[PATCH 3/3] sched_ext: Add SCX_OPS_ALWAYS_ENQ_IMMED ops flag

[Tejun Heo <tj@kernel.org>]

SCX_ENQ_IMMED makes enqueue to local DSQs succeed only if the task can start
running immediately. Otherwise, the task is re-enqueued through ops.enqueue().
This provides tighter control but requires specifying the flag on every
insertion.

Add SCX_OPS_ALWAYS_ENQ_IMMED ops flag. When set, SCX_ENQ_IMMED is
automatically applied to all local DSQ enqueues.

scx_qmap is updated with -I option to test the feature.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c                   | 29 ++++++++++++++++------------
 kernel/sched/ext_internal.h          |  7 +++++++
 tools/sched_ext/include/scx/compat.h |  1 +
 tools/sched_ext/scx_qmap.bpf.c       |  7 +++++--
 tools/sched_ext/scx_qmap.c           |  9 +++++++--
 5 files changed, 37 insertions(+), 16 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index eae8fc3e7b8a..a7ac4126e62f 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -7633,20 +7633,25 @@ void __init init_sched_ext_class(void)
 /********************************************************************************
  * Helpers that can be called from the BPF scheduler.
  */
-static bool scx_vet_enq_flags(struct scx_sched *sch, u64 dsq_id, u64 enq_flags)
+static bool scx_vet_enq_flags(struct scx_sched *sch, u64 dsq_id, u64 *enq_flags)
 {
-	if ((enq_flags & SCX_ENQ_IMMED) &&
-	    unlikely(dsq_id != SCX_DSQ_LOCAL &&
-		     (dsq_id & SCX_DSQ_LOCAL_ON) != SCX_DSQ_LOCAL_ON)) {
-		scx_error(sch, "SCX_ENQ_IMMED on a non-local DSQ 0x%llx", dsq_id);
-		return false;
+	bool is_local = dsq_id == SCX_DSQ_LOCAL ||
+		(dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON;
+
+	if (*enq_flags & SCX_ENQ_IMMED) {
+		if (unlikely(!is_local)) {
+			scx_error(sch, "SCX_ENQ_IMMED on a non-local DSQ 0x%llx", dsq_id);
+			return false;
+		}
+	} else if ((sch->ops.flags & SCX_OPS_ALWAYS_ENQ_IMMED) && is_local) {
+		*enq_flags |= SCX_ENQ_IMMED;
 	}
 
 	return true;
 }
 
 static bool scx_dsq_insert_preamble(struct scx_sched *sch, struct task_struct *p,
-				    u64 dsq_id, u64 enq_flags)
+				    u64 dsq_id, u64 *enq_flags)
 {
 	if (!scx_kf_allowed(sch, SCX_KF_ENQUEUE | SCX_KF_DISPATCH))
 		return false;
@@ -7658,8 +7663,8 @@ static bool scx_dsq_insert_preamble(struct scx_sched *sch, struct task_struct *p
 		return false;
 	}
 
-	if (unlikely(enq_flags & __SCX_ENQ_INTERNAL_MASK)) {
-		scx_error(sch, "invalid enq_flags 0x%llx", enq_flags);
+	if (unlikely(*enq_flags & __SCX_ENQ_INTERNAL_MASK)) {
+		scx_error(sch, "invalid enq_flags 0x%llx", *enq_flags);
 		return false;
 	}
 
@@ -7753,7 +7758,7 @@ __bpf_kfunc bool scx_bpf_dsq_insert___v2(struct task_struct *p, u64 dsq_id,
 	if (unlikely(!sch))
 		return false;
 
-	if (!scx_dsq_insert_preamble(sch, p, dsq_id, enq_flags))
+	if (!scx_dsq_insert_preamble(sch, p, dsq_id, &enq_flags))
 		return false;
 
 	if (slice)
@@ -7779,7 +7784,7 @@ __bpf_kfunc void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id,
 static bool scx_dsq_insert_vtime(struct scx_sched *sch, struct task_struct *p,
 				 u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags)
 {
-	if (!scx_dsq_insert_preamble(sch, p, dsq_id, enq_flags))
+	if (!scx_dsq_insert_preamble(sch, p, dsq_id, &enq_flags))
 		return false;
 
 	if (slice)
@@ -7906,7 +7911,7 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit,
 	    !scx_kf_allowed(sch, SCX_KF_DISPATCH))
 		return false;
 
-	if (!scx_vet_enq_flags(sch, dsq_id, enq_flags))
+	if (!scx_vet_enq_flags(sch, dsq_id, &enq_flags))
 		return false;
 
 	/*
diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index cd4272117be4..20142d101ddb 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -182,6 +182,12 @@ enum scx_ops_flags {
 	 */
 	SCX_OPS_BUILTIN_IDLE_PER_NODE	= 1LLU << 6,
 
