sched_ext: Allow BPF schedulers to disallow specific tasks from joining SCHED_EXT

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_qmap is updated with the -d option to disallow a specific PID:

  # echo $$
  1092
  # grep -E '(policy)|(ext\.enabled)' /proc/self/sched
  policy                                       :                    0
  ext.enabled                                  :                    0
  # ./set-scx 1092
  # grep -E '(policy)|(ext\.enabled)' /proc/self/sched
  policy                                       :                    7
  ext.enabled                                  :                    0

Run "scx_qmap -p -d 1092" in another terminal.

  # cat /sys/kernel/sched_ext/nr_rejected
  1
  # grep -E '(policy)|(ext\.enabled)' /proc/self/sched
  policy                                       :                    0
  ext.enabled                                  :                    0
  # ./set-scx 1092
  setparam failed for 1092 (Permission denied)

- v4: Refreshed on top of tip:sched/core.

- v3: Update description to reflect /sys/kernel/sched_ext interface change.

- v2: Use atomic_long_t instead of atomic64_t for scx_kick_cpus_pnt_seqs to
      accommodate 32bit archs.

Signed-off-by: Tejun Heo <tj@kernel.org>
Suggested-by: Barret Rhoden <brho@google.com>
Reviewed-by: David Vernet <dvernet@meta.com>
Acked-by: Josh Don <joshdon@google.com>
Acked-by: Hao Luo <haoluo@google.com>
Acked-by: Barret Rhoden <brho@google.com>

2 files changed, 13 insertions, 2 deletions

diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index 8beae08dfdc7..5ff217c4bfa0 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -32,6 +32,7 @@ const volatile u64 slice_ns = SCX_SLICE_DFL;
 const volatile u32 stall_user_nth;
 const volatile u32 stall_kernel_nth;
 const volatile u32 dsp_batch;
+const volatile s32 disallow_tgid;
 
 u32 test_error_cnt;
 
@@ -243,6 +244,9 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev)
 s32 BPF_STRUCT_OPS(qmap_init_task, struct task_struct *p,
 		   struct scx_init_task_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_qmap.c b/tools/sched_ext/scx_qmap.c
index 6e9e9726cd62..a2614994cfaa 100644
--- a/tools/sched_ext/scx_qmap.c
+++ b/tools/sched_ext/scx_qmap.c
@@ -19,13 +19,15 @@ 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] [-b COUNT] [-p] [-v]\n"
+"Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-b COUNT]\n"
+"       [-d PID] [-p] [-v]\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"
 "  -b COUNT      Dispatch upto COUNT tasks together\n"
+"  -d PID        Disallow a process from switching into SCHED_EXT (-1 for self)\n"
 "  -p            Switch only tasks on SCHED_EXT policy intead of all\n"
 "  -v            Print libbpf debug messages\n"
 "  -h            Display this help and exit\n";
@@ -57,7 +59,7 @@ int main(int argc, char **argv)
 
 	skel = SCX_OPS_OPEN(qmap_ops, scx_qmap);
 
-	while ((opt = getopt(argc, argv, "s:e:t:T:b:pvh")) != -1) {
+	while ((opt = getopt(argc, argv, "s:e:t:T:b:d:pvh")) != -1) {
 		switch (opt) {
 		case 's':
 			skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;
@@ -74,6 +76,11 @@ int main(int argc, char **argv)
 		case 'b':
 			skel->rodata->dsp_batch = 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;
 		case 'p':
 			skel->struct_ops.qmap_ops->flags |= SCX_OPS_SWITCH_PARTIAL;
 			break;