nfp: bpf: implement jitting of JMP32

This patch implements code-gen for new JMP32 instructions on NFP.
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

drivers/net/ethernet/netronome/nfp/bpf/jit.c

@@ -1334,8 +1334,9 @@ wrp_test_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 
 	wrp_test_reg_one(nfp_prog, insn->dst_reg * 2, alu_op,
 			 insn->src_reg * 2, br_mask, insn->off);
-	wrp_test_reg_one(nfp_prog, insn->dst_reg * 2 + 1, alu_op,
-			 insn->src_reg * 2 + 1, br_mask, insn->off);
+	if (is_mbpf_jmp64(meta))
+		wrp_test_reg_one(nfp_prog, insn->dst_reg * 2 + 1, alu_op,
+				 insn->src_reg * 2 + 1, br_mask, insn->off);
 
 	return 0;
 }
@@ -1390,13 +1391,15 @@ static int cmp_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	else
 		emit_alu(nfp_prog, reg_none(), tmp_reg, alu_op, reg_a(reg));
 
-	tmp_reg = ur_load_imm_any(nfp_prog, imm >> 32, imm_b(nfp_prog));
-	if (!code->swap)
-		emit_alu(nfp_prog, reg_none(),
-			 reg_a(reg + 1), carry_op, tmp_reg);
-	else
-		emit_alu(nfp_prog, reg_none(),
-			 tmp_reg, carry_op, reg_a(reg + 1));
+	if (is_mbpf_jmp64(meta)) {
+		tmp_reg = ur_load_imm_any(nfp_prog, imm >> 32, imm_b(nfp_prog));
+		if (!code->swap)
+			emit_alu(nfp_prog, reg_none(),
+				 reg_a(reg + 1), carry_op, tmp_reg);
+		else
+			emit_alu(nfp_prog, reg_none(),
+				 tmp_reg, carry_op, reg_a(reg + 1));
+	}
 
 	emit_br(nfp_prog, code->br_mask, insn->off, 0);
 
@@ -1423,8 +1426,9 @@ static int cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	}
 
 	emit_alu(nfp_prog, reg_none(), reg_a(areg), ALU_OP_SUB, reg_b(breg));
-	emit_alu(nfp_prog, reg_none(),
-		 reg_a(areg + 1), ALU_OP_SUB_C, reg_b(breg + 1));
+	if (is_mbpf_jmp64(meta))
+		emit_alu(nfp_prog, reg_none(),
+			 reg_a(areg + 1), ALU_OP_SUB_C, reg_b(breg + 1));
 	emit_br(nfp_prog, code->br_mask, insn->off, 0);
 
 	return 0;
@@ -3048,6 +3052,19 @@ static int jeq_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return 0;
 }
 
+static int jeq32_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	swreg tmp_reg;
+
+	tmp_reg = ur_load_imm_any(nfp_prog, insn->imm, imm_b(nfp_prog));
+	emit_alu(nfp_prog, reg_none(),
+		 reg_a(insn->dst_reg * 2), ALU_OP_XOR, tmp_reg);
+	emit_br(nfp_prog, BR_BEQ, insn->off, 0);
+
+	return 0;
+}
+
 static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
@@ -3061,9 +3078,10 @@ static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	/* Upper word of the mask can only be 0 or ~0 from sign extension,
 	 * so either ignore it or OR the whole thing in.
 	 */
-	if (imm >> 32)
+	if (is_mbpf_jmp64(meta) && imm >> 32) {
 		emit_alu(nfp_prog, reg_none(),
 			 reg_a(dst_gpr + 1), ALU_OP_OR, imm_b(nfp_prog));
+	}
 	emit_br(nfp_prog, BR_BNE, insn->off, 0);
 
 	return 0;
@@ -3073,11 +3091,16 @@ static int jne_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
 	u64 imm = insn->imm; /* sign extend */
+	bool is_jmp32 = is_mbpf_jmp32(meta);
 	swreg tmp_reg;
 