+	/*
+	 * If set, %SCX_ENQ_IMMED is assumed to be set on all local DSQ
+	 * enqueues.
+	 */
+	SCX_OPS_ALWAYS_ENQ_IMMED	= 1LLU << 7,
+
 	/*
 	 * CPU cgroup support flags
 	 */
@@ -194,6 +200,7 @@ enum scx_ops_flags {
 					  SCX_OPS_ALLOW_QUEUED_WAKEUP |
 					  SCX_OPS_SWITCH_PARTIAL |
 					  SCX_OPS_BUILTIN_IDLE_PER_NODE |
+					  SCX_OPS_ALWAYS_ENQ_IMMED |
 					  SCX_OPS_HAS_CGROUP_WEIGHT,
 
 	/* high 8 bits are internal, don't include in SCX_OPS_ALL_FLAGS */
diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h
index 9b6df13b187b..fc4077b5a717 100644
--- a/tools/sched_ext/include/scx/compat.h
+++ b/tools/sched_ext/include/scx/compat.h
@@ -115,6 +115,7 @@ static inline bool __COMPAT_struct_has_field(const char *type, const char *field
 #define SCX_OPS_ENQ_MIGRATION_DISABLED SCX_OPS_FLAG(SCX_OPS_ENQ_MIGRATION_DISABLED)
 #define SCX_OPS_ALLOW_QUEUED_WAKEUP SCX_OPS_FLAG(SCX_OPS_ALLOW_QUEUED_WAKEUP)
 #define SCX_OPS_BUILTIN_IDLE_PER_NODE SCX_OPS_FLAG(SCX_OPS_BUILTIN_IDLE_PER_NODE)
+#define SCX_OPS_ALWAYS_ENQ_IMMED SCX_OPS_FLAG(SCX_OPS_ALWAYS_ENQ_IMMED)
 
 #define SCX_PICK_IDLE_FLAG(name) __COMPAT_ENUM_OR_ZERO("scx_pick_idle_cpu_flags", #name)
 
diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index a4a1b84fe359..dfd5ce222e39 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -47,6 +47,7 @@ const volatile bool print_msgs;
 const volatile u64 sub_cgroup_id;
 const volatile s32 disallow_tgid;
 const volatile bool suppress_dump;
+const volatile bool always_enq_immed;
 
 u64 nr_highpri_queued;
 u32 test_error_cnt;
@@ -144,8 +145,10 @@ static s32 pick_direct_dispatch_cpu(struct task_struct *p, s32 prev_cpu)
 {
 	s32 cpu;
 
-	if (p->nr_cpus_allowed == 1 ||
-	    scx_bpf_test_and_clear_cpu_idle(prev_cpu))
+	if (!always_enq_immed && p->nr_cpus_allowed == 1)
+		return prev_cpu;
+
+	if (scx_bpf_test_and_clear_cpu_idle(prev_cpu))
 		return prev_cpu;
 
 	cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c
index 9252037284d3..38b088bd44d5 100644
--- a/tools/sched_ext/scx_qmap.c
+++ b/tools/sched_ext/scx_qmap.c
@@ -21,7 +21,7 @@ const char help_fmt[] =
 "See the top-level comment in .bpf.c for more details.\n"
 "\n"
 "Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-l COUNT] [-b COUNT]\n"
-"       [-P] [-M] [-d PID] [-D LEN] [-p] [-v]\n"
+"       [-P] [-M] [-d PID] [-D LEN] [-p] [-I] [-v]\n"
 "\n"
 "  -s SLICE_US   Override slice duration\n"
 "  -e COUNT      Trigger scx_bpf_error() after COUNT enqueues\n"
@@ -36,6 +36,7 @@ const char help_fmt[] =
 "  -D LEN        Set scx_exit_info.dump buffer length\n"
 "  -S            Suppress qmap-specific debug dump\n"
 "  -p            Switch only tasks on SCHED_EXT policy instead of all\n"
+"  -I            Turn on SCX_OPS_ALWAYS_ENQ_IMMED\n"
 "  -v            Print libbpf debug messages\n"
 "  -h            Display this help and exit\n";
 
@@ -68,7 +69,7 @@ int main(int argc, char **argv)
 
 	skel->rodata->slice_ns = __COMPAT_ENUM_OR_ZERO("scx_public_consts", "SCX_SLICE_DFL");
 
-	while ((opt = getopt(argc, argv, "s:e:t:T:l:b:PMHc:d:D:Spvh")) != -1) {
+	while ((opt = getopt(argc, argv, "s:e:t:T:l:b:PMHc:d:D:SpIvh")) != -1) {
 		switch (opt) {
 		case 's':
 			skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;
@@ -121,6 +122,10 @@ int main(int argc, char **argv)
 		case 'p':
 			skel->struct_ops.qmap_ops->flags |= SCX_OPS_SWITCH_PARTIAL;
 			break;
+		case 'I':
+			skel->rodata->always_enq_immed = true;
+			skel->struct_ops.qmap_ops->flags |= SCX_OPS_ALWAYS_ENQ_IMMED;
+			break;
 		case 'v':
 			verbose = true;
 			break;
-- 
2.53.0