[BPF] Make llvm-objdump disasm default cpu v4 (#102166)

Currently, with the following example,
  $ cat t.c
  void foo(int a, _Atomic int *b)
  {
   *b &= a;
  }
  $ clang --target=bpf -O2 -c -mcpu=v3 t.c
  $ llvm-objdump -d t.o
  t.o:    file format elf64-bpf

  Disassembly of section .text:

  0000000000000000 <foo>:
       0:       c3 12 00 00 51 00 00 00 <unknown>
       1:       95 00 00 00 00 00 00 00 exit

Basically, the default cpu for llvm-objdump is v1 and it won't be able
to decode insn properly.

If we add --mcpu=v3 to llvm-objdump command line, we will have
  $ llvm-objdump -d --mcpu=v3 t.o

  t.o:    file format elf64-bpf

  Disassembly of section .text:

  0000000000000000 <foo>:
0: c3 12 00 00 51 00 00 00 w1 = atomic_fetch_and((u32 *)(r2 + 0x0), w1)
       1:       95 00 00 00 00 00 00 00 exit

The atomic_fetch_and insn can be decoded properly. Using latest cpu
version --mcpu=v4 can also decode properly like the above --mcpu=v3.

To avoid the above '<unknown>' decoding with common 'llvm-objdump -d
t.o', this patch marked the default cpu for llvm-objdump with the
current highest cpu number v4 in ELFObjectFileBase::tryGetCPUName(). The
cpu number in ELFObjectFileBase::tryGetCPUName() will be adjusted in the
future if cpu number is increased e.g. v5 etc. Such an approach also
aligns with gcc-bpf as discussed in [1].

Six bpf unit tests are affected with this change. I changed test output
for three unit tests and added --mcpu=v1 for the other three unit tests,
to demonstrate the default (cpu v4) behavior and explicit --mcpu=v1
behavior.

[1]
https://lore.kernel.org/bpf/[email protected]/T/#m0f7e63c390bc8f5a5523e7f2f0537becd4205200

Co-authored-by: Yonghong Song <[email protected]>

Author: yonghong-song

llvm/lib/Object/ELFObjectFile.cpp

@@ -441,6 +441,8 @@ std::optional<StringRef> ELFObjectFileBase::tryGetCPUName() const {
   case ELF::EM_PPC:
   case ELF::EM_PPC64:
     return StringRef("future");
+  case ELF::EM_BPF:
+    return StringRef("v4");
   default:
     return std::nullopt;
   }

llvm/test/CodeGen/BPF/objdump_atomics.ll

@@ -2,7 +2,7 @@
 
 ; CHECK-LABEL: test_load_add_32
 ; CHECK: c3 21
-; CHECK: r2 = atomic_fetch_add((u32 *)(r1 + 0), r2)
+; CHECK: w2 = atomic_fetch_add((u32 *)(r1 + 0), w2)
 define void @test_load_add_32(ptr %p, i32 zeroext %v) {
 entry:
   atomicrmw add ptr %p, i32 %v seq_cst

llvm/test/CodeGen/BPF/objdump_cond_op.ll

@@ -1,4 +1,4 @@
-; RUN: llc -mtriple=bpfel -filetype=obj -o - %s | llvm-objdump --no-print-imm-hex -d - | FileCheck %s
+; RUN: llc -mtriple=bpfel -filetype=obj -o - %s | llvm-objdump --no-print-imm-hex --mcpu=v1 -d - | FileCheck %s
 
 ; Source Code:
 ; int gbl;

llvm/test/CodeGen/BPF/objdump_imm_hex.ll

@@ -53,8 +53,8 @@ define i32 @test(i64, i64) local_unnamed_addr #0 {
   %14 = phi i32 [ %12, %10 ], [ %7, %4 ]
   %15 = phi i32 [ 2, %10 ], [ 1, %4 ]
   store i32 %14, ptr @gbl, align 4
-; CHECK-DEC: 63 12 00 00 00 00 00 00         *(u32 *)(r2 + 0) = r1
-; CHECK-HEX: 63 12 00 00 00 00 00 00         *(u32 *)(r2 + 0x0) = r1
+; CHECK-DEC: 63 12 00 00 00 00 00 00         *(u32 *)(r2 + 0) = w1
+; CHECK-HEX: 63 12 00 00 00 00 00 00         *(u32 *)(r2 + 0x0) = w1
   br label %16
 
