#include <linux/kernel.h>
#include <linux/taskstats_kern.h>
+#include <linux/tsacct_kern.h>
#include <linux/delayacct.h>
+#include <linux/cpumask.h>
+#include <linux/percpu.h>
+#include <linux/cgroupstats.h>
+#include <linux/cgroup.h>
+#include <linux/fs.h>
+#include <linux/file.h>
#include <net/genetlink.h>
#include <asm/atomic.h>
-static DEFINE_PER_CPU(__u32, taskstats_seqnum) = { 0 };
+/*
+ * Maximum length of a cpumask that can be specified in
+ * the TASKSTATS_CMD_ATTR_REGISTER/DEREGISTER_CPUMASK attribute
+ */
+#define TASKSTATS_CPUMASK_MAXLEN (100+6*NR_CPUS)
+
+static DEFINE_PER_CPU(__u32, taskstats_seqnum);
static int family_registered;
-kmem_cache_t *taskstats_cache;
+struct kmem_cache *taskstats_cache;
static struct genl_family family = {
.id = GENL_ID_GENERATE,
__read_mostly = {
[TASKSTATS_CMD_ATTR_PID] = { .type = NLA_U32 },
[TASKSTATS_CMD_ATTR_TGID] = { .type = NLA_U32 },
+ [TASKSTATS_CMD_ATTR_REGISTER_CPUMASK] = { .type = NLA_STRING },
+ [TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK] = { .type = NLA_STRING },};
+
+static struct nla_policy
+cgroupstats_cmd_get_policy[CGROUPSTATS_CMD_ATTR_MAX+1] __read_mostly = {
+ [CGROUPSTATS_CMD_ATTR_FD] = { .type = NLA_U32 },
};
+struct listener {
+ struct list_head list;
+ pid_t pid;
+ char valid;
+};
+
+struct listener_list {
+ struct rw_semaphore sem;
+ struct list_head list;
+};
+static DEFINE_PER_CPU(struct listener_list, listener_array);
+
+enum actions {
+ REGISTER,
+ DEREGISTER,
+ CPU_DONT_CARE
+};
static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp,
- void **replyp, size_t size)
+ size_t size)
{
struct sk_buff *skb;
void *reply;
/*
* If new attributes are added, please revisit this allocation
*/
- skb = nlmsg_new(size);
+ skb = genlmsg_new(size, GFP_KERNEL);
if (!skb)
return -ENOMEM;
int seq = get_cpu_var(taskstats_seqnum)++;
put_cpu_var(taskstats_seqnum);
- reply = genlmsg_put(skb, 0, seq,
- family.id, 0, 0,
- cmd, family.version);
+ reply = genlmsg_put(skb, 0, seq, &family, 0, cmd);
} else
- reply = genlmsg_put(skb, info->snd_pid, info->snd_seq,
- family.id, 0, 0,
- cmd, family.version);
+ reply = genlmsg_put_reply(skb, info, &family, 0, cmd);
if (reply == NULL) {
nlmsg_free(skb);
return -EINVAL;
}
*skbp = skb;
- *replyp = reply;
return 0;
}
-static int send_reply(struct sk_buff *skb, pid_t pid, int event)
+/*
+ * Send taskstats data in @skb to listener with nl_pid @pid
+ */
+static int send_reply(struct sk_buff *skb, pid_t pid)
{
- struct genlmsghdr *genlhdr = nlmsg_data((struct nlmsghdr *)skb->data);
- void *reply;
+ struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb));
+ void *reply = genlmsg_data(genlhdr);
int rc;
- reply = genlmsg_data(genlhdr);
-
rc = genlmsg_end(skb, reply);
if (rc < 0) {
nlmsg_free(skb);
return rc;
}
- if (event == TASKSTATS_MSG_MULTICAST)
- return genlmsg_multicast(skb, pid, TASKSTATS_LISTEN_GROUP);
return genlmsg_unicast(skb, pid);
}
-static int fill_pid(pid_t pid, struct task_struct *pidtsk,
+/*
+ * Send taskstats data in @skb to listeners registered for @cpu's exit data
+ */
+static void send_cpu_listeners(struct sk_buff *skb,
+ struct listener_list *listeners)
+{
+ struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb));
+ struct listener *s, *tmp;
+ struct sk_buff *skb_next, *skb_cur = skb;
+ void *reply = genlmsg_data(genlhdr);
+ int rc, delcount = 0;
+
+ rc = genlmsg_end(skb, reply);
+ if (rc < 0) {
+ nlmsg_free(skb);
