diff options
Diffstat (limited to 'kernel')
37 files changed, 1287 insertions, 1049 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 76d5a794e426..633a650d7aeb 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -328,8 +328,8 @@ static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key) } /* only called from syscall */ -static int fd_array_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, + void *key, void *value, u64 map_flags) { struct bpf_array *array = container_of(map, struct bpf_array, map); void *new_ptr, *old_ptr; @@ -342,7 +342,7 @@ static int fd_array_map_update_elem(struct bpf_map *map, void *key, return -E2BIG; ufd = *(u32 *)value; - new_ptr = map->ops->map_fd_get_ptr(map, ufd); + new_ptr = map->ops->map_fd_get_ptr(map, map_file, ufd); if (IS_ERR(new_ptr)) return PTR_ERR(new_ptr); @@ -371,10 +371,12 @@ static int fd_array_map_delete_elem(struct bpf_map *map, void *key) } } -static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd) +static void *prog_fd_array_get_ptr(struct bpf_map *map, + struct file *map_file, int fd) { struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog = bpf_prog_get(fd); + if (IS_ERR(prog)) return prog; @@ -382,14 +384,13 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd) bpf_prog_put(prog); return ERR_PTR(-EINVAL); } + return prog; } static void prog_fd_array_put_ptr(void *ptr) { - struct bpf_prog *prog = ptr; - - bpf_prog_put_rcu(prog); + bpf_prog_put(ptr); } /* decrement refcnt of all bpf_progs that are stored in this map */ @@ -407,7 +408,6 @@ static const struct bpf_map_ops prog_array_ops = { .map_free = fd_array_map_free, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, - .map_update_elem = fd_array_map_update_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = prog_fd_array_get_ptr, .map_fd_put_ptr = prog_fd_array_put_ptr, @@ -425,59 +425,105 @@ static int __init register_prog_array_map(void) } late_initcall(register_prog_array_map); -static void perf_event_array_map_free(struct bpf_map *map) +static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file, + struct file *map_file) { - bpf_fd_array_map_clear(map); - fd_array_map_free(map); + struct bpf_event_entry *ee; + + ee = kzalloc(sizeof(*ee), GFP_ATOMIC); + if (ee) { + ee->event = perf_file->private_data; + ee->perf_file = perf_file; + ee->map_file = map_file; + } + + return ee; } -static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd) +static void __bpf_event_entry_free(struct rcu_head *rcu) { - struct perf_event *event; - const struct perf_event_attr *attr; - struct file *file; + struct bpf_event_entry *ee; - file = perf_event_get(fd); - if (IS_ERR(file)) - return file; + ee = container_of(rcu, struct bpf_event_entry, rcu); + fput(ee->perf_file); + kfree(ee); +} - event = file->private_data; +static void bpf_event_entry_free_rcu(struct bpf_event_entry *ee) +{ + call_rcu(&ee->rcu, __bpf_event_entry_free); +} - attr = perf_event_attrs(event); - if (IS_ERR(attr)) - goto err; +static void *perf_event_fd_array_get_ptr(struct bpf_map *map, + struct file *map_file, int fd) +{ + const struct perf_event_attr *attr; + struct bpf_event_entry *ee; + struct perf_event *event; + struct file *perf_file; - if (attr->inherit) - goto err; + perf_file = perf_event_get(fd); + if (IS_ERR(perf_file)) + return perf_file; - if (attr->type == PERF_TYPE_RAW) - return file; + event = perf_file->private_data; + ee = ERR_PTR(-EINVAL); - if (attr->type == PERF_TYPE_HARDWARE) - return file; + attr = perf_event_attrs(event); + if (IS_ERR(attr) || attr->inherit) + goto err_out; + + switch (attr->type) { + case PERF_TYPE_SOFTWARE: + if (attr->config != PERF_COUNT_SW_BPF_OUTPUT) + goto err_out; + /* fall-through */ + case PERF_TYPE_RAW: + case PERF_TYPE_HARDWARE: + ee = bpf_event_entry_gen(perf_file, map_file); + if (ee) + return ee; + ee = ERR_PTR(-ENOMEM); + /* fall-through */ + default: + break; + } - if (attr->type == PERF_TYPE_SOFTWARE && - attr->config == PERF_COUNT_SW_BPF_OUTPUT) - return file; -err: - fput(file); - return ERR_PTR(-EINVAL); +err_out: + fput(perf_file); + return ee; } static void perf_event_fd_array_put_ptr(void *ptr) { - fput((struct file *)ptr); + bpf_event_entry_free_rcu(ptr); +} + +static void perf_event_fd_array_release(struct bpf_map *map, + struct file *map_file) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + struct bpf_event_entry *ee; + int i; + + rcu_read_lock(); + for (i = 0; i < array->map.max_entries; i++) { + ee = READ_ONCE(array->ptrs[i]); + if (ee && ee->map_file == map_file) + fd_array_map_delete_elem(map, &i); + } + rcu_read_unlock(); } static const struct bpf_map_ops perf_event_array_ops = { .map_alloc = fd_array_map_alloc, - .map_free = perf_event_array_map_free, + .map_free = fd_array_map_free, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, - .map_update_elem = fd_array_map_update_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = perf_event_fd_array_get_ptr, .map_fd_put_ptr = perf_event_fd_array_put_ptr, + .map_release = perf_event_fd_array_release, }; static struct bpf_map_type_list perf_event_array_type __read_mostly = { @@ -491,3 +537,46 @@ static int __init register_perf_event_array_map(void) return 0; } late_initcall(register_perf_event_array_map); + +#ifdef CONFIG_SOCK_CGROUP_DATA +static void *cgroup_fd_array_get_ptr(struct bpf_map *map, + struct file *map_file /* not used */, + int fd) +{ + return cgroup_get_from_fd(fd); +} + +static void cgroup_fd_array_put_ptr(void *ptr) +{ + /* cgroup_put free cgrp after a rcu grace period */ + cgroup_put(ptr); +} + +static void cgroup_fd_array_free(struct bpf_map *map) +{ + bpf_fd_array_map_clear(map); + fd_array_map_free(map); +} + +static const struct bpf_map_ops cgroup_array_ops = { + .map_alloc = fd_array_map_alloc, + .map_free = cgroup_fd_array_free, + .map_get_next_key = array_map_get_next_key, + .map_lookup_elem = fd_array_map_lookup_elem, + .map_delete_elem = fd_array_map_delete_elem, + .map_fd_get_ptr = cgroup_fd_array_get_ptr, + .map_fd_put_ptr = cgroup_fd_array_put_ptr, +}; + +static struct bpf_map_type_list cgroup_array_type __read_mostly = { + .ops = &cgroup_array_ops, + .type = BPF_MAP_TYPE_CGROUP_ARRAY, +}; + +static int __init register_cgroup_array_map(void) +{ + bpf_register_map_type(&cgroup_array_type); + return 0; +} +late_initcall(register_cgroup_array_map); +#endif diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index b94a36550591..03fd23d4d587 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -719,14 +719,13 @@ select_insn: if (unlikely(index >= array->map.max_entries)) goto out; - if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT)) goto out; tail_call_cnt++; prog = READ_ONCE(array->ptrs[index]); - if (unlikely(!prog)) + if (!prog) goto out; /* ARG1 at this point is guaranteed to point to CTX from @@ -1055,9 +1054,11 @@ const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) return NULL; } -const struct bpf_func_proto * __weak bpf_get_event_output_proto(void) +u64 __weak +bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, + void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { - return NULL; + return -ENOTSUPP; } /* Always built-in helper functions. */ diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index ad7a0573f71b..1ea3afba1a4f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -101,7 +101,7 @@ const struct bpf_func_proto bpf_get_prandom_u32_proto = { static u64 bpf_get_smp_processor_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { - return raw_smp_processor_id(); + return smp_processor_id(); } const struct bpf_func_proto bpf_get_smp_processor_id_proto = { diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 318858edb1cd..5967b870a895 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -11,7 +11,7 @@ * version 2 as published by the Free Software Foundation. */ -#include <linux/module.h> +#include <linux/init.h> #include <linux/magic.h> #include <linux/major.h> #include <linux/mount.h> @@ -367,8 +367,6 @@ static struct file_system_type bpf_fs_type = { .kill_sb = kill_litter_super, }; -MODULE_ALIAS_FS("bpf"); - static int __init bpf_init(void) { int ret; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 46ecce4b79ed..228f962447a5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -124,7 +124,12 @@ void bpf_map_put_with_uref(struct bpf_map *map) static int bpf_map_release(struct inode *inode, struct file *filp) { - bpf_map_put_with_uref(filp->private_data); + struct bpf_map *map = filp->private_data; + + if (map->ops->map_release) + map->ops->map_release(map, filp); + + bpf_map_put_with_uref(map); return 0; } @@ -387,6 +392,13 @@ static int map_update_elem(union bpf_attr *attr) err = bpf_percpu_hash_update(map, key, value, attr->flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_update(map, key, value, attr->flags); + } else if (map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || + map->map_type == BPF_MAP_TYPE_PROG_ARRAY || + map->map_type == BPF_MAP_TYPE_CGROUP_ARRAY) { + rcu_read_lock(); + err = bpf_fd_array_map_update_elem(map, f.file, key, value, + attr->flags); + rcu_read_unlock(); } else { rcu_read_lock(); err = map->ops->map_update_elem(map, key, value, attr->flags); @@ -612,7 +624,7 @@ static void bpf_prog_uncharge_memlock(struct bpf_prog *prog) free_uid(user); } -static void __prog_put_common(struct rcu_head *rcu) +static void __bpf_prog_put_rcu(struct rcu_head *rcu) { struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); @@ -621,17 +633,10 @@ static void __prog_put_common(struct rcu_head *rcu) bpf_prog_free(aux->prog); } -/* version of bpf_prog_put() that is called after a grace period */ -void bpf_prog_put_rcu(struct bpf_prog *prog) -{ - if (atomic_dec_and_test(&prog->aux->refcnt)) - call_rcu(&prog->aux->rcu, __prog_put_common); -} - void bpf_prog_put(struct bpf_prog *prog) { if (atomic_dec_and_test(&prog->aux->refcnt)) - __prog_put_common(&prog->aux->rcu); + call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); } EXPORT_SYMBOL_GPL(bpf_prog_put); @@ -639,7 +644,7 @@ static int bpf_prog_release(struct inode *inode, struct file *filp) { struct bpf_prog *prog = filp->private_data; - bpf_prog_put_rcu(prog); + bpf_prog_put(prog); return 0; } @@ -653,7 +658,7 @@ int bpf_prog_new_fd(struct bpf_prog *prog) O_RDWR | O_CLOEXEC); } -static struct bpf_prog *__bpf_prog_get(struct fd f) +static struct bpf_prog *____bpf_prog_get(struct fd f) { if (!f.file) return ERR_PTR(-EBADF); @@ -665,33 +670,50 @@ static struct bpf_prog *__bpf_prog_get(struct fd f) return f.file->private_data; } -struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) +struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i) { - if (atomic_inc_return(&prog->aux->refcnt) > BPF_MAX_REFCNT) { - atomic_dec(&prog->aux->refcnt); + if (atomic_add_return(i, &prog->aux->refcnt) > BPF_MAX_REFCNT) { + atomic_sub(i, &prog->aux->refcnt); return ERR_PTR(-EBUSY); } return prog; } +EXPORT_SYMBOL_GPL(bpf_prog_add); -/* called by sockets/tracing/seccomp before attaching program to an event - * pairs with bpf_prog_put() - */ -struct bpf_prog *bpf_prog_get(u32 ufd) +struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) +{ + return bpf_prog_add(prog, 1); +} + +static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type) { struct fd f = fdget(ufd); struct bpf_prog *prog; - prog = __bpf_prog_get(f); + prog = ____bpf_prog_get(f); if (IS_ERR(prog)) return prog; + if (type && prog->type != *type) { + prog = ERR_PTR(-EINVAL); + goto out; + } prog = bpf_prog_inc(prog); +out: fdput(f); - return prog; } -EXPORT_SYMBOL_GPL(bpf_prog_get); + +struct bpf_prog *bpf_prog_get(u32 ufd) +{ + return __bpf_prog_get(ufd, NULL); +} + +struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) +{ + return __bpf_prog_get(ufd, &type); +} +EXPORT_SYMBOL_GPL(bpf_prog_get_type); /* last field in 'union bpf_attr' used by this command */ #define BPF_PROG_LOAD_LAST_FIELD kern_version diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index eec9f90ba030..f72f23b8fdab 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -653,6 +653,16 @@ static int check_map_access(struct verifier_env *env, u32 regno, int off, #define MAX_PACKET_OFF 0xffff +static bool may_write_pkt_data(enum bpf_prog_type type) +{ + switch (type) { + case BPF_PROG_TYPE_XDP: + return true; + default: + return false; + } +} + static int check_packet_access(struct verifier_env *env, u32 regno, int off, int size) { @@ -713,6 +723,7 @@ static int check_ptr_alignment(struct verifier_env *env, struct reg_state *reg, switch (env->prog->type) { case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: + case BPF_PROG_TYPE_XDP: break; default: verbose("verifier is misconfigured\n"); @@ -805,10 +816,15 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off, err = check_stack_read(state, off, size, value_regno); } } else if (state->regs[regno].type == PTR_TO_PACKET) { - if (t == BPF_WRITE) { + if (t == BPF_WRITE && !may_write_pkt_data(env->prog->type)) { verbose("cannot write into packet\n"); return -EACCES; } + if (t == BPF_WRITE && value_regno >= 0 && + is_pointer_value(env, value_regno)) { + verbose("R%d leaks addr into packet\n", value_regno); + return -EACCES; + } err = check_packet_access(env, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown_value(state->regs, value_regno); @@ -1035,6 +1051,10 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) if (func_id != BPF_FUNC_get_stackid) goto error; break; + case BPF_MAP_TYPE_CGROUP_ARRAY: + if (func_id != BPF_FUNC_skb_in_cgroup) + goto error; + break; default: break; } @@ -1054,6 +1074,10 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) if (map->map_type != BPF_MAP_TYPE_STACK_TRACE) goto error; break; + case BPF_FUNC_skb_in_cgroup: + if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY) + goto error; + break; default: break; } diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 33a2f63d4a10..d1c51b7f5221 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -61,6 +61,7 @@ #include <linux/cpuset.h> #include <linux/proc_ns.h> #include <linux/nsproxy.h> +#include <linux/file.h> #include <net/sock.h> /* @@ -2208,12 +2209,8 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, goto out_unlock; } - /* - * We know this subsystem has not yet been bound. Users in a non-init - * user namespace may only mount hierarchies with no bound subsystems, - * i.e. 