Merge tag 'sched_ext-for-6.13-rc5-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext

torvalds · torvalds · commit 63676eefb7a0 · 2025-01-03T15:09:12.000-08:00
Pull sched_ext fixes from Tejun Heo:

 - Fix a bug where bpf_iter_scx_dsq_new() was not initializing the
   iterator's flags and could inadvertently enable e.g. reverse
   iteration

 - Fix a bug where scx_ops_bypass() could call irq_restore twice

 - Add Andrea and Changwoo as maintainers for better review coverage

 - selftests and tools/sched_ext build and other fixes

* tag 'sched_ext-for-6.13-rc5-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext:
  sched_ext: Fix dsq_local_on selftest
  sched_ext: initialize kit-&gt;cursor.flags
  sched_ext: Fix invalid irq restore in scx_ops_bypass()
  MAINTAINERS: add me as reviewer for sched_ext
  MAINTAINERS: add self as reviewer for sched_ext
  scx: Fix maximal BPF selftest prog
  sched_ext: fix application of sizeof to pointer
  selftests/sched_ext: fix build after renames in sched_ext API
  sched_ext: Add __weak to fix the build errors
diff --git a/MAINTAINERS b/MAINTAINERS
@@ -20907,6 +20907,8 @@ F:	kernel/sched/
 SCHEDULER - SCHED_EXT
 R:	Tejun Heo <tj@kernel.org>
 R:	David Vernet <void@manifault.com>
+R:	Andrea Righi <arighi@nvidia.com>
+R:	Changwoo Min <changwoo@igalia.com>
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 W:	https://github.com/sched-ext/scx
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
@@ -4763,7 +4763,7 @@ static void scx_ops_bypass(bool bypass)
 		 * sees scx_rq_bypassing() before moving tasks to SCX.
 		 */
 		if (!scx_enabled()) {
-			rq_unlock_irqrestore(rq, &rf);
+			rq_unlock(rq, &rf);
 			continue;
 		}
 
@@ -7013,7 +7013,7 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id,
 		return -ENOENT;
 
 	INIT_LIST_HEAD(&kit->cursor.node);
-	kit->cursor.flags |= SCX_DSQ_LNODE_ITER_CURSOR | flags;
+	kit->cursor.flags = SCX_DSQ_LNODE_ITER_CURSOR | flags;
 	kit->cursor.priv = READ_ONCE(kit->dsq->seq);
 
 	return 0;
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
@@ -40,9 +40,9 @@ void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_fl
 void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym __weak;
 u32 scx_bpf_dispatch_nr_slots(void) __ksym;
 void scx_bpf_dispatch_cancel(void) __ksym;
-bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym;
-void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym;
-void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym;
+bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym __weak;
+void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym __weak;
+void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym __weak;
 bool scx_bpf_dsq_move(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
 bool scx_bpf_dsq_move_vtime(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
 u32 scx_bpf_reenqueue_local(void) __ksym;
diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c
@@ -97,7 +97,7 @@ int main(int argc, char **argv)
 	SCX_BUG_ON(!cpuset, "Failed to allocate cpuset");
 	CPU_ZERO(cpuset);
 	CPU_SET(skel->rodata->central_cpu, cpuset);
-	SCX_BUG_ON(sched_setaffinity(0, sizeof(cpuset), cpuset),
+	SCX_BUG_ON(sched_setaffinity(0, sizeof(*cpuset), cpuset),
 		   "Failed to affinitize to central CPU %d (max %d)",
 		   skel->rodata->central_cpu, skel->rodata->nr_cpu_ids - 1);
 	CPU_FREE(cpuset);
diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
@@ -20,7 +20,7 @@ s32 BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_select_cpu, struct task_struct *p,
 		 * If we dispatch to a bogus DSQ that will fall back to the
 		 * builtin global DSQ, we fail gracefully.
 		 */
-		scx_bpf_dispatch_vtime(p, 0xcafef00d, SCX_SLICE_DFL,
+		scx_bpf_dsq_insert_vtime(p, 0xcafef00d, SCX_SLICE_DFL,
 				       p->scx.dsq_vtime, 0);
 		return cpu;
 	}
diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
@@ -17,8 +17,8 @@ s32 BPF_STRUCT_OPS(ddsp_vtimelocal_fail_select_cpu, struct task_struct *p,
 
 	if (cpu >= 0) {
 		/* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */
-		scx_bpf_dispatch_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL,
-				       p->scx.dsq_vtime, 0);
+		scx_bpf_dsq_insert_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL,
+					 p->scx.dsq_vtime, 0);
 		return cpu;
 	}
 
diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
@@ -43,9 +43,12 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev)
 	if (!p)
 		return;
 