+ return;
+ }
+
+ rc = 0;
+ down_read(&listeners->sem);
+ list_for_each_entry(s, &listeners->list, list) {
+ skb_next = NULL;
+ if (!list_is_last(&s->list, &listeners->list)) {
+ skb_next = skb_clone(skb_cur, GFP_KERNEL);
+ if (!skb_next)
+ break;
+ }
+ rc = genlmsg_unicast(skb_cur, s->pid);
+ if (rc == -ECONNREFUSED) {
+ s->valid = 0;
+ delcount++;
+ }
+ skb_cur = skb_next;
+ }
+ up_read(&listeners->sem);
+
+ if (skb_cur)
+ nlmsg_free(skb_cur);
+
+ if (!delcount)
+ return;
+
+ /* Delete invalidated entries */
+ down_write(&listeners->sem);
+ list_for_each_entry_safe(s, tmp, &listeners->list, list) {
+ if (!s->valid) {
+ list_del(&s->list);
+ kfree(s);
+ }
+ }
+ up_write(&listeners->sem);
+}
+
+static int fill_pid(pid_t pid, struct task_struct *tsk,
struct taskstats *stats)
{
- int rc;
- struct task_struct *tsk = pidtsk;
+ int rc = 0;
- if (!pidtsk) {
- read_lock(&tasklist_lock);
- tsk = find_task_by_pid(pid);
- if (!tsk) {
- read_unlock(&tasklist_lock);
+ if (!tsk) {
+ rcu_read_lock();
+ tsk = find_task_by_vpid(pid);
+ if (tsk)
+ get_task_struct(tsk);
+ rcu_read_unlock();
+ if (!tsk)
return -ESRCH;
- }
- get_task_struct(tsk);
- read_unlock(&tasklist_lock);
} else
get_task_struct(tsk);
+ memset(stats, 0, sizeof(*stats));
/*
* Each accounting subsystem adds calls to its functions to
* fill in relevant parts of struct taskstsats as follows
*
- * rc = per-task-foo(stats, tsk);
- * if (rc)
- * goto err;
+ * per-task-foo(stats, tsk);
*/
- rc = delayacct_add_tsk(stats, tsk);
+ delayacct_add_tsk(stats, tsk);
+
+ /* fill in basic acct fields */
stats->version = TASKSTATS_VERSION;
+ stats->nvcsw = tsk->nvcsw;
+ stats->nivcsw = tsk->nivcsw;
+ bacct_add_tsk(stats, tsk);
+
+ /* fill in extended acct fields */
+ xacct_add_tsk(stats, tsk);
/* Define err: label here if needed */
put_task_struct(tsk);
}
-static int fill_tgid(pid_t tgid, struct task_struct *tgidtsk,
+static int fill_tgid(pid_t tgid, struct task_struct *first,
struct taskstats *stats)
{
- int rc;
- struct task_struct *tsk, *first;
-
- first = tgidtsk;
- read_lock(&tasklist_lock);
- if (!first) {
- first = find_task_by_pid(tgid);
- if (!first) {
- read_unlock(&tasklist_lock);
- return -ESRCH;
- }
- }
+ struct task_struct *tsk;
+ unsigned long flags;
+ int rc = -ESRCH;
+
+ /*
+ * Add additional stats from live tasks except zombie thread group
+ * leaders who are already counted with the dead tasks
+ */
+ rcu_read_lock();
+ if (!first)
+ first = find_task_by_vpid(tgid);
+
+ if (!first || !lock_task_sighand(first, &flags))
+ goto out;
+
+ if (first->signal->stats)
+ memcpy(stats, first->signal->stats, sizeof(*stats));
+ else
+ memset(stats, 0, sizeof(*stats));
+
tsk = first;
do {
+ if (tsk->exit_state)
+ continue;
/*
- * Each accounting subsystem adds calls its functions to
+ * Accounting subsystem can call its functions here to
* fill in relevant parts of struct taskstsats as follows
*
- * rc = per-task-foo(stats, tsk);
- * if (rc)
- * break;
+ * per-task-foo(stats, tsk);
*/
+ delayacct_add_tsk(stats, tsk);
- rc = delayacct_add_tsk(stats, tsk);
- if (rc)
- break;
-
+ stats->nvcsw += tsk->nvcsw;
+ stats->nivcsw += tsk->nivcsw;
} while_each_thread(first, tsk);
- read_unlock(&tasklist_lock);
+
+ unlock_task_sighand(first, &flags);
+ rc = 0;
+out:
+ rcu_read_unlock();
+
stats->version = TASKSTATS_VERSION;
+ /*
+ * Accounting subsystems can also add calls here to modify
+ * fields of taskstats.
+ */
+ return rc;
+}
+
+static void fill_tgid_exit(struct task_struct *tsk)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&tsk->sighand->siglock, flags);
+ if (!tsk->signal->stats)
+ goto ret;
/*
- * Accounting subsytems can also add calls here if they don't
- * wish to aggregate statistics for per-tgid stats
+ * Each accounting subsystem calls its functions here to
+ * accumalate its per-task stats for tsk, into the per-tgid structure
+ *
+ * per-task-foo(tsk->signal->stats, tsk);
*/
+ delayacct_add_tsk(tsk->signal->stats, tsk);
+ret:
+ spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
+ return;
+}
- return rc;
+static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd)
+{
+ struct listener_list *listeners;
+ struct listener *s, *tmp;
+ unsigned int cpu;
+
+ if (!cpumask_subset(mask, cpu_possible_mask))
+ return -EINVAL;
+
+ if (isadd == REGISTER) {
+ for_each_cpu(cpu, mask) {
+ s = kmalloc_node(sizeof(struct listener), GFP_KERNEL,
+ cpu_to_node(cpu));
+ if (!s)
+ goto cleanup;
+ s->pid = pid;
+ INIT_LIST_HEAD(&s->list);
+ s->valid = 1;
+
+ listeners = &per_cpu(listener_array, cpu);
+ down_write(&listeners->sem);
+ list_add(&s->list, &listeners->list);
+ up_write(&listeners->sem);
+ }
+ return 0;
+ }
+
+ /* Deregister or cleanup */
+cleanup:
+ for_each_cpu(cpu, mask) {
+ listeners = &per_cpu(listener_array, cpu);
+ down_write(&listeners->sem);
+ list_for_each_entry_safe(s, tmp, &listeners->list, list) {
+ if (s->pid == pid) {
+ list_del(&s->list);
+ kfree(s);
+ break;
+ }
+ }
+ up_write(&listeners->sem);
+ }
+ return 0;
+}
+
+static int parse(struct nlattr *na, struct cpumask *mask)
+{
+ char *data;
+ int len;
+ int ret;
+
+ if (na == NULL)
+ return 1;
+ len = nla_len(na);
+ if (len > TASKSTATS_CPUMASK_MAXLEN)
+ return -E2BIG;
+ if (len < 1)
+ return -EINVAL;
+ data = kmalloc(len, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+ nla_strlcpy(data, na, len);
+ ret = cpulist_parse(data, mask);
+ kfree(data);
+ return ret;
}
-static int taskstats_send_stats(struct sk_buff *skb, struct genl_info *info)
+static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid)
+{
+ struct nlattr *na, *ret;
+ int aggr;
+
+ aggr = (type == TASKSTATS_TYPE_PID)
+ ? TASKSTATS_TYPE_AGGR_PID
+ : TASKSTATS_TYPE_AGGR_TGID;
+
+ na = nla_nest_start(skb, aggr);
+ if (!na)
+ goto err;
+ if (nla_put(skb, type, sizeof(pid), &pid) < 0)
+ goto err;
+ ret = nla_reserve(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats));
+ if (!ret)
+ goto err;
+ nla_nest_end(skb, na);
+
+ return nla_data(ret);
+err:
+ return NULL;
+}
+
+static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
{
int rc = 0;
struct sk_buff *rep_skb;
- struct taskstats stats;
- void *reply;
- size_t size;
+ struct cgroupstats *stats;
struct nlattr *na;
+ size_t size;
+ u32 fd;
+ struct file *file;
+ int fput_needed;
+
+ na = info->attrs[CGROUPSTATS_CMD_ATTR_FD];
+ if (!na)
+ return -EINVAL;
+
+ fd = nla_get_u32(info->attrs[CGROUPSTATS_CMD_ATTR_FD]);
+ file = fget_light(fd, &fput_needed);
+ if (!file)
+ return 0;
+
+ size = nla_total_size(sizeof(struct cgroupstats));
+
+ rc = prepare_reply(info, CGROUPSTATS_CMD_NEW, &rep_skb,
+ size);
+ if (rc < 0)
+ goto err;
+
+ na = nla_reserve(rep_skb, CGROUPSTATS_TYPE_CGROUP_STATS,
+ sizeof(struct cgroupstats));
+ stats = nla_data(na);
+ memset(stats, 0, sizeof(*stats));
+
+ rc = cgroupstats_build(stats, file->f_dentry);
+ if (rc < 0) {
+ nlmsg_free(rep_skb);
+ goto err;
+ }
+
+ rc = send_reply(rep_skb, info->snd_pid);
