diff options
Diffstat (limited to 'kernel/taskstats.c')
| -rw-r--r-- | kernel/taskstats.c | 575 |
1 files changed, 365 insertions, 210 deletions
diff --git a/kernel/taskstats.c b/kernel/taskstats.c index e7818765733..13d2f7cd65d 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -18,11 +18,18 @@ #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/slab.h> +#include <linux/cgroupstats.h> +#include <linux/cgroup.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/pid_namespace.h> #include <net/genetlink.h> -#include <asm/atomic.h> +#include <linux/atomic.h> /* * Maximum length of a cpumask that can be specified in @@ -30,9 +37,9 @@ */ #define TASKSTATS_CPUMASK_MAXLEN (100+6*NR_CPUS) -static DEFINE_PER_CPU(__u32, taskstats_seqnum) = { 0 }; +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, @@ -41,13 +48,16 @@ static struct genl_family family = { .maxattr = TASKSTATS_CMD_ATTR_MAX, }; -static struct nla_policy taskstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1] -__read_mostly = { +static const struct nla_policy taskstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1] = { [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 const struct nla_policy cgroupstats_cmd_get_policy[CGROUPSTATS_CMD_ATTR_MAX+1] = { + [CGROUPSTATS_CMD_ATTR_FD] = { .type = NLA_U32 }, +}; + struct listener { struct list_head list; pid_t pid; @@ -67,7 +77,7 @@ enum actions { }; 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; @@ -75,37 +85,31 @@ static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp, /* * If new attributes are added, please revisit this allocation */ - skb = nlmsg_new(size); + skb = genlmsg_new(size, GFP_KERNEL); if (!skb) return -ENOMEM; if (!info) { - int seq = get_cpu_var(taskstats_seqnum)++; - put_cpu_var(taskstats_seqnum); + int seq = this_cpu_inc_return(taskstats_seqnum) - 1; - 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; } /* * Send taskstats data in @skb to listener with nl_pid @pid */ -static int send_reply(struct sk_buff *skb, pid_t pid) +static int send_reply(struct sk_buff *skb, struct genl_info *info) { - struct genlmsghdr *genlhdr = nlmsg_data((struct nlmsghdr *)skb->data); + struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); void *reply = genlmsg_data(genlhdr); int rc; @@ -115,16 +119,16 @@ static int send_reply(struct sk_buff *skb, pid_t pid) return rc; } - return genlmsg_unicast(skb, pid); + 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, unsigned int cpu) +static void send_cpu_listeners(struct sk_buff *skb, + struct listener_list *listeners) { - struct genlmsghdr *genlhdr = nlmsg_data((struct nlmsghdr *)skb->data); - 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); @@ -137,7 +141,6 @@ static void send_cpu_listeners(struct sk_buff *skb, unsigned int cpu) } rc = 0; - listeners = &per_cpu(listener_array, cpu); down_read(&listeners->sem); list_for_each_entry(s, &listeners->list, list) { skb_next = NULL; @@ -146,7 +149,7 @@ static void send_cpu_listeners(struct sk_buff *skb, unsigned int cpu) if (!skb_next) break; } - rc = genlmsg_unicast(skb_cur, s->pid); + rc = genlmsg_unicast(&init_net, skb_cur, s->pid); if (rc == -ECONNREFUSED) { s->valid = 0; delcount++; @@ -172,24 +175,11 @@ static void send_cpu_listeners(struct sk_buff *skb, unsigned int cpu) up_write(&listeners->sem); } -static int fill_pid(pid_t pid, struct task_struct *pidtsk, - struct taskstats *stats) +static void fill_stats(struct user_namespace *user_ns, + struct pid_namespace *pid_ns, + struct task_struct *tsk, struct taskstats *stats) { - int rc = 0; - struct task_struct *tsk = pidtsk; - - if (!pidtsk) { - read_lock(&tasklist_lock); - tsk = find_task_by_pid(pid); - if (!tsk) { - read_unlock(&tasklist_lock); - 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 @@ -198,47 +188,57 @@ static int fill_pid(pid_t pid, struct task_struct *pidtsk, */ 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(user_ns, pid_ns, stats, tsk); - /* Define err: label here if needed */ - put_task_struct(tsk); - return rc; + /* fill in extended acct fields */ + xacct_add_tsk(stats, tsk); +} + +static int fill_stats_for_pid(pid_t pid, struct taskstats *stats) +{ + struct task_struct *tsk; + rcu_read_lock(); + tsk = find_task_by_vpid(pid); + if (tsk) + get_task_struct(tsk); + rcu_read_unlock(); + if (!tsk) + return -ESRCH; + fill_stats(current_user_ns(), task_active_pid_ns(current), tsk, stats); + put_task_struct(tsk); + return 0; } -static int fill_tgid(pid_t