linux-sg2042/kernel/taskstats.c

637 lines
14 KiB
C
Raw Normal View History

/*
* taskstats.c - Export per-task statistics to userland
*
* Copyright (C) Shailabh Nagar, IBM Corp. 2006
* (C) Balbir Singh, IBM Corp. 2006
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
*/
#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>
Add cgroupstats This patch is inspired by the discussion at http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263. The patch is on top of 2.6.21-mm1 with Paul's cgroups v9 patches (forward ported) This patch implements per cgroup statistics infrastructure and re-uses code from the taskstats interface. A new set of cgroup operations are registered with commands and attributes. It should be very easy to *extend* per cgroup statistics, by adding members to the cgroupstats structure. The current model for cgroupstats is a pull, a push model (to post statistics on interesting events), should be very easy to add. Currently user space requests for statistics by passing the cgroup file descriptor. Statistics about the state of all the tasks in the cgroup is returned to user space. TODO's/NOTE: This patch provides an infrastructure for implementing cgroup statistics. Based on the needs of each controller, we can incrementally add more statistics, event based support for notification of statistics, accumulation of taskstats into cgroup statistics in the future. Sample output # ./cgroupstats -C /cgroup/a sleeping 2, blocked 0, running 1, stopped 0, uninterruptible 0 # ./cgroupstats -C /cgroup/ sleeping 154, blocked 0, running 0, stopped 0, uninterruptible 0 If the approach looks good, I'll enhance and post the user space utility for the same Feedback, comments, test results are always welcome! [akpm@linux-foundation.org: build fix] Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Jay Lan <jlan@engr.sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:44 +08:00
#include <linux/cgroupstats.h>
#include <linux/cgroup.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <net/genetlink.h>
#include <asm/atomic.h>
/*
* 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;
struct kmem_cache *taskstats_cache;
static struct genl_family family = {
.id = GENL_ID_GENERATE,
.name = TASKSTATS_GENL_NAME,
.version = TASKSTATS_GENL_VERSION,
.maxattr = TASKSTATS_CMD_ATTR_MAX,
};
static struct nla_policy taskstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1]
__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 },};
Add cgroupstats This patch is inspired by the discussion at http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263. The patch is on top of 2.6.21-mm1 with Paul's cgroups v9 patches (forward ported) This patch implements per cgroup statistics infrastructure and re-uses code from the taskstats interface. A new set of cgroup operations are registered with commands and attributes. It should be very easy to *extend* per cgroup statistics, by adding members to the cgroupstats structure. The current model for cgroupstats is a pull, a push model (to post statistics on interesting events), should be very easy to add. Currently user space requests for statistics by passing the cgroup file descriptor. Statistics about the state of all the tasks in the cgroup is returned to user space. TODO's/NOTE: This patch provides an infrastructure for implementing cgroup statistics. Based on the needs of each controller, we can incrementally add more statistics, event based support for notification of statistics, accumulation of taskstats into cgroup statistics in the future. Sample output # ./cgroupstats -C /cgroup/a sleeping 2, blocked 0, running 1, stopped 0, uninterruptible 0 # ./cgroupstats -C /cgroup/ sleeping 154, blocked 0, running 0, stopped 0, uninterruptible 0 If the approach looks good, I'll enhance and post the user space utility for the same Feedback, comments, test results are always welcome! [akpm@linux-foundation.org: build fix] Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Jay Lan <jlan@engr.sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:44 +08:00
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,
size_t size)
{
struct sk_buff *skb;
void *reply;
/*
* If new attributes are added, please revisit this allocation
*/
skb = genlmsg_new(size, GFP_KERNEL);
if (!skb)
return -ENOMEM;
if (!info) {
int seq = get_cpu_var(taskstats_seqnum)++;
put_cpu_var(taskstats_seqnum);
reply = genlmsg_put(skb, 0, seq, &family, 0, cmd);
} else
reply = genlmsg_put_reply(skb, info, &family, 0, cmd);
if (reply == NULL) {
nlmsg_free(skb);
return -EINVAL;
}
*skbp = skb;
return 0;
}
/*
* Send taskstats data in @skb to listener with nl_pid @pid
*/
