This happens whenever libld is used to load a dynamically linked library.

Full output:

==10913== Memcheck, a memory error detector
==10913== Copyright (C) 2002-2015, and GNU GPL'd, by Julian Seward et al.
==10913== Using Valgrind-3.11.0 and LibVEX; rerun with -h for copyright info
==10913== Command: gdb
==10913== 
vex amd64->IR: unhandled instruction bytes: 0x8F 0xEA 0xF8 0x10 0xC9 0x3 0x1D 0x0
vex amd64->IR:   REX=0 REX.W=0 REX.R=0 REX.X=0 REX.B=0
vex amd64->IR:   VEX=0 VEX.L=0 VEX.nVVVV=0x0 ESC=NONE
vex amd64->IR:   PFX.66=0 PFX.F2=0 PFX.F3=0
==10913== valgrind: Unrecognised instruction at address 0x4011d04.
==10913==    at 0x4011D04: _dl_allocate_tls_storage (in /lib64/ld-2.22.so)
==10913==    by 0x4000B9A: init_tls (in /lib64/ld-2.22.so)
==10913==    by 0x40034AF: dl_main (in /lib64/ld-2.22.so)
==10913==    by 0x4016978: _dl_sysdep_start (in /lib64/ld-2.22.so)
==10913==    by 0x4004C28: _dl_start (in /lib64/ld-2.22.so)
==10913==    by 0x4000C47: ??? (in /lib64/ld-2.22.so)
==10913== Your program just tried to execute an instruction that Valgrind
==10913== did not recognise.  There are two possible reasons for this.
==10913== 1. Your program has a bug and erroneously jumped to a non-code
==10913==    location.  If you are running Memcheck and you just saw a
==10913==    warning about a bad jump, it's probably your program's fault.
==10913== 2. The instruction is legitimate but Valgrind doesn't handle it,
==10913==    i.e. it's Valgrind's fault.  If you think this is the case or
==10913==    you are not sure, please let us know and we'll try to fix it.
==10913== Either way, Valgrind will now raise a SIGILL signal which will
==10913== probably kill your program.
==10913== 
==10913== Process terminating with default action of signal 4 (SIGILL)
==10913==  Illegal opcode at address 0x4011D04
==10913==    at 0x4011D04: _dl_allocate_tls_storage (in /lib64/ld-2.22.so)
==10913==    by 0x4000B9A: init_tls (in /lib64/ld-2.22.so)
==10913==    by 0x40034AF: dl_main (in /lib64/ld-2.22.so)
==10913==    by 0x4016978: _dl_sysdep_start (in /lib64/ld-2.22.so)
==10913==    by 0x4004C28: _dl_start (in /lib64/ld-2.22.so)
==10913==    by 0x4000C47: ??? (in /lib64/ld-2.22.so)
==10913== Jump to the invalid address stated on the next line
==10913==    at 0x596: ???
==10913==  Address 0x596 is not stack'd, malloc'd or (recently) free'd
==10913== 
==10913== 
==10913== Process terminating with default action of signal 11 (SIGSEGV)
==10913==  Bad permissions for mapped region at address 0x596
==10913==    at 0x596: ???
==10913== 
==10913== HEAP SUMMARY:
==10913==     in use at exit: 0 bytes in 0 blocks
==10913==   total heap usage: 0 allocs, 0 frees, 0 bytes allocated
==10913== 
==10913== All heap blocks were freed -- no leaks are possible
==10913== 
==10913== For counts of detected and suppressed errors, rerun with: -v
==10913== ERROR SUMMARY: 1 errors from 1 contexts (suppressed: 0 from 0)
Segmentation fault


Reproducible: Always

Steps to Reproduce:
1. valgrind gdb
2. crash



I am using Valgrind 3.11.0 and glibc-2.22 (compiled with -arch=native and -O2)

uname -a:
Linux localhost 4.3.0-gentoo #1 SMP Sat Dec 5 16:08:19 2015 x86_64 AMD A8-4500M APU with Radeon(tm) HD Graphics AuthenticAMD GNU/Linux