1 files changed, 148 insertions, 155 deletions

diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index a293f0273263..6dd5f1970e01 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1,7 +1,5 @@
 #define MSNFS   /* HACK HACK */
 /*
- * linux/fs/nfsd/vfs.c
- *
  * File operations used by nfsd. Some of these have been ripped from
  * other parts of the kernel because they weren't exported, others
  * are partial duplicates with added or changed functionality.
@@ -16,48 +14,33 @@
  * Zerocpy NFS support (C) 2002 Hirokazu Takahashi <taka@valinux.co.jp>
  */
 
-#include <linux/string.h>
-#include <linux/time.h>
-#include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/file.h>
-#include <linux/mount.h>
-#include <linux/major.h>
 #include <linux/splice.h>
-#include <linux/proc_fs.h>
-#include <linux/stat.h>
 #include <linux/fcntl.h>
-#include <linux/net.h>
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/pagemap.h>
-#include <linux/in.h>
-#include <linux/module.h>
 #include <linux/namei.h>
-#include <linux/vfs.h>
 #include <linux/delay.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#ifdef CONFIG_NFSD_V3
-#include <linux/nfs3.h>
-#include <linux/nfsd/xdr3.h>
-#endif /* CONFIG_NFSD_V3 */
-#include <linux/nfsd/nfsfh.h>
-#include <linux/quotaops.h>
 #include <linux/fsnotify.h>
-#include <linux/posix_acl.h>
 #include <linux/posix_acl_xattr.h>
 #include <linux/xattr.h>
+#include <linux/jhash.h>
+#include <linux/ima.h>
+#include <linux/slab.h>
+#include <asm/uaccess.h>
+#include <linux/exportfs.h>
+#include <linux/writeback.h>
+
+#ifdef CONFIG_NFSD_V3
+#include "xdr3.h"
+#endif /* CONFIG_NFSD_V3 */
+
 #ifdef CONFIG_NFSD_V4
-#include <linux/nfs4.h>
 #include <linux/nfs4_acl.h>
 #include <linux/nfsd_idmap.h>
-#include <linux/security.h>
 #endif /* CONFIG_NFSD_V4 */
-#include <linux/jhash.h>
-#include <linux/ima.h>
 
-#include <asm/uaccess.h>
+#include "nfsd.h"
+#include "vfs.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_FILEOP
 
@@ -89,12 +72,6 @@ struct raparm_hbucket {
 #define RAPARM_HASH_MASK        (RAPARM_HASH_SIZE-1)
 static struct raparm_hbucket    raparm_hash[RAPARM_HASH_SIZE];
 
-static inline int
-nfsd_v4client(struct svc_rqst *rq)
-{
-    return rq->rq_prog == NFS_PROGRAM && rq->rq_vers == 4;
-}
-
 /* 
  * Called from nfsd_lookup and encode_dirent. Check if we have crossed 
  * a mount point.
@@ -116,8 +93,16 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
 
         exp2 = rqst_exp_get_by_name(rqstp, &path);
         if (IS_ERR(exp2)) {
-                if (PTR_ERR(exp2) != -ENOENT)
-                        err = PTR_ERR(exp2);
+                err = PTR_ERR(exp2);
+                /*
+                 * We normally allow NFS clients to continue
+                 * "underneath" a mountpoint that is not exported.
+                 * The exception is V4ROOT, where no traversal is ever
+                 * allowed without an explicit export of the new
+                 * directory.
+                 */
+                if (err == -ENOENT && !(exp->ex_flags & NFSEXP_V4ROOT))
+                        err = 0;
                 path_put(&path);
                 goto out;
         }
@@ -141,6 +126,53 @@ out:
         return err;
 }
 