genetlink: make netns aware This makes generic netlink network namespace aware. No generic netlink families except for the controller family are made namespace aware, they need to be checked one by one and then set the family->netnsok member to true. A new function genlmsg_multicast_netns() is introduced to allow sending a multicast message in a given namespace, for example when it applies to an object that lives in that namespace, a new function genlmsg_multicast_allns() to send a message to all network namespaces (for objects that do not have an associated netns). The function genlmsg_multicast() is changed to multicast the message in just init_net, which is currently correct for all generic netlink families since they only work in init_net right now. Some will later want to work in all net namespaces because they do not care about the netns at all -- those will have to be converted to use one of the new functions genlmsg_multicast_allns() or genlmsg_multicast_netns() whenever they are made netns aware in some way. After this patch families can easily decide whether or not they should be available in all net namespaces. Many genl families us it for objects not related to networking and should therefore be available in all namespaces, but that will have to be done on a per family basis. Note that this doesn't touch on the checkpoint/restart problem where network namespaces could be used, genl families and multicast groups are numbered globally and I see no easy way of changing that, especially since it must be possible to multicast to all network namespaces for those families that do not care about netns. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-07-10 17:51:34 +08:00
static int send_reply(struct sk_buff *skb, struct genl_info *info)
{
struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb));
void *reply = genlmsg_data(genlhdr);
int rc;
rc = genlmsg_end(skb, reply);
if (rc < 0) {
nlmsg_free(skb);
return rc;
}
genetlink: make netns aware This makes generic netlink network namespace aware. No generic netlink families except for the controller family are made namespace aware, they need to be checked one by one and then set the family->netnsok member to true. A new function genlmsg_multicast_netns() is introduced to allow sending a multicast message in a given namespace, for example when it applies to an object that lives in that namespace, a new function genlmsg_multicast_allns() to send a message to all network namespaces (for objects that do not have an associated netns). The function genlmsg_multicast() is changed to multicast the message in just init_net, which is currently correct for all generic netlink families since they only work in init_net right now. Some will later want to work in all net namespaces because they do not care about the netns at all -- those will have to be converted to use one of the new functions genlmsg_multicast_allns() or genlmsg_multicast_netns() whenever they are made netns aware in some way. After this patch families can easily decide whether or not they should be available in all net namespaces. Many genl families us it for objects not related to networking and should therefore be available in all namespaces, but that will have to be done on a per family basis. Note that this doesn't touch on the checkpoint/restart problem where network namespaces could be used, genl families and multicast groups are numbered globally and I see no easy way of changing that, especially since it must be possible to multicast to all network namespaces for those families that do not care about netns. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-07-10 17:51:34 +08:00
return genlmsg_reply(skb, info);
}
/*
* 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;
}
genetlink: make netns aware This makes generic netlink network namespace aware. No generic netlink families except for the controller family are made namespace aware, they need to be checked one by one and then set the family->netnsok member to true. A new function genlmsg_multicast_netns() is introduced to allow sending a multicast message in a given namespace, for example when it applies to an object that lives in that namespace, a new function genlmsg_multicast_allns() to send a message to all network namespaces (for objects that do not have an associated netns). The function genlmsg_multicast() is changed to multicast the message in just init_net, which is currently correct for all generic netlink families since they only work in init_net right now. Some will later want to work in all net namespaces because they do not care about the netns at all -- those will have to be converted to use one of the new functions genlmsg_multicast_allns() or genlmsg_multicast_netns() whenever they are made netns aware in some way. After this patch families can easily decide whether or not they should be available in all net namespaces. Many genl families us it for objects not related to networking and should therefore be available in all namespaces, but that will have to be done on a per family basis. Note that this doesn't touch on the checkpoint/restart problem where network namespaces could be used, genl families and multicast groups are numbered globally and I see no easy way of changing that, especially since it must be possible to multicast to all network namespaces for those families that do not care about netns. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-07-10 17:51:34 +08:00
rc = genlmsg_unicast(&init_net, 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 = 0;
if (!tsk) {
rcu_read_lock();
tsk = find_task_by_vpid(pid);
if (tsk)
get_task_struct(tsk);
rcu_read_unlock();
if (!tsk)
return -ESRCH;
} 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
*
