[PowerPC] Add support for R_PPC64_GOT_TPREL_PCREL34 used in TLS Initial Exec

Add Thread Local Storage Initial Exec support to LLD.

This patch adds the computation for the relocations as well as the relaxation from Initial Exec to Local Exec.

Initial Exec:
```
pld r9, x@got@tprel@pcrel
add r9, r9, x@tls@pcrel
```
or
```
pld r9, x@got@tprel@pcrel
lbzx r10, r9, x@tls@pcrel
```
Note that @tls@pcrel is actually encoded as R_PPC64_TLS with a one byte displacement.

For the above examples relaxing Intitial Exec to Local Exec:
```
paddi r9, r9, x@tprel
nop
```
or
```
paddi r9, r13, x@tprel
lbz r10, 0(r9)
```

Reviewed By: nemanjai, MaskRay, #powerpc

Differential Revision: https://reviews.llvm.org/D86893

2 files changed, 170 insertions, 9 deletions

diff --git a/lld/ELF/Arch/PPC64.cpp b/lld/ELF/Arch/PPC64.cpp
index 5225463..e367535 100644
--- a/lld/ELF/Arch/PPC64.cpp
+++ b/lld/ELF/Arch/PPC64.cpp
@@ -840,16 +840,49 @@ void PPC64::relaxTlsIeToLe(uint8_t *loc, const Relocation &rel,
     relocateNoSym(loc, R_PPC64_TPREL16_HA, val);
     break;
   }
+  case R_PPC64_GOT_TPREL_PCREL34: {
+    const uint64_t pldRT = readPrefixedInstruction(loc) & 0x0000000003e00000;
+    // paddi RT(from pld), r13, symbol@tprel, 0
+    writePrefixedInstruction(loc, 0x06000000380d0000 | pldRT);
+    relocateNoSym(loc, R_PPC64_TPREL34, val);
+    break;
+  }
   case R_PPC64_TLS: {
-    uint32_t primaryOp = getPrimaryOpCode(read32(loc));
-    if (primaryOp != 31)
-      error("unrecognized instruction for IE to LE R_PPC64_TLS");
-    uint32_t secondaryOp = (read32(loc) & 0x000007FE) >> 1; // bits 21-30
-    uint32_t dFormOp = getPPCDFormOp(secondaryOp);
-    if (dFormOp == 0)
-      error("unrecognized instruction for IE to LE R_PPC64_TLS");
-    write32(loc, ((dFormOp << 26) | (read32(loc) & 0x03FFFFFF)));
-    relocateNoSym(loc + offset, R_PPC64_TPREL16_LO, val);
+    const uintptr_t locAsInt = reinterpret_cast<uintptr_t>(loc);
+    if (locAsInt % 4 == 0) {
+      uint32_t primaryOp = getPrimaryOpCode(read32(loc));
+      if (primaryOp != 31)
+        error("unrecognized instruction for IE to LE R_PPC64_TLS");
+      uint32_t secondaryOp = (read32(loc) & 0x000007FE) >> 1; // bits 21-30
+      uint32_t dFormOp = getPPCDFormOp(secondaryOp);
+      if (dFormOp == 0)
+        error("unrecognized instruction for IE to LE R_PPC64_TLS");
+      write32(loc, ((dFormOp << 26) | (read32(loc) & 0x03FFFFFF)));
+      relocateNoSym(loc + offset, R_PPC64_TPREL16_LO, val);
+    } else if (locAsInt % 4 == 1) {
+      // If the offset is not 4 byte aligned then we have a PCRel type reloc.
+      // This version of the relocation is offset by one byte from the
+      // instruction it references.
+      uint32_t tlsInstr = read32(loc - 1);
+      uint32_t primaryOp = getPrimaryOpCode(tlsInstr);
