[PATCH sched_ext/for-6.13 1/2] sched_ext: Rename CFI stubs to names that are recognized by BPF

[PATCH sched_ext/for-6.13 1/2] sched_ext: Rename CFI stubs to names that are recognized by BPF

[Tejun Heo]

CFI stubs can be used to tag arguments with __nullable (and possibly other
tags in the future) but for that to work the CFI stubs must have names that
are recognized by BPF. Rename them.

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 |  132 ++++++++++++++++++++++++++---------------------------
 1 file changed, 66 insertions(+), 66 deletions(-)

--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -5634,78 +5634,78 @@ static int bpf_scx_validate(void *kdata)
 	return 0;
 }
 
-static s32 select_cpu_stub(struct task_struct *p, s32 prev_cpu, u64 wake_flags) { return -EINVAL; }
-static void enqueue_stub(struct task_struct *p, u64 enq_flags) {}
-static void dequeue_stub(struct task_struct *p, u64 enq_flags) {}
-static void dispatch_stub(s32 prev_cpu, struct task_struct *p) {}
-static void tick_stub(struct task_struct *p) {}
-static void runnable_stub(struct task_struct *p, u64 enq_flags) {}
-static void running_stub(struct task_struct *p) {}
-static void stopping_stub(struct task_struct *p, bool runnable) {}
-static void quiescent_stub(struct task_struct *p, u64 deq_flags) {}
-static bool yield_stub(struct task_struct *from, struct task_struct *to) { return false; }
-static bool core_sched_before_stub(struct task_struct *a, struct task_struct *b) { return false; }
-static void set_weight_stub(struct task_struct *p, u32 weight) {}
-static void set_cpumask_stub(struct task_struct *p, const struct cpumask *mask) {}
-static void update_idle_stub(s32 cpu, bool idle) {}
-static void cpu_acquire_stub(s32 cpu, struct scx_cpu_acquire_args *args) {}
-static void cpu_release_stub(s32 cpu, struct scx_cpu_release_args *args) {}
-static s32 init_task_stub(struct task_struct *p, struct scx_init_task_args *args) { return -EINVAL; }
-static void exit_task_stub(struct task_struct *p, struct scx_exit_task_args *args) {}
-static void enable_stub(struct task_struct *p) {}
-static void disable_stub(struct task_struct *p) {}
+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__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__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) {}
+static void sched_ext_ops__update_idle(s32 cpu, bool idle) {}
+static void sched_ext_ops__cpu_acquire(s32 cpu, struct scx_cpu_acquire_args *args) {}
+static void sched_ext_ops__cpu_release(s32 cpu, struct scx_cpu_release_args *args) {}
+static s32 sched_ext_ops__init_task(struct task_struct *p, struct scx_init_task_args *args) { return -EINVAL; }
+static void sched_ext_ops__exit_task(struct task_struct *p, struct scx_exit_task_args *args) {}
+static void sched_ext_ops__enable(struct task_struct *p) {}
+static void sched_ext_ops__disable(struct task_struct *p) {}
 #ifdef CONFIG_EXT_GROUP_SCHED
-static s32 cgroup_init_stub(struct cgroup *cgrp, struct scx_cgroup_init_args *args) { return -EINVAL; }
-static void cgroup_exit_stub(struct cgroup *cgrp) {}
-static s32 cgroup_prep_move_stub(struct task_struct *p, struct cgroup *from, struct cgroup *to) { return -EINVAL; }
-static void cgroup_move_stub(struct task_struct *p, struct cgroup *from, struct cgroup *to) {}
-static void cgroup_cancel_move_stub(struct task_struct *p, struct cgroup *from, struct cgroup *to) {}
-static void cgroup_set_weight_stub(struct cgroup *cgrp, u32 weight) {}
+static s32 sched_ext_ops__cgroup_init(struct cgroup *cgrp, struct scx_cgroup_init_args *args) { return -EINVAL; }
+static void sched_ext_ops__cgroup_exit(struct cgroup *cgrp) {}
+static s32 sched_ext_ops__cgroup_prep_move(struct task_struct *p, struct cgroup *from, struct cgroup *to) { return -EINVAL; }
+static void sched_ext_ops__cgroup_move(struct task_struct *p, struct cgroup *from, struct cgroup *to) {}
+static void sched_ext_ops__cgroup_cancel_move(struct task_struct *p, struct cgroup *from, struct cgroup *to) {}
+static void sched_ext_ops__cgroup_set_weight(struct cgroup *cgrp, u32 weight) {}
 #endif
-static void cpu_online_stub(s32 cpu) {}
-static void cpu_offline_stub(s32 cpu) {}
-static s32 init_stub(void) { return -EINVAL; }
-static void exit_stub(struct scx_exit_info *info) {}
-static void dump_stub(struct scx_dump_ctx *ctx) {}
-static void dump_cpu_stub(struct scx_dump_ctx *ctx, s32 cpu, bool idle) {}
-static void dump_task_stub(struct scx_dump_ctx *ctx, struct task_struct *p) {}
+static void sched_ext_ops__cpu_online(s32 cpu) {}
+static void sched_ext_ops__cpu_offline(s32 cpu) {}
+static s32 sched_ext_ops__init(void) { return -EINVAL; }
+static void sched_ext_ops__exit(struct scx_exit_info *info) {}
+static void sched_ext_ops__dump(struct scx_dump_ctx *ctx) {}
+static void sched_ext_ops__dump_cpu(struct scx_dump_ctx *ctx, s32 cpu, bool idle) {}
+static void sched_ext_ops__dump_task(struct scx_dump_ctx *ctx, struct task_struct *p) {}
 
