diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/cgroup.c | 75 | ||||
-rw-r--r-- | kernel/cpu.c | 2 | ||||
-rw-r--r-- | kernel/cpuset.c | 13 | ||||
-rw-r--r-- | kernel/events/uprobes.c | 6 | ||||
-rw-r--r-- | kernel/fork.c | 7 | ||||
-rw-r--r-- | kernel/irq/manage.c | 1 | ||||
-rw-r--r-- | kernel/printk/printk.c | 4 | ||||
-rw-r--r-- | kernel/ptrace.c | 16 | ||||
-rw-r--r-- | kernel/rcu/tiny.c | 2 | ||||
-rw-r--r-- | kernel/rcu/tree.c | 2 | ||||
-rw-r--r-- | kernel/sched/debug.c | 3 | ||||
-rw-r--r-- | kernel/sched/fair.c | 22 | ||||
-rw-r--r-- | kernel/softirq.c | 4 | ||||
-rw-r--r-- | kernel/time/alarmtimer.c | 2 | ||||
-rw-r--r-- | kernel/time/timer.c | 2 |
15 files changed, 104 insertions, 57 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 44066158f0d1..85bc9beb046d 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -64,6 +64,9 @@ #include <linux/file.h> #include <net/sock.h> +#define CREATE_TRACE_POINTS +#include <trace/events/cgroup.h> + /* * pidlists linger the following amount before being destroyed. The goal * is avoiding frequent destruction in the middle of consecutive read calls @@ -1176,6 +1179,8 @@ static void cgroup_destroy_root(struct cgroup_root *root) struct cgroup *cgrp = &root->cgrp; struct cgrp_cset_link *link, *tmp_link; + trace_cgroup_destroy_root(root); + cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); BUG_ON(atomic_read(&root->nr_cgrps)); @@ -1874,6 +1879,9 @@ static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data) strcpy(root->release_agent_path, opts.release_agent); spin_unlock(&release_agent_path_lock); } + + trace_cgroup_remount(root); + out_unlock: kfree(opts.release_agent); kfree(opts.name); @@ -2031,6 +2039,8 @@ static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) if (ret) goto destroy_root; + trace_cgroup_setup_root(root); + /* * There must be no failure case after here, since rebinding takes * care of subsystems' refcounts, which are explicitly dropped in @@ -2315,22 +2325,18 @@ static struct file_system_type cgroup2_fs_type = { .fs_flags = FS_USERNS_MOUNT, }; -static char *cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, - struct cgroup_namespace *ns) +static int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, + struct cgroup_namespace *ns) { struct cgroup *root = cset_cgroup_from_root(ns->root_cset, cgrp->root); - int ret; - ret = kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen); - if (ret < 0 || ret >= buflen) - return NULL; - return buf; + return kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen); } -char *cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, - struct cgroup_namespace *ns) +int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, + struct cgroup_namespace *ns) { - char *ret; + int ret; mutex_lock(&cgroup_mutex); spin_lock_irq(&css_set_lock); @@ -2357,12 +2363,12 @@ EXPORT_SYMBOL_GPL(cgroup_path_ns); * * Return value is the same as kernfs_path(). */ -char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) +int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) { struct cgroup_root *root; struct cgroup *cgrp; int hierarchy_id = 1; - char *path = NULL; + int ret; mutex_lock(&cgroup_mutex); spin_lock_irq(&css_set_lock); @@ -2371,16 +2377,15 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) if (root) { cgrp = task_cgroup_from_root(task, root); - path = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns); + ret = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns); } else { /* if no hierarchy exists, everyone is in "/" */ - if (strlcpy(buf, "/", buflen) < buflen) - path = buf; + ret = strlcpy(buf, "/", buflen); } spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); - return path; + return ret; } EXPORT_SYMBOL_GPL(task_cgroup_path); @@ -2830,6 +2835,10 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp, ret = cgroup_migrate(leader, threadgroup, dst_cgrp->root); cgroup_migrate_finish(&preloaded_csets); + + if (!ret) + trace_cgroup_attach_task(dst_cgrp, leader, threadgroup); + return ret; } @@ -3611,6 +3620,8 @@ static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, mutex_lock(&cgroup_mutex); ret = kernfs_rename(kn, new_parent, new_name_str); + if (!ret) + trace_cgroup_rename(cgrp); mutex_unlock(&cgroup_mutex); @@ -4381,6 +4392,8 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) if (task) { ret = cgroup_migrate(task, false, to->root); + if (!ret) + trace_cgroup_transfer_tasks(to, task, false); put_task_struct(task); } } while (task && !ret); @@ -5046,6 +5059,8 @@ static void css_release_work_fn(struct work_struct *work) ss->css_released(css); } else { /* cgroup release path */ + trace_cgroup_release(cgrp); + cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id); cgrp->id = -1; @@ -5332,6 +5347,8 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, if (ret) goto out_destroy; + trace_cgroup_mkdir(cgrp); + /* let's create and online css's */ kernfs_activate(kn); @@ -5507,6 +5524,9 @@ static int cgroup_rmdir(struct kernfs_node *kn) ret = cgroup_destroy_locked(cgrp); + if (!ret) + trace_cgroup_rmdir(cgrp); + cgroup_kn_unlock(kn); return ret; } @@ -5743,7 +5763,7 @@ core_initcall(cgroup_wq_init); int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk) { - char *buf, *path; + char *buf; int retval; struct cgroup_root *root; @@ -5786,18 +5806,18 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, * " (deleted)" is appended to the cgroup path. */ if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) { - path = cgroup_path_ns_locked(cgrp, buf, PATH_MAX, + retval = cgroup_path_ns_locked(cgrp, buf, PATH_MAX, current->nsproxy->cgroup_ns); - if (!path) { + if (retval >= PATH_MAX) retval = -ENAMETOOLONG; + if (retval < 0) goto out_unlock; - } + + seq_puts(m, buf); } else { - path = "/"; + seq_puts(m, "/"); } - seq_puts(m, path); - if (cgroup_on_dfl(cgrp) && cgroup_is_dead(cgrp)) seq_puts(m, " (deleted)\n"); else @@ -6062,8 +6082,9 @@ static void cgroup_release_agent(struct work_struct *work) { struct cgroup *cgrp = container_of(work, struct cgroup, release_agent_work); - char *pathbuf = NULL, *agentbuf = NULL, *path; + char *pathbuf = NULL, *agentbuf = NULL; char *argv[3], *envp[3]; + int ret; mutex_lock(&cgroup_mutex); @@ -6073,13 +6094,13 @@ static void cgroup_release_agent(struct work_struct *work) goto out; spin_lock_irq(&css_set_lock); - path = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); + ret = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); spin_unlock_irq(&css_set_lock); - if (!path) + if (ret < 0 || ret >= PATH_MAX) goto out; argv[0] = agentbuf; - argv[1] = path; + argv[1] = pathbuf; argv[2] = NULL; /* minimal command environment */ diff --git a/kernel/cpu.c b/kernel/cpu.c index 5df20d6d1520..29de1a9352c0 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -228,7 +228,7 @@ static struct { .wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq), .lock = __MUTEX_INITIALIZER(cpu_hotplug.lock), #ifdef CONFIG_DEBUG_LOCK_ALLOC - .dep_map = {.name = "cpu_hotplug.lock" }, + .dep_map = STATIC_LOCKDEP_MAP_INIT("cpu_hotplug.dep_map", &cpu_hotplug.dep_map), #endif }; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 2b4c20ab5bbe..29f815d2ef7e 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2715,7 +2715,7 @@ void __cpuset_memory_pressure_bump(void) int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk) { - char *buf, *p; + char *buf; struct cgroup_subsys_state *css; int retval; @@ -2724,14 +2724,15 @@ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, if (!buf) goto out; - retval = -ENAMETOOLONG; css = task_get_css(tsk, cpuset_cgrp_id); - p = cgroup_path_ns(css->cgroup, buf, PATH_MAX, - current->nsproxy->cgroup_ns); + retval = cgroup_path_ns(css->cgroup, buf, PATH_MAX, + current->nsproxy->cgroup_ns); css_put(css); - if (!p) + if (retval >= PATH_MAX) + retval = -ENAMETOOLONG; + if (retval < 0) goto out_free; - seq_puts(m, p); + seq_puts(m, buf); seq_putc(m, '\n'); retval = 0; out_free: diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index d4129bb05e5d..f9ec9add2164 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -300,7 +300,8 @@ int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr, retry: /* Read the page with vaddr into memory */ - ret = get_user_pages_remote(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma); + ret = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_FORCE, &old_page, + &vma); if (ret <= 0) return ret; @@ -1710,7 +1711,8 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr) * but we treat this as a 'remote' access since it is * essentially a kernel access to the memory. */ - result = get_user_pages_remote(NULL, mm, vaddr, 1, 0, 1, &page, NULL); + result = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_FORCE, &page, + NULL); if (result < 0) return result; diff --git a/kernel/fork.c b/kernel/fork.c index 6d42242485cb..623259fc794d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -547,7 +547,8 @@ free_tsk: } #ifdef CONFIG_MMU -static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) +static __latent_entropy int dup_mmap(struct mm_struct *mm, + struct mm_struct *oldmm) { struct vm_area_struct *mpnt, *tmp, *prev, **pprev; struct rb_node **rb_link, *rb_parent; @@ -1441,7 +1442,8 @@ init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ -static struct task_struct *copy_process(unsigned long clone_flags, +static __latent_entropy struct task_struct *copy_process( + unsigned long clone_flags, unsigned long stack_start, unsigned long stack_size, int __user *child_tidptr, @@ -1926,6 +1928,7 @@ long _do_fork(unsigned long clone_flags, p = copy_process(clone_flags, stack_start, stack_size, child_tidptr, NULL, trace, tls, NUMA_NO_NODE); + add_latent_entropy(); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 0c5f1a5db654..9c4d30483264 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -721,6 +721,7 @@ int irq_set_parent(int irq, int parent_irq) irq_put_desc_unlock(desc, flags); return 0; } +EXPORT_SYMBOL_GPL(irq_set_parent); #endif /* diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index d5e397315473..de08fc90baaf 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1769,6 +1769,10 @@ static size_t log_output(int facility, int level, enum log_flags lflags, const c cont_flush(); } + /* Skip empty continuation lines that couldn't be added - they just flush */ + if (!text_len && (lflags & LOG_CONT)) + return 0; + /* If it doesn't end in a newline, try to buffer the current line */ if (!(lflags & LOG_NEWLINE)) { if (cont_add(facility, level, lflags, text, text_len)) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 2a99027312a6..e6474f7272ec 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -537,7 +537,7 @@ int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst int this_len, retval; this_len = (len > sizeof(buf)) ? sizeof(buf) : len; - retval = access_process_vm(tsk, src, buf, this_len, 0); + retval = access_process_vm(tsk, src, buf, this_len, FOLL_FORCE); if (!retval) { if (copied) break; @@ -564,7 +564,8 @@ int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long ds this_len = (len > sizeof(buf)) ? sizeof(buf) : len; if (copy_from_user(buf, src, this_len)) return -EFAULT; - retval = access_process_vm(tsk, dst, buf, this_len, 1); + retval = access_process_vm(tsk, dst, buf, this_len, + FOLL_FORCE | FOLL_WRITE); if (!retval) { if (copied) break; @@ -1127,7 +1128,7 @@ int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr, unsigned long tmp; int copied; - copied = access_process_vm(tsk, addr, &tmp, sizeof(tmp), 0); + copied = access_process_vm(tsk, addr, &tmp, sizeof(tmp), FOLL_FORCE); if (copied != sizeof(tmp)) return -EIO; return put_user(tmp, (unsigned long __user *)data); @@ -1138,7 +1139,8 @@ int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, { int copied; - copied = access_process_vm(tsk, addr, &data, sizeof(data), 1); + copied = access_process_vm(tsk, addr, &data, sizeof(data), + FOLL_FORCE | FOLL_WRITE); return (copied == sizeof(data)) ? 0 : -EIO; } @@ -1155,7 +1157,8 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request, switch (request) { case PTRACE_PEEKTEXT: case PTRACE_PEEKDATA: - ret = access_process_vm(child, addr, &word, sizeof(word), 0); + ret = access_process_vm(child, addr, &word, sizeof(word), + FOLL_FORCE); if (ret != sizeof(word)) ret = -EIO; else @@ -1164,7 +1167,8 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request, case PTRACE_POKETEXT: case PTRACE_POKEDATA: - ret = access_process_vm(child, addr, &data, sizeof(data), 1); + ret = access_process_vm(child, addr, &data, sizeof(data), + FOLL_FORCE | FOLL_WRITE); ret = (ret != sizeof(data) ? -EIO : 0); break; diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index 944b1b491ed8..1898559e6b60 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -170,7 +170,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) false)); } -static void rcu_process_callbacks(struct softirq_action *unused) +static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) { __rcu_process_callbacks(&rcu_sched_ctrlblk); __rcu_process_callbacks(&rcu_bh_ctrlblk); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 7e2e03879c2e..69a5611a7e7c 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3013,7 +3013,7 @@ __rcu_process_callbacks(struct rcu_state *rsp) /* * Do RCU core processing for the current CPU. */ -static void rcu_process_callbacks(struct softirq_action *unused) +static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) { struct rcu_state *rsp; diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 13935886a471..fa178b62ea79 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -415,7 +415,8 @@ static char *task_group_path(struct task_group *tg) if (autogroup_path(tg, group_path, PATH_MAX)) return group_path; - return cgroup_path(tg->css.cgroup, group_path, PATH_MAX); + cgroup_path(tg->css.cgroup, group_path, PATH_MAX); + return group_path; } #endif diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 502e95a6e927..d941c97dfbc3 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -690,7 +690,14 @@ void init_entity_runnable_average(struct sched_entity *se) * will definitely be update (after enqueue). */ sa->period_contrib = 1023; - sa->load_avg = scale_load_down(se->load.weight); + /* + * Tasks are intialized with full load to be seen as heavy tasks until + * they get a chance to stabilize to their real load level. + * Group entities are intialized with zero load to reflect the fact that + * nothing has been attached to the task group yet. + */ + if (entity_is_task(se)) + sa->load_avg = scale_load_down(se->load.weight); sa->load_sum = sa->load_avg * LOAD_AVG_MAX; /* * At this point, util_avg won't be used in select_task_rq_fair anyway @@ -5471,13 +5478,18 @@ static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd */ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target) { - struct sched_domain *this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc)); - u64 avg_idle = this_rq()->avg_idle; - u64 avg_cost = this_sd->avg_scan_cost; + struct sched_domain *this_sd; + u64 avg_cost, avg_idle = this_rq()->avg_idle; u64 time, cost; s64 delta; int cpu, wrap; + this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc)); + if (!this_sd) + return -1; + + avg_cost = this_sd->avg_scan_cost; + /* * Due to large variance we need a large fuzz factor; hackbench in * particularly is sensitive here. @@ -8522,7 +8534,7 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { } * run_rebalance_domains is triggered when needed from the scheduler tick. * Also triggered for nohz idle balancing (with nohz_balancing_kick set). */ -static void run_rebalance_domains(struct softirq_action *h) +static __latent_entropy void run_rebalance_domains(struct softirq_action *h) { struct rq *this_rq = this_rq(); enum cpu_idle_type idle = this_rq->idle_balance ? diff --git a/kernel/softirq.c b/kernel/softirq.c index 66762645f9e8..1bf81ef91375 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -496,7 +496,7 @@ void __tasklet_hi_schedule_first(struct tasklet_struct *t) } EXPORT_SYMBOL(__tasklet_hi_schedule_first); -static void tasklet_action(struct softirq_action *a) +static __latent_entropy void tasklet_action(struct softirq_action *a) { struct tasklet_struct *list; @@ -532,7 +532,7 @@ static void tasklet_action(struct softirq_action *a) } } -static void tasklet_hi_action(struct softirq_action *a) +static __latent_entropy void tasklet_hi_action(struct softirq_action *a) { struct tasklet_struct *list; diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index c3aad685bbc0..12dd190634ab 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -542,7 +542,6 @@ static int alarm_clock_get(clockid_t which_clock, struct timespec *tp) static int alarm_timer_create(struct k_itimer *new_timer) { enum alarmtimer_type type; - struct alarm_base *base; if (!alarmtimer_get_rtcdev()) return -ENOTSUPP; @@ -551,7 +550,6 @@ static int alarm_timer_create(struct k_itimer *new_timer) return -EPERM; type = clock2alarm(new_timer->it_clock); - base = &alarm_bases[type]; alarm_init(&new_timer->it.alarm.alarmtimer, type, alarm_handle_timer); return 0; } diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 32bf6f75a8fe..2d47980a1bc4 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1633,7 +1633,7 @@ static inline void __run_timers(struct timer_base *base) /* * This function runs timers and the timer-tq in bottom half context. */ -static void run_timer_softirq(struct softirq_action *h) +static __latent_entropy void run_timer_softirq(struct softirq_action *h) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); |