This updates the proxy-exec logic in android16-6.12 which was added at v14, to be synced with the v18 series of the patchset. v14 series: https://github.com/johnstultz-work/linux-dev/commits/proxy-exec-v14-6.12 v18 series: https://github.com/johnstultz-work/linux-dev/commits/proxy-exec-v18-6.12 Changes since v14: * Improved naming consistency and using the guard macro where appropriate * Improved comments * Build fixes for !CONFIG_SMP * Fixes for when sched_proxy_exec() is disabled * Renamed update_curr_se to update_se_times, as suggested by Steven Rostedt. * Use put_prev_set_next_task as suggested by K Prateek Nayak * Try to rework find_proxy_task() locking to use guard and proxy_deactivate_task() in the way Peter suggested. * Simplified changes to enqueue_task_rt to match deadline's logic, as pointed out by Peter * Get rid of preserve_need_resched flag and rework per Peter's suggestion * Rework find_proxy_task() to use guard to cleanup the exit gotos as Peter suggested. * Reworked the forced return-migration from find_proxy_task to use Peter’s dequeue+wakeup approach, which helps resolve the cpuhotplug issues I had also seen, caused by the manual return migration sending tasks to offline cpus. * A number of improvements to the commit messages and comments suggested by Juri Lelli and Peter Zijlstra * Added missing logic to put_prev_task_dl as pointed out by K Prateek Nayak * Add lockdep_assert_held_once and drop the READ_ONCE in __get_task_blocked_on(), as suggested by Juri Lelli * Moved update_curr_task logic into update_curr_se to simplify things * Renamed update_se_times to update_se, as suggested by Peter * Reworked logic to fix an issue Peter pointed out with thread group accounting being done on the donor, rather than the running execution context. * Fixed typos caught by Metin Kaya * Suleiman Souhlal noticed an inefficiency in that we evaluate if the lock owner’s task_cpu() is the current cpu, before we look to see if the lock owner is on_rq at all. With v17 this would result in us proxy-migrating a donor to a remote cpu, only to then realize the task wasn’t even on the runqueue, and doing the sleeping owner enqueuing. Suleiman suggested instead that we evaluate on_rq first, so we can immediately do sleeping owner enqueueing. Then only if the owner is on a runqueue do we proxy-migrate the donor (which requires the more costly lock juggling). While not a huge logical change, it did uncover other problems, which needed to be resolved. * One issue found was there was a race where if do_activate_blocked_waiter() from the sleeping owner wakeup was delayed and the task had already been woken up elsewhere. It’s possible if that task was running and called into schedule() to be blocked, it would be dequeued from the runqueue, but before we switched to the new task, do_activate_blocked_waiter() might try to activate it on a different cpu. Clearly the do_activate_blocked_waiter() needed to check the task on_cpu value as well. * I found that we still can hit wakeups that end up skipping the BO_WAKING -> BO_RUNNALBE transition (causing find_proxy_task() to end up spinning waiting for that transition), so I re-added the logic to handle doing return migrations from find_proxy_task() if we hit that case. * Hupu suggested a tweak in ttwu_runnable() to evaluate proxy_needs_return() slightly earlier. * Kuyo Chang reported and isolated a fix for a problem with __task_is_pushable() in the !sched_proxy_exec case, which was folded into the “sched: Fix rt/dl load balancing via chain level balance” patch * Reworked some of the logic around releasing the rq->donor reference on migrations, using rq->idle directly. * Sueliman also pointed out that some added task_struct elements were not being initialized in the init_task code path, so that was good to fix. Bug: 427820735 Change-Id: I20ce778e474124a917dbf51378dc1301535ac858 Signed-off-by: John Stultz <jstultz@google.com>
251 lines
7.2 KiB
C
251 lines
7.2 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/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,
|
|
.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,
|
|
.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),
|
|
.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,
|
|
.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
|
|
.blocked_on_state = BO_RUNNABLE,
|
|
.blocked_donor = NULL,
|
|
.migration_node = LIST_HEAD_INIT(init_task.migration_node),
|
|
#ifdef CONFIG_SCHED_PROXY_EXEC
|
|
.blocked_head = LIST_HEAD_INIT(init_task.blocked_head),
|
|
.blocked_node = LIST_HEAD_INIT(init_task.blocked_node),
|
|
.blocked_activation_node = LIST_HEAD_INIT(init_task.blocked_activation_node),
|
|
.sleeping_owner = NULL,
|
|
#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
|
|
#ifdef CONFIG_ANDROID_VENDOR_OEM_DATA
|
|
.android_vendor_data1 = {0, },
|
|
.android_oem_data1 = {0, },
|
|
#endif
|
|
};
|
|
EXPORT_SYMBOL(init_task);
|
|
|
|
#ifdef CONFIG_GKI_DYNAMIC_TASK_STRUCT_SIZE
|
|
u64 vendor_data_pad[CONFIG_GKI_TASK_STRUCT_VENDOR_SIZE_MAX / sizeof(u64)];
|
|
EXPORT_SYMBOL_GPL(vendor_data_pad);
|
|
#endif
|
|
|
|
/*
|
|
* 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
|