bpf: Add BPF_FETCH field / create atomic_fetch_add instruction

The BPF_FETCH field can be set in bpf_insn.imm, for BPF_ATOMIC
instructions, in order to have the previous value of the
atomically-modified memory location loaded into the src register
after an atomic op is carried out.

Suggested-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Brendan Jackman <jackmanb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210114181751.768687-7-jackmanb@google.com

3 files changed, 44 insertions, 9 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 4836ebf459cf..28d6000463e4 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1624,16 +1624,29 @@ out:
 			/* lock xadd *(u32 *)(dst_reg + off16) += src_reg */
 			atomic_add((u32) SRC, (atomic_t *)(unsigned long)
 				   (DST + insn->off));
+			break;
+		case BPF_ADD | BPF_FETCH:
+			SRC = (u32) atomic_fetch_add(
+				(u32) SRC,
+				(atomic_t *)(unsigned long) (DST + insn->off));
+			break;
 		default:
 			goto default_label;
 		}
 		CONT;
+
 	STX_ATOMIC_DW:
 		switch (IMM) {
 		case BPF_ADD:
 			/* lock xadd *(u64 *)(dst_reg + off16) += src_reg */
 			atomic64_add((u64) SRC, (atomic64_t *)(unsigned long)
 				     (DST + insn->off));
+			break;
+		case BPF_ADD | BPF_FETCH:
+			SRC = (u64) atomic64_fetch_add(
+				(u64) SRC,
+				(atomic64_t *)(unsigned long) (DST + insn->off));
+			break;
 		default:
 			goto default_label;
 		}
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index 37c8d6e9b4cc..d2e20f6d0516 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -160,6 +160,13 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
 				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_ADD | BPF_FETCH)) {
+			verbose(cbs->private_data, "(%02x) r%d = atomic%s_fetch_add((%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 d8a85f4e5b95..6aa1fc919761 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3608,7 +3608,11 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 {
 	int err;
 
-	if (insn->imm != BPF_ADD) {
+	switch (insn->imm) {
+	case BPF_ADD:
+	case BPF_ADD | BPF_FETCH:
+		break;
+	default:
 		verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", insn->imm);
 		return -EINVAL;
 	}
@@ -3650,8 +3654,20 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 		return err;
 
 	/* check whether we can write into the same memory */
-	return check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
-				BPF_SIZE(insn->code), BPF_WRITE, -1, true);
+	err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
+			       BPF_SIZE(insn->code), BPF_WRITE, -1, true);
+	if (err)
+		return err;
+
+	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 (err)
+		return err;
+
+	return 0;
 }
 
 static int __check_stack_boundary(struct bpf_verifier_env *env, u32 regno,
@@ -9528,12 +9544,6 @@ static int do_check(struct bpf_verifier_env *env)
 		} else if (class == BPF_STX) {
 			enum bpf_reg_type *prev_dst_type, dst_reg_type;
 
-			if (((BPF_MODE(insn->code) != BPF_MEM &&
-			      BPF_MODE(insn->code) != BPF_ATOMIC) || insn->imm != 0)) {
-				verbose(env, "BPF_STX uses reserved fields\n");
-				return -EINVAL;
-			}
-
 			if (BPF_MODE(insn->code) == BPF_ATOMIC) {
 				err = check_atomic(env, env->insn_idx, insn);
 				if (err)
@@ -9542,6 +9552,11 @@ static int do_check(struct bpf_verifier_env *env)
 				continue;
 			}
 
+			if (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0) {
+				verbose(env, "BPF_STX uses reserved fields\n");
+				return -EINVAL;
+			}
+
 			/* check src1 operand */
 			err = check_reg_arg(env, insn->src_reg, SRC_OP);
 			if (err)