[InstrProfiling] Use !associated metadata for counters, data and values
C identifier name input sections such as __llvm_prf_* are GC roots so
they cannot be discarded. In LLD, the SHF_LINK_ORDER flag overrides the
C identifier name semantics.
The !associated metadata may be attached to a global object declaration
with a single argument that references another global object, and it
gets lowered to SHF_LINK_ORDER flag. When a function symbol is discarded
by the linker, setting up !associated metadata allows linker to discard
counters, data and values associated with that function symbol.
Note that !associated metadata is only supported by ELF, it does not have
any effect on non-ELF targets.
Differential Revision: https://reviews.llvm.org/D76802
GitOrigin-RevId: df3e39f60b356ca9dbfc11e96e5fdda30afa7acb
diff --git a/test/profile/instrprof-gc-sections.c b/test/profile/instrprof-gc-sections.c
new file mode 100644
index 0000000..b1f0720
--- /dev/null
+++ b/test/profile/instrprof-gc-sections.c
@@ -0,0 +1,91 @@
+// REQUIRES: linux, lld-available
+
+// RUN: %clang_profgen=%t.profraw -fuse-ld=lld -fcoverage-mapping -mllvm -counter-link-order -mllvm -enable-name-compression=false -DCODE=1 -ffunction-sections -fdata-sections -Wl,--gc-sections -o %t %s
+// RUN: %run %t
+// RUN: llvm-profdata merge -o %t.profdata %t.profraw
+// RUN: llvm-profdata show --all-functions %t.profdata | FileCheck %s -check-prefix=PROF
+// RUN: llvm-cov show %t -instr-profile %t.profdata | FileCheck %s -check-prefix=COV
+// RUN: llvm-nm %t | FileCheck %s -check-prefix=NM
+// RUN: llvm-readelf -x __llvm_prf_names %t | FileCheck %s -check-prefix=PRF_NAMES
+// RUN: llvm-readelf -x __llvm_prf_cnts %t | FileCheck %s -check-prefix=PRF_CNTS
+
+// RUN: %clang_lto_profgen=%t.lto.profraw -fuse-ld=lld -fcoverage-mapping -mllvm -counter-link-order -mllvm -enable-name-compression=false -DCODE=1 -ffunction-sections -fdata-sections -Wl,--gc-sections -flto -o %t.lto %s
+// RUN: %run %t.lto
+// RUN: llvm-profdata merge -o %t.lto.profdata %t.lto.profraw
+// RUN: llvm-profdata show --all-functions %t.lto.profdata | FileCheck %s -check-prefix=PROF
+// RUN: llvm-cov show %t.lto -instr-profile %t.lto.profdata | FileCheck %s -check-prefix=COV
+// RUN: llvm-nm %t.lto | FileCheck %s -check-prefix=NM
+// RUN: llvm-readelf -x __llvm_prf_names %t.lto | FileCheck %s -check-prefix=PRF_NAMES
+// RUN: llvm-readelf -x __llvm_prf_cnts %t.lto | FileCheck %s -check-prefix=PRF_CNTS
+
+// Note: We expect foo() and some of the profiling data associated with it to
+// be garbage collected.
+
+// Note: When there is no code in a program, we expect to see the exact same
+// set of external functions provided by the profile runtime.
+
+// RUN: %clang_profgen -fuse-ld=lld -fcoverage-mapping -mllvm -counter-link-order -ffunction-sections -fdata-sections -Wl,--gc-sections -shared -o %t.nocode.so %s
+// RUN: llvm-nm -jgU %t.nocode.so | grep -vE "__start_.*|__stop_.*" > %t.nocode.syms
+// RUN: llvm-nm -jgU %t | grep -vE "main|_start|_IO_stdin_used|__libc_.*" > %t.code.syms
+// RUN: diff %t.nocode.syms %t.code.syms
+
+// Note: We also check the IR instrumentation and expect foo() to be garbage
+// collected as well.
+
+// RUN: %clang_pgogen=%t.pgo.profraw -fuse-ld=lld -mllvm -counter-link-order -DCODE=1 -ffunction-sections -fdata-sections -Wl,--gc-sections -o %t.pgo %s
+// RUN: %run %t.pgo
+// RUN: llvm-profdata merge -o %t.pgo.profdata %t.pgo.profraw
+// RUN: llvm-profdata show --all-functions %t.pgo.profdata | FileCheck %s -check-prefix=PGO
+// RUN: llvm-nm %t.pgo | FileCheck %s -check-prefix=NM
+
+#ifdef CODE
+
+// COV: [[@LINE+1]]{{ *}}|{{ *}}0|void foo()
+void foo() {}
+
+// COV: [[@LINE+1]]{{ *}}|{{ *}}1|int main
+int main() { return 0; }
+
+#endif // CODE
+
+// NM-NOT: foo
+
+// PROF: Counters:
+// PROF-NEXT: main:
+// PROF-NEXT: Hash:
+// PROF-NEXT: Counters: 1
+// PROF-NEXT: Function count: 1
+// PROF-NEXT: Instrumentation level: Front-end
+// PROF-NEXT: Functions shown: 1
+// PROF-NEXT: Total functions: 1
+// PROF-NEXT: Maximum function count:
+// PROF-NEXT: Maximum internal block count:
+
+// Note: We don't expect the names of garbage collected functions to disappear
+// from __llvm_prf_names, because collectPGOFuncNameStrings() glues the names
+// together.
+
+// PRF_NAMES: Hex dump of section '__llvm_prf_names':
+// PRF_NAMES-NEXT: {{.*}} 0800666f 6f016d61 696e {{.*$}}
+// | | f o o # m a i n
+// | |___________|
+// | |
+// UncompressedLen = 8 |
+// |
+// CompressedLen = 0
+
+// Note: We expect the profile counters for garbage collected functions to also
+// be garbage collected.
+
+// PRF_CNTS: Hex dump of section '__llvm_prf_cnts':
+// PRF_CNTS-NEXT: {{.*}} 00000000 00000000 {{.*$}}
+
+// PGO: Counters:
+// PGO-NEXT: main:
+// PGO-NEXT: Hash:
+// PGO-NEXT: Counters: 1
+// PGO-NEXT: Instrumentation level: IR
+// PGO-NEXT: Functions shown: 1
+// PGO-NEXT: Total functions: 1
+// PGO-NEXT: Maximum function count:
+// PGO-NEXT: Maximum internal block count:
