diff options
Diffstat (limited to 'kernel/cpu.c')
| -rw-r--r-- | kernel/cpu.c | 1069 |
1 files changed, 852 insertions, 217 deletions
diff --git a/kernel/cpu.c b/kernel/cpu.c index 407a2568f35e..b674fdf96208 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -17,6 +17,7 @@ #include <linux/cpu.h> #include <linux/oom.h> #include <linux/rcupdate.h> +#include <linux/delay.h> #include <linux/export.h> #include <linux/bug.h> #include <linux/kthread.h> @@ -34,6 +35,9 @@ #include <linux/scs.h> #include <linux/percpu-rwsem.h> #include <linux/cpuset.h> +#include <linux/random.h> +#include <linux/cc_platform.h> +#include <linux/parser.h> #include <trace/events/power.h> #define CREATE_TRACE_POINTS @@ -51,12 +55,12 @@ * @rollback: Perform a rollback * @single: Single callback invocation * @bringup: Single callback bringup or teardown selector - * @cpu: CPU number * @node: Remote CPU node; for multi-instance, do a * single entry callback for install/remove * @last: For multi-instance rollback, remember how far we got * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation + * @ap_sync_state: State for AP synchronization * @done_up: Signal completion to the issuer of the task for cpu-up * @done_down: Signal completion to the issuer of the task for cpu-down */ @@ -70,11 +74,11 @@ struct cpuhp_cpu_state { bool rollback; bool single; bool bringup; - int cpu; struct hlist_node *node; struct hlist_node *last; enum cpuhp_state cb_state; int result; + atomic_t ap_sync_state; struct completion done_up; struct completion done_down; #endif @@ -275,6 +279,182 @@ static bool cpuhp_is_atomic_state(enum cpuhp_state state) return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; } +/* Synchronization state management */ +enum cpuhp_sync_state { + SYNC_STATE_DEAD, + SYNC_STATE_KICKED, + SYNC_STATE_SHOULD_DIE, + SYNC_STATE_ALIVE, + SYNC_STATE_SHOULD_ONLINE, + SYNC_STATE_ONLINE, +}; + +#ifdef CONFIG_HOTPLUG_CORE_SYNC +/** + * cpuhp_ap_update_sync_state - Update synchronization state during bringup/teardown + * @state: The synchronization state to set + * + * No synchronization point. Just update of the synchronization state, but implies + * a full barrier so that the AP changes are visible before the control CPU proceeds. + */ +static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) +{ + atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state); + + (void)atomic_xchg(st, state); +} + +void __weak arch_cpuhp_sync_state_poll(void) { cpu_relax(); } + +static bool cpuhp_wait_for_sync_state(unsigned int cpu, enum cpuhp_sync_state state, + enum cpuhp_sync_state next_state) +{ + atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); + ktime_t now, end, start = ktime_get(); + int sync; + + end = start + 10ULL * NSEC_PER_SEC; + + sync = atomic_read(st); + while (1) { + if (sync == state) { + if (!atomic_try_cmpxchg(st, &sync, next_state)) + continue; + return true; + } + + now = ktime_get(); + if (now > end) { + /* Timeout. Leave the state unchanged */ + return false; + } else if (now - start < NSEC_PER_MSEC) { + /* Poll for one millisecond */ + arch_cpuhp_sync_state_poll(); + } else { + usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC); + } + sync = atomic_read(st); + } + return true; +} +#else /* CONFIG_HOTPLUG_CORE_SYNC */ +static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) { } +#endif /* !CONFIG_HOTPLUG_CORE_SYNC */ + +#ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD +/** + * cpuhp_ap_report_dead - Update synchronization state to DEAD + * + * No synchronization point. Just update of the synchronization state. + */ +void cpuhp_ap_report_dead(void) +{ + cpuhp_ap_update_sync_state(SYNC_STATE_DEAD); +} + +void __weak arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { } + +/* + * Late CPU shutdown synchronization point. Cannot use cpuhp_state::done_down + * because the AP cannot issue complete() at this stage. + */ +static void cpuhp_bp_sync_dead(unsigned int cpu) +{ + atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); + int sync = atomic_read(st); + + do { + /* CPU can have reported dead already. Don't overwrite that! */ + if (sync == SYNC_STATE_DEAD) + break; + } while (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_SHOULD_DIE)); + + if (cpuhp_wait_for_sync_state(cpu, SYNC_STATE_DEAD, SYNC_STATE_DEAD)) { + /* CPU reached dead state. Invoke the cleanup function */ + arch_cpuhp_cleanup_dead_cpu(cpu); + return; + } + + /* No further action possible. Emit message and give up. */ + pr_err("CPU%u failed to report dead state\n", cpu); +} +#else /* CONFIG_HOTPLUG_CORE_SYNC_DEAD */ +static inline void cpuhp_bp_sync_dead(unsigned int cpu) { } +#endif /* !CONFIG_HOTPLUG_CORE_SYNC_DEAD */ + +#ifdef CONFIG_HOTPLUG_CORE_SYNC_FULL +/** + * cpuhp_ap_sync_alive - Synchronize AP with the control CPU once it is alive + * + * Updates the AP synchronization state to SYNC_STATE_ALIVE and waits + * for the BP to release it. + */ +void cpuhp_ap_sync_alive(void) +{ + atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state); + + cpuhp_ap_update_sync_state(SYNC_STATE_ALIVE); + + /* Wait for the control CPU to release it. */ + while (atomic_read(st) != SYNC_STATE_SHOULD_ONLINE) + cpu_relax(); +} + +static bool cpuhp_can_boot_ap(unsigned int cpu) +{ + atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); + int sync = atomic_read(st); + +again: + switch (sync) { + case SYNC_STATE_DEAD: + /* CPU is properly dead */ + break; + case SYNC_STATE_KICKED: + /* CPU did not come up in previous attempt */ + break; + case SYNC_STATE_ALIVE: + /* CPU is stuck cpuhp_ap_sync_alive(). */ + break; + default: + /* CPU failed to report online or dead and is in limbo state. */ + return false; + } + + /* Prepare for booting */ + if (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_KICKED)) + goto again; + + return true; +} + +void __weak arch_cpuhp_cleanup_kick_cpu(unsigned int cpu) { } + +/* + * Early CPU bringup synchronization point. Cannot use