 static struct sched_ext_ops __bpf_ops_sched_ext_ops = {
-	.select_cpu = select_cpu_stub,
-	.enqueue = enqueue_stub,
-	.dequeue = dequeue_stub,
-	.dispatch = dispatch_stub,
-	.tick = tick_stub,
-	.runnable = runnable_stub,
-	.running = running_stub,
-	.stopping = stopping_stub,
-	.quiescent = quiescent_stub,
-	.yield = yield_stub,
-	.core_sched_before = core_sched_before_stub,
-	.set_weight = set_weight_stub,
-	.set_cpumask = set_cpumask_stub,
-	.update_idle = update_idle_stub,
-	.cpu_acquire = cpu_acquire_stub,
-	.cpu_release = cpu_release_stub,
-	.init_task = init_task_stub,
-	.exit_task = exit_task_stub,
-	.enable = enable_stub,
-	.disable = disable_stub,
+	.select_cpu		= sched_ext_ops__select_cpu,
+	.enqueue		= sched_ext_ops__enqueue,
+	.dequeue		= sched_ext_ops__dequeue,
+	.dispatch		= sched_ext_ops__dispatch,
+	.tick			= sched_ext_ops__tick,
+	.runnable		= sched_ext_ops__runnable,
+	.running		= sched_ext_ops__running,
+	.stopping		= sched_ext_ops__stopping,
+	.quiescent		= sched_ext_ops__quiescent,
+	.yield			= sched_ext_ops__yield,
+	.core_sched_before	= sched_ext_ops__core_sched_before,
+	.set_weight		= sched_ext_ops__set_weight,
+	.set_cpumask		= sched_ext_ops__set_cpumask,
+	.update_idle		= sched_ext_ops__update_idle,
+	.cpu_acquire		= sched_ext_ops__cpu_acquire,
+	.cpu_release		= sched_ext_ops__cpu_release,
+	.init_task		= sched_ext_ops__init_task,
+	.exit_task		= sched_ext_ops__exit_task,
+	.enable			= sched_ext_ops__enable,
+	.disable		= sched_ext_ops__disable,
 #ifdef CONFIG_EXT_GROUP_SCHED
-	.cgroup_init = cgroup_init_stub,
-	.cgroup_exit = cgroup_exit_stub,
-	.cgroup_prep_move = cgroup_prep_move_stub,
-	.cgroup_move = cgroup_move_stub,
-	.cgroup_cancel_move = cgroup_cancel_move_stub,
-	.cgroup_set_weight = cgroup_set_weight_stub,
+	.cgroup_init		= sched_ext_ops__cgroup_init,
+	.cgroup_exit		= sched_ext_ops__cgroup_exit,
+	.cgroup_prep_move	= sched_ext_ops__cgroup_prep_move,
+	.cgroup_move		= sched_ext_ops__cgroup_move,
+	.cgroup_cancel_move	= sched_ext_ops__cgroup_cancel_move,
+	.cgroup_set_weight	= sched_ext_ops__cgroup_set_weight,
 #endif
-	.cpu_online = cpu_online_stub,
-	.cpu_offline = cpu_offline_stub,
-	.init = init_stub,
-	.exit = exit_stub,
-	.dump = dump_stub,
-	.dump_cpu = dump_cpu_stub,
-	.dump_task = dump_task_stub,
+	.cpu_online		= sched_ext_ops__cpu_online,
+	.cpu_offline		= sched_ext_ops__cpu_offline,
+	.init			= sched_ext_ops__init,
+	.exit			= sched_ext_ops__exit,
+	.dump			= sched_ext_ops__dump,
+	.dump_cpu		= sched_ext_ops__dump_cpu,
+	.dump_task		= sched_ext_ops__dump_task,
 };
 
 static struct bpf_struct_ops bpf_sched_ext_ops = {

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

[Tejun Heo]

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(-)

--- 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) {}

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

[Alexei Starovoitov]

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!