* per-task-foo(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);
return rc;
}
static int fill_tgid(pid_t tgid, struct task_struct *first,
struct taskstats *stats)
{
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;
/*
* Accounting subsystem can call its functions here to
* fill in relevant parts of struct taskstsats as follows
*
* per-task-foo(stats, tsk);
*/
delayacct_add_tsk(stats, tsk);
stats->nvcsw += tsk->nvcsw;
stats->nivcsw += tsk->nivcsw;
} while_each_thread(first, tsk);
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;
/*
* 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;
}
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 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;
}
Add cgroupstats This patch is inspired by the discussion at http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263. The patch is on top of 2.6.21-mm1 with Paul's cgroups v9 patches (forward ported) This patch implements per cgroup statistics infrastructure and re-uses code from the taskstats interface. A new set of cgroup operations are registered with commands and attributes. It should be very easy to *extend* per cgroup statistics, by adding members to the cgroupstats structure. The current model for cgroupstats is a pull, a push model (to post statistics on interesting events), should be very easy to add. Currently user space requests for statistics by passing the cgroup file descriptor. Statistics about the state of all the tasks in the cgroup is returned to user space. TODO's/NOTE: This patch provides an infrastructure for implementing cgroup statistics. Based on the needs of each controller, we can incrementally add more statistics, event based support for notification of statistics, accumulation of taskstats into cgroup statistics in the future. Sample output # ./cgroupstats -C /cgroup/a sleeping 2, blocked 0, running 1, stopped 0, uninterruptible 0 # ./cgroupstats -C /cgroup/ sleeping 154, blocked 0, running 0, stopped 0, uninterruptible 0 If the approach looks good, I'll enhance and post the user space utility for the same Feedback, comments, test results are always welcome! [akpm@linux-foundation.org: build fix] Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Jay Lan <jlan@engr.sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:44 +08:00
static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
{
int rc = 0;
struct sk_buff *rep_skb;
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;
Add cgroupstats This patch is inspired by the discussion at http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263. The patch is on top of 2.6.21-mm1 with Paul's cgroups v9 patches (forward ported) This patch implements per cgroup statistics infrastructure and re-uses code from the taskstats interface. A new set of cgroup operations are registered with commands and attributes. It should be very easy to *extend* per cgroup statistics, by adding members to the cgroupstats structure. The current model for cgroupstats is a pull, a push model (to post statistics on interesting events), should be very easy to add. Currently user space requests for statistics by passing the cgroup file descriptor. Statistics about the state of all the tasks in the cgroup is returned to user space. TODO's/NOTE: This patch provides an infrastructure for implementing cgroup statistics. Based on the needs of each controller, we can incrementally add more statistics, event based support for notification of statistics, accumulation of taskstats into cgroup statistics in the future. Sample output # ./cgroupstats -C /cgroup/a sleeping 2, blocked 0, running 1, stopped 0, uninterruptible 0 # ./cgroupstats -C /cgroup/ sleeping 154, blocked 0, running 0, stopped 0, uninterruptible 0 If the approach looks good, I'll enhance and post the user space utility for the same Feedback, comments, test results are always welcome! [akpm@linux-foundation.org: build fix] Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Jay Lan <jlan@engr.sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:44 +08:00
size = nla_total_size(sizeof(struct cgroupstats));
Add cgroupstats This patch is inspired by the discussion at http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263. The patch is on top of 2.6.21-mm1 with Paul's cgroups v9 patches (forward ported) This patch implements per cgroup statistics infrastructure and re-uses code from the taskstats interface. A new set of cgroup operations are registered with commands and attributes. It should be very easy to *extend* per cgroup statistics, by adding members to the cgroupstats structure. The current model for cgroupstats is a pull, a push model (to post statistics on interesting events), should be very easy to add. Currently user space requests for statistics by passing the cgroup file descriptor. Statistics about the state of all the tasks in the cgroup is returned to user space. TODO's/NOTE: This patch provides an infrastructure for implementing cgroup statistics. Based on the needs of each controller, we can incrementally add more statistics, event based support for notification of statistics, accumulation of taskstats into cgroup statistics in the future. Sample output # ./cgroupstats -C /cgroup/a sleeping 2, blocked 0, running 1, stopped 0, uninterruptible 0 # ./cgroupstats -C /cgroup/ sleeping 154, blocked 0, running 0, stopped 0, uninterruptible 0 If the approach looks good, I'll enhance and post the user space utility for the same Feedback, comments, test results are always welcome! [akpm@linux-foundation.org: build fix] Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Jay Lan <jlan@engr.sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:44 +08:00