'none,name=user1' - */ - if (!opts.none && !capable(CAP_SYS_ADMIN)) { + /* Hierarchies may only be created in the initial cgroup namespace. */ + if (ns != &init_cgroup_ns) { ret = -EPERM; goto out_unlock; } @@ -2955,6 +2952,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) int retval = 0; mutex_lock(&cgroup_mutex); + percpu_down_write(&cgroup_threadgroup_rwsem); for_each_root(root) { struct cgroup *from_cgrp; @@ -2969,6 +2967,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) if (retval) break; } + percpu_up_write(&cgroup_threadgroup_rwsem); mutex_unlock(&cgroup_mutex); return retval; @@ -4336,6 +4335,8 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) mutex_lock(&cgroup_mutex); + percpu_down_write(&cgroup_threadgroup_rwsem); + /* all tasks in @from are being moved, all csets are source */ spin_lock_irq(&css_set_lock); list_for_each_entry(link, &from->cset_links, cset_link) @@ -4364,6 +4365,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) } while (task && !ret); out_err: cgroup_migrate_finish(&preloaded_csets); + percpu_up_write(&cgroup_threadgroup_rwsem); mutex_unlock(&cgroup_mutex); return ret; } @@ -6204,6 +6206,40 @@ struct cgroup *cgroup_get_from_path(const char *path) } EXPORT_SYMBOL_GPL(cgroup_get_from_path); +/** + * cgroup_get_from_fd - get a cgroup pointer from a fd + * @fd: fd obtained by open(cgroup2_dir) + * + * Find the cgroup from a fd which should be obtained + * by opening a cgroup directory. Returns a pointer to the + * cgroup on success. ERR_PTR is returned if the cgroup + * cannot be found. + */ +struct cgroup *cgroup_get_from_fd(int fd) +{ + struct cgroup_subsys_state *css; + struct cgroup *cgrp; + struct file *f; + + f = fget_raw(fd); + if (!f) + return ERR_PTR(-EBADF); + + css = css_tryget_online_from_dir(f->f_path.dentry, NULL); + fput(f); + if (IS_ERR(css)) + return ERR_CAST(css); + + cgrp = css->cgroup; + if (!cgroup_on_dfl(cgrp)) { + cgroup_put(cgrp); + return ERR_PTR(-EBADF); + } + + return cgrp; +} +EXPORT_SYMBOL_GPL(cgroup_get_from_fd); + /* * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data * definition in cgroup-defs.h. @@ -6304,14 +6340,11 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - mutex_lock(&cgroup_mutex); + /* It is not safe to take cgroup_mutex here */ spin_lock_irq(&css_set_lock); - cset = task_css_set(current); get_css_set(cset); - spin_unlock_irq(&css_set_lock); - mutex_unlock(&cgroup_mutex); new_ns = alloc_cgroup_ns(); if (IS_ERR(new_ns)) { diff --git a/kernel/cpu.c b/kernel/cpu.c index 7b61887f7ccd..341bf80f80bd 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -517,6 +517,13 @@ static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, if (!cpu_online(cpu)) return 0; + /* + * If we are up and running, use the hotplug thread. For early calls + * we invoke the thread function directly. + */ + if (!st->thread) + return cpuhp_invoke_callback(cpu, state, cb); + st->cb_state = state; st->cb = cb; /* @@ -1173,6 +1180,31 @@ static struct cpuhp_step cpuhp_bp_states[] = { .teardown = NULL, .cant_stop = true, }, + [CPUHP_PERF_PREPARE] = { + .name = "perf prepare", + .startup = perf_event_init_cpu, + .teardown = perf_event_exit_cpu, + }, + [CPUHP_WORKQUEUE_PREP] = { + .name = "workqueue prepare", + .startup = workqueue_prepare_cpu, + .teardown = NULL, + }, + [CPUHP_HRTIMERS_PREPARE] = { + .name = "hrtimers prepare", + .startup = hrtimers_prepare_cpu, + .teardown = hrtimers_dead_cpu, + }, + [CPUHP_SMPCFD_PREPARE] = { + .name = "SMPCFD prepare", + .startup = smpcfd_prepare_cpu, + .teardown = smpcfd_dead_cpu, + }, + [CPUHP_RCUTREE_PREP] = { + .name = "RCU-tree prepare", + .startup = rcutree_prepare_cpu, + .teardown = rcutree_dead_cpu, + }, /* * Preparatory and dead notifiers. Will be replaced once the notifiers * are converted to states. @@ -1184,6 +1216,16 @@ static struct cpuhp_step cpuhp_bp_states[] = { .skip_onerr = true, .cant_stop = true, }, + /* + * On the tear-down path, timers_dead_cpu() must be invoked + * before blk_mq_queue_reinit_notify() from notify_dead(), + * otherwise a RCU stall occurs. + */ + [CPUHP_TIMERS_DEAD] = { + .name = "timers dead", + .startup = NULL, + .teardown = timers_dead_cpu, + }, /* Kicks the plugged cpu into life */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", @@ -1191,6 +1233,10 @@ static struct cpuhp_step cpuhp_bp_states[] = { .teardown = NULL, .cant_stop = true, }, + [CPUHP_AP_SMPCFD_DYING] = { + .startup = NULL, + .teardown = smpcfd_dying_cpu, + }, /* * Handled on controll processor until the plugged processor manages * this itself. @@ -1227,6 +1273,10 @@ static struct cpuhp_step cpuhp_ap_states[] = { .startup = sched_cpu_starting, .teardown = sched_cpu_dying, }, + [CPUHP_AP_RCUTREE_DYING] = { + .startup = NULL, + .teardown = rcutree_dying_cpu, + }, /* * Low level startup/teardown notifiers. Run with interrupts * disabled. Will be removed once the notifiers are converted to @@ -1250,6 +1300,22 @@ static struct cpuhp_step cpuhp_ap_states[] = { .startup = smpboot_unpark_threads, .teardown = NULL, }, + [CPUHP_AP_PERF_ONLINE] = { + .name = "perf online", + .startup = perf_event_init_cpu, + .teardown = perf_event_exit_cpu, + }, + [CPUHP_AP_WORKQUEUE_ONLINE] = { + .name = "workqueue online", + .startup = workqueue_online_cpu, + .teardown = workqueue_offline_cpu, + }, + [CPUHP_AP_RCUTREE_ONLINE] = { + .name = "RCU-tree online", + .startup = rcutree_online_cpu, + .teardown = rcutree_offline_cpu, + }, + /* * Online/down_prepare notifiers. Will be removed once the notifiers * are converted to states. diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 73e93e53884d..c7fd2778ed50 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1034,15 +1034,6 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, { bool need_loop; - /* - * Allow tasks that have access to memory reserves because they have - * been OOM killed to get memory anywhere. - */ - if (unlikely(test_thread_flag(TIF_MEMDIE))) - return; - if (current->flags & PF_EXITING) /* Let dying task have memory */ - return; - task_lock(tsk); /* * Determine if a loop is necessary if another thread is doing diff --git a/kernel/events/core.c b/kernel/events/core.c index 79dae188a987..356a6c7cb52a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5617,16 +5617,26 @@ void perf_output_sample(struct perf_output_handle *handle, } if (sample_type & PERF_SAMPLE_RAW) { - if (data->raw) { - u32 raw_size = data->raw->size; - u32 real_size = round_up(raw_size + sizeof(u32), - sizeof(u64)) - sizeof(u32); - u64 zero = 0; - - perf_output_put(handle, real_size); - __output_copy(handle, data->raw->data, raw_size); - if (real_size - raw_size) - __output_copy(handle, &zero, real_size - raw_size); + struct perf_raw_record *raw = data->raw; + + if (raw) { + struct perf_raw_frag *frag = &raw->frag; + + perf_output_put(handle, raw->size); + do { + if (frag->copy) { + __output_custom(handle, frag->copy, + frag->data, frag->size); + } else { + __output_copy(handle, frag->data, + frag->size); + } + if (perf_raw_frag_last(frag)) + break; + frag = frag->next; + } while (1); + if (frag->pad) + __output_skip(handle, NULL, frag->pad); } else { struct { u32 size; @@ -5751,14 +5761,28 @@ void perf_prepare_sample(struct perf_event_header *header, } if (sample_type & PERF_SAMPLE_RAW) { - int size = sizeof(u32); - - if (data->raw) - size += data->raw->size; - else - size += sizeof(u32); + struct perf_raw_record *raw = data->raw; + int size; + + if (raw) { + struct perf_raw_frag *frag = &raw->frag; + u32 sum = 0; + + do { + sum += frag->size; + if (perf_raw_frag_last(frag)) + break; + frag = frag->next; + } while (1); + + size = round_up(sum + sizeof(u32), sizeof(u64)); + raw->size = size - sizeof(u32); + frag->pad = raw->size - sum; + } else { + size = sizeof(u64); + } - header->size += round_up(size, sizeof(u64)); + header->size += size; } if (sample_type & PERF_SAMPLE_BRANCH_STACK) { @@ -7398,7 +7422,7 @@ static struct pmu perf_swevent = { static int perf_tp_filter_match(struct perf_event *event, struct perf_sample_data *data) { - void *record = data->raw->data; + void *record = data->raw->frag.data; /* only top level events have filters set */ if (event->parent) @@ -7454,8 +7478,10 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct perf_event *event; struct perf_raw_record raw = { - .size = entry_size, - .data = record, + .frag = { + .size = entry_size, + .data = record, + }, }; perf_sample_data_init(&data, 0, 0); @@ -7596,7 +7622,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event) prog = event->tp_event->prog; if (prog) { event->tp_event->prog = NULL; - bpf_prog_put_rcu(prog); + bpf_prog_put(prog); } } @@ -10331,7 +10357,7 @@ static void __init perf_event_init_all_cpus(void) } } -static void perf_event_init_cpu(int cpu) +int perf_event_init_cpu(unsigned int cpu) { struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); @@ -10344,6 +10370,7 @@ static void perf_event_init_cpu(int cpu) rcu_assign_pointer(swhash->swevent_hlist, hlist); } mutex_unlock(&swhash->hlist_mutex); + return 0; } #if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC_CORE @@ -10375,14 +10402,17 @@ static void perf_event_exit_cpu_context(int cpu) } srcu_read_unlock(&pmus_srcu, idx); } +#else -static void perf_event_exit_cpu(int cpu) +static void perf_event_exit_cpu_context(int cpu) { } + +#endif + +int perf_event_exit_cpu(unsigned int cpu) { perf_event_exit_cpu_context(cpu); + return 0; } -#else -static inline void perf_event_exit_cpu(int cpu) { } -#endif static int perf_reboot(struct notifier_block *notifier, unsigned long val, void *v) @@ -10404,46 +10434,6 @@ static struct notifier_block perf_reboot_notifier = { .priority = INT_MIN, }; -static int -perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) -{ - unsigned int cpu = (long)hcpu; - - switch (action & ~CPU_TASKS_FROZEN) { - - case CPU_UP_PREPARE: - /* - * This must be done before the CPU comes alive, because the - * moment we can run tasks we can encounter (software) events. - * - * Specifically, someone can have inherited events on kthreadd - * or a pre-existing worker thread that gets re-bound. - */ - perf_event_init_cpu(cpu); - break; - - case CPU_DOWN_PREPARE: - /* - * This must be done before the CPU dies because after that an - * active event might want to IPI the CPU and that'll not work - * so great for dead CPUs. - * - * XXX smp_call_function_single() return -ENXIO without a warn - * so we could possibly deal with this. - * - * This is safe against new events arriving because - * sys_perf_event_open() serializes against hotplug using - * get_online_cpus(). - */ - perf_event_exit_cpu(cpu); - break; - default: - break; - } - - return NOTIFY_OK; -} - void __init perf_event_init(void) { int ret; @@ -10456,7 +10446,7 @@ void __init perf_event_init(void) perf_pmu_register(&perf_cpu_clock, NULL, -1); perf_pmu_register(&perf_task_clock, NULL, -1); perf_tp_register(); - perf_cpu_notifier(perf_cpu_notify); + perf_event_init_cpu(smp_processor_id()); register_reboot_notifier(&perf_reboot_notifier); ret = init_hw_breakpoint(); diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 