* kn_to: /n1/n2/n3 [depth=3]
* result: /../..
*
- * return value: length of the string. If greater than buflen,
- * then contents of buf are undefined. On error, -1 is returned.
+ * Returns the length of the full path. If the full length is equal to or
+ * greater than @buflen, @buf contains the truncated path with the trailing
+ * '\0'. On error, -errno is returned.
*/
static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
struct kernfs_node *kn_from,
{
struct kernfs_node *kn, *common;
const char parent_str[] = "/..";
- size_t depth_from, depth_to, len = 0, nlen = 0;
- char *p;
- int i;
+ size_t depth_from, depth_to, len = 0;
+ int i, j;
if (!kn_from)
kn_from = kernfs_root(kn_to)->kn;
common = kernfs_common_ancestor(kn_from, kn_to);
if (WARN_ON(!common))
- return -1;
+ return -EINVAL;
depth_to = kernfs_depth(common, kn_to);
depth_from = kernfs_depth(common, kn_from);
len < buflen ? buflen - len : 0);
/* Calculate how many bytes we need for the rest */
- for (kn = kn_to; kn != common; kn = kn->parent)
- nlen += strlen(kn->name) + 1;
-
- if (len + nlen >= buflen)
- return len + nlen;
-
- p = buf + len + nlen;
- *p = '\0';
- for (kn = kn_to; kn != common; kn = kn->parent) {
- size_t tmp = strlen(kn->name);
- p -= tmp;
- memcpy(p, kn->name, tmp);
- *(--p) = '/';
+ for (i = depth_to - 1; i >= 0; i--) {
+ for (kn = kn_to, j = 0; j < i; j++)
+ kn = kn->parent;
+ len += strlcpy(buf + len, "/",
+ len < buflen ? buflen - len : 0);
+ len += strlcpy(buf + len, kn->name,
+ len < buflen ? buflen - len : 0);
}
- return len + nlen;
+ return len;
}
/**
return ret;
}
- /**
- * kernfs_path_len - determine the length of the full path of a given node
- * @kn: kernfs_node of interest
- *
- * The returned length doesn't include the space for the terminating '\0'.
- */
- size_t kernfs_path_len(struct kernfs_node *kn)
- {
- size_t len = 0;
- unsigned long flags;
-
- spin_lock_irqsave(&kernfs_rename_lock, flags);
-
- do {
- len += strlen(kn->name) + 1;
- kn = kn->parent;
- } while (kn && kn->parent);
-
- spin_unlock_irqrestore(&kernfs_rename_lock, flags);
-
- return len;
- }
-
/**
* kernfs_path_from_node - build path of node @to relative to @from.
* @from: parent kernfs_node relative to which we need to build the path
* path (which includes '..'s) as needed to reach from @from to @to is
* returned.
*
- * If @buf isn't long enough, the return value will be greater than @buflen
- * and @buf contents are undefined.
+ * Returns the length of the full path. If the full length is equal to or
+ * greater than @buflen, @buf contains the truncated path with the trailing
+ * '\0'. On error, -errno is returned.
*/
int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from,
char *buf, size_t buflen)
}
EXPORT_SYMBOL_GPL(kernfs_path_from_node);
- /**
- * kernfs_path - build full path of a given node
- * @kn: kernfs_node of interest
- * @buf: buffer to copy @kn's name into
- * @buflen: size of @buf
- *
- * Builds and returns the full path of @kn in @buf of @buflen bytes. The
- * path is built from the end of @buf so the returned pointer usually
- * doesn't match @buf. If @buf isn't long enough, @buf is nul terminated
- * and %NULL is returned.
- */
- char *kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen)
- {
- int ret;
-
- ret = kernfs_path_from_node(kn, NULL, buf, buflen);
- if (ret < 0 || ret >= buflen)
- return NULL;
- return buf;
- }
- EXPORT_SYMBOL_GPL(kernfs_path);
-
/**
* pr_cont_kernfs_name - pr_cont name of a kernfs_node
* @kn: kernfs_node of interest
}
static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry)
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags)
{
struct kernfs_node *kn = old_dentry->d_fsdata;
struct kernfs_node *new_parent = new_dir->i_private;
struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops;
int ret;
+ if (flags)
+ return -EINVAL;
+
if (!scops || !scops->rename)
return -EPERM;
int cgroup_rm_cftypes(struct cftype *cfts);
void cgroup_file_notify(struct cgroup_file *cfile);
- 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);
int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry);
int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *tsk);
return cgrp->ancestor_ids[ancestor->level] == ancestor->id;
}
+/**
+ * task_under_cgroup_hierarchy - test task's membership of cgroup ancestry
+ * @task: the task to be tested
+ * @ancestor: possible ancestor of @task's cgroup
+ *
+ * Tests whether @task's default cgroup hierarchy is a descendant of @ancestor.
+ * It follows all the same rules as cgroup_is_descendant, and only applies
+ * to the default hierarchy.
+ */
+static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
+ struct cgroup *ancestor)
+{
+ struct css_set *cset = task_css_set(task);
+
+ return cgroup_is_descendant(cset->dfl_cgrp, ancestor);
+}
+
/* no synchronization, the result can only be used as a hint */
static inline bool cgroup_is_populated(struct cgroup *cgrp)
{
return kernfs_name(cgrp->kn, buf, buflen);
}
- static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf,
- size_t buflen)
+ static inline int cgroup_path(struct cgroup *cgrp, char *buf, size_t buflen)
{
return kernfs_path(cgrp->kn, buf, buflen);
}
#else /* !CONFIG_CGROUPS */
struct cgroup_subsys_state;
+struct cgroup;
static inline void css_put(struct cgroup_subsys_state *css) {}
static inline int cgroup_attach_task_all(struct task_struct *from,
static inline int cgroup_init_early(void) { return 0; }
static inline int cgroup_init(void) { return 0; }
+static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
+ struct cgroup *ancestor)
+{
+ return true;
+}
#endif /* !CONFIG_CGROUPS */
/*
struct user_namespace *user_ns,
struct cgroup_namespace *old_ns);
- 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);
#else /* !CONFIG_CGROUPS */
#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
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));
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);
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
.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);
*
* 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);
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);
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;
}
mutex_lock(&cgroup_mutex);
ret = kernfs_rename(kn, new_parent, new_name_str);
+ if (!ret)
+ trace_cgroup_rename(cgrp);
mutex_unlock(&cgroup_mutex);
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);
ss->css_released(css);
} else {
/* cgroup release path */
+ trace_cgroup_release(cgrp);
+
cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
cgrp->id = -1;
if (ret)
goto out_destroy;
+ trace_cgroup_mkdir(cgrp);
+
/* let's create and online css's */
kernfs_activate(kn);
ret = cgroup_destroy_locked(cgrp);
+ if (!ret)
+ trace_cgroup_rmdir(cgrp);
+
cgroup_kn_unlock(kn);
return ret;
}
BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files));
BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files));
+ /*
+ * The latency of the synchronize_sched() is too high for cgroups,
+ * avoid it at the cost of forcing all readers into the slow path.
+ */
+ rcu_sync_enter_start(&cgroup_threadgroup_rwsem.rss);
+
get_user_ns(init_cgroup_ns.user_ns);
mutex_lock(&cgroup_mutex);
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;
* " (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;
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
{
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);
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 >= PATH_MAX)
goto out;
argv[0] = agentbuf;
- argv[1] = path;
+ argv[1] = pathbuf;
argv[2] = NULL;
/* minimal command environment */
#define P(F) \
SEQ_printf(m, " .%-30s: %lld\n", #F, (long long)F)
+#define P_SCHEDSTAT(F) \
+ SEQ_printf(m, " .%-30s: %lld\n", #F, (long long)schedstat_val(F))
#define PN(F) \
SEQ_printf(m, " .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F))
+#define PN_SCHEDSTAT(F) \
+ SEQ_printf(m, " .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)schedstat_val(F)))
if (!se)
return;
PN(se->exec_start);
PN(se->vruntime);
PN(se->sum_exec_runtime);
-#ifdef CONFIG_SCHEDSTATS
if (schedstat_enabled()) {
- PN(se->statistics.wait_start);
- PN(se->statistics.sleep_start);
- PN(se->statistics.block_start);
- PN(se->statistics.sleep_max);
- PN(se->statistics.block_max);
- PN(se->statistics.exec_max);
- PN(se->statistics.slice_max);
- PN(se->statistics.wait_max);
- PN(se->statistics.wait_sum);
- P(se->statistics.wait_count);
+ PN_SCHEDSTAT(se->statistics.wait_start);
+ PN_SCHEDSTAT(se->statistics.sleep_start);
+ PN_SCHEDSTAT(se->statistics.block_start);
+ PN_SCHEDSTAT(se->statistics.sleep_max);
+ PN_SCHEDSTAT(se->statistics.block_max);
+ PN_SCHEDSTAT(se->statistics.exec_max);
+ PN_SCHEDSTAT(se->statistics.slice_max);
+ PN_SCHEDSTAT(se->statistics.wait_max);
+ PN_SCHEDSTAT(se->statistics.wait_sum);
