4 files changed, 215 insertions, 58 deletions

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index e23ca90289f7..aa3a2098a583 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -1266,7 +1266,7 @@ wrp_alu64_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	u64 imm = insn->imm; /* sign extend */
 
 	if (skip) {
-		meta->skip = true;
+		meta->flags |= FLAG_INSN_SKIP_NOOP;
 		return 0;
 	}
 
@@ -1296,7 +1296,7 @@ wrp_alu32_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	const struct bpf_insn *insn = &meta->insn;
 
 	if (skip) {
-		meta->skip = true;
+		meta->flags |= FLAG_INSN_SKIP_NOOP;
 		return 0;
 	}
 
@@ -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;
@@ -3182,7 +3211,7 @@ bpf_to_bpf_call(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 		wrp_immed_relo(nfp_prog, imm_b(nfp_prog), 0, RELO_IMMED_REL);
 	} else {
 		ret_tgt = nfp_prog_current_offset(nfp_prog) + 2;
-		emit_br(nfp_prog, BR_UNC, meta->n + 1 + meta->insn.imm, 1);
+		emit_br(nfp_prog, BR_UNC, meta->insn.imm, 1);
 		offset_br = nfp_prog_current_offset(nfp_prog);
 	}
 	wrp_immed_relo(nfp_prog, ret_reg(nfp_prog), ret_tgt, RELO_IMMED_REL);
@@ -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,
 };
@@ -3395,9 +3446,9 @@ static int nfp_fixup_branches(struct nfp_prog *nfp_prog)
 	int err;
 
 	list_for_each_entry(meta, &nfp_prog->insns, l) {
-		if (meta->skip)
+		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))
@@ -3439,7 +3490,7 @@ static int nfp_fixup_branches(struct nfp_prog *nfp_prog)
 
 		jmp_dst = meta->jmp_dst;
 
-		if (jmp_dst->skip) {
+		if (jmp_dst->flags & FLAG_INSN_SKIP_PREC_DEPENDENT) {
 			pr_err("Branch landing on removed instruction!!\n");
 			return -ELOOP;
 		}
@@ -3689,7 +3740,7 @@ static int nfp_translate(struct nfp_prog *nfp_prog)
 				return nfp_prog->error;
 		}
 
-		if (meta->skip) {
+		if (meta->flags & FLAG_INSN_SKIP_MASK) {
 			nfp_prog->n_translated++;
 			continue;
 		}
@@ -3737,10 +3788,10 @@ static void nfp_bpf_opt_reg_init(struct nfp_prog *nfp_prog)
 		/* Programs start with R6 = R1 but we ignore the skb pointer */
 		if (insn.code == (BPF_ALU64 | BPF_MOV | BPF_X) &&
 		    insn.src_reg == 1 && insn.dst_reg == 6)
-			meta->skip = true;
+			meta->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
 
 		/* Return as soon as something doesn't match */
-		if (!meta->skip)
+		if (!(meta->flags & FLAG_INSN_SKIP_MASK))
 			return;
 	}
 }
@@ -3755,19 +3806,17 @@ static void nfp_bpf_opt_neg_add_sub(struct nfp_prog *nfp_prog)
 	list_for_each_entry(meta, &nfp_prog->insns, l) {
 		struct bpf_insn insn = meta->insn;
 
-		if (meta->skip)
+		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:
@@ -3829,7 +3878,7 @@ static void nfp_bpf_opt_ld_mask(struct nfp_prog *nfp_prog)
 		if (meta2->flags & FLAG_INSN_IS_JUMP_DST)
 			continue;
 
-		meta2->skip = true;
+		meta2->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
 	}
 }
 
@@ -3869,8 +3918,8 @@ static void nfp_bpf_opt_ld_shift(struct nfp_prog *nfp_prog)
 		    meta3->flags & FLAG_INSN_IS_JUMP_DST)
 			continue;
 
-		meta2->skip = true;
-		meta3->skip = true;
+		meta2->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
+		meta3->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
 	}
 }
 
@@ -4065,7 +4114,8 @@ static void nfp_bpf_opt_ldst_gather(struct nfp_prog *nfp_prog)
 				}
 
 				head_ld_meta->paired_st = &head_st_meta->insn;
-				head_st_meta->skip = true;
+				head_st_meta->flags |=
+					FLAG_INSN_SKIP_PREC_DEPENDENT;
 			} else {
 				head_ld_meta->ldst_gather_len = 0;
 			}
@@ -4098,8 +4148,8 @@ static void nfp_bpf_opt_ldst_gather(struct nfp_prog *nfp_prog)
 			head_ld_meta = meta1;
 			head_st_meta = meta2;
 		} else {
-			meta1->skip = true;
-			meta2->skip = true;
+			meta1->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
+			meta2->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
 		}
 
 		head_ld_meta->ldst_gather_len += BPF_LDST_BYTES(ld);
@@ -4124,7 +4174,7 @@ static void nfp_bpf_opt_pkt_cache(struct nfp_prog *nfp_prog)
 		if (meta->flags & FLAG_INSN_IS_JUMP_DST)
 			cache_avail = false;
 
