[bpf-next,v14,09/14] bpf: hold module refcnt in bpf_struct_ops map creation and prog verification.

Commit Message

Kui-Feng Lee Dec. 17, 2023, 8:11 a.m. UTC

From: Kui-Feng Lee <[e-mail]>

To ensure that a module remains accessible whenever a struct_ops object of
a struct_ops type provided by the module is still in use.

struct bpf_struct_ops_map doesn't hold a refcnt to btf anymore since a
module will hold a refcnt to it's btf already. But, struct_ops programs are
different. They hold their associated btf, not the module since they need
only btf to assure their types (signatures).

However, verifier holds the refcnt of the associated module of a struct_ops
type temporarily when verify a struct_ops prog. Verifier needs the help
from the verifier operators (struct bpf_verifier_ops) provided by the owner
module to verify data access of a prog, provide information, and generate
code.

Signed-off-by: Kui-Feng Lee <[e-mail]>
---
 include/linux/bpf.h          |  1 +
 include/linux/bpf_verifier.h |  1 +
 kernel/bpf/bpf_struct_ops.c  | 24 +++++++++++++++++++++---
 kernel/bpf/verifier.c        | 10 ++++++++++
 4 files changed, 33 insertions(+), 3 deletions(-)

Patch

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 0163b46910b1..b60f09449c7f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1683,6 +1683,7 @@  struct bpf_struct_ops {
 	void (*unreg)(void *kdata);
 	int (*update)(void *kdata, void *old_kdata);
 	int (*validate)(void *kdata);
+	struct module *owner;
 	const char *name;
 	struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS];
 };
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index c2819a6579a5..14a0ffb9283a 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -651,6 +651,7 @@  struct bpf_verifier_env {
 	u32 prev_insn_idx;
 	struct bpf_prog *prog;		/* eBPF program being verified */
 	const struct bpf_verifier_ops *ops;
+	struct module *attach_btf_mod;	/* The owner module of prog->aux->attach_btf */
 	struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */
 	int stack_size;			/* number of states to be processed */
 	bool strict_alignment;		/* perform strict pointer alignment checks */
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 381175f97b25..ac7fbcc66da9 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -641,12 +641,20 @@  static void __bpf_struct_ops_map_free(struct bpf_map *map)
 		bpf_jit_uncharge_modmem(PAGE_SIZE);
 	}
 	bpf_map_area_free(st_map->uvalue);
-	btf_put(st_map->btf);
 	bpf_map_area_free(st_map);
 }
 
 static void bpf_struct_ops_map_free(struct bpf_map *map)
 {
+	struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map;
+
+	/* st_ops->owner was acquired during map_alloc to implicitly holds
+	 * the btf's refcnt. The acquire was only done when btf_is_module()
+	 * st_map->btf cannot be NULL here.
+	 */
+	if (btf_is_module(st_map->btf))
+		module_put(st_map->st_ops_desc->st_ops->owner);
+
 	/* The struct_ops's function may switch to another struct_ops.
 	 *
 	 * For example, bpf_tcp_cc_x->init() may switch to
@@ -681,6 +689,7 @@  static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	size_t st_map_size;
 	struct bpf_struct_ops_map *st_map;
 	const struct btf_type *t, *vt;
+	struct module *mod = NULL;
 	struct bpf_map *map;
 	struct btf *btf;
 	int ret;
@@ -694,11 +703,20 @@  static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 			btf_put(btf);
 			return ERR_PTR(-EINVAL);
 		}
+
+		mod = btf_try_get_module(btf);
+		if (!mod) {
+			btf_put(btf);
+			return ERR_PTR(-EINVAL);
+		}
+		/* mod holds a refcnt to btf. We don't need an extra refcnt
+		 * here.
+		 */
+		btf_put(btf);
 	} else {
 		btf = bpf_get_btf_vmlinux();
 		if (IS_ERR(btf))
 			return ERR_CAST(btf);
-		btf_get(btf);
 	}
 
 	st_ops_desc = bpf_struct_ops_find_value(btf, attr->btf_vmlinux_value_type_id);
@@ -762,7 +780,7 @@  static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 errout_free:
 	__bpf_struct_ops_map_free(map);
 errout:
-	btf_put(btf);
+	module_put(mod);
 
 	return ERR_PTR(ret);
 }
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 970b601ac2ba..dfcd1b7463d9 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -20095,6 +20095,14 @@  static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
 	}
 
 	btf = prog->aux->attach_btf ?: bpf_get_btf_vmlinux();
+	if (btf_is_module(btf)) {
+		/* Make sure st_ops is valid through the lifetime of env */
+		env->attach_btf_mod = btf_try_get_module(btf);
+		if (!env->attach_btf_mod) {
+			verbose(env, "owner module of btf is not found\n");
+			return -ENOTSUPP;
+		}
+	}
 
 	btf_id = prog->aux->attach_btf_id;
 	st_ops_desc = bpf_struct_ops_find(btf, btf_id);
@@ -20808,6 +20816,8 @@  int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 		env->prog->expected_attach_type = 0;
 
 	*prog = env->prog;
+
+	module_put(env->attach_btf_mod);
 err_unlock:
 	if (!is_priv)
 		mutex_unlock(&bpf_verifier_lock);