 	if (!imm) {
-		emit_alu(nfp_prog, reg_none(), reg_a(insn->dst_reg * 2),
-			 ALU_OP_OR, reg_b(insn->dst_reg * 2 + 1));
+		if (is_jmp32)
+			emit_alu(nfp_prog, reg_none(), reg_none(), ALU_OP_NONE,
+				 reg_b(insn->dst_reg * 2));
+		else
+			emit_alu(nfp_prog, reg_none(), reg_a(insn->dst_reg * 2),
+				 ALU_OP_OR, reg_b(insn->dst_reg * 2 + 1));
 		emit_br(nfp_prog, BR_BNE, insn->off, 0);
 		return 0;
 	}
@@ -3087,6 +3110,9 @@ static int jne_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 		 reg_a(insn->dst_reg * 2), ALU_OP_XOR, tmp_reg);
 	emit_br(nfp_prog, BR_BNE, insn->off, 0);
 
+	if (is_jmp32)
+		return 0;
+
 	tmp_reg = ur_load_imm_any(nfp_prog, imm >> 32, imm_b(nfp_prog));
 	emit_alu(nfp_prog, reg_none(),
 		 reg_a(insn->dst_reg * 2 + 1), ALU_OP_XOR, tmp_reg);
@@ -3101,10 +3127,13 @@ static int jeq_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 	emit_alu(nfp_prog, imm_a(nfp_prog), reg_a(insn->dst_reg * 2),
 		 ALU_OP_XOR, reg_b(insn->src_reg * 2));
-	emit_alu(nfp_prog, imm_b(nfp_prog), reg_a(insn->dst_reg * 2 + 1),
-		 ALU_OP_XOR, reg_b(insn->src_reg * 2 + 1));
-	emit_alu(nfp_prog, reg_none(),
-		 imm_a(nfp_prog), ALU_OP_OR, imm_b(nfp_prog));
+	if (is_mbpf_jmp64(meta)) {
+		emit_alu(nfp_prog, imm_b(nfp_prog),
+			 reg_a(insn->dst_reg * 2 + 1), ALU_OP_XOR,
+			 reg_b(insn->src_reg * 2 + 1));
+		emit_alu(nfp_prog, reg_none(), imm_a(nfp_prog), ALU_OP_OR,
+			 imm_b(nfp_prog));
+	}
 	emit_br(nfp_prog, BR_BEQ, insn->off, 0);
 
 	return 0;
@@ -3369,6 +3398,28 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_JMP | BPF_JSLE | BPF_X] =  cmp_reg,
 	[BPF_JMP | BPF_JSET | BPF_X] =	jset_reg,
 	[BPF_JMP | BPF_JNE | BPF_X] =	jne_reg,
+	[BPF_JMP32 | BPF_JEQ | BPF_K] =	jeq32_imm,
+	[BPF_JMP32 | BPF_JGT | BPF_K] =	cmp_imm,
+	[BPF_JMP32 | BPF_JGE | BPF_K] =	cmp_imm,
+	[BPF_JMP32 | BPF_JLT | BPF_K] =	cmp_imm,
+	[BPF_JMP32 | BPF_JLE | BPF_K] =	cmp_imm,
+	[BPF_JMP32 | BPF_JSGT | BPF_K] =cmp_imm,
+	[BPF_JMP32 | BPF_JSGE | BPF_K] =cmp_imm,
+	[BPF_JMP32 | BPF_JSLT | BPF_K] =cmp_imm,
+	[BPF_JMP32 | BPF_JSLE | BPF_K] =cmp_imm,
+	[BPF_JMP32 | BPF_JSET | BPF_K] =jset_imm,
+	[BPF_JMP32 | BPF_JNE | BPF_K] =	jne_imm,
+	[BPF_JMP32 | BPF_JEQ | BPF_X] =	jeq_reg,
+	[BPF_JMP32 | BPF_JGT | BPF_X] =	cmp_reg,
+	[BPF_JMP32 | BPF_JGE | BPF_X] =	cmp_reg,
+	[BPF_JMP32 | BPF_JLT | BPF_X] =	cmp_reg,
+	[BPF_JMP32 | BPF_JLE | BPF_X] =	cmp_reg,
+	[BPF_JMP32 | BPF_JSGT | BPF_X] =cmp_reg,
+	[BPF_JMP32 | BPF_JSGE | BPF_X] =cmp_reg,
+	[BPF_JMP32 | BPF_JSLT | BPF_X] =cmp_reg,
+	[BPF_JMP32 | BPF_JSLE | BPF_X] =cmp_reg,
+	[BPF_JMP32 | BPF_JSET | BPF_X] =jset_reg,
+	[BPF_JMP32 | BPF_JNE | BPF_X] =	jne_reg,
 	[BPF_JMP | BPF_CALL] =		call,
 	[BPF_JMP | BPF_EXIT] =		jmp_exit,
 };
@@ -3397,7 +3448,7 @@ static int nfp_fixup_branches(struct nfp_prog *nfp_prog)
 	list_for_each_entry(meta, &nfp_prog->insns, l) {
 		if (meta->flags & FLAG_INSN_SKIP_MASK)
 			continue;
-		if (BPF_CLASS(meta->insn.code) != BPF_JMP)
+		if (!is_mbpf_jmp(meta))
 			continue;
 		if (meta->insn.code == (BPF_JMP | BPF_EXIT) &&
 		    !nfp_is_main_function(meta))
@@ -3758,16 +3809,14 @@ static void nfp_bpf_opt_neg_add_sub(struct nfp_prog *nfp_prog)
 		if (meta->flags & FLAG_INSN_SKIP_MASK)
 			continue;
 