cpuhp_state::done_up + * because the AP cannot issue complete() so early in the bringup. + */ +static int cpuhp_bp_sync_alive(unsigned int cpu) +{ + int ret = 0; + + if (!IS_ENABLED(CONFIG_HOTPLUG_CORE_SYNC_FULL)) + return 0; + + if (!cpuhp_wait_for_sync_state(cpu, SYNC_STATE_ALIVE, SYNC_STATE_SHOULD_ONLINE)) { + pr_err("CPU%u failed to report alive state\n", cpu); + ret = -EIO; + } + + /* Let the architecture cleanup the kick alive mechanics. */ + arch_cpuhp_cleanup_kick_cpu(cpu); + return ret; +} +#else /* CONFIG_HOTPLUG_CORE_SYNC_FULL */ +static inline int cpuhp_bp_sync_alive(unsigned int cpu) { return 0; } +static inline bool cpuhp_can_boot_ap(unsigned int cpu) { return true; } +#endif /* !CONFIG_HOTPLUG_CORE_SYNC_FULL */ + /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; @@ -304,6 +484,8 @@ static int cpu_hotplug_disabled; DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); +static bool cpu_hotplug_offline_disabled __ro_after_init; + void cpus_read_lock(void) { percpu_down_read(&cpu_hotplug_lock); @@ -345,6 +527,7 @@ void lockdep_assert_cpus_held(void) percpu_rwsem_assert_held(&cpu_hotplug_lock); } +EXPORT_SYMBOL_GPL(lockdep_assert_cpus_held); #ifdef CONFIG_LOCKDEP int lockdep_is_cpus_held(void) @@ -363,6 +546,14 @@ static void lockdep_release_cpus_lock(void) rwsem_release(&cpu_hotplug_lock.dep_map, _THIS_IP_); } +/* Declare CPU offlining not supported */ +void cpu_hotplug_disable_offlining(void) +{ + cpu_maps_update_begin(); + cpu_hotplug_offline_disabled = true; + cpu_maps_update_done(); +} + /* * Wait for currently running CPU hotplug operations to complete (if any) and * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects @@ -412,7 +603,10 @@ static void lockdep_release_cpus_lock(void) void __weak arch_smt_update(void) { } #ifdef CONFIG_HOTPLUG_SMT + enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; +static unsigned int cpu_smt_max_threads __ro_after_init; +unsigned int cpu_smt_num_threads __read_mostly = UINT_MAX; void __init cpu_smt_disable(bool force) { @@ -426,16 +620,33 @@ void __init cpu_smt_disable(bool force) pr_info("SMT: disabled\n"); cpu_smt_control = CPU_SMT_DISABLED; } + cpu_smt_num_threads = 1; } /* * The decision whether SMT is supported can only be done after the full * CPU identification. Called from architecture code. */ -void __init cpu_smt_check_topology(void) +void __init cpu_smt_set_num_threads(unsigned int num_threads, + unsigned int max_threads) { - if (!topology_smt_supported()) + WARN_ON(!num_threads || (num_threads > max_threads)); + + if (max_threads == 1) cpu_smt_control = CPU_SMT_NOT_SUPPORTED; + + cpu_smt_max_threads = max_threads; + + /* + * If SMT has been disabled via the kernel command line or SMT is + * not supported, set cpu_smt_num_threads to 1 for consistency. + * If enabled, take the architecture requested number of threads + * to bring up into account. + */ + if (cpu_smt_control != CPU_SMT_ENABLED) + cpu_smt_num_threads = 1; + else if (num_threads < cpu_smt_num_threads) + cpu_smt_num_threads = num_threads; } static int __init smt_cmdline_disable(char *str) @@ -445,9 +656,31 @@ static int __init smt_cmdline_disable(char *str) } early_param("nosmt", smt_cmdline_disable); -static inline bool cpu_smt_allowed(unsigned int cpu) +/* + * For Archicture supporting partial SMT states check if the thread is allowed. + * Otherwise this has already been checked through cpu_smt_max_threads when + * setting the SMT level. + */ +static inline bool cpu_smt_thread_allowed(unsigned int cpu) +{ +#ifdef CONFIG_SMT_NUM_THREADS_DYNAMIC + return topology_smt_thread_allowed(cpu); +#else + return true; +#endif +} + +static inline bool cpu_bootable(unsigned int cpu) { - if (cpu_smt_control == CPU_SMT_ENABLED) + if (cpu_smt_control == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu)) + return true; + + /* All CPUs are bootable if controls are not configured */ + if (cpu_smt_control == CPU_SMT_NOT_IMPLEMENTED) + return true; + + /* All CPUs are bootable if CPU is not SMT capable */ + if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return true; if (topology_is_primary_thread(cpu)) @@ -462,19 +695,20 @@ static inline bool cpu_smt_allowed(unsigned int cpu) return !cpumask_test_cpu(cpu, &cpus_booted_once_mask); } -/* Returns true if SMT is not supported of forcefully (irreversibly) disabled */ +/* Returns true if SMT is supported and not forcefully (irreversibly) disabled */ bool cpu_smt_possible(void) { return cpu_smt_control != CPU_SMT_FORCE_DISABLED && cpu_smt_control != CPU_SMT_NOT_SUPPORTED; } EXPORT_SYMBOL_GPL(cpu_smt_possible); + #else -static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } +static inline bool cpu_bootable(unsigned int cpu) { return true; } #endif static inline enum cpuhp_state -cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) +cpuhp_set_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; bool bringup = st->state < target; @@ -485,14 +719,15 @@ cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) st->target = target; st->single = false; st->bringup = bringup; - if (cpu_dying(st->cpu) != !bringup) - set_cpu_dying(st->cpu, !bringup); + if (cpu_dying(cpu) != !bringup) + set_cpu_dying(cpu, !bringup); return prev_state; } static inline void -cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) +cpuhp_reset_state(int cpu, struct cpuhp_cpu_state *st, + enum cpuhp_state prev_state) { bool bringup = !st->bringup; @@ -519,8 +754,8 @@ cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) } st->bringup = bringup; - if (cpu_dying(st->cpu) != !bringup) - set_cpu_dying(st->cpu, !bringup); + if (cpu_dying(cpu) != !bringup) + set_cpu_dying(cpu, !bringup); } /* Regular hotplug invocation of the AP hotplug thread */ @@ -540,22 +775,23 @@ static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) wait_for_ap_thread(st, st->bringup); } -static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target) +static int cpuhp_kick_ap(int cpu, struct cpuhp_cpu_state *st, + enum cpuhp_state target) { enum cpuhp_state prev_state; int ret; - prev_state = cpuhp_set_state(st, target); + prev_state = cpuhp_set_state(cpu, st, target); __cpuhp_kick_ap(st); if ((ret = st->result)) { - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } return ret; } -static int bringup_wait_for_ap(unsigned int cpu) +static int bringup_wait_for_ap_online(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); @@ -571,43 +807,99 @@ static int bringup_wait_for_ap(unsigned int cpu) * SMT soft disabling on X86 requires to bring the CPU out of the * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The * CPU marked itself as booted_once in notify_cpu_starting() so the - * cpu_smt_allowed() check will now return false if this is not the + * cpu_bootable() check will now return false if this is not the * primary sibling. */ - if (!cpu_smt_allowed(cpu)) + if (!cpu_bootable(cpu)) return -ECANCELED; + return 0; +} + +#ifdef CONFIG_HOTPLUG_SPLIT_STARTUP +static int cpuhp_kick_ap_alive(unsigned int cpu) +{ + if (!cpuhp_can_boot_ap(cpu)) + return -EAGAIN; + + return arch_cpuhp_kick_ap_alive(cpu, idle_thread_get(cpu)); +} + +static int cpuhp_bringup_ap(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int ret; + + /* + * Some architectures have to walk the irq descriptors to + * setup the vector space for the cpu which comes online. + * Prevent irq alloc/free across the bringup. + */ + irq_lock_sparse(); + + ret = cpuhp_bp_sync_alive(cpu); + if (ret) + goto out_unlock; + + ret = bringup_wait_for_ap_online(cpu); + if (ret) + goto out_unlock; + + irq_unlock_sparse(); if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; - return cpuhp_kick_ap(st, st->target); -} + return cpuhp_kick_ap(cpu, st, st->target); +out_unlock: + irq_unlock_sparse(); + return ret; +} +#else static int bringup_cpu(unsigned int cpu) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle = idle_thread_get(cpu); int ret; - /* - * Reset stale stack state from the last time this CPU was online. - */ - scs_task_reset(idle); - kasan_unpoison_task_stack(idle); + if (!cpuhp_can_boot_ap(cpu)) + return -EAGAIN; /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. - * Prevent irq alloc/free across the bringup. + * + * Prevent irq alloc/free across the bringup by acquiring the + * sparse irq lock. Hold it until the upcoming CPU completes the + * startup in cpuhp_online_idle() which allows to avoid + * intermediate synchronization points in the architecture code. */ irq_lock_sparse(); - /* Arch-specific enabling code. */ ret = __cpu_up(cpu, idle); - irq_unlock_sparse(); if (ret) - return ret; - return bringup_wait_for_ap(cpu); + goto out_unlock; + + ret = cpuhp_bp_sync_alive(cpu); + if (ret) + goto out_unlock; + + ret = bringup_wait_for_ap_online(cpu); + if (ret) + goto out_unlock; + + irq_unlock_sparse(); + + if (st->target <= CPUHP_AP_ONLINE_IDLE) + return 0; + + return cpuhp_kick_ap(cpu, st, st->target); + +out_unlock: + irq_unlock_sparse(); + return ret; } +#endif static int finish_cpu(unsigned int cpu) { @@ -615,12 +907,13 @@ static int finish_cpu(unsigned int cpu) struct mm_struct *mm = idle->active_mm; /* - * idle_task_exit() will have switched to &init_mm, now - * clean up any remaining active_mm state. + * sched_force_init_mm() ensured the use of &init_mm, + * drop that refcount now that the CPU has stopped. */ - if (mm != &init_mm) - idle->active_mm = &init_mm; - mmdrop(mm); + WARN_ON(mm != &init_mm); + idle->active_mm = NULL; + mmdrop_lazy_tlb(mm); + return 0; } @@ -660,21 +953,51 @@ static bool cpuhp_next_state(bool bringup, return true; } -static int cpuhp_invoke_callback_range(bool bringup, - unsigned int cpu, - struct cpuhp_cpu_state *st, - enum cpuhp_state target) +static int __cpuhp_invoke_callback_range(bool bringup, + unsigned int cpu, + struct cpuhp_cpu_state *st, + enum cpuhp_state target, + bool nofail) { enum cpuhp_state state; - int err = 0; + int ret = 0; while (cpuhp_next_state(bringup, &state, st, target)) { + int err; + err = cpuhp_invoke_callback(cpu, state, bringup, NULL, NULL); - if (err) + if (!err) + continue; + + if (nofail) { + pr_warn("CPU %u %s state %s (%d) failed (%d)\n", + cpu, bringup ? "UP" : "DOWN", + cpuhp_get_step(st->state)->name, + st->state, err); + ret = -1; + } else { + ret = err; break; + } } - return err; + return ret; +} + +static inline int cpuhp_invoke_callback_range(bool bringup, + unsigned int cpu, + struct cpuhp_cpu_state *st, + enum cpuhp_state target) +{ + return __cpuhp_invoke_callback_range(bringup, cpu, st, target, false); +} + +static inline void cpuhp_invoke_callback_range_nofail(bool bringup, + unsigned int cpu, + struct cpuhp_cpu_state *st, + enum cpuhp_state target) +{ + __cpuhp_invoke_callback_range(bringup, cpu, st, target, true); } static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st) @@ -703,7 +1026,7 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, ret, cpu, cpuhp_get_step(st->state)->name, st->state); - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); if (can_rollback_cpu(st)) WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, prev_state)); @@ -714,15 +1037,6 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, /* * The cpu hotplug threads manage the bringup and teardown of the cpus */ -static void cpuhp_create(unsigned int cpu) -{ - struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); - - init_completion(&st->done_up); - init_completion(&st->done_down); - st->cpu = cpu; -} - static int cpuhp_should_run(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); @@ -874,7 +1188,7 @@ static int cpuhp_kick_ap_work(unsigned int cpu) cpuhp_lock_release(true); trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); - ret = cpuhp_kick_ap(st, st->target); + ret = cpuhp_kick_ap(cpu, st, st->target); trace_cpuhp_exit(cpu, st->state, prev_state, ret); return ret; @@ -882,63 +1196,29 @@ static int cpuhp_kick_ap_work(unsigned int cpu) static struct smp_hotplug_thread cpuhp_threads = { .store = &cpuhp_state.thread, - .create = &cpuhp_create, .thread_should_run = cpuhp_should_run, .thread_fn = cpuhp_thread_fun, .thread_comm = "cpuhp/%u", .selfparking = true, }; -void __init cpuhp_threads_init(void) +static __init void cpuhp_init_state(void) { - BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads)); - kthread_unpark(this_cpu_read(cpuhp_state.thread)); + struct cpuhp_cpu_state *st; + int cpu; + + for_each_possible_cpu(cpu) { + st = per_cpu_ptr(&cpuhp_state, cpu); + init_completion(&st->done_up); + init_completion(&st->done_down); + } } -/* - * - * Serialize hotplug trainwrecks outside of the cpu_hotplug_lock - * protected region. - * - * The operation is still serialized against concurrent CPU hotplug via - * cpu_add_remove_lock, i.e. CPU map protection. But it is _not_ - * serialized against other hotplug related activity like adding or - * removing of state callbacks and state instances, which invoke either the - * startup or the teardown callback of the affected state. - * - * This is required for subsystems which are unfixable vs. CPU hotplug and - * evade lock inversion problems by scheduling work which has to be - * completed _before_ cpu_up()/_cpu_down() returns. - * - * Don't even think about adding anything to this for any new code or even - * drivers. It's only purpose is to keep existing lock order trainwrecks - * working. - * - * For cpu_down() there might be valid reasons to finish cleanups which are - * not required to be done under cpu_hotplug_lock, but that's a different - * story and would be not invoked via this. - */ -static void cpu_up_down_serialize_trainwrecks(bool tasks_frozen) +void __init cpuhp_threads_init(void) { - /* - * cpusets delegate hotplug operations to a worker to "solve" the - * lock order problems. Wait for the worker, but only if tasks are - * _not_ frozen (suspend, hibernate) as that would wait forever. - * - * The wait is required because otherwise the hotplug operation - * returns with inconsistent state, which could even be observed in - * user space when a new CPU is brought up. The CPU plug uevent - * would be delivered and user space reacting on it would fail to - * move tasks to the newly plugged CPU up to the point where the - * work has finished because up to that point the newly plugged CPU - * is not assignable in cpusets/cgroups. On unplug that's not - * necessarily a visible issue, but it is still inconsistent state, - * which is the real problem which needs to be "fixed". This can't - * prevent the transient state between scheduling the work and - * returning from waiting for it. - */ - if (!tasks_frozen) - cpuset_wait_for_hotplug(); + cpuhp_init_state(); + BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads)); + kthread_unpark(this_cpu_read(cpuhp_state.thread)); } #ifdef CONFIG_HOTPLUG_CPU @@ -993,7 +1273,6 @@ static int take_cpu_down(void *_param) struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); - int ret; /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); @@ -1006,18 +1285,11 @@ static int take_cpu_down(void *_param) */ WARN_ON(st->state != (CPUHP_TEARDOWN_CPU - 1)); - /* Invoke the former CPU_DYING callbacks */ - ret = cpuhp_invoke_callback_range(false, cpu, st, target); - /* - * DYING must not fail! + * Invoke the former CPU_DYING callbacks. DYING must not fail! */ - WARN_ON_ONCE(ret); + cpuhp_invoke_callback_range_nofail(false, cpu, st, target); - /* Give up timekeeping duties */ - tick_handover_do_timer(); - /* Remove CPU from timer broadcasting */ - tick_offline_cpu(cpu); /* Park the stopper thread */ stop_machine_park(cpu); return 0; @@ -1037,9 +1309,6 @@ static int takedown_cpu(unsigned int cpu) */ irq_lock_sparse(); - /* - * So now all preempt/rcu users must observe !cpu_active(). - */ err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); if (err) { /* CPU refused to die */ @@ -1067,8 +1336,17 @@ static int takedown_cpu(unsigned int cpu) /* This actually kills the CPU. */ __cpu_die(cpu); - tick_cleanup_dead_cpu(cpu); + cpuhp_bp_sync_dead(cpu); + + lockdep_cleanup_dead_cpu(cpu, idle_thread_get(cpu)); + + /* + * Callbacks must be re-integrated right away to the RCU state machine. + * Otherwise an RCU callback could block a further teardown function + * waiting for its completion. + */ rcutree_migrate_callbacks(cpu); + return 0; } @@ -1084,10 +1362,11 @@ void cpuhp_report_idle_dead(void) struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); BUG_ON(st->state != CPUHP_AP_OFFLINE); - rcu_report_dead(smp_processor_id()); + tick_assert_timekeeping_handover(); + rcutree_report_cpu_dead(); st->state = CPUHP_AP_IDLE_DEAD; /* - * We cannot call complete after rcu_report_dead() so we delegate it + * We cannot call complete after rcutree_report_cpu_dead() so we delegate it * to an online cpu. */ smp_call_function_single(cpumask_first(cpu_online_mask), @@ -1106,7 +1385,7 @@ static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, ret, cpu, cpuhp_get_step(st->state)->name, st->state); - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); if (st->state < prev_state) WARN_ON(cpuhp_invoke_callback_range(true, cpu, st, @@ -1133,7 +1412,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, cpuhp_tasks_frozen = tasks_frozen; - prev_state = cpuhp_set_state(st, target); + prev_state = cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. @@ -1164,7 +1443,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state < prev_state) { if (st->state == CPUHP_TEARDOWN_CPU) { - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } else { WARN(1, "DEAD callback error for CPU%d", cpu); @@ -1173,21 +1452,46 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, out: cpus_write_unlock(); - /* - * Do post unplug cleanup. This is still protected against - * concurrent CPU hotplug via cpu_add_remove_lock. - */ - lockup_detector_cleanup(); arch_smt_update(); - cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } +struct cpu_down_work { + unsigned int