[PATCH 19/31] sched_ext: Allow BPF schedulers to disallow specific tasks from joining SCHED_EXT
From: Tejun Heo
Date: Wed Nov 30 2022 - 03:26:30 EST
BPF schedulers might not want to schedule certain tasks - e.g. kernel
threads. This patch adds p->scx.disallow which can be set by BPF schedulers
in such cases. The field can be changed anytime and setting it in
ops.prep_enable() guarantees that the task can never be scheduled by
sched_ext.
scx_example_qmap is updated with the -d option to disallow a specific PID:
# echo $$
1092
# egrep '(policy)|(ext\.enabled)' /proc/self/sched
policy : 0
ext.enabled : 0
# ./set-scx 1092
# egrep '(policy)|(ext\.enabled)' /proc/self/sched
policy : 7
ext.enabled : 0
Run "scx_example_qmap -d 1092" in another terminal.
# grep rejected /sys/kernel/debug/sched/ext
nr_rejected : 1
# egrep '(policy)|(ext\.enabled)' /proc/self/sched
policy : 0
ext.enabled : 0
# ./set-scx 1092
setparam failed for 1092 (Permission denied)
Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Suggested-by: Barret Rhoden <brho@xxxxxxxxxx>
Reviewed-by: David Vernet <dvernet@xxxxxxxx>
Acked-by: Josh Don <joshdon@xxxxxxxxxx>
Acked-by: Hao Luo <haoluo@xxxxxxxxxx>
Acked-by: Barret Rhoden <brho@xxxxxxxxxx>
---
include/linux/sched/ext.h | 12 ++++++++
kernel/sched/core.c | 4 +++
kernel/sched/ext.c | 38 ++++++++++++++++++++++++++
kernel/sched/ext.h | 3 ++
tools/sched_ext/scx_example_qmap.bpf.c | 4 +++
tools/sched_ext/scx_example_qmap.c | 8 +++++-
6 files changed, 68 insertions(+), 1 deletion(-)
diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index 1a57945abea0..82dcbecfcfb9 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -397,6 +397,18 @@ struct sched_ext_entity {
*/
u64 slice;
+ /*
+ * If set, reject future sched_setscheduler(2) calls updating the policy
+ * to %SCHED_EXT with -%EACCES.
+ *
+ * If set from ops.prep_enable() and the task's policy is already
+ * %SCHED_EXT, which can happen while the BPF scheduler is being loaded
+ * or by inhering the parent's policy during fork, the task's policy is
+ * rejected and forcefully reverted to %SCHED_NORMAL. The number of such
+ * events are reported through /sys/kernel/debug/sched_ext::nr_rejected.
+ */
+ bool disallow; /* reject switching into SCX */
+
/* cold fields */
struct list_head tasks_node;
};
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 39d9ccb64f40..3404277fed30 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7552,6 +7552,10 @@ static int __sched_setscheduler(struct task_struct *p,
goto unlock;
}
+ retval = scx_check_setscheduler(p, policy);
+ if (retval)
+ goto unlock;
+
/*
* If not changing anything there's no need to proceed further,
* but store a possible modification of reset_on_fork.
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 030175f2b1d6..ddd5aa4a8bca 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1509,6 +1509,8 @@ static int scx_ops_prepare_task(struct task_struct *p, struct task_group *tg)
WARN_ON_ONCE(p->scx.flags & SCX_TASK_OPS_PREPPED);
+ p->scx.disallow = false;
+
if (SCX_HAS_OP(prep_enable)) {
struct scx_enable_args args = { };
@@ -1519,6 +1521,27 @@ static int scx_ops_prepare_task(struct task_struct *p, struct task_group *tg)
}
}
+ if (p->scx.disallow) {
+ struct rq *rq;
+ struct rq_flags rf;
+
+ rq = task_rq_lock(p, &rf);
+
+ /*
+ * We're either in fork or load path and @p->policy will be
+ * applied right after. Reverting @p->policy here and rejecting
+ * %SCHED_EXT transitions from scx_check_setscheduler()
+ * guarantees that if ops.prep_enable() sets @p->disallow, @p
+ * can never be in SCX.
