@@ -1917,6 +1917,20 @@ __bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign)
__bpf_obj_drop_impl(p, meta ? meta->record : NULL);
}
+__bpf_kfunc void *bpf_refcount_acquire_impl(void *p__refcounted_kptr, void *meta__ign)
+{
+ struct btf_struct_meta *meta = meta__ign;
+ struct bpf_refcount *ref;
+
+ /* Could just cast directly to refcount_t *, but need some code using
+ * bpf_refcount type so that it is emitted in vmlinux BTF
+ */
+ ref = (struct bpf_refcount *)p__refcounted_kptr + meta->record->refcount_off;
+
+ refcount_inc((refcount_t *)ref);
+ return (void *)p__refcounted_kptr;
+}
+
static void __bpf_list_add(struct bpf_list_node *node, struct bpf_list_head *head, bool tail)
{
struct list_head *n = (void *)node, *h = (void *)head;
@@ -2276,6 +2290,7 @@ BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE)
#endif
BTF_ID_FLAGS(func, bpf_obj_new_impl, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_obj_drop_impl, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_refcount_acquire_impl, KF_ACQUIRE)
BTF_ID_FLAGS(func, bpf_list_push_front)
BTF_ID_FLAGS(func, bpf_list_push_back)
BTF_ID_FLAGS(func, bpf_list_pop_front, KF_ACQUIRE | KF_RET_NULL)
@@ -273,6 +273,11 @@ struct bpf_call_arg_meta {
struct btf_field *kptr_field;
};
+struct btf_and_id {
+ struct btf *btf;
+ u32 btf_id;
+};
+
struct bpf_kfunc_call_arg_meta {
/* In parameters */
struct btf *btf;
@@ -291,10 +296,10 @@ struct bpf_kfunc_call_arg_meta {
u64 value;
bool found;
} arg_constant;
- struct {
- struct btf *btf;
- u32 btf_id;
- } arg_obj_drop;
+ union {
+ struct btf_and_id arg_obj_drop;
+ struct btf_and_id arg_refcount_acquire;
+ };
struct {
struct btf_field *field;
} arg_list_head;
@@ -9403,6 +9408,11 @@ static bool is_kfunc_arg_uninit(const struct btf *btf, const struct btf_param *a
return __kfunc_param_match_suffix(btf, arg, "__uninit");
}
+static bool is_kfunc_arg_refcounted_kptr(const struct btf *btf, const struct btf_param *arg)
+{
+ return __kfunc_param_match_suffix(btf, arg, "__refcounted_kptr");
+}
+
static bool is_kfunc_arg_scalar_with_name(const struct btf *btf,
const struct btf_param *arg,
const char *name)
@@ -9542,15 +9552,16 @@ static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
enum kfunc_ptr_arg_type {
KF_ARG_PTR_TO_CTX,
- KF_ARG_PTR_TO_ALLOC_BTF_ID, /* Allocated object */
- KF_ARG_PTR_TO_KPTR, /* PTR_TO_KPTR but type specific */
+ KF_ARG_PTR_TO_ALLOC_BTF_ID, /* Allocated object */
+ KF_ARG_PTR_TO_REFCOUNTED_KPTR, /* Refcounted local kptr */
+ KF_ARG_PTR_TO_KPTR, /* PTR_TO_KPTR but type specific */
KF_ARG_PTR_TO_DYNPTR,
KF_ARG_PTR_TO_ITER,
KF_ARG_PTR_TO_LIST_HEAD,
KF_ARG_PTR_TO_LIST_NODE,
- KF_ARG_PTR_TO_BTF_ID, /* Also covers reg2btf_ids conversions */
+ KF_ARG_PTR_TO_BTF_ID, /* Also covers reg2btf_ids conversions */
KF_ARG_PTR_TO_MEM,
- KF_ARG_PTR_TO_MEM_SIZE, /* Size derived from next argument, skip it */
+ KF_ARG_PTR_TO_MEM_SIZE, /* Size derived from next argument, skip it */
KF_ARG_PTR_TO_CALLBACK,
KF_ARG_PTR_TO_RB_ROOT,
KF_ARG_PTR_TO_RB_NODE,
@@ -9559,6 +9570,7 @@ enum kfunc_ptr_arg_type {
enum special_kfunc_type {
KF_bpf_obj_new_impl,
KF_bpf_obj_drop_impl,
+ KF_bpf_refcount_acquire_impl,
KF_bpf_list_push_front,
KF_bpf_list_push_back,
KF_bpf_list_pop_front,
@@ -9579,6 +9591,7 @@ enum special_kfunc_type {
BTF_SET_START(special_kfunc_set)
BTF_ID(func, bpf_obj_new_impl)
BTF_ID(func, bpf_obj_drop_impl)
+BTF_ID(func, bpf_refcount_acquire_impl)
BTF_ID(func, bpf_list_push_front)
BTF_ID(func, bpf_list_push_back)
BTF_ID(func, bpf_list_pop_front)
@@ -9597,6 +9610,7 @@ BTF_SET_END(special_kfunc_set)
BTF_ID_LIST(special_kfunc_list)
BTF_ID(func, bpf_obj_new_impl)
BTF_ID(func, bpf_obj_drop_impl)
+BTF_ID(func, bpf_refcount_acquire_impl)
BTF_ID(func, bpf_list_push_front)
