From 790de9d74881a0f1ad9f0c2f3998aac98c9b9000 Mon Sep 17 00:00:00 2001
From: Pranith Kumar K <pkarampu@redhat.com>
Date: Thu, 30 Mar 2017 14:58:38 +0530
Subject: [PATCH 377/393] cluster/dht: Modify local->loc.gfid in thread safe
 manner

	Backport of https://review.gluster.org/16986

Problem:
local->loc.gfid in dht_lookup_directory() will be null-gfid for a fresh lookup.
dht_lookup_dir_cbk() updates local->loc.gfid while in other thread dht_lookup_directory()
is still winding lookup calls to subvolumes so there is a chance of partial gfid being
seen by EC.

We saw in 12x(4+2) volume, ec is receiving an loc where the gfid has last 10 bytes matching
with the gfid of the directory and the first 4 bytes are all-zeros. This is leading to EC
erroring out the lookup with EINVAL which leads to NFS failing lookup with EIO.

snip from gdb:
$37 = (dht_local_t *) 0x7fde5de5b3cc
(gdb) p /x $37->loc.gfid
$39 = {0x3b, 0x82, 0x10, 0x5e, 0x40, 0x65, 0x43, 0x14, 0xa0, 0xc6, 0x8, 0xf5,
0x6c, 0x2c, 0xb8, 0x56}
(gdb) fr 7
state=<optimized out>) at ec-generic.c:837
837	                ec_lookup_rebuild(fop->xl->private, fop, cbk);
(gdb) p /x fop->loc[0].gfid
$40 = {0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x43, 0x14, 0xa0, 0xc6, 0x8, 0xf5, 0x6c,
0x2c, 0xb8, 0x56}

snip from log:
[2017-01-29 03:22:30.132328] W [MSGID: 122019]
[ec-helpers.c:354:ec_loc_gfid_check] 0-butcher-disperse-4: Mismatching GFID's
in loc [2017-01-29 03:22:30.132709] W [MSGID: 112199]
[nfs3-helpers.c:3515:nfs3_log_newfh_res] 0-nfs-nfsv3:
/linux-4.9.5/Documentation => (XID: b27b9474, MKDIR: NFS: 5(I/O error), POSIX:
5(Input/output error)), FH: exportid 00000000-0000-0000-0000-000000000000, gfid
00000000-0000-0000-0000-000000000000, mountid
00000000-0000-0000-0000-000000000000 [Invalid argument]

Fix:
update local->loc.gfid in last-call to make sure there are no races.

 >BUG: 1438411
 >Change-Id: Ifcb7e911568c1f1f83123da6ff0cf742b91800a0
 >Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>

BUG: 1415038
Change-Id: If039956205cfac5e798c2c90e92a9a47b404e804
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
Reviewed-on: https://code.engineering.redhat.com/gerrit/102307
---
 xlators/cluster/dht/src/dht-common.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/xlators/cluster/dht/src/dht-common.c b/xlators/cluster/dht/src/dht-common.c
index 717bd7a..9533940 100644
--- a/xlators/cluster/dht/src/dht-common.c
+++ b/xlators/cluster/dht/src/dht-common.c
@@ -810,8 +810,6 @@ dht_lookup_dir_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
         if (!op_ret && gf_uuid_is_null (local->gfid))
                 memcpy (local->gfid, stbuf->ia_gfid, 16);
 
-        memcpy (local->loc.gfid, local->gfid, 16);
-
         /* Check if the gfid is different for file from other node */
         if (!op_ret && gf_uuid_compare (local->gfid, stbuf->ia_gfid)) {
 
@@ -879,6 +877,8 @@ unlock:
         this_call_cnt = dht_frame_return (frame);
 
         if (is_last_call (this_call_cnt)) {
+                gf_uuid_copy (local->loc.gfid, local->gfid);
+
                 if (local->need_selfheal) {
                         local->need_selfheal = 0;
                         dht_lookup_everywhere (frame, this, &local->loc);
@@ -918,7 +918,6 @@ unlock:
 
 selfheal:
         FRAME_SU_DO (frame, dht_local_t);
-        gf_uuid_copy (local->loc.gfid, local->gfid);
         ret = dht_selfheal_directory (frame, dht_lookup_selfheal_cbk,
                                       &local->loc, layout);
 out:
-- 
1.8.3.1