Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

Pull two Ceph fixes from Sage Weil:
 "One of these is fixing a regression from the d_flags file type patch
  that went into -rc1 that broke instantiation of inodes and dentries
  (we were doing dentries first).  The other is just an off-by-one
  corner case"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client:
  ceph: Avoid data inconsistency due to d-cache aliasing in readpage()
  ceph: initialize inode before instantiating dentry

2 files changed, 64 insertions, 80 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 1e561c059539..ec3ba43b9faa 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -210,9 +210,13 @@ static int readpage_nounlock(struct file *filp, struct page *page)
         if (err < 0) {
                 SetPageError(page);
                 goto out;
-        } else if (err < PAGE_CACHE_SIZE) {
+        } else {
+                if (err < PAGE_CACHE_SIZE) {
                 /* zero fill remainder of page */
-                zero_user_segment(page, err, PAGE_CACHE_SIZE);
+                        zero_user_segment(page, err, PAGE_CACHE_SIZE);
+                } else {
+                        flush_dcache_page(page);
+                }
         }
         SetPageUptodate(page);
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 9a8e396aed89..278fd2891288 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -978,7 +978,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
         struct ceph_mds_reply_inode *ininfo;
         struct ceph_vino vino;
         struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
-        int i = 0;
         int err = 0;
 
         dout("fill_trace %p is_dentry %d is_target %d\n", req,
@@ -1039,6 +1038,29 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
                 }
         }
 
+        if (rinfo->head->is_target) {
+                vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
+                vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
+
+                in = ceph_get_inode(sb, vino);
+                if (IS_ERR(in)) {
+                        err = PTR_ERR(in);
+                        goto done;
+                }
+                req->r_target_inode = in;
+
+                err = fill_inode(in, &rinfo->targeti, NULL,
+                                session, req->r_request_started,
+                                (le32_to_cpu(rinfo->head->result) == 0) ?
+                                req->r_fmode : -1,
+                                &req->r_caps_reservation);
+                if (err < 0) {
+                        pr_err("fill_inode badness %p %llx.%llx\n",
+                                in, ceph_vinop(in));
+                        goto done;
+                }
+        }
+
         /*
          * ignore null lease/binding on snapdir ENOENT, or else we
          * will have trouble splicing in the virtual snapdir later
@@ -1108,7 +1130,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
                              ceph_dentry(req->r_old_dentry)->offset);
 
                         dn = req->r_old_dentry;  /* use old_dentry */
-                        in = dn->d_inode;
                 }
 
                 /* null dentry? */
@@ -1130,44 +1151,28 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
                 }
 
                 /* attach proper inode */
-                ininfo = rinfo->targeti.in;
-                vino.ino = le64_to_cpu(ininfo->ino);
-                vino.snap = le64_to_cpu(ininfo->snapid);
-                in = dn->d_inode;
-                if (!in) {
-                        in = ceph_get_inode(sb, vino);
-                        if (IS_ERR(in)) {
-                                pr_err("fill_trace bad get_inode "
-                                       "%llx.%llx\n", vino.ino, vino.snap);
-                                err = PTR_ERR(in);
-                                d_drop(dn);
-                                goto done;
-                        }
+                if (!dn->d_inode) {
+                        ihold(in);
                         dn = splice_dentry(dn, in, &have_lease, true);
                         if (IS_ERR(dn)) {
                                 err = PTR_ERR(dn);
                                 goto done;
                         }
                         req->r_dentry = dn;  /* may have spliced */
-                        ihold(in);
-                } else if (ceph_ino(in) == vino.ino &&
-                           ceph_snap(in) == vino.snap) {
-                        ihold(in);
-                } else {
+                } else if (dn->d_inode && dn->d_inode != in) {
                         dout(" %p links to %p %llx.%llx, not %llx.%llx\n",
-                             dn, in, ceph_ino(in), ceph_snap(in),
-                             vino.ino, vino.snap);
+                             dn, dn->d_inode, ceph_vinop(dn->d_inode),
+                             ceph_vinop(in));
                         have_lease = false;
-                        in = NULL;
                 }
 
                 if (have_lease)
                         update_dentry_lease(dn, rinfo->dlease, session,
                                             req->r_request_started);
                 dout(" final dn %p\n", dn);
-                i++;
-        } else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
-                   req->r_op == CEPH_MDS_OP_MKSNAP) && !req->r_aborted) {
+        } else if (!req->r_aborted &&
+                   (req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
+                    req->r_op == CEPH_MDS_OP_MKSNAP)) {
                 struct dentry *dn = req->r_dentry;
 