tgid, struct task_struct *tgidtsk, - struct taskstats *stats) +static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats) { struct task_struct *tsk, *first; 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 */ - first = tgidtsk; - if (!first) { - read_lock(&tasklist_lock); - first = find_task_by_pid(tgid); - if (!first) { - read_unlock(&tasklist_lock); - return -ESRCH; - } - get_task_struct(first); - read_unlock(&tasklist_lock); - } else - get_task_struct(first); + rcu_read_lock(); + first = find_task_by_vpid(tgid); + + if (!first || !lock_task_sighand(first, &flags)) + goto out; - /* Start with stats from dead tasks */ - spin_lock_irqsave(&first->signal->stats_lock, flags); if (first->signal->stats) memcpy(stats, first->signal->stats, sizeof(*stats)); - spin_unlock_irqrestore(&first->signal->stats_lock, flags); + else + memset(stats, 0, sizeof(*stats)); tsk = first; - read_lock(&tasklist_lock); do { - if (tsk->exit_state == EXIT_ZOMBIE && thread_group_leader(tsk)) + if (tsk->exit_state) continue; /* * Accounting subsystem can call its functions here to @@ -248,24 +248,28 @@ static int fill_tgid(pid_t tgid, struct task_struct *tgidtsk, */ delayacct_add_tsk(stats, tsk); + stats->nvcsw += tsk->nvcsw; + stats->nivcsw += tsk->nivcsw; } while_each_thread(first, tsk); - read_unlock(&tasklist_lock); - stats->version = TASKSTATS_VERSION; + unlock_task_sighand(first, &flags); + rc = 0; +out: + rcu_read_unlock(); + + stats->version = TASKSTATS_VERSION; /* - * Accounting subsytems can also add calls here to modify + * Accounting subsystems can also add calls here to modify * fields of taskstats. */ - - return 0; + return rc; } - static void fill_tgid_exit(struct task_struct *tsk) { unsigned long flags; - spin_lock_irqsave(&tsk->signal->stats_lock, flags); + spin_lock_irqsave(&tsk->sighand->siglock, flags); if (!tsk->signal->stats) goto ret; @@ -277,41 +281,55 @@ static void fill_tgid_exit(struct task_struct *tsk) */ delayacct_add_tsk(tsk->signal->stats, tsk); ret: - spin_unlock_irqrestore(&tsk->signal->stats_lock, flags); + spin_unlock_irqrestore(&tsk->sighand->siglock, flags); return; } -static int add_del_listener(pid_t pid, cpumask_t *maskp, int isadd) +static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd) { struct listener_list *listeners; - struct listener *s, *tmp; + struct listener *s, *tmp, *s2; unsigned int cpu; - cpumask_t mask = *maskp; + int ret = 0; - if (!cpus_subset(mask, cpu_possible_map)) + if (!cpumask_subset(mask, cpu_possible_mask)) + return -EINVAL; + + if (current_user_ns() != &init_user_ns) + return -EINVAL; + + if (task_active_pid_ns(current) != &init_pid_ns) return -EINVAL; if (isadd == REGISTER) { - for_each_cpu_mask(cpu, mask) { - s = kmalloc_node(sizeof(struct listener), GFP_KERNEL, - cpu_to_node(cpu)); - if (!s) + for_each_cpu(cpu, mask) { + s = kmalloc_node(sizeof(struct listener), + GFP_KERNEL, cpu_to_node(cpu)); + if (!s) { + ret = -ENOMEM; goto cleanup; + } s->pid = pid; - INIT_LIST_HEAD(&s->list); s->valid = 1; listeners = &per_cpu(listener_array, cpu); down_write(&listeners->sem); + list_for_each_entry(s2, &listeners->list, list) { + if (s2->pid == pid && s2->valid) + goto exists; + } list_add(&s->list, &listeners->list); + s = NULL; +exists: up_write(&listeners->sem); + kfree(s); /* nop if NULL */ } return 0; } /* Deregister or cleanup */ cleanup: - for_each_cpu_mask(cpu, mask) { + 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) { @@ -323,10 +341,10 @@ cleanup: } up_write(&listeners->sem); } - return 0; + return ret; } -static int parse(struct nlattr *na, cpumask_t *mask) +static int parse(struct nlattr *na, struct cpumask *mask) { char *data; int len; @@ -343,185 +361,330 @@ static int parse(struct nlattr *na, cpumask_t *mask) if (!data) return -ENOMEM; nla_strlcpy(data, na, len); - ret = cpulist_parse(data, *mask); + ret = cpulist_parse(data, mask); kfree(data); return ret; } -static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info) +#if defined(CONFIG_64BIT) && !defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) +#define TASKSTATS_NEEDS_PADDING 1 +#endif + +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; + + /* + * The taskstats structure is internally aligned on 8 byte + * boundaries but the layout of the aggregrate reply, with + * two NLA headers and the pid (each 4 bytes), actually + * force the entire structure to be unaligned. This causes + * the kernel to issue unaligned access warnings on some + * architectures like ia64. Unfortunately, some software out there + * doesn't properly unroll the NLA packet and assumes that the start + * of the taskstats structure will always be 20 bytes from the start + * of the netlink payload. Aligning the start of the taskstats + * structure breaks this software, which we don't want. So, for now + * the alignment only happens on architectures that require it + * and those users will have to update to fixed versions of those + * packages. Space is reserved in the packet only when needed. + * This ifdef should be removed in several years e.g. 2012 once + * we can be confident that fixed versions are installed on most + * systems. We add the padding before the aggregate since the + * aggregate is already a defined type. + */ +#ifdef TASKSTATS_NEEDS_PADDING + if (nla_put(skb, TASKSTATS_TYPE_NULL, 0, NULL) < 0) + goto err; +#endif + na = nla_nest_start(skb, aggr); + if (!na) + goto err; + + if (nla_put(skb, type, sizeof(pid), &pid) < 0) { + nla_nest_cancel(skb, na); + goto err; + } + ret = nla_reserve(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats)); + if (!ret) { + nla_nest_cancel(skb, na); + 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; - cpumask_t mask; + size_t size; + u32 fd; + struct fd f; + + na = info->attrs[CGROUPSTATS_CMD_ATTR_FD]; + if (!na) + return -EINVAL; + + fd = nla_get_u32(info->attrs[CGROUPSTATS_CMD_ATTR_FD]); + f = fdget(fd); + if (!f.file) + return 0; + + size = nla_total_size(sizeof(struct cgroupstats)); - rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], &mask); + rc = prepare_reply(info, CGROUPSTATS_CMD_NEW, &rep_skb, + size); if (rc < 0) - return rc; - if (rc == 0) - return add_del_listener(info->snd_pid, &mask, REGISTER); + goto err; + + na = nla_reserve(rep_skb, CGROUPSTATS_TYPE_CGROUP_STATS, + sizeof(struct cgroupstats)); + if (na == NULL) { + nlmsg_free(rep_skb); + rc = -EMSGSIZE; + goto err; + } + + stats = nla_data(na); + memset(stats, 0, sizeof(*stats)); + + rc = cgroupstats_build(stats, f.file->f_dentry); + if (rc < 0) { + nlmsg_free(rep_skb); + goto err; + } + + rc = send_reply(rep_skb, info); - rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], &mask); +err: + fdput(f); + return rc; +} + +static int cmd_attr_register_cpumask(struct genl_info *info) +{ + cpumask_var_t mask; + int rc; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask); if (rc < 0) - return rc; - if (rc == 0) - return add_del_listener(info->snd_pid, &mask, DEREGISTER); + goto out; + rc = add_del_listener(info->snd_portid, mask, REGISTER); +out: + free_cpumask_var(mask); + return rc; +} + +static int cmd_attr_deregister_cpumask(struct genl_info *info) +{ + cpumask_var_t mask; + int rc; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask); + if (rc < 0) + goto out; + rc = add_del_listener(info->snd_portid, mask, DEREGISTER); +out: + free_cpumask_var(mask); + return rc; +} + +static size_t taskstats_packet_size(void) +{ + size_t size; - /* - * Size includes space for nested attributes - */ size = nla_total_size(sizeof(u32)) + nla_total_size(sizeof(struct taskstats)) + nla_total_size(0); +#ifdef TASKSTATS_NEEDS_PADDING + size += nla_total_size(0); /* Padding for alignment */ +#endif + return size; +} + +static int cmd_attr_pid(struct genl_info *info) +{ + struct taskstats *stats; + struct sk_buff *rep_skb; + size_t size; + u32 pid; + int rc; - memset(&stats, 0, sizeof(stats)); - rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, &reply, size); + size = taskstats_packet_size(); + + rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) return rc; - 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) - 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); - } 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) - 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 = -EINVAL; + pid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_PID]); + stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, pid); + if (!stats) goto err; - } - nla_nest_end(rep_skb, na); + rc = fill_stats_for_pid(pid, stats); + if (rc < 0) + goto err; + return send_reply(rep_skb, info); +err: + nlmsg_free(rep_skb); + return rc; +} - return send_reply(rep_skb, info->snd_pid); +static int cmd_attr_tgid(struct genl_info *info) +{ + struct taskstats *stats; + struct sk_buff *rep_skb; + size_t size; + u32 tgid; + int rc; + + size = taskstats_packet_size(); + + rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); + if (rc < 0) + return rc; -nla_put_failure: - return genlmsg_cancel(rep_skb, reply); + rc = -EINVAL; + 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_stats_for_tgid(tgid, stats); + if (rc < 0) + goto err; + return send_reply(rep_skb, info); err: nlmsg_free(rep_skb); return rc; } -void taskstats_exit_alloc(struct taskstats **ptidstats, unsigned int *mycpu) +static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info) +{ + if (info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK]) + return cmd_attr_register_cpumask(info); + else if (info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK]) + return cmd_attr_deregister_cpumask(info); + else if (info->attrs[TASKSTATS_CMD_ATTR_PID]) + return cmd_attr_pid(info); + else if (info->attrs[TASKSTATS_CMD_ATTR_TGID]) + return cmd_attr_tgid(info); + else + return -EINVAL; +} + +static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk) { - struct listener_list *listeners; - struct taskstats *tmp; - /* - * This is the cpu on which the task is exiting currently and will - * be the one for which the exit event is sent, even if the cpu - * on which this function is running changes later. - */ - *mycpu = raw_smp_processor_id(); + struct signal_struct *sig = tsk->signal; + struct taskstats *stats; - *ptidstats = NULL; - tmp = kmem_cache_zalloc(taskstats_cache, SLAB_KERNEL); - if (!tmp) - return; + if (sig->stats || thread_group_empty(tsk)) + goto ret; - listeners = &per_cpu(listener_array, *mycpu); - down_read(&listeners->sem); - if (!list_empty(&listeners->list)) { - *ptidstats = tmp; - tmp = NULL; + /* 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; } - up_read(&listeners->sem); - kfree(tmp); + 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, - int group_dead, unsigned int mycpu) +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; - unsigned long flags; - if (!family_registered || !tidstats) + if (!family_registered) return; - spin_lock_irqsave(&tsk->signal->stats_lock, flags); - is_thread_group = tsk->signal->stats ? 1 : 0; - spin_unlock_irqrestore(&tsk->signal->stats_lock, flags); - - 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 */ + size = taskstats_packet_size(); + + 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 = __this_cpu_ptr(&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, + task_pid_nr_ns(tsk, &init_pid_ns)); + if (!stats) + goto err; - if (!is_thread_group) - goto send; + fill_stats(&init_user_ns, &init_pid_ns, tsk, stats); /* - * tsk has/had a thread group so fill the tsk->signal->stats structure * Doesn't matter if tsk is the leader or the last group member leaving */ - - fill_tgid_exit(tsk); - if (!group_dead) + 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); - /* No locking needed for tsk->signal->stats since group is dead */ - NLA_PUT_TYPE(rep_skb, struct taskstats, TASKSTATS_TYPE_STATS, - *tsk->signal->stats); - nla_nest_end(rep_skb, na); + stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, + task_tgid_nr_ns(tsk, &init_pid_ns)); + if (!stats) + goto err; + + memcpy(stats, tsk->signal->stats, sizeof(*stats)); send: - send_cpu_listeners(rep_skb, mycpu); + send_cpu_listeners(rep_skb, listeners); return; - -nla_put_failure: - genlmsg_cancel(rep_skb, reply); - goto ret; -err_skb: +err: nlmsg_free(rep_skb); -ret: - return; } -static struct genl_ops taskstats_ops = { - .cmd = TASKSTATS_CMD_GET, - .doit = taskstats_user_cmd, - .policy = taskstats_cmd_get_policy, +static const struct genl_ops taskstats_ops[] = { + { + .cmd = TASKSTATS_CMD_GET, + .doit = taskstats_user_cmd, + .policy = taskstats_cmd_get_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = CGROUPSTATS_CMD_GET, + .doit = cgroupstats_user_cmd, + .policy = cgroupstats_cmd_get_policy, + }, }; /* Needed early in initialization */ @@ -529,9 +692,7 @@ void __init taskstats_init_early(void) { unsigned int i; - taskstats_cache = kmem_cache_create("taskstats_cache", - sizeof(struct taskstats), - 0, SLAB_PANIC, NULL, NULL); + 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)); @@ -542,19 +703,13 @@ static int __init taskstats_init(void) { int rc; - rc = genl_register_family(&family); + rc = genl_register_family_with_ops(&family, taskstats_ops); if (rc) return rc; - rc = genl_register_ops(&family, &taskstats_ops); - if (rc < 0) - goto err; - family_registered = 1; + pr_info("registered taskstats version %d\n", TASKSTATS_GENL_VERSION); return 0; -err: - genl_unregister_family(&family); - return rc; } /* |