maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/CodeGenCXX/sections.cpp

73 lines
2.4 KiB
C++
Raw Normal View History

Move test/CodeGen/sections.c to CodeGenCXX/sections.cpp The test was running with -xc++. Seems it wants to be a C++ file. llvm-svn: 220069
2014-10-18 02:13:21 +08:00
// RUN: %clang_cc1 -emit-llvm -triple i686-pc-win32 -fms-extensions -o - %s | FileCheck %s
The emitted IR is the same, we need these flags to actually use the LLVM target. Mark it as requiring the x86 target. llvm-svn: 192417
2013-10-11 11:52:43 +08:00
[MS-ABI] Add support for #pragma section and related pragmas This patch adds support for the msvc pragmas section, bss_seg, code_seg, const_seg and data_seg as well as support for __declspec(allocate()). Additionally it corrects semantics and adds diagnostics for __attribute__((section())) and the interaction between the attribute and the msvc pragmas and declspec. In general conflicts should now be well diganosed within and among these features. In supporting the pragmas new machinery for uniform lexing for msvc pragmas was introduced. The new machinery always lexes the entire pragma and stores it on an annotation token. The parser is responsible for parsing the pragma when the handling the annotation token. There is a known outstanding bug in this implementation in C mode. Because these attributes and pragmas apply _only_ to definitions, we process them at the time we detect a definition. Due to tentative definitions in C, we end up processing the definition late. This means that in C mode, everything that ends up in a BSS section will end up in the _last_ BSS section rather than the one that was live at the time of tentative definition, even if that turns out to be the point of actual definition. This issue is not known to impact anything as of yet because we are not aware of a clear use or use case for #pragma bss_seg but should be fixed at some point. Differential Revision=http://reviews.llvm.org/D3065#inline-16241 llvm-svn: 205810
2014-04-09 06:30:47 +08:00
extern "C" {
Move test/CodeGen/sections.c to CodeGenCXX/sections.cpp The test was running with -xc++. Seems it wants to be a C++ file. llvm-svn: 220069
2014-10-18 02:13:21 +08:00
[MS-ABI] Add support for #pragma section and related pragmas This patch adds support for the msvc pragmas section, bss_seg, code_seg, const_seg and data_seg as well as support for __declspec(allocate()). Additionally it corrects semantics and adds diagnostics for __attribute__((section())) and the interaction between the attribute and the msvc pragmas and declspec. In general conflicts should now be well diganosed within and among these features. In supporting the pragmas new machinery for uniform lexing for msvc pragmas was introduced. The new machinery always lexes the entire pragma and stores it on an annotation token. The parser is responsible for parsing the pragma when the handling the annotation token. There is a known outstanding bug in this implementation in C mode. Because these attributes and pragmas apply _only_ to definitions, we process them at the time we detect a definition. Due to tentative definitions in C, we end up processing the definition late. This means that in C mode, everything that ends up in a BSS section will end up in the _last_ BSS section rather than the one that was live at the time of tentative definition, even if that turns out to be the point of actual definition. This issue is not known to impact anything as of yet because we are not aware of a clear use or use case for #pragma bss_seg but should be fixed at some point. Differential Revision=http://reviews.llvm.org/D3065#inline-16241 llvm-svn: 205810
2014-04-09 06:30:47 +08:00
#pragma const_seg(".my_const")
#pragma bss_seg(".my_bss")
int D = 1;
#pragma data_seg(".data")
int a = 1;
#pragma data_seg(push, label, ".data2")
extern const int b;
const int b = 1;
const char* s = "my string!";
#pragma data_seg(push, ".my_seg")
int c = 1;
#pragma data_seg(pop, label)
int d = 1;
int e;
#pragma bss_seg(".c")
int f;
void g(void){}
#pragma code_seg(".my_code")
void h(void){}
#pragma bss_seg()
int i;
#pragma bss_seg(".bss1")
#pragma bss_seg(push, test, ".bss2")
#pragma bss_seg()
#pragma bss_seg()
int TEST1;
#pragma bss_seg(pop)
int TEST2;
MS Compat: mark globals emitted in read-only sections const They cannot be written to, so marking them const makes sense and may improve optimisation. As a side-effect, SectionInfos has to be moved from Sema to ASTContext. It also fixes this problem, that occurs when compiling ATL: warning LNK4254: section 'ATL' (C0000040) merged into '.rdata' (40000040) with different attributes The ATL headers are putting variables in a special section that's marked read-only. However, Clang currently can't model that read-onlyness in the IR. But, by making the variables const, the section does become read-only, and the linker warning is avoided. Differential Revision: http://reviews.llvm.org/D5812 llvm-svn: 219960
2014-10-17 04:52:46 +08:00
#pragma section("read_flag_section", read)
// Even though they are not declared const, these become constant since they are
// in a read-only section.
