[lld] a6db64e - [ELF] Allow sections after a non-SHF_ALLOC section to be covered by PT_LOAD
Fangrui Song via llvm-commits
llvm-commits at lists.llvm.org
Thu Aug 6 08:27:25 PDT 2020
Author: Fangrui Song
Date: 2020-08-06T08:27:15-07:00
New Revision: a6db64ef4a9906c96ef5652739ac15aefaa7827c
URL: https://github.com/llvm/llvm-project/commit/a6db64ef4a9906c96ef5652739ac15aefaa7827c
DIFF: https://github.com/llvm/llvm-project/commit/a6db64ef4a9906c96ef5652739ac15aefaa7827c.diff
LOG: [ELF] Allow sections after a non-SHF_ALLOC section to be covered by PT_LOAD
GNU ld allows sections after a non-SHF_ALLOC section to be covered by PT_LOAD
(PR37607) and assigns addresses to non-SHF_ALLOC output sections (similar to
SHF_ALLOC NOBITS sections. The location counter is not advanced).
This patch tries to fix PR37607 (remove a special case in
`Writer<ELFT>::createPhdrs`). To make the created PT_LOAD meaningful, we cannot
reset dot to 0 for a middle non-SHF_ALLOC output section. This results in
removal of two special cases in LinkerScript::assignOffsets. Non-SHF_ALLOC
non-orphan sections can have non-zero addresses like in GNU ld.
The zero address rule for non-SHF_ALLOC sections is weakened to apply to orphan
only. This results in a special case in createSection and findOrphanPos, respectively.
Reviewed By: jhenderson
Differential Revision: https://reviews.llvm.org/D85100
Added:
Modified:
lld/ELF/LinkerScript.cpp
lld/ELF/Writer.cpp
lld/test/ELF/linkerscript/compress-debug-sections-custom.s
lld/test/ELF/linkerscript/sections.s
lld/test/ELF/linkerscript/symbols-non-alloc.test
lldb/test/Shell/SymbolFile/DWARF/Inputs/debug-line-basic.script
Removed:
################################################################################
diff --git a/lld/ELF/LinkerScript.cpp b/lld/ELF/LinkerScript.cpp
index 72e2ebff9b8c..a187aa1eb05a 100644
--- a/lld/ELF/LinkerScript.cpp
+++ b/lld/ELF/LinkerScript.cpp
@@ -586,6 +586,8 @@ static OutputSection *findByName(ArrayRef<BaseCommand *> vec,
static OutputSection *createSection(InputSectionBase *isec,
StringRef outsecName) {
OutputSection *sec = script->createOutputSection(outsecName, "<internal>");
+ if (!(isec->flags & SHF_ALLOC))
+ sec->addrExpr = [] { return 0; };
sec->recordSection(isec);
return sec;
}
@@ -848,9 +850,6 @@ static OutputSection *findFirstSection(PhdrEntry *load) {
// This function assigns offsets to input sections and an output section
// for a single sections command (e.g. ".text { *(.text); }").
void LinkerScript::assignOffsets(OutputSection *sec) {
- if (!(sec->flags & SHF_ALLOC))
- dot = 0;
-
const bool sameMemRegion = ctx->memRegion == sec->memRegion;
const bool prevLMARegionIsDefault = ctx->lmaRegion == nullptr;
ctx->memRegion = sec->memRegion;
@@ -858,7 +857,7 @@ void LinkerScript::assignOffsets(OutputSection *sec) {
if (ctx->memRegion)
dot = ctx->memRegion->curPos;
- if ((sec->flags & SHF_ALLOC) && sec->addrExpr)
+ if (sec->addrExpr)
setDot(sec->addrExpr, sec->location, false);
// If the address of the section has been moved forward by an explicit
diff --git a/lld/ELF/Writer.cpp b/lld/ELF/Writer.cpp
index c1469e123336..1bd6fb61e2e4 100644
--- a/lld/ELF/Writer.cpp
+++ b/lld/ELF/Writer.cpp
@@ -1234,7 +1234,13 @@ static bool shouldSkip(BaseCommand *cmd) {
static std::vector<BaseCommand *>::iterator
findOrphanPos(std::vector<BaseCommand *>::iterator b,
std::vector<BaseCommand *>::iterator e) {
+ // OutputSections without the SHF_ALLOC flag are not part of the memory image
+ // and their addresses usually don't matter. Place any orphan sections without
+ // the SHF_ALLOC flag at the end so that these do not affect the address
+ // assignment of OutputSections with the SHF_ALLOC flag.
