[BOLT][RISCV] Implement TLS le/ie relocations (#67112)

mtvec · web-flow · commit c7d6d62252e3 · 2023-10-05T08:53:51.000Z
Handle the following relocations related to TLS local-exec and
initial-exec:
- R_RISCV_TLS_GOT_HI20
- R_RISCV_TPREL_HI20
- R_RISCV_TPREL_ADD
- R_RISCV_TPREL_LO12_I
- R_RISCV_TPREL_LO12_S

In addition, GNU ld has a quirk where after TLS le relaxation, two
unofficial relocation types may be emitted:
- R_RISCV_TPREL_I
- R_RISCV_TPREL_S

Since they are unofficial (defined in the reserved range of relocation
types), LLVM does not define them. Hence, I've defined them locally in
BOLT in a private namespace.
diff --git a/bolt/lib/Core/Relocation.cpp b/bolt/lib/Core/Relocation.cpp
@@ -20,6 +20,13 @@
 using namespace llvm;
 using namespace bolt;
 
+namespace ELFReserved {
+enum {
+  R_RISCV_TPREL_I = 49,
+  R_RISCV_TPREL_S = 50,
+};
+} // namespace ELFReserved
+
 Triple::ArchType Relocation::Arch;
 
 static bool isSupportedX86(uint64_t Type) {
@@ -111,6 +118,13 @@ static bool isSupportedRISCV(uint64_t Type) {
   case ELF::R_RISCV_LO12_I:
   case ELF::R_RISCV_LO12_S:
   case ELF::R_RISCV_64:
+  case ELF::R_RISCV_TLS_GOT_HI20:
+  case ELF::R_RISCV_TPREL_HI20:
+  case ELF::R_RISCV_TPREL_ADD:
+  case ELF::R_RISCV_TPREL_LO12_I:
+  case ELF::R_RISCV_TPREL_LO12_S:
+  case ELFReserved::R_RISCV_TPREL_I:
+  case ELFReserved::R_RISCV_TPREL_S:
     return true;
   }
 }
@@ -214,6 +228,7 @@ static size_t getSizeForTypeRISCV(uint64_t Type) {
     return 4;
   case ELF::R_RISCV_64:
   case ELF::R_RISCV_GOT_HI20:
+  case ELF::R_RISCV_TLS_GOT_HI20:
     // See extractValueRISCV for why this is necessary.
     return 8;
   }
@@ -532,6 +547,7 @@ static uint64_t extractValueRISCV(uint64_t Type, uint64_t Contents,
   case ELF::R_RISCV_BRANCH:
     return extractBImmRISCV(Contents);
   case ELF::R_RISCV_GOT_HI20:
+  case ELF::R_RISCV_TLS_GOT_HI20:
     // We need to know the exact address of the GOT entry so we extract the
     // value from both the AUIPC and L[D|W]. We cannot rely on the symbol in the
     // relocation for this since it simply refers to the object that is stored
@@ -600,6 +616,7 @@ static bool isGOTRISCV(uint64_t Type) {
   default:
     return false;
   case ELF::R_RISCV_GOT_HI20:
+  case ELF::R_RISCV_TLS_GOT_HI20:
     return true;
   }
 }
@@ -636,6 +653,14 @@ static bool isTLSRISCV(uint64_t Type) {
   switch (Type) {
   default:
     return false;
+  case ELF::R_RISCV_TLS_GOT_HI20:
+  case ELF::R_RISCV_TPREL_HI20:
+  case ELF::R_RISCV_TPREL_ADD:
+  case ELF::R_RISCV_TPREL_LO12_I:
+  case ELF::R_RISCV_TPREL_LO12_S:
+  case ELFReserved::R_RISCV_TPREL_I:
+  case ELFReserved::R_RISCV_TPREL_S:
+    return true;
   }
 }
 