cpu; + enum cpuhp_state target; +}; + +static long __cpu_down_maps_locked(void *arg) +{ + struct cpu_down_work *work = arg; + + return _cpu_down(work->cpu, 0, work->target); +} + static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) { + struct cpu_down_work work = { .cpu = cpu, .target = target, }; + + /* + * If the platform does not support hotplug, report it explicitly to + * differentiate it from a transient offlining failure. + */ + if (cpu_hotplug_offline_disabled) + return -EOPNOTSUPP; if (cpu_hotplug_disabled) return -EBUSY; - return _cpu_down(cpu, 0, target); + + /* + * Ensure that the control task does not run on the to be offlined + * CPU to prevent a deadlock against cfs_b->period_timer. + * Also keep at least one housekeeping cpu onlined to avoid generating + * an empty sched_domain span. + */ + for_each_cpu_and(cpu, cpu_online_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)) { + if (cpu != work.cpu) + return work_on_cpu(cpu, __cpu_down_maps_locked, &work); + } + return -EBUSY; } static int cpu_down(unsigned int cpu, enum cpuhp_state target) @@ -1284,16 +1588,14 @@ void notify_cpu_starting(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); - int ret; - rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ + rcutree_report_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ cpumask_set_cpu(cpu, &cpus_booted_once_mask); - ret = cpuhp_invoke_callback_range(true, cpu, st, target); /* * STARTING must not fail! */ - WARN_ON_ONCE(ret); + cpuhp_invoke_callback_range_nofail(true, cpu, st, target); } /* @@ -1309,8 +1611,10 @@ void cpuhp_online_idle(enum cpuhp_state state) if (state != CPUHP_AP_ONLINE_IDLE) return; + cpuhp_ap_update_sync_state(SYNC_STATE_ONLINE); + /* - * Unpart the stopper thread before we start the idle loop (and start + * Unpark the stopper thread before we start the idle loop (and start * scheduling); this ensures the stopper task is always available. */ stop_machine_unpark(smp_processor_id()); @@ -1347,11 +1651,17 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) ret = PTR_ERR(idle); goto out; } + + /* + * Reset stale stack state from the last time this CPU was online. + */ + scs_task_reset(idle); + kasan_unpoison_task_stack(idle); } cpuhp_tasks_frozen = tasks_frozen; - cpuhp_set_state(st, target); + cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. @@ -1376,7 +1686,6 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) out: cpus_write_unlock(); arch_smt_update(); - cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } @@ -1387,9 +1696,6 @@ static int cpu_up(unsigned int cpu, enum cpuhp_state target) if (!cpu_possible(cpu)) { pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n", cpu); -#if defined(CONFIG_IA64) - pr_err("please check additional_cpus= boot parameter\n"); -#endif return -EINVAL; } @@ -1403,7 +1709,7 @@ static int cpu_up(unsigned int cpu, enum cpuhp_state target) err = -EBUSY; goto out; } - if (!cpu_smt_allowed(cpu)) { + if (!cpu_bootable(cpu)) { err = -EPERM; goto out; } @@ -1466,18 +1772,125 @@ int bringup_hibernate_cpu(unsigned int sleep_cpu) return 0; } -void bringup_nonboot_cpus(unsigned int setup_max_cpus) +static void __init cpuhp_bringup_mask(const struct cpumask *mask, unsigned int ncpus, + enum cpuhp_state target) { unsigned int cpu; - for_each_present_cpu(cpu) { - if (num_online_cpus() >= setup_max_cpus) + for_each_cpu(cpu, mask) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + + if (cpu_up(cpu, target) && can_rollback_cpu(st)) { + /* + * If this failed then cpu_up() might have only + * rolled back to CPUHP_BP_KICK_AP for the final + * online. Clean it up. NOOP if already rolled back. + */ + WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, CPUHP_OFFLINE)); + } + + if (!--ncpus) break; - if (!cpu_online(cpu)) - cpu_up(cpu, CPUHP_ONLINE); } } +#ifdef CONFIG_HOTPLUG_PARALLEL +static bool __cpuhp_parallel_bringup __ro_after_init = true; + +static int __init parallel_bringup_parse_param(char *arg) +{ + return kstrtobool(arg, &__cpuhp_parallel_bringup); +} +early_param("cpuhp.parallel", parallel_bringup_parse_param); + +#ifdef CONFIG_HOTPLUG_SMT +static inline bool cpuhp_smt_aware(void) +{ + return cpu_smt_max_threads > 1; +} + +static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) +{ + return cpu_primary_thread_mask; +} +#else +static inline bool cpuhp_smt_aware(void) +{ + return false; +} +static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) +{ + return cpu_none_mask; +} +#endif + +bool __weak arch_cpuhp_init_parallel_bringup(void) +{ + return true; +} + +/* + * On architectures which have enabled parallel bringup this invokes all BP + * prepare states for each of the to be onlined APs first. The last state + * sends the startup IPI to the APs. The APs proceed through the low level + * bringup code in parallel and then wait for the control CPU to release + * them one by one for the final onlining procedure. + * + * This avoids waiting for each AP to respond to the startup IPI in + * CPUHP_BRINGUP_CPU. + */ +static bool __init cpuhp_bringup_cpus_parallel(unsigned int ncpus) +{ + const struct cpumask *mask = cpu_present_mask; + + if (__cpuhp_parallel_bringup) + __cpuhp_parallel_bringup = arch_cpuhp_init_parallel_bringup(); + if (!__cpuhp_parallel_bringup) + return false; + + if (cpuhp_smt_aware()) { + const struct cpumask *pmask = cpuhp_get_primary_thread_mask(); + static struct cpumask tmp_mask __initdata; + + /* + * X86 requires to prevent that SMT siblings stopped while + * the primary thread does a microcode update for various + * reasons. Bring the primary threads up first. + */ + cpumask_and(&tmp_mask, mask, pmask); + cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_BP_KICK_AP); + cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_ONLINE); + /* Account for the online CPUs */ + ncpus -= num_online_cpus(); + if (!ncpus) + return true; + /* Create the mask for secondary CPUs */ + cpumask_andnot(&tmp_mask, mask, pmask); + mask = &tmp_mask; + } + + /* Bring the not-yet started CPUs up */ + cpuhp_bringup_mask(mask, ncpus, CPUHP_BP_KICK_AP); + cpuhp_bringup_mask(mask, ncpus, CPUHP_ONLINE); + return true; +} +#else +static inline bool cpuhp_bringup_cpus_parallel(unsigned int ncpus) { return false; } +#endif /* CONFIG_HOTPLUG_PARALLEL */ + +void __init bringup_nonboot_cpus(unsigned int max_cpus) +{ + if (!max_cpus) + return; + + /* Try parallel bringup optimization if enabled */ + if (cpuhp_bringup_cpus_parallel(max_cpus)) + return; + + /* Full per CPU serialized bringup */ + cpuhp_bringup_mask(cpu_present_mask, max_cpus, CPUHP_ONLINE); +} + #ifdef CONFIG_PM_SLEEP_SMP static cpumask_var_t frozen_cpus; @@ -1488,8 +1901,8 @@ int freeze_secondary_cpus(int primary) cpu_maps_update_begin(); if (primary == -1) { primary = cpumask_first(cpu_online_mask); - if (!housekeeping_cpu(primary, HK_FLAG_TIMER)) - primary = housekeeping_any_cpu(HK_FLAG_TIMER); + if (!housekeeping_cpu(primary, HK_TYPE_TIMER)) + primary = housekeeping_any_cpu(HK_TYPE_TIMER); } else { if (!cpu_online(primary)) primary = cpumask_first(cpu_online_mask); @@ -1502,8 +1915,8 @@ int freeze_secondary_cpus(int primary) cpumask_clear(frozen_cpus); pr_info("Disabling non-boot CPUs ...\n"); - for_each_online_cpu(cpu) { - if (cpu == primary) + for (cpu = nr_cpu_ids - 1; cpu >= 0; cpu--) { + if (!cpu_online(cpu) || cpu == primary) continue; if (pm_wakeup_pending()) { @@ -1654,10 +2067,10 @@ static struct cpuhp_step cpuhp_hp_states[] = { .teardown.single = NULL, .cant_stop = true, }, - [CPUHP_PERF_PREPARE] = { - .name = "perf:prepare", - .startup.single = perf_event_init_cpu, - .teardown.single = perf_event_exit_cpu, + [CPUHP_RANDOM_PREPARE] = { + .name = "random:prepare", + .startup.single = random_prepare_cpu, + .teardown.single = NULL, }, [CPUHP_WORKQUEUE_PREP] = { .name = "workqueue:prepare", @@ -1667,7 +2080,7 @@ static struct cpuhp_step cpuhp_hp_states[] = { [CPUHP_HRTIMERS_PREPARE] = { .name = "hrtimers:prepare", .startup.single = hrtimers_prepare_cpu, - .teardown.single = hrtimers_dead_cpu, + .teardown.single = NULL, }, [CPUHP_SMPCFD_PREPARE] = { .name = "smpcfd:prepare", @@ -1679,11 +2092,6 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = relay_prepare_cpu, .teardown.single = NULL, }, - [CPUHP_SLAB_PREPARE] = { - .name = "slab:prepare", - .startup.single = slab_prepare_cpu, - .teardown.single = slab_dead_cpu, - }, [CPUHP_RCUTREE_PREP] = { .name = "RCU/tree:prepare", .startup.single = rcutree_prepare_cpu, @@ -1699,13 +2107,38 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = timers_prepare_cpu, .teardown.single = timers_dead_cpu, }, - /* Kicks the plugged cpu into life */ + +#ifdef CONFIG_HOTPLUG_SPLIT_STARTUP + /* + * Kicks the AP alive. AP will wait in cpuhp_ap_sync_alive() until + * the next step will release it. + */ + [CPUHP_BP_KICK_AP] = { + .name = "cpu:kick_ap", + .startup.single = cpuhp_kick_ap_alive, + }, + + /* + * Waits for the AP to reach cpuhp_ap_sync_alive() and then + * releases it for the complete bringup. + */ + [CPUHP_BRINGUP_CPU] = { + .name = "cpu:bringup", + .startup.single = cpuhp_bringup_ap, + .teardown.single = finish_cpu, + .cant_stop = true, + }, +#else + /* + * All-in-one CPU bringup state which includes the kick alive. + */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = bringup_cpu, .teardown.single = finish_cpu, .cant_stop = true, }, +#endif /* Final state before CPU kills itself */ [CPUHP_AP_IDLE_DEAD] = { .name = "idle:dead", @@ -1734,6 +2167,16 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = NULL, .teardown.single = smpcfd_dying_cpu, }, + [CPUHP_AP_HRTIMERS_DYING] = { + .name = "hrtimers:dying", + .startup.single = hrtimers_cpu_starting, + .teardown.single = hrtimers_cpu_dying, + }, + [CPUHP_AP_TICK_DYING] = { + .name = "tick:dying", + .startup.single = NULL, + .teardown.single = tick_cpu_dying, + }, /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { @@ -1782,6 +2225,11 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = workqueue_online_cpu, .teardown.single = workqueue_offline_cpu, }, + [CPUHP_AP_RANDOM_ONLINE] = { + .name = "random:online", + .startup.single = random_online_cpu, + .teardown.single = NULL, + }, [CPUHP_AP_RCUTREE_ONLINE] = { .name = "RCU/tree:online", .startup.single = rcutree_online_cpu, @@ -2017,7 +2465,7 @@ EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance); * The caller needs to hold cpus read locked while calling this function. * Return: * On success: - * Positive state number if @state is CPUHP_AP_ONLINE_DYN; + * Positive state number if @state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN; * 0 for all other states * On failure: proper (negative) error code */ @@ -2040,7 +2488,7 @@ int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, ret = cpuhp_store_callbacks(state, name, startup, teardown, multi_instance); - dynstate = state == CPUHP_AP_ONLINE_DYN; + dynstate = state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN; if (ret > 0 && dynstate) { state = ret; ret = 0; @@ -2071,8 +2519,8 @@ int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, out: mutex_unlock(&cpuhp_state_mutex); /* - * If the requested state is CPUHP_AP_ONLINE_DYN, return the - * dynamically allocated state in case of success. + * If the requested state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN, + * return the dynamically allocated state in case of success. */ if (!ret && dynstate) return state; @@ -2217,6 +2665,12 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) for_each_online_cpu(cpu) { if (topology_is_primary_thread(cpu)) continue; + /* + * Disable can be called with CPU_SMT_ENABLED when changing + * from a higher to lower number of SMT threads per core. + */ + if (ctrlval == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu)) + continue; ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (ret) break; @@ -2241,6 +2695,14 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) return ret; } +/* Check