OutputSection *sec = cast<OutputSection>(*e);
+ if (!(sec->flags & SHF_ALLOC))
+ return e;
// Find the first element that has as close a rank as possible.
auto i = std::max_element(b, e, [=](BaseCommand *a, BaseCommand *b) {
@@ -2329,8 +2335,6 @@ std::vector<PhdrEntry *> Writer<ELFT>::createPhdrs(Partition &part) {
}
for (OutputSection *sec : outputSections) {
- if (!(sec->flags & SHF_ALLOC))
- break;
if (!needsPtLoad(sec))
continue;
diff --git a/lld/test/ELF/linkerscript/compress-debug-sections-custom.s b/lld/test/ELF/linkerscript/compress-debug-sections-custom.s
index f61d6398b1f0..7b9a8d091bf5 100644
--- a/lld/test/ELF/linkerscript/compress-debug-sections-custom.s
+++ b/lld/test/ELF/linkerscript/compress-debug-sections-custom.s
@@ -1,9 +1,10 @@
# REQUIRES: x86, zlib
+## NOTE GNU ld makes .debug_str and .debug_info SHF_ALLOC due to `. += 10`.
# RUN: echo "SECTIONS { \
# RUN: .text : { . += 0x10; *(.text) } \
-# RUN: .debug_str : { . += 0x10; *(.debug_str) } \
-# RUN: .debug_info : { . += 0x10; *(.debug_info) } \
+# RUN: .debug_str 0 : { . += 0x10; *(.debug_str) } \
+# RUN: .debug_info 0 : { . += 0x10; *(.debug_info) } \
# RUN: }" > %t.script
# RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t.o
diff --git a/lld/test/ELF/linkerscript/sections.s b/lld/test/ELF/linkerscript/sections.s
index 14a9ac5ab75b..fa346406b743 100644
--- a/lld/test/ELF/linkerscript/sections.s
+++ b/lld/test/ELF/linkerscript/sections.s
@@ -25,8 +25,10 @@
# SEC-DEFAULT: 7 .shstrtab 0000003b {{[0-9a-f]*}}
# SEC-DEFAULT: 8 .strtab 00000008 {{[0-9a-f]*}}
-# Sections are put in order specified in linker script, other than alloc
-# sections going first.
+## Sections are placed in the order specified by the linker script. .data has
+## a PT_LOAD segment, even if it is preceded by a non-alloc section. To
+## allow this, place non-alloc orphan sections at the end and advance
+## location counters for non-alloc non-orphan sections.
