mirror of git://sourceware.org/git/glibc.git
317f1c0a8a
Crossing 2GB boundaries with indirect calls and jumps can use more branch prediction resources on Intel Golden Cove CPU (see the "Misprediction for Branches >2GB" section in Intel 64 and IA-32 Architectures Optimization Reference Manual.) There is visible performance improvement on workloads with many PLT calls when executable and shared libraries are mmapped below 2GB. Add the Prefer_MAP_32BIT_EXEC bit so that mmap will try to map executable or denywrite pages in shared libraries with MAP_32BIT first. NB: Prefer_MAP_32BIT_EXEC reduces bits available for address space layout randomization (ASLR), which is always disabled for SUID programs and can only be enabled by the tunable, glibc.cpu.prefer_map_32bit_exec, or the environment variable, LD_PREFER_MAP_32BIT_EXEC. This works only between shared libraries or between shared libraries and executables with addresses below 2GB. PIEs are usually loaded at a random address above 4GB by the kernel. |
||
|---|---|---|
| .. | ||
| 64 | ||
| x32 | ||
| Implies | ||
| Makefile | ||
| Versions | ||
| ____longjmp_chk.S | ||
| __start_context.S | ||
| clone.S | ||
| clone3.S | ||
| configure | ||
| configure.ac | ||
| dl-cache.h | ||
| dl-procinfo.c | ||
| dl-procinfo.h | ||
| getcontext.S | ||
| kernel-features.h | ||
| ldd-rewrite.sed | ||
| libc_sigaction.c | ||
| libmvec.abilist | ||
| makecontext.c | ||
| pointer_guard.h | ||
| setcontext.S | ||
| sigaltstack-offsets.sym | ||
| sigcontextinfo.h | ||
| single-thread.h | ||
| swapcontext.S | ||
| syscall.S | ||
| syscalls.list | ||
| sysdep.S | ||
| sysdep.h | ||
| tst-glibc-hwcaps-2.c | ||
| ucontext_i.sym | ||
| vfork.S | ||
| x86-64-isa-level-VALUE.c | ||