-		if (meta->skip)
+		if (meta->flags & FLAG_INSN_SKIP_MASK)
 			continue;
 
 		insn = &meta->insn;
@@ -4210,7 +4260,7 @@ start_new:
 	}
 
 	list_for_each_entry(meta, &nfp_prog->insns, l) {
-		if (meta->skip)
+		if (meta->flags & FLAG_INSN_SKIP_MASK)
 			continue;
 
 		if (is_mbpf_load_pkt(meta) && !meta->ldst_gather_len) {
@@ -4246,7 +4296,8 @@ static int nfp_bpf_replace_map_ptrs(struct nfp_prog *nfp_prog)
 	u32 id;
 
 	nfp_for_each_insn_walk2(nfp_prog, meta1, meta2) {
-		if (meta1->skip || meta2->skip)
+		if (meta1->flags & FLAG_INSN_SKIP_MASK ||
+		    meta2->flags & FLAG_INSN_SKIP_MASK)
 			continue;
 
 		if (meta1->insn.code != (BPF_LD | BPF_IMM | BPF_DW) ||
@@ -4325,7 +4376,7 @@ int nfp_bpf_jit(struct nfp_prog *nfp_prog)
 	return ret;
 }
 
-void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt)
+void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog)
 {
 	struct nfp_insn_meta *meta;
 
@@ -4336,7 +4387,7 @@ void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt)
 		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;
@@ -4353,7 +4404,7 @@ void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt)
 		else
 			dst_idx = meta->n + 1 + meta->insn.off;
 
-		dst_meta = nfp_bpf_goto_meta(nfp_prog, meta, dst_idx, cnt);
+		dst_meta = nfp_bpf_goto_meta(nfp_prog, meta, dst_idx);
 
 		if (pseudo_call)
 			dst_meta->flags |= FLAG_INSN_IS_SUBPROG_START;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index 941277936475..b25a48218bcf 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -243,6 +243,16 @@ struct nfp_bpf_reg_state {
 #define FLAG_INSN_IS_JUMP_DST			BIT(0)
 #define FLAG_INSN_IS_SUBPROG_START		BIT(1)
 #define FLAG_INSN_PTR_CALLER_STACK_FRAME	BIT(2)
+/* Instruction is pointless, noop even on its own */
+#define FLAG_INSN_SKIP_NOOP			BIT(3)
+/* Instruction is optimized out based on preceding instructions */
+#define FLAG_INSN_SKIP_PREC_DEPENDENT		BIT(4)
+/* Instruction is optimized by the verifier */
+#define FLAG_INSN_SKIP_VERIFIER_OPT		BIT(5)
+
+#define FLAG_INSN_SKIP_MASK		(FLAG_INSN_SKIP_NOOP | \
+					 FLAG_INSN_SKIP_PREC_DEPENDENT | \
+					 FLAG_INSN_SKIP_VERIFIER_OPT)
 
 /**
  * struct nfp_insn_meta - BPF instruction wrapper
@@ -271,7 +281,6 @@ struct nfp_bpf_reg_state {
  * @n: eBPF instruction number
  * @flags: eBPF instruction extra optimization flags
  * @subprog_idx: index of subprogram to which the instruction belongs
- * @skip: skip this instruction (optimized out)
  * @double_cb: callback for second part of the instruction
  * @l: link on nfp_prog->insns list
  */
@@ -319,7 +328,6 @@ struct nfp_insn_meta {
 	unsigned short n;
 	unsigned short flags;
 	unsigned short subprog_idx;
-	bool skip;
 	instr_cb_t double_cb;
 
 	struct list_head l;
@@ -357,6 +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);
@@ -407,6 +430,20 @@ static inline bool is_mbpf_div(const struct nfp_insn_meta *meta)
 	return is_mbpf_alu(meta) && mbpf_op(meta) == BPF_DIV;
 }
 
