AMDHSA: Code object v3 updates

  - Copy kernel symbol attributes into kernel descriptor attributes
  - Make sure kernel symbol's visibility is not "higher" than protected

Differential Revision: https://reviews.llvm.org/D59057

llvm-svn: 355630

diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
index 5499fa9..c1c00f4 100644 (file)
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
@@ -554,16 +554,25 @@ void AMDGPUTargetELFStreamer::EmitAmdhsaKernelDescriptor(
   auto &Streamer = getStreamer();
   auto &Context = Streamer.getContext();
 
+  MCSymbolELF *KernelCodeSymbol = cast<MCSymbolELF>(
+      Context.getOrCreateSymbol(Twine(KernelName)));
   MCSymbolELF *KernelDescriptorSymbol = cast<MCSymbolELF>(
       Context.getOrCreateSymbol(Twine(KernelName) + Twine(".kd")));
-  KernelDescriptorSymbol->setBinding(ELF::STB_GLOBAL);
+
+  // Copy kernel descriptor symbol's binding, other and visibility from the
+  // kernel code symbol.
+  KernelDescriptorSymbol->setBinding(KernelCodeSymbol->getBinding());
+  KernelDescriptorSymbol->setOther(KernelCodeSymbol->getOther());
+  KernelDescriptorSymbol->setVisibility(KernelCodeSymbol->getVisibility());
+  // Kernel descriptor symbol's type and size are fixed.
   KernelDescriptorSymbol->setType(ELF::STT_OBJECT);
   KernelDescriptorSymbol->setSize(
       MCConstantExpr::create(sizeof(KernelDescriptor), Context));
 
-  MCSymbolELF *KernelCodeSymbol = cast<MCSymbolELF>(
-      Context.getOrCreateSymbol(Twine(KernelName)));
-  KernelCodeSymbol->setBinding(ELF::STB_LOCAL);
+  // The visibility of the kernel code symbol must be protected or less to allow
+  // static relocations from the kernel descriptor to be used.
+  if (KernelCodeSymbol->getVisibility() == ELF::STV_DEFAULT)
+    KernelCodeSymbol->setVisibility(ELF::STV_PROTECTED);
 
   Streamer.EmitLabel(KernelDescriptorSymbol);
   Streamer.EmitBytes(StringRef(

diff --git a/llvm/test/CodeGen/AMDGPU/code-object-v3.ll b/llvm/test/CodeGen/AMDGPU/code-object-v3.ll
index d843255..32898fd 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/code-object-v3.ll
+++ b/llvm/test/CodeGen/AMDGPU/code-object-v3.ll
@@ -50,14 +50,14 @@
 ; OSABI-AMDHSA-ELF: .rodata PROGBITS {{[0-9]+}} {{[0-9]+}} {{[0-9a-f]+}} {{[0-9]+}}  A {{[0-9]+}} {{[0-9]+}} 64
 
 ; OSABI-AMDHSA-ELF: Relocation section '.rela.rodata' at offset
-; OSABI-AMDHSA-ELF: 0000000000000010 0000000300000005 R_AMDGPU_REL64 0000000000000000 .text + 10
-; OSABI-AMDHSA-ELF: 0000000000000050 0000000300000005 R_AMDGPU_REL64 0000000000000000 .text + 110
+; OSABI-AMDHSA-ELF: 0000000000000010 0000000100000005 R_AMDGPU_REL64 0000000000000000 fadd + 10
+; OSABI-AMDHSA-ELF: 0000000000000050 0000000300000005 R_AMDGPU_REL64 0000000000000100 fsub + 10
 