if the core a CPU belongs to is online */ +#if !defined(topology_is_core_online) +static inline bool topology_is_core_online(unsigned int cpu) +{ + return true; +} +#endif + int cpuhp_smt_enable(void) { int cpu, ret = 0; @@ -2251,6 +2713,8 @@ int cpuhp_smt_enable(void) /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) continue; + if (!cpu_smt_thread_allowed(cpu) || !topology_is_core_online(cpu)) + continue; ret = _cpu_up(cpu, 0, CPUHP_ONLINE); if (ret) break; @@ -2304,8 +2768,10 @@ static ssize_t target_store(struct device *dev, struct device_attribute *attr, if (st->state < target) ret = cpu_up(dev->id, target); - else + else if (st->state > target) ret = cpu_down(dev->id, target); + else if (WARN_ON(st->target != target)) + st->target = target; out: unlock_device_hotplug(); return ret ? ret : count; @@ -2390,7 +2856,6 @@ static struct attribute *cpuhp_cpu_attrs[] = { static const struct attribute_group cpuhp_cpu_attr_group = { .attrs = cpuhp_cpu_attrs, .name = "hotplug", - NULL }; static ssize_t states_show(struct device *dev, @@ -2422,25 +2887,23 @@ static struct attribute *cpuhp_cpu_root_attrs[] = { static const struct attribute_group cpuhp_cpu_root_attr_group = { .attrs = cpuhp_cpu_root_attrs, .name = "hotplug", - NULL }; #ifdef CONFIG_HOTPLUG_SMT +static bool cpu_smt_num_threads_valid(unsigned int threads) +{ + if (IS_ENABLED(CONFIG_SMT_NUM_THREADS_DYNAMIC)) + return threads >= 1 && threads <= cpu_smt_max_threads; + return threads == 1 || threads == cpu_smt_max_threads; +} + static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - int ctrlval, ret; - - if (sysfs_streq(buf, "on")) - ctrlval = CPU_SMT_ENABLED; - else if (sysfs_streq(buf, "off")) - ctrlval = CPU_SMT_DISABLED; - else if (sysfs_streq(buf, "forceoff")) - ctrlval = CPU_SMT_FORCE_DISABLED; - else - return -EINVAL; + int ctrlval, ret, num_threads, orig_threads; + bool force_off; if (cpu_smt_control == CPU_SMT_FORCE_DISABLED) return -EPERM; @@ -2448,21 +2911,39 @@ __store_smt_control(struct device *dev, struct device_attribute *attr, if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return -ENODEV; + if (sysfs_streq(buf, "on")) { + ctrlval = CPU_SMT_ENABLED; + num_threads = cpu_smt_max_threads; + } else if (sysfs_streq(buf, "off")) { + ctrlval = CPU_SMT_DISABLED; + num_threads = 1; + } else if (sysfs_streq(buf, "forceoff")) { + ctrlval = CPU_SMT_FORCE_DISABLED; + num_threads = 1; + } else if (kstrtoint(buf, 10, &num_threads) == 0) { + if (num_threads == 1) + ctrlval = CPU_SMT_DISABLED; + else if (cpu_smt_num_threads_valid(num_threads)) + ctrlval = CPU_SMT_ENABLED; + else + return -EINVAL; + } else { + return -EINVAL; + } + ret = lock_device_hotplug_sysfs(); if (ret) return ret; - if (ctrlval != cpu_smt_control) { - switch (ctrlval) { - case CPU_SMT_ENABLED: - ret = cpuhp_smt_enable(); - break; - case CPU_SMT_DISABLED: - case CPU_SMT_FORCE_DISABLED: - ret = cpuhp_smt_disable(ctrlval); - break; - } - } + orig_threads = cpu_smt_num_threads; + cpu_smt_num_threads = num_threads; + + force_off = ctrlval != cpu_smt_control && ctrlval == CPU_SMT_FORCE_DISABLED; + + if (num_threads > orig_threads) + ret = cpuhp_smt_enable(); + else if (num_threads < orig_threads || force_off) + ret = cpuhp_smt_disable(ctrlval); unlock_device_hotplug(); return ret ? ret : count; @@ -2490,7 +2971,18 @@ static ssize_t control_show(struct device *dev, { const char *state = smt_states[cpu_smt_control]; - return snprintf(buf, PAGE_SIZE - 2, "%s\n", state); +#ifdef CONFIG_HOTPLUG_SMT + /* + * If SMT is enabled but not all threads are enabled then show the + * number of threads. If all threads are enabled show "on". Otherwise + * show the state name. + */ + if (cpu_smt_control == CPU_SMT_ENABLED && + cpu_smt_num_threads != cpu_smt_max_threads) + return sysfs_emit(buf, "%d\n", cpu_smt_num_threads); +#endif + + return sysfs_emit(buf, "%s\n", state); } static ssize_t control_store(struct device *dev, struct device_attribute *attr, @@ -2503,7 +2995,7 @@ static DEVICE_ATTR_RW(control); static ssize_t active_show(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE - 2, "%d\n", sched_smt_active()); + return sysfs_emit(buf, "%d\n", sched_smt_active()); } static DEVICE_ATTR_RO(active); @@ -2516,27 +3008,37 @@ static struct attribute *cpuhp_smt_attrs[] = { static const struct attribute_group cpuhp_smt_attr_group = { .attrs = cpuhp_smt_attrs, .name = "smt", - NULL }; static int __init cpu_smt_sysfs_init(void) { - return sysfs_create_group(&cpu_subsys.dev_root->kobj, - &cpuhp_smt_attr_group); + struct device *dev_root; + int ret = -ENODEV; + + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + ret = sysfs_create_group(&dev_root->kobj, &cpuhp_smt_attr_group); + put_device(dev_root); + } + return ret; } static int __init cpuhp_sysfs_init(void) { + struct device *dev_root; int cpu, ret; ret = cpu_smt_sysfs_init(); if (ret) return ret; - ret = sysfs_create_group(&cpu_subsys.dev_root->kobj, - &cpuhp_cpu_root_attr_group); - if (ret) - return ret; + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + ret = sysfs_create_group(&dev_root->kobj, &cpuhp_cpu_root_attr_group); + put_device(dev_root); + if (ret) + return ret; + } for_each_possible_cpu(cpu) { struct device *dev = get_cpu_device(cpu); @@ -2581,16 +3083,22 @@ const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL; EXPORT_SYMBOL(cpu_all_bits); #ifdef CONFIG_INIT_ALL_POSSIBLE -struct cpumask __cpu_possible_mask __read_mostly +struct cpumask __cpu_possible_mask __ro_after_init = {CPU_BITS_ALL}; +unsigned int __num_possible_cpus __ro_after_init = NR_CPUS; #else -struct cpumask __cpu_possible_mask __read_mostly; +struct cpumask __cpu_possible_mask __ro_after_init; +unsigned int __num_possible_cpus __ro_after_init; #endif EXPORT_SYMBOL(__cpu_possible_mask); +EXPORT_SYMBOL(__num_possible_cpus); struct cpumask __cpu_online_mask __read_mostly; EXPORT_SYMBOL(__cpu_online_mask); +struct cpumask __cpu_enabled_mask __read_mostly; +EXPORT_SYMBOL(__cpu_enabled_mask); + struct