# RUN: echo "SECTIONS { \
# RUN: .bss : { *(.bss) } \
# RUN: other : { *(other) } \
@@ -34,20 +36,27 @@
# RUN: .symtab : { *(.symtab) } \
# RUN: .strtab : { *(.strtab) } \
# RUN: .data : { *(.data) } \
-# RUN: .text : { *(.text) } }" > %t.script
-# RUN: ld.lld -o %t3 --script %t.script %t
-# RUN: llvm-objdump --section-headers %t3 | \
-# RUN: FileCheck -check-prefix=SEC-ORDER %s
+# RUN: .text : { *(.text) } }" > %t3.lds
+# RUN: ld.lld -o %t3a -T %t3.lds %t
+# RUN: llvm-readelf -S -l %t3a | FileCheck --check-prefix=SEC-ORDER %s
+# RUN: ld.lld -o %t3b -T %t3.lds --unique %t
+# RUN: llvm-readelf -S -l %t3b | FileCheck --check-prefix=SEC-ORDER %s
-# Idx Name Size
-# SEC-ORDER: 1 .bss 00000002 {{[0-9a-f]*}} BSS
-# SEC-ORDER: 2 other 00000003 {{[0-9a-f]*}} DATA
-# SEC-ORDER: 3 .shstrtab 0000003b {{[0-9a-f]*}}
-# SEC-ORDER: 4 .symtab 00000030 {{[0-9a-f]*}}
-# SEC-ORDER: 5 .strtab 00000008 {{[0-9a-f]*}}
-# SEC-ORDER: 6 .comment 00000008 {{[0-9a-f]*}}
-# SEC-ORDER: 7 .data 00000020 {{[0-9a-f]*}} DATA
-# SEC-ORDER: 8 .text 0000000e {{[0-9a-f]*}} TEXT
+# SEC-ORDER: [Nr] Name Type Address Off Size ES Flg
+# SEC-ORDER: [ 0] NULL 0000000000000000 000000 000000 00
+# SEC-ORDER-NEXT: [ 1] .bss NOBITS 0000000000000000 001000 000002 00 WA
+# SEC-ORDER-NEXT: [ 2] other PROGBITS 0000000000000002 001002 000003 00 WA
+# SEC-ORDER-NEXT: [ 3] .shstrtab STRTAB 0000000000000005 001005 00003b 00
+# SEC-ORDER-NEXT: [ 4] .symtab SYMTAB 0000000000000040 001040 000030 18
+# SEC-ORDER-NEXT: [ 5] .strtab STRTAB 0000000000000070 001070 000008 00
+# SEC-ORDER-NEXT: [ 6] .data PROGBITS 0000000000000078 001078 000020 00 WA
+# SEC-ORDER-NEXT: [ 7] .text PROGBITS 0000000000000098 001098 00000e 00 AX
+# SEC-ORDER-NEXT: [ 8] .comment PROGBITS 0000000000000000 0010a6 000008 01 MS
+
+# SEC-ORDER: Type Offset VirtAddr PhysAddr FileSiz MemSiz Flg Align
+# SEC-ORDER-NEXT: LOAD 0x001000 0x0000000000000000 0x0000000000000000 0x000098 0x000098 RW 0x1000
+# SEC-ORDER-NEXT: LOAD 0x001098 0x0000000000000098 0x0000000000000098 0x00000e 0x00000e R E 0x1000
+# SEC-ORDER-NEXT: GNU_STACK 0x000000 0x0000000000000000 0x0000000000000000 0x000000 0x000000 RW 0
# .text and .data have swapped names but proper sizes and types.
# RUN: echo "SECTIONS { \
@@ -89,6 +98,28 @@
# SEC-MULTI-NEXT: .shstrtab 00000035 {{[0-9a-f]*}}
# SEC-MULTI-NEXT: .strtab 00000008 {{[0-9a-f]*}}
+## other is placed in a PT_LOAD segment even if it is preceded by a non-alloc section.
+## The current implementation places .data, .bss, .comment and other in the same PT_LOAD.
