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
/* 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;
*
* 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) \
#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 {
(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;
}
(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;
}
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);
}
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);
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;
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;
*
* 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) \
#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 {
OSDN Git Service