-	target = bpf_get_prandom_u32() % nr_cpus;
+	if (p->nr_cpus_allowed == nr_cpus)
+		target = bpf_get_prandom_u32() % nr_cpus;
+	else
+		target = scx_bpf_task_cpu(p);
 
-	scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0);
+	scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0);
 	bpf_task_release(p);
 }
 
diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.c b/tools/testing/selftests/sched_ext/dsp_local_on.c
@@ -34,9 +34,10 @@ static enum scx_test_status run(void *ctx)
 	/* Just sleeping is fine, plenty of scheduling events happening */
 	sleep(1);
 
-	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR));
 	bpf_link__destroy(link);
 
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG));
+
 	return SCX_TEST_PASS;
 }
 
@@ -50,7 +51,7 @@ static void cleanup(void *ctx)
 struct scx_test dsp_local_on = {
 	.name = "dsp_local_on",
 	.description = "Verify we can directly dispatch tasks to a local DSQs "
-		       "from osp.dispatch()",
+		       "from ops.dispatch()",
 	.setup = setup,
 	.run = run,
 	.cleanup = cleanup,
diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
@@ -31,7 +31,7 @@ void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p,
 	/* Can only call from ops.select_cpu() */
 	scx_bpf_select_cpu_dfl(p, 0, 0, &found);
 
-	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
 }
 
 SEC(".struct_ops.link")
diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c
@@ -33,15 +33,15 @@ void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags)
 	if (exit_point == EXIT_ENQUEUE)
 		EXIT_CLEANLY();
 
-	scx_bpf_dispatch(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);
+	scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);
 }
 
 void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p)
 {
 	if (exit_point == EXIT_DISPATCH)
 		EXIT_CLEANLY();
 
-	scx_bpf_consume(DSQ_ID);
+	scx_bpf_dsq_move_to_local(DSQ_ID);
 }
 
 void BPF_STRUCT_OPS(exit_enable, struct task_struct *p)
diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c
@@ -12,6 +12,8 @@
 
 char _license[] SEC("license") = "GPL";
 
+#define DSQ_ID 0
+
 s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu,
 		   u64 wake_flags)
 {
@@ -20,15 +22,15 @@ s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu,
 
 void BPF_STRUCT_OPS(maximal_enqueue, struct task_struct *p, u64 enq_flags)
 {
-	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+	scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);
 }
 
 void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags)
 {}
 
 void BPF_STRUCT_OPS(maximal_dispatch, s32 cpu, struct task_struct *prev)
 {
-	scx_bpf_consume(SCX_DSQ_GLOBAL);
+	scx_bpf_dsq_move_to_local(DSQ_ID);
 }
 
 void BPF_STRUCT_OPS(maximal_runnable, struct task_struct *p, u64 enq_flags)
@@ -123,7 +125,7 @@ void BPF_STRUCT_OPS(maximal_cgroup_set_weight, struct cgroup *cgrp, u32 weight)
 
 s32 BPF_STRUCT_OPS_SLEEPABLE(maximal_init)
 {
-	return 0;
+	return scx_bpf_create_dsq(DSQ_ID, -1);
 }
 
 void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info)
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
@@ -30,7 +30,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p,
 	}
 	scx_bpf_put_idle_cpumask(idle_mask);
 
-	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
 }
 
 SEC(".struct_ops.link")
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
@@ -67,7 +67,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_enqueue, struct task_struct *p,
 		saw_local = true;
 	}
 
-	scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, enq_flags);
+	scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, enq_flags);
 }
 
 s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task,
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
@@ -29,7 +29,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_select_cpu, struct task_struct *p,
 	cpu = prev_cpu;
 
 dispatch:
-	scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, 0);
+	scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, 0);
 	return cpu;
 }
 
