Maksytka/linux
1
1
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2025-11-30 23:16:01 +07:00
Code Issues Packages Projects Releases Wiki Activity
Files
master
linux/init/init_task.c
Yi Tao 0568f89d4f cgroup: replace global percpu_rwsem with per threadgroup resem when writing to cgroup.procs 
The static usage pattern of creating a cgroup, enabling controllers,
and then seeding it with CLONE_INTO_CGROUP doesn't require write
locking cgroup_threadgroup_rwsem and thus doesn't benefit from this
patch.

To avoid affecting other users, the per threadgroup rwsem is only used
when the favordynmods is enabled.

As computer hardware advances, modern systems are typically equipped
with many CPU cores and large amounts of memory, enabling the deployment
of numerous applications. On such systems, container creation and
deletion become frequent operations, making cgroup process migration no
longer a cold path. This leads to noticeable contention with common
process operations such as fork, exec, and exit.

To alleviate the contention between cgroup process migration and
operations like process fork, this patch modifies lock to take the write
lock on signal_struct->group_rwsem when writing pid to
cgroup.procs/threads instead of holding a global write lock.

Cgroup process migration has historically relied on
signal_struct->group_rwsem to protect thread group integrity. In commit
<1ed1328792ff> ("sched, cgroup: replace signal_struct->group_rwsem with
a global percpu_rwsem"), this was changed to a global
cgroup_threadgroup_rwsem. The advantage of using a global lock was
simplified handling of process group migrations. This patch retains the
use of the global lock for protecting process group migration, while
reducing contention by using per thread group lock during
cgroup.procs/threads writes.

The locking behavior is as follows:

write cgroup.procs/threads  | process fork,exec,exit | process group migration
------------------------------------------------------------------------------
cgroup_lock()               | down_read(&g_rwsem)    | cgroup_lock()
down_write(&p_rwsem)        | down_read(&p_rwsem)    | down_write(&g_rwsem)
critical section            | critical section       | critical section
up_write(&p_rwsem)          | up_read(&p_rwsem)      | up_write(&g_rwsem)
cgroup_unlock()             | up_read(&g_rwsem)      | cgroup_unlock()

g_rwsem denotes cgroup_threadgroup_rwsem, p_rwsem denotes
signal_struct->group_rwsem.

This patch eliminates contention between cgroup migration and fork
operations for threads that belong to different thread groups, thereby
reducing the long-tail latency of cgroup migrations and lowering system
load.

With this patch, under heavy fork and exec interference, the long-tail
latency of cgroup migration has been reduced from milliseconds to
microseconds. Under heavy cgroup migration interference, the multi-CPU
score of the spawn test case in UnixBench increased by 9%.

tj: Update comment in cgroup_favor_dynmods() and switch WARN_ONCE() to
    pr_warn_once().

Signed-off-by: Yi Tao <escape@linux.alibaba.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
2025-09-10 07:44:51 -10:00

236 lines
6.6 KiB
C
Raw Permalink Blame History

// 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/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),
};
#ifdef CONFIG_SHADOW_CALL_STACK
unsigned long init_shadow_call_stack[SCS_SIZE / sizeof(long)] = {
[(SCS_SIZE / sizeof(long)) - 1] = SCS_END_MAGIC
};
#endif
/*
* 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,
.faults_disabled_mapping = NULL,
.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_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),
.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,
.trc_reader_special.s = 0,
.trc_holdout_list = LIST_HEAD_INIT(init_task.trc_holdout_list),
.trc_blkd_node = LIST_HEAD_INIT(init_task.trc_blkd_node),
#endif
#ifdef CONFIG_CPUSETS
.mems_allowed_seq = SEQCNT_SPINLOCK_ZERO(init_task.mems_allowed_seq,
&init_task.alloc_lock),
#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
#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
};
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
Reference in New Issue View Git Blame Copy Permalink