+ */
+ if (p->policy == SCHED_EXT) {
+ p->policy = SCHED_NORMAL;
+ atomic64_inc(&scx_nr_rejected);
+ }
+
+ task_rq_unlock(rq, p, &rf);
+ }
+
p->scx.flags |= (SCX_TASK_OPS_PREPPED | SCX_TASK_WATCHDOG_RESET);
return 0;
}
@@ -1664,6 +1687,18 @@ static void switching_to_scx(struct rq *rq, struct task_struct *p)
static void check_preempt_curr_scx(struct rq *rq, struct task_struct *p,int wake_flags) {}
static void switched_to_scx(struct rq *rq, struct task_struct *p) {}
+int scx_check_setscheduler(struct task_struct *p, int policy)
+{
+ lockdep_assert_rq_held(task_rq(p));
+
+ /* if disallow, reject transitioning into SCX */
+ if (scx_enabled() && READ_ONCE(p->scx.disallow) &&
+ p->policy != policy && policy == SCHED_EXT)
+ return -EACCES;
+
+ return 0;
+}
+
/*
* Omitted operations:
*
@@ -2367,6 +2402,9 @@ static int bpf_scx_btf_struct_access(struct bpf_verifier_log *log,
if (off >= offsetof(struct task_struct, scx.slice) &&
off + size <= offsetofend(struct task_struct, scx.slice))
return SCALAR_VALUE;
+ if (off >= offsetof(struct task_struct, scx.disallow) &&
+ off + size <= offsetofend(struct task_struct, scx.disallow))
+ return SCALAR_VALUE;
}
if (atype == BPF_READ)
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
index bda1d9c11486..0743a0536560 100644
--- a/kernel/sched/ext.h
+++ b/kernel/sched/ext.h
@@ -79,6 +79,7 @@ int scx_fork(struct task_struct *p);
void scx_post_fork(struct task_struct *p);
void scx_cancel_fork(struct task_struct *p);
int balance_scx(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
+int scx_check_setscheduler(struct task_struct *p, int policy);
void init_sched_ext_class(void);
__printf(2, 3) void scx_ops_error_type(enum scx_exit_type type,
@@ -136,6 +137,8 @@ static inline void scx_post_fork(struct task_struct *p) {}
static inline void scx_cancel_fork(struct task_struct *p) {}
static inline int balance_scx(struct rq *rq, struct task_struct *prev,
struct rq_flags *rf) { return 0; }
+static inline int scx_check_setscheduler(struct task_struct *p,
+ int policy) { return 0; }
static inline void init_sched_ext_class(void) {}
static inline void scx_notify_sched_tick(void) {}
diff --git a/tools/sched_ext/scx_example_qmap.bpf.c b/tools/sched_ext/scx_example_qmap.bpf.c
index 9e0b6519c8a4..b6febc5dadbf 100644
--- a/tools/sched_ext/scx_example_qmap.bpf.c
+++ b/tools/sched_ext/scx_example_qmap.bpf.c
@@ -24,6 +24,7 @@ char _license[] SEC("license") = "GPL";
const volatile u64 slice_ns = SCX_SLICE_DFL;
const volatile u32 stall_user_nth;
const volatile u32 stall_kernel_nth;
+const volatile s32 disallow_tgid;
u32 test_error_cnt;
@@ -208,6 +209,9 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev)
s32 BPF_STRUCT_OPS(qmap_prep_enable, struct task_struct *p,
struct scx_enable_args *args)
{
+ if (p->tgid == disallow_tgid)
+ p->scx.disallow = true;
+
/*
* @p is new. Let's ensure that its task_ctx is available. We can sleep
* in this function and the following will automatically use GFP_KERNEL.
diff --git a/tools/sched_ext/scx_example_qmap.c b/tools/sched_ext/scx_example_qmap.c
index 34c764c38e19..99cc7169bd90 100644
--- a/tools/sched_ext/scx_example_qmap.c
+++ b/tools/sched_ext/scx_example_qmap.c
@@ -20,12 +20,13 @@ const char help_fmt[] =
"\n"
"See the top-level comment in .bpf.c for more details.\n"
"\n"
-"Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT]\n"
+"Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-d PID]\n"
"\n"
" -s SLICE_US Override slice duration\n"
" -e COUNT Trigger scx_bpf_error() after COUNT enqueues\n"
" -t COUNT Stall every COUNT'th user thread\n"
" -T COUNT Stall every COUNT'th kernel thread\n"
+" -d PID Disallow a process from switching into SCHED_EXT (-1 for self)\n"
" -h Display this help and exit\n";
static volatile int exit_req;
@@ -63,6 +64,11 @@ int main(int argc, char **argv)
case 'T':
skel->rodata->stall_kernel_nth = strtoul(optarg, NULL, 0);
break;
+ case 'd':
+ skel->rodata->disallow_tgid = strtol(optarg, NULL, 0);
+ if (skel->rodata->disallow_tgid < 0)
+ skel->rodata->disallow_tgid = getpid();
+ break;
default:
fprintf(stderr, help_fmt, basename(argv[0]));
return opt != 'h';
--
2.38.1