diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h
index d26e5472fe50..6f3df004479b 100644
--- a/tools/lib/bpf/bpf_gen_internal.h
+++ b/tools/lib/bpf/bpf_gen_internal.h
@@ -45,8 +45,8 @@ struct bpf_gen {
 	int nr_fd_array;
 };
 
-void bpf_gen__init(struct bpf_gen *gen, int log_level);
-int bpf_gen__finish(struct bpf_gen *gen);
+void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps);
+int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps);
 void bpf_gen__free(struct bpf_gen *gen);
 void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size);
 void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_params *map_attr, int map_idx);
diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index 502dea53a742..9934851ccde7 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -18,7 +18,7 @@
 #define MAX_USED_MAPS	64
 #define MAX_USED_PROGS	32
 #define MAX_KFUNC_DESCS 256
-#define MAX_FD_ARRAY_SZ (MAX_USED_PROGS + MAX_KFUNC_DESCS)
+#define MAX_FD_ARRAY_SZ (MAX_USED_MAPS + MAX_KFUNC_DESCS)
 
 /* The following structure describes the stack layout of the loader program.
  * In addition R6 contains the pointer to context.
@@ -33,8 +33,8 @@
  */
 struct loader_stack {
 	__u32 btf_fd;
-	__u32 prog_fd[MAX_USED_PROGS];
 	__u32 inner_map_fd;
+	__u32 prog_fd[MAX_USED_PROGS];
 };
 
 #define stack_off(field) \
@@ -42,6 +42,11 @@ struct loader_stack {
 
 #define attr_field(attr, field) (attr + offsetof(union bpf_attr, field))
 
+static int blob_fd_array_off(struct bpf_gen *gen, int index)
+{
+	return gen->fd_array + index * sizeof(int);
+}
+
 static int realloc_insn_buf(struct bpf_gen *gen, __u32 size)
 {
 	size_t off = gen->insn_cur - gen->insn_start;
@@ -102,11 +107,15 @@ static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn in
 	emit(gen, insn2);
 }
 
-void bpf_gen__init(struct bpf_gen *gen, int log_level)
+static int add_data(struct bpf_gen *gen, const void *data, __u32 size);
+static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off);
+
+void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps)
 {
-	size_t stack_sz = sizeof(struct loader_stack);
+	size_t stack_sz = sizeof(struct loader_stack), nr_progs_sz;
 	int i;
 
+	gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
 	gen->log_level = log_level;
 	/* save ctx pointer into R6 */
 	emit(gen, BPF_MOV64_REG(BPF_REG_6, BPF_REG_1));
@@ -118,19 +127,27 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level)
 	emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0));
 	emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel));
 
+	/* amount of stack actually used, only used to calculate iterations, not stack offset */
+	nr_progs_sz = offsetof(struct loader_stack, prog_fd[nr_progs]);
 	/* jump over cleanup code */
 	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0,
-			      /* size of cleanup code below */
-			      (stack_sz / 4) * 3 + 2));
+			      /* size of cleanup code below (including map fd cleanup) */
+			      (nr_progs_sz / 4) * 3 + 2 +
+			      /* 6 insns for emit_sys_close_blob,
+			       * 6 insns for debug_regs in emit_sys_close_blob
+			       */
+			      nr_maps * (6 + (gen->log_level ? 6 : 0))));
 
 	/* remember the label where all error branches will jump to */
 	gen->cleanup_label = gen->insn_cur - gen->insn_start;
 	/* emit cleanup code: close all temp FDs */
-	for (i = 0; i < stack_sz; i += 4) {
+	for (i = 0; i < nr_progs_sz; i += 4) {
 		emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -stack_sz + i));
 		emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, 1));
 		emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close));
 	}
+	for (i = 0; i < nr_maps; i++)
+		emit_sys_close_blob(gen, blob_fd_array_off(gen, i));
 	/* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */
 	emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
 	emit(gen, BPF_EXIT_INSN());
@@ -160,8 +177,6 @@ static int add_data(struct bpf_gen *gen, const void *data, __u32 size)
  */
 static int add_map_fd(struct bpf_gen *gen)
 {
-	if (!gen->fd_array)
-		gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
 	if (gen->nr_maps == MAX_USED_MAPS) {
 		pr_warn("Total maps exceeds %d\n", MAX_USED_MAPS);
 		gen->error = -E2BIG;
@@ -174,8 +189,6 @@ static int add_kfunc_btf_fd(struct bpf_gen *gen)
 {
 	int cur;
 
-	if (!gen->fd_array)
-		gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
 	if (gen->nr_fd_array == MAX_KFUNC_DESCS) {
 		cur = add_data(gen, NULL, sizeof(int));
 		return (cur - gen->fd_array) / sizeof(int);
@@ -183,11 +196,6 @@ static int add_kfunc_btf_fd(struct bpf_gen *gen)
 	return MAX_USED_MAPS + gen->nr_fd_array++;
 }
 
-static int blob_fd_array_off(struct bpf_gen *gen, int index)
-{
-	return gen->fd_array + index * sizeof(int);
-}
-
 static int insn_bytes_to_bpf_size(__u32 sz)
 {
 	switch (sz) {
@@ -359,10 +367,15 @@ static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off)
 	__emit_sys_close(gen);
 }
 
-int bpf_gen__finish(struct bpf_gen *gen)
+int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
 {
 	int i;
 
+	if (nr_progs != gen->nr_progs || nr_maps != gen->nr_maps) {
+		pr_warn("progs/maps mismatch\n");
+		gen->error = -EFAULT;
+		return gen->error;
+	}
 	emit_sys_close_stack(gen, stack_off(btf_fd));
 	for (i = 0; i < gen->nr_progs; i++)
 		move_stack2ctx(gen,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index a1bea1953df6..7c74342bb668 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -7258,7 +7258,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 	}
 
 	if (obj->gen_loader)
-		bpf_gen__init(obj->gen_loader, attr->log_level);
+		bpf_gen__init(obj->gen_loader, attr->log_level, obj->nr_programs, obj->nr_maps);
 
 	err = bpf_object__probe_loading(obj);
 	err = err ? : bpf_object__load_vmlinux_btf(obj, false);
@@ -7277,7 +7277,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 		for (i = 0; i < obj->nr_maps; i++)
 			obj->maps[i].fd = -1;
 		if (!err)
-			err = bpf_gen__finish(obj->gen_loader);
+			err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps);
 	}
 
 	/* clean up fd_array */