name, unsigned int len,
+ struct svc_export **exp_ret, struct dentry **dentry_ret)
{
struct svc_export *exp;
struct dentry *dparent;
exp = fhp->fh_export;
exp_get(exp);
- err = nfserr_acces;
-
/* Lookup the name, but don't follow links */
if (isdotent(name, len)) {
if (len==1)
dentry = dget(dparent);
- else if (dparent != exp->ex_dentry) {
+ else if (dparent != exp->ex_path.dentry)
dentry = dget_parent(dparent);
- } else if (!EX_NOHIDE(exp))
+ else if (!EX_NOHIDE(exp))
dentry = dget(dparent); /* .. == . just like at / */
else {
/* checking mountpoint crossing is very different when stepping up */
struct svc_export *exp2 = NULL;
struct dentry *dp;
- struct vfsmount *mnt = mntget(exp->ex_mnt);
+ struct vfsmount *mnt = mntget(exp->ex_path.mnt);
dentry = dget(dparent);
while(dentry == mnt->mnt_root && follow_up(&mnt, &dentry))
;
dput(dentry);
dentry = dp;
- exp2 = exp_parent(exp->ex_client, mnt, dentry,
- &rqstp->rq_chandle);
- if (IS_ERR(exp2)) {
+ exp2 = rqst_exp_parent(rqstp, mnt, dentry);
+ if (PTR_ERR(exp2) == -ENOENT) {
+ dput(dentry);
+ dentry = dget(dparent);
+ } else if (IS_ERR(exp2)) {
host_err = PTR_ERR(exp2);
dput(dentry);
mntput(mnt);
goto out_nfserr;
- }
- if (!exp2) {
- dput(dentry);
- dentry = dget(dparent);
} else {
exp_put(exp);
exp = exp2;
}
}
}
+ *dentry_ret = dentry;
+ *exp_ret = exp;
+ return 0;
+
+out_nfserr:
+ exp_put(exp);
+ return nfserrno(host_err);
+}
+
+/*
+ * Look up one component of a pathname.
+ * N.B. After this call _both_ fhp and resfh need an fh_put
+ *
+ * If the lookup would cross a mountpoint, and the mounted filesystem
+ * is exported to the client with NFSEXP_NOHIDE, then the lookup is
+ * accepted as it stands and the mounted directory is
+ * returned. Otherwise the covered directory is returned.
+ * NOTE: this mountpoint crossing is not supported properly by all
+ * clients and is explicitly disallowed for NFSv3
+ * NeilBrown <neilb@cse.unsw.edu.au>
+ */
+__be32
+nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
+ unsigned int len, struct svc_fh *resfh)
+{
+ struct svc_export *exp;
+ struct dentry *dentry;
+ __be32 err;
+
+ err = nfsd_lookup_dentry(rqstp, fhp, name, len, &exp, &dentry);
+ if (err)
+ return err;
+ err = check_nfsd_access(exp, rqstp);
+ if (err)
+ goto out;
/*
* Note: we compose the file handle now, but as the
* dentry may be negative, it may need to be updated.
err = fh_compose(resfh, exp, dentry, fhp);
if (!err && !dentry->d_inode)
err = nfserr_noent;
- dput(dentry);
out:
+ dput(dentry);
exp_put(exp);
return err;
-
-out_nfserr:
- err = nfserrno(host_err);
- goto out;
}
+
/*
* Set various file attributes.
* N.B. After this call fhp needs an fh_put
if (!iap->ia_valid)
goto out;
- /* NFSv2 does not differentiate between "set-[ac]time-to-now"
+ /*
+ * NFSv2 does not differentiate between "set-[ac]time-to-now"
* which only requires access, and "set-[ac]time-to-X" which
* requires ownership.
* So if it looks like it might be "set both to the same time which
*/
#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
#define MAX_TOUCH_TIME_ERROR (30*60)
- if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET
- && iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec
- ) {
- /* Looks probable. Now just make sure time is in the right ballpark.
- * Solaris, at least, doesn't seem to care what the time request is.
- * We require it be within 30 minutes of now.
- */
- time_t delta = iap->ia_atime.tv_sec - get_seconds();
- if (delta<0) delta = -delta;
- if (delta < MAX_TOUCH_TIME_ERROR &&
- inode_change_ok(inode, iap) != 0) {
- /* turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME
- * this will cause notify_change to set these times to "now"
+ if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET &&
+ iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec) {
+ /*
+ * Looks probable.
+ *
+ * Now just make sure time is in the right ballpark.
+ * Solaris, at least, doesn't seem to care what the time
+ * request is. We require it be within 30 minutes of now.
*/
- iap->ia_valid &= ~BOTH_TIME_SET;
- }
+ time_t delta = iap->ia_atime.tv_sec - get_seconds();
+ if (delta < 0)
+ delta = -delta;
+ if (delta < MAX_TOUCH_TIME_ERROR &&
+ inode_change_ok(inode, iap) != 0) {
+ /*
+ * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME.