rc = prepare_reply(info, CGROUPSTATS_CMD_NEW, &rep_skb,
size);
if (rc < 0)
goto err;
Add cgroupstats This patch is inspired by the discussion at http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263. The patch is on top of 2.6.21-mm1 with Paul's cgroups v9 patches (forward ported) This patch implements per cgroup statistics infrastructure and re-uses code from the taskstats interface. A new set of cgroup operations are registered with commands and attributes. It should be very easy to *extend* per cgroup statistics, by adding members to the cgroupstats structure. The current model for cgroupstats is a pull, a push model (to post statistics on interesting events), should be very easy to add. Currently user space requests for statistics by passing the cgroup file descriptor. Statistics about the state of all the tasks in the cgroup is returned to user space. TODO's/NOTE: This patch provides an infrastructure for implementing cgroup statistics. Based on the needs of each controller, we can incrementally add more statistics, event based support for notification of statistics, accumulation of taskstats into cgroup statistics in the future. Sample output # ./cgroupstats -C /cgroup/a sleeping 2, blocked 0, running 1, stopped 0, uninterruptible 0 # ./cgroupstats -C /cgroup/ sleeping 154, blocked 0, running 0, stopped 0, uninterruptible 0 If the approach looks good, I'll enhance and post the user space utility for the same Feedback, comments, test results are always welcome! [akpm@linux-foundation.org: build fix] Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Jay Lan <jlan@engr.sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:44 +08:00
na = nla_reserve(rep_skb, CGROUPSTATS_TYPE_CGROUP_STATS,
sizeof(struct cgroupstats));
stats = nla_data(na);
memset(stats, 0, sizeof(*stats));
Add cgroupstats This patch is inspired by the discussion at http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263. The patch is on top of 2.6.21-mm1 with Paul's cgroups v9 patches (forward ported) This patch implements per cgroup statistics infrastructure and re-uses code from the taskstats interface. A new set of cgroup operations are registered with commands and attributes. It should be very easy to *extend* per cgroup statistics, by adding members to the cgroupstats structure. The current model for cgroupstats is a pull, a push model (to post statistics on interesting events), should be very easy to add. Currently user space requests for statistics by passing the cgroup file descriptor. Statistics about the state of all the tasks in the cgroup is returned to user space. TODO's/NOTE: This patch provides an infrastructure for implementing cgroup statistics. Based on the needs of each controller, we can incrementally add more statistics, event based support for notification of statistics, accumulation of taskstats into cgroup statistics in the future. Sample output # ./cgroupstats -C /cgroup/a sleeping 2, blocked 0, running 1, stopped 0, uninterruptible 0 # ./cgroupstats -C /cgroup/ sleeping 154, blocked 0, running 0, stopped 0, uninterruptible 0 If the approach looks good, I'll enhance and post the user space utility for the same Feedback, comments, test results are always welcome! [akpm@linux-foundation.org: build fix] Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Jay Lan <jlan@engr.sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:44 +08:00
rc = cgroupstats_build(stats, file->f_dentry);
if (rc < 0) {
nlmsg_free(rep_skb);
goto err;
Add cgroupstats This patch is inspired by the discussion at http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263. The patch is on top of 2.6.21-mm1 with Paul's cgroups v9 patches (forward ported) This patch implements per cgroup statistics infrastructure and re-uses code from the taskstats interface. A new set of cgroup operations are registered with commands and attributes. It should be very easy to *extend* per cgroup statistics, by adding members to the cgroupstats structure. The current model for cgroupstats is a pull, a push model (to post statistics on interesting events), should be very easy to add. Currently user space requests for statistics by passing the cgroup file descriptor. Statistics about the state of all the tasks in the cgroup is returned to user space. TODO's/NOTE: This patch provides an infrastructure for implementing cgroup statistics. Based on the needs of each controller, we can incrementally add more statistics, event based support for notification of statistics, accumulation of taskstats into cgroup statistics in the future. Sample output # ./cgroupstats -C /cgroup/a sleeping 2, blocked 0, running 1, stopped 0, uninterruptible 0 # ./cgroupstats -C /cgroup/ sleeping 154, blocked 0, running 0, stopped 0, uninterruptible 0 If the approach looks good, I'll enhance and post the user space utility for the same Feedback, comments, test results are always welcome! [akpm@linux-foundation.org: build fix] Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Jay Lan <jlan@engr.sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:44 +08:00