__declspec(allocate("read_flag_section")) int unreferenced = 0;
extern __declspec(allocate("read_flag_section")) int referenced = 42;
int *user() { return &referenced; }
Parse: Ignore "long" and "short" in #pragma section This fixes PR21337. llvm-svn: 220429
2014-10-23 05:08:43 +08:00
#pragma section("no_section_attributes")
// A pragma section with no section attributes is read/write.
__declspec(allocate("no_section_attributes")) int implicitly_read_write = 42;
#pragma section("long_section", long)
// Pragma section ignores "long".
__declspec(allocate("long_section")) long long_var = 42;
#pragma section("short_section", short)
// Pragma section ignores "short".
__declspec(allocate("short_section")) short short_var = 42;
[MS-ABI] Add support for #pragma section and related pragmas This patch adds support for the msvc pragmas section, bss_seg, code_seg, const_seg and data_seg as well as support for __declspec(allocate()). Additionally it corrects semantics and adds diagnostics for __attribute__((section())) and the interaction between the attribute and the msvc pragmas and declspec. In general conflicts should now be well diganosed within and among these features. In supporting the pragmas new machinery for uniform lexing for msvc pragmas was introduced. The new machinery always lexes the entire pragma and stores it on an annotation token. The parser is responsible for parsing the pragma when the handling the annotation token. There is a known outstanding bug in this implementation in C mode. Because these attributes and pragmas apply _only_ to definitions, we process them at the time we detect a definition. Due to tentative definitions in C, we end up processing the definition late. This means that in C mode, everything that ends up in a BSS section will end up in the _last_ BSS section rather than the one that was live at the time of tentative definition, even if that turns out to be the point of actual definition. This issue is not known to impact anything as of yet because we are not aware of a clear use or use case for #pragma bss_seg but should be fixed at some point. Differential Revision=http://reviews.llvm.org/D3065#inline-16241 llvm-svn: 205810
2014-04-09 06:30:47 +08:00
}
Add -fno-function-sections and -fno-data-sections. Since -f{function,data}-sections had no tests at all, add some, and verify that the -fno variants work as well. llvm-svn: 192413
2013-10-11 11:35:10 +08:00
[MS-ABI] Add support for #pragma section and related pragmas This patch adds support for the msvc pragmas section, bss_seg, code_seg, const_seg and data_seg as well as support for __declspec(allocate()). Additionally it corrects semantics and adds diagnostics for __attribute__((section())) and the interaction between the attribute and the msvc pragmas and declspec. In general conflicts should now be well diganosed within and among these features. In supporting the pragmas new machinery for uniform lexing for msvc pragmas was introduced. The new machinery always lexes the entire pragma and stores it on an annotation token. The parser is responsible for parsing the pragma when the handling the annotation token. There is a known outstanding bug in this implementation in C mode. Because these attributes and pragmas apply _only_ to definitions, we process them at the time we detect a definition. Due to tentative definitions in C, we end up processing the definition late. This means that in C mode, everything that ends up in a BSS section will end up in the _last_ BSS section rather than the one that was live at the time of tentative definition, even if that turns out to be the point of actual definition. This issue is not known to impact anything as of yet because we are not aware of a clear use or use case for #pragma bss_seg but should be fixed at some point. Differential Revision=http://reviews.llvm.org/D3065#inline-16241 llvm-svn: 205810
2014-04-09 06:30:47 +08:00
//CHECK: @D = global i32 1
//CHECK: @a = global i32 1, section ".data"
//CHECK: @b = constant i32 1, section ".my_const"
[MS-ABI] Lit fix for r205810 On linux strings have different linkage than on windows. This patch makes the lit test more general. llvm-svn: 205812
2014-04-09 06:49:38 +08:00
//CHECK: @[[MYSTR:.*]] = {{.*}} unnamed_addr constant [11 x i8] c"my string!\00"
Test case updates for explicit type parameter to the gep operator llvm-svn: 232187
2015-03-14 02:21:46 +08:00
//CHECK: @s = global i8* getelementptr inbounds ([11 x i8], [11 x i8]* @[[MYSTR]], i32 0, i32 0), section ".data2"