05f9f6d626df..486fd78eb8d5 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -123,21 +123,19 @@ static inline unsigned long perf_aux_size(struct ring_buffer *rb) return rb->aux_nr_pages << PAGE_SHIFT; } -#define DEFINE_OUTPUT_COPY(func_name, memcpy_func) \ -static inline unsigned long \ -func_name(struct perf_output_handle *handle, \ - const void *buf, unsigned long len) \ +#define __DEFINE_OUTPUT_COPY_BODY(advance_buf, memcpy_func, ...) \ { \ unsigned long size, written; \ \ do { \ size = min(handle->size, len); \ - written = memcpy_func(handle->addr, buf, size); \ + written = memcpy_func(__VA_ARGS__); \ written = size - written; \ \ len -= written; \ handle->addr += written; \ - buf += written; \ + if (advance_buf) \ + buf += written; \ handle->size -= written; \ if (!handle->size) { \ struct ring_buffer *rb = handle->rb; \ @@ -152,6 +150,21 @@ func_name(struct perf_output_handle *handle, \ return len; \ } +#define DEFINE_OUTPUT_COPY(func_name, memcpy_func) \ +static inline unsigned long \ +func_name(struct perf_output_handle *handle, \ + const void *buf, unsigned long len) \ +__DEFINE_OUTPUT_COPY_BODY(true, memcpy_func, handle->addr, buf, size) + +static inline unsigned long +__output_custom(struct perf_output_handle *handle, perf_copy_f copy_func, + const void *buf, unsigned long len) +{ + unsigned long orig_len = len; + __DEFINE_OUTPUT_COPY_BODY(false, copy_func, handle->addr, buf, + orig_len - len, size) +} + static inline unsigned long memcpy_common(void *dst, const void *src, unsigned long n) { diff --git a/kernel/fork.c b/kernel/fork.c index 4a7ec0c6c88c..52e725d4a866 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -162,23 +162,15 @@ void __weak arch_release_thread_stack(unsigned long *stack) static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { - struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP, - THREAD_SIZE_ORDER); - - if (page) - memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK, - 1 << THREAD_SIZE_ORDER); + struct page *page = alloc_pages_node(node, THREADINFO_GFP, + THREAD_SIZE_ORDER); return page ? page_address(page) : NULL; } static inline void free_thread_stack(unsigned long *stack) { - struct page *page = virt_to_page(stack); - - memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK, - -(1 << THREAD_SIZE_ORDER)); - __free_kmem_pages(page, THREAD_SIZE_ORDER); + __free_pages(virt_to_page(stack), THREAD_SIZE_ORDER); } # else static struct kmem_cache *thread_stack_cache; @@ -223,9 +215,15 @@ static struct kmem_cache *mm_cachep; static void account_kernel_stack(unsigned long *stack, int account) { - struct zone *zone = page_zone(virt_to_page(stack)); + /* All stack pages are in the same zone and belong to the same memcg. */ + struct page *first_page = virt_to_page(stack); + + mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB, + THREAD_SIZE / 1024 * account); - mod_zone_page_state(zone, NR_KERNEL_STACK, account); + memcg_kmem_update_page_stat( + first_page, MEMCG_KERNEL_STACK_KB, + account * (THREAD_SIZE / 1024)); } void free_task(struct task_struct *tsk) diff --git a/kernel/freezer.c b/kernel/freezer.c index a8900a3bc27a..6f56a9e219fa 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -42,7 +42,7 @@ bool freezing_slow_path(struct task_struct *p) if (p->flags & (PF_NOFREEZE | PF_SUSPEND_TASK)) return false; - if (test_thread_flag(TIF_MEMDIE)) + if (test_tsk_thread_flag(p, TIF_MEMDIE)) return false; if (pm_nosig_freezing || cgroup_freezing(p)) diff --git a/kernel/memremap.c b/kernel/memremap.c index 017532193fb1..251d16b4cb41 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -169,12 +169,6 @@ void devm_memunmap(struct device *dev, void *addr) } EXPORT_SYMBOL(devm_memunmap); -pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags) -{ - return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags); -} -EXPORT_SYMBOL(phys_to_pfn_t); - #ifdef CONFIG_ZONE_DEVICE static DEFINE_MUTEX(pgmap_lock); static RADIX_TREE(pgmap_radix, GFP_KERNEL); @@ -308,12 +302,6 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, if (is_ram == REGION_INTERSECTS) return __va(res->start); - if (altmap && !IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) { - dev_err(dev, "%s: altmap requires CONFIG_SPARSEMEM_VMEMMAP=y\n", - __func__); - return ERR_PTR(-ENXIO); - } - if (!ref) return ERR_PTR(-EINVAL); @@ -401,7 +389,6 @@ void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) altmap->alloc -= nr_pfns; } -#ifdef CONFIG_SPARSEMEM_VMEMMAP struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) { /* @@ -427,5 +414,4 @@ struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) return pgmap ? pgmap->altmap : NULL; } -#endif /* CONFIG_SPARSEMEM_VMEMMAP */ #endif /* CONFIG_ZONE_DEVICE */ diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index d90df926b59f..9a0178c2ac1d 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1627,11 +1627,11 @@ static unsigned long minimum_image_size(unsigned long saveable) unsigned long size; size = global_page_state(NR_SLAB_RECLAIMABLE) - + global_page_state(NR_ACTIVE_ANON) - + global_page_state(NR_INACTIVE_ANON) - + global_page_state(NR_ACTIVE_FILE) - + global_page_state(NR_INACTIVE_FILE) - - global_page_state(NR_FILE_MAPPED); + + global_node_page_state(NR_ACTIVE_ANON) + + global_node_page_state(NR_INACTIVE_ANON) + + global_node_page_state(NR_ACTIVE_FILE) + + global_node_page_state(NR_INACTIVE_FILE) + - global_node_page_state(NR_FILE_MAPPED); return saveable <= size ? 0 : saveable - size; } diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 60cdf6386763..d4de33934dac 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -3177,9 +3177,8 @@ void show_regs_print_info(const char *log_lvl) { dump_stack_print_info(log_lvl); - printk("%stask: %p ti: %p task.ti: %p\n", - log_lvl, current, current_thread_info(), - task_thread_info(current)); + printk("%stask: %p task.stack: %p\n", + log_lvl, current, task_stack_page(current)); } #endif diff --git a/kernel/profile.c b/kernel/profile.c index c2199e9901c9..2dbccf2d806c 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -328,68 +328,57 @@ out: put_cpu(); } -static int profile_cpu_callback(struct notifier_block *info, - unsigned long action, void *__cpu) +static int profile_dead_cpu(unsigned int cpu) { - int node, cpu = (unsigned long)__cpu; struct page *page; + int i; - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - node = cpu_to_mem(cpu); - per_cpu(cpu_profile_flip, cpu) = 0; - if (!per_cpu(cpu_profile_hits, cpu)[1]) { - page = __alloc_pages_node(node, - GFP_KERNEL | __GFP_ZERO, - 0); - if (!page) - return notifier_from_errno(-ENOMEM); - per_cpu(cpu_profile_hits, cpu)[1] = page_address(page); - } - if (!per_cpu(cpu_profile_hits, cpu)[0]) { - page = __alloc_pages_node(node, - GFP_KERNEL | __GFP_ZERO, - 0); - if (!page) - goto out_free; - per_cpu(cpu_profile_hits, cpu)[0] = page_address(page); - } - break; -out_free: - page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[1]); - per_cpu(cpu_profile_hits, cpu)[1] = NULL; - __free_page(page); - return notifier_from_errno(-ENOMEM); - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - if (prof_cpu_mask != NULL) - cpumask_set_cpu(cpu, prof_cpu_mask); - break; - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - case CPU_DEAD: - case CPU_DEAD_FROZEN: - if (prof_cpu_mask != NULL) - cpumask_clear_cpu(cpu, prof_cpu_mask); - if (per_cpu(cpu_profile_hits, cpu)[0]) { - page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[0]); - per_cpu(cpu_profile_hits, cpu)[0] = NULL; + if (prof_cpu_mask != NULL) + cpumask_clear_cpu(cpu, prof_cpu_mask); + + for (i = 0; i < 2; i++) { + if (per_cpu(cpu_profile_hits, cpu)[i]) { + page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[i]); + per_cpu(cpu_profile_hits, cpu)[i] = NULL; __free_page(page); } - if (per_cpu(cpu_profile_hits, cpu)[1]) { - page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[1]); - per_cpu(cpu_profile_hits, cpu)[1] = NULL; - __free_page(page); + } + return 0; +} + +static int profile_prepare_cpu(unsigned int cpu) +{ + int i, node = cpu_to_mem(cpu); + struct page *page; + + per_cpu(cpu_profile_flip, cpu) = 0; + + for (i = 0; i < 2; i++) { + if (per_cpu(cpu_profile_hits, cpu)[i]) + continue; + + page = __alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); + if (!page) { + profile_dead_cpu(cpu); + return -ENOMEM; } - break; + per_cpu(cpu_profile_hits, cpu)[i] = page_address(page); + } - return NOTIFY_OK; + return 0; +} + +static int profile_online_cpu(unsigned int cpu) +{ + if (prof_cpu_mask != NULL) + cpumask_set_cpu(cpu, prof_cpu_mask); + + return 0; } + #else /* !CONFIG_SMP */ #define profile_flip_buffers() do { } while (0) #define profile_discard_flip_buffers() do { } while (0) -#define profile_cpu_callback NULL static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) { @@ -531,83 +520,43 @@ static const struct file_operations proc_profile_operations = { .llseek = default_llseek, }; -#ifdef CONFIG_SMP -static void profile_nop(void *unused) -{ -} - -static int create_hash_tables(void) +int __ref create_proc_profile(void) { - int cpu; - - for_each_online_cpu(cpu) { - int node = cpu_to_mem(cpu); - struct page *page; - - page = __alloc_pages_node(node, - GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, - 0); - if (!page) - goto out_cleanup; - per_cpu(cpu_profile_hits, cpu)[1] - = (struct profile_hit *)page_address(page); - page = __alloc_pages_node(node, - GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, - 0); - if (!page) - goto out_cleanup; - per_cpu(cpu_profile_hits, cpu)[0] - = (struct profile_hit *)page_address(page); - } - return 0; -out_cleanup: - prof_on = 0; - smp_mb(); - on_each_cpu(profile_nop, NULL, 1); - for_each_online_cpu(cpu) { - struct page *page; - - if (per_cpu(cpu_profile_hits, cpu)[0]) { - page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[0]); - per_cpu(cpu_profile_hits, cpu)[0] = NULL; - __free_page(page); - } - if (per_cpu(cpu_profile_hits, cpu)[1]) { - page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[1]); - per_cpu(cpu_profile_hits, cpu)[1] = NULL; - __free_page(page); - } - } - return -1; -} -#else -#define create_hash_tables() ({ 0; }) + struct proc_dir_entry *entry; +#ifdef CONFIG_SMP + enum cpuhp_state online_state; #endif -int __ref create_proc_profile(void) /* false positive from hotcpu_notifier */ -{ - struct proc_dir_entry *entry; int err = 0; if (!prof_on) return 0; - - cpu_notifier_register_begin(); - - if (create_hash_tables()) { - err = -ENOMEM; - goto out; - } - +#ifdef CONFIG_SMP + err = cpuhp_setup_state(CPUHP_PROFILE_PREPARE, "PROFILE_PREPARE", + profile_prepare_cpu, profile_dead_cpu); + if (err) + return err; + + err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_PROFILE_ONLINE", + profile_online_cpu, NULL); + if (err < 0) + goto err_state_prep; + online_state = err; + err = 0; +#endif entry = proc_create("profile", S_IWUSR | S_IRUGO, NULL, &proc_profile_operations); if (!entry) - goto out; + goto err_state_onl; proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t)); - __hotcpu_notifier(profile_cpu_callback, 0); -out: - cpu_notifier_register_done(); + return err; +err_state_onl: +#ifdef CONFIG_SMP + cpuhp_remove_state(online_state); +err_state_prep: + cpuhp_remove_state(CPUHP_PROFILE_PREPARE); +#endif return err; } subsys_initcall(create_proc_profile); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index f433959e9322..5d80925e7fc8 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1073,11 +1073,11 @@ EXPORT_SYMBOL_GPL(rcu_is_watching); * offline to continue to use RCU for one jiffy after marking itself * offline in the cpu_online_mask. This leniency is necessary given the * non-atomic nature of the online and offline processing, for example, - * the fact that a CPU enters the scheduler after completing the CPU_DYING - * notifiers. + * the fact that a CPU enters the scheduler after completing the teardown + * of the CPU. * - * This is also why RCU internally marks CPUs online during the - * CPU_UP_PREPARE phase and offline during the CPU_DEAD phase. + * This is also why RCU internally marks CPUs online during in the + * preparation phase and offline after the CPU has been taken down. * * Disable checking if in an NMI handler because we cannot safely report * errors from NMI handlers anyway. @@ -3806,12 +3806,58 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } -static void rcu_prepare_cpu(int cpu) +int rcutree_prepare_cpu(unsigned int cpu) { struct rcu_state *rsp; for_each_rcu_flavor(rsp) rcu_init_percpu_data(cpu, rsp); + + rcu_prepare_kthreads(cpu); + rcu_spawn_all_nocb_kthreads(cpu); + + return 0; +} + +static void rcutree_affinity_setting(unsigned int cpu, int outgoing) +{ + struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu); + + rcu_boost_kthread_setaffinity(rdp->mynode, outgoing); +} + +int rcutree_online_cpu(unsigned int cpu) +{ + sync_sched_exp_online_cleanup(cpu); + rcutree_affinity_setting(cpu, -1); + return 0; +} + +int rcutree_offline_cpu(unsigned int cpu) +{ + rcutree_affinity_setting(cpu, cpu); + return 0; +} + + +int rcutree_dying_cpu(unsigned int cpu) +{ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + rcu_cleanup_dying_cpu(rsp); + return 0; +} + +int rcutree_dead_cpu(unsigned int cpu) +{ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) { + rcu_cleanup_dead_cpu(cpu, rsp); + do_nocb_deferred_wakeup(per_cpu_ptr(rsp->rda, cpu)); + } + return 0; } #ifdef CONFIG_HOTPLUG_CPU @@ -3851,52 +3897,6 @@ void rcu_report_dead(unsigned int cpu) } #endif -/* - * Handle CPU online/offline notification events. - */ -int rcu_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) -{ - long cpu = (long)hcpu; - struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu); - struct rcu_node *rnp = rdp->mynode; - struct rcu_state *rsp; - - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - rcu_prepare_cpu(cpu); - rcu_prepare_kthreads(cpu); - rcu_spawn_all_nocb_kthreads(cpu); - break; - case CPU_ONLINE: - case CPU_DOWN_FAILED: - sync_sched_exp_online_cleanup(cpu); - rcu_boost_kthread_setaffinity(rnp, -1); - break; - case CPU_DOWN_PREPARE: - rcu_boost_kthread_setaffinity(rnp, cpu); - break; - case CPU_DYING: - case CPU_DYING_FROZEN: - for_each_rcu_flavor(rsp) - rcu_cleanup_dying_cpu(rsp); - break; - case CPU_DEAD: - case CPU_DEAD_FROZEN: - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - for_each_rcu_flavor(rsp) { - rcu_cleanup_dead_cpu(cpu, rsp); - do_nocb_deferred_wakeup(per_cpu_ptr(rsp->rda, cpu)); - } - break; - default: - break; - } - return NOTIFY_OK; -} - static int rcu_pm_notify(struct notifier_block *self, unsigned long action, void *hcpu) { @@ -4208,10 +4208,9 @@ void __init rcu_init(void) * this is called early in boot, before either interrupts * or the scheduler are operational. */ - cpu_notifier(rcu_cpu_notify, 0); pm_notifier(rcu_pm_notify, 0); for_each_online_cpu(cpu) - rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu); + rcutree_prepare_cpu(cpu); } #include "tree_exp.h" diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index ea0f6f31a244..1934f658c036 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -503,16 +503,6 @@ void account_process_tick(struct task_struct *p, int user_tick) } /* - * Account multiple ticks of steal time. - * @p: the process from which the cpu time has been stolen - * @ticks: number of stolen ticks - */ -void account_steal_ticks(unsigned long ticks) -{ - account_steal_time(jiffies_to_cputime(ticks)); -} - -/* * Account multiple ticks of idle time. * @ticks: number of stolen ticks */ diff --git a/kernel/smp.c b/kernel/smp.c index 36552beed397..3aa642d39c03 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -33,69 +33,54 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue); static void flush_smp_call_function_queue(bool warn_cpu_offline); -static int -hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu) +int smpcfd_prepare_cpu(unsigned int cpu) { - long cpu = (long)hcpu; struct call_function_data *cfd = &per_cpu(cfd_data, cpu); - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, - cpu_to_node(cpu))) - return notifier_from_errno(-ENOMEM); - cfd->csd = alloc_percpu(struct call_single_data); - if (!cfd->csd) { - free_cpumask_var(cfd->cpumask); - return notifier_from_errno(-ENOMEM); - } - break; - -#ifdef CONFIG_HOTPLUG_CPU - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - /* Fall-through to the CPU_DEAD[_FROZEN] case. */ - - case CPU_DEAD: - case CPU_DEAD_FROZEN: + if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, + cpu_to_node(cpu))) + return -ENOMEM; + cfd->csd = alloc_percpu(struct call_single_data); + if (!cfd->csd) { free_cpumask_var(cfd->cpumask); - free_percpu(cfd->csd); - break; + return -ENOMEM; + } - case CPU_DYING: - case CPU_DYING_FROZEN: - /* - * The IPIs for the smp-call-function callbacks queued by other - * CPUs might arrive late, either due to hardware latencies or - * because this CPU disabled interrupts (inside stop-machine) - * before the IPIs were sent. So flush out any pending callbacks - * explicitly (without waiting for the IPIs to arrive), to - * ensure that the outgoing CPU doesn't go offline with work - * still pending. - */ - flush_smp_call_function_queue(false); - break; -#endif - }; + return 0; +} + +int smpcfd_dead_cpu(unsigned int cpu) +{ + struct call_function_data *cfd = &per_cpu(cfd_data, cpu); - return NOTIFY_OK; + free_cpumask_var(cfd->cpumask); + free_percpu(cfd->csd); + return 0; } -static struct notifier_block hotplug_cfd_notifier = { - .notifier_call = hotplug_cfd, -}; +int smpcfd_dying_cpu(unsigned int cpu) +{ + /* + * The IPIs for the smp-call-function callbacks queued by other + * CPUs might arrive late, either due to hardware latencies or + * because this CPU disabled interrupts (inside stop-machine) + * before the IPIs were sent. So flush out any pending callbacks + * explicitly (without waiting for the IPIs to arrive), to + * ensure that the outgoing CPU doesn't go offline with work + * still pending. + */ + flush_smp_call_function_queue(false); + return 0; +} void __init call_function_init(void) { - void *cpu = (void *)(long)smp_processor_id(); int i; for_each_possible_cpu(i) init_llist_head(&per_cpu(call_single_queue, i)); - hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu); - register_cpu_notifier(&hotplug_cfd_notifier); + smpcfd_prepare_cpu(smp_processor_id()); } /* diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 35f0dcb1cb4f..53954631a4e1 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1508,8 +1508,8 @@ static struct ctl_table vm_table[] = { #ifdef CONFIG_NUMA { .procname = "zone_reclaim_mode", - .data = &zone_reclaim_mode, - .maxlen = sizeof(zone_reclaim_mode), + .data = &node_reclaim_mode, + .maxlen = sizeof(node_reclaim_mode), .mode = 0644, .proc_handler = proc_dointvec, .extra1 = &zero, diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index d13c9aebf7a3..9ba7c820fc23 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1590,7 +1590,7 @@ SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp, /* * Functions related to boot-time initialization: */ -static void init_hrtimers_cpu(int cpu) +int hrtimers_prepare_cpu(unsigned int cpu) { struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); int i; @@ -1602,6 +1602,7 @@ static void init_hrtimers_cpu(int cpu) cpu_base->cpu = cpu; hrtimer_init_hres(cpu_base); + return 0; } #ifdef CONFIG_HOTPLUG_CPU @@ -1636,7 +1637,7 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, } } -static void migrate_hrtimers(int scpu) +int hrtimers_dead_cpu(unsigned int scpu) { struct hrtimer_cpu_base *old_base, *new_base; int i; @@ -1665,45 +1666,14 @@ static void migrate_hrtimers(int scpu) /* Check, if we got expired work to do */ __hrtimer_peek_ahead_timers(); local_irq_enable(); + return 0; } #endif /* CONFIG_HOTPLUG_CPU */ -static int hrtimer_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) -{ - int scpu = (long)hcpu; - - switch (action) { - - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - init_hrtimers_cpu(scpu); - break; - -#ifdef CONFIG_HOTPLUG_CPU - case CPU_DEAD: - case CPU_DEAD_FROZEN: - migrate_hrtimers(scpu); - break; -#endif - - default: - break; - } - - return NOTIFY_OK; -} - -static struct notifier_block hrtimers_nb = { - .notifier_call = hrtimer_cpu_notify, -}; - void __init hrtimers_init(void) { - hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE, - (void *)(long)smp_processor_id()); - register_cpu_notifier(&hrtimers_nb); + hrtimers_prepare_cpu(smp_processor_id()); } /** diff --git a/kernel/time/timer.c b/kernel/time/timer.c index cb9ab401e2d9..555670a5143c 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1804,7 +1804,7 @@ static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *h } } -static void migrate_timers(int cpu) +int timers_dead_cpu(unsigned int cpu) { struct timer_base *old_base; struct timer_base *new_base; @@ -1831,29 +1831,9 @@ static void migrate_timers(int cpu) spin_unlock_irq(&new_base->lock); put_cpu_ptr(&timer_bases); } + return 0; } -static int timer_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) -{ - switch (action) { - case CPU_DEAD: - case CPU_DEAD_FROZEN: - migrate_timers((long)hcpu); - break; - default: - break; - } - - return NOTIFY_OK; -} - -static inline void timer_register_cpu_notifier(void) -{ - cpu_notifier(timer_cpu_notify, 0); -} -#else -static inline void timer_register_cpu_notifier(void) { } #endif /* CONFIG_HOTPLUG_CPU */ static void __init init_timer_cpu(int cpu) @@ -1881,7 +1861,6 @@ void __init init_timers(void) { init_timer_cpus(); init_timer_stats(); - timer_register_cpu_notifier(); open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index fafeaf803bd0..f4b86e8ca1e7 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -542,6 +542,7 @@ config HIST_TRIGGERS bool "Histogram triggers" depends on ARCH_HAVE_NMI_SAFE_CMPXCHG select TRACING_MAP + select TRACING default n help Hist triggers allow one or more arbitrary trace event fields diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 26f603da7e26..b20438fdb029 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -81,6 +81,49 @@ static const struct bpf_func_proto bpf_probe_read_proto = { .arg3_type = ARG_ANYTHING, }; +static u64 bpf_probe_write_user(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + void *unsafe_ptr = (void *) (long) r1; + void *src = (void *) (long) r2; + int size = (int) r3; + + /* + * Ensure we're in user context which is safe for the helper to + * run. This helper has no business in a kthread. + * + * access_ok() should prevent writing to non-user memory, but in + * some situations (nommu, temporary switch, etc) access_ok() does + * not provide enough validation, hence the check on KERNEL_DS. + */ + + if (unlikely(in_interrupt() || + current->flags & (PF_KTHREAD | PF_EXITING))) + return -EPERM; + if (unlikely(segment_eq(get_fs(), KERNEL_DS))) + return -EPERM; + if (!access_ok(VERIFY_WRITE, unsafe_ptr, size)) + return -EPERM; + + return probe_kernel_write(unsafe_ptr, src, size); +} + +static const struct bpf_func_proto bpf_probe_write_user_proto = { + .func = bpf_probe_write_user, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_PTR_TO_STACK, + .arg3_type = ARG_CONST_STACK_SIZE, +}; + +static const struct bpf_func_proto *bpf_get_probe_write_proto(void) +{ + pr_warn_ratelimited("%s[%d] is installing a program with bpf_probe_write_user helper that may corrupt user memory!", + current->comm, task_pid_nr(current)); + + return &bpf_probe_write_user_proto; +} + /* * limited trace_printk() * only %d %u %x %ld %lu %lx %lld %llu %llx %p %s conversion specifiers allowed @@ -188,31 +231,35 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) return &bpf_trace_printk_proto; } -static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5) +static u64 bpf_perf_event_read(u64 r1, u64 flags, u64 r3, u64 r4, u64 r5) { struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; struct bpf_array *array = container_of(map, struct bpf_array, map); + unsigned int cpu = smp_processor_id(); + u64 index = flags & BPF_F_INDEX_MASK; + struct bpf_event_entry *ee; struct perf_event *event; - struct file *file; + if (unlikely(flags & ~(BPF_F_INDEX_MASK))) + return -EINVAL; + if (index == BPF_F_CURRENT_CPU) + index = cpu; if (unlikely(index >= array->map.max_entries)) return -E2BIG; - file = READ_ONCE(array->ptrs[index]); - if (unlikely(!file)) + ee = READ_ONCE(array->ptrs[index]); + if (!ee) return -ENOENT; - event = file->private_data; - - /* make sure event is local and doesn't have pmu::count */ - if (event->oncpu != smp_processor_id() || - event->pmu->count) - return -EINVAL; - + event = ee->event; if (unlikely(event->attr.type != PERF_TYPE_HARDWARE && event->attr.type != PERF_TYPE_RAW)) return -EINVAL; + /* make sure event is local and doesn't have pmu::count */ + if (unlikely(event->oncpu != cpu || event->pmu->count)) + return -EINVAL; + /* * we don't know if the function is run successfully by the * return value. It can be judged in other places, such as @@ -229,47 +276,58 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = { .arg2_type = ARG_ANYTHING, }; -static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size) +static __always_inline u64 +__bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, + u64 flags, struct perf_raw_record *raw) { - struct pt_regs *regs = (struct pt_regs *) (long) r1; - struct bpf_map *map = (struct bpf_map *) (long) r2; struct