                 /* fill out a snapdir LOOKUPSNAP dentry */
@@ -1177,52 +1182,15 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
                 ininfo = rinfo->targeti.in;
                 vino.ino = le64_to_cpu(ininfo->ino);
                 vino.snap = le64_to_cpu(ininfo->snapid);
-                in = ceph_get_inode(sb, vino);
-                if (IS_ERR(in)) {
-                        pr_err("fill_inode get_inode badness %llx.%llx\n",
-                               vino.ino, vino.snap);
-                        err = PTR_ERR(in);
-                        d_delete(dn);
-                        goto done;
-                }
                 dout(" linking snapped dir %p to dn %p\n", in, dn);
+                ihold(in);
                 dn = splice_dentry(dn, in, NULL, true);
                 if (IS_ERR(dn)) {
                         err = PTR_ERR(dn);
                         goto done;
                 }
                 req->r_dentry = dn;  /* may have spliced */
-                ihold(in);
-                rinfo->head->is_dentry = 1;  /* fool notrace handlers */
-        }
-
-        if (rinfo->head->is_target) {
-                vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
-                vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
-
-                if (in == NULL || ceph_ino(in) != vino.ino ||
-                    ceph_snap(in) != vino.snap) {
-                        in = ceph_get_inode(sb, vino);
-                        if (IS_ERR(in)) {
-                                err = PTR_ERR(in);
-                                goto done;
-                        }
-                }
-                req->r_target_inode = in;
-
-                err = fill_inode(in,
-                                 &rinfo->targeti, NULL,
-                                 session, req->r_request_started,
-                                 (le32_to_cpu(rinfo->head->result) == 0) ?
-                                 req->r_fmode : -1,
-                                 &req->r_caps_reservation);
-                if (err < 0) {
-                        pr_err("fill_inode badness %p %llx.%llx\n",
-                               in, ceph_vinop(in));
-                        goto done;
-                }
         }
-
 done:
         dout("fill_trace done err=%d\n", err);
         return err;
@@ -1272,7 +1240,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
         struct qstr dname;
         struct dentry *dn;
         struct inode *in;
-        int err = 0, i;
+        int err = 0, ret, i;
         struct inode *snapdir = NULL;
         struct ceph_mds_request_head *rhead = req->r_request->front.iov_base;
         struct ceph_dentry_info *di;
@@ -1305,6 +1273,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
                         ceph_fill_dirfrag(parent->d_inode, rinfo->dir_dir);
         }
 
+        /* FIXME: release caps/leases if error occurs */
         for (i = 0; i < rinfo->dir_nr; i++) {
                 struct ceph_vino vino;
 
@@ -1329,9 +1298,10 @@ retry_lookup:
                                 err = -ENOMEM;
                                 goto out;
                         }
-                        err = ceph_init_dentry(dn);
-                        if (err < 0) {
+                        ret = ceph_init_dentry(dn);
+                        if (ret < 0) {
                                 dput(dn);
+                                err = ret;
                                 goto out;
                         }
                 } else if (dn->d_inode &&
@@ -1351,9 +1321,6 @@ retry_lookup:
                         spin_unlock(&parent->d_lock);
                 }
 
-                di = dn->d_fsdata;
-                di->offset = ceph_make_fpos(frag, i + r_readdir_offset);
-
                 /* inode */
                 if (dn->d_inode) {
                         in = dn->d_inode;
@@ -1366,26 +1333,39 @@ retry_lookup:
                                 err = PTR_ERR(in);
                                 goto out;
                         }
-                        dn = splice_dentry(dn, in, NULL, false);
-                        if (IS_ERR(dn))
-                                dn = NULL;
                 }
 
                 if (fill_inode(in, &rinfo->dir_in[i], NULL, session,
                                req->r_request_started, -1,
                                &req->r_caps_reservation) < 0) {
                         pr_err("fill_inode badness on %p\n", in);
+                        if (!dn->d_inode)
+                                iput(in);
+                        d_drop(dn);
                         goto next_item;
                 }
-                if (dn)
-                        update_dentry_lease(dn, rinfo->dir_dlease[i],
-                                            req->r_session,
-                                            req->r_request_started);
+
+                if (!dn->d_inode) {
+                        dn = splice_dentry(dn, in, NULL, false);
+                        if (IS_ERR(dn)) {
+                                err = PTR_ERR(dn);
+                                dn = NULL;
+                                goto next_item;
+                        }
+                }
+
+                di = dn->d_fsdata;
+                di->offset = ceph_make_fpos(frag, i + r_readdir_offset);
+
+                update_dentry_lease(dn, rinfo->dir_dlease[i],
+                                    req->r_session,
+                                    req->r_request_started);
 next_item:
                 if (dn)
                         dput(dn);
         }
-        req->r_did_prepopulate = true;
+        if (err == 0)
+                req->r_did_prepopulate = true;
 
 out:
         if (snapdir) {