linux/init/init_task.c
Paul E. McKenney d5f177d35c rcu-tasks: Add an RCU Tasks Trace to simplify protection of tracing hooks
Because RCU does not watch exception early-entry/late-exit, idle-loop,
or CPU-hotplug execution, protection of tracing and BPF operations is
needlessly complicated.  This commit therefore adds a variant of
Tasks RCU that:

o	Has explicit read-side markers to allow finite grace periods in
	the face of in-kernel loops for PREEMPT=n builds.  These markers
	are rcu_read_lock_trace() and rcu_read_unlock_trace().

o	Protects code in the idle loop, exception entry/exit, and
	CPU-hotplug code paths.  In this respect, RCU-tasks trace is
	similar to SRCU, but with lighter-weight readers.

o	Avoids expensive read-side instruction, having overhead similar
	to that of Preemptible RCU.

There are of course downsides:

o	The grace-period code can send IPIs to CPUs, even when those
	CPUs are in the idle loop or in nohz_full userspace.  This is
	mitigated by later commits.

o	It is necessary to scan the full tasklist, much as for Tasks RCU.

o	There is a single callback queue guarded by a single lock,
	again, much as for Tasks RCU.  However, those early use cases
	that request multiple grace periods in quick succession are
	expected to do so from a single task, which makes the single
	lock almost irrelevant.  If needed, multiple callback queues
	can be provided using any number of schemes.

Perhaps most important, this variant of RCU does not affect the vanilla
flavors, rcu_preempt and rcu_sched.  The fact that RCU Tasks Trace
readers can operate from idle, offline, and exception entry/exit in no
way enables rcu_preempt and rcu_sched readers to do so.

The memory ordering was outlined here:
https://lore.kernel.org/lkml/20200319034030.GX3199@paulmck-ThinkPad-P72/

This effort benefited greatly from off-list discussions of BPF
requirements with Alexei Starovoitov and Andrii Nakryiko.  At least
some of the on-list discussions are captured in the Link: tags below.
In addition, KCSAN was quite helpful in finding some early bugs.

Link: https://lore.kernel.org/lkml/20200219150744.428764577@infradead.org/
Link: https://lore.kernel.org/lkml/87mu8p797b.fsf@nanos.tec.linutronix.de/
Link: https://lore.kernel.org/lkml/20200225221305.605144982@linutronix.de/
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Andrii Nakryiko <andriin@fb.com>
[ paulmck: Apply feedback from Steve Rostedt and Joel Fernandes. ]
[ paulmck: Decrement trc_n_readers_need_end upon IPI failure. ]
[ paulmck: Fix locking issue reported by rcutorture. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-04-27 11:03:51 -07:00

199 lines
5.5 KiB
C

// 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/init.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/audit.h>
#include <linux/numa.h>
#include <asm/pgtable.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,
.cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex),
.exec_update_mutex = __MUTEX_INITIALIZER(init_signals.exec_update_mutex),
#ifdef CONFIG_POSIX_TIMERS
.posix_timers = LIST_HEAD_INIT(init_signals.posix_timers),
.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),
};
/*
* Set up the first task table, touch at your own risk!. Base=0,
* limit=0x1fffff (=2MB)
*/
struct task_struct init_task
#ifdef CONFIG_ARCH_TASK_STRUCT_ON_STACK
__init_task_data
#endif
= {
#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,
.cpus_mask = CPU_MASK_ALL,
.nr_cpus_allowed= NR_CPUS,
.mm = NULL,
.active_mm = &init_mm,
.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
.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,
.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),
.timer_slack_ns = 50000, /* 50 usec default slack */
.thread_pid = &init_struct_pid,
.thread_group = LIST_HEAD_INIT(init_task.thread_group),
.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,
#endif
#ifdef CONFIG_TASKS_TRACE_RCU
.trc_reader_nesting = 0,
.trc_holdout_list = LIST_HEAD_INIT(init_task.trc_holdout_list),
#endif
#ifdef CONFIG_CPUSETS
.mems_allowed_seq = SEQCNT_ZERO(init_task.mems_allowed_seq),
#endif
#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_KASAN
.kasan_depth = 1,
#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,
#endif
#if defined(CONFIG_TRACING) && defined(CONFIG_PREEMPTION)
.trace_recursion = 0,
#endif
#ifdef CONFIG_LIVEPATCH
.patch_state = KLP_UNDEFINED,
#endif
#ifdef CONFIG_SECURITY
.security = NULL,
#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