diff options
Diffstat (limited to 'init')
| -rw-r--r-- | init/Kconfig | 14 | ||||
| -rw-r--r-- | init/Makefile | 2 | ||||
| -rw-r--r-- | init/init_task.c | 170 | ||||
| -rw-r--r-- | init/main.c | 16 |
4 files changed, 187 insertions, 15 deletions
diff --git a/init/Kconfig b/init/Kconfig index 2934249fba46..a9a2e2c86671 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -461,10 +461,15 @@ endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION bool "CPU isolation" + depends on SMP || COMPILE_TEST + default y help Make sure that CPUs running critical tasks are not disturbed by any source of "noise" such as unbound workqueues, timers, kthreads... - Unbound jobs get offloaded to housekeeping CPUs. + Unbound jobs get offloaded to housekeeping CPUs. This is driven by + the "isolcpus=" boot parameter. + + Say Y if unsure. source "kernel/rcu/Kconfig" @@ -1392,6 +1397,13 @@ config BPF_SYSCALL Enable the bpf() system call that allows to manipulate eBPF programs and maps via file descriptors. +config BPF_JIT_ALWAYS_ON + bool "Permanently enable BPF JIT and remove BPF interpreter" + depends on BPF_SYSCALL && HAVE_EBPF_JIT && BPF_JIT + help + Enables BPF JIT and removes BPF interpreter to avoid + speculative execution of BPF instructions by the interpreter + config USERFAULTFD bool "Enable userfaultfd() system call" select ANON_INODES diff --git a/init/Makefile b/init/Makefile index 1dbb23787290..a3e5ce2bcf08 100644 --- a/init/Makefile +++ b/init/Makefile @@ -13,9 +13,7 @@ obj-$(CONFIG_BLK_DEV_INITRD) += initramfs.o endif obj-$(CONFIG_GENERIC_CALIBRATE_DELAY) += calibrate.o -ifneq ($(CONFIG_ARCH_INIT_TASK),y) obj-y += init_task.o -endif mounts-y := do_mounts.o mounts-$(CONFIG_BLK_DEV_RAM) += do_mounts_rd.o diff --git a/init/init_task.c b/init/init_task.c index 9325fee7dc82..3ac6e754cf64 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -13,19 +13,175 @@ #include <asm/pgtable.h> #include <linux/uaccess.h> -static struct signal_struct init_signals = INIT_SIGNALS(init_signals); -static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); +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}} + }, + .rlim = INIT_RLIMITS, + .cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex), +#ifdef CONFIG_POSIX_TIMERS + .posix_timers = LIST_HEAD_INIT(init_signals.posix_timers), + .cputimer = { + .cputime_atomic = INIT_CPUTIME_ATOMIC, + .running = false, + .checking_timer = false, + }, +#endif + INIT_CPU_TIMERS(init_signals) + INIT_PREV_CPUTIME(init_signals) +}; + +static struct sighand_struct init_sighand = { + .count = ATOMIC_INIT(1), + .action = { { { .sa_handler = SIG_DFL, } }, }, + .siglock = __SPIN_LOCK_UNLOCKED(init_sighand.siglock), + .signalfd_wqh = __WAIT_QUEUE_HEAD_INITIALIZER(init_sighand.signalfd_wqh), +}; -/* Initial task structure */ -struct task_struct init_task = INIT_TASK(init_task); +/* + * 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 = ATOMIC_INIT(1), +#endif + .state = 0, + .stack = init_stack, + .usage = ATOMIC_INIT(2), + .flags = PF_KTHREAD, + .prio = MAX_PRIO - 20, + .static_prio = MAX_PRIO - 20, + .normal_prio = MAX_PRIO - 20, + .policy = SCHED_NORMAL, + .cpus_allowed = 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 */ + .pids = { + [PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), + [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), + [PIDTYPE_SID] = INIT_PID_LINK(PIDTYPE_SID), + }, + .thread_group = LIST_HEAD_INIT(init_task.thread_group), + .thread_node = LIST_HEAD_INIT(init_signals.thread_head), +#ifdef CONFIG_AUDITSYSCALL + .loginuid = INVALID_UID, + .sessionid = (unsigned int)-1, +#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_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 = -1, + .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_recursion = 0, +#endif +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + .ret_stack = NULL, +#endif +#if defined(CONFIG_TRACING) && defined(CONFIG_PREEMPT) + .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. */ -union thread_union init_thread_union __init_task_data = { #ifndef CONFIG_THREAD_INFO_IN_TASK - INIT_THREAD_INFO(init_task) +struct thread_info init_thread_info __init_thread_info = INIT_THREAD_INFO(init_task); #endif -}; diff --git a/init/main.c b/init/main.c index dfec3809e740..a8100b954839 100644 --- a/init/main.c +++ b/init/main.c @@ -75,6 +75,7 @@ #include <linux/slab.h> #include <linux/perf_event.h> #include <linux/ptrace.h> +#include <linux/pti.h> #include <linux/blkdev.h> #include <linux/elevator.h> #include <linux/sched_clock.h> @@ -504,6 +505,10 @@ static void __init mm_init(void) pgtable_init(); vmalloc_init(); ioremap_huge_init(); + /* Should be run before the first non-init thread is created */ + init_espfix_bsp(); + /* Should be run after espfix64 is set up. */ + pti_init(); } asmlinkage __visible void __init start_kernel(void) @@ -589,6 +594,12 @@ asmlinkage __visible void __init start_kernel(void) radix_tree_init(); /* + * Set up housekeeping before setting up workqueues to allow the unbound + * workqueue to take non-housekeeping into account. + */ + housekeeping_init(); + + /* * Allow workqueue creation and work item queueing/cancelling * early. Work item execution depends on kthreads and starts after * workqueue_init(). @@ -605,7 +616,6 @@ asmlinkage __visible void __init start_kernel(void) early_irq_init(); init_IRQ(); tick_init(); - housekeeping_init(); rcu_init_nohz(); init_timers(); hrtimers_init(); @@ -674,10 +684,6 @@ asmlinkage __visible void __init start_kernel(void) if (efi_enabled(EFI_RUNTIME_SERVICES)) efi_enter_virtual_mode(); #endif -#ifdef CONFIG_X86_ESPFIX64 - /* Should be run before the first non-init thread is created */ - init_espfix_bsp(); -#endif thread_stack_cache_init(); cred_init(); fork_init(); |