bpf: Let bpf_iter_task_new accept null task ptr

When using task_iter to iterate all threads of a specific task, we enforce
that the user must pass a valid task pointer to ensure safety. However,
when iterating all threads/process in the system, BPF verifier still
require a valid ptr instead of "nullable" pointer, even though it's
pointless, which is a kind of surprising from usability standpoint. It
would be nice if we could let that kfunc accept a explicit null pointer
when we are using BPF_TASK_ITER_ALL_{PROCS, THREADS} and a valid pointer
when using BPF_TASK_ITER_THREAD.

Given a trival kfunc:
	__bpf_kfunc void FN(struct TYPE_A *obj);

BPF Prog would reject a nullptr for obj. The error info is:
"arg#x pointer type xx xx must point to scalar, or struct with scalar"
reported by get_kfunc_ptr_arg_type(). The reg->type is SCALAR_VALUE and
the btf type of ref_t is not scalar or scalar_struct which leads to the
rejection of get_kfunc_ptr_arg_type.

This patch add "__nullable" annotation:
	__bpf_kfunc void FN(struct TYPE_A *obj__nullable);
Here __nullable indicates obj can be optional, user can pass a explicit
nullptr or a normal TYPE_A pointer. In get_kfunc_ptr_arg_type(), we will
detect whether the current arg is optional and register is null, If so,
return a new kfunc_ptr_arg_type KF_ARG_PTR_TO_NULL and skip to the next
arg in check_kfunc_args().

Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231018061746.111364-7-zhouchuyi@bytedance.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index faa1712c1df54747c28adc38d8375fe02f621455..59e747938bdbb197c20419f6a7223e5021bbdc0c 100644 (file)
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -976,7 +976,7 @@ __diag_ignore_all("-Wmissing-prototypes",
                  "Global functions as their definitions will be in vmlinux BTF");
 
 __bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it,
-               struct task_struct *task, unsigned int flags)
+               struct task_struct *task__nullable, unsigned int flags)
 {
        struct bpf_iter_task_kern *kit = (void *)it;
 
@@ -988,14 +988,17 @@ __bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it,
        switch (flags) {
        case BPF_TASK_ITER_ALL_THREADS:
        case BPF_TASK_ITER_ALL_PROCS:
+               break;
        case BPF_TASK_ITER_PROC_THREADS:
+               if (!task__nullable)
+                       return -EINVAL;
                break;
        default:
                return -EINVAL;
        }
 
        if (flags == BPF_TASK_ITER_PROC_THREADS)
-               kit->task = task;
+               kit->task = task__nullable;
        else
                kit->task = &init_task;
        kit->pos = kit->task;

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index fcdf2382153ac2aad59de1cd7224986b1973470e..e9bc5d4a25a176065fb4bee2723339ce6d794eee 100644 (file)
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -10332,6 +10332,11 @@ static bool is_kfunc_arg_refcounted_kptr(const struct btf *btf, const struct btf
        return __kfunc_param_match_suffix(btf, arg, "__refcounted_kptr");
 }
 
+static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param *arg)
+{
+       return __kfunc_param_match_suffix(btf, arg, "__nullable");
+}
+
 static bool is_kfunc_arg_scalar_with_name(const struct btf *btf,
                                          const struct btf_param *arg,
                                          const char *name)
@@ -10474,6 +10479,7 @@ enum kfunc_ptr_arg_type {
        KF_ARG_PTR_TO_CALLBACK,
        KF_ARG_PTR_TO_RB_ROOT,
        KF_ARG_PTR_TO_RB_NODE,
+       KF_ARG_PTR_TO_NULL,
 };
 
 enum special_kfunc_type {
@@ -10630,6 +10636,8 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
        if (is_kfunc_arg_callback(env, meta->btf, &args[argno]))
                return KF_ARG_PTR_TO_CALLBACK;
 
+       if (is_kfunc_arg_nullable(meta->btf, &args[argno]) && register_is_null(reg))
+               return KF_ARG_PTR_TO_NULL;
 
        if (argno + 1 < nargs &&
            (is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], &regs[regno + 1]) ||
@@ -11180,7 +11188,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
                }
 
                if ((is_kfunc_trusted_args(meta) || is_kfunc_rcu(meta)) &&
-                   (register_is_null(reg) || type_may_be_null(reg->type))) {
+                   (register_is_null(reg) || type_may_be_null(reg->type)) &&
+                       !is_kfunc_arg_nullable(meta->btf, &args[i])) {
                        verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i);
                        return -EACCES;
                }
@@ -11205,6 +11214,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
                        return kf_arg_type;
 
                switch (kf_arg_type) {
+               case KF_ARG_PTR_TO_NULL:
+                       continue;
                case KF_ARG_PTR_TO_ALLOC_BTF_ID:
                case KF_ARG_PTR_TO_BTF_ID:
                        if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta))