2018-03-21 23:04:04 +08:00
|
|
|
# REQUIRES: ppc
|
2018-05-04 23:09:49 +08:00
|
|
|
|
2019-04-23 19:47:28 +08:00
|
|
|
# RUN: llvm-mc -filetype=obj -triple=powerpc64le-unknown-linux %s -o %t.o
|
|
|
|
|
# RUN: ld.lld %t.o -o %t
|
|
|
|
|
# RUN: llvm-nm %t | FileCheck --check-prefix=NM %s
|
|
|
|
|
# RUN: llvm-objdump -d --no-show-raw-insn %t | FileCheck %s
|
2018-03-21 23:04:04 +08:00
|
|
|
|
2019-04-23 19:47:28 +08:00
|
|
|
# RUN: llvm-mc -filetype=obj -triple=powerpc64-unknown-linux %s -o %t.o
|
|
|
|
|
# RUN: ld.lld %t.o -o %t
|
|
|
|
|
# RUN: llvm-nm %t | FileCheck --check-prefix=NM %s
|
|
|
|
|
# RUN: llvm-objdump -d --no-show-raw-insn %t | FileCheck %s
|
2018-05-04 23:09:49 +08:00
|
|
|
|
2018-03-21 23:04:04 +08:00
|
|
|
.text
|
|
|
|
|
.abiversion 2
|
|
|
|
|
.globl _start
|
|
|
|
|
.p2align 4
|
|
|
|
|
.type _start,@function
|
|
|
|
|
|
|
|
|
|
_start:
|
|
|
|
|
.Lfunc_begin0:
|
|
|
|
|
.Lfunc_gep0:
|
|
|
|
|
lis 4, .Lfunc_gep0@ha
|
|
|
|
|
addi 4, 4, .Lfunc_gep0@l
|
|
|
|
|
# now r4 should contain the address of _start
|
|
|
|
|
|
2019-04-23 19:47:28 +08:00
|
|
|
lis 5, .TOC.-.Lfunc_gep0@ha # R_PPC64_REL16_HA
|
|
|
|
|
addi 5, 5, .TOC.-.Lfunc_gep0@l # R_PPC64_REL16_LO
|
2018-03-21 23:04:04 +08:00
|
|
|
# now r5 should contain the offset s.t. r4 + r5 = TOC base
|
|
|
|
|
|
|
|
|
|
# exit 55
|
|
|
|
|
li 0, 1
|
|
|
|
|
li 3, 55
|
|
|
|
|
sc
|
|
|
|
|
.Lfunc_end0:
|
|
|
|
|
.size _start, .Lfunc_end0-.Lfunc_begin0
|
|
|
|
|
|
[ELF][PPC] Allow PT_LOAD to have overlapping p_offset ranges
This change affects the non-linker script case (precisely, when the
`SECTIONS` command is not used). It deletes 3 alignments at PT_LOAD
boundaries for the default case: the size of a powerpc64 binary can be
decreased by at most 192kb. The technique can be ported to other
targets.
Let me demonstrate the idea with a maxPageSize=65536 example:
When assigning the address to the first output section of a new PT_LOAD,
if the end p_vaddr of the previous PT_LOAD is 0x10020, we advance to
the next multiple of maxPageSize: 0x20000. The new PT_LOAD will thus
have p_vaddr=0x20000. Because p_offset and p_vaddr are congruent modulo
maxPageSize, p_offset will be 0x20000, leaving a p_offset gap [0x10020,
0x20000) in the output.
Alternatively, if we advance to 0x20020, the new PT_LOAD will have
p_vaddr=0x20020. We can pick either 0x10020 or 0x20020 for p_offset!
Obviously 0x10020 is the choice because it leaves no gap. At runtime,
p_vaddr will be rounded down by pagesize (65536 if
pagesize=maxPageSize). This PT_LOAD will load additional initial
contents from p_offset ranges [0x10000,0x10020), which will also be
loaded by the previous PT_LOAD. This is fine if -z noseparate-code is in
effect or if we are not transiting between executable and non-executable
segments.
ld.bfd -z noseparate-code leverages this technique to keep output small.
This patch implements the technique in lld, which is mostly effective on
targets with large defaultMaxPageSize (AArch64/MIPS/PPC: 65536). The 3
removed alignments can save almost 3*65536 bytes.
Two places that rely on p_vaddr%pagesize = 0 have to be updated.
1) We used to round p_memsz(PT_GNU_RELRO) up to commonPageSize (defaults
to 4096 on all targets). Now p_vaddr%commonPageSize may be non-zero.
The updated formula takes account of that factor.
2) Our TP offsets formulae are only correct if p_vaddr%p_align = 0.
Fix them. See the updated comments in InputSection.cpp for details.
On targets that we enable the technique (only PPC64 now),
we can potentially make `p_vaddr(PT_TLS)%p_align(PT_TLS) != 0`
if `sh_addralign(.tdata) < sh_addralign(.tbss)`
This exposes many problems in ld.so implementations, especially the
offsets of dynamic TLS blocks. Known issues:
FreeBSD 13.0-CURRENT rtld-elf (i386/amd64/powerpc/arm64)
glibc (HEAD) i386 and x86_64 https://sourceware.org/bugzilla/show_bug.cgi?id=24606
musl<=1.1.22 on TLS Variant I architectures (aarch64/powerpc64/...)
So, force p_vaddr%p_align = 0 by rounding dot up to p_align(PT_TLS).
The technique will be enabled (with updated tests) for other targets in
subsequent patches.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D64906
llvm-svn: 369343
2019-08-20 16:34:25 +08:00
|
|
|
# NM-DAG: 00000000100281f0 d .TOC.
|
|
|
|
|
# NM-DAG: 00000000100101d0 T _start
|
|
|
|
|
|
|
|
|
|
# 0x100101d0 = (4097<<16) + 464
|
|
|
|
|
# CHECK: 100101d0: lis 4, 4097
|
|
|
|
|
# CHECK-NEXT: 100101d4: addi 4, 4, 464
|
|
|
|
|
# .TOC. - _start = (2<<16) - 32736
|
|
|
|
|
# CHECK-NEXT: 100101d8: lis 5, 2
|
|
|
|
|
# CHECK-NEXT: 100101dc: addi 5, 5, -32736
|