3 files changed, 78 insertions, 24 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 8b32376ce746..c9eafa67f2a2 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -543,6 +543,35 @@ enum bpf_type_flag {
 	 */
 	MEM_ALLOC		= BIT(11 + BPF_BASE_TYPE_BITS),
 
+	/* PTR was passed from the kernel in a trusted context, and may be
+	 * passed to KF_TRUSTED_ARGS kfuncs or BPF helper functions.
+	 * Confusingly, this is _not_ the opposite of PTR_UNTRUSTED above.
+	 * PTR_UNTRUSTED refers to a kptr that was read directly from a map
+	 * without invoking bpf_kptr_xchg(). What we really need to know is
+	 * whether a pointer is safe to pass to a kfunc or BPF helper function.
+	 * While PTR_UNTRUSTED pointers are unsafe to pass to kfuncs and BPF
+	 * helpers, they do not cover all possible instances of unsafe
+	 * pointers. For example, a pointer that was obtained from walking a
+	 * struct will _not_ get the PTR_UNTRUSTED type modifier, despite the
+	 * fact that it may be NULL, invalid, etc. This is due to backwards
+	 * compatibility requirements, as this was the behavior that was first
+	 * introduced when kptrs were added. The behavior is now considered
+	 * deprecated, and PTR_UNTRUSTED will eventually be removed.
+	 *
+	 * PTR_TRUSTED, on the other hand, is a pointer that the kernel
+	 * guarantees to be valid and safe to pass to kfuncs and BPF helpers.
+	 * For example, pointers passed to tracepoint arguments are considered
+	 * PTR_TRUSTED, as are pointers that are passed to struct_ops
+	 * callbacks. As alluded to above, pointers that are obtained from
+	 * walking PTR_TRUSTED pointers are _not_ trusted. For example, if a
+	 * struct task_struct *task is PTR_TRUSTED, then accessing
+	 * task->last_wakee will lose the PTR_TRUSTED modifier when it's stored
+	 * in a BPF register. Similarly, pointers passed to certain programs
+	 * types such as kretprobes are not guaranteed to be valid, as they may
+	 * for example contain an object that was recently freed.
+	 */
+	PTR_TRUSTED		= BIT(12 + BPF_BASE_TYPE_BITS),
+
 	__BPF_TYPE_FLAG_MAX,
 	__BPF_TYPE_LAST_FLAG	= __BPF_TYPE_FLAG_MAX - 1,
 };
@@ -636,6 +665,7 @@ enum bpf_return_type {
 	RET_PTR_TO_RINGBUF_MEM_OR_NULL	= PTR_MAYBE_NULL | MEM_RINGBUF | RET_PTR_TO_MEM,
 	RET_PTR_TO_DYNPTR_MEM_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_MEM,
 	RET_PTR_TO_BTF_ID_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID,
+	RET_PTR_TO_BTF_ID_TRUSTED	= PTR_TRUSTED	 | RET_PTR_TO_BTF_ID,
 
 	/* This must be the last entry. Its purpose is to ensure the enum is
 	 * wide enough to hold the higher bits reserved for bpf_type_flag.
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 608dde740fef..545152ac136c 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -680,4 +680,11 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog)
 	}
 }
 
+#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED)
+
+static inline bool bpf_type_has_unsafe_modifiers(u32 type)
+{
+	return type_flag(type) & ~BPF_REG_TRUSTED_MODIFIERS;
+}
+
 #endif /* _LINUX_BPF_VERIFIER_H */
diff --git a/include/linux/btf.h b/include/linux/btf.h
index d5b26380a60f..d38aa4251c28 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -19,36 +19,53 @@
 #define KF_RELEASE	(1 << 1) /* kfunc is a release function */
 #define KF_RET_NULL	(1 << 2) /* kfunc returns a pointer that may be NULL */
 #define KF_KPTR_GET	(1 << 3) /* kfunc returns reference to a kptr */
-/* Trusted arguments are those which are meant to be referenced arguments with
- * unchanged offset. It is used to enforce that pointers obtained from acquire
- * kfuncs remain unmodified when being passed to helpers taking trusted args.
+/* Trusted arguments are those which are guaranteed to be valid when passed to
+ * the kfunc. It is used to enforce that pointers obtained from either acquire
+ * kfuncs, or from the main kernel on a tracepoint or struct_ops callback
+ * invocation, remain unmodified when being passed to helpers taking trusted
+ * args.
  *
- * Consider
- *	struct foo {
- *		int data;
- *		struct foo *next;
- *	};
+ * Consider, for example, the following new task tracepoint:
  *
- *	struct bar {
- *		int data;
- *		struct foo f;
- *	};
+ *	SEC("tp_btf/task_newtask")
+ *	int BPF_PROG(new_task_tp, struct task_struct *task, u64 clone_flags)
+ *	{
+ *		...
+ *	}
  *
- *	struct foo *f = alloc_foo(); // Acquire kfunc
- *	struct bar *b = alloc_bar(); // Acquire kfunc
+ * And the following kfunc:
  *
- * If a kfunc set_foo_data() wants to operate only on the allocated object, it
- * will set the KF_TRUSTED_ARGS flag, which will prevent unsafe usage like:
+ *	BTF_ID_FLAGS(func, bpf_task_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS)
  *
- *	set_foo_data(f, 42);	   // Allowed
- *	set_foo_data(f->next, 42); // Rejected, non-referenced pointer
- *	set_foo_data(&f->next, 42);// Rejected, referenced, but wrong type
- *	set_foo_data(&b->f, 42);   // Rejected, referenced, but bad offset
+ * All invocations to the kfunc must pass the unmodified, unwalked task:
  *
- * In the final case, usually for the purposes of type matching, it is deduced
- * by looking at the type of the member at the offset, but due to the
- * requirement of trusted argument, this deduction will be strict and not done
- * for this case.
+ *	bpf_task_acquire(task);		    // Allowed
+ *	bpf_task_acquire(task->last_wakee); // Rejected, walked task
+ *
+ * Programs may also pass referenced tasks directly to the kfunc:
+ *
+ *	struct task_struct *acquired;
+ *
+ *	acquired = bpf_task_acquire(task);	// Allowed, same as above
+ *	bpf_task_acquire(acquired);		// Allowed
+ *	bpf_task_acquire(task);			// Allowed
+ *	bpf_task_acquire(acquired->last_wakee); // Rejected, walked task
+ *
+ * Programs may _not_, however, pass a task from an arbitrary fentry/fexit, or
+ * kprobe/kretprobe to the kfunc, as BPF cannot guarantee that all of these
+ * pointers are guaranteed to be safe. For example, the following BPF program
+ * would be rejected:
+ *
+ * SEC("kretprobe/free_task")
+ * int BPF_PROG(free_task_probe, struct task_struct *tsk)
+ * {
+ *	struct task_struct *acquired;
+ *
+ *	acquired = bpf_task_acquire(acquired); // Rejected, not a trusted pointer
+ *	bpf_task_release(acquired);
+ *
+ *	return 0;
+ * }
  */
 #define KF_TRUSTED_ARGS (1 << 4) /* kfunc only takes trusted pointer arguments */
 #define KF_SLEEPABLE    (1 << 5) /* kfunc may sleep */