 ; <label>:16:                                     ; preds = %13, %8

llvm/test/CodeGen/BPF/objdump_static_var.ll

@@ -1,5 +1,5 @@
-; RUN: llc -mtriple=bpfel -filetype=obj -o - %s | llvm-objdump --no-print-imm-hex -d - | FileCheck --check-prefix=CHECK %s
-; RUN: llc -mtriple=bpfeb -filetype=obj -o - %s | llvm-objdump --no-print-imm-hex -d - | FileCheck --check-prefix=CHECK %s
+; RUN: llc -mtriple=bpfel -filetype=obj -o - %s | llvm-objdump --no-print-imm-hex --mcpu=v1 -d - | FileCheck --check-prefix=CHECK %s
+; RUN: llc -mtriple=bpfeb -filetype=obj -o - %s | llvm-objdump --no-print-imm-hex --mcpu=v1 -d - | FileCheck --check-prefix=CHECK %s
 
 ; src:
 ;   static volatile long a = 2;

llvm/test/MC/BPF/insn-unit.s

@@ -34,9 +34,9 @@
   r6 = *(u16 *)(r1 + 8)  // BPF_LDX | BPF_H
   r7 = *(u32 *)(r2 + 16) // BPF_LDX | BPF_W
   r8 = *(u64 *)(r3 - 30) // BPF_LDX | BPF_DW
-// CHECK-64: 71 05 00 00 00 00 00 00 	r5 = *(u8 *)(r0 + 0)
-// CHECK-64: 69 16 08 00 00 00 00 00 	r6 = *(u16 *)(r1 + 8)
-// CHECK-64: 61 27 10 00 00 00 00 00 	r7 = *(u32 *)(r2 + 16)
+// CHECK-64: 71 05 00 00 00 00 00 00 	w5 = *(u8 *)(r0 + 0)
+// CHECK-64: 69 16 08 00 00 00 00 00 	w6 = *(u16 *)(r1 + 8)
+// CHECK-64: 61 27 10 00 00 00 00 00 	w7 = *(u32 *)(r2 + 16)
 // CHECK-32: 71 05 00 00 00 00 00 00 	w5 = *(u8 *)(r0 + 0)
 // CHECK-32: 69 16 08 00 00 00 00 00 	w6 = *(u16 *)(r1 + 8)
 // CHECK-32: 61 27 10 00 00 00 00 00 	w7 = *(u32 *)(r2 + 16)
@@ -47,17 +47,17 @@
   *(u16 *)(r1 + 8) = r8   // BPF_STX | BPF_H
   *(u32 *)(r2 + 16) = r9  // BPF_STX | BPF_W
   *(u64 *)(r3 - 30) = r10 // BPF_STX | BPF_DW
-// CHECK-64: 73 70 00 00 00 00 00 00 	*(u8 *)(r0 + 0) = r7
-// CHECK-64: 6b 81 08 00 00 00 00 00 	*(u16 *)(r1 + 8) = r8
-// CHECK-64: 63 92 10 00 00 00 00 00 	*(u32 *)(r2 + 16) = r9
+// CHECK-64: 73 70 00 00 00 00 00 00 	*(u8 *)(r0 + 0) = w7
+// CHECK-64: 6b 81 08 00 00 00 00 00 	*(u16 *)(r1 + 8) = w8
+// CHECK-64: 63 92 10 00 00 00 00 00 	*(u32 *)(r2 + 16) = w9
 // CHECK-32: 73 70 00 00 00 00 00 00 	*(u8 *)(r0 + 0) = w7
 // CHECK-32: 6b 81 08 00 00 00 00 00 	*(u16 *)(r1 + 8) = w8
 // CHECK-32: 63 92 10 00 00 00 00 00 	*(u32 *)(r2 + 16) = w9
 // CHECK: 7b a3 e2 ff 00 00 00 00 	*(u64 *)(r3 - 30) = r10
 
   lock *(u32 *)(r2 + 16) += r9  // BPF_STX | BPF_W | BPF_XADD
   lock *(u64 *)(r3 - 30) += r10 // BPF_STX | BPF_DW | BPF_XADD
-// CHECK-64: c3 92 10 00 00 00 00 00 	lock *(u32 *)(r2 + 16) += r9
+// CHECK-64: c3 92 10 00 00 00 00 00 	lock *(u32 *)(r2 + 16) += w9
 // CHECK-32: c3 92 10 00 00 00 00 00 	lock *(u32 *)(r2 + 16) += w9
 // CHECK: db a3 e2 ff 00 00 00 00 	lock *(u64 *)(r3 - 30) += r10
 

llvm/test/MC/BPF/load-store-32.s

@@ -1,6 +1,6 @@
 # RUN: llvm-mc -triple bpfel -filetype=obj -o %t %s
 # RUN: llvm-objdump --no-print-imm-hex --mattr=+alu32 -d -r %t | FileCheck --check-prefix=CHECK-32 %s
-# RUN: llvm-objdump --no-print-imm-hex -d -r %t | FileCheck %s
+# RUN: llvm-objdump --no-print-imm-hex --mcpu=v1 -d -r %t | FileCheck %s
 
 // ======== BPF_LDX Class ========
   w5 = *(u8 *)(r0 + 0)   // BPF_LDX | BPF_B