+static inline bool is_mbpf_cond_jump(const struct nfp_insn_meta *meta)
+{
+	u8 op;
+
+	if (is_mbpf_jmp32(meta))
+		return true;
+
+	if (!is_mbpf_jmp64(meta))
+		return false;
+
+	op = mbpf_op(meta);
+	return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL;
+}
+
 static inline bool is_mbpf_helper_call(const struct nfp_insn_meta *meta)
 {
 	struct bpf_insn insn = meta->insn;
@@ -457,6 +494,7 @@ struct nfp_bpf_subprog_info {
  * @subprog_cnt: number of sub-programs, including main function
  * @map_records: the map record pointers from bpf->maps_neutral
  * @subprog: pointer to an array of objects holding info about sub-programs
+ * @n_insns: number of instructions on @insns list
  * @insns: list of BPF instruction wrappers (struct nfp_insn_meta)
  */
 struct nfp_prog {
@@ -489,6 +527,7 @@ struct nfp_prog {
 	struct nfp_bpf_neutral_map **map_records;
 	struct nfp_bpf_subprog_info *subprog;
 
+	unsigned int n_insns;
 	struct list_head insns;
 };
 
@@ -505,7 +544,7 @@ struct nfp_bpf_vnic {
 };
 
 bool nfp_is_subprog_start(struct nfp_insn_meta *meta);
-void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt);
+void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog);
 int nfp_bpf_jit(struct nfp_prog *prog);
 bool nfp_bpf_supported_opcode(u8 code);
 
@@ -513,6 +552,10 @@ int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx,
 		    int prev_insn_idx);
 int nfp_bpf_finalize(struct bpf_verifier_env *env);
 
+int nfp_bpf_opt_replace_insn(struct bpf_verifier_env *env, u32 off,
+			     struct bpf_insn *insn);
+int nfp_bpf_opt_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt);
+
 extern const struct bpf_prog_offload_ops nfp_bpf_dev_ops;
 
 struct netdev_bpf;
@@ -526,7 +569,7 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog,
 
 struct nfp_insn_meta *
 nfp_bpf_goto_meta(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
-		  unsigned int insn_idx, unsigned int n_insns);
+		  unsigned int insn_idx);
 
 void *nfp_bpf_relo_for_vnic(struct nfp_prog *nfp_prog, struct nfp_bpf_vnic *bv);
 
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index f0283854fade..55c7dbf8b421 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -163,8 +163,9 @@ nfp_prog_prepare(struct nfp_prog *nfp_prog, const struct bpf_insn *prog,
 
 		list_add_tail(&meta->l, &nfp_prog->insns);
 	}
+	nfp_prog->n_insns = cnt;
 
-	nfp_bpf_jit_prepare(nfp_prog, cnt);
+	nfp_bpf_jit_prepare(nfp_prog);
 
 	return 0;
 }
@@ -219,6 +220,10 @@ static int nfp_bpf_translate(struct bpf_prog *prog)
 	unsigned int max_instr;
 	int err;
 
+	/* We depend on dead code elimination succeeding */
+	if (prog->aux->offload->opt_failed)
+		return -EINVAL;
+
 	max_instr = nn_readw(nn, NFP_NET_CFG_BPF_MAX_LEN);
 	nfp_prog->__prog_alloc_len = max_instr * sizeof(u64);
 
@@ -591,6 +596,8 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog,
 const struct bpf_prog_offload_ops nfp_bpf_dev_ops = {
 	.insn_hook	= nfp_verify_insn,
 	.finalize	= nfp_bpf_finalize,
+	.replace_insn	= nfp_bpf_opt_replace_insn,
+	.remove_insns	= nfp_bpf_opt_remove_insns,
 	.prepare	= nfp_bpf_verifier_prep,
 	.translate	= nfp_bpf_translate,
 	.destroy	= nfp_bpf_destroy,
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
index 337bb862ec1d..36f56eb4cbe2 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
@@ -18,15 +18,15 @@
 
 struct nfp_insn_meta *
 nfp_bpf_goto_meta(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
-		  unsigned int insn_idx, unsigned int n_insns)
+		  unsigned int insn_idx)
 {
 	unsigned int forward, backward, i;
 
 	backward = meta->n - insn_idx;
 	forward = insn_idx - meta->n;
 
-	if (min(forward, backward) > n_insns - insn_idx - 1) {
-		backward = n_insns - insn_idx - 1;
+	if (min(forward, backward) > nfp_prog->n_insns - insn_idx - 1) {
+		backward = nfp_prog->n_insns - insn_idx - 1;
 		meta = nfp_prog_last_meta(nfp_prog);
 	}
 	if (min(forward, backward) > insn_idx && backward > insn_idx) {
@@ -629,7 +629,7 @@ int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx,
 	struct nfp_prog *nfp_prog = env->prog->aux->offload->dev_priv;
 	struct nfp_insn_meta *meta = nfp_prog->verifier_meta;
 
-	meta = nfp_bpf_goto_meta(nfp_prog, meta, insn_idx, env->prog->len);
+	meta = nfp_bpf_goto_meta(nfp_prog, meta, insn_idx);
 	nfp_prog->verifier_meta = meta;
 
 	if (!nfp_bpf_supported_opcode(meta->insn.code)) {
@@ -690,8 +690,7 @@ nfp_assign_subprog_idx_and_regs(struct bpf_verifier_env *env,
 	return 0;
 }
 
-static unsigned int
-nfp_bpf_get_stack_usage(struct nfp_prog *nfp_prog, unsigned int cnt)
+static unsigned int nfp_bpf_get_stack_usage(struct nfp_prog *nfp_prog)
 {
 	struct nfp_insn_meta *meta = nfp_prog_first_meta(nfp_prog);
 	unsigned int max_depth = 0, depth = 0, frame = 0;
@@ -726,7 +725,7 @@ continue_subprog:
 
 		/* Find the callee and start processing it. */
 		meta = nfp_bpf_goto_meta(nfp_prog, meta,
-					 meta->n + 1 + meta->insn.imm, cnt);
+					 meta->n + 1 + meta->insn.imm);
 		idx = meta->subprog_idx;
 		frame++;
 		goto process_subprog;
@@ -778,8 +777,7 @@ int nfp_bpf_finalize(struct bpf_verifier_env *env)
 
 	nn = netdev_priv(env->prog->aux->offload->netdev);
 	max_stack = nn_readb(nn, NFP_NET_CFG_BPF_STACK_SZ) * 64;
-	nfp_prog->stack_size = nfp_bpf_get_stack_usage(nfp_prog,
-						       env->prog->len);
+	nfp_prog->stack_size = nfp_bpf_get_stack_usage(nfp_prog);
 	if (nfp_prog->stack_size > max_stack) {
 		pr_vlog(env, "stack too large: program %dB > FW stack %dB\n",
 			nfp_prog->stack_size, max_stack);
@@ -788,3 +786,61 @@ int nfp_bpf_finalize(struct bpf_verifier_env *env)
 
 	return 0;
 }
+
+int nfp_bpf_opt_replace_insn(struct bpf_verifier_env *env, u32 off,
+			     struct bpf_insn *insn)
+{
+	struct nfp_prog *nfp_prog = env->prog->aux->offload->dev_priv;
+	struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+	struct nfp_insn_meta *meta = nfp_prog->verifier_meta;
+
+	meta = nfp_bpf_goto_meta(nfp_prog, meta, aux_data[off].orig_idx);
+	nfp_prog->verifier_meta = meta;
+
+	/* conditional jump to jump conversion */
+	if (is_mbpf_cond_jump(meta) &&
+	    insn->code == (BPF_JMP | BPF_JA | BPF_K)) {
+		unsigned int tgt_off;
+
+		tgt_off = off + insn->off + 1;
+
+		if (!insn->off) {
+			meta->jmp_dst = list_next_entry(meta, l);
+			meta->jump_neg_op = false;
+		} else if (meta->jmp_dst->n != aux_data[tgt_off].orig_idx) {
+			pr_vlog(env, "branch hard wire at %d changes target %d -> %d\n",
+				off, meta->jmp_dst->n,
+				aux_data[tgt_off].orig_idx);
+			return -EINVAL;
+		}
+		return 0;
+	}
+
+	pr_vlog(env, "unsupported instruction replacement %hhx -> %hhx\n",
+		meta->insn.code, insn->code);
+	return -EINVAL;
+}
+
+int nfp_bpf_opt_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt)
+{
+	struct nfp_prog *nfp_prog = env->prog->aux->offload->dev_priv;
+	struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+	struct nfp_insn_meta *meta = nfp_prog->verifier_meta;
+	unsigned int i;
+
+	meta = nfp_bpf_goto_meta(nfp_prog, meta, aux_data[off].orig_idx);
+
+	for (i = 0; i < cnt; i++) {
+		if (WARN_ON_ONCE(&meta->l == &nfp_prog->insns))
+			return -EINVAL;
+
+		/* doesn't count if it already has the flag */
+		if (meta->flags & FLAG_INSN_SKIP_VERIFIER_OPT)
+			i--;
+
+		meta->flags |= FLAG_INSN_SKIP_VERIFIER_OPT;
+		meta = list_next_entry(meta, l);
+	}
+
+	return 0;
+}