[all-commits] [llvm/llvm-project] 2aacb5: BPF address space insn (#84410)

[4ast via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 2aacb56e8361213c1bd69c2ceafdea3aa0ca9125
      https://github.com/llvm/llvm-project/commit/2aacb56e8361213c1bd69c2ceafdea3aa0ca9125
  Author: 4ast <alexei.starovoitov at gmail.com>
  Date:   2024-03-13 (Wed, 13 Mar 2024)

  Changed paths:
    M clang/lib/Basic/Targets/BPF.cpp
    M clang/test/Preprocessor/bpf-predefined-macros.c
    M llvm/lib/Target/BPF/AsmParser/BPFAsmParser.cpp
    M llvm/lib/Target/BPF/BPF.h
    A llvm/lib/Target/BPF/BPFASpaceCastSimplifyPass.cpp
    M llvm/lib/Target/BPF/BPFCheckAndAdjustIR.cpp
    M llvm/lib/Target/BPF/BPFInstrInfo.td
    M llvm/lib/Target/BPF/BPFTargetMachine.cpp
    M llvm/lib/Target/BPF/CMakeLists.txt
    A llvm/test/CodeGen/BPF/addr-space-auto-casts.ll
    A llvm/test/CodeGen/BPF/addr-space-cast.ll
    A llvm/test/CodeGen/BPF/addr-space-gep-chain.ll
    A llvm/test/CodeGen/BPF/addr-space-globals.ll
    A llvm/test/CodeGen/BPF/addr-space-globals2.ll
    A llvm/test/CodeGen/BPF/addr-space-phi.ll
    A llvm/test/CodeGen/BPF/addr-space-simplify-1.ll
    A llvm/test/CodeGen/BPF/addr-space-simplify-2.ll
    A llvm/test/CodeGen/BPF/addr-space-simplify-3.ll
    A llvm/test/CodeGen/BPF/addr-space-simplify-4.ll
    A llvm/test/CodeGen/BPF/addr-space-simplify-5.ll
    M llvm/test/CodeGen/BPF/assembler-disassembler.s

  Log Message:
  -----------
  BPF address space insn (#84410)

This commit aims to support BPF arena kernel side
[feature](https://lore.kernel.org/bpf/20240209040608.98927-1-alexei.starovoitov@gmail.com/):
- arena is a memory region accessible from both BPF program and
userspace;
- base pointers for this memory region differ between kernel and user
spaces;
- `dst_reg = addr_space_cast(src_reg, dst_addr_space, src_addr_space)`
translates src_reg, a pointer in src_addr_space to dst_reg, equivalent
pointer in dst_addr_space, {src,dst}_addr_space are immediate constants;
- number 0 is assigned to kernel address space;
- number 1 is assigned to user address space.

On the LLVM side, the goal is to make load and store operations on arena
pointers "transparent" for BPF programs:
- assume that pointers with non-zero address space are pointers to
  arena memory;
- assume that arena is identified by address space number;
- assume that address space zero corresponds to kernel address space;
- assume that every BPF-side load or store from arena is done via
pointer in user address space, thus convert base pointers using
`addr_space_cast(src_reg, 0, 1)`;

Only load, store, cmpxchg and atomicrmw IR instructions are handled by
this transformation.

For example, the following C code:

```c
   #define __as __attribute__((address_space(1)))
   void copy(int __as *from, int __as *to) { *to = *from; }
```

Compiled to the following IR:

```llvm
    define void @copy(ptr addrspace(1) %from, ptr addrspace(1) %to) {
    entry:
      %0 = load i32, ptr addrspace(1) %from, align 4
      store i32 %0, ptr addrspace(1) %to, align 4
      ret void
    }
```

Is transformed to:

```llvm
    %to2 = addrspacecast ptr addrspace(1) %to to ptr     ;; !
    %from1 = addrspacecast ptr addrspace(1) %from to ptr ;; !
    %0 = load i32, ptr %from1, align 4, !tbaa !3
    store i32 %0, ptr %to2, align 4, !tbaa !3
    ret void
```

And compiled as:

```asm
    r2 = addr_space_cast(r2, 0, 1)
    r1 = addr_space_cast(r1, 0, 1)
    r1 = *(u32 *)(r1 + 0)
    *(u32 *)(r2 + 0) = r1
    exit
```

Co-authored-by: Eduard Zingerman <eddyz87 at gmail.com>



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications