diff options
author | H.J. Lu <hjl.tools@gmail.com> | 2024-02-26 06:37:03 -0800 |
---|---|---|
committer | H.J. Lu <hjl.tools@gmail.com> | 2024-02-28 09:02:56 -0800 |
commit | 0aac205a814a8511e98d02b91a8dc908f1c53cde (patch) | |
tree | e9ad8dfa06abd2f6d9b521bb95e9b7cfaa0d7de7 /sysdeps/x86_64/dl-trampoline.S | |
parent | e6350be7e9cae8f71c96c1f06eab61b9acb227c8 (diff) | |
download | glibc-0aac205a814a8511e98d02b91a8dc908f1c53cde.tar.gz glibc-0aac205a814a8511e98d02b91a8dc908f1c53cde.tar.xz glibc-0aac205a814a8511e98d02b91a8dc908f1c53cde.zip |
x86: Update _dl_tlsdesc_dynamic to preserve caller-saved registers
Compiler generates the following instruction sequence for GNU2 dynamic TLS access: leaq tls_var@TLSDESC(%rip), %rax call *tls_var@TLSCALL(%rax) or leal tls_var@TLSDESC(%ebx), %eax call *tls_var@TLSCALL(%eax) CALL instruction is transparent to compiler which assumes all registers, except for EFLAGS and RAX/EAX, are unchanged after CALL. When _dl_tlsdesc_dynamic is called, it calls __tls_get_addr on the slow path. __tls_get_addr is a normal function which doesn't preserve any caller-saved registers. _dl_tlsdesc_dynamic saved and restored integer caller-saved registers, but didn't preserve any other caller-saved registers. Add _dl_tlsdesc_dynamic IFUNC functions for FNSAVE, FXSAVE, XSAVE and XSAVEC to save and restore all caller-saved registers. This fixes BZ #31372. Add GLRO(dl_x86_64_runtime_resolve) with GLRO(dl_x86_tlsdesc_dynamic) to optimize elf_machine_runtime_setup. Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
Diffstat (limited to 'sysdeps/x86_64/dl-trampoline.S')
-rw-r--r-- | sysdeps/x86_64/dl-trampoline.S | 20 |
1 files changed, 1 insertions, 19 deletions
diff --git a/sysdeps/x86_64/dl-trampoline.S b/sysdeps/x86_64/dl-trampoline.S index b2e7e0f69b..87c5137837 100644 --- a/sysdeps/x86_64/dl-trampoline.S +++ b/sysdeps/x86_64/dl-trampoline.S @@ -22,25 +22,7 @@ #include <features-offsets.h> #include <link-defines.h> #include <isa-level.h> - -#ifndef DL_STACK_ALIGNMENT -/* Due to GCC bug: - - https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58066 - - __tls_get_addr may be called with 8-byte stack alignment. Although - this bug has been fixed in GCC 4.9.4, 5.3 and 6, we can't assume - that stack will be always aligned at 16 bytes. We use unaligned - 16-byte move to load and store SSE registers, which has no penalty - on modern processors if stack is 16-byte aligned. */ -# define DL_STACK_ALIGNMENT 8 -#endif - -/* True if _dl_runtime_resolve should align stack for STATE_SAVE or align - stack to 16 bytes before calling _dl_fixup. */ -#define DL_RUNTIME_RESOLVE_REALIGN_STACK \ - (STATE_SAVE_ALIGNMENT > DL_STACK_ALIGNMENT \ - || 16 > DL_STACK_ALIGNMENT) +#include "dl-trampoline-save.h" /* Area on stack to save and restore registers used for parameter passing when calling _dl_fixup. */ |