bpf_array *array = container_of(map, struct bpf_array, map); + unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; - void *data = (void *) (long) r4; struct perf_sample_data sample_data; + struct bpf_event_entry *ee; struct perf_event *event; - struct file *file; - struct perf_raw_record raw = { - .size = size, - .data = data, - }; - if (unlikely(flags & ~(BPF_F_INDEX_MASK))) - return -EINVAL; if (index == BPF_F_CURRENT_CPU) - index = raw_smp_processor_id(); + index = cpu; if (unlikely(index >= array->map.max_entries)) return -E2BIG; - file = READ_ONCE(array->ptrs[index]); - if (unlikely(!file)) + ee = READ_ONCE(array->ptrs[index]); + if (!ee) return -ENOENT; - event = file->private_data; - + event = ee->event; if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE || event->attr.config != PERF_COUNT_SW_BPF_OUTPUT)) return -EINVAL; - if (unlikely(event->oncpu != smp_processor_id())) + if (unlikely(event->oncpu != cpu)) return -EOPNOTSUPP; perf_sample_data_init(&sample_data, 0, 0); - sample_data.raw = &raw; + sample_data.raw = raw; perf_event_output(event, &sample_data, regs); return 0; } +static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size) +{ + struct pt_regs *regs = (struct pt_regs *)(long) r1; + struct bpf_map *map = (struct bpf_map *)(long) r2; + void *data = (void *)(long) r4; + struct perf_raw_record raw = { + .frag = { + .size = size, + .data = data, + }, + }; + + if (unlikely(flags & ~(BPF_F_INDEX_MASK))) + return -EINVAL; + + return __bpf_perf_event_output(regs, map, flags, &raw); +} + static const struct bpf_func_proto bpf_perf_event_output_proto = { .func = bpf_perf_event_output, .gpl_only = true, @@ -283,31 +341,41 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = { static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs); -static u64 bpf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size) +u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, + void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs); + struct perf_raw_frag frag = { + .copy = ctx_copy, + .size = ctx_size, + .data = ctx, + }; + struct perf_raw_record raw = { + .frag = { + { + .next = ctx_size ? &frag : NULL, + }, + .size = meta_size, + .data = meta, + }, + }; perf_fetch_caller_regs(regs); - return bpf_perf_event_output((long)regs, r2, flags, r4, size); + return __bpf_perf_event_output(regs, map, flags, &raw); +} + +static u64 bpf_get_current_task(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + return (long) current; } -static const struct bpf_func_proto bpf_event_output_proto = { - .func = bpf_event_output, +static const struct bpf_func_proto bpf_get_current_task_proto = { + .func = bpf_get_current_task, .gpl_only = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_CONST_MAP_PTR, - .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_STACK, - .arg5_type = ARG_CONST_STACK_SIZE, }; -const struct bpf_func_proto *bpf_get_event_output_proto(void) -{ - return &bpf_event_output_proto; -} - static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@ -325,6 +393,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id) return &bpf_tail_call_proto; case BPF_FUNC_get_current_pid_tgid: return &bpf_get_current_pid_tgid_proto; + case BPF_FUNC_get_current_task: + return &bpf_get_current_task_proto; case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_current_comm: @@ -335,6 +405,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id) return &bpf_get_smp_processor_id_proto; case BPF_FUNC_perf_event_read: return &bpf_perf_event_read_proto; + case BPF_FUNC_probe_write_user: + return bpf_get_probe_write_proto(); default: return NULL; } @@ -356,18 +428,12 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type, enum bpf_reg_type *reg_type) { - /* check bounds */ if (off < 0 || off >= sizeof(struct pt_regs)) return false; - - /* only read is allowed */ if (type != BPF_READ) return false; - - /* disallow misaligned access */ if (off % size != 0) return false; - return true; } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 900dbb1efff2..84752c8e28b5 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -89,16 +89,16 @@ struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end; /* What to set function_trace_op to */ static struct ftrace_ops *set_function_trace_op; -/* List for set_ftrace_pid's pids. */ -LIST_HEAD(ftrace_pids); -struct ftrace_pid { - struct list_head list; - struct pid *pid; -}; - -static bool ftrace_pids_enabled(void) +static bool ftrace_pids_enabled(struct ftrace_ops *ops) { - return !list_empty(&ftrace_pids); + struct trace_array *tr; + + if (!(ops->flags & FTRACE_OPS_FL_PID) || !ops->private) + return false; + + tr = ops->private; + + return tr->function_pids != NULL; } static void ftrace_update_trampoline(struct ftrace_ops *ops); @@ -179,7 +179,9 @@ int ftrace_nr_registered_ops(void) static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *regs) { - if (!test_tsk_trace_trace(current)) + struct trace_array *tr = op->private; + + if (tr && this_cpu_read(tr->trace_buffer.data->ftrace_ignore_pid)) return; op->saved_func(ip, parent_ip, op, regs); @@ -417,7 +419,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops) /* Always save the function, and reset at unregistering */ ops->saved_func = ops->func; - if (ops->flags & FTRACE_OPS_FL_PID && ftrace_pids_enabled()) + if (ftrace_pids_enabled(ops)) ops->func = ftrace_pid_func; ftrace_update_trampoline(ops); @@ -450,7 +452,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) static void ftrace_update_pid_func(void) { - bool enabled = ftrace_pids_enabled(); struct ftrace_ops *op; /* Only do something if we are tracing something */ @@ -459,8 +460,8 @@ static void ftrace_update_pid_func(void) do_for_each_ftrace_op(op, ftrace_ops_list) { if (op->flags & FTRACE_OPS_FL_PID) { - op->func = enabled ? ftrace_pid_func : - op->saved_func; + op->func = ftrace_pids_enabled(op) ? + ftrace_pid_func : op->saved_func; ftrace_update_trampoline(op); } } while_for_each_ftrace_op(op); @@ -5324,179 +5325,99 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops) return ops->func; } -static void clear_ftrace_swapper(void) +static void +ftrace_filter_pid_sched_switch_probe(void *data, bool preempt, + struct task_struct *prev, struct task_struct *next) { - struct task_struct *p; - int cpu; + struct trace_array *tr = data; + struct trace_pid_list *pid_list; - get_online_cpus(); - for_each_online_cpu(cpu) { - p = idle_task(cpu); - clear_tsk_trace_trace(p); - } - put_online_cpus(); -} - -static void set_ftrace_swapper(void) -{ - struct task_struct *p; - int cpu; + pid_list = rcu_dereference_sched(tr->function_pids); - get_online_cpus(); - for_each_online_cpu(cpu) { - p = idle_task(cpu); - set_tsk_trace_trace(p); - } - put_online_cpus(); + this_cpu_write(tr->trace_buffer.data->ftrace_ignore_pid, + trace_ignore_this_task(pid_list, next)); } -static void clear_ftrace_pid(struct pid *pid) +static void clear_ftrace_pids(struct trace_array *tr) { - struct task_struct *p; + struct trace_pid_list *pid_list; + int cpu; - rcu_read_lock(); - do_each_pid_task(pid, PIDTYPE_PID, p) { - clear_tsk_trace_trace(p); - } while_each_pid_task(pid, PIDTYPE_PID, p); - rcu_read_unlock(); + pid_list = rcu_dereference_protected(tr->function_pids, + lockdep_is_held(&ftrace_lock)); + if (!pid_list) + return; - put_pid(pid); -} + unregister_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr); -static void set_ftrace_pid(struct pid *pid) -{ - struct task_struct *p; + for_each_possible_cpu(cpu) + per_cpu_ptr(tr->trace_buffer.data, cpu)->ftrace_ignore_pid = false; - rcu_read_lock(); - do_each_pid_task(pid, PIDTYPE_PID, p) { - set_tsk_trace_trace(p); - } while_each_pid_task(pid, PIDTYPE_PID, p); - rcu_read_unlock(); -} + rcu_assign_pointer(tr->function_pids, NULL); -static void clear_ftrace_pid_task(struct pid *pid) -{ - if (pid == ftrace_swapper_pid) - clear_ftrace_swapper(); - else - clear_ftrace_pid(pid); -} + /* Wait till all users are no longer using pid filtering */ + synchronize_sched(); -static void set_ftrace_pid_task(struct pid *pid) -{ - if (pid == ftrace_swapper_pid) - set_ftrace_swapper(); - else - set_ftrace_pid(pid); + trace_free_pid_list(pid_list); } -static int ftrace_pid_add(int p) +static void ftrace_pid_reset(struct trace_array *tr) { - struct pid *pid; - struct ftrace_pid *fpid; - int ret = -EINVAL; - mutex_lock(&ftrace_lock); - - if (!p) - pid = ftrace_swapper_pid; - else - pid = find_get_pid(p); - - if (!pid) - goto out; - - ret = 0; - - list_for_each_entry(fpid, &ftrace_pids, list) - if (fpid->pid == pid) - goto out_put; - - ret = -ENOMEM; - - fpid = kmalloc(sizeof(*fpid), GFP_KERNEL); - if (!fpid) - goto out_put; - - list_add(&fpid->list, &ftrace_pids); - fpid->pid = pid; - - set_ftrace_pid_task(pid); + clear_ftrace_pids(tr); ftrace_update_pid_func(); - ftrace_startup_all(0); mutex_unlock(&ftrace_lock); - return 0; - -out_put: - if (pid != ftrace_swapper_pid) - put_pid(pid); - -out: - mutex_unlock(&ftrace_lock); - return ret; } -static void ftrace_pid_reset(void) -{ - struct ftrace_pid *fpid, *safe; - - mutex_lock(&ftrace_lock); - list_for_each_entry_safe(fpid, safe, &ftrace_pids, list) { - struct pid *pid = fpid->pid; - - clear_ftrace_pid_task(pid); - - list_del(&fpid->list); - kfree(fpid); - } - - ftrace_update_pid_func(); - ftrace_startup_all(0); - - mutex_unlock(&ftrace_lock); -} +/* Greater than any max PID */ +#define FTRACE_NO_PIDS (void *)(PID_MAX_LIMIT + 1) static void *fpid_start(struct seq_file *m, loff_t *pos) + __acquires(RCU) { + struct trace_pid_list *pid_list; + struct trace_array *tr = m->private; + mutex_lock(&ftrace_lock); + rcu_read_lock_sched(); - if (!ftrace_pids_enabled() && (!*pos)) - return (void *) 1; + pid_list = rcu_dereference_sched(tr->function_pids); - return seq_list_start(&ftrace_pids, *pos); + if (!pid_list) + return !(*pos) ? FTRACE_NO_PIDS : NULL; + + return trace_pid_start(pid_list, pos); } static void *fpid_next(struct seq_file *m, void *v, loff_t *pos) { - if (v == (void *)1) + struct trace_array *tr = m->private; + struct trace_pid_list *pid_list = rcu_dereference_sched(tr->function_pids); + + if (v == FTRACE_NO_PIDS) return NULL; - return seq_list_next(v, &ftrace_pids, pos); + return trace_pid_next(pid_list, v, pos); } static void fpid_stop(struct seq_file *m, void *p) + __releases(RCU) { + rcu_read_unlock_sched(); mutex_unlock(&ftrace_lock); } static int fpid_show(struct seq_file *m, void *v) { - const struct ftrace_pid *fpid = list_entry(v, struct ftrace_pid, list); - - if (v == (void *)1) { + if (v == FTRACE_NO_PIDS) { seq_puts(m, "no pid\n"); return 0; } - if (fpid->pid == ftrace_swapper_pid) - seq_puts(m, "swapper tasks\n"); - else - seq_printf(m, "%u\n", pid_vnr(fpid->pid)); - - return 0; + return trace_pid_show(m, v); } static const struct seq_operations ftrace_pid_sops = { @@ -5509,58 +5430,103 @@ static const struct seq_operations ftrace_pid_sops = { static int ftrace_pid_open(struct inode *inode, struct file *file) { + struct trace_array *tr = inode->i_private; + struct seq_file *m; int ret = 0; + if (trace_array_get(tr) < 0) + return -ENODEV; + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) - ftrace_pid_reset(); + ftrace_pid_reset(tr); - if (file->f_mode & FMODE_READ) - ret = seq_open(file, &ftrace_pid_sops); + ret = seq_open(file, &ftrace_pid_sops); + if (ret < 0) { + trace_array_put(tr); + } else { + m = file->private_data; + /* copy tr over to seq ops */ + m->private = tr; + } return ret; } +static void ignore_task_cpu(void *data) +{ + struct trace_array *tr = data; + struct trace_pid_list *pid_list; + + /* + * This function is called by on_each_cpu() while the + * event_mutex is held. + */ + pid_list = rcu_dereference_protected(tr->function_pids, + mutex_is_locked(&ftrace_lock)); + + this_cpu_write(tr->trace_buffer.data->ftrace_ignore_pid, + trace_ignore_this_task(pid_list, current)); +} + static ssize_t ftrace_pid_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - char buf[64], *tmp; - long val; - int ret; + struct seq_file *m = filp->private_data; + struct trace_array *tr = m->private; + struct trace_pid_list *filtered_pids = NULL; + struct trace_pid_list *pid_list; + ssize_t ret; - if (cnt >= sizeof(buf)) - return -EINVAL; + if (!cnt) + return 0; + + mutex_lock(&ftrace_lock); + + filtered_pids = rcu_dereference_protected(tr->function_pids, + lockdep_is_held(&ftrace_lock)); + + ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt); + if (ret < 0) + goto out; - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; + rcu_assign_pointer(tr->function_pids, pid_list); - buf[cnt] = 0; + if (filtered_pids) { + synchronize_sched(); + trace_free_pid_list(filtered_pids); + } else if (pid_list) { + /* Register a probe to set whether to ignore the tracing of a task */ + register_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr); + } /* - * Allow "echo > set_ftrace_pid" or "echo -n '' > set_ftrace_pid" - * to clean the filter quietly. + * Ignoring of pids is done at task switch. But we have to + * check for those tasks that are currently running. + * Always do this in case a pid was appended or removed. */ - tmp = strstrip(buf); - if (strlen(tmp) == 0) - return 1; + on_each_cpu(ignore_task_cpu, tr, 1); - ret = kstrtol(tmp, 10, &val); - if (ret < 0) - return ret; + ftrace_update_pid_func(); + ftrace_startup_all(0); + out: + mutex_unlock(&ftrace_lock); - ret = ftrace_pid_add(val); + if (ret > 0) + *ppos += ret; - return ret ? ret : cnt; + return ret; } static int ftrace_pid_release(struct inode *inode, struct file *file) { - if (file->f_mode & FMODE_READ) - seq_release(inode, file); + struct trace_array *tr = inode->i_private; - return 0; + trace_array_put(tr); + + return seq_release(inode, file); } static const struct file_operations ftrace_pid_fops = { @@ -5571,24 +5537,21 @@ static const struct file_operations ftrace_pid_fops = { .release = ftrace_pid_release, }; -static __init int ftrace_init_tracefs(void) +void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer) { - struct dentry *d_tracer; + trace_create_file("set_ftrace_pid", 0644, d_tracer, + tr, &ftrace_pid_fops); +} - d_tracer = tracing_init_dentry(); - if (IS_ERR(d_tracer)) - return 0; +void __init ftrace_init_tracefs_toplevel(struct trace_array *tr, + struct dentry *d_tracer) +{ + /* Only the top level directory has the dyn_tracefs and profile */ + WARN_ON(!