@@ -733,6 +758,7 @@ static bool isPCRelativeRISCV(uint64_t Type) {
   case ELF::R_RISCV_RVC_JUMP:
   case ELF::R_RISCV_RVC_BRANCH:
   case ELF::R_RISCV_32_PCREL:
+  case ELF::R_RISCV_TLS_GOT_HI20:
     return true;
   }
 }
diff --git a/bolt/lib/Rewrite/RewriteInstance.cpp b/bolt/lib/Rewrite/RewriteInstance.cpp
@@ -2334,7 +2334,8 @@ void RewriteInstance::handleRelocation(const SectionRef &RelocatedSection,
     if (BC->isX86())
       return;
 
-    // The non-got related TLS relocations on AArch64 also could be skipped.
+    // The non-got related TLS relocations on AArch64 and RISC-V also could be
+    // skipped.
     if (!Relocation::isGOT(RType))
       return;
   }
diff --git a/bolt/lib/Target/RISCV/RISCVMCPlusBuilder.cpp b/bolt/lib/Target/RISCV/RISCVMCPlusBuilder.cpp
@@ -46,6 +46,7 @@ class RISCVMCPlusBuilder : public MCPlusBuilder {
     case ELF::R_RISCV_HI20:
     case ELF::R_RISCV_LO12_I:
     case ELF::R_RISCV_LO12_S:
+    case ELF::R_RISCV_TLS_GOT_HI20:
       return true;
     default:
       llvm_unreachable("Unexpected RISCV relocation type in code");
@@ -396,6 +397,7 @@ class RISCVMCPlusBuilder : public MCPlusBuilder {
     default:
       return Expr;
     case ELF::R_RISCV_GOT_HI20:
+    case ELF::R_RISCV_TLS_GOT_HI20:
       // The GOT is reused so no need to create GOT relocations
     case ELF::R_RISCV_PCREL_HI20:
       return RISCVMCExpr::create(Expr, RISCVMCExpr::VK_RISCV_PCREL_HI, Ctx);
diff --git a/bolt/test/RISCV/Inputs/tls-le-gnu-ld.yaml b/bolt/test/RISCV/Inputs/tls-le-gnu-ld.yaml
@@ -0,0 +1,92 @@
+--- !ELF
+FileHeader:
+  Class:           ELFCLASS64
+  Data:            ELFDATA2LSB
+  Type:            ET_EXEC
+  Machine:         EM_RISCV
+  Entry:           0x100B0
+ProgramHeaders:
+  - Type:            PT_LOAD
+    Flags:           [ PF_X, PF_R ]
+    FirstSec:        .text
+    LastSec:         .text
+    VAddr:           0x10000
+    Align:           0x1000
+    Offset:          0x0
+  - Type:            PT_TLS
+    Flags:           [ PF_R ]
+    FirstSec:        .tbss
+    LastSec:         .tbss
+    VAddr:           0x110C0
+    Align:           0x8
+    Offset:          0xc0
+Sections:
+  - Name:            .text
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC, SHF_EXECINSTR ]
+    Address:         0x100B0
+    AddressAlign:    0x4
+    Content:         '13000000832202002320520067800000'
+  - Name:            .tbss
+    Type:            SHT_NOBITS
+    Flags:           [ SHF_WRITE, SHF_ALLOC, SHF_TLS ]
+    Address:         0x110C0
+    AddressAlign:    0x8
+    Size:            0x8
+  - Name:            .rela.text
+    Type:            SHT_RELA
+    Flags:           [ SHF_INFO_LINK ]
+    Link:            .symtab
+    AddressAlign:    0x8
+    Info:            .text
+    Relocations:
+      - Offset:          0x100B4
+        Type:            R_RISCV_NONE
+      - Offset:          0x100B4
+        Type:            R_RISCV_RELAX
+      - Offset:          0x100B4
+        Type:            R_RISCV_NONE
+      - Offset:          0x100B4
+        Type:            R_RISCV_RELAX
+      - Offset:          0x100B4
+        Symbol:          i
+        Type:            0x31
+      - Offset:          0x100B4
+        Type:            R_RISCV_RELAX
+      - Offset:          0x100B8
+        Symbol:          i
