bpf: Wire up freeing of referenced kptr

A destructor kfunc can be defined as void func(type *), where type may
be void or any other pointer type as per convenience.

In this patch, we ensure that the type is sane and capture the function
pointer into off_desc of ptr_off_tab for the specific pointer offset,
with the invariant that the dtor pointer is always set when 'kptr_ref'
tag is applied to the pointer's pointee type, which is indicated by the
flag BPF_MAP_VALUE_OFF_F_REF.

Note that only BTF IDs whose destructor kfunc is registered, thus become
the allowed BTF IDs for embedding as referenced kptr. Hence it serves
the purpose of finding dtor kfunc BTF ID, as well acting as a check
against the whitelist of allowed BTF IDs for this purpose.

Finally, wire up the actual freeing of the referenced pointer if any at
all available offsets, so that no references are leaked after the BPF
map goes away and the BPF program previously moved the ownership a
referenced pointer into it.

The behavior is similar to BPF timers, where bpf_map_{update,delete}_elem
will free any existing referenced kptr. The same case is with LRU map's
bpf_lru_push_free/htab_lru_push_free functions, which are extended to
reset unreferenced and free referenced kptr.

Note that unlike BPF timers, kptr is not reset or freed when map uref
drops to zero.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220424214901.2743946-8-memxor@gmail.com

1 files changed, 97 insertions, 1 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index a0b1665a4a48..1f2012fd89fb 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3416,6 +3416,7 @@ struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf,
 	struct btf_field_info info_arr[BPF_MAP_VALUE_OFF_MAX];
 	struct bpf_map_value_off *tab;
 	struct btf *kernel_btf = NULL;
+	struct module *mod = NULL;
 	int ret, i, nr_off;
 
 	ret = btf_find_field(btf, t, BTF_FIELD_KPTR, info_arr, ARRAY_SIZE(info_arr));
@@ -3444,16 +3445,69 @@ struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf,
 			goto end;
 		}
 
+		/* Find and stash the function pointer for the destruction function that
+		 * needs to be eventually invoked from the map free path.
+		 */
+		if (info_arr[i].type == BPF_KPTR_REF) {
+			const struct btf_type *dtor_func;
+			const char *dtor_func_name;
+			unsigned long addr;
+			s32 dtor_btf_id;
+
+			/* This call also serves as a whitelist of allowed objects that
+			 * can be used as a referenced pointer and be stored in a map at
+			 * the same time.
+			 */
+			dtor_btf_id = btf_find_dtor_kfunc(kernel_btf, id);
+			if (dtor_btf_id < 0) {
+				ret = dtor_btf_id;
+				goto end_btf;
+			}
+
+			dtor_func = btf_type_by_id(kernel_btf, dtor_btf_id);
+			if (!dtor_func) {
+				ret = -ENOENT;
+				goto end_btf;
+			}
+
+			if (btf_is_module(kernel_btf)) {
+				mod = btf_try_get_module(kernel_btf);
+				if (!mod) {
+					ret = -ENXIO;
+					goto end_btf;
+				}
+			}
+
+			/* We already verified dtor_func to be btf_type_is_func
+			 * in register_btf_id_dtor_kfuncs.
+			 */
+			dtor_func_name = __btf_name_by_offset(kernel_btf, dtor_func->name_off);
+			addr = kallsyms_lookup_name(dtor_func_name);
+			if (!addr) {
+				ret = -EINVAL;
+				goto end_mod;
+			}
+			tab->off[i].kptr.dtor = (void *)addr;
+		}
+
 		tab->off[i].offset = info_arr[i].off;
 		tab->off[i].type = info_arr[i].type;
 		tab->off[i].kptr.btf_id = id;
 		tab->off[i].kptr.btf = kernel_btf;
+		tab->off[i].kptr.module = mod;
 	}
 	tab->nr_off = nr_off;
 	return tab;
+end_mod:
+	module_put(mod);
+end_btf:
+	btf_put(kernel_btf);
 end:
-	while (i--)
+	while (i--) {
 		btf_put(tab->off[i].kptr.btf);
+		if (tab->off[i].kptr.module)
+			module_put(tab->off[i].kptr.module);
+	}
 	kfree(tab);
 	return ERR_PTR(ret);
 }
@@ -7111,6 +7165,43 @@ s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id)
 	return dtor->kfunc_btf_id;
 }
 
+static int btf_check_dtor_kfuncs(struct btf *btf, const struct btf_id_dtor_kfunc *dtors, u32 cnt)
+{
+	const struct btf_type *dtor_func, *dtor_func_proto, *t;
+	const struct btf_param *args;
+	s32 dtor_btf_id;
+	u32 nr_args, i;
+
+	for (i = 0; i < cnt; i++) {
+		dtor_btf_id = dtors[i].kfunc_btf_id;
+
+		dtor_func = btf_type_by_id(btf, dtor_btf_id);
+		if (!dtor_func || !btf_type_is_func(dtor_func))
+			return -EINVAL;
+
+		dtor_func_proto = btf_type_by_id(btf, dtor_func->type);
+		if (!dtor_func_proto || !btf_type_is_func_proto(dtor_func_proto))
+			return -EINVAL;
+
+		/* Make sure the prototype of the destructor kfunc is 'void func(type *)' */
+		t = btf_type_by_id(btf, dtor_func_proto->type);
+		if (!t || !btf_type_is_void(t))
+			return -EINVAL;
+
+		nr_args = btf_type_vlen(dtor_func_proto);
+		if (nr_args != 1)
+			return -EINVAL;
+		args = btf_params(dtor_func_proto);
+		t = btf_type_by_id(btf, args[0].type);
+		/* Allow any pointer type, as width on targets Linux supports
+		 * will be same for all pointer types (i.e. sizeof(void *))
+		 */
+		if (!t || !btf_type_is_ptr(t))
+			return -EINVAL;
+	}
+	return 0;
+}
+
 /* This function must be invoked only from initcalls/module init functions */
 int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt,
 				struct module *owner)
@@ -7141,6 +7232,11 @@ int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_c
 		goto end;
 	}
 
+	/* Ensure that the prototype of dtor kfuncs being registered is sane */
+	ret = btf_check_dtor_kfuncs(btf, dtors, add_cnt);
+	if (ret < 0)
+		goto end;
+
 	tab = btf->dtor_kfunc_tab;
 	/* Only one call allowed for modules */
 	if (WARN_ON_ONCE(tab && btf_is_module(btf))) {