1 files changed, 85 insertions, 101 deletions

diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 661a6cf8e826..fd0acca5370a 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1,4 +1,3 @@
-#define MSNFS   /* HACK HACK */
 /*
  * File operations used by nfsd. Some of these have been ripped from
  * other parts of the kernel because they weren't exported, others
@@ -35,8 +34,8 @@
 #endif /* CONFIG_NFSD_V3 */
 
 #ifdef CONFIG_NFSD_V4
-#include <linux/nfs4_acl.h>
-#include <linux/nfsd_idmap.h>
+#include "acl.h"
+#include "idmap.h"
 #endif /* CONFIG_NFSD_V4 */
 
 #include "nfsd.h"
@@ -88,8 +87,9 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
                             .dentry = dget(dentry)};
         int err = 0;
 
-        while (d_mountpoint(path.dentry) && follow_down(&path))
-                ;
+        err = follow_down(&path);
+        if (err < 0)
+                goto out;
 
         exp2 = rqst_exp_get_by_name(rqstp, &path);
         if (IS_ERR(exp2)) {
@@ -181,16 +181,10 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
         struct svc_export       *exp;
         struct dentry           *dparent;
         struct dentry           *dentry;
-        __be32                  err;
         int                     host_err;
 
         dprintk("nfsd: nfsd_lookup(fh %s, %.*s)\n", SVCFH_fmt(fhp), len,name);
 
-        /* Obtain dentry and export. */
-        err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
-        if (err)
-                return err;
-
         dparent = fhp->fh_dentry;
         exp  = fhp->fh_export;
         exp_get(exp);
@@ -254,6 +248,9 @@ nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
         struct dentry           *dentry;
         __be32 err;
 
+        err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
+        if (err)
+                return err;
         err = nfsd_lookup_dentry(rqstp, fhp, name, len, &exp, &dentry);
         if (err)
                 return err;
@@ -273,6 +270,13 @@ out:
         return err;
 }
 
+static int nfsd_break_lease(struct inode *inode)
+{
+        if (!S_ISREG(inode->i_mode))
+                return 0;
+        return break_lease(inode, O_WRONLY | O_NONBLOCK);
+}
+
 /*
  * Commit metadata changes to stable storage.
  */
@@ -281,23 +285,13 @@ 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;
+        if (export_ops->commit_metadata)
+                return export_ops->commit_metadata(inode);
+        return sync_inode_metadata(inode, 1);
 }
 
 /*
@@ -385,16 +379,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
                                 goto out;
                 }
 
-                /*
-                 * If we are changing the size of the file, then
-                 * we need to break all leases.
-                 */
-                host_err = break_lease(inode, O_WRONLY | O_NONBLOCK);
-                if (host_err == -EWOULDBLOCK)
-                        host_err = -ETIMEDOUT;
-                if (host_err) /* ENOMEM or EWOULDBLOCK */
-                        goto out_nfserr;
-
                 host_err = get_write_access(inode);
                 if (host_err)
                         goto out_nfserr;
@@ -435,7 +419,11 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 
         err = nfserr_notsync;
         if (!check_guard || guardtime == inode->i_ctime.tv_sec) {
+                host_err = nfsd_break_lease(inode);
+                if (host_err)
+                        goto out_nfserr;
                 fh_lock(fhp);
+
                 host_err = notify_change(dentry, iap);
                 err = nfserrno(host_err);
                 fh_unlock(fhp);
@@ -708,7 +696,15 @@ nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *suppor
 }
 #endif /* CONFIG_NFSD_V3 */
 
+static int nfsd_open_break_lease(struct inode *inode, int access)
+{
+        unsigned int mode;
 
+        if (access & NFSD_MAY_NOT_BREAK_LEASE)
+                return 0;
+        mode = (access & NFSD_MAY_WRITE) ? O_WRONLY : O_RDONLY;
+        return break_lease(inode, mode | O_NONBLOCK);
+}
 
 /*
  * Open an existing file or directory.
@@ -756,14 +752,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
         if (!inode->i_fop)
                 goto out;
 
