LU-11579 llite: remove cl_file_inode_init() LASSERT

If there is some corruption or other reason that the file layout
cannot be used, the first call to cl_file_inode_init() will fail.
If it is called a second time on the same file then it will hit
an LASSERT() since I_NEW is no longer set on the inode.

It would be good to handle the error in lov_init_raid0() better,
but we still want to avoid this LASSERT() if there is an error.

Convert the LASSERT() in cl_file_inode_init() into a CERROR() and
error return.  This is being triggered due to corruption on the
server, but that shouldn't cause the client to assert.

    lov_dump_lmm_common() oid 0xdf4e:311367, magic 0x0bd10bd0
    lov_dump_lmm_common() stripe_size 1048576, stripe_count 4
    lov_dump_lmm_objects() stripe 0 idx 10 subobj 0x0:151194471
    lov_dump_lmm_objects() stripe 1 idx 12 subobj 0x0:152477530
    lov_dump_lmm_objects() stripe 2 idx 25 subobj 0x0:151589797
    lov_dump_lmm_objects() stripe 3 idx 2 subobj 0x0:150332564
    lov_init_raid0() fsname-clilov: OST0019 is not initialized
    cl_file_inode_init() Failure to initialize cl object
        [0x20004c047:0xdf4e:0x0]: -5

    cl_file_inode_init() ASSERTION(inode->i_state & (1 << 3) ) failed
    cl_file_inode_init() LBUG
    Pid: 37233, comm: ll_sa_4709 3.10.0-862.14.4.el7.x86_64 #1 SMP
    Call Trace:
    libcfs_call_trace+0x8c/0xc0 [libcfs]
    lbug_with_loc+0x4c/0xa0 [libcfs]
    cl_file_inode_init+0x2ac/0x300 [lustre]
    ll_update_inode+0x315/0x600 [lustre]
    ll_iget+0x163/0x350 [lustre]
    ll_prep_inode+0x232/0xc80 [lustre]
    sa_handle_callback+0x3a4/0xf70 [lustre]
    ll_statahead_thread+0x40e/0x2080 [lustre]

Instead, return an IO error instead of killing the client.

Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: If8a6eb24df09e7e158b61f02e2517132893ebbe5
Reviewed-on: https://review.whamcloud.com/33505
Reviewed-by: Patrick Farrell <paf@cray.com>
Tested-by: Jenkins
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Bobi Jam <bobijam@hotmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

diff --git a/lustre/llite/lcommon_cl.c b/lustre/llite/lcommon_cl.c
index 010b6cc..c4b6cc9 100644 (file)
--- a/lustre/llite/lcommon_cl.c
+++ b/lustre/llite/lcommon_cl.c
@@ -152,27 +152,36 @@ int cl_file_inode_init(struct inode *inode, struct lustre_md *md)
 
        site = ll_i2sbi(inode)->ll_site;
        lli  = ll_i2info(inode);
-        fid  = &lli->lli_fid;
-        LASSERT(fid_is_sane(fid));
-
-        if (lli->lli_clob == NULL) {
-                /* clob is slave of inode, empty lli_clob means for new inode,
-                 * there is no clob in cache with the given fid, so it is
-                 * unnecessary to perform lookup-alloc-lookup-insert, just
-                 * alloc and insert directly. */
-                LASSERT(inode->i_state & I_NEW);
-                conf.coc_lu.loc_flags = LOC_F_NEW;
-                clob = cl_object_find(env, lu2cl_dev(site->ls_top_dev),
-                                      fid, &conf);
-                if (!IS_ERR(clob)) {
-                        /*
-                         * No locking is necessary, as new inode is
-                         * locked by I_NEW bit.
-                         */
-                        lli->lli_clob = clob;
-                        lu_object_ref_add(&clob->co_lu, "inode", inode);
-                } else
-                        result = PTR_ERR(clob);
+       fid  = &lli->lli_fid;
+       LASSERT(fid_is_sane(fid));
+
+       if (lli->lli_clob == NULL) {
+               /* clob is slave of inode, empty lli_clob means for new inode,
+                * there is no clob in cache with the given fid, so it is
+                * unnecessary to perform lookup-alloc-lookup-insert, just
+                * alloc and insert directly.
+                */
+               if (!(inode->i_state & I_NEW)) {
+                       result = -EIO;
+                       CERROR("%s: unexpected not-NEW inode "DFID": rc = %d\n",
+                              ll_get_fsname(inode->i_sb, NULL, 0), PFID(fid),
+                              result);
+                       goto out;
+               }
+
+               conf.coc_lu.loc_flags = LOC_F_NEW;
+               clob = cl_object_find(env, lu2cl_dev(site->ls_top_dev),
+                                     fid, &conf);
+               if (!IS_ERR(clob)) {
+                       /*
+                        * No locking is necessary, as new inode is
+                        * locked by I_NEW bit.
+                        */
+                       lli->lli_clob = clob;
+                       lu_object_ref_add(&clob->co_lu, "inode", inode);
+               } else {
+                       result = PTR_ERR(clob);
+               }
        } else {
                result = cl_conf_set(env, lli->lli_clob, &conf);
                if (result == -EBUSY) {
@@ -181,12 +190,14 @@ int cl_file_inode_init(struct inode *inode, struct lustre_md *md)
                }
        }
 
-        cl_env_put(env, &refcheck);
+       if (result != 0)
+               CERROR("%s: failed to initialize cl_object "DFID": rc = %d\n",
+                       ll_get_fsname(inode->i_sb, NULL, 0), PFID(fid), result);
+
+out:
+       cl_env_put(env, &refcheck);
 
-        if (result != 0)
-                CERROR("Failure to initialize cl object "DFID": %d\n",
-                       PFID(fid), result);
-        return result;
+       return result;
 }
 
 /**