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
@@ -18,7 +18,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_select_cpu, struct task_struct *p
 		   s32 prev_cpu, u64 wake_flags)
 {
 	/* Dispatching to a random DSQ should fail. */
-	scx_bpf_dispatch(p, 0xcafef00d, SCX_SLICE_DFL, 0);
+	scx_bpf_dsq_insert(p, 0xcafef00d, SCX_SLICE_DFL, 0);
 
 	return prev_cpu;
 }
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
@@ -18,8 +18,8 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_select_cpu, struct task_struct *p
 		   s32 prev_cpu, u64 wake_flags)
 {
 	/* Dispatching twice in a row is disallowed. */
-	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
-	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
 
 	return prev_cpu;
 }
diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
@@ -2,8 +2,8 @@
 /*
  * A scheduler that validates that enqueue flags are properly stored and
  * applied at dispatch time when a task is directly dispatched from
- * ops.select_cpu(). We validate this by using scx_bpf_dispatch_vtime(), and
- * making the test a very basic vtime scheduler.
+ * ops.select_cpu(). We validate this by using scx_bpf_dsq_insert_vtime(),
+ * and making the test a very basic vtime scheduler.
  *
  * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
  * Copyright (c) 2024 David Vernet <dvernet@meta.com>
@@ -47,13 +47,13 @@ s32 BPF_STRUCT_OPS(select_cpu_vtime_select_cpu, struct task_struct *p,
 	cpu = prev_cpu;
 	scx_bpf_test_and_clear_cpu_idle(cpu);
 ddsp:
-	scx_bpf_dispatch_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0);
+	scx_bpf_dsq_insert_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0);
 	return cpu;
 }
 
 void BPF_STRUCT_OPS(select_cpu_vtime_dispatch, s32 cpu, struct task_struct *p)
 {
-	if (scx_bpf_consume(VTIME_DSQ))
+	if (scx_bpf_dsq_move_to_local(VTIME_DSQ))
 		consumed = true;
 }
 

Original file line number	Diff line number	Diff line change
`@@ -20,7 +20,7 @@ s32 BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_select_cpu, struct task_struct *p,`
`20`	`20`	`* If we dispatch to a bogus DSQ that will fall back to the`
`21`	`21`	`* builtin global DSQ, we fail gracefully.`
`22`	`22`	`*/`
`23`		`- scx_bpf_dispatch_vtime(p, 0xcafef00d, SCX_SLICE_DFL,`
	`23`	`+ scx_bpf_dsq_insert_vtime(p, 0xcafef00d, SCX_SLICE_DFL,`
`24`	`24`	`p->scx.dsq_vtime, 0);`
`25`	`25`	`return cpu;`
`26`	`26`	`}`
Original file line number	Diff line number	Diff line change
`@@ -17,8 +17,8 @@ s32 BPF_STRUCT_OPS(ddsp_vtimelocal_fail_select_cpu, struct task_struct *p,`
`17`	`17`
`18`	`18`	`if (cpu >= 0) {`
`19`	`19`	`/* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */`
`20`		`- scx_bpf_dispatch_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL,`
`21`		`- p->scx.dsq_vtime, 0);`
	`20`	`+ scx_bpf_dsq_insert_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL,`
	`21`	`+ p->scx.dsq_vtime, 0);`
`22`	`22`	`return cpu;`
`23`	`23`	`}`
`24`	`24`
Original file line number	Diff line number	Diff line change
`@@ -31,7 +31,7 @@ void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p,`
`31`	`31`	`/* Can only call from ops.select_cpu() */`
`32`	`32`	`scx_bpf_select_cpu_dfl(p, 0, 0, &found);`
`33`	`33`
`34`		`- scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);`
	`34`	`+ scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);`
`35`	`35`	`}`
`36`	`36`
`37`	`37`	`SEC(".struct_ops.link")`
Original file line number	Diff line number	Diff line change
`@@ -33,15 +33,15 @@ void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags)`
`33`	`33`	`if (exit_point == EXIT_ENQUEUE)`
`34`	`34`	`EXIT_CLEANLY();`
`35`	`35`
`36`		`- scx_bpf_dispatch(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);`
	`36`	`+ scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);`
`37`	`37`	`}`
`38`	`38`
`39`	`39`	`void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p)`
`40`	`40`	`{`
`41`	`41`	`if (exit_point == EXIT_DISPATCH)`
`42`	`42`	`EXIT_CLEANLY();`
`43`	`43`
`44`		`- scx_bpf_consume(DSQ_ID);`
	`44`	`+ scx_bpf_dsq_move_to_local(DSQ_ID);`
`45`	`45`	`}`
`46`	`46`
`47`	`47`	`void BPF_STRUCT_OPS(exit_enable, struct task_struct *p)`