diff mbox series

[sched_ext/for-6.13,2/2] sched_ext: Replace set_arg_maybe_null() with __nullable CFI stub tags

Message ID Zxma-ZFPKYZDqCGu@slm.duckdns.org (mailing list archive)
State Not Applicable
Delegated to: BPF
Headers show
Series [sched_ext/for-6.13,1/2] sched_ext: Rename CFI stubs to names that are recognized by BPF | expand

Checks

Context Check Description
netdev/tree_selection success Not a local patch, async

Commit Message

Tejun Heo Oct. 24, 2024, 12:55 a.m. UTC
ops.dispatch() and ops.yield() may be fed a NULL task_struct pointer.
set_arg_maybe_null() is used to tell the verifier that they should be NULL
checked before being dereferenced. BPF now has an a lot prettier way to
express this - tagging arguments in CFI stubs with __nullable. Replace
set_arg_maybe_null() with __nullable CFI stub tags.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Martin KaFai Lau <martin.lau@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
---
 kernel/sched/ext.c |   66 +----------------------------------------------------
 1 file changed, 2 insertions(+), 64 deletions(-)

Comments

Alexei Starovoitov Oct. 24, 2024, 1:04 a.m. UTC | #1
On Wed, Oct 23, 2024 at 5:55 PM Tejun Heo <tj@kernel.org> wrote:
>
> ops.dispatch() and ops.yield() may be fed a NULL task_struct pointer.
> set_arg_maybe_null() is used to tell the verifier that they should be NULL
> checked before being dereferenced. BPF now has an a lot prettier way to
> express this - tagging arguments in CFI stubs with __nullable. Replace
> set_arg_maybe_null() with __nullable CFI stub tags.
>
> Signed-off-by: Tejun Heo <tj@kernel.org>
> Cc: Martin KaFai Lau <martin.lau@kernel.org>
> Cc: Alexei Starovoitov <ast@kernel.org>

for this and 1st patch:
Acked-by: Alexei Starovoitov <ast@kernel.org>

Nice cleanup!
Martin KaFai Lau Oct. 24, 2024, 4:19 p.m. UTC | #2
On 10/23/24 5:55 PM, Tejun Heo wrote:
> ops.dispatch() and ops.yield() may be fed a NULL task_struct pointer.
> set_arg_maybe_null() is used to tell the verifier that they should be NULL
> checked before being dereferenced. BPF now has an a lot prettier way to
> express this - tagging arguments in CFI stubs with __nullable. Replace
> set_arg_maybe_null() with __nullable CFI stub tags.

Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
diff mbox series

Patch

--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -5407,67 +5407,8 @@  err_disable:
 #include <linux/bpf.h>
 #include <linux/btf.h>
 
-extern struct btf *btf_vmlinux;
 static const struct btf_type *task_struct_type;
 
-static bool set_arg_maybe_null(const char *op, int arg_n, int off, int size,
-			       enum bpf_access_type type,
-			       const struct bpf_prog *prog,
-			       struct bpf_insn_access_aux *info)
-{
-	struct btf *btf = bpf_get_btf_vmlinux();
-	const struct bpf_struct_ops_desc *st_ops_desc;
-	const struct btf_member *member;
-	const struct btf_type *t;
-	u32 btf_id, member_idx;
-	const char *mname;
-
-	/* struct_ops op args are all sequential, 64-bit numbers */
-	if (off != arg_n * sizeof(__u64))
-		return false;
-
-	/* btf_id should be the type id of struct sched_ext_ops */
-	btf_id = prog->aux->attach_btf_id;
-	st_ops_desc = bpf_struct_ops_find(btf, btf_id);
-	if (!st_ops_desc)
-		return false;
-
-	/* BTF type of struct sched_ext_ops */
-	t = st_ops_desc->type;
-
-	member_idx = prog->expected_attach_type;
-	if (member_idx >= btf_type_vlen(t))
-		return false;
-
-	/*
-	 * Get the member name of this struct_ops program, which corresponds to
-	 * a field in struct sched_ext_ops. For example, the member name of the
-	 * dispatch struct_ops program (callback) is "dispatch".
-	 */
-	member = &btf_type_member(t)[member_idx];
-	mname = btf_name_by_offset(btf_vmlinux, member->name_off);
-
-	if (!strcmp(mname, op)) {
-		/*
-		 * The value is a pointer to a type (struct task_struct) given
-		 * by a BTF ID (PTR_TO_BTF_ID). It is trusted (PTR_TRUSTED),
-		 * however, can be a NULL (PTR_MAYBE_NULL). The BPF program
-		 * should check the pointer to make sure it is not NULL before
-		 * using it, or the verifier will reject the program.
-		 *
-		 * Longer term, this is something that should be addressed by
-		 * BTF, and be fully contained within the verifier.
-		 */
-		info->reg_type = PTR_MAYBE_NULL | PTR_TO_BTF_ID | PTR_TRUSTED;
-		info->btf = btf_vmlinux;
-		info->btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK];
-
-		return true;
-	}
-
-	return false;
-}
-
 static bool bpf_scx_is_valid_access(int off, int size,
 				    enum bpf_access_type type,
 				    const struct bpf_prog *prog,
@@ -5475,9 +5416,6 @@  static bool bpf_scx_is_valid_access(int
 {
 	if (type != BPF_READ)
 		return false;
-	if (set_arg_maybe_null("dispatch", 1, off, size, type, prog, info) ||
-	    set_arg_maybe_null("yield", 1, off, size, type, prog, info))
-		return true;
 	if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS)
 		return false;
 	if (off % size != 0)
@@ -5637,13 +5575,13 @@  static int bpf_scx_validate(void *kdata)
 static s32 sched_ext_ops__select_cpu(struct task_struct *p, s32 prev_cpu, u64 wake_flags) { return -EINVAL; }
 static void sched_ext_ops__enqueue(struct task_struct *p, u64 enq_flags) {}
 static void sched_ext_ops__dequeue(struct task_struct *p, u64 enq_flags) {}
-static void sched_ext_ops__dispatch(s32 prev_cpu, struct task_struct *p) {}
+static void sched_ext_ops__dispatch(s32 prev_cpu, struct task_struct *prev__nullable) {}
 static void sched_ext_ops__tick(struct task_struct *p) {}
 static void sched_ext_ops__runnable(struct task_struct *p, u64 enq_flags) {}
 static void sched_ext_ops__running(struct task_struct *p) {}
 static void sched_ext_ops__stopping(struct task_struct *p, bool runnable) {}
 static void sched_ext_ops__quiescent(struct task_struct *p, u64 deq_flags) {}
-static bool sched_ext_ops__yield(struct task_struct *from, struct task_struct *to) { return false; }
+static bool sched_ext_ops__yield(struct task_struct *from, struct task_struct *to__nullable) { return false; }
 static bool sched_ext_ops__core_sched_before(struct task_struct *a, struct task_struct *b) { return false; }
 static void sched_ext_ops__set_weight(struct task_struct *p, u32 weight) {}
 static void sched_ext_ops__set_cpumask(struct task_struct *p, const struct cpumask *mask) {}