diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index dbd00982fd2b698bfa5bedc1572583890e75fe63..2134045e14c36a88c51717b7f4b36f07bbaa5c83 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -206,6 +206,11 @@ enum nfp_bpf_map_use {
 	NFP_MAP_USE_ATOMIC_CNT,
 };
 
+struct nfp_bpf_map_word {
+	unsigned char type		:4;
+	unsigned char non_zero_update	:1;
+};
+
 /**
  * struct nfp_bpf_map - private per-map data attached to BPF maps for offload
  * @offmap:	pointer to the offloaded BPF map
@@ -219,7 +224,7 @@ struct nfp_bpf_map {
 	struct nfp_app_bpf *bpf;
 	u32 tid;
 	struct list_head l;
-	enum nfp_bpf_map_use use_map[];
+	struct nfp_bpf_map_word use_map[];
 };
 
 struct nfp_bpf_neutral_map {
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 1ccd6371a15b5c3c0a142909d63b4e0796418fd4..6140e4650b71cc249d82f84fefc1fda1efe26b56 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -299,10 +299,25 @@ static void nfp_map_bpf_byte_swap(struct nfp_bpf_map *nfp_map, void *value)
 	unsigned int i;
 
 	for (i = 0; i < DIV_ROUND_UP(nfp_map->offmap->map.value_size, 4); i++)
-		if (nfp_map->use_map[i] == NFP_MAP_USE_ATOMIC_CNT)
+		if (nfp_map->use_map[i].type == NFP_MAP_USE_ATOMIC_CNT)
 			word[i] = (__force u32)cpu_to_be32(word[i]);
 }
 
+/* Mark value as unsafely initialized in case it becomes atomic later
+ * and we didn't byte swap something non-byte swap neutral.
+ */
+static void
+nfp_map_bpf_byte_swap_record(struct nfp_bpf_map *nfp_map, void *value)
+{
+	u32 *word = value;
+	unsigned int i;
+
+	for (i = 0; i < DIV_ROUND_UP(nfp_map->offmap->map.value_size, 4); i++)
+		if (nfp_map->use_map[i].type == NFP_MAP_UNUSED &&
+		    word[i] != (__force u32)cpu_to_be32(word[i]))
+			nfp_map->use_map[i].non_zero_update = 1;
+}
+
 static int
 nfp_bpf_map_lookup_entry(struct bpf_offloaded_map *offmap,
 			 void *key, void *value)
@@ -322,6 +337,7 @@ nfp_bpf_map_update_entry(struct bpf_offloaded_map *offmap,
 			 void *key, void *value, u64 flags)
 {
 	nfp_map_bpf_byte_swap(offmap->dev_priv, value);
+	nfp_map_bpf_byte_swap_record(offmap->dev_priv, value);
 	return nfp_bpf_ctrl_update_entry(offmap, key, value, flags);
 }
 
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
index a6e9248669e141d4d19f0536eed52adf6ef78d90..db7e186dae56d4c0dda0d3ba59c5408867ef7371 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
@@ -108,6 +108,46 @@ nfp_record_adjust_head(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 	nfp_prog->adjust_head_location = location;
 }
 
+static bool nfp_bpf_map_update_value_ok(struct bpf_verifier_env *env)
+{
+	const struct bpf_reg_state *reg1 = cur_regs(env) + BPF_REG_1;
+	const struct bpf_reg_state *reg3 = cur_regs(env) + BPF_REG_3;
+	struct bpf_offloaded_map *offmap;
+	struct bpf_func_state *state;
+	struct nfp_bpf_map *nfp_map;
+	int off, i;
+
+	state = env->cur_state->frame[reg3->frameno];
+
+	/* We need to record each time update happens with non-zero words,
+	 * in case such word is used in atomic operations.
+	 * Implicitly depend on nfp_bpf_stack_arg_ok(reg3) being run before.
+	 */
+
+	offmap = map_to_offmap(reg1->map_ptr);
+	nfp_map = offmap->dev_priv;
+	off = reg3->off + reg3->var_off.value;
+
+	for (i = 0; i < offmap->map.value_size; i++) {
+		struct bpf_stack_state *stack_entry;
+		unsigned int soff;
+
+		soff = -(off + i) - 1;
+		stack_entry = &state->stack[soff / BPF_REG_SIZE];
+		if (stack_entry->slot_type[soff % BPF_REG_SIZE] == STACK_ZERO)
+			continue;
+
+		if (nfp_map->use_map[i / 4].type == NFP_MAP_USE_ATOMIC_CNT) {
+			pr_vlog(env, "value at offset %d/%d may be non-zero, bpf_map_update_elem() is required to initialize atomic counters to zero to avoid offload endian issues\n",
+				i, soff);
+			return false;
+		}
+		nfp_map->use_map[i / 4].non_zero_update = 1;
+	}
+
+	return true;
+}
+
 static int
 nfp_bpf_stack_arg_ok(const char *fname, struct bpf_verifier_env *env,
 		     const struct bpf_reg_state *reg,
@@ -198,7 +238,8 @@ nfp_bpf_check_call(struct nfp_prog *nfp_prog, struct bpf_verifier_env *env,
 					 bpf->helpers.map_update, reg1) ||
 		    !nfp_bpf_stack_arg_ok("map_update", env, reg2,
 					  meta->func_id ? &meta->arg2 : NULL) ||
-		    !nfp_bpf_stack_arg_ok("map_update", env, reg3, NULL))
+		    !nfp_bpf_stack_arg_ok("map_update", env, reg3, NULL) ||
+		    !nfp_bpf_map_update_value_ok(env))
 			return -EOPNOTSUPP;
 		break;
 
@@ -376,15 +417,22 @@ nfp_bpf_map_mark_used_one(struct bpf_verifier_env *env,
 			  struct nfp_bpf_map *nfp_map,
 			  unsigned int off, enum nfp_bpf_map_use use)
 {
-	if (nfp_map->use_map[off / 4] != NFP_MAP_UNUSED &&
-	    nfp_map->use_map[off / 4] != use) {
+	if (nfp_map->use_map[off / 4].type != NFP_MAP_UNUSED &&
+	    nfp_map->use_map[off / 4].type != use) {
 		pr_vlog(env, "map value use type conflict %s vs %s off: %u\n",
-			nfp_bpf_map_use_name(nfp_map->use_map[off / 4]),
+			nfp_bpf_map_use_name(nfp_map->use_map[off / 4].type),
 			nfp_bpf_map_use_name(use), off);
 		return -EOPNOTSUPP;
 	}
 
-	nfp_map->use_map[off / 4] = use;
+	if (nfp_map->use_map[off / 4].non_zero_update &&
+	    use == NFP_MAP_USE_ATOMIC_CNT) {
+		pr_vlog(env, "atomic counter in map value may already be initialized to non-zero value off: %u\n",
+			off);
+		return -EOPNOTSUPP;
+	}
+
+	nfp_map->use_map[off / 4].type = use;
 
 	return 0;
 }