File _service:obs_scm:0003-Backport-ELF-RISCV-Implem... of Package lld

File _service:obs_scm:0003-Backport-ELF-RISCV-Implement-emit-relocs-with-relaxation.patch of Package lld

From d53182c7fcc371f575fd71fa74e28220db6e9b82 Mon Sep 17 00:00:00 2001
From: Job Noorman <jnoorman@igalia.com>
Date: Sat, 9 Sep 2023 10:24:16 +0200
Subject: [PATCH 09/14] [ELF][RISCV] Implement --emit-relocs with relaxation

Linker relaxation may change relocations (offsets and types). However,
when --emit-relocs is used, relocations are simply copied from the input
section causing a mismatch with the corresponding (relaxed) code
section.

This patch fixes this as follows: for non-relocatable RISC-V binaries,
`InputSection::copyRelocations` reads relocations from the relocated
section's `relocations` array (since this gets updated by the relaxation
code). For all other cases, relocations are read from the input section
directly as before.

In order to reuse as much code as possible, and to keep the diff small,
the original `InputSection::copyRelocations` is changed to accept the
relocations as a range of `Relocation` objects. This means that, in the
general case when reading from the input section, raw relocations need
to be converted to `Relocation`s first, which introduces quite a bit of
boiler plate. It also means there's a slight code size increase due to
the extra instantiations of `copyRelocations` (for both range types).

Reviewed By: MaskRay

Differential Revision: https://reviews.llvm.org/D159082

(cherry picked from commit 649cac3b627fa3d466b8807536c8be970cc8c32f)
Change-Id: I53aeeeed4bea0d74c5571bc90405bcbd363781b2
---
 lld/ELF/InputSection.cpp               | 56 ++++++++++++++++-----
 lld/ELF/InputSection.h                 |  6 ++-
 lld/test/ELF/riscv-relax-emit-relocs.s | 69 ++++++++++++++++++++++++++
 3 files changed, 117 insertions(+), 14 deletions(-)
 create mode 100644 lld/test/ELF/riscv-relax-emit-relocs.s

diff --git a/lld/ELF/InputSection.cpp b/lld/ELF/InputSection.cpp
index 2edaa2b40493..1aff6b968d86 100644
--- a/lld/ELF/InputSection.cpp
+++ b/lld/ELF/InputSection.cpp
@@ -349,29 +349,61 @@ InputSectionBase *InputSection::getRelocatedSection() const {
   return sections[info];
 }
 
+template <class ELFT, class RelTy>
+void InputSection::copyRelocations(uint8_t *buf) {
+  if (config->relax && !config->relocatable && config->emachine == EM_RISCV) {
+    // On RISC-V, relaxation might change relocations: copy from
+    // internal ones that are updated by relaxation.
+    InputSectionBase *sec = getRelocatedSection();
+    copyRelocations<ELFT, RelTy>(buf, llvm::make_range(sec->relocations.begin(),
+                                                       sec->relocations.end()));
+  } else {
+    // Convert the raw relocations in the input section into Relocation objects
+    // suitable to be used by copyRelocations below.
+    struct MapRel {
+      const ObjFile<ELFT> &file;
+      Relocation operator()(const RelTy &rel) const {
+        // RelExpr is not used so set to a dummy value.
+        return Relocation{R_NONE, rel.getType(config->isMips64EL), rel.r_offset,
+                          getAddend<ELFT>(rel), &file.getRelocTargetSym(rel)};
+      }
+    };
+
+    using RawRels = ArrayRef<RelTy>;
+    using MapRelIter =
+        llvm::mapped_iterator<typename RawRels::iterator, MapRel>;
+    auto mapRel = MapRel{*getFile<ELFT>()};
+    RawRels rawRels = getDataAs<RelTy>();
+    auto rels = llvm::make_range(MapRelIter(rawRels.begin(), mapRel),
+                                 MapRelIter(rawRels.end(), mapRel));
+    copyRelocations<ELFT, RelTy>(buf, rels);
+  }
+}
+
 // This is used for -r and --emit-relocs. We can't use memcpy to copy
 // relocations because we need to update symbol table offset and section index
 // for each relocation. So we copy relocations one by one.
-template <class ELFT, class RelTy>
-void InputSection::copyRelocations(uint8_t *buf, ArrayRef<RelTy> rels) {
+template <class ELFT, class RelTy, class RelIt>
+void InputSection::copyRelocations(uint8_t *buf,
+                                   llvm::iterator_range<RelIt> rels) {
   const TargetInfo &target = *elf::target;
   InputSectionBase *sec = getRelocatedSection();
   (void)sec->contentMaybeDecompress(); // uncompress if needed
 