[MS-ABI] Add support for #pragma section and related pragmas This patch adds support for the msvc pragmas section, bss_seg, code_seg, const_seg and data_seg as well as support for __declspec(allocate()). Additionally it corrects semantics and adds diagnostics for __attribute__((section())) and the interaction between the attribute and the msvc pragmas and declspec. In general conflicts should now be well diganosed within and among these features. In supporting the pragmas new machinery for uniform lexing for msvc pragmas was introduced. The new machinery always lexes the entire pragma and stores it on an annotation token. The parser is responsible for parsing the pragma when the handling the annotation token. There is a known outstanding bug in this implementation in C mode. Because these attributes and pragmas apply _only_ to definitions, we process them at the time we detect a definition. Due to tentative definitions in C, we end up processing the definition late. This means that in C mode, everything that ends up in a BSS section will end up in the _last_ BSS section rather than the one that was live at the time of tentative definition, even if that turns out to be the point of actual definition. This issue is not known to impact anything as of yet because we are not aware of a clear use or use case for #pragma bss_seg but should be fixed at some point. Differential Revision=http://reviews.llvm.org/D3065#inline-16241 llvm-svn: 205810
2014-04-09 06:30:47 +08:00
//CHECK: @c = global i32 1, section ".my_seg"
//CHECK: @d = global i32 1, section ".data"
//CHECK: @e = global i32 0, section ".my_bss"
//CHECK: @f = global i32 0, section ".c"
//CHECK: @i = global i32 0
//CHECK: @TEST1 = global i32 0
//CHECK: @TEST2 = global i32 0, section ".bss1"
MS Compat: mark globals emitted in read-only sections const They cannot be written to, so marking them const makes sense and may improve optimisation. As a side-effect, SectionInfos has to be moved from Sema to ASTContext. It also fixes this problem, that occurs when compiling ATL: warning LNK4254: section 'ATL' (C0000040) merged into '.rdata' (40000040) with different attributes The ATL headers are putting variables in a special section that's marked read-only. However, Clang currently can't model that read-onlyness in the IR. But, by making the variables const, the section does become read-only, and the linker warning is avoided. Differential Revision: http://reviews.llvm.org/D5812 llvm-svn: 219960
2014-10-17 04:52:46 +08:00
//CHECK: @unreferenced = constant i32 0, section "read_flag_section"
//CHECK: @referenced = constant i32 42, section "read_flag_section"
Parse: Ignore "long" and "short" in #pragma section This fixes PR21337. llvm-svn: 220429
2014-10-23 05:08:43 +08:00
//CHECK: @implicitly_read_write = global i32 42, section "no_section_attributes"
//CHECK: @long_var = global i32 42, section "long_section"
//CHECK: @short_var = global i16 42, section "short_section"
[MS-ABI] Add support for #pragma section and related pragmas This patch adds support for the msvc pragmas section, bss_seg, code_seg, const_seg and data_seg as well as support for __declspec(allocate()). Additionally it corrects semantics and adds diagnostics for __attribute__((section())) and the interaction between the attribute and the msvc pragmas and declspec. In general conflicts should now be well diganosed within and among these features. In supporting the pragmas new machinery for uniform lexing for msvc pragmas was introduced. The new machinery always lexes the entire pragma and stores it on an annotation token. The parser is responsible for parsing the pragma when the handling the annotation token. There is a known outstanding bug in this implementation in C mode. Because these attributes and pragmas apply _only_ to definitions, we process them at the time we detect a definition. Due to tentative definitions in C, we end up processing the definition late. This means that in C mode, everything that ends up in a BSS section will end up in the _last_ BSS section rather than the one that was live at the time of tentative definition, even if that turns out to be the point of actual definition. This issue is not known to impact anything as of yet because we are not aware of a clear use or use case for #pragma bss_seg but should be fixed at some point. Differential Revision=http://reviews.llvm.org/D3065#inline-16241 llvm-svn: 205810
2014-04-09 06:30:47 +08:00
//CHECK: define void @g()
//CHECK: define void @h() {{.*}} section ".my_code"