From 5ffa25502b5ab3d639829a2d1e316cff7f59a41e Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Thu, 14 Jan 2021 18:17:47 +0000 Subject: bpf: Add instructions for atomic_[cmp]xchg This adds two atomic opcodes, both of which include the BPF_FETCH flag. XCHG without the BPF_FETCH flag would naturally encode atomic_set. This is not supported because it would be of limited value to userspace (it doesn't imply any barriers). CMPXCHG without BPF_FETCH woulud be an atomic compare-and-write. We don't have such an operation in the kernel so it isn't provided to BPF either. There are two significant design decisions made for the CMPXCHG instruction: - To solve the issue that this operation fundamentally has 3 operands, but we only have two register fields. Therefore the operand we compare against (the kernel's API calls it 'old') is hard-coded to be R0. x86 has similar design (and A64 doesn't have this problem). A potential alternative might be to encode the other operand's register number in the immediate field. - The kernel's atomic_cmpxchg returns the old value, while the C11 userspace APIs return a boolean indicating the comparison result. Which should BPF do? A64 returns the old value. x86 returns the old value in the hard-coded register (and also sets a flag). That means return-old-value is easier to JIT, so that's what we use. Signed-off-by: Brendan Jackman Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210114181751.768687-8-jackmanb@google.com --- tools/include/linux/filter.h | 2 ++ tools/include/uapi/linux/bpf.h | 4 +++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h index 7211ce9fba53..d75998b0d5ac 100644 --- a/tools/include/linux/filter.h +++ b/tools/include/linux/filter.h @@ -174,6 +174,8 @@ * * BPF_ADD *(uint *) (dst_reg + off16) += src_reg * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); + * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) + * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) */ #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index ea262b009049..c001766adcbc 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -45,7 +45,9 @@ #define BPF_EXIT 0x90 /* function return */ /* atomic op type fields (stored in immediate) */ -#define BPF_FETCH 0x01 /* fetch previous value into src reg */ +#define BPF_FETCH 0x01 /* not an opcode on its own, used to build others */ +#define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ +#define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ /* Register numbers */ enum { -- cgit v1.2.3