+        Type:            0x32
+      - Offset:          0x100B8
+        Type:            R_RISCV_RELAX
+  - Type:            SectionHeaderTable
+    Sections:
+      - Name:            .text
+      - Name:            .rela.text
+      - Name:            .tbss
+      - Name:            .symtab
+      - Name:            .strtab
+      - Name:            .shstrtab
+Symbols:
+  - Name:            .text
+    Type:            STT_SECTION
+    Section:         .text
+    Value:           0x100B0
+  - Name:            .tbss
+    Type:            STT_SECTION
+    Section:         .tbss
+    Value:           0x110C0
+  - Name:            '__global_pointer$'
+    Index:           SHN_ABS
+    Binding:         STB_GLOBAL
+    Value:           0x118C0
+  - Name:            i
+    Type:            STT_TLS
+    Section:         .tbss
+    Binding:         STB_GLOBAL
+    Size:            0x8
+  - Name:            _start
+    Section:         .text
+    Binding:         STB_GLOBAL
+    Value:           0x100B0
+    Size:            0x10
+...
diff --git a/bolt/test/RISCV/reloc-tls.s b/bolt/test/RISCV/reloc-tls.s
@@ -0,0 +1,44 @@
+// RUN: llvm-mc -triple riscv64 -filetype obj -o %t.o %s
+// RUN: ld.lld --emit-relocs -o %t %t.o
+// RUN: llvm-bolt --print-cfg --print-only=tls_le,tls_ie -o /dev/null %t \
+// RUN:    | FileCheck %s
+
+// CHECK-LABEL: Binary Function "tls_le{{.*}}" after building cfg {
+// CHECK:      lui a5, 0
+// CHECK-NEXT: add a5, a5, tp
+// CHECK-NEXT: lw t0, 0(a5)
+// CHECK-NEXT: sw t0, 0(a5)
+
+// CHECK-LABEL: Binary Function "tls_ie" after building cfg {
+// CHECK-LABEL: .Ltmp0
+// CHECK:      auipc a0, %pcrel_hi(__BOLT_got_zero+{{[0-9]+}})
+// CHECK-NEXT: ld a0, %pcrel_lo(.Ltmp0)(a0)
+    .text
+    .globl tls_le, _start
+    .p2align 2
+tls_le:
+_start:
+    nop
+    lui a5, %tprel_hi(i)
+    add a5, a5, tp, %tprel_add(i)
+    lw t0, %tprel_lo(i)(a5)
+    sw t0, %tprel_lo(i)(a5)
+    ret
+    .size _start, .-_start
+
+    .globl tls_ie
+    .p2align 2
+tls_ie:
+    nop
+    la.tls.ie a0, i
+    ret
+    .size tls_ie, .-tls_ie
+
+    .section .tbss,"awT",@nobits
+    .type i,@object
+    .globl i
+    .p2align 3
+i:
+    .quad 0
+    .size i, .-i
+
diff --git a/bolt/test/RISCV/tls-le-gnu-ld.test b/bolt/test/RISCV/tls-le-gnu-ld.test
@@ -0,0 +1,11 @@
+// This test checks that the binaries produces with GNU ld TLS le relaxation are
+// properly processed by BOLT. GNU ld currently emits two non-standard
+// relocations (R_RISCV_TPREL_I and R_RISCV_TPREL_S) in this case.
+
+// RUN: yaml2obj %p/Inputs/tls-le-gnu-ld.yaml &> %t.exe
+// RUN: llvm-bolt %t.exe -o %t.bolt.exe --print-cfg --print-only=_start \
+// RUN:   | FileCheck %s
+
+// CHECK: Binary Function "_start" after building cfg {
+// CHECK:      lw t0, 0(tp)
+// CHECK-NEXT: sw t0, 0(tp)

Original file line number	Diff line number	Diff line change
`@@ -2334,7 +2334,8 @@ void RewriteInstance::handleRelocation(const SectionRef &RelocatedSection,`
`2334`	`2334`	`if (BC->isX86())`
`2335`	`2335`	`return;`
`2336`	`2336`
`2337`		`- // The non-got related TLS relocations on AArch64 also could be skipped.`
	`2337`	`+ // The non-got related TLS relocations on AArch64 and RISC-V also could be`
	`2338`	`+ // skipped.`
`2338`	`2339`	`if (!Relocation::isGOT(RType))`
`2339`	`2340`	`return;`
`2340`	`2341`	`}`