+      if (primaryOp != 31)
+        errorOrWarn("unrecognized instruction for IE to LE R_PPC64_TLS");
+      uint32_t secondaryOp = (tlsInstr & 0x000007FE) >> 1; // bits 21-30
+      // The add is a special case and should be turned into a nop. The paddi
+      // that comes before it will already have computed the address of the
+      // symbol.
+      if (secondaryOp == 266) {
+        write32(loc - 1, NOP);
+      } else {
+        uint32_t dFormOp = getPPCDFormOp(secondaryOp);
+        if (dFormOp == 0)
+          errorOrWarn("unrecognized instruction for IE to LE R_PPC64_TLS");
+        write32(loc - 1, ((dFormOp << 26) | (tlsInstr & 0x03FF0000)));
+      }
+    } else {
+      errorOrWarn("R_PPC64_TLS must be either 4 byte aligned or one byte "
+                  "offset from 4 byte aligned");
+    }
     break;
   }
   default:
@@ -889,6 +922,7 @@ RelExpr PPC64::getRelExpr(RelType type, const Symbol &s,
   case R_PPC64_TOC16_LO:
     return R_GOTREL;
   case R_PPC64_GOT_PCREL34:
+  case R_PPC64_GOT_TPREL_PCREL34:
   case R_PPC64_PCREL_OPT:
     return R_GOT_PC;
   case R_PPC64_TOC16_HA:
@@ -1237,6 +1271,7 @@ void PPC64::relocate(uint8_t *loc, const Relocation &rel, uint64_t val) const {
     break;
   }
   case R_PPC64_GOT_PCREL34:
+  case R_PPC64_GOT_TPREL_PCREL34:
   case R_PPC64_TPREL34: {
     const uint64_t si0Mask = 0x00000003ffff0000;
     const uint64_t si1Mask = 0x000000000000ffff;
diff --git a/lld/test/ELF/ppc64-tls-pcrel-ie.s b/lld/test/ELF/ppc64-tls-pcrel-ie.s
new file mode 100644
index 0000000..93a286a
--- /dev/null
+++ b/lld/test/ELF/ppc64-tls-pcrel-ie.s
@@ -0,0 +1,126 @@
+# REQUIRES: ppc
+
+# RUN: split-file %s %t
+
+# RUN: llvm-mc -filetype=obj -triple=powerpc64le %t/asm -o %t.o
+# RUN: llvm-mc -filetype=obj -triple=powerpc64le %t/defs -o %t-defs.o
+# RUN: ld.lld --shared %t-defs.o --soname=t-defs -o %t-defs.so
+# RUN: ld.lld -T %t/lds %t.o %t-defs.so -o %t-ie
+# RUN: ld.lld -T %t/lds %t.o %t-defs.o -o %t-le
+
+# RUN: llvm-readelf -r %t-ie | FileCheck %s --check-prefix=IE-RELOC
+# RUN: llvm-readelf -s %t-ie | FileCheck %s --check-prefix=IE-SYM
+# RUN: llvm-readelf -x .got %t-ie | FileCheck %s --check-prefix=IE-GOT
+# RUN: llvm-objdump -d --no-show-raw-insn --mcpu=pwr10 %t-ie | FileCheck %s --check-prefix=IE
+
+# RUN: llvm-readelf -r %t-le | FileCheck %s --check-prefix=LE-RELOC
+# RUN: llvm-readelf -s %t-le | FileCheck %s --check-prefix=LE-SYM
+# RUN: llvm-readelf -x .got %t-le 2>&1 | FileCheck %s --check-prefix=LE-GOT
+# RUN: llvm-objdump -d --no-show-raw-insn --mcpu=pwr10 %t-le | FileCheck %s --check-prefix=LE
+
+## This test checks the Initial Exec PC Relative TLS implementation.
+## The IE version checks that the relocations are generated correctly.
+## The LE version checks that the Initial Exec to Local Exec relaxation is