-        /*
-         * Check to see if there are any leases on this file.
-         * This may block while leases are broken.
-         */
-        if (!(access & NFSD_MAY_NOT_BREAK_LEASE))
-                host_err = break_lease(inode, O_NONBLOCK | ((access & NFSD_MAY_WRITE) ? O_WRONLY : 0));
-        if (host_err == -EWOULDBLOCK)
-                host_err = -ETIMEDOUT;
+        host_err = nfsd_open_break_lease(inode, access);
         if (host_err) /* NOMEM or WOULDBLOCK */
                 goto out_nfserr;
 
@@ -819,7 +808,7 @@ nfsd_get_raparms(dev_t dev, ino_t ino)
                 if (ra->p_count == 0)
                         frap = rap;
         }
-        depth = nfsdstats.ra_size*11/10;
+        depth = nfsdstats.ra_size;
         if (!frap) {    
                 spin_unlock(&rab->pb_lock);
                 return NULL;
@@ -855,11 +844,6 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
         struct page **pp = rqstp->rq_respages + rqstp->rq_resused;
         struct page *page = buf->page;
         size_t size;
-        int ret;
-
-        ret = buf->ops->confirm(pipe, buf);
-        if (unlikely(ret))
-                return ret;
 
         size = sd->len;
 
@@ -889,29 +873,15 @@ static int nfsd_direct_splice_actor(struct pipe_inode_info *pipe,
         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)
 {
-        struct inode *inode;
         mm_segment_t    oldfs;
         __be32          err;
         int             host_err;
 
         err = nfserr_perm;
-        inode = file->f_path.dentry->d_inode;
-
-        if (svc_msnfs(fhp) && !lock_may_read(inode, offset, *count))
-                goto out;
 
         if (file->f_op->splice_read && rqstp->rq_splice_ok) {
                 struct splice_desc sd = {
@@ -937,7 +907,6 @@ nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
                 fsnotify_access(file);
         } else 
                 err = nfserrno(host_err);
-out:
         return err;
 }
 
@@ -1002,14 +971,6 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
         int                     stable = *stablep;
         int                     use_wgather;
 
-#ifdef MSNFS
-        err = nfserr_perm;
-
-        if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
-                (!lock_may_write(file->f_path.dentry->d_inode, offset, *cnt)))
-                goto out;
-#endif
-
         dentry = file->f_path.dentry;
         inode = dentry->d_inode;
         exp   = fhp->fh_export;
@@ -1060,7 +1021,6 @@ out_nfserr:
                 err = 0;
         else
                 err = nfserrno(host_err);
-out:
         return err;
 }
 
@@ -1378,11 +1338,18 @@ out_nfserr:
 }
 
 #ifdef CONFIG_NFSD_V3
+
+static inline int nfsd_create_is_exclusive(int createmode)
+{
+        return createmode == NFS3_CREATE_EXCLUSIVE
+               || createmode == NFS4_CREATE_EXCLUSIVE4_1;
+}
+
 /*
- * NFSv3 version of nfsd_create
+ * NFSv3 and NFSv4 version of nfsd_create
  */
 __be32
-nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
+do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
                 char *fname, int flen, struct iattr *iap,
                 struct svc_fh *resfhp, int createmode, u32 *verifier,
                 int *truncp, int *created)
@@ -1401,7 +1368,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
                 goto out;
         if (!(iap->ia_valid & ATTR_MODE))
                 iap->ia_mode = 0;
-        err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE);
+        err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
         if (err)
                 goto out;
 
@@ -1423,11 +1390,18 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
         if (IS_ERR(dchild))
                 goto out_nfserr;
 
+        /* If file doesn't exist, check for permissions to create one */
+        if (!dchild->d_inode) {
+                err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE);
+                if (err)
+                        goto out;
+        }
+
         err = fh_compose(resfhp, fhp->fh_export, dchild, fhp);
         if (err)
                 goto out;
 
-        if (createmode == NFS3_CREATE_EXCLUSIVE) {
+        if (nfsd_create_is_exclusive(createmode)) {
                 /* solaris7 gets confused (bugid 4218508) if these have
                  * the high bit set, so just clear the high bits. If this is
                  * ever changed to use different attrs for storing the
@@ -1468,6 +1442,11 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
                             && dchild->d_inode->i_atime.tv_sec == v_atime
                             && dchild->d_inode->i_size  == 0 )
                                 break;
+                case NFS4_CREATE_EXCLUSIVE4_1:
+                        if (   dchild->d_inode->i_mtime.tv_sec == v_mtime
+                            && dchild->d_inode->i_atime.tv_sec == v_atime
+                            && dchild->d_inode->i_size  == 0 )
+                                goto set_attr;
                          /* fallthru */
                 case NFS3_CREATE_GUARDED:
                         err = nfserr_exist;
@@ -1486,7 +1465,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
 
         nfsd_check_ignore_resizing(iap);
 