cpumask __cpu_present_mask __read_mostly; EXPORT_SYMBOL(__cpu_present_mask); @@ -2611,11 +3119,7 @@ void init_cpu_present(const struct cpumask *src) void init_cpu_possible(const struct cpumask *src) { cpumask_copy(&__cpu_possible_mask, src); -} - -void init_cpu_online(const struct cpumask *src) -{ - cpumask_copy(&__cpu_online_mask, src); + __num_possible_cpus = cpumask_weight(&__cpu_possible_mask); } void set_cpu_online(unsigned int cpu, bool online) @@ -2640,6 +3144,21 @@ void set_cpu_online(unsigned int cpu, bool online) } /* + * This should be marked __init, but there is a boatload of call sites + * which need to be fixed up to do so. Sigh... + */ +void set_cpu_possible(unsigned int cpu, bool possible) +{ + if (possible) { + if (!cpumask_test_and_set_cpu(cpu, &__cpu_possible_mask)) + __num_possible_cpus++; + } else { + if (cpumask_test_and_clear_cpu(cpu, &__cpu_possible_mask)) + __num_possible_cpus--; + } +} + +/* * Activate the first processor. */ void __init boot_cpu_init(void) @@ -2664,13 +3183,46 @@ void __init boot_cpu_hotplug_init(void) { #ifdef CONFIG_SMP cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask); + atomic_set(this_cpu_ptr(&cpuhp_state.ap_sync_state), SYNC_STATE_ONLINE); #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); + this_cpu_write(cpuhp_state.target, CPUHP_ONLINE); } +#ifdef CONFIG_CPU_MITIGATIONS /* - * These are used for a global "mitigations=" cmdline option for toggling - * optional CPU mitigations. + * All except the cross-thread attack vector are mitigated by default. + * Cross-thread mitigation often requires disabling SMT which is expensive + * so cross-thread mitigations are only partially enabled by default. + * + * Guest-to-Host and Guest-to-Guest vectors are only needed if KVM support is + * present. + */ +static bool attack_vectors[NR_CPU_ATTACK_VECTORS] __ro_after_init = { + [CPU_MITIGATE_USER_KERNEL] = true, + [CPU_MITIGATE_USER_USER] = true, + [CPU_MITIGATE_GUEST_HOST] = IS_ENABLED(CONFIG_KVM), + [CPU_MITIGATE_GUEST_GUEST] = IS_ENABLED(CONFIG_KVM), +}; + +bool cpu_attack_vector_mitigated(enum cpu_attack_vectors v) +{ + if (v < NR_CPU_ATTACK_VECTORS) + return attack_vectors[v]; + + WARN_ONCE(1, "Invalid attack vector %d\n", v); + return false; +} + +/* + * There are 3 global options, 'off', 'auto', 'auto,nosmt'. These may optionally + * be combined with attack-vector disables which follow them. + * + * Examples: + * mitigations=auto,no_user_kernel,no_user_user,no_cross_thread + * mitigations=auto,nosmt,no_guest_host,no_guest_guest + * + * mitigations=off is equivalent to disabling all attack vectors. */ enum cpu_mitigations { CPU_MITIGATIONS_OFF, @@ -2678,24 +3230,99 @@ enum cpu_mitigations { CPU_MITIGATIONS_AUTO_NOSMT, }; -static enum cpu_mitigations cpu_mitigations __ro_after_init = - CPU_MITIGATIONS_AUTO; +enum { + NO_USER_KERNEL, + NO_USER_USER, + NO_GUEST_HOST, + NO_GUEST_GUEST, + NO_CROSS_THREAD, + NR_VECTOR_PARAMS, +}; + +enum smt_mitigations smt_mitigations __ro_after_init = SMT_MITIGATIONS_AUTO; +static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; + +static const match_table_t global_mitigations = { + { CPU_MITIGATIONS_AUTO_NOSMT, "auto,nosmt"}, + { CPU_MITIGATIONS_AUTO, "auto"}, + { CPU_MITIGATIONS_OFF, "off"}, +}; + +static const match_table_t vector_mitigations = { + { NO_USER_KERNEL, "no_user_kernel"}, + { NO_USER_USER, "no_user_user"}, + { NO_GUEST_HOST, "no_guest_host"}, + { NO_GUEST_GUEST, "no_guest_guest"}, + { NO_CROSS_THREAD, "no_cross_thread"}, + { NR_VECTOR_PARAMS, NULL}, +}; + +static int __init mitigations_parse_global_opt(char *arg) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(global_mitigations); i++) { + const char *pattern = global_mitigations[i].pattern; + + if (!strncmp(arg, pattern, strlen(pattern))) { + cpu_mitigations = global_mitigations[i].token; + return strlen(pattern); + } + } + + return 0; +} static int __init mitigations_parse_cmdline(char *arg) { - if (!strcmp(arg, "off")) - cpu_mitigations = CPU_MITIGATIONS_OFF; - else if (!strcmp(arg, "auto")) - cpu_mitigations = CPU_MITIGATIONS_AUTO; - else if (!strcmp(arg, "auto,nosmt")) - cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT; - else - pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n", - arg); + char *s, *p; + int len; + + len = mitigations_parse_global_opt(arg); + + if (cpu_mitigations_off()) { + memset(attack_vectors, 0, sizeof(attack_vectors)); + smt_mitigations = SMT_MITIGATIONS_OFF; + } else if (cpu_mitigations_auto_nosmt()) { + smt_mitigations = SMT_MITIGATIONS_ON; + } + + p = arg + len; + + if (!*p) + return 0; + + /* Attack vector controls may come after the ',' */ + if (*p++ != ',' || !IS_ENABLED(CONFIG_ARCH_HAS_CPU_ATTACK_VECTORS)) { + pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n", arg); + return 0; + } + + while ((s = strsep(&p, ",")) != NULL) { + switch (match_token(s, vector_mitigations, NULL)) { + case NO_USER_KERNEL: + attack_vectors[CPU_MITIGATE_USER_KERNEL] = false; + break; + case NO_USER_USER: + attack_vectors[CPU_MITIGATE_USER_USER] = false; + break; + case NO_GUEST_HOST: + attack_vectors[CPU_MITIGATE_GUEST_HOST] = false; + break; + case NO_GUEST_GUEST: + attack_vectors[CPU_MITIGATE_GUEST_GUEST] = false; + break; + case NO_CROSS_THREAD: + smt_mitigations = SMT_MITIGATIONS_OFF; + break; + default: + pr_crit("Unsupported mitigations options %s\n", s); + return 0; + } + } return 0; } -early_param("mitigations", mitigations_parse_cmdline); /* mitigations=off */ bool cpu_mitigations_off(void) @@ -2710,3 +3337,11 @@ bool cpu_mitigations_auto_nosmt(void) return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; } EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt); +#else +static int __init mitigations_parse_cmdline(char *arg) +{ + pr_crit("Kernel compiled without mitigations, ignoring 'mitigations'; system may still be vulnerable\n"); + return 0; +} +#endif +early_param("mitigations", mitigations_parse_cmdline); |