syncop: Change return value of syncop

Problem:
We found a day-1 bug when syncop_xxx() infra is used inside a synctask with
compilation optimization (CFLAGS -O2).

Detailed explanation of the Root cause:
We found the bug in 'gf_defrag_migrate_data' in rebalance operation:

Lets look at interesting parts of the function:

int
gf_defrag_migrate_data (xlator_t *this, gf_defrag_info_t *defrag, loc_t *loc,
                        dict_t *migrate_data)
{
.....
code section - [ Loop ]
        while ((ret = syncop_readdirp (this, fd, 131072, offset, NULL,
                                       &entries)) != 0) {
.....
code section - [ ERRNO-1 ] (errno of readdirp is stored in readdir_operrno by a
thread)
                /* Need to keep track of ENOENT errno, that means, there is no
                   need to send more readdirp() */
                readdir_operrno = errno;
.....
code section - [ SYNCOP-1 ] (syncop_getxattr is called by a thread)
                        ret = syncop_getxattr (this, &entry_loc, &dict,
                                               GF_XATTR_LINKINFO_KEY);
code section - [ ERRNO-2]   (checking for failures of syncop_getxattr(). This
may not always be executed in same thread which executed [SYNCOP-1])
                        if (ret < 0) {
                                if (errno != ENODATA) {
                                        loglevel = GF_LOG_ERROR;
                                        defrag->total_failures += 1;
.....
}

the function above could be executed by thread(t1) till [SYNCOP-1] and code
from [ERRNO-2] can be executed by a different thread(t2) because of the way
syncop-infra schedules the tasks.

when the code is compiled with -O2 optimization this is the assembly code that
is generated:
 [ERRNO-1]
1165                        readdir_operrno = errno; <<---- errno gets expanded
as *(__errno_location())
   0x00007fd149d48b60 <+496>:        callq  0x7fd149d410c0 <address@hidden>
   0x00007fd149d48b72 <+514>:        mov    %rax,0x50(%rsp) <<------ Address
returned by __errno_location() is stored in a special location in stack for
later use.
   0x00007fd149d48b77 <+519>:        mov    (%rax),%eax
   0x00007fd149d48b79 <+521>:        mov    %eax,0x78(%rsp)
....
 [ERRNO-2]
1281                                        if (errno != ENODATA) {
   0x00007fd149d492ae <+2366>:        mov    0x50(%rsp),%rax <<-----  Because
it already stored the address returned by __errno_location(), it just
dereferences the address to get the errno value. BUT THIS CODE NEED NOT BE
EXECUTED BY SAME THREAD!!!
   0x00007fd149d492b3 <+2371>:        mov    $0x9,%ebp
   0x00007fd149d492b8 <+2376>:        mov    (%rax),%edi
   0x00007fd149d492ba <+2378>:        cmp    $0x3d,%edi

The problem is that __errno_location() value of t1 and t2 are different. So
[ERRNO-2] ends up reading errno of t1 instead of errno of t2 even though t2 is
executing [ERRNO-2] code section.

When code is compiled without any optimization for [ERRNO-2]:
1281                                        if (errno != ENODATA) {
   0x00007fd58e7a326f <+2237>:        callq  0x7fd58e797300
<address@hidden><<--- As it is calling __errno_location() again it gets the
location from t2 so it works as intended.
   0x00007fd58e7a3274 <+2242>:        mov    (%rax),%eax
   0x00007fd58e7a3276 <+2244>:        cmp    $0x3d,%eax
   0x00007fd58e7a3279 <+2247>:        je     0x7fd58e7a32a1
<gf_defrag_migrate_data+2287>

Fix:
Make syncop_xxx() return (-errno) value as the return value in
case of errors and all the functions which make syncop_xxx() will need to use
(-ret) to figure out the reason for failure in case of syncop_xxx() failures.

Change-Id: I314d20dabe55d3e62ff66f3b4adb1cac2eaebb57
BUG: 1040356
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
Reviewed-on: http://review.gluster.org/6475
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Anand Avati <avati@redhat.com>

1 files changed, 16 insertions, 8 deletions

diff --git a/xlators/cluster/dht/src/dht-helper.c b/xlators/cluster/dht/src/dht-helper.c
index 00a98f1cfa5..76bfbaedb77 100644
--- a/xlators/cluster/dht/src/dht-helper.c
+++ b/xlators/cluster/dht/src/dht-helper.c
@@ -769,17 +769,20 @@ dht_migration_complete_check_task (void *data)
                 dst_node = dht_linkfile_subvol (this, NULL, NULL, dict);
 
         if (ret) {
-                if (!dht_inode_missing(errno) || (!local->loc.inode)) {
+                if (!dht_inode_missing(-ret) || (!local->loc.inode)) {
                         gf_log (this->name, GF_LOG_ERROR,
                                 "%s: failed to get the 'linkto' xattr %s",
-                                local->loc.path, strerror (errno));
+                                local->loc.path, strerror (-ret));
+                        ret = -1;
                         goto out;
                 }
                 /* Need to do lookup on hashed subvol, then get the file */
                 ret = syncop_lookup (this, &local->loc, NULL, &stbuf, NULL,
                                      NULL);
-                if (ret)
+                if (ret) {
+                        ret = -1;
                         goto out;
+                }
                 dst_node = dht_subvol_get_cached (this, local->loc.inode);
         }
 
@@ -799,6 +802,7 @@ dht_migration_complete_check_task (void *data)
                         gf_log (this->name, GF_LOG_ERROR,
                                 "%s: failed to lookup the file on %s",
                                 local->loc.path, dst_node->name);
+                        ret = -1;
                         goto out;
                 }
 
@@ -869,10 +873,11 @@ dht_migration_complete_check_task (void *data)
 
                 ret = syncop_open (dst_node, &tmp_loc,
                                    iter_fd->flags, iter_fd);
-                if (ret == -1) {
+                if (ret < 0) {
                         gf_log (this->name, GF_LOG_ERROR, "failed to open "
                                 "the fd (%p, flags=0%o) on file %s @ %s",
                                 iter_fd, iter_fd->flags, path, dst_node->name);
+                        ret = -1;
                         open_failed = 1;
                 }
         }
@@ -955,11 +960,12 @@ dht_rebalance_inprogress_task (void *data)
                                         conf->link_xattr_name);
         }
 
-        if (ret) {
+        if (ret < 0) {
                 gf_log (this->name, GF_LOG_ERROR,
                         "%s: failed to get the 'linkto' xattr %s",
-                        local->loc.path, strerror (errno));
-                        goto out;
+                        local->loc.path, strerror (-ret));
+                ret = -1;
+                goto out;
         }
 
         dst_node = dht_linkfile_subvol (this, NULL, NULL, dict);
@@ -981,6 +987,7 @@ dht_rebalance_inprogress_task (void *data)
                         gf_log (this->name, GF_LOG_ERROR,
                                 "%s: failed to lookup the file on %s",
                                 local->loc.path, dst_node->name);
+                        ret = -1;
                         goto out;
                 }
 
@@ -1014,10 +1021,11 @@ dht_rebalance_inprogress_task (void *data)
 
                 ret = syncop_open (dst_node, &tmp_loc,
                                    iter_fd->flags, iter_fd);
-                if (ret == -1) {
+                if (ret < 0) {
                         gf_log (this->name, GF_LOG_ERROR, "failed to send open "
                                 "the fd (%p, flags=0%o) on file %s @ %s",
                                 iter_fd, iter_fd->flags, path, dst_node->name);
+                        ret = -1;
                         open_failed = 1;
                 }
         }