BTF_ID(func, bpf_list_push_back)
BTF_ID(func, bpf_list_pop_front)
@@ -9649,6 +9663,9 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
if (is_kfunc_arg_alloc_obj(meta->btf, &args[argno]))
return KF_ARG_PTR_TO_ALLOC_BTF_ID;
+ if (is_kfunc_arg_refcounted_kptr(meta->btf, &args[argno]))
+ return KF_ARG_PTR_TO_REFCOUNTED_KPTR;
+
if (is_kfunc_arg_kptr_get(meta, argno)) {
if (!btf_type_is_ptr(ref_t)) {
verbose(env, "arg#0 BTF type must be a double pointer for kptr_get kfunc\n");
@@ -9952,7 +9969,8 @@ static bool is_bpf_rbtree_api_kfunc(u32 btf_id)
static bool is_bpf_graph_api_kfunc(u32 btf_id)
{
- return is_bpf_list_api_kfunc(btf_id) || is_bpf_rbtree_api_kfunc(btf_id);
+ return is_bpf_list_api_kfunc(btf_id) || is_bpf_rbtree_api_kfunc(btf_id) ||
+ btf_id == special_kfunc_list[KF_bpf_refcount_acquire_impl];
}
static bool is_callback_calling_kfunc(u32 btf_id)
@@ -10171,6 +10189,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
const char *func_name = meta->func_name, *ref_tname;
const struct btf *btf = meta->btf;
const struct btf_param *args;
+ struct btf_record *rec;
u32 i, nargs;
int ret;
@@ -10306,6 +10325,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
case KF_ARG_PTR_TO_MEM:
case KF_ARG_PTR_TO_MEM_SIZE:
case KF_ARG_PTR_TO_CALLBACK:
+ case KF_ARG_PTR_TO_REFCOUNTED_KPTR:
/* Trusted by default */
break;
default:
@@ -10523,6 +10543,26 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
case KF_ARG_PTR_TO_CALLBACK:
meta->subprogno = reg->subprogno;
break;
+ case KF_ARG_PTR_TO_REFCOUNTED_KPTR:
+ if (!type_is_ptr_alloc_obj(reg->type) && !type_is_non_owning_ref(reg->type)) {
+ verbose(env, "arg#%d is neither owning or non-owning ref\n", i);
+ return -EINVAL;
+ }
+
+ rec = reg_btf_record(reg);
+ if (!rec) {
+ verbose(env, "verifier internal error: Couldn't find btf_record\n");
+ return -EFAULT;
+ }
+
+ if (rec->refcount_off < 0) {
+ verbose(env, "arg#%d doesn't point to a type with bpf_refcount field\n", i);
+ return -EINVAL;
+ }
+
+ meta->arg_refcount_acquire.btf = reg->btf;
+ meta->arg_refcount_acquire.btf_id = reg->btf_id;
+ break;
}
}
@@ -10699,7 +10739,9 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
if (is_kfunc_acquire(&meta) && !btf_type_is_struct_ptr(meta.btf, t)) {
/* Only exception is bpf_obj_new_impl */
- if (meta.btf != btf_vmlinux || meta.func_id != special_kfunc_list[KF_bpf_obj_new_impl]) {
+ if (meta.btf != btf_vmlinux ||
+ (meta.func_id != special_kfunc_list[KF_bpf_obj_new_impl] &&
+ meta.func_id != special_kfunc_list[KF_bpf_refcount_acquire_impl])) {
verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n");
return -EINVAL;
}
@@ -10747,6 +10789,15 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
insn_aux->obj_new_size = ret_t->size;
insn_aux->kptr_struct_meta =
btf_find_struct_meta(ret_btf, ret_btf_id);
+ } else if (meta.func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) {
+ mark_reg_known_zero(env, regs, BPF_REG_0);
+ regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
+ regs[BPF_REG_0].btf = meta.arg_refcount_acquire.btf;
+ regs[BPF_REG_0].btf_id = meta.arg_refcount_acquire.btf_id;
+
+ insn_aux->kptr_struct_meta =
+ btf_find_struct_meta(meta.arg_refcount_acquire.btf,
+ meta.arg_refcount_acquire.btf_id);
} else if (meta.func_id == special_kfunc_list[KF_bpf_list_pop_front] ||
meta.func_id == special_kfunc_list[KF_bpf_list_pop_back]) {
struct btf_field *field = meta.arg_list_head.field;
@@ -17393,7 +17444,8 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
insn_buf[2] = addr[1];
insn_buf[3] = *insn;
*cnt = 4;
- } else if (desc->func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) {
+ } else if (desc->func_id == special_kfunc_list[KF_bpf_obj_drop_impl] ||
+ desc->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) {
struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) };
@@ -37,6 +37,19 @@ extern void bpf_obj_drop_impl(void *kptr, void *meta) __ksym;
/* Convenience macro to wrap over bpf_obj_drop_impl */
#define bpf_obj_drop(kptr) bpf_obj_drop_impl(kptr, NULL)
+/* Description
+ * Increment the refcount on a refcounted local kptr, turning the
+ * non-owning reference input into an owning reference in the process.
+ *
+ * The 'meta' parameter is a hidden argument that is ignored.
+ * Returns
+ * An owning reference to the object pointed to by 'kptr'
+ */
+extern void *bpf_refcount_acquire_impl(void *kptr, void *meta) __ksym;
+
+/* Convenience macro to wrap over bpf_refcount_acquire_impl */
+#define bpf_refcount_acquire(kptr) bpf_refcount_acquire_impl(kptr, NULL)
+
/* Description
* Add a new entry to the beginning of the BPF linked list.
* Returns
Currently, BPF programs can interact with the lifetime of refcounted local kptrs in the following ways: bpf_obj_new - Initialize refcount to 1 as part of new object creation bpf_obj_drop - Decrement refcount and free object if it's 0 collection add - Pass ownership to the collection. No change to refcount but collection is responsible for bpf_obj_dropping it In order to be able to add a refcounted local kptr to multiple collections we need to be able to increment the refcount and acquire a new owning reference. This patch adds a kfunc, bpf_refcount_acquire, implementing such an operation. bpf_refcount_acquire takes a refcounted local kptr and returns a new owning reference to the same underlying memory as the input. The input can be either owning or non-owning. To reinforce why this is safe, consider the following code snippets: struct node *n = bpf_obj_new(typeof(*n)); // A struct node *m = bpf_refcount_acquire(n); // B In the above snippet, n will be alive with refcount=1 after (A), and since nothing changes that state before (B), it's obviously safe. If n is instead added to some rbtree, we can still safely refcount_acquire it: struct node *n = bpf_obj_new(typeof(*n)); struct node *m; bpf_spin_lock(&glock); bpf_rbtree_add(&groot, &n->node, less); // A m = bpf_refcount_acquire(n); // B bpf_spin_unlock(&glock); In the above snippet, after (A) n is a non-owning reference, and after (B) m is an owning reference pointing to the same memory as n. Although n has no ownership of that memory's lifetime, it's guaranteed to be alive until the end of the critical section, and n would be clobbered if we were past the end of the critical section, so it's safe to bump refcount. Implementation details: * From verifier's perspective, bpf_refcount_acquire handling is similar to bpf_obj_new and bpf_obj_drop. Like the former, it returns a new owning reference matching input type, although like the latter, type can be inferred from concrete kptr input. Verifier changes in {check,fixup}_kfunc_call and check_kfunc_args are largely copied from aforementioned functions' verifier changes. * An exception to the above is the new KF_ARG_PTR_TO_REFCOUNTED_KPTR arg, indicated by new "__refcounted_kptr" kfunc arg suffix. This is necessary in order to handle both owning and non-owning input without adding special-casing to "__alloc" arg handling. Also a convenient place to confirm that input type has bpf_refcount field. * The implemented kfunc is actually bpf_refcount_acquire_impl, with 'hidden' second arg that the verifier sets to the type's struct_meta in fixup_kfunc_call. Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com> --- kernel/bpf/helpers.c | 15 ++++ kernel/bpf/verifier.c | 74 ++++++++++++++++--- .../testing/selftests/bpf/bpf_experimental.h | 13 ++++ 3 files changed, 91 insertions(+), 11 deletions(-)