+static void follow_to_parent(struct path *path)
+{
+        struct dentry *dp;
+
+        while (path->dentry == path->mnt->mnt_root && follow_up(path))
+                ;
+        dp = dget_parent(path->dentry);
+        dput(path->dentry);
+        path->dentry = dp;
+}
+
+static int nfsd_lookup_parent(struct svc_rqst *rqstp, struct dentry *dparent, struct svc_export **exp, struct dentry **dentryp)
+{
+        struct svc_export *exp2;
+        struct path path = {.mnt = mntget((*exp)->ex_path.mnt),
+                            .dentry = dget(dparent)};
+
+        follow_to_parent(&path);
+
+        exp2 = rqst_exp_parent(rqstp, &path);
+        if (PTR_ERR(exp2) == -ENOENT) {
+                *dentryp = dget(dparent);
+        } else if (IS_ERR(exp2)) {
+                path_put(&path);
+                return PTR_ERR(exp2);
+        } else {
+                *dentryp = dget(path.dentry);
+                exp_put(*exp);
+                *exp = exp2;
+        }
+        path_put(&path);
+        return 0;
+}
+
+/*
+ * For nfsd purposes, we treat V4ROOT exports as though there was an
+ * export at *every* directory.
+ */
+int nfsd_mountpoint(struct dentry *dentry, struct svc_export *exp)
+{
+        if (d_mountpoint(dentry))
+                return 1;
+        if (!(exp->ex_flags & NFSEXP_V4ROOT))
+                return 0;
+        return dentry->d_inode != NULL;
+}
+
 __be32
 nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
                    const char *name, unsigned int len,
@@ -169,35 +201,13 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
                         dentry = dget(dparent);
                 else if (dparent != exp->ex_path.dentry)
                         dentry = dget_parent(dparent);
-                else if (!EX_NOHIDE(exp))
+                else if (!EX_NOHIDE(exp) && !nfsd_v4client(rqstp))
                         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 path path = {.mnt = mntget(exp->ex_path.mnt),
-                                            .dentry = dget(dparent)};
-
-                        while (path.dentry == path.mnt->mnt_root &&
-                               follow_up(&path))
-                                ;
-                        dp = dget_parent(path.dentry);
-                        dput(path.dentry);
-                        path.dentry = dp;
-
-                        exp2 = rqst_exp_parent(rqstp, &path);
-                        if (PTR_ERR(exp2) == -ENOENT) {
-                                dentry = dget(dparent);
-                        } else if (IS_ERR(exp2)) {
-                                host_err = PTR_ERR(exp2);
-                                path_put(&path);
+                        host_err = nfsd_lookup_parent(rqstp, dparent, &exp, &dentry);
+                        if (host_err)
                                 goto out_nfserr;
-                        } else {
-                                dentry = dget(path.dentry);
-                                exp_put(exp);
-                                exp = exp2;
-                        }
-                        path_put(&path);
                 }
         } else {
                 fh_lock(fhp);
@@ -208,7 +218,7 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
                 /*
                  * check if we have crossed a mount point ...
                  */
-                if (d_mountpoint(dentry)) {
+                if (nfsd_mountpoint(dentry, exp)) {
                         if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) {
                                 dput(dentry);
                                 goto out_nfserr;
@@ -263,6 +273,32 @@ out:
         return err;
 }
 
+/*
+ * Commit metadata changes to stable storage.
+ */
+static int
+commit_metadata(struct svc_fh *fhp)
+{
+        struct inode *inode = fhp->fh_dentry->d_inode;
+        const struct export_operations *export_ops = inode->i_sb->s_export_op;
+        int error = 0;
+
+        if (!EX_ISSYNC(fhp->fh_export))
+                return 0;
+
+        if (export_ops->commit_metadata) {
+                error = export_ops->commit_metadata(inode);
+        } else {
+                struct writeback_control wbc = {
+                        .sync_mode = WB_SYNC_ALL,
+                        .nr_to_write = 0, /* metadata only */
+                };
+
+                error = sync_inode(inode, &wbc);
+        }
+
+        return error;
+}
 
 /*
  * Set various file attributes.
@@ -353,7 +389,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
                  * If we are changing the size of the file, then
                  * we need to break all leases.
                  */
-                host_err = break_lease(inode, FMODE_WRITE | O_NONBLOCK);
+                host_err = break_lease(inode, O_WRONLY | O_NONBLOCK);
                 if (host_err == -EWOULDBLOCK)
                         host_err = -ETIMEDOUT;
                 if (host_err) /* ENOMEM or EWOULDBLOCK */
@@ -369,7 +405,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
                         put_write_access(inode);
                         goto out_nfserr;
                 }
-                vfs_dq_init(inode);
         }
 
