bpf: Pull out a macro for interpreting atomic ALU operations

Since the atomic operations that are added in subsequent commits are
all isomorphic with BPF_ADD, pull out a macro to avoid the
interpreter becoming dominated by lines of atomic-related code.

Note that this sacrificies interpreter performance (combining
STX_ATOMIC_W and STX_ATOMIC_DW into single switch case means that we
need an extra conditional branch to differentiate them) in favour of
compact and (relatively!) simple C code.
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/20210114181751.768687-9-jackmanb@google.com

kernel/bpf/core.c

@@ -1618,55 +1618,53 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 	LDX_PROBE(DW, 8)
 #undef LDX_PROBE
 
-	STX_ATOMIC_W:
-		switch (IMM) {
-		case BPF_ADD:
-			/* 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;
-		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);
+#define ATOMIC_ALU_OP(BOP, KOP)						\
+		case BOP:						\
+			if (BPF_SIZE(insn->code) == BPF_W)		\
+				atomic_##KOP((u32) SRC, (atomic_t *)(unsigned long) \
+					     (DST + insn->off));	\
+			else						\
+				atomic64_##KOP((u64) SRC, (atomic64_t *)(unsigned long) \
+					       (DST + insn->off));	\
+			break;						\
+		case BOP | BPF_FETCH:					\
+			if (BPF_SIZE(insn->code) == BPF_W)		\
+				SRC = (u32) atomic_fetch_##KOP(		\
+					(u32) SRC,			\
+					(atomic_t *)(unsigned long) (DST + insn->off)); \
+			else						\
+				SRC = (u64) atomic64_fetch_##KOP(	\
+					(u64) SRC,			\
+					(atomic64_t *)(unsigned long) (DST + insn->off)); \
 			break;
-		default:
-			goto default_label;
-		}
-		CONT;
 
 	STX_ATOMIC_DW:
+	STX_ATOMIC_W:
 		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;
+		ATOMIC_ALU_OP(BPF_ADD, add)
+#undef ATOMIC_ALU_OP
+
 		case BPF_XCHG:
-			SRC = (u64) atomic64_xchg(
-				(atomic64_t *)(unsigned long) (DST + insn->off),
-				(u64) SRC);
+			if (BPF_SIZE(insn->code) == BPF_W)
+				SRC = (u32) atomic_xchg(
+					(atomic_t *)(unsigned long) (DST + insn->off),
+					(u32) SRC);
+			else
+				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);
+			if (BPF_SIZE(insn->code) == BPF_W)
+				BPF_R0 = (u32) atomic_cmpxchg(
+					(atomic_t *)(unsigned long) (DST + insn->off),
+					(u32) BPF_R0, (u32) SRC);
+			else
+				BPF_R0 = (u64) atomic64_cmpxchg(
+					(atomic64_t *)(unsigned long) (DST + insn->off),
+					(u64) BPF_R0, (u64) SRC);
 			break;
+
 		default:
 			goto default_label;
 		}