}
genetlink: make netns aware This makes generic netlink network namespace aware. No generic netlink families except for the controller family are made namespace aware, they need to be checked one by one and then set the family->netnsok member to true. A new function genlmsg_multicast_netns() is introduced to allow sending a multicast message in a given namespace, for example when it applies to an object that lives in that namespace, a new function genlmsg_multicast_allns() to send a message to all network namespaces (for objects that do not have an associated netns). The function genlmsg_multicast() is changed to multicast the message in just init_net, which is currently correct for all generic netlink families since they only work in init_net right now. Some will later want to work in all net namespaces because they do not care about the netns at all -- those will have to be converted to use one of the new functions genlmsg_multicast_allns() or genlmsg_multicast_netns() whenever they are made netns aware in some way. After this patch families can easily decide whether or not they should be available in all net namespaces. Many genl families us it for objects not related to networking and should therefore be available in all namespaces, but that will have to be done on a per family basis. Note that this doesn't touch on the checkpoint/restart problem where network namespaces could be used, genl families and multicast groups are numbered globally and I see no easy way of changing that, especially since it must be possible to multicast to all network namespaces for those families that do not care about netns. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-07-10 17:51:34 +08:00
rc = send_reply(rep_skb, info);
Add cgroupstats This patch is inspired by the discussion at http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263. The patch is on top of 2.6.21-mm1 with Paul's cgroups v9 patches (forward ported) This patch implements per cgroup statistics infrastructure and re-uses code from the taskstats interface. A new set of cgroup operations are registered with commands and attributes. It should be very easy to *extend* per cgroup statistics, by adding members to the cgroupstats structure. The current model for cgroupstats is a pull, a push model (to post statistics on interesting events), should be very easy to add. Currently user space requests for statistics by passing the cgroup file descriptor. Statistics about the state of all the tasks in the cgroup is returned to user space. TODO's/NOTE: This patch provides an infrastructure for implementing cgroup statistics. Based on the needs of each controller, we can incrementally add more statistics, event based support for notification of statistics, accumulation of taskstats into cgroup statistics in the future. Sample output # ./cgroupstats -C /cgroup/a sleeping 2, blocked 0, running 1, stopped 0, uninterruptible 0 # ./cgroupstats -C /cgroup/ sleeping 154, blocked 0, running 0, stopped 0, uninterruptible 0 If the approach looks good, I'll enhance and post the user space utility for the same Feedback, comments, test results are always welcome! [akpm@linux-foundation.org: build fix] Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Jay Lan <jlan@engr.sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:44 +08:00
err:
fput_light(file, fput_needed);
Add cgroupstats This patch is inspired by the discussion at http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263. The patch is on top of 2.6.21-mm1 with Paul's cgroups v9 patches (forward ported) This patch implements per cgroup statistics infrastructure and re-uses code from the taskstats interface. A new set of cgroup operations are registered with commands and attributes. It should be very easy to *extend* per cgroup statistics, by adding members to the cgroupstats structure. The current model for cgroupstats is a pull, a push model (to post statistics on interesting events), should be very easy to add. Currently user space requests for statistics by passing the cgroup file descriptor. Statistics about the state of all the tasks in the cgroup is returned to user space. TODO's/NOTE: This patch provides an infrastructure for implementing cgroup statistics. Based on the needs of each controller, we can incrementally add more statistics, event based support for notification of statistics, accumulation of taskstats into cgroup statistics in the future. Sample output # ./cgroupstats -C /cgroup/a sleeping 2, blocked 0, running 1, stopped 0, uninterruptible 0 # ./cgroupstats -C /cgroup/ sleeping 154, blocked 0, running 0, stopped 0, uninterruptible 0 If the approach looks good, I'll enhance and post the user space utility for the same Feedback, comments, test results are always welcome! [akpm@linux-foundation.org: build fix] Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Jay Lan <jlan@engr.sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:44 +08:00
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);
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]);
stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, pid);
if (!stats)
goto err;
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]);
stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tgid);
if (!stats)
goto err;
rc = fill_tgid(tgid, NULL, stats);
if (rc < 0)
goto err;
} else
goto err;
genetlink: make netns aware This makes generic netlink network namespace aware. No generic netlink families except for the controller family are made namespace aware, they need to be checked one by one and then set the family->netnsok member to true. A new function genlmsg_multicast_netns() is introduced to allow sending a multicast message in a given namespace, for example when it applies to an object that lives in that namespace, a new function genlmsg_multicast_allns() to send a message to all network namespaces (for objects that do not have an associated netns). The function genlmsg_multicast() is changed to multicast the message in just init_net, which is currently correct for all generic netlink families since they only work in init_net right now. Some will later want to work in all net namespaces because they do not care about the netns at all -- those will have to be converted to use one of the new functions genlmsg_multicast_allns() or genlmsg_multicast_netns() whenever they are made netns aware in some way. After this patch families can easily decide whether or not they should be available in all net namespaces. Many genl families us it for objects not related to networking and should therefore be available in all namespaces, but that will have to be done on a per family basis. Note that this doesn't touch on the checkpoint/restart problem where network namespaces could be used, genl families and multicast groups are numbered globally and I see no easy way of changing that, especially since it must be possible to multicast to all network namespaces for those families that do not care about netns. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-07-10 17:51:34 +08:00
return send_reply(rep_skb, info);
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(struct task_struct *tsk, int group_dead)
{
int rc;
struct listener_list *listeners;
struct taskstats *stats;
struct sk_buff *rep_skb;
size_t size;
int is_thread_group;
if (!family_registered)
return;
/*
* Size includes space for nested attributes
*/
size = nla_total_size(sizeof(u32)) +
nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
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);
}
listeners = &__raw_get_cpu_var(listener_array);
if (list_empty(&listeners->list))
return;
rc = prepare_reply(NULL, TASKSTATS_CMD_NEW, &rep_skb, size);
if (rc < 0)
return;
stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, tsk->pid);
if (!stats)
goto err;
rc = fill_pid(-1, tsk, stats);
if (rc < 0)
goto err;
/*
* Doesn't matter if tsk is the leader or the last group member leaving
*/
if (!is_thread_group || !group_dead)
goto send;
stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tsk->tgid);
if (!stats)
goto err;
memcpy(stats, tsk->signal->stats, sizeof(*stats));
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_user_cmd,
.policy = taskstats_cmd_get_policy,
};
Add cgroupstats This patch is inspired by the discussion at http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263. The patch is on top of 2.6.21-mm1 with Paul's cgroups v9 patches (forward ported) This patch implements per cgroup statistics infrastructure and re-uses code from the taskstats interface. A new set of cgroup operations are registered with commands and attributes. It should be very easy to *extend* per cgroup statistics, by adding members to the cgroupstats structure. The current model for cgroupstats is a pull, a push model (to post statistics on interesting events), should be very easy to add. Currently user space requests for statistics by passing the cgroup file descriptor. Statistics about the state of all the tasks in the cgroup is returned to user space. TODO's/NOTE: This patch provides an infrastructure for implementing cgroup statistics. Based on the needs of each controller, we can incrementally add more statistics, event based support for notification of statistics, accumulation of taskstats into cgroup statistics in the future. Sample output # ./cgroupstats -C /cgroup/a sleeping 2, blocked 0, running 1, stopped 0, uninterruptible 0 # ./cgroupstats -C /cgroup/ sleeping 154, blocked 0, running 0, stopped 0, uninterruptible 0 If the approach looks good, I'll enhance and post the user space utility for the same Feedback, comments, test results are always welcome! [akpm@linux-foundation.org: build fix] Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Jay Lan <jlan@engr.sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:44 +08:00
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)
{
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)
{
int rc;
rc = genl_register_family(&family);
if (rc)
return rc;
rc = genl_register_ops(&family, &taskstats_ops);
if (rc < 0)
goto err;