+
+err:
+ fput_light(file, fput_needed);
+ return rc;
+}
+
+static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
+{
+ int rc;
+ struct sk_buff *rep_skb;
+ struct taskstats *stats;
+ size_t size;
+ cpumask_var_t mask;
+
+ if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+ return -ENOMEM;
+
+ rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask);
+ if (rc < 0)
+ goto free_return_rc;
+ if (rc == 0) {
+ rc = add_del_listener(info->snd_pid, mask, REGISTER);
+ goto free_return_rc;
+ }
+
+ rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask);
+ if (rc < 0)
+ goto free_return_rc;
+ if (rc == 0) {
+ rc = add_del_listener(info->snd_pid, mask, DEREGISTER);
+free_return_rc:
+ free_cpumask_var(mask);
+ return rc;
+ }
+ free_cpumask_var(mask);
/*
* Size includes space for nested attributes
size = nla_total_size(sizeof(u32)) +
nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
- memset(&stats, 0, sizeof(stats));
- rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, &reply, size);
+ rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size);
if (rc < 0)
return rc;
+ rc = -EINVAL;
if (info->attrs[TASKSTATS_CMD_ATTR_PID]) {
u32 pid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_PID]);
- rc = fill_pid(pid, NULL, &stats);
- if (rc < 0)
+ stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, pid);
+ if (!stats)
goto err;
- na = nla_nest_start(rep_skb, TASKSTATS_TYPE_AGGR_PID);
- NLA_PUT_U32(rep_skb, TASKSTATS_TYPE_PID, pid);
- NLA_PUT_TYPE(rep_skb, struct taskstats, TASKSTATS_TYPE_STATS,
- stats);
+ rc = fill_pid(pid, NULL, stats);
+ if (rc < 0)
+ goto err;
} else if (info->attrs[TASKSTATS_CMD_ATTR_TGID]) {
u32 tgid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_TGID]);
- rc = fill_tgid(tgid, NULL, &stats);
- if (rc < 0)
+ stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tgid);
+ if (!stats)
goto err;
- na = nla_nest_start(rep_skb, TASKSTATS_TYPE_AGGR_TGID);
- NLA_PUT_U32(rep_skb, TASKSTATS_TYPE_TGID, tgid);
- NLA_PUT_TYPE(rep_skb, struct taskstats, TASKSTATS_TYPE_STATS,
- stats);
- } else {
- rc = -EINVAL;
+ rc = fill_tgid(tgid, NULL, stats);
+ if (rc < 0)
+ goto err;
+ } else
goto err;
- }
- nla_nest_end(rep_skb, na);
-
- return send_reply(rep_skb, info->snd_pid, TASKSTATS_MSG_UNICAST);
-
-nla_put_failure:
- return genlmsg_cancel(rep_skb, reply);
+ return send_reply(rep_skb, info->snd_pid);
err:
nlmsg_free(rep_skb);
return rc;
}
+static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk)
+{
+ struct signal_struct *sig = tsk->signal;
+ struct taskstats *stats;
+
+ if (sig->stats || thread_group_empty(tsk))
+ goto ret;
+
+ /* No problem if kmem_cache_zalloc() fails */
+ stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
+
+ spin_lock_irq(&tsk->sighand->siglock);
+ if (!sig->stats) {
+ sig->stats = stats;
+ stats = NULL;
+ }
+ spin_unlock_irq(&tsk->sighand->siglock);
+
+ if (stats)
+ kmem_cache_free(taskstats_cache, stats);
+ret:
+ return sig->stats;
+}
+
/* Send pid data out on exit */
-void taskstats_exit_send(struct task_struct *tsk, struct taskstats *tidstats,
- struct taskstats *tgidstats)
+void taskstats_exit(struct task_struct *tsk, int group_dead)
{
int rc;
+ struct listener_list *listeners;
+ struct taskstats *stats;
struct sk_buff *rep_skb;
- void *reply;
size_t size;
int is_thread_group;
- struct nlattr *na;
- if (!family_registered || !tidstats)
+ if (!family_registered)
return;
- is_thread_group = !thread_group_empty(tsk);
- rc = 0;