+ P_SCHEDSTAT(se->statistics.wait_count);
}
-#endif
P(se->load.weight);
#ifdef CONFIG_SMP
P(se->avg.load_avg);
P(se->avg.util_avg);
#endif
+
+#undef PN_SCHEDSTAT
#undef PN
+#undef P_SCHEDSTAT
#undef P
}
#endif
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
p->prio);
SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
- SPLIT_NS(schedstat_val(p, se.statistics.wait_sum)),
+ SPLIT_NS(schedstat_val_or_zero(p->se.statistics.wait_sum)),
SPLIT_NS(p->se.sum_exec_runtime),
- SPLIT_NS(schedstat_val(p, se.statistics.sum_sleep_runtime)));
+ SPLIT_NS(schedstat_val_or_zero(p->se.statistics.sum_sleep_runtime)));
#ifdef CONFIG_NUMA_BALANCING
SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
#undef P64
#endif
-#ifdef CONFIG_SCHEDSTATS
-#define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n);
-
+#define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, schedstat_val(rq->n));
if (schedstat_enabled()) {
P(yld_count);
P(sched_count);
P(ttwu_count);
P(ttwu_local);
}
-
#undef P
-#endif
+
spin_lock_irqsave(&sched_debug_lock, flags);
print_cfs_stats(m, cpu);
print_rt_stats(m, cpu);
SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F)
#define P(F) \
SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F)
+#define P_SCHEDSTAT(F) \
+ SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)schedstat_val(p->F))
#define __PN(F) \
SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
#define PN(F) \
SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
+#define PN_SCHEDSTAT(F) \
+ SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)schedstat_val(p->F)))
PN(se.exec_start);
PN(se.vruntime);
P(se.nr_migrations);
-#ifdef CONFIG_SCHEDSTATS
if (schedstat_enabled()) {
u64 avg_atom, avg_per_cpu;
- PN(se.statistics.sum_sleep_runtime);
- PN(se.statistics.wait_start);
- PN(se.statistics.sleep_start);
- PN(se.statistics.block_start);
- PN(se.statistics.sleep_max);
- PN(se.statistics.block_max);
- PN(se.statistics.exec_max);
- PN(se.statistics.slice_max);
- PN(se.statistics.wait_max);
- PN(se.statistics.wait_sum);
- P(se.statistics.wait_count);
- PN(se.statistics.iowait_sum);
- P(se.statistics.iowait_count);
- P(se.statistics.nr_migrations_cold);
- P(se.statistics.nr_failed_migrations_affine);
- P(se.statistics.nr_failed_migrations_running);
- P(se.statistics.nr_failed_migrations_hot);
- P(se.statistics.nr_forced_migrations);
- P(se.statistics.nr_wakeups);
- P(se.statistics.nr_wakeups_sync);
- P(se.statistics.nr_wakeups_migrate);
- P(se.statistics.nr_wakeups_local);
- P(se.statistics.nr_wakeups_remote);
- P(se.statistics.nr_wakeups_affine);
- P(se.statistics.nr_wakeups_affine_attempts);
- P(se.statistics.nr_wakeups_passive);
- P(se.statistics.nr_wakeups_idle);
+ PN_SCHEDSTAT(se.statistics.sum_sleep_runtime);
+ PN_SCHEDSTAT(se.statistics.wait_start);
+ PN_SCHEDSTAT(se.statistics.sleep_start);
+ PN_SCHEDSTAT(se.statistics.block_start);
+ PN_SCHEDSTAT(se.statistics.sleep_max);
+ PN_SCHEDSTAT(se.statistics.block_max);
+ PN_SCHEDSTAT(se.statistics.exec_max);
+ PN_SCHEDSTAT(se.statistics.slice_max);
+ PN_SCHEDSTAT(se.statistics.wait_max);
+ PN_SCHEDSTAT(se.statistics.wait_sum);
+ P_SCHEDSTAT(se.statistics.wait_count);
+ PN_SCHEDSTAT(se.statistics.iowait_sum);
+ P_SCHEDSTAT(se.statistics.iowait_count);
+ P_SCHEDSTAT(se.statistics.nr_migrations_cold);
+ P_SCHEDSTAT(se.statistics.nr_failed_migrations_affine);
+ P_SCHEDSTAT(se.statistics.nr_failed_migrations_running);
+ P_SCHEDSTAT(se.statistics.nr_failed_migrations_hot);
+ P_SCHEDSTAT(se.statistics.nr_forced_migrations);
+ P_SCHEDSTAT(se.statistics.nr_wakeups);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_sync);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_migrate);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_local);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_remote);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_affine);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_affine_attempts);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_passive);
+ P_SCHEDSTAT(se.statistics.nr_wakeups_idle);
avg_atom = p->se.sum_exec_runtime;
if (nr_switches)
__PN(avg_atom);
__PN(avg_per_cpu);
}
-#endif
+
__P(nr_switches);
SEQ_printf(m, "%-45s:%21Ld\n",
"nr_voluntary_switches", (long long)p->nvcsw);
#endif
P(policy);
P(prio);
+#undef PN_SCHEDSTAT
#undef PN
#undef __PN
+#undef P_SCHEDSTAT
#undef P
#undef __P