 ; OSABI-AMDHSA-ELF: Symbol table '.symtab' contains {{[0-9]+}} entries
-; OSABI-AMDHSA-ELF: {{[0-9]+}}: 0000000000000000 {{[0-9]+}} FUNC   LOCAL  DEFAULT {{[0-9]+}} fadd
-; OSABI-AMDHSA-ELF: {{[0-9]+}}: 0000000000000100 {{[0-9]+}} FUNC   LOCAL  DEFAULT {{[0-9]+}} fsub
-; OSABI-AMDHSA-ELF: {{[0-9]+}}: 0000000000000000 64         OBJECT GLOBAL DEFAULT {{[0-9]+}} fadd.kd
-; OSABI-AMDHSA-ELF: {{[0-9]+}}: 0000000000000040 64         OBJECT GLOBAL DEFAULT {{[0-9]+}} fsub.kd
+; OSABI-AMDHSA-ELF: {{[0-9]+}}: 0000000000000000 {{[0-9]+}} FUNC   GLOBAL PROTECTED {{[0-9]+}} fadd
+; OSABI-AMDHSA-ELF: {{[0-9]+}}: 0000000000000000 64         OBJECT GLOBAL DEFAULT   {{[0-9]+}} fadd.kd
+; OSABI-AMDHSA-ELF: {{[0-9]+}}: 0000000000000100 {{[0-9]+}} FUNC   GLOBAL PROTECTED {{[0-9]+}} fsub
+; OSABI-AMDHSA-ELF: {{[0-9]+}}: 0000000000000040 64         OBJECT GLOBAL DEFAULT   {{[0-9]+}} fsub.kd
 
 ; OSABI-AMDHSA-ELF: Displaying notes found at file offset
 ; OSABI-AMDHSA-ELF: AMDGPU 0x{{[0-9a-f]+}} NT_AMDGPU_METADATA (AMDGPU Metadata)

diff --git a/llvm/test/MC/AMDGPU/hsa-v3.s b/llvm/test/MC/AMDGPU/hsa-v3.s
index 515da88..36c504d 100644 (file)
--- a/llvm/test/MC/AMDGPU/hsa-v3.s
+++ b/llvm/test/MC/AMDGPU/hsa-v3.s
@@ -16,12 +16,12 @@
 // READOBJ: 0000000000000090 {{[0-9a-f]+}}00000005 R_AMDGPU_REL64 0000000000000000 .text + 210
 
 // READOBJ: Symbol table '.symtab' contains {{[0-9]+}} entries:
-// READOBJ: {{[0-9]+}}: 0000000000000100  0 FUNC    LOCAL  DEFAULT 2 complete
-// READOBJ: {{[0-9]+}}: 0000000000000000  0 FUNC    LOCAL  DEFAULT 2 minimal
-// READOBJ: {{[0-9]+}}: 0000000000000200  0 FUNC    LOCAL  DEFAULT 2 special_sgpr
-// READOBJ: {{[0-9]+}}: 0000000000000040 64 OBJECT  GLOBAL DEFAULT 3 complete.kd
-// READOBJ: {{[0-9]+}}: 0000000000000000 64 OBJECT  GLOBAL DEFAULT 3 minimal.kd
-// READOBJ: {{[0-9]+}}: 0000000000000080 64 OBJECT  GLOBAL DEFAULT 3 special_sgpr.kd
+// READOBJ: {{[0-9]+}}: 0000000000000100  0 FUNC    LOCAL  PROTECTED 2 complete
+// READOBJ: {{[0-9]+}}: 0000000000000040 64 OBJECT  LOCAL  DEFAULT   3 complete.kd
+// READOBJ: {{[0-9]+}}: 0000000000000000  0 FUNC    LOCAL  PROTECTED 2 minimal
+// READOBJ: {{[0-9]+}}: 0000000000000000 64 OBJECT  LOCAL  DEFAULT   3 minimal.kd
+// READOBJ: {{[0-9]+}}: 0000000000000200  0 FUNC    LOCAL  PROTECTED 2 special_sgpr
+// READOBJ: {{[0-9]+}}: 0000000000000080 64 OBJECT  LOCAL  DEFAULT   3 special_sgpr.kd
 
 // OBJDUMP: Contents of section .rodata
 // Note, relocation for KERNEL_CODE_ENTRY_BYTE_OFFSET is not resolved here.