         /* sanitize the mode change */
@@ -726,7 +761,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
          * Check to see if there are any leases on this file.
          * This may block while leases are broken.
          */
-        host_err = break_lease(inode, O_NONBLOCK | ((access & NFSD_MAY_WRITE) ? FMODE_WRITE : 0));
+        host_err = break_lease(inode, O_NONBLOCK | ((access & NFSD_MAY_WRITE) ? O_WRONLY : 0));
         if (host_err == -EWOULDBLOCK)
                 host_err = -ETIMEDOUT;
         if (host_err) /* NOMEM or WOULDBLOCK */
@@ -737,15 +772,13 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
                         flags = O_RDWR|O_LARGEFILE;
                 else
                         flags = O_WRONLY|O_LARGEFILE;
-
-                vfs_dq_init(inode);
         }
         *filp = dentry_open(dget(dentry), mntget(fhp->fh_export->ex_path.mnt),
                             flags, current_cred());
         if (IS_ERR(*filp))
                 host_err = PTR_ERR(*filp);
         else
-                ima_counts_get(*filp);
+                host_err = ima_file_check(*filp, access);
 out_nfserr:
         err = nfserrno(host_err);
 out:
@@ -763,46 +796,6 @@ nfsd_close(struct file *filp)
 }
 
 /*
- * Sync a file
- * As this calls fsync (not fdatasync) there is no need for a write_inode
- * after it.
- */
-static inline int nfsd_dosync(struct file *filp, struct dentry *dp,
-                              const struct file_operations *fop)
-{
-        struct inode *inode = dp->d_inode;
-        int (*fsync) (struct file *, struct dentry *, int);
-        int err;
-
-        err = filemap_fdatawrite(inode->i_mapping);
-        if (err == 0 && fop && (fsync = fop->fsync))
-                err = fsync(filp, dp, 0);
-        if (err == 0)
-                err = filemap_fdatawait(inode->i_mapping);
-
-        return err;
-}
-
-static int
-nfsd_sync(struct file *filp)
-{
-        int err;
-        struct inode *inode = filp->f_path.dentry->d_inode;
-        dprintk("nfsd: sync file %s\n", filp->f_path.dentry->d_name.name);
-        mutex_lock(&inode->i_mutex);
-        err=nfsd_dosync(filp, filp->f_path.dentry, filp->f_op);
-        mutex_unlock(&inode->i_mutex);
-
-        return err;
-}
-
-int
-nfsd_sync_dir(struct dentry *dp)
-{
-        return nfsd_dosync(NULL, dp, dp->d_inode->i_fop);
-}
-
-/*
  * Obtain the readahead parameters for the file
  * specified by (dev, ino).
  */
@@ -1005,7 +998,7 @@ static int wait_for_concurrent_writes(struct file *file)
 
         if (inode->i_state & I_DIRTY) {
                 dprintk("nfsd: write sync %d\n", task_pid_nr(current));
-                err = nfsd_sync(file);
+                err = vfs_fsync(file, file->f_path.dentry, 0);
         }
         last_ino = inode->i_ino;
         last_dev = inode->i_sb->s_dev;
@@ -1153,8 +1146,9 @@ out:
 #ifdef CONFIG_NFSD_V3
 /*
  * Commit all pending writes to stable storage.
- * Strictly speaking, we could sync just the indicated file region here,
- * but there's currently no way we can ask the VFS to do so.
+ *
+ * Note: we only guarantee that data that lies within the range specified
+ * by the 'offset' and 'count' parameters will be synced.
  *
  * Unfortunately we cannot lock the file to make sure we return full WCC
  * data to the client, as locking happens lower down in the filesystem.
@@ -1164,23 +1158,32 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
                loff_t offset, unsigned long count)
 {
         struct file     *file;
-        __be32          err;
+        loff_t          end = LLONG_MAX;
+        __be32          err = nfserr_inval;
 
-        if ((u64)count > ~(u64)offset)
-                return nfserr_inval;
+        if (offset < 0)
+                goto out;
+        if (count != 0) {
+                end = offset + (loff_t)count - 1;
+                if (end < offset)
+                        goto out;
+        }
 
         err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_WRITE, &file);
         if (err)
-                return err;
+                goto out;
         if (EX_ISSYNC(fhp->fh_export)) {
-                if (file->f_op && file->f_op->fsync) {
-                        err = nfserrno(nfsd_sync(file));
-                } else {
+                int err2 = vfs_fsync_range(file, file->f_path.dentry,
+                                offset, end, 0);
+
+                if (err2 != -EINVAL)
+                        err = nfserrno(err2);
+                else
                         err = nfserr_notsupp;
-                }
         }
 
         nfsd_close(file);
+out:
         return err;
 }
 #endif /* CONFIG_NFSD_V3 */
@@ -1333,12 +1336,14 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
                 goto out_nfserr;
         }
 