(tr->flags & TRACE_ARRAY_FL_GLOBAL)); ftrace_init_dyn_tracefs(d_tracer); - - trace_create_file("set_ftrace_pid", 0644, d_tracer, - NULL, &ftrace_pid_fops); - ftrace_profile_tracefs(d_tracer); - - return 0; } -fs_initcall(ftrace_init_tracefs); /** * ftrace_kill - kill ftrace diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8a4bd6b68a0b..dade4c9559cc 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -25,7 +25,7 @@ #include <linux/hardirq.h> #include <linux/linkage.h> #include <linux/uaccess.h> -#include <linux/kprobes.h> +#include <linux/vmalloc.h> #include <linux/ftrace.h> #include <linux/module.h> #include <linux/percpu.h> @@ -319,6 +319,258 @@ int call_filter_check_discard(struct trace_event_call *call, void *rec, return 0; } +void trace_free_pid_list(struct trace_pid_list *pid_list) +{ + vfree(pid_list->pids); + kfree(pid_list); +} + +/** + * trace_find_filtered_pid - check if a pid exists in a filtered_pid list + * @filtered_pids: The list of pids to check + * @search_pid: The PID to find in @filtered_pids + * + * Returns true if @search_pid is fonud in @filtered_pids, and false otherwis. + */ +bool +trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid) +{ + /* + * If pid_max changed after filtered_pids was created, we + * by default ignore all pids greater than the previous pid_max. + */ + if (search_pid >= filtered_pids->pid_max) + return false; + + return test_bit(search_pid, filtered_pids->pids); +} + +/** + * trace_ignore_this_task - should a task be ignored for tracing + * @filtered_pids: The list of pids to check + * @task: The task that should be ignored if not filtered + * + * Checks if @task should be traced or not from @filtered_pids. + * Returns true if @task should *NOT* be traced. + * Returns false if @task should be traced. + */ +bool +trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct *task) +{ + /* + * Return false, because if filtered_pids does not exist, + * all pids are good to trace. + */ + if (!filtered_pids) + return false; + + return !trace_find_filtered_pid(filtered_pids, task->pid); +} + +/** + * trace_pid_filter_add_remove - Add or remove a task from a pid_list + * @pid_list: The list to modify + * @self: The current task for fork or NULL for exit + * @task: The task to add or remove + * + * If adding a task, if @self is defined, the task is only added if @self + * is also included in @pid_list. This happens on fork and tasks should + * only be added when the parent is listed. If @self is NULL, then the + * @task pid will be removed from the list, which would happen on exit + * of a task. + */ +void trace_filter_add_remove_task(struct trace_pid_list *pid_list, + struct task_struct *self, + struct task_struct *task) +{ + if (!pid_list) + return; + + /* For forks, we only add if the forking task is listed */ + if (self) { + if (!trace_find_filtered_pid(pid_list, self->pid)) + return; + } + + /* Sorry, but we don't support pid_max changing after setting */ + if (task->pid >= pid_list->pid_max) + return; + + /* "self" is set for forks, and NULL for exits */ + if (self) + set_bit(task->pid, pid_list->pids); + else + clear_bit(task->pid, pid_list->pids); +} + +/** + * trace_pid_next - Used for seq_file to get to the next pid of a pid_list + * @pid_list: The pid list to show + * @v: The last pid that was shown (+1 the actual pid to let zero be displayed) + * @pos: The position of the file + * + * This is used by the seq_file "next" operation to iterate the pids + * listed in a trace_pid_list structure. + * + * Returns the pid+1 as we want to display pid of zero, but NULL would + * stop the iteration. + */ +void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos) +{ + unsigned long pid = (unsigned long)v; + + (*pos)++; + + /* pid already is +1 of the actual prevous bit */ + pid = find_next_bit(pid_list->pids, pid_list->pid_max, pid); + + /* Return pid + 1 to allow zero to be represented */ + if (pid < pid_list->pid_max) + return (void *)(pid + 1); + + return NULL; +} + +/** + * trace_pid_start - Used for seq_file to start reading pid lists + * @pid_list: The pid list to show + * @pos: The position of the file + * + * This is used by seq_file "start" operation to start the iteration + * of listing pids. + * + * Returns the pid+1 as we want to display pid of zero, but NULL would + * stop the iteration. + */ +void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos) +{ + unsigned long pid; + loff_t l = 0; + + pid = find_first_bit(pid_list->pids, pid_list->pid_max); + if (pid >= pid_list->pid_max) + return NULL; + + /* Return pid + 1 so that zero can be the exit value */ + for (pid++; pid && l < *pos; + pid = (unsigned long)trace_pid_next(pid_list, (void *)pid, &l)) + ; + return (void *)pid; +} + +/** + * trace_pid_show - show the current pid in seq_file processing + * @m: The seq_file structure to write into + * @v: A void pointer of the pid (+1) value to display + * + * Can be directly used by seq_file operations to display the current + * pid value. + */ +int trace_pid_show(struct seq_file *m, void *v) +{ + unsigned long pid = (unsigned long)v - 1; + + seq_printf(m, "%lu\n", pid); + return 0; +} + +/* 128 should be much more than enough */ +#define PID_BUF_SIZE 127 + +int trace_pid_write(struct trace_pid_list *filtered_pids, + struct trace_pid_list **new_pid_list, + const char __user *ubuf, size_t cnt) +{ + struct trace_pid_list *pid_list; + struct trace_parser parser; + unsigned long val; + int nr_pids = 0; + ssize_t read = 0; + ssize_t ret = 0; + loff_t pos; + pid_t pid; + + if (trace_parser_get_init(&parser, PID_BUF_SIZE + 1)) + return -ENOMEM; + + /* + * Always recreate a new array. The write is an all or nothing + * operation. Always create a new array when adding new pids by + * the user. If the operation fails, then the current list is + * not modified. + */ + pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL); + if (!pid_list) + return -ENOMEM; + + pid_list->pid_max = READ_ONCE(pid_max); + + /* Only truncating will shrink pid_max */ + if (filtered_pids && filtered_pids->pid_max > pid_list->pid_max) + pid_list->pid_max = filtered_pids->pid_max; + + pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3); + if (!pid_list->pids) { + kfree(pid_list); + return -ENOMEM; + } + + if (filtered_pids) { + /* copy the current bits to the new max */ + for_each_set_bit(pid, filtered_pids->pids, + filtered_pids->pid_max) { + set_bit(pid, pid_list->pids); + nr_pids++; + } + } + + while (cnt > 0) { + + pos = 0; + + ret = trace_get_user(&parser, ubuf, cnt, &pos); + if (ret < 0 || !trace_parser_loaded(&parser)) + break; + + read += ret; + ubuf += ret; + cnt -= ret; + + parser.buffer[parser.idx] = 0; + + ret = -EINVAL; + if (kstrtoul(parser.buffer, 0, &val)) + break; + if (val >= pid_list->pid_max) + break; + + pid = (pid_t)val; + + set_bit(pid, pid_list->pids); + nr_pids++; + + trace_parser_clear(&parser); + ret = 0; + } + trace_parser_put(&parser); + + if (ret < 0) { + trace_free_pid_list(pid_list); + return ret; + } + + if (!nr_pids) { + /* Cleared the list of pids */ + trace_free_pid_list(pid_list); + read = ret; + pid_list = NULL; + } + + *new_pid_list = pid_list; + + return read; +} + static cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu) { u64 ts; @@ -1862,7 +2114,17 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr, { __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(tr, buffer, flags, 0, pc, regs); + /* + * If regs is not set, then skip the following callers: + * trace_buffer_unlock_commit_regs + * event_trigger_unlock_commit + * trace_event_buffer_commit + * trace_event_raw_event_sched_switch + * Note, we can still get here via blktrace, wakeup tracer + * and mmiotrace, but that's ok if they lose a function or + * two. They are that meaningful. + */ + ftrace_trace_stack(tr, buffer, flags, regs ? 0 : 4, pc, regs); ftrace_trace_userstack(buffer, flags, pc); } @@ -1913,6 +2175,13 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, trace.skip = skip; /* + * Add two, for this function and the call to save_stack_trace() + * If regs is set, then these functions will not be in the way. + */ + if (!regs) + trace.skip += 2; + + /* * Since events can happen in NMIs there's no safe way to * use the per cpu ftrace_stacks. We reserve it and if an interrupt * or NMI comes in, it will just have to use the default @@ -2083,83 +2352,41 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags) /* created for use with alloc_percpu */ struct trace_buffer_struct { - char buffer[TRACE_BUF_SIZE]; + int nesting; + char buffer[4][TRACE_BUF_SIZE]; }; static struct trace_buffer_struct *trace_percpu_buffer; -static struct trace_buffer_struct *trace_percpu_sirq_buffer; -static struct trace_buffer_struct *trace_percpu_irq_buffer; -static struct trace_buffer_struct *trace_percpu_nmi_buffer; /* - * The buffer used is dependent on the context. There is a per cpu - * buffer for normal context, softirq contex, hard irq context and - * for NMI context. Thise allows for lockless recording. - * - * Note, if the buffers failed to be allocated, then this returns NULL + * Thise allows for lockless recording. If we're nested too deeply, then + * this returns NULL. */ static char *get_trace_buf(void) { - struct trace_buffer_struct *percpu_buffer; - - /* - * If we have allocated per cpu buffers, then we do not - * need to do any locking. - */ - if (in_nmi()) - percpu_buffer = trace_percpu_nmi_buffer; - else if (in_irq()) - percpu_buffer = trace_percpu_irq_buffer; - else if (in_softirq()) - percpu_buffer = trace_percpu_sirq_buffer; - else - percpu_buffer = trace_percpu_buffer; + struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer); - if (!percpu_buffer) + if (!buffer || buffer->nesting >= 4) return NULL; - return this_cpu_ptr(&percpu_buffer->buffer[0]); + return &buffer->buffer[buffer->nesting++][0]; +} + +static void put_trace_buf(void) +{ + this_cpu_dec(trace_percpu_buffer->nesting); } static int alloc_percpu_trace_buffer(void) { struct trace_buffer_struct *buffers; - struct trace_buffer_struct *sirq_buffers; - struct trace_buffer_struct *irq_buffers; - struct trace_buffer_struct *nmi_buffers; buffers = alloc_percpu(struct trace_buffer_struct); - if (!buffers) - goto err_warn; - - sirq_buffers = alloc_percpu(struct trace_buffer_struct); - if (!sirq_buffers) - goto err_sirq; - - irq_buffers = alloc_percpu(struct trace_buffer_struct); - if (!irq_buffers) - goto err_irq; - - nmi_buffers = alloc_percpu(struct trace_buffer_struct); - if (!nmi_buffers) - goto err_nmi; + if (WARN(!buffers, "Could not allocate percpu trace_printk buffer")) + return -ENOMEM; trace_percpu_buffer = buffers; - trace_percpu_sirq_buffer = sirq_buffers; - trace_percpu_irq_buffer = irq_buffers; - trace_percpu_nmi_buffer = nmi_buffers; - return 0; - - err_nmi: - free_percpu(irq_buffers); - err_irq: - free_percpu(sirq_buffers); - err_sirq: - free_percpu(buffers); - err_warn: - WARN(1, "Could not allocate percpu trace_printk buffer"); - return -ENOMEM; } static int buffers_allocated; @@ -2250,7 +2477,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) tbuffer = get_trace_buf(); if (!tbuffer) { len = 0; - goto out; + goto out_nobuffer; } len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args); @@ -2276,6 +2503,9 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) } out: + put_trace_buf(); + +out_nobuffer: preempt_enable_notrace(); unpause_graph_tracing(); @@ -2307,7 +2537,7 @@ __trace_array_vprintk(struct ring_buffer *buffer, tbuffer = get_trace_buf(); if (!tbuffer) { len = 0; - goto out; + goto out_nobuffer; } len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args); @@ -2326,7 +2556,11 @@ __trace_array_vprintk(struct ring_buffer *buffer, __buffer_unlock_commit(buffer, event); ftrace_trace_stack(&global_trace, buffer, flags, 6, pc, NULL); } - out: + +out: + put_trace_buf(); + +out_nobuffer: preempt_enable_notrace(); unpause_graph_tracing(); @@ -6977,6 +7211,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) for_each_tracing_cpu(cpu) tracing_init_tracefs_percpu(tr, cpu); + ftrace_init_tracefs(tr, d_tracer); } static struct vfsmount *trace_automount(void *ingore) @@ -7130,6 +7365,7 @@ static __init int tracer_init_tracefs(void) return 0; init_tracer_tracefs(&global_trace, d_tracer); + ftrace_init_tracefs_toplevel(&global_trace, d_tracer); trace_create_file("tracing_thresh", 0644, d_tracer, &global_trace, &tracing_thresh_fops); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 5167c366d6b7..f783df416726 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -80,6 +80,12 @@ enum trace_type { FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ filter) +#undef FTRACE_ENTRY_PACKED +#define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print, \ + filter) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ + filter) __packed + #include "trace_entries.h" /* @@ -156,6 +162,9 @@ struct trace_array_cpu { char comm[TASK_COMM_LEN]; bool ignore_pid; +#ifdef CONFIG_FUNCTION_TRACER + bool ftrace_ignore_pid; +#endif }; struct tracer; @@ -247,6 +256,7 @@ struct trace_array { int ref; #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops *ops; + struct trace_pid_list __rcu *function_pids; /* function tracing enabled */ int function_enabled; #endif @@ -628,6 +638,25 @@ extern unsigned long nsecs_to_usecs(unsigned long nsecs); extern unsigned long tracing_thresh; +/* PID filtering */ + +extern int pid_max; + +bool trace_find_filtered_pid(struct trace_pid_list *filtered_pids, + pid_t search_pid); +bool trace_ignore_this_task(struct trace_pid_list *filtered_pids, + struct task_struct *task); +void trace_filter_add_remove_task(struct trace_pid_list *pid_list, + struct task_struct *self, + struct task_struct *task); +void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos); +void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos); +int trace_pid_show(struct seq_file *m, void *v); +void trace_free_pid_list(struct trace_pid_list *pid_list); +int trace_pid_write(struct trace_pid_list *filtered_pids, + struct trace_pid_list **new_pid_list, + const char __user *ubuf, size_t cnt); + #ifdef CONFIG_TRACER_MAX_TRACE void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu); void update_max_tr_single(struct trace_array *tr, @@ -821,12 +850,9 @@ extern struct list_head ftrace_pids; #ifdef CONFIG_FUNCTION_TRACER extern bool ftrace_filter_param __initdata; -static inline int ftrace_trace_task(struct task_struct *task) +static inline int ftrace_trace_task(struct trace_array *tr) { - if (list_empty(&ftrace_pids)) - return 1; - - return test_tsk_trace_trace(task); + return !this_cpu_read(tr->trace_buffer.data->ftrace_ignore_pid); } extern int ftrace_is_dead(void); int ftrace_create_function_files(struct trace_array *tr, @@ -836,8 +862,11 @@ void ftrace_init_global_array_ops(struct trace_array *tr); void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func); void ftrace_reset_array_ops(struct trace_array *tr); int using_ftrace_ops_list_func(void); +void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer); +void ftrace_init_tracefs_toplevel(struct trace_array *tr, + struct dentry *d_tracer); #else -static inline int ftrace_trace_task(struct task_struct *task) +static inline int ftrace_trace_task(struct trace_array *tr) { return 1; } @@ -852,6 +881,8 @@ static inline void ftrace_destroy_function_files(struct trace_array *tr) { } static inline __init void ftrace_init_global_array_ops(struct trace_array *tr) { } static inline void ftrace_reset_array_ops(struct trace_array *tr) { } +static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { } +static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { } /* ftace_func_t type is not defined, use macro instead of static inline */ #define ftrace_init_array_ops(tr, func) do { } while (0) #endif /* CONFIG_FUNCTION_TRACER */ @@ -1600,6 +1631,11 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled); #define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \ FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ filter) +#undef FTRACE_ENTRY_PACKED +#define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print, filter) \ + FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ + filter) + #include "trace_entries.h" #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_FUNCTION_TRACER) diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index ee7b94a4810a..5c30efcda5e6 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -72,7 +72,7 @@ FTRACE_ENTRY_REG(function, ftrace_entry, ); /* Function call entry */ -FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry, +FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry, TRACE_GRAPH_ENT, @@ -88,7 +88,7 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry, ); /* Function return entry */ -FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry, +FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry, TRACE_GRAPH_RET, diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 3d4155892a1e..03c0a48c3ac4 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -15,7 +15,6 @@ #include <linux/kthread.h> #include <linux/tracefs.h> #include <linux/uaccess.h> -#include <linux/vmalloc.h> #include <linux/module.h> #include <linux/ctype.h> #include <linux/sort.h> @@ -262,6 +261,14 @@ void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer, local_save_flags(fbuffer->flags); fbuffer->pc = preempt_count(); + /* + * If CONFIG_PREEMPT is enabled, then the tracepoint itself disables + * preemption (adding one to the preempt_count). Since we are + * interested in the preempt_count at the time the tracepoint was + * hit, we need to subtract one to offset the increment. + */ + if (IS_ENABLED(CONFIG_PREEMPT)) + fbuffer->pc--; fbuffer->trace_file = trace_file; fbuffer->event = @@ -499,60 +506,6 @@ static void ftrace_clear_events(struct trace_array *tr) mutex_unlock(&event_mutex); } -/* Shouldn't this be in a header? */ -extern int pid_max; - -/* Returns true if found in filter */ -static bool -find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid) -{ - /* - * If pid_max changed after filtered_pids was created, we - * by default ignore all pids greater than the previous pid_max. - */ - if (search_pid >= filtered_pids->pid_max) - return false; - - return test_bit(search_pid, filtered_pids->pids); -} - -static bool -ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct *task) -{ - /* - * Return false, because if filtered_pids does not exist, - * all pids are good to trace. - */ - if (!filtered_pids) - return false; - - return !find_filtered_pid(filtered_pids, task->pid); -} - -static void filter_add_remove_task(struct trace_pid_list *pid_list, - struct task_struct *self, - struct task_struct *task) -{ - if (!pid_list) - return; - - /* For forks, we only add if the forking task is listed */ - if (self) { - if (!find_filtered_pid(pid_list, self->pid)) - return; - } - - /* Sorry, but we don't support pid_max changing after setting */ - if (task->pid >= pid_list->pid_max) - return; - - /* "self" is set for forks, and NULL for exits */ - if (self) - set_bit(task->pid, pid_list->pids); - else - clear_bit(task->pid, pid_list->pids); -} - static void event_filter_pid_sched_process_exit(void *data, struct task_struct *task) { @@ -560,7 +513,7 @@ event_filter_pid_sched_process_exit(void *data, struct task_struct *task) struct trace_array *tr = data; pid_list = rcu_dereference_sched(tr->filtered_pids); - filter_add_remove_task(pid_list, NULL, task); + trace_filter_add_remove_task(pid_list, NULL, task); } static void @@ -572,7 +525,7 @@ event_filter_pid_sched_process_fork(void *data, struct trace_array *tr = data; pid_list = rcu_dereference_sched(tr->filtered_pids); - filter_add_remove_task(pid_list, self, task); + trace_filter_add_remove_task(pid_list, self, task); } void trace_event_follow_fork(struct trace_array *tr, bool enable) @@ -600,8 +553,8 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt, pid_list = rcu_dereference_sched(tr->filtered_pids); this_cpu_write(tr->trace_buffer.data->ignore_pid, - ignore_this_task(pid_list, prev) && - ignore_this_task(pid_list, next)); + trace_ignore_this_task(pid_list, prev) && + trace_ignore_this_task(pid_list, next)); } static void @@ -614,7 +567,7 @@ event_filter_pid_sched_switch_probe_post(void *data, bool preempt, pid_list = rcu_dereference_sched(tr->filtered_pids); this_cpu_write(tr->trace_buffer.data->ignore_pid, - ignore_this_task(pid_list, next)); + trace_ignore_this_task(pid_list, next)); } static void @@ -630,7 +583,7 @@ event_filter_pid_sched_wakeup_probe_pre(void *data, struct task_struct *task) pid_list = rcu_dereference_sched(tr->filtered_pids); this_cpu_write(tr->trace_buffer.data->ignore_pid, - ignore_this_task(pid_list, task)); + trace_ignore_this_task(pid_list, task)); } static void @@ -647,7 +600,7 @@ event_filter_pid_sched_wakeup_probe_post(void *data, struct task_struct *task) /* Set tracing if current is enabled */ this_cpu_write(tr->trace_buffer.data->ignore_pid, - ignore_this_task(pid_list, current)); + trace_ignore_this_task(pid_list, current)); } static void __ftrace_clear_event_pids(struct trace_array *tr) @@ -685,8 +638,7 @@ static void __ftrace_clear_event_pids(struct trace_array *tr) /* Wait till all users are no longer using pid filtering */ synchronize_sched(); - vfree(pid_list->pids); - kfree(pid_list); + trace_free_pid_list(pid_list); } static void ftrace_clear_event_pids(struct trace_array *tr) @@ -1034,18 +986,8 @@ p_next(struct seq_file *m, void *v, loff_t *pos) { struct trace_array *tr = m->private; struct trace_pid_list *pid_list = rcu_dereference_sched(tr->filtered_pids); - unsigned long pid = (unsigned long)v; - - (*pos)++; - - /* pid already is +1 of the actual prevous bit */ - pid = find_next_bit(pid_list->pids, pid_list->pid_max, pid); - /* Return pid + 1 to allow zero to be represented */ - if (pid < pid_list->pid_max) - return (void *)(pid + 1); - - return NULL; + return trace_pid_next(pid_list, v, pos); } static void *p_start(struct seq_file *m, loff_t *pos) @@ -1053,8 +995,6 @@ static void *p_start(struct seq_file *m, loff_t *pos) { struct trace_pid_list *pid_list; struct trace_array *tr = m->private; - unsigned long pid; - loff_t l = 0; /* * Grab the mutex, to keep calls to p_next() having the same @@ -1070,15 +1010,7 @@ static void *p_start(struct seq_file *m, loff_t *pos) if (!pid_list) return NULL; - pid = find_first_bit(pid_list->pids, pid_list->pid_max); - if (pid >= pid_list->pid_max) - return NULL; - - /* Return pid + 1 so that zero can be the exit value */ - for (pid++; pid && l < *pos; - pid = (unsigned long)p_next(m, (void *)pid, &l)) - ; - return (void *)pid; + return trace_pid_start(pid_list, pos); } static void p_stop(struct seq_file *m, void *p) @@ -1088,14 +1020,6 @@ static void p_stop(struct seq_file *m, void *p) mutex_unlock(&event_mutex); } -static int p_show(struct seq_file *m, void *v) -{ - unsigned long pid = (unsigned long)v - 1; - - seq_printf(m, "%lu\n", pid); - return 0; -} - static ssize_t event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) @@ -1654,7 +1578,7 @@ static void ignore_task_cpu(void *data) mutex_is_locked(&event_mutex)); this_cpu_write(tr->trace_buffer.data->ignore_pid, - ignore_this_task(pid_list, current)); + trace_ignore_this_task(pid_list, current)); } static ssize_t @@ -1666,13 +1590,7 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf, struct trace_pid_list *filtered_pids = NULL; struct trace_pid_list *pid_list; struct trace_event_file *file; - struct trace_parser parser; - unsigned long val; - loff_t this_pos; - ssize_t read = 0; - ssize_t ret = 0; - pid_t pid; - int nr_pids = 0; + ssize_t ret; if (!cnt) return 0; @@ -1681,93 +1599,15 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf, if (ret < 0) return ret; - if (trace_parser_get_init(&parser, EVENT_BUF_SIZE + 1)) - return -ENOMEM; - mutex_lock(&event_mutex); + filtered_pids = rcu_dereference_protected(tr->filtered_pids, lockdep_is_held(&event_mutex)); - /* - * Always recreate a new array. The write is an all or nothing - * operation. Always create a new array when adding new pids by - * the user. If the operation fails, then the current list is - * not modified. - */ - pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL); - if (!pid_list) { - read = -ENOMEM; - goto out; - } - pid_list->pid_max = READ_ONCE(pid_max); - /* Only truncating will shrink pid_max */ - if (filtered_pids && filtered_pids->pid_max > pid_list->pid_max) - pid_list->pid_max = filtered_pids->pid_max; - pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3); - if (!pid_list->pids) { - kfree(pid_list); - read = -ENOMEM; - goto out; - } - if (filtered_pids) { - /* copy the current bits to the new max */ - pid = find_first_bit(filtered_pids->pids, - filtered_pids->pid_max); - while (pid < filtered_pids->pid_max) { - set_bit(pid, pid_list->pids); - pid = find_next_bit(filtered_pids->pids, - filtered_pids->pid_max, - pid + 1); - nr_pids++; - } - } - - while (cnt > 0) { - - this_pos = 0; - - ret = trace_get_user(&parser, ubuf, cnt, &this_pos); - if (ret < 0 || !trace_parser_loaded(&parser)) - break; - - read += ret; - ubuf += ret; - cnt -= ret; - - parser.buffer[parser.idx] = 0; - - ret = -EINVAL; - if (kstrtoul(parser.buffer, 0, &val)) - break; - if (val >= pid_list->pid_max) - break; - - pid = (pid_t)val; - - set_bit(pid, pid_list->pids); - nr_pids++; - - trace_parser_clear(&parser); - ret = 0; - } - trace_parser_put(&parser); - - if (ret < 0) { - vfree(pid_list->pids); - kfree(pid_list); - read = ret; + ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt); + if (ret < 0) goto out; - } - if (!nr_pids) { - /* Cleared the list of pids */ - vfree(pid_list->pids); - kfree(pid_list); - read = ret; - if (!filtered_pids) - goto out; - pid_list = NULL; - } rcu_assign_pointer(tr->filtered_pids, pid_list); list_for_each_entry(file, &tr->events, list) { @@ -1776,10 +1616,8 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf, if (filtered_pids) { synchronize_sched(); - - vfree(filtered_pids->pids); - kfree(filtered_pids); - } else { + trace_free_pid_list(filtered_pids); + } else if (pid_list) { /* * Register a probe that is called before all other probes * to set ignore_pid if next or prev do not match. @@ -1817,9 +1655,8 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf, out: mutex_unlock(&event_mutex); - ret = read; - if (read > 0) - *ppos += read; + if (ret > 0) + *ppos += ret; return ret; } @@ -1846,7 +1683,7 @@ static const struct seq_operations show_set_event_seq_ops = { static const struct seq_operations show_set_pid_seq_ops = { .start = p_start, .next = p_next, - .show = p_show, + .show = trace_pid_show, .stop = p_stop, }; diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 5a095c2e4b69..0efa00d80623 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -43,7 +43,7 @@ static int allocate_ftrace_ops(struct trace_array *tr) /* Currently only the non stack verision is supported */ ops->func = function_trace_call; - ops->flags = FTRACE_OPS_FL_RECURSION_SAFE; + ops->flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_PID; tr->ops = ops; ops->private = tr; diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 3a0244ff7ea8..7363ccf79512 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -319,7 +319,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) int cpu; int pc; - if (!ftrace_trace_task(current)) + if (!ftrace_trace_task(tr)) return 0; /* trace it when it is-nested-in or is a function enabled. */ @@ -338,6 +338,13 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) if (ftrace_graph_notrace_addr(trace->func)) return 1; + /* + * Stop here if tracing_threshold is set. We only write function return + * events to the ring buffer. + */ + if (tracing_thresh) + return 1; + local_irq_save(flags); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->trace_buffer.data, cpu); @@ -355,14 +362,6 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) return ret; } -static int trace_graph_thresh_entry(struct ftrace_graph_ent *trace) -{ - if (tracing_thresh) - return 1; - else - return trace_graph_entry(trace); -} - static void __trace_graph_function(struct trace_array *tr, unsigned long ip, unsigned long flags, int pc) @@ -457,7 +456,7 @@ static int graph_trace_init(struct trace_array *tr) set_graph_array(tr); if (tracing_thresh) ret = register_ftrace_graph(&trace_graph_thresh_return, - &trace_graph_thresh_entry); + &trace_graph_entry); else ret = register_ftrace_graph(&trace_graph_return, &trace_graph_entry); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 5546eec0505f..9aedb0b06683 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -587,6 +587,7 @@ static int create_trace_kprobe(int argc, char **argv) * $retval : fetch return value * $stack : fetch stack address * $stackN : fetch Nth of stack (N:0-) + * $comm : fetch current task comm * @ADDR : fetch memory at ADDR (ADDR should be in kernel) * @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol) * %REG : fetch register REG diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index 68f376ca6d3f..cd7480d0a201 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -68,19 +68,15 @@ static void mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev) trace_seq_printf(s, "PCIDEV %02x%02x %04x%04x %x", dev->bus->number, dev->devfn, dev->vendor, dev->device, dev->irq); - /* - * XXX: is pci_resource_to_user() appropriate, since we are - * supposed to interpret the __ioremap() phys_addr argument based on - * these printed values? - */ for (i = 0; i < 7; i++) { - pci_resource_to_user(dev, i, &dev->resource[i], &start, &end); + start = dev->resource[i].start; trace_seq_printf(s, " %llx", (unsigned long long)(start | (dev->resource[i].flags & PCI_REGION_FLAG_MASK))); } for (i = 0; i < 7; i++) { - pci_resource_to_user(dev, i, &dev->resource[i], &start, &end); + start = dev->resource[i].start; + end = dev->resource[i].end; trace_seq_printf(s, " %llx", dev->resource[i].start < dev->resource[i].end ? (unsigned long long)(end - start) + 1 : 0); diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 1d372fa6fefb..74e80a582c28 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -218,6 +218,28 @@ free_bitfield_fetch_param(struct bitfield_fetch_param *data) kfree(data); } +void FETCH_FUNC_NAME(comm, string)(struct pt_regs *regs, + void *data, void *dest) +{ + int maxlen = get_rloc_len(*(u32 *)dest); + u8 *dst = get_rloc_data(dest); + long ret; + + if (!maxlen) + return; + + ret = strlcpy(dst, current->comm, maxlen); + *(u32 *)dest = make_data_rloc(ret, get_rloc_offs(*(u32 *)dest)); +} +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(comm, string)); + +void FETCH_FUNC_NAME(comm, string_size)(struct pt_regs *regs, + void *data, void *dest) +{ + *(u32 *)dest = strlen(current->comm) + 1; +} +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(comm, string_size)); + static const struct fetch_type *find_fetch_type(const char *type, const struct fetch_type *ftbl) { @@ -348,6 +370,11 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t, } } else ret = -EINVAL; + } else if (strcmp(arg, "comm") == 0) { + if (strcmp(t->name, "string") != 0 && + strcmp(t->name, "string_size") != 0) + return -EINVAL; + f->fn = t->fetch[FETCH_MTD_comm]; } else ret = -EINVAL; @@ -522,6 +549,12 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size, arg[t - parg->comm] = '\0'; t++; } + /* + * The default type of $comm should be "string", and it can't be + * dereferenced. + */ + if (!t && strcmp(arg, "$comm") == 0) + t = "string"; parg->type = find_fetch_type(t, ftbl); if (!parg->type) { pr_info("Unsupported type: %s\n", t); diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index f6398db09114..45400ca5ded1 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -102,6 +102,7 @@ enum { FETCH_MTD_reg = 0, FETCH_MTD_stack, FETCH_MTD_retval, + FETCH_MTD_comm, FETCH_MTD_memory, FETCH_MTD_symbol, FETCH_MTD_deref, @@ -183,6 +184,14 @@ DECLARE_BASIC_FETCH_FUNCS(bitfield); #define fetch_bitfield_string NULL #define fetch_bitfield_string_size NULL +/* comm only makes sense as a string */ +#define fetch_comm_u8 NULL +#define fetch_comm_u16 NULL +#define fetch_comm_u32 NULL +#define fetch_comm_u64 NULL +DECLARE_FETCH_FUNC(comm, string); +DECLARE_FETCH_FUNC(comm, string_size); + /* * Define macro for basic types - we don't need to define s* types, because * we have to care only about bitwidth at recording time. @@ -213,6 +222,7 @@ DEFINE_FETCH_##method(u64) ASSIGN_FETCH_FUNC(reg, ftype), \ ASSIGN_FETCH_FUNC(stack, ftype), \ ASSIGN_FETCH_FUNC(retval, ftype), \ +ASSIGN_FETCH_FUNC(comm, ftype), \ ASSIGN_FETCH_FUNC(memory, ftype), \ ASSIGN_FETCH_FUNC(symbol, ftype), \ ASSIGN_FETCH_FUNC(deref, ftype), \ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index d12bd958077e..ef071ca73fc3 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4607,84 +4607,65 @@ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, &cpumask) < 0); } -/* - * Workqueues should be brought up before normal priority CPU notifiers. - * This will be registered high priority CPU notifier. - */ -static int workqueue_cpu_up_callback(struct notifier_block *nfb, - unsigned long action, - void *hcpu) +int workqueue_prepare_cpu(unsigned int cpu) +{ + struct worker_pool *pool; + + for_each_cpu_worker_pool(pool, cpu) { + if (pool->nr_workers) + continue; + if (!create_worker(pool)) + return -ENOMEM; + } + return 0; +} + +int workqueue_online_cpu(unsigned int cpu) { - int cpu = (unsigned long)hcpu; struct worker_pool *pool; struct workqueue_struct *wq; int pi; - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_UP_PREPARE: - for_each_cpu_worker_pool(pool, cpu) { - if (pool->nr_workers) - continue; - if (!create_worker(pool)) - return NOTIFY_BAD; - } - break; - - case CPU_DOWN_FAILED: - case CPU_ONLINE: - mutex_lock(&wq_pool_mutex); + mutex_lock(&wq_pool_mutex); - for_each_pool(pool, pi) { - mutex_lock(&pool->attach_mutex); + for_each_pool(pool, pi) { + mutex_lock(&pool->attach_mutex); - if (pool->cpu == cpu) - rebind_workers(pool); - else if (pool->cpu < 0) - restore_unbound_workers_cpumask(pool, cpu); + if (pool->cpu == cpu) + rebind_workers(pool); + else if (pool->cpu < 0) + restore_unbound_workers_cpumask(pool, cpu); - mutex_unlock(&pool->attach_mutex); - } + mutex_unlock(&pool->attach_mutex); + } - /* update NUMA affinity of unbound workqueues */ - list_for_each_entry(wq, &workqueues, list) - wq_update_unbound_numa(wq, cpu, true); + /* update NUMA affinity of unbound workqueues */ + list_for_each_entry(wq, &workqueues, list) + wq_update_unbound_numa(wq, cpu, true); - mutex_unlock(&wq_pool_mutex); - break; - } - return NOTIFY_OK; + mutex_unlock(&wq_pool_mutex); + return 0; } -/* - * Workqueues should be brought down after normal priority CPU notifiers. - * This will be registered as low priority CPU notifier. - */ -static int workqueue_cpu_down_callback(struct notifier_block *nfb, - unsigned long action, - void *hcpu) +int workqueue_offline_cpu(unsigned int cpu) { - int cpu = (unsigned long)hcpu; struct work_struct unbind_work; struct workqueue_struct *wq; - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_DOWN_PREPARE: - /* unbinding per-cpu workers should happen on the local CPU */ - INIT_WORK_ONSTACK(&unbind_work, wq_unbind_fn); - queue_work_on(cpu, system_highpri_wq, &unbind_work); - - /* update NUMA affinity of unbound workqueues */ - mutex_lock(&wq_pool_mutex); - list_for_each_entry(wq, &workqueues, list) - wq_update_unbound_numa(wq, cpu, false); - mutex_unlock(&wq_pool_mutex); - - /* wait for per-cpu unbinding to finish */ - flush_work(&unbind_work); - destroy_work_on_stack(&unbind_work); - break; - } - return NOTIFY_OK; + /* unbinding per-cpu workers should happen on the local CPU */ + INIT_WORK_ONSTACK(&unbind_work, wq_unbind_fn); + queue_work_on(cpu, system_highpri_wq, &unbind_work); + + /* update NUMA affinity of unbound workqueues */ + mutex_lock(&wq_pool_mutex); + list_for_each_entry(wq, &workqueues, list) + wq_update_unbound_numa(wq, cpu, false); + mutex_unlock(&wq_pool_mutex); + + /* wait for per-cpu unbinding to finish */ + flush_work(&unbind_work); + destroy_work_on_stack(&unbind_work); + return 0; } #ifdef CONFIG_SMP @@ -5486,9 +5467,6 @@ static int __init init_workqueues(void) pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); - cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_UP); - hotcpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_DOWN); - wq_numa_init(); /* initialize CPU pools */ |