sched_ext: Implement core-sched support

The core-sched support is composed of the following parts:

* task_struct->scx.core_sched_at is added. This is a timestamp which can be
  used to order tasks. Depending on whether the BPF scheduler implements
  custom ordering, it tracks either global FIFO ordering of all tasks or
  local-DSQ ordering within the dispatched tasks on a CPU.

* prio_less() is updated to call scx_prio_less() when comparing SCX tasks.
  scx_prio_less() calls ops.core_sched_before() if available or uses the
  core_sched_at timestamp. For global FIFO ordering, the BPF scheduler
  doesn't need to do anything. Otherwise, it should implement
  ops.core_sched_before() which reflects the ordering.

* When core-sched is enabled, balance_scx() balances all SMT siblings so
  that they all have tasks dispatched if necessary before pick_task_scx() is
  called. pick_task_scx() picks between the current task and the first
  dispatched task on the local DSQ based on availability and the
  core_sched_at timestamps. Note that FIFO ordering is expected among the
  already dispatched tasks whether running or on the local DSQ, so this path
  always compares core_sched_at instead of calling into
  ops.core_sched_before().

qmap_core_sched_before() is added to scx_example_qmap. It scales the
distances from the heads of the queues to compare the tasks across different
priority queues and seems to behave as expected.

v2: * Sched core added the const qualifiers to prio_less task arguments.
      Explicitly drop them for ops.core_sched_before() task arguments. BPF
      enforces access control through the verifier, so the qualifier isn't
      actually operative and only gets in the way when interacting with
      various helpers.

Signed-off-by: Tejun Heo <[email protected]>
Reviewed-by: David Vernet <[email protected]>
Reviewed-by: Josh Don <[email protected]>

include/linux/sched/ext.h

@@ -316,6 +316,24 @@ struct sched_ext_ops {
 	 */
 	bool (*yield)(struct task_struct *from, struct task_struct *to);
 
+	/**
+	 * core_sched_before - Task ordering for core-sched
+	 * @a: task A
+	 * @b: task B
+	 *
+	 * Used by core-sched to determine the ordering between two tasks. See
+	 * Documentation/admin-guide/hw-vuln/core-scheduling.rst for details on
+	 * core-sched.
+	 *
+	 * Both @a and @b are runnable and may or may not currently be queued on
+	 * the BPF scheduler. Should return %true if @a should run before @b.
+	 * %false if there's no required ordering or @b should run before @a.
+	 *
+	 * If not specified, the default is ordering them according to when they
+	 * became runnable.
+	 */
+	bool (*core_sched_before)(struct task_struct *a,struct task_struct *b);
+
 	/**
 	 * set_weight - Set task weight
 	 * @p: task to set weight for
@@ -628,6 +646,9 @@ struct sched_ext_entity {
 	struct task_struct	*kf_tasks[2];	/* see SCX_CALL_OP_TASK() */
 	atomic64_t		ops_state;
 	unsigned long		runnable_at;
+#ifdef CONFIG_SCHED_CORE
+	u64			core_sched_at;	/* see scx_prio_less() */
+#endif
 
 	/* BPF scheduler modifiable fields */
 

kernel/Kconfig.preempt

@@ -135,7 +135,7 @@ config SCHED_CORE
 
 config SCHED_CLASS_EXT
 	bool "Extensible Scheduling Class"
-	depends on BPF_SYSCALL && BPF_JIT && !SCHED_CORE
+	depends on BPF_SYSCALL && BPF_JIT
 	help
 	  This option enables a new scheduler class sched_ext (SCX), which
 	  allows scheduling policies to be implemented as BPF programs to

kernel/sched/core.c

@@ -163,7 +163,12 @@ static inline int __task_prio(const struct task_struct *p)
 	if (p->sched_class == &idle_sched_class)
 		return MAX_RT_PRIO + NICE_WIDTH; /* 140 */
 
-	return MAX_RT_PRIO + MAX_NICE; /* 120, squash fair */
+#ifdef CONFIG_SCHED_CLASS_EXT
+	if (p->sched_class == &ext_sched_class)
+		return MAX_RT_PRIO + MAX_NICE + 1; /* 120, squash ext */
+#endif
+
+	return MAX_RT_PRIO + MAX_NICE; /* 119, squash fair */
 }
 
 /*
@@ -192,6 +197,11 @@ static inline bool prio_less(const struct task_struct *a,
 	if (pa == MAX_RT_PRIO + MAX_NICE)	/* fair */
 		return cfs_prio_less(a, b, in_fi);
 
+#ifdef CONFIG_SCHED_CLASS_EXT
+	if (pa == MAX_RT_PRIO + MAX_NICE + 1)	/* ext */
+		return scx_prio_less(a, b, in_fi);
+#endif
+
 	return false;
 }