+## done correctly.
+
+#--- lds
+SECTIONS {
+  .text_addr 0x1001000 : { *(.text_addr) }
+  .text_val 0x1002000 : { *(.text_val) }
+  .text_twoval 0x1003000 : { *(.text_twoval) }
+  .text_incrval 0x1004000 : { *(.text_incrval) }
+}
+
+#--- defs
+.section .tbss,"awT",@nobits
+.globl	x
+x:
+	.long	0
+.globl	y
+y:
+	.long	0
+
+#--- asm
+# IE-RELOC: Relocation section '.rela.dyn' at offset 0x10090 contains 2 entries:
+# IE-RELOC: 00000000010040d8  0000000100000049 R_PPC64_TPREL64        0000000000000000 x + 0
+# IE-RELOC: 00000000010040e0  0000000200000049 R_PPC64_TPREL64        0000000000000000 y + 0
+
+# IE-SYM:   Symbol table '.dynsym' contains 3 entries:
+# IE-SYM:   1: 0000000000000000     0 TLS     GLOBAL DEFAULT   UND x
+# IE-SYM:   2: 0000000000000000     0 TLS     GLOBAL DEFAULT   UND y
+
+# IE-GOT:      Hex dump of section '.got':
+# IE-GOT-NEXT: 0x010040d8 d8c00001 00000000 00000000 00000000
+
+# LE-RELOC: There are no relocations in this file.
+
+# LE-SYM: Symbol table '.symtab' contains 7 entries:
+# LE-SYM: 5: 0000000000000000     0 TLS     GLOBAL DEFAULT     6 x
+# LE-SYM: 6: 0000000000000004     0 TLS     GLOBAL DEFAULT     6 y
+
+# LE-GOT: could not find section '.got'
+
+# IE-LABEL: <IEAddr>:
+# IE-NEXT:    pld 3, 12504(0), 1
+# IE-NEXT:    add 3, 3, 13
+# IE-NEXT:    blr
+# LE-LABEL: <IEAddr>:
+# LE-NEXT:    paddi 3, 13, -28672, 0
+# LE-NEXT:    nop
+# LE-NEXT:    blr
+.section .text_addr, "ax", %progbits
+IEAddr:
+	pld 3, x@got@tprel@pcrel(0), 1
+	add 3, 3, x@tls@pcrel
+	blr
+
+# IE-LABEL: <IEVal>:
+# IE-NEXT:    pld 3, 8408(0), 1
+# IE-NEXT:    lwzx 3, 3, 13
+# IE-NEXT:    blr
+# LE-LABEL: <IEVal>:
+# LE-NEXT:    paddi 3, 13, -28672, 0
+# LE-NEXT:    lwz 3, 0(3)
+# LE-NEXT:    blr
+.section .text_val, "ax", %progbits
+IEVal:
+	pld 3, x@got@tprel@pcrel(0), 1
+	lwzx 3, 3, x@tls@pcrel
+	blr
+
+# IE-LABEL: <IETwoVal>:
+# IE-NEXT:    pld 3, 4312(0), 1
+# IE-NEXT:    pld 4, 4312(0), 1
+# IE-NEXT:    lwzx 3, 3, 13
+# IE-NEXT:    lwzx 4, 4, 13
+# IE-NEXT:    blr
+# LE-LABEL: <IETwoVal>:
+# LE-NEXT:    paddi 3, 13, -28672, 0
+# LE-NEXT:    paddi 4, 13, -28668, 0
+# LE-NEXT:    lwz 3, 0(3)
+# LE-NEXT:    lwz 4, 0(4)
+# LE-NEXT:    blr
+.section .text_twoval, "ax", %progbits
+IETwoVal:
+	pld 3, x@got@tprel@pcrel(0), 1
+	pld 4, y@got@tprel@pcrel(0), 1
+	lwzx 3, 3, x@tls@pcrel
+	lwzx 4, 4, y@tls@pcrel
+	blr
+
+# IE-LABEL: <IEIncrementVal>:
+# IE-NEXT:    pld 4, 224(0), 1
+# IE-NEXT:    lwzx 3, 4, 13
+# IE-NEXT:    stwx 3, 4, 13
+# IE-NEXT:    blr
+# LE-LABEL: <IEIncrementVal>:
+# LE-NEXT:    paddi 4, 13, -28668, 0
+# LE-NEXT:    lwz 3, 0(4)
+# LE-NEXT:    stw 3, 0(4)
+# LE-NEXT:    blr
+.section .text_incrval, "ax", %progbits
+IEIncrementVal:
+	pld 4, y@got@tprel@pcrel(0), 1
+	lwzx 3, 4, y@tls@pcrel
+	stwx 3, 4, y@tls@pcrel
+	blr