From: Brendan Jackman jackmanb@google.com
mainline inclusion from mainline-5.12-rc1 commit 5ffa25502b5ab3d639829a2d1e316cff7f59a41e category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I5EUVD CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
-------------------------------------------------
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 jackmanb@google.com Signed-off-by: Alexei Starovoitov ast@kernel.org Acked-by: Yonghong Song yhs@fb.com Link: https://lore.kernel.org/bpf/20210114181751.768687-8-jackmanb@google.com (cherry picked from commit 5ffa25502b5ab3d639829a2d1e316cff7f59a41e) Signed-off-by: Wang Yufen wangyufen@huawei.com --- arch/x86/net/bpf_jit_comp.c | 8 ++++++++ include/linux/filter.h | 2 ++ include/uapi/linux/bpf.h | 4 +++- kernel/bpf/core.c | 20 ++++++++++++++++++++ kernel/bpf/disasm.c | 15 +++++++++++++++ kernel/bpf/verifier.c | 19 +++++++++++++++++-- tools/include/linux/filter.h | 2 ++ tools/include/uapi/linux/bpf.h | 4 +++- 8 files changed, 70 insertions(+), 4 deletions(-)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index d79585615580..5b9a7db44229 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -818,6 +818,14 @@ static int emit_atomic(u8 **pprog, u8 atomic_op, /* src_reg = atomic_fetch_add(dst_reg + off, src_reg); */ EMIT2(0x0F, 0xC1); break; + case BPF_XCHG: + /* src_reg = atomic_xchg(dst_reg + off, src_reg); */ + EMIT1(0x87); + break; + case BPF_CMPXCHG: + /* r0 = atomic_cmpxchg(dst_reg + off, r0, src_reg); */ + EMIT2(0x0F, 0xB1); + break; default: pr_err("bpf_jit: unknown atomic opcode %02x\n", atomic_op); return -EFAULT; diff --git a/include/linux/filter.h b/include/linux/filter.h index 9d4563850f54..0e2f7eaf1854 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -270,6 +270,8 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) * * 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/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index cccb6d6d5712..b1e94b261479 100644 --- a/include/uapi/linux/bpf.h +++ b/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 { diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index db328aa9908e..74abac5bcc3d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1682,6 +1682,16 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) (u32) SRC, (atomic_t *)(unsigned long) (DST + insn->off)); break; + case BPF_XCHG: + SRC = (u32) atomic_xchg( + (atomic_t *)(unsigned long) (DST + insn->off), + (u32) SRC); + break; + case BPF_CMPXCHG: + BPF_R0 = (u32) atomic_cmpxchg( + (atomic_t *)(unsigned long) (DST + insn->off), + (u32) BPF_R0, (u32) SRC); + break; default: goto default_label; } @@ -1699,6 +1709,16 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) (u64) SRC, (atomic64_t *)(unsigned long) (DST + insn->off)); break; + case BPF_XCHG: + SRC = (u64) atomic64_xchg( + (atomic64_t *)(unsigned long) (DST + insn->off), + (u64) SRC); + break; + case BPF_CMPXCHG: + BPF_R0 = (u64) atomic64_cmpxchg( + (atomic64_t *)(unsigned long) (DST + insn->off), + (u64) BPF_R0, (u64) SRC); + break; default: goto default_label; } diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index 0f64a9cf20b5..42635b7bfeef 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -167,6 +167,21 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, BPF_SIZE(insn->code) == BPF_DW ? "64" : "", bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); + } else if (BPF_MODE(insn->code) == BPF_ATOMIC && + insn->imm == BPF_CMPXCHG) { + verbose(cbs->private_data, "(%02x) r0 = atomic%s_cmpxchg((%s *)(r%d %+d), r0, r%d)\n", + insn->code, + BPF_SIZE(insn->code) == BPF_DW ? "64" : "", + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, insn->off, + insn->src_reg); + } else if (BPF_MODE(insn->code) == BPF_ATOMIC && + insn->imm == BPF_XCHG) { + verbose(cbs->private_data, "(%02x) r%d = atomic%s_xchg((%s *)(r%d %+d), r%d)\n", + insn->code, insn->src_reg, + BPF_SIZE(insn->code) == BPF_DW ? "64" : "", + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, insn->off, insn->src_reg); } else { verbose(cbs->private_data, "BUG_%02x\n", insn->code); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 080f8e20dea0..ec1c80e4e703 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3963,11 +3963,14 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn) { + int load_reg; int err;
switch (insn->imm) { case BPF_ADD: case BPF_ADD | BPF_FETCH: + case BPF_XCHG: + case BPF_CMPXCHG: break; default: verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", insn->imm); @@ -3989,6 +3992,13 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i if (err) return err;
+ if (insn->imm == BPF_CMPXCHG) { + /* Check comparison of R0 with memory location */ + err = check_reg_arg(env, BPF_REG_0, SRC_OP); + if (err) + return err; + } + if (is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d leaks addr into mem\n", insn->src_reg); return -EACCES; @@ -4019,8 +4029,13 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i if (!(insn->imm & BPF_FETCH)) return 0;
- /* check and record load of old value into src reg */ - err = check_reg_arg(env, insn->src_reg, DST_OP); + if (insn->imm == BPF_CMPXCHG) + load_reg = BPF_REG_0; + else + load_reg = insn->src_reg; + + /* check and record load of old value */ + err = check_reg_arg(env, load_reg, DST_OP); if (err) return err;
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 bd99439b4375..f478890e0e16 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 {