diff options
| author | Andrii Nakryiko <andrii@kernel.org> | 2024-04-03 20:47:26 -0700 |
|---|---|---|
| committer | Alexei Starovoitov <ast@kernel.org> | 2024-04-03 21:36:35 -0700 |
| commit | 1e9e0b85255e6eca6036b59d8a5fbca6501905ac (patch) | |
| tree | 0b90da08e9a36a61517c7e31b761e140234e82b7 /arch/x86/net | |
| parent | 519e1de94b719f741e0de42b085b9a4551c5b15c (diff) | |
bpf: handle CONFIG_SMP=n configuration in x86 BPF JIT
On non-SMP systems, there is no "per-CPU" data, it's just global data.
So in such case just don't do this_cpu_off-based per-CPU address adjustment.
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202404040951.d4CUx5S6-lkp@intel.com/
Fixes: 7bdbf7446305 ("bpf: add special internal-only MOV instruction to resolve per-CPU addrs")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240404034726.2766740-1-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'arch/x86/net')
| -rw-r--r-- | arch/x86/net/bpf_jit_comp.c | 7 |
1 files changed, 3 insertions, 4 deletions
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index af89dd117dce..964e8154da66 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1383,15 +1383,14 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image EMIT3(0x0F, 0x44, add_2reg(0xC0, AUX_REG, dst_reg)); break; } else if (insn_is_mov_percpu_addr(insn)) { - u32 off = (u32)(unsigned long)&this_cpu_off; - /* mov <dst>, <src> (if necessary) */ EMIT_mov(dst_reg, src_reg); - +#ifdef CONFIG_SMP /* add <dst>, gs:[<off>] */ EMIT2(0x65, add_1mod(0x48, dst_reg)); EMIT3(0x03, add_1reg(0x04, dst_reg), 0x25); - EMIT(off, 4); + EMIT((u32)(unsigned long)&this_cpu_off, 4); +#endif break; } fallthrough; |