Add cgroupstats This patch is inspired by the discussion at http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263. The patch is on top of 2.6.21-mm1 with Paul's cgroups v9 patches (forward ported) This patch implements per cgroup statistics infrastructure and re-uses code from the taskstats interface. A new set of cgroup operations are registered with commands and attributes. It should be very easy to *extend* per cgroup statistics, by adding members to the cgroupstats structure. The current model for cgroupstats is a pull, a push model (to post statistics on interesting events), should be very easy to add. Currently user space requests for statistics by passing the cgroup file descriptor. Statistics about the state of all the tasks in the cgroup is returned to user space. TODO's/NOTE: This patch provides an infrastructure for implementing cgroup statistics. Based on the needs of each controller, we can incrementally add more statistics, event based support for notification of statistics, accumulation of taskstats into cgroup statistics in the future. Sample output # ./cgroupstats -C /cgroup/a sleeping 2, blocked 0, running 1, stopped 0, uninterruptible 0 # ./cgroupstats -C /cgroup/ sleeping 154, blocked 0, running 0, stopped 0, uninterruptible 0 If the approach looks good, I'll enhance and post the user space utility for the same Feedback, comments, test results are always welcome! [akpm@linux-foundation.org: build fix] Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Jay Lan <jlan@engr.sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:44 +08:00
rc = genl_register_ops(&family, &cgroupstats_ops);
if (rc < 0)
goto err_cgroup_ops;
family_registered = 1;
Add cgroupstats This patch is inspired by the discussion at http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263. The patch is on top of 2.6.21-mm1 with Paul's cgroups v9 patches (forward ported) This patch implements per cgroup statistics infrastructure and re-uses code from the taskstats interface. A new set of cgroup operations are registered with commands and attributes. It should be very easy to *extend* per cgroup statistics, by adding members to the cgroupstats structure. The current model for cgroupstats is a pull, a push model (to post statistics on interesting events), should be very easy to add. Currently user space requests for statistics by passing the cgroup file descriptor. Statistics about the state of all the tasks in the cgroup is returned to user space. TODO's/NOTE: This patch provides an infrastructure for implementing cgroup statistics. Based on the needs of each controller, we can incrementally add more statistics, event based support for notification of statistics, accumulation of taskstats into cgroup statistics in the future. Sample output # ./cgroupstats -C /cgroup/a sleeping 2, blocked 0, running 1, stopped 0, uninterruptible 0 # ./cgroupstats -C /cgroup/ sleeping 154, blocked 0, running 0, stopped 0, uninterruptible 0 If the approach looks good, I'll enhance and post the user space utility for the same Feedback, comments, test results are always welcome! [akpm@linux-foundation.org: build fix] Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Jay Lan <jlan@engr.sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:44 +08:00
printk("registered taskstats version %d\n", TASKSTATS_GENL_VERSION);
return 0;
Add cgroupstats This patch is inspired by the discussion at http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263. The patch is on top of 2.6.21-mm1 with Paul's cgroups v9 patches (forward ported) This patch implements per cgroup statistics infrastructure and re-uses code from the taskstats interface. A new set of cgroup operations are registered with commands and attributes. It should be very easy to *extend* per cgroup statistics, by adding members to the cgroupstats structure. The current model for cgroupstats is a pull, a push model (to post statistics on interesting events), should be very easy to add. Currently user space requests for statistics by passing the cgroup file descriptor. Statistics about the state of all the tasks in the cgroup is returned to user space. TODO's/NOTE: This patch provides an infrastructure for implementing cgroup statistics. Based on the needs of each controller, we can incrementally add more statistics, event based support for notification of statistics, accumulation of taskstats into cgroup statistics in the future. Sample output # ./cgroupstats -C /cgroup/a sleeping 2, blocked 0, running 1, stopped 0, uninterruptible 0 # ./cgroupstats -C /cgroup/ sleeping 154, blocked 0, running 0, stopped 0, uninterruptible 0 If the approach looks good, I'll enhance and post the user space utility for the same Feedback, comments, test results are always welcome! [akpm@linux-foundation.org: build fix] Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Jay Lan <jlan@engr.sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:44 +08:00
err_cgroup_ops:
genl_unregister_ops(&family, &taskstats_ops);
err:
genl_unregister_family(&family);
return rc;
}
/*
* late initcall ensures initialization of statistics collection
* mechanisms precedes initialization of the taskstats interface
*/
late_initcall(taskstats_init);