sched_ext: Maintain an online cid mask in the scheduler arenagrafted

Schedulers on the default cid mapping treat [0, nr_online_cids) as the
online set and restart on hotplug. Schedulers that install their own mapping
with scx_bpf_cid_override() have no way to learn which cids are online: the
count no longer identifies members and the CPU-form cpumask is unusable from
cid programs. This is an obvious hole in the cid API.

Add scx_bpf_online_cmask(), a kernel-maintained cmask in the scheduler's
arena, allocated alongside the per-CPU scratch masks and populated after the
cid mapping is finalized and before ops.init(), for child schedulers too.
The pointer stays valid through ops.exit() with no reference to take. It is
the arena offset as a void pointer, the same form struct_ops arena arguments
arrive in. The verifier types the void return as a scalar for the program's
arena cast.

The mask follows the SCX hotplug notifications: seeded from cpu_active_mask
and updated before ops.cid_online/offline() runs, so it lags cpu_online_mask
only inside a hotplug transition. Updates walk the scheduler list under the
lock that also serializes unlinking. Reads are live, not atomic snapshots.
Root initialization excludes hotplug.

v2: Reworded the getter kerneldoc (Andrea Righi).

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

1 files changed, 278 insertions, 0 deletions

diff --git a/init/init_task.c b/init/init_task.c
new file mode 100644
index 000000000..5c7ad50ac
--- /dev/null
+++ b/init/init_task.c
@@ -0,0 +1,278 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init_task.h>
+#include <linux/export.h>
+#include <linux/mqueue.h>
+#include <linux/sched.h>
+#include <linux/sched/sysctl.h>
+#include <linux/sched/rt.h>
+#include <linux/sched/task.h>
+#include <linux/sched/ext.h>
+#include <linux/sched/exec_state.h>
+#include <linux/user_namespace.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/audit.h>
+#include <linux/numa.h>
+#include <linux/scs.h>
+#include <linux/plist.h>
+
+#include <linux/uaccess.h>
+
+static struct signal_struct init_signals = {
+	.nr_threads	= 1,
+	.thread_head	= LIST_HEAD_INIT(init_task.thread_node),
+	.wait_chldexit	= __WAIT_QUEUE_HEAD_INITIALIZER(init_signals.wait_chldexit),
+	.shared_pending	= {
+		.list = LIST_HEAD_INIT(init_signals.shared_pending.list),
+		.signal =  {{0}}
+	},
+	.multiprocess	= HLIST_HEAD_INIT,
+	.rlim		= INIT_RLIMITS,
+#ifdef CONFIG_CGROUPS
+	.cgroup_threadgroup_rwsem	= __RWSEM_INITIALIZER(init_signals.cgroup_threadgroup_rwsem),
+#endif
+	.cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex),
+	.exec_update_lock = __RWSEM_INITIALIZER(init_signals.exec_update_lock),
+#ifdef CONFIG_POSIX_TIMERS
+	.posix_timers		= HLIST_HEAD_INIT,
+	.ignored_posix_timers	= HLIST_HEAD_INIT,
+	.cputimer		= {
+		.cputime_atomic	= INIT_CPUTIME_ATOMIC,
+	},
+#endif
+	INIT_CPU_TIMERS(init_signals)
+	.pids = {
+		[PIDTYPE_PID]	= &init_struct_pid,
+		[PIDTYPE_TGID]	= &init_struct_pid,
+		[PIDTYPE_PGID]	= &init_struct_pid,
+		[PIDTYPE_SID]	= &init_struct_pid,
+	},
+	INIT_PREV_CPUTIME(init_signals)
+};
+
+static struct sighand_struct init_sighand = {
+	.count		= REFCOUNT_INIT(1),
+	.action		= { { { .sa_handler = SIG_DFL, } }, },
+	.siglock	= __SPIN_LOCK_UNLOCKED(init_sighand.siglock),
+	.signalfd_wqh	= __WAIT_QUEUE_HEAD_INITIALIZER(init_sighand.signalfd_wqh),
+};
+
+/* init to 2 - one for init_task, one to ensure it is never freed */
+struct task_exec_state init_task_exec_state = {
+	.count		= REFCOUNT_INIT(2),
+	.dumpable	= TASK_DUMPABLE_OWNER,
+	.user_ns	= &init_user_ns,
+};
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+unsigned long init_shadow_call_stack[SCS_SIZE / sizeof(long)] = {
+	[(SCS_SIZE / sizeof(long)) - 1] = SCS_END_MAGIC
+};
+#endif
+
+/* init to 2 - one for init_task, one to ensure it is never freed */
+static struct group_info init_groups = { .usage = REFCOUNT_INIT(2) };
+
+/*
+ * The initial credentials for the initial task
+ */
+static struct cred init_cred = {
+	.usage			= ATOMIC_INIT(4),
+	.uid			= GLOBAL_ROOT_UID,
+	.gid			= GLOBAL_ROOT_GID,
+	.suid			= GLOBAL_ROOT_UID,
+	.sgid			= GLOBAL_ROOT_GID,
+	.euid			= GLOBAL_ROOT_UID,
+	.egid			= GLOBAL_ROOT_GID,
+	.fsuid			= GLOBAL_ROOT_UID,
+	.fsgid			= GLOBAL_ROOT_GID,
+	.securebits		= SECUREBITS_DEFAULT,
+	.cap_inheritable	= CAP_EMPTY_SET,
+	.cap_permitted		= CAP_FULL_SET,
+	.cap_effective		= CAP_FULL_SET,
+	.cap_bset		= CAP_FULL_SET,
+	.user			= INIT_USER,
+	.user_ns		= &init_user_ns,
+	.group_info		= &init_groups,
+	.ucounts		= &init_ucounts,
+};
+
+/*
+ * Set up the first task table, touch at your own risk!. Base=0,
+ * limit=0x1fffff (=2MB)
+ */
+struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+	.thread_info	= INIT_THREAD_INFO(init_task),
+	.stack_refcount	= REFCOUNT_INIT(1),
+#endif
+	.__state	= 0,
+	.stack		= init_stack,
+	.usage		= REFCOUNT_INIT(2),
+	.flags		= PF_KTHREAD,
+	.prio		= MAX_PRIO - 20,
+	.static_prio	= MAX_PRIO - 20,
+	.normal_prio	= MAX_PRIO - 20,
+	.policy		= SCHED_NORMAL,
+	.cpus_ptr	= &init_task.cpus_mask,
+	.user_cpus_ptr	= NULL,
+	.cpus_mask	= CPU_MASK_ALL,
+	.max_allowed_capacity	= SCHED_CAPACITY_SCALE,
+	.nr_cpus_allowed= NR_CPUS,
+	.mm		= NULL,
+	.active_mm	= &init_mm,
+	.exec_state	= &init_task_exec_state,
+	.restart_block	= {
+		.fn = do_no_restart_syscall,
+	},
+	.se		= {
+		.group_node 	= LIST_HEAD_INIT(init_task.se.group_node),
+	},
+	.rt		= {
+		.run_list	= LIST_HEAD_INIT(init_task.rt.run_list),
+		.time_slice	= RR_TIMESLICE,
+	},
+	.tasks		= LIST_HEAD_INIT(init_task.tasks),
+#ifdef CONFIG_SMP
+	.pushable_tasks	= PLIST_NODE_INIT(init_task.pushable_tasks, MAX_PRIO),
+#endif
+#ifdef CONFIG_CGROUP_SCHED
+	.sched_task_group = &root_task_group,
+#endif
+#ifdef CONFIG_SCHED_CLASS_EXT
+	.scx		= {
+		.dsq_list.node	= LIST_HEAD_INIT(init_task.scx.dsq_list.node),
+		.sticky_cpu	= -1,
+		.holding_cpu	= -1,
+		.runnable_cpu	= -1,
+		.runnable_node	= LIST_HEAD_INIT(init_task.scx.runnable_node),
+		.runnable_at	= INITIAL_JIFFIES,
+		.ddsp_dsq_id	= SCX_DSQ_INVALID,
+		.slice		= SCX_SLICE_DFL,
+	},
+#endif
+	.ptraced	= LIST_HEAD_INIT(init_task.ptraced),
+	.ptrace_entry	= LIST_HEAD_INIT(init_task.ptrace_entry),
+	.real_parent	= &init_task,
+	.parent		= &init_task,
+	.children	= LIST_HEAD_INIT(init_task.children),
+	.sibling	= LIST_HEAD_INIT(init_task.sibling),
+	.group_leader	= &init_task,
+	RCU_POINTER_INITIALIZER(real_cred, &init_cred),
+	RCU_POINTER_INITIALIZER(cred, &init_cred),
+	.comm		= INIT_TASK_COMM,
+	.thread		= INIT_THREAD,