-
/*
* Size includes space for nested attributes
*/
size = nla_total_size(sizeof(u32)) +
nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
- if (is_thread_group)
- size = 2 * size; /* PID + STATS + TGID + STATS */
+ is_thread_group = !!taskstats_tgid_alloc(tsk);
+ if (is_thread_group) {
+ /* PID + STATS + TGID + STATS */
+ size = 2 * size;
+ /* fill the tsk->signal->stats structure */
+ fill_tgid_exit(tsk);
+ }
- rc = prepare_reply(NULL, TASKSTATS_CMD_NEW, &rep_skb, &reply, size);
- if (rc < 0)
- goto ret;
+ listeners = &__raw_get_cpu_var(listener_array);
+ if (list_empty(&listeners->list))
+ return;
- rc = fill_pid(tsk->pid, tsk, tidstats);
+ rc = prepare_reply(NULL, TASKSTATS_CMD_NEW, &rep_skb, size);
if (rc < 0)
- goto err_skb;
+ return;
- na = nla_nest_start(rep_skb, TASKSTATS_TYPE_AGGR_PID);
- NLA_PUT_U32(rep_skb, TASKSTATS_TYPE_PID, (u32)tsk->pid);
- NLA_PUT_TYPE(rep_skb, struct taskstats, TASKSTATS_TYPE_STATS,
- *tidstats);
- nla_nest_end(rep_skb, na);
+ stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, tsk->pid);
+ if (!stats)
+ goto err;
- if (!is_thread_group || !tgidstats) {
- send_reply(rep_skb, 0, TASKSTATS_MSG_MULTICAST);
- goto ret;
- }
+ rc = fill_pid(-1, tsk, stats);
+ if (rc < 0)
+ goto err;
- rc = fill_tgid(tsk->pid, tsk, tgidstats);
/*
- * If fill_tgid() failed then one probable reason could be that the
- * thread group leader has exited. fill_tgid() will fail, send out
- * the pid statistics collected earlier.
+ * Doesn't matter if tsk is the leader or the last group member leaving
*/
- if (rc < 0) {
- send_reply(rep_skb, 0, TASKSTATS_MSG_MULTICAST);
- goto ret;
- }
+ if (!is_thread_group || !group_dead)
+ goto send;
- na = nla_nest_start(rep_skb, TASKSTATS_TYPE_AGGR_TGID);
- NLA_PUT_U32(rep_skb, TASKSTATS_TYPE_TGID, (u32)tsk->tgid);
- NLA_PUT_TYPE(rep_skb, struct taskstats, TASKSTATS_TYPE_STATS,
- *tgidstats);
- nla_nest_end(rep_skb, na);
+ stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tsk->tgid);
+ if (!stats)
+ goto err;
- send_reply(rep_skb, 0, TASKSTATS_MSG_MULTICAST);
- goto ret;
+ memcpy(stats, tsk->signal->stats, sizeof(*stats));
-nla_put_failure:
- genlmsg_cancel(rep_skb, reply);
- goto ret;
-err_skb:
- nlmsg_free(rep_skb);
-ret:
+send:
+ send_cpu_listeners(rep_skb, listeners);
return;
+err:
+ nlmsg_free(rep_skb);
}
static struct genl_ops taskstats_ops = {
.cmd = TASKSTATS_CMD_GET,
- .doit = taskstats_send_stats,
+ .doit = taskstats_user_cmd,
.policy = taskstats_cmd_get_policy,
};
+static struct genl_ops cgroupstats_ops = {
+ .cmd = CGROUPSTATS_CMD_GET,
+ .doit = cgroupstats_user_cmd,
+ .policy = cgroupstats_cmd_get_policy,
+};
+
/* Needed early in initialization */
void __init taskstats_init_early(void)
{
- taskstats_cache = kmem_cache_create("taskstats_cache",
- sizeof(struct taskstats),
- 0, SLAB_PANIC, NULL, NULL);
+ unsigned int i;
+
+ taskstats_cache = KMEM_CACHE(taskstats, SLAB_PANIC);
+ for_each_possible_cpu(i) {
+ INIT_LIST_HEAD(&(per_cpu(listener_array, i).list));
+ init_rwsem(&(per_cpu(listener_array, i).sem));
+ }
}
static int __init taskstats_init(void)
if (rc < 0)
goto err;
+ rc = genl_register_ops(&family, &cgroupstats_ops);
+ if (rc < 0)
+ goto err_cgroup_ops;
+
family_registered = 1;
+ printk("registered taskstats version %d\n", TASKSTATS_GENL_VERSION);
return 0;
+err_cgroup_ops:
+ genl_unregister_ops(&family, &taskstats_ops);
err:
genl_unregister_family(&family);
return rc;
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff