aboutsummaryrefslogtreecommitdiff
path: root/kernel/taskstats.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/taskstats.c')
-rw-r--r--kernel/taskstats.c174
1 files changed, 111 insertions, 63 deletions
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index c8231fb1570..13d2f7cd65d 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -27,8 +27,9 @@
#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
@@ -89,8 +90,7 @@ static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp,
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, 0, cmd);
} else
@@ -175,7 +175,9 @@ static void send_cpu_listeners(struct sk_buff *skb,
up_write(&listeners->sem);
}
-static void fill_stats(struct task_struct *tsk, struct taskstats *stats)
+static void fill_stats(struct user_namespace *user_ns,
+ struct pid_namespace *pid_ns,
+ struct task_struct *tsk, struct taskstats *stats)
{
memset(stats, 0, sizeof(*stats));
/*
@@ -191,7 +193,7 @@ static void fill_stats(struct task_struct *tsk, struct taskstats *stats)
stats->version = TASKSTATS_VERSION;
stats->nvcsw = tsk->nvcsw;
stats->nivcsw = tsk->nivcsw;
- bacct_add_tsk(stats, tsk);
+ bacct_add_tsk(user_ns, pid_ns, stats, tsk);
/* fill in extended acct fields */
xacct_add_tsk(stats, tsk);
@@ -208,7 +210,7 @@ static int fill_stats_for_pid(pid_t pid, struct taskstats *stats)
rcu_read_unlock();
if (!tsk)
return -ESRCH;
- fill_stats(tsk, stats);
+ fill_stats(current_user_ns(), task_active_pid_ns(current), tsk, stats);
put_task_struct(tsk);
return 0;
}
@@ -286,26 +288,41 @@ ret:
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;
+ int ret = 0;
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(cpu, mask) {
- s = kmalloc_node(sizeof(struct listener), GFP_KERNEL,
- cpu_to_node(cpu));
- if (!s)
+ 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;
}
@@ -324,7 +341,7 @@ cleanup:
}
up_write(&listeners->sem);
}
- return 0;
+ return ret;
}
static int parse(struct nlattr *na, struct cpumask *mask)
@@ -349,29 +366,55 @@ static int parse(struct nlattr *na, struct cpumask *mask)
return ret;
}
+#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;
- /* If we don't pad, we end up with alignment on a 4 byte boundary.
- * This causes lots of runtime warnings on systems requiring 8 byte
- * alignment */
- u32 pids[2] = { pid, 0 };
- int pid_size = ALIGN(sizeof(pid), sizeof(long));
-
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, pid_size, pids) < 0)
+
+ 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)
+ if (!ret) {
+ nla_nest_cancel(skb, na);
goto err;
+ }
nla_nest_end(skb, na);
return nla_data(ret);
@@ -387,16 +430,15 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
struct nlattr *na;
size_t size;
u32 fd;
- struct file *file;
- int fput_needed;
+ struct fd f;
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)
+ f = fdget(fd);
+ if (!f.file)
return 0;
size = nla_total_size(sizeof(struct cgroupstats));
@@ -408,10 +450,16 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
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, file->f_dentry);
+ rc = cgroupstats_build(stats, f.file->f_dentry);
if (rc < 0) {
nlmsg_free(rep_skb);
goto err;
@@ -420,7 +468,7 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
rc = send_reply(rep_skb, info);
err:
- fput_light(file, fput_needed);
+ fdput(f);
return rc;
}
@@ -434,7 +482,7 @@ static int cmd_attr_register_cpumask(struct genl_info *info)
rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask);
if (rc < 0)
goto out;
- rc = add_del_listener(info->snd_pid, mask, REGISTER);
+ rc = add_del_listener(info->snd_portid, mask, REGISTER);
out:
free_cpumask_var(mask);
return rc;
@@ -450,12 +498,24 @@ static int cmd_attr_deregister_cpumask(struct genl_info *info)
rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask);
if (rc < 0)
goto out;
- rc = add_del_listener(info->snd_pid, mask, DEREGISTER);
+ 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 = 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;
@@ -464,8 +524,7 @@ static int cmd_attr_pid(struct genl_info *info)
u32 pid;
int rc;
- size = nla_total_size(sizeof(u32)) +
- nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+ size = taskstats_packet_size();
rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size);
if (rc < 0)
@@ -494,8 +553,7 @@ static int cmd_attr_tgid(struct genl_info *info)
u32 tgid;
int rc;
- size = nla_total_size(sizeof(u32)) +
- nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+ size = taskstats_packet_size();
rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size);
if (rc < 0)
@@ -570,8 +628,7 @@ void taskstats_exit(struct task_struct *tsk, int group_dead)
/*
* Size includes space for nested attributes
*/
- size = nla_total_size(sizeof(u32)) +
- nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+ size = taskstats_packet_size();
is_thread_group = !!taskstats_tgid_alloc(tsk);
if (is_thread_group) {
@@ -581,7 +638,7 @@ void taskstats_exit(struct task_struct *tsk, int group_dead)
fill_tgid_exit(tsk);
}
- listeners = &__raw_get_cpu_var(listener_array);
+ listeners = __this_cpu_ptr(&listener_array);
if (list_empty(&listeners->list))
return;
@@ -589,11 +646,12 @@ void taskstats_exit(struct task_struct *tsk, int group_dead)
if (rc < 0)
return;
- stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, tsk->pid);
+ stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID,
+ task_pid_nr_ns(tsk, &init_pid_ns));
if (!stats)
goto err;
- fill_stats(tsk, stats);
+ fill_stats(&init_user_ns, &init_pid_ns, tsk, stats);
/*
* Doesn't matter if tsk is the leader or the last group member leaving
@@ -601,7 +659,8 @@ void taskstats_exit(struct task_struct *tsk, int group_dead)
if (!is_thread_group || !group_dead)
goto send;
- stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tsk->tgid);
+ stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID,
+ task_tgid_nr_ns(tsk, &init_pid_ns));
if (!stats)
goto err;
@@ -614,16 +673,18 @@ err:
nlmsg_free(rep_skb);
}
-static struct genl_ops taskstats_ops = {
- .cmd = TASKSTATS_CMD_GET,
- .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,
+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 */
@@ -642,26 +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;
-
- 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);
+ pr_info("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;
}
/*
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-12-06 15:57:01 +0000