-        if (EX_ISSYNC(fhp->fh_export)) {
-                err = nfserrno(nfsd_sync_dir(dentry));
-                write_inode_now(dchild->d_inode, 1);
-        }
+        err = nfsd_create_setattr(rqstp, resfhp, iap);
 
-        err2 = nfsd_create_setattr(rqstp, resfhp, iap);
+        /*
+         * nfsd_setattr already committed the child.  Transactional filesystems
+         * had a chance to commit changes for both parent and child
+         * simultaneously making the following commit_metadata a noop.
+         */
+        err2 = nfserrno(commit_metadata(fhp));
         if (err2)
                 err = err2;
         mnt_drop_write(fhp->fh_export->ex_path.mnt);
@@ -1370,7 +1375,6 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
         struct dentry   *dentry, *dchild = NULL;
         struct inode    *dirp;
         __be32          err;
-        __be32          err2;
         int             host_err;
         __u32           v_mtime=0, v_atime=0;
 
@@ -1465,11 +1469,6 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
         if (created)
                 *created = 1;
 
-        if (EX_ISSYNC(fhp->fh_export)) {
-                err = nfserrno(nfsd_sync_dir(dentry));
-                /* setattr will sync the child (or not) */
-        }
-
         nfsd_check_ignore_resizing(iap);
 
         if (createmode == NFS3_CREATE_EXCLUSIVE) {
@@ -1484,9 +1483,13 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
         }
 
  set_attr:
-        err2 = nfsd_create_setattr(rqstp, resfhp, iap);
-        if (err2)
-                err = err2;
+        err = nfsd_create_setattr(rqstp, resfhp, iap);
+
+        /*
+         * nfsd_setattr already committed the child (and possibly also the parent).
+         */
+        if (!err)
+                err = nfserrno(commit_metadata(fhp));
 
         mnt_drop_write(fhp->fh_export->ex_path.mnt);
         /*
@@ -1601,12 +1604,9 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
                 }
         } else
                 host_err = vfs_symlink(dentry->d_inode, dnew, path);
-
-        if (!host_err) {
-                if (EX_ISSYNC(fhp->fh_export))
-                        host_err = nfsd_sync_dir(dentry);
-        }
         err = nfserrno(host_err);
+        if (!err)
+                err = nfserrno(commit_metadata(fhp));
         fh_unlock(fhp);
 
         mnt_drop_write(fhp->fh_export->ex_path.mnt);
@@ -1668,11 +1668,9 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
         }
         host_err = vfs_link(dold, dirp, dnew);
         if (!host_err) {
-                if (EX_ISSYNC(ffhp->fh_export)) {
-                        err = nfserrno(nfsd_sync_dir(ddir));
-                        write_inode_now(dest, 1);
-                }
-                err = 0;
+                err = nfserrno(commit_metadata(ffhp));
+                if (!err)
+                        err = nfserrno(commit_metadata(tfhp));
         } else {
                 if (host_err == -EXDEV && rqstp->rq_vers == 2)
                         err = nfserr_acces;
@@ -1768,10 +1766,10 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
                 goto out_dput_new;
 
         host_err = vfs_rename(fdir, odentry, tdir, ndentry);
-        if (!host_err && EX_ISSYNC(tfhp->fh_export)) {
-                host_err = nfsd_sync_dir(tdentry);
+        if (!host_err) {
+                host_err = commit_metadata(tfhp);
                 if (!host_err)
-                        host_err = nfsd_sync_dir(fdentry);
+                        host_err = commit_metadata(ffhp);
         }
 
         mnt_drop_write(ffhp->fh_export->ex_path.mnt);
@@ -1852,12 +1850,9 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 
         dput(rdentry);
 
-        if (host_err)
-                goto out_drop;
-        if (EX_ISSYNC(fhp->fh_export))
-                host_err = nfsd_sync_dir(dentry);
+        if (!host_err)
+                host_err = commit_metadata(fhp);
 
-out_drop:
         mnt_drop_write(fhp->fh_export->ex_path.mnt);
 out_nfserr:
         err = nfserrno(host_err);
@@ -2124,8 +2119,6 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
          */
         path.mnt = exp->ex_path.mnt;
         path.dentry = dentry;
-        err = ima_path_check(&path, acc & (MAY_READ | MAY_WRITE | MAY_EXEC),
-                             IMA_COUNT_LEAVE);
 nfsd_out:
         return err? nfserrno(err) : 0;
 }