+	.fs		= &init_fs,
+	.files		= &init_files,
+#ifdef CONFIG_IO_URING
+	.io_uring	= NULL,
+#endif
+	.signal		= &init_signals,
+	.sighand	= &init_sighand,
+	.nsproxy	= &init_nsproxy,
+	.pending	= {
+		.list = LIST_HEAD_INIT(init_task.pending.list),
+		.signal = {{0}}
+	},
+	.blocked	= {{0}},
+	.alloc_lock	= __SPIN_LOCK_UNLOCKED(init_task.alloc_lock),
+	.journal_info	= NULL,
+	INIT_CPU_TIMERS(init_task)
+	.pi_lock	= __RAW_SPIN_LOCK_UNLOCKED(init_task.pi_lock),
+	.blocked_lock	= __RAW_SPIN_LOCK_UNLOCKED(init_task.blocked_lock),
+	.timer_slack_ns = 50000, /* 50 usec default slack */
+	.thread_pid	= &init_struct_pid,
+	.thread_node	= LIST_HEAD_INIT(init_signals.thread_head),
+#ifdef CONFIG_AUDIT
+	.loginuid	= INVALID_UID,
+	.sessionid	= AUDIT_SID_UNSET,
+#endif
+#ifdef CONFIG_PERF_EVENTS
+	.perf_event_mutex = __MUTEX_INITIALIZER(init_task.perf_event_mutex),
+	.perf_event_list = LIST_HEAD_INIT(init_task.perf_event_list),
+#endif
+#ifdef CONFIG_PREEMPT_RCU
+	.rcu_read_lock_nesting = 0,
+	.rcu_read_unlock_special.s = 0,
+	.rcu_node_entry = LIST_HEAD_INIT(init_task.rcu_node_entry),
+	.rcu_blocked_node = NULL,
+#endif
+#ifdef CONFIG_TASKS_RCU
+	.rcu_tasks_holdout = false,
+	.rcu_tasks_holdout_list = LIST_HEAD_INIT(init_task.rcu_tasks_holdout_list),
+	.rcu_tasks_idle_cpu = -1,
+	.rcu_tasks_exit_list = LIST_HEAD_INIT(init_task.rcu_tasks_exit_list),
+#endif
+#ifdef CONFIG_TASKS_TRACE_RCU
+	.trc_reader_nesting = 0,
+#endif
+#ifdef CONFIG_CPUSETS
+	.mems_allowed_seq = SEQCNT_SPINLOCK_ZERO(init_task.mems_allowed_seq,
+						 &init_task.alloc_lock),
+#endif
+	.blocked_donor = NULL,
+#ifdef CONFIG_RT_MUTEXES
+	.pi_waiters	= RB_ROOT_CACHED,
+	.pi_top_task	= NULL,
+#endif
+	INIT_PREV_CPUTIME(init_task)
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+	.vtime.seqcount	= SEQCNT_ZERO(init_task.vtime_seqcount),
+	.vtime.starttime = 0,
+	.vtime.state	= VTIME_SYS,
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+	.numa_preferred_nid = NUMA_NO_NODE,
+	.numa_group	= NULL,
+	.numa_faults	= NULL,
+#endif
+#ifdef CONFIG_SCHED_CACHE
+	.preferred_llc  = -1,
+	.pref_llc_queued  = 0,
+#endif
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
+	.kasan_depth	= 1,
+#endif
+#ifdef CONFIG_KCSAN
+	.kcsan_ctx = {
+		.scoped_accesses	= {LIST_POISON1, NULL},
+	},
+#endif
+#ifdef CONFIG_TRACE_IRQFLAGS
+	.softirqs_enabled = 1,
+#endif
+#ifdef CONFIG_LOCKDEP
+	.lockdep_depth = 0, /* no locks held yet */
+	.curr_chain_key = INITIAL_CHAIN_KEY,
+	.lockdep_recursion = 0,
+#endif
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	.ret_stack		= NULL,
+	.tracing_graph_pause	= ATOMIC_INIT(0),
+#endif
+#if defined(CONFIG_TRACING) && defined(CONFIG_PREEMPTION)
+	.trace_recursion = 0,
+#endif
+#ifdef CONFIG_LIVEPATCH
+	.patch_state	= KLP_TRANSITION_IDLE,
+#endif
+#ifdef CONFIG_SECURITY
+	.security	= NULL,
+#endif
+#ifdef CONFIG_SECCOMP_FILTER
+	.seccomp	= { .filter_count = ATOMIC_INIT(0) },
+#endif
+#ifdef CONFIG_SCHED_MM_CID
+	.mm_cid		= { .cid = MM_CID_UNSET, },
+#endif
+};
+EXPORT_SYMBOL(init_task);
+
+/*
+ * Initial thread structure. Alignment of this is handled by a special
+ * linker map entry.
+ */
+#ifndef CONFIG_THREAD_INFO_IN_TASK
+struct thread_info init_thread_info __init_thread_info = INIT_THREAD_INFO(init_task);
+#endif