+ * This will cause notify_change to set these times
+ * to "now"
+ */
+ iap->ia_valid &= ~BOTH_TIME_SET;
+ }
}
- /* The size case is special. It changes the file as well as the attributes. */
+ /*
+ * The size case is special.
+ * It changes the file as well as the attributes.
+ */
if (iap->ia_valid & ATTR_SIZE) {
if (iap->ia_size < inode->i_size) {
- err = nfsd_permission(fhp->fh_export, dentry, MAY_TRUNC|MAY_OWNER_OVERRIDE);
+ err = nfsd_permission(rqstp, fhp->fh_export, dentry, MAY_TRUNC|MAY_OWNER_OVERRIDE);
if (err)
goto out;
}
if (iap->ia_valid & ATTR_MODE) {
iap->ia_mode &= S_IALLUGO;
imode = iap->ia_mode |= (imode & ~S_IALLUGO);
+ /* if changing uid/gid revoke setuid/setgid in mode */
+ if ((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid) {
+ iap->ia_valid |= ATTR_KILL_PRIV;
+ iap->ia_mode &= ~S_ISUID;
+ }
+ if ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid)
+ iap->ia_mode &= ~S_ISGID;
+ } else {
+ /*
+ * Revoke setuid/setgid bit on chown/chgrp
+ */
+ if ((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid)
+ iap->ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV;
+ if ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid)
+ iap->ia_valid |= ATTR_KILL_SGID;
}
- /* Revoke setuid/setgid bit on chown/chgrp */
- if ((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid)
- iap->ia_valid |= ATTR_KILL_SUID;
- if ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid)
- iap->ia_valid |= ATTR_KILL_SGID;
-
/* Change the attributes. */
iap->ia_valid |= ATTR_CTIME;
sresult |= map->access;
- err2 = nfsd_permission(export, dentry, map->how);
+ err2 = nfsd_permission(rqstp, export, dentry, map->how);
switch (err2) {
case nfs_ok:
result |= map->access;
err = nfserr_perm;
if (IS_APPEND(inode) && (access & MAY_WRITE))
goto out;
- if (IS_ISMNDLK(inode))
+ /*
+ * We must ignore files (but only files) which might have mandatory
+ * locks on them because there is no way to know if the accesser has
+ * the lock.
+ */
+ if (S_ISREG((inode)->i_mode) && mandatory_lock(inode))
goto out;
if (!inode->i_fop)
DQUOT_INIT(inode);
}
- *filp = dentry_open(dget(dentry), mntget(fhp->fh_export->ex_mnt), flags);
+ *filp = dentry_open(dget(dentry), mntget(fhp->fh_export->ex_path.mnt),
+ flags);
if (IS_ERR(*filp))
host_err = PTR_ERR(*filp);
out_nfserr:
return __splice_from_pipe(pipe, sd, nfsd_splice_actor);
}
+static inline int svc_msnfs(struct svc_fh *ffhp)
+{
+#ifdef MSNFS
+ return (ffhp->fh_export->ex_flags & NFSEXP_MSNFS);
+#else
+ return 0;
+#endif
+}
+
static __be32
nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
err = nfserr_perm;
inode = file->f_path.dentry->d_inode;
-#ifdef MSNFS
- if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
- (!lock_may_read(inode, offset, *count)))
+
+ if (svc_msnfs(fhp) && !lock_may_read(inode, offset, *count))
goto out;
-#endif
/* Get readahead parameters */
ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino);
static void kill_suid(struct dentry *dentry)
{
struct iattr ia;
- ia.ia_valid = ATTR_KILL_SUID | ATTR_KILL_SGID;
+ ia.ia_valid = ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
mutex_lock(&dentry->d_inode->i_mutex);
notify_change(dentry, &ia);
if (EX_WGATHER(exp)) {
if (atomic_read(&inode->i_writecount) > 1
|| (last_ino == inode->i_ino && last_dev == inode->i_sb->s_dev)) {
- dprintk("nfsd: write defer %d\n", current->pid);
+ dprintk("nfsd: write defer %d\n", task_pid_nr(current));
msleep(10);
- dprintk("nfsd: write resume %d\n", current->pid);
+ dprintk("nfsd: write resume %d\n", task_pid_nr(current));
}
if (inode->i_state & I_DIRTY) {
- dprintk("nfsd: write sync %d\n", current->pid);
+ dprintk("nfsd: write sync %d\n", task_pid_nr(current));
host_err=nfsd_sync(file);
}
#if 0
__be32 err;
if (file) {
- err = nfsd_permission(fhp->fh_export, fhp->fh_dentry,
+ err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
MAY_READ|MAY_OWNER_OVERRIDE);
if (err)
goto out;
__be32 err = 0;
if (file) {
- err = nfsd_permission(fhp->fh_export, fhp->fh_dentry,
+ err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
MAY_WRITE|MAY_OWNER_OVERRIDE);
if (err)
goto out;
}
#endif /* CONFIG_NFSD_V3 */
+__be32
+nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp,
+ struct iattr *iap)
+{
+ /*
+ * Mode has already been set earlier in create:
+ */
+ iap->ia_valid &= ~ATTR_MODE;
+ /*
+ * Setting uid/gid works only for root. Irix appears to
+ * send along the gid on create when it tries to implement
+ * setgid directories via NFS:
+ */
+ if (current->fsuid != 0)
+ iap->ia_valid &= ~(ATTR_UID|ATTR_GID);
+ if (iap->ia_valid)
+ return nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0);
+ return 0;
+}
+
/*
* Create a file (regular, directory, device, fifo); UNIX sockets
* not yet implemented.
struct dentry *dentry, *dchild = NULL;
struct inode *dirp;
__be32 err;
+ __be32 err2;
int host_err;
err = nfserr_perm;
}
- /* Set file attributes. Mode has already been set and
- * setting uid/gid works only for root. Irix appears to
- * send along the gid when it tries to implement setgid
- * directories via NFS.
- */
- if ((iap->ia_valid &= ~(ATTR_UID|ATTR_GID|ATTR_MODE)) != 0) {
- __be32 err2 = nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0);
- if (err2)
- err = err2;
- }
+ err2 = nfsd_create_setattr(rqstp, resfhp, iap);
+ if (err2)
+ err = err2;
/*
* Update the file handle to get the new inode info.
*/
struct dentry *dentry, *dchild = NULL;
struct inode *dirp;
__be32 err;
+ __be32 err2;
int host_err;
__u32 v_mtime=0, v_atime=0;
if (createmode == NFS3_CREATE_EXCLUSIVE) {
/* solaris7 gets confused (bugid 4218508) if these have
- * the high bit set, so just clear the high bits.
+ * the high bit set, so just clear the high bits. If this is
+ * ever changed to use different attrs for storing the
+ * verifier, then do_open_lookup() will also need to be fixed
+ * accordingly.
*/
v_mtime = verifier[0]&0x7fffffff;
v_atime = verifier[1]&0x7fffffff;
iap->ia_atime.tv_nsec = 0;
}
- /* Set file attributes.
- * Irix appears to send along the gid when it tries to
- * implement setgid directories via NFS. Clear out all that cruft.
- */
set_attr:
- if ((iap->ia_valid &= ~(ATTR_UID|ATTR_GID|ATTR_MODE)) != 0) {
- __be32 err2 = nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0);
- if (err2)
- err = err2;
- }
+ err2 = nfsd_create_setattr(rqstp, resfhp, iap);
+ if (err2)
+ err = err2;
/*
* Update the filehandle to get the new inode info.
if (!inode->i_op || !inode->i_op->readlink)
goto out;
- touch_atime(fhp->fh_export->ex_mnt, dentry);
+ touch_atime(fhp->fh_export->ex_path.mnt, dentry);
/* N.B. Why does this call need a get_fs()??
* Remove the set_fs and watch the fireworks:-) --okir
*/
if (!type)
type = rdentry->d_inode->i_mode & S_IFMT;
+ host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
+ if (host_err)
+ goto out_nfserr;
+
if (type != S_IFDIR) { /* It's UNLINK */
#ifdef MSNFS
if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
dput(rdentry);
if (host_err)
- goto out_nfserr;
+ goto out_drop;
if (EX_ISSYNC(fhp->fh_export))
host_err = nfsd_sync_dir(dentry);
+out_drop:
+ mnt_drop_write(fhp->fh_export->ex_path.mnt);
out_nfserr:
err = nfserrno(host_err);
out:
return err;
}
+static int exp_rdonly(struct svc_rqst *rqstp, struct svc_export *exp)
+{
+ return nfsexp_flags(rqstp, exp) & NFSEXP_READONLY;
+}
+
/*
* Check for a user's access permissions to this inode.
*/
__be32
-nfsd_permission(struct svc_export *exp, struct dentry *dentry, int acc)
+nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
+ struct dentry *dentry, int acc)
{
struct inode *inode = dentry->d_inode;
int err;
*/
if (!(acc & MAY_LOCAL_ACCESS))
if (acc & (MAY_WRITE | MAY_SATTR | MAY_TRUNC)) {
- if (EX_RDONLY(exp) || IS_RDONLY(inode))
+ if (exp_rdonly(rqstp, exp) || IS_RDONLY(inode))
return nfserr_rofs;
if (/* (acc & MAY_WRITE) && */ IS_IMMUTABLE(inode))
return nfserr_perm;
raparm_hash[i].pb_head = NULL;
spin_lock_init(&raparm_hash[i].pb_lock);
}
- nperbucket = cache_size >> RAPARM_HASH_BITS;
+ nperbucket = DIV_ROUND_UP(cache_size, RAPARM_HASH_SIZE);
for (i = 0; i < cache_size - 1; i++) {
if (i % nperbucket == 0)
raparm_hash[j++].pb_head = raparml + i;