-  for (const RelTy &rel : rels) {
-    RelType type = rel.getType(config->isMips64EL);
+  for (const Relocation &rel : rels) {
+    RelType type = rel.type;
     const ObjFile<ELFT> *file = getFile<ELFT>();
-    Symbol &sym = file->getRelocTargetSym(rel);
+    Symbol &sym = *rel.sym;
 
     auto *p = reinterpret_cast<typename ELFT::Rela *>(buf);
     buf += sizeof(RelTy);
 
     if (RelTy::IsRela)
-      p->r_addend = getAddend<ELFT>(rel);
+      p->r_addend = rel.addend;
 
     // Output section VA is zero for -r, so r_offset is an offset within the
     // section, but for --emit-relocs it is a virtual address.
-    p->r_offset = sec->getVA(rel.r_offset);
+    p->r_offset = sec->getVA(rel.offset);
     p->setSymbolAndType(in.symTab->getSymbolIndex(&sym), type,
                         config->isMips64EL);
 
@@ -408,8 +440,8 @@ void InputSection::copyRelocations(uint8_t *buf, ArrayRef<RelTy> rels) {
         continue;
       }
 
-      int64_t addend = getAddend<ELFT>(rel);
-      const uint8_t *bufLoc = sec->content().begin() + rel.r_offset;
+      int64_t addend = rel.addend;
+      const uint8_t *bufLoc = sec->content().begin() + rel.offset;
       if (!RelTy::IsRela)
         addend = target.getImplicitAddend(bufLoc, type);
 
@@ -432,7 +464,7 @@ void InputSection::copyRelocations(uint8_t *buf, ArrayRef<RelTy> rels) {
       if (RelTy::IsRela)
         p->r_addend = sym.getVA(addend) - section->getOutputSection()->addr;
       else if (config->relocatable && type != target.noneRel)
-        sec->addReloc({R_ABS, type, rel.r_offset, addend, &sym});
+        sec->addReloc({R_ABS, type, rel.offset, addend, &sym});
     } else if (config->emachine == EM_PPC && type == R_PPC_PLTREL24 &&
                p->r_addend >= 0x8000 && sec->file->ppc32Got2) {
       // Similar to R_MIPS_GPREL{16,32}. If the addend of R_PPC_PLTREL24
@@ -1106,11 +1138,11 @@ template <class ELFT> void InputSection::writeTo(uint8_t *buf) {
   // If -r or --emit-relocs is given, then an InputSection
   // may be a relocation section.
   if (LLVM_UNLIKELY(type == SHT_RELA)) {
-    copyRelocations<ELFT>(buf, getDataAs<typename ELFT::Rela>());
+    copyRelocations<ELFT, typename ELFT::Rela>(buf);
     return;
   }
   if (LLVM_UNLIKELY(type == SHT_REL)) {
-    copyRelocations<ELFT>(buf, getDataAs<typename ELFT::Rel>());
+    copyRelocations<ELFT, typename ELFT::Rel>(buf);
     return;
   }
 
diff --git a/lld/ELF/InputSection.h b/lld/ELF/InputSection.h
index 15122d6abd6b..2b91711abba3 100644
--- a/lld/ELF/InputSection.h
+++ b/lld/ELF/InputSection.h
@@ -396,8 +396,10 @@ public:
   static InputSection discarded;
 
 private:
-  template <class ELFT, class RelTy>
-  void copyRelocations(uint8_t *buf, llvm::ArrayRef<RelTy> rels);
+  template <class ELFT, class RelTy> void copyRelocations(uint8_t *buf);
+
+  template <class ELFT, class RelTy, class RelIt>
+  void copyRelocations(uint8_t *buf, llvm::iterator_range<RelIt> rels);
 
   template <class ELFT> void copyShtGroup(uint8_t *buf);
 };
diff --git a/lld/test/ELF/riscv-relax-emit-relocs.s b/lld/test/ELF/riscv-relax-emit-relocs.s
new file mode 100644
index 000000000000..ebd69b742d4f
--- /dev/null
+++ b/lld/test/ELF/riscv-relax-emit-relocs.s
@@ -0,0 +1,69 @@
+# REQUIRES: riscv
+## Test that we can handle --emit-relocs while relaxing.
+
+# RUN: rm -rf %t && mkdir %t && cd %t
+
+# RUN: llvm-mc -filetype=obj -triple=riscv32 -mattr=+relax %s -o 32.o
+# RUN: ld.lld -Ttext=0x10000 --emit-relocs 32.o -o 32
+# RUN: llvm-objdump -dr --no-show-raw-insn -M no-aliases 32 | FileCheck %s
+
+# RUN: llvm-mc -filetype=obj -triple=riscv64 -mattr=+relax %s -o 64.o
+# RUN: ld.lld -Ttext=0x10000 --emit-relocs 64.o -o 64
+# RUN: llvm-objdump -dr --no-show-raw-insn -M no-aliases 64 | FileCheck %s
+
+## -r should keep original relocations.
+# RUN: ld.lld -r 64.o -o 64.r
+# RUN: llvm-objdump -dr --no-show-raw-insn -M no-aliases 64.r | FileCheck %s --check-prefix=CHECKR
+
+## --no-relax should keep original relocations.
+# RUN: ld.lld --emit-relocs --no-relax 64.o -o 64.norelax
+# RUN: llvm-objdump -dr --no-show-raw-insn -M no-aliases 64.norelax | FileCheck %s --check-prefix=CHECKNORELAX
+
+# CHECK:      <_start>:
+# CHECK-NEXT:     jal ra, 0x10008 <f>
+# CHECK-NEXT:         R_RISCV_JAL f
+# CHECK-NEXT:         R_RISCV_RELAX *ABS*
+# CHECK-NEXT:     jal ra, 0x10008 <f>
+# CHECK-NEXT:         R_RISCV_JAL f
+# CHECK-NEXT:         R_RISCV_RELAX *ABS*
+# CHECK-EMPTY:
+# CHECK-NEXT: <f>:
+# CHECK-NEXT:     jalr zero, 0(ra)
+# CHECK-NEXT:         R_RISCV_ALIGN *ABS*+0x4
+
+# CHECKR:      <_start>:
+# CHECKR-NEXT:     auipc ra, 0
+# CHECKR-NEXT:         R_RISCV_CALL_PLT f
+# CHECKR-NEXT:         R_RISCV_RELAX *ABS*
+# CHECKR-NEXT:     jalr ra, 0(ra)
+# CHECKR-NEXT:     auipc ra, 0
+# CHECKR-NEXT:         R_RISCV_CALL_PLT f
+# CHECKR-NEXT:         R_RISCV_RELAX *ABS*
+# CHECKR-NEXT:     jalr ra, 0(ra)
+# CHECKR-NEXT:     addi zero, zero, 0
+# CHECKR-NEXT:         R_RISCV_ALIGN *ABS*+0x4
+# CHECKR-EMPTY:
+# CHECKR-NEXT: <f>:
+# CHECKR-NEXT:     jalr zero, 0(ra)
+
+# CHECKNORELAX:      <_start>:
+# CHECKNORELAX-NEXT:     auipc ra, 0
+# CHECKNORELAX-NEXT:         R_RISCV_CALL_PLT f
+# CHECKNORELAX-NEXT:         R_RISCV_RELAX *ABS*
+# CHECKNORELAX-NEXT:     jalr ra, 16(ra)
+# CHECKNORELAX-NEXT:     auipc ra, 0
+# CHECKNORELAX-NEXT:         R_RISCV_CALL_PLT f
+# CHECKNORELAX-NEXT:         R_RISCV_RELAX *ABS*
+# CHECKNORELAX-NEXT:     jalr ra, 8(ra)
+# CHECKNORELAX-EMPTY:
+# CHECKNORELAX-NEXT: <f>:
+# CHECKNORELAX-NEXT:     jalr zero, 0(ra)
+# CHECKNORELAX-NEXT:         R_RISCV_ALIGN *ABS*+0x4
+
+.global _start
+_start:
+  call f
+  call f
+  .balign 8
+f:
+  ret
-- 
2.20.1