-        if (createmode == NFS3_CREATE_EXCLUSIVE) {
+        if (nfsd_create_is_exclusive(createmode)) {
                 /* Cram the verifier into atime/mtime */
                 iap->ia_valid = ATTR_MTIME|ATTR_ATIME
                         | ATTR_MTIME_SET|ATTR_ATIME_SET;
@@ -1680,6 +1659,14 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
                 err = nfserrno(host_err);
                 goto out_dput;
         }
+        err = nfserr_noent;
+        if (!dold->d_inode)
+                goto out_drop_write;
+        host_err = nfsd_break_lease(dold->d_inode);
+        if (host_err) {
+                err = nfserrno(host_err);
+                goto out_drop_write;
+        }
         host_err = vfs_link(dold, dirp, dnew);
         if (!host_err) {
                 err = nfserrno(commit_metadata(ffhp));
@@ -1691,6 +1678,7 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
                 else
                         err = nfserrno(host_err);
         }
+out_drop_write:
         mnt_drop_write(tfhp->fh_export->ex_path.mnt);
 out_dput:
         dput(dnew);
@@ -1765,13 +1753,6 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
         if (ndentry == trap)
                 goto out_dput_new;
 
-        if (svc_msnfs(ffhp) &&
-                ((atomic_read(&odentry->d_count) > 1)
-                 || (atomic_read(&ndentry->d_count) > 1))) {
-                        host_err = -EPERM;
-                        goto out_dput_new;
-        }
-
         host_err = -EXDEV;
         if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt)
                 goto out_dput_new;
@@ -1779,15 +1760,22 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
         if (host_err)
                 goto out_dput_new;
 
+        host_err = nfsd_break_lease(odentry->d_inode);
+        if (host_err)
+                goto out_drop_write;
+        if (ndentry->d_inode) {
+                host_err = nfsd_break_lease(ndentry->d_inode);
+                if (host_err)
+                        goto out_drop_write;
+        }
         host_err = vfs_rename(fdir, odentry, tdir, ndentry);
         if (!host_err) {
                 host_err = commit_metadata(tfhp);
                 if (!host_err)
                         host_err = commit_metadata(ffhp);
         }
-
+out_drop_write:
         mnt_drop_write(ffhp->fh_export->ex_path.mnt);
-
  out_dput_new:
         dput(ndentry);
  out_dput_old:
@@ -1848,26 +1836,22 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 
         host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
         if (host_err)
-                goto out_nfserr;
+                goto out_put;
 
-        if (type != S_IFDIR) { /* It's UNLINK */
-#ifdef MSNFS
-                if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
-                        (atomic_read(&rdentry->d_count) > 1)) {
-                        host_err = -EPERM;
-                } else
-#endif
+        host_err = nfsd_break_lease(rdentry->d_inode);
+        if (host_err)
+                goto out_drop_write;
+        if (type != S_IFDIR)
                 host_err = vfs_unlink(dirp, rdentry);
-        } else { /* It's RMDIR */
+        else
                 host_err = vfs_rmdir(dirp, rdentry);
-        }
-
-        dput(rdentry);
-
         if (!host_err)
                 host_err = commit_metadata(fhp);
-
+out_drop_write:
         mnt_drop_write(fhp->fh_export->ex_path.mnt);
+out_put:
+        dput(rdentry);
+
 out_nfserr:
         err = nfserrno(host_err);
 out:
@@ -2062,7 +2046,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
         struct inode    *inode = dentry->d_inode;
         int             err;
 
-        if (acc == NFSD_MAY_NOP)
+        if ((acc & NFSD_MAY_MASK) == NFSD_MAY_NOP)
                 return 0;
 #if 0
         dprintk("nfsd: permission 0x%x%s%s%s%s%s%s%s mode 0%o%s%s%s\n",