-		if (BPF_CLASS(insn.code) != BPF_ALU &&
-		    BPF_CLASS(insn.code) != BPF_ALU64 &&
-		    BPF_CLASS(insn.code) != BPF_JMP)
+		if (!is_mbpf_alu(meta) && !is_mbpf_jmp(meta))
 			continue;
 		if (BPF_SRC(insn.code) != BPF_K)
 			continue;
 		if (insn.imm >= 0)
 			continue;
 
-		if (BPF_CLASS(insn.code) == BPF_JMP) {
+		if (is_mbpf_jmp(meta)) {
 			switch (BPF_OP(insn.code)) {
 			case BPF_JGE:
 			case BPF_JSGE:
@@ -4338,7 +4387,7 @@ void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog)
 		unsigned int dst_idx;
 		bool pseudo_call;
 
-		if (BPF_CLASS(code) != BPF_JMP)
+		if (!is_mbpf_jmp(meta))
 			continue;
 		if (BPF_OP(code) == BPF_EXIT)
 			continue;

drivers/net/ethernet/netronome/nfp/bpf/main.h

@@ -365,6 +365,21 @@ static inline bool is_mbpf_load(const struct nfp_insn_meta *meta)
 	return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_LDX | BPF_MEM);
 }
 
+static inline bool is_mbpf_jmp32(const struct nfp_insn_meta *meta)
+{
+	return mbpf_class(meta) == BPF_JMP32;
+}
+
+static inline bool is_mbpf_jmp64(const struct nfp_insn_meta *meta)
+{
+	return mbpf_class(meta) == BPF_JMP;
+}
+
+static inline bool is_mbpf_jmp(const struct nfp_insn_meta *meta)
+{
+	return is_mbpf_jmp32(meta) || is_mbpf_jmp64(meta);
+}
+
 static inline bool is_mbpf_store(const struct nfp_insn_meta *meta)
 {
 	return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_STX | BPF_MEM);
@@ -419,10 +434,13 @@ static inline bool is_mbpf_cond_jump(const struct nfp_insn_meta *meta)
 {
 	u8 op;
 
-	if (BPF_CLASS(meta->insn.code) != BPF_JMP)
+	if (is_mbpf_jmp32(meta))
+		return true;
+
+	if (!is_mbpf_jmp64(meta))
 		return false;
 
-	op = BPF_OP(meta->insn.code);
+	op = mbpf_op(meta);
 	return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL;
 }