diff options
author | Alan Modra <amodra@gmail.com> | 2022-01-22 11:48:50 +1030 |
---|---|---|
committer | Alan Modra <amodra@gmail.com> | 2022-04-10 08:33:06 +0930 |
commit | d6efcc118e406a1cfeb309f835d7118df53419bb (patch) | |
tree | 31bbfdb82f662a47fece23a2e7f1324ea0c3ce6e /sysdeps/powerpc/powerpc64/dl-trampoline.S | |
parent | 30afd8c44d6a0a8b0eddbadecb02c9b9dad3facf (diff) | |
download | glibc-d6efcc118e406a1cfeb309f835d7118df53419bb.tar.gz glibc-d6efcc118e406a1cfeb309f835d7118df53419bb.tar.xz glibc-d6efcc118e406a1cfeb309f835d7118df53419bb.zip |
powerpc64: Use medium model toc accesses throughout
The PowerPC64 linker edits medium model toc-indirect code to toc-pointer relative: addis r9,r2,tc_entry_for_var@toc@ha ld r9,tc_entry_for_var@toc@l(r9) becomes addis r9,r2,(var-.TOC.)@ha addi r9,r9,(var-.TOC.)@l when "var" is known to be local to the binary. This isn't done for small-model toc-indirect code, because "var" is almost guaranteed to be too far away from .TOC. for a 16-bit signed offset. And, because the analysis of which .toc entry can be removed becomes much more complicated in objects that mix code models, they aren't removed if any small-model toc sequence appears in an object file. Unfortunately, glibc's build of ld.so smashes the needed objects together in a ld -r linking stage. This means the GOT/TOC is left with a whole lot of relative relocations which is untidy, but in itself is not a serious problem. However, static-pie on powerpc64 bombs due to a segfault caused by one of the small-model accesses before _dl_relocate_static_pie. (The very first one in rcrt1.o passing start_addresses in r8 to __libc_start_main.) So this patch makes all the toc/got accesses in assembly medium code model, and a couple of functions hidden. By itself this is not enough to give us working static-pie, but it is useful in isolation to enable better linker optimisation. There's a serious problem in libgcc too. libgcc ifuncs access the AT_HWCAP words stored in the tcb with an offset from the thread pointer (r13), but r13 isn't set at the time _dl_relocate_static_pie. A followup patch will fix that. Reviewed-by: Tulio Magno Quites Machado Filho <tuliom@linux.ibm.com>
Diffstat (limited to 'sysdeps/powerpc/powerpc64/dl-trampoline.S')
-rw-r--r-- | sysdeps/powerpc/powerpc64/dl-trampoline.S | 8 |
1 files changed, 6 insertions, 2 deletions
diff --git a/sysdeps/powerpc/powerpc64/dl-trampoline.S b/sysdeps/powerpc/powerpc64/dl-trampoline.S index 23debc2faf..45b821607b 100644 --- a/sysdeps/powerpc/powerpc64/dl-trampoline.S +++ b/sysdeps/powerpc/powerpc64/dl-trampoline.S @@ -32,6 +32,7 @@ because gcc as of 2010/05 doesn't allocate a proper stack frame for a function that makes no calls except for __tls_get_addr and we might be here resolving the __tls_get_addr call. */ + .hidden _dl_runtime_resolve #define INT_PARMS FRAME_MIN_SIZE ENTRY (_dl_runtime_resolve, 4) stdu r1,-FRAME_SIZE(r1) @@ -195,6 +196,7 @@ END(_dl_runtime_resolve) parm1 (r3) and the index (r0) needs to be converted to an offset (index * 24) in parm2 (r4). */ #ifndef PROF + .hidden _dl_profile_resolve ENTRY (_dl_profile_resolve, 4) /* Spill r30, r31 to preserve the link_map* and reloc_addr, in case we need to call _dl_audit_pltexit. */ @@ -225,12 +227,14 @@ ENTRY (_dl_profile_resolve, 4) std r9,INT_PARMS+48(r1) std r10,INT_PARMS+56(r1) std r8,CALLING_SP(r1) - ld r12,.LC__dl_hwcap@toc(r2) + addis r12,r2,.LC__dl_hwcap@toc@ha + ld r12,.LC__dl_hwcap@toc@l(r12) #ifdef SHARED /* Load _rtld_local_ro._dl_hwcap. */ ld r12,RTLD_GLOBAL_RO_DL_HWCAP_OFFSET(r12) #else - ld r12,0(r12) /* Load extern _dl_hwcap. */ + /* Load extern _dl_hwcap. */ + ld r12,0(r12) #endif andis. r0,r12,(PPC_FEATURE_HAS_ALTIVEC >> 16) beq L(saveFP) |