+# RUN: echo 'SECTIONS { \
+# RUN: .text : { *(.text) } \
+# RUN: .data : { *(.data) } \
+# RUN: .comment : { *(.comment) } \
+# RUN: other : { *(other) } }' > %t5.lds
+# RUN: ld.lld -o %t5 -T %t5.lds %t
+# RUN: llvm-readelf -S -l %t5 | FileCheck --check-prefix=SEP-BY-NONALLOC %s
+
+# SEP-BY-NONALLOC: [Nr] Name Type Address Off Size ES Flg
+# SEP-BY-NONALLOC: [ 1] .text PROGBITS 0000000000000000 001000 00000e 00 AX
+# SEP-BY-NONALLOC-NEXT: [ 2] .data PROGBITS 000000000000000e 00100e 000020 00 WA
+# SEP-BY-NONALLOC-NEXT: [ 3] .bss NOBITS 000000000000002e 00102e 000002 00 WA
+# SEP-BY-NONALLOC-NEXT: [ 4] .comment PROGBITS 0000000000000030 00102e 000008 01 MS
+# SEP-BY-NONALLOC-NEXT: [ 5] other PROGBITS 0000000000000038 001038 000003 00 WA
+
+# SEP-BY-NONALLOC: Type Offset VirtAddr PhysAddr FileSiz MemSiz Flg Align
+# SEP-BY-NONALLOC-NEXT: LOAD 0x001000 0x0000000000000000 0x0000000000000000 0x00000e 0x00000e R E 0x1000
+# SEP-BY-NONALLOC-NEXT: LOAD 0x00100e 0x000000000000000e 0x000000000000000e 0x00002d 0x00002d RW 0x1000
+# SEP-BY-NONALLOC-NEXT: GNU_STACK 0x000000 0x0000000000000000 0x0000000000000000 0x000000 0x000000 RW 0
+
# Input section pattern contains additional semicolon.
# Case found in linux kernel script. Check we are able to parse it.
# RUN: echo "SECTIONS { .text : { ;;*(.text);;S = 0;; } }" > %t.script
diff --git a/lld/test/ELF/linkerscript/symbols-non-alloc.test b/lld/test/ELF/linkerscript/symbols-non-alloc.test
index 920cff96a3a2..2bd6fc84df46 100644
--- a/lld/test/ELF/linkerscript/symbols-non-alloc.test
+++ b/lld/test/ELF/linkerscript/symbols-non-alloc.test
@@ -1,14 +1,17 @@
# REQUIRES: x86
+## The address of a symbol assignment after a non-SHF_ALLOC section equals the
+## end address of the section.
+
# RUN: echo '.section .nonalloc,""; .quad 0' \
# RUN: | llvm-mc -filetype=obj -triple=x86_64-unknown-linux - -o %t
# RUN: ld.lld -o %t2 --script %s %t
# RUN: llvm-objdump --section-headers -t %t2 | FileCheck %s
# CHECK: Sections:
-# CHECK: .nonalloc 00000008 0000000000000000
+# CHECK: .nonalloc 00000008 0000000000000120
# CHECK: SYMBOL TABLE:
-# CHECK: 0000000000000008 g .nonalloc 0000000000000000 Sym
+# CHECK: 0000000000000128 g .nonalloc 0000000000000000 Sym
SECTIONS {
. = SIZEOF_HEADERS;
diff --git a/lldb/test/Shell/SymbolFile/DWARF/Inputs/debug-line-basic.script b/lldb/test/Shell/SymbolFile/DWARF/Inputs/debug-line-basic.script
index 7f3a1b9c2ff9..f5f89d137813 100644
--- a/lldb/test/Shell/SymbolFile/DWARF/Inputs/debug-line-basic.script
+++ b/lldb/test/Shell/SymbolFile/DWARF/Inputs/debug-line-basic.script
@@ -2,11 +2,11 @@ PHDRS {
text PT_LOAD;
}
SECTIONS {
- .shstrtab : { *(.shstrtab ) }
- .debug_info : { *(.debug_info ) }
- .debug_line : { *(.debug_line ) }
- .debug_str : { *(.debug_str ) }
- .debug_abbrev : { *(.debug_abbrev) }
+ .shstrtab 0 : { *(.shstrtab ) }
+ .debug_info 0 : { *(.debug_info ) }
+ .debug_line 0 : { *(.debug_line ) }
+ .debug_str 0 : { *(.debug_str ) }
+ .debug_abbrev 0 : { *(.debug_abbrev) }
. = 0x201000;
.text : { *(.text .text.f) } :text
More information about the llvm-commits
mailing list