From 1e36ed705548ae2a5170bb00dfee0954b8ef76de Mon Sep 17 00:00:00 2001
From: Romain Geissler <romain.geissler@amadeus.com>
Date: Tue, 29 Jan 2019 18:31:19 +0000
Subject: [PATCH 38/39] Use initial exec TLS model for all thread local
 variables from thread_cache.cc

This avoids a deadlock when a library which is being dlopen'ed creates
as part of its static constructors a thread which quickly need to call
malloc. We are still in the dlopen call (so with some internal glibc
mutex taken) when the thread executes code and later needs to call
malloc which in term calls tls_get_addr_tail, which wait for the dlopen
mutex to be unlocked. If later the dlopen'ing thread also calls malloc
as part of its constructors, we are in a deadlock.

Fix is similar to
https://github.com/gperftools/gperftools/commit/7852eeb75b9375cf52a7da01be044da6e915dd08

Stack of the dlopening thread:
    #0  0x00007fd5406ca93c in __lll_lock_wait () from /data3/mwrep/rgeissler/core.tls/opt/1A/toolchain/x86_64-2.6.32-v2/lib64/libpthread.so.0
    #1  0x00007fd5406c45a5 in pthread_mutex_lock () from /data3/mwrep/rgeissler/core.tls/opt/1A/toolchain/x86_64-2.6.32-v2/lib64/libpthread.so.0
    ... proprietary code in the stack
    #9  0x00007fd5074f0367 in __static_initialization_and_destruction_0 (__initialize_p=1, __priority=65535) at src/ClientImpl.cpp:15
    #10 0x00007fd5074f06d7 in _GLOBAL__sub_I_ClientImpl.cpp(void) () at src/ClientImpl.cpp:85
    #11 0x00007fd50757aa46 in __do_global_ctors_aux ()
    #12 0x00007fd5073e985f in _init () from ...
    #13 0x00007fd53bf9dec8 in ?? () from ...
    #14 0x00007fd54d637a5d in call_init.part () from /data3/mwrep/rgeissler/core.tls/opt/1A/toolchain/x86_64-2.6.32-v2/lib64/ld-linux-x86-64.so.2
    #15 0x00007fd54d637bab in _dl_init () from /data3/mwrep/rgeissler/core.tls/opt/1A/toolchain/x86_64-2.6.32-v2/lib64/ld-linux-x86-64.so.2
    #16 0x00007fd54d63c160 in dl_open_worker () from /data3/mwrep/rgeissler/core.tls/opt/1A/toolchain/x86_64-2.6.32-v2/lib64/ld-linux-x86-64.so.2
    #17 0x00007fd54d637944 in _dl_catch_error () from /data3/mwrep/rgeissler/core.tls/opt/1A/toolchain/x86_64-2.6.32-v2/lib64/ld-linux-x86-64.so.2
    #18 0x00007fd54d63b7d9 in _dl_open () from /data3/mwrep/rgeissler/core.tls/opt/1A/toolchain/x86_64-2.6.32-v2/lib64/ld-linux-x86-64.so.2
    #19 0x00007fd54d61f2b9 in dlopen_doit () from /data3/mwrep/rgeissler/core.tls/opt/1A/toolchain/x86_64-2.6.32-v2/lib64/libdl.so.2
    #20 0x00007fd54d637944 in _dl_catch_error () from /data3/mwrep/rgeissler/core.tls/opt/1A/toolchain/x86_64-2.6.32-v2/lib64/ld-linux-x86-64.so.2
    #21 0x00007fd54d61f889 in _dlerror_run () from /data3/mwrep/rgeissler/core.tls/opt/1A/toolchain/x86_64-2.6.32-v2/lib64/libdl.so.2
    #22 0x00007fd54d61f351 in dlopen@@GLIBC_2.2.5 () from /data3/mwrep/rgeissler/core.tls/opt/1A/toolchain/x86_64-2.6.32-v2/lib64/libdl.so.2

Stack of the newly created thread calling tls_get_addr_tail:
    #0  0x00007fd5406ca93c in __lll_lock_wait () from /data3/mwrep/rgeissler/core.tls/opt/1A/toolchain/x86_64-2.6.32-v2/lib64/libpthread.so.0
    #1  0x00007fd5406c4622 in pthread_mutex_lock () from /data3/mwrep/rgeissler/core.tls/opt/1A/toolchain/x86_64-2.6.32-v2/lib64/libpthread.so.0
    #2  0x00007fd54d63a2ed in tls_get_addr_tail () from /data3/mwrep/rgeissler/core.tls/opt/1A/toolchain/x86_64-2.6.32-v2/lib64/ld-linux-x86-64.so.2
    #3  0x00007fd53fee877d in tcmalloc::ThreadCache::CreateCacheIfNecessary () at src/thread_cache.cc:344
    #4  0x00007fd53fecb4ab in tcmalloc::ThreadCache::GetCache () at src/thread_cache.h:437
    #5  0x00007fd53fefeccb in (anonymous namespace)::do_malloc (size=56) at src/tcmalloc.cc:1354
    #6  tcmalloc::do_allocate_full<tcmalloc::cpp_throw_oom> (size=56) at src/tcmalloc.cc:1762
    #7  tcmalloc::allocate_full_cpp_throw_oom (size=56) at src/tcmalloc.cc:1776
    #8  0x00007fd53ff01b80 in tcmalloc::dispatch_allocate_full<tcmalloc::cpp_throw_oom> (size=56) at src/tcmalloc.cc:1785
    #9  malloc_fast_path<tcmalloc::cpp_throw_oom> (size=56) at src/tcmalloc.cc:1845
    #10 tc_new (size=56) at src/tcmalloc.cc:1980
    ... proprietary code in the stack
    #26 0x00007fd5406c1ef4 in start_thread () from /data3/mwrep/rgeissler/core.tls/opt/1A/toolchain/x86_64-2.6.32-v2/lib64/libpthread.so.0
    #27 0x00007fd5403ba01d in clone () from /data3/mwrep/rgeissler/core.tls/opt/1A/toolchain/x86_64-2.6.32-v2/lib64/libc.so.6
---
 src/thread_cache.cc | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/thread_cache.cc b/src/thread_cache.cc
index 6d2f832..97f3ffe 100644
--- a/src/thread_cache.cc
+++ b/src/thread_cache.cc
@@ -334,7 +334,7 @@ ThreadCache* ThreadCache::CreateCacheIfNecessary() {
 
   bool seach_condition = true;
 #ifdef HAVE_TLS
-  static __thread ThreadCache** current_heap_ptr;
+  static __thread ThreadCache** current_heap_ptr ATTR_INITIAL_EXEC;
   if (tsd_inited_) {
     // In most common case we're avoiding expensive linear search
     // through all heaps (see below). Working TLS enables faster
-- 
1.8.3.1