Re: [PATCH sched_ext/for-6.13 1/2] sched_ext: Rename CFI stubs to names that are recognized by BPF

[David Vernet]

[-- Attachment #1: Type: text/plain, Size: 2543 bytes --]

On Wed, Oct 23, 2024 at 02:54:41PM -1000, Tejun Heo wrote:
> CFI stubs can be used to tag arguments with __nullable (and possibly other
> tags in the future) but for that to work the CFI stubs must have names that
> are recognized by BPF. Rename them.
> 
> Signed-off-by: Tejun Heo <tj@kernel.org>

For both patches:

Acked-by: David Vernet <void@manifault.com>

Here's the selftest output for posterity / FYI:

[root@virtme-ng sched_ext]# ./runner -t maybe_null
===== START =====
TEST: maybe_null
DESCRIPTION: Verify if PTR_MAYBE_NULL work for .dispatch
OUTPUT:
libbpf: prog 'maybe_null_fail_dispatch': BPF program load failed: Permission denied
libbpf: prog 'maybe_null_fail_dispatch': -- BEGIN PROG LOAD LOG --
Global function maybe_null_fail_dispatch() doesn't return scalar. Only those are supported.
0: R1=ctx() R10=fp0
; void BPF_STRUCT_OPS(maybe_null_fail_dispatch, s32 cpu, struct task_struct *p) @ maybe_null_fail_dsp.bpf.c:15
0: (79) r1 = *(u64 *)(r1 +8)          ; R1_w=trusted_ptr_or_null_task_struct(id=1)
; vtime_test = p->scx.dsq_vtime; @ maybe_null_fail_dsp.bpf.c:17
1: (79) r1 = *(u64 *)(r1 +848)
R1 invalid mem access 'trusted_ptr_or_null_'
processed 2 insns (limit 1000000) max_states_per_insn 0 total_states 0 peak_states 0 mark_read 0
-- END PROG LOAD LOG --
libbpf: prog 'maybe_null_fail_dispatch': failed to load: -13
libbpf: failed to load object 'maybe_null_fail_dsp'
libbpf: failed to load BPF skeleton 'maybe_null_fail_dsp': -13
libbpf: prog 'maybe_null_fail_yield': BPF program load failed: Permission denied
libbpf: prog 'maybe_null_fail_yield': -- BEGIN PROG LOAD LOG --
0: R1=ctx() R10=fp0
; bool BPF_STRUCT_OPS(maybe_null_fail_yield, struct task_struct *from, @ maybe_null_fail_yld.bpf.c:15
0: (b7) r2 = 2328                     ; R2_w=2328
1: (79) r1 = *(u64 *)(r1 +8)          ; R1_w=trusted_ptr_or_null_task_struct(id=1)
2: (bf) r3 = r1                       ; R1_w=trusted_ptr_or_null_task_struct(id=1) R3_w=trusted_ptr_or_null_task_struct(id=1)
3: (0f) r3 += r2
R3 pointer arithmetic on trusted_ptr_or_null_ prohibited, null-check it first
processed 4 insns (limit 1000000) max_states_per_insn 0 total_states 0 peak_states 0 mark_read 0
-- END PROG LOAD LOG --
libbpf: prog 'maybe_null_fail_yield': failed to load: -13
libbpf: failed to load object 'maybe_null_fail_yld'
libbpf: failed to load BPF skeleton 'maybe_null_fail_yld': -13
ok 1 maybe_null #
=====  END  =====


=============================

RESULTS:

PASSED:  1
SKIPPED: 0
FAILED:  0


[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]

Re: [PATCH sched_ext/for-6.13 1/2] sched_ext: Rename CFI stubs to names that are recognized by BPF

[Martin KaFai Lau]

On 10/23/24 5:54 PM, Tejun Heo wrote:
> CFI stubs can be used to tag arguments with __nullable (and possibly other
> tags in the future) but for that to work the CFI stubs must have names that
> are recognized by BPF. Rename them.

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

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

[Martin KaFai Lau]

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>

Re: [PATCH sched_ext/for-6.13 1/2] sched_ext: Rename CFI stubs to names that are recognized by BPF

[Tejun Heo]

On Wed, Oct 23, 2024 at 02:54:41PM -1000, Tejun Heo wrote:
> CFI stubs can be used to tag arguments with __nullable (and possibly other
> tags in the future) but for that to work the CFI stubs must have names that
> are recognized by BPF. Rename them.
> 
> Signed-off-by: Tejun Heo <tj@kernel.org>
> Cc: Martin KaFai Lau <martin.lau@kernel.org>
> Cc: Alexei Starovoitov <ast@kernel.org>

Applied 1-2 to sched_ext/for-6.13.

Thanks.

-- 
tejun