Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-24 21:21:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

fs/proc: do_task_stat: use sig->stats_lock to gather the threads/children stats

Browse Source 
lock_task_sighand() can trigger a hard lockup.  If NR_CPUS threads call
do_task_stat() at the same time and the process has NR_THREADS, it will
spin with irqs disabled O(NR_CPUS * NR_THREADS) time.

Change do_task_stat() to use sig->stats_lock to gather the statistics
outside of ->siglock protected section, in the likely case this code will
run lockless.

Link: https://lkml.kernel.org/r/20240123153357.GA21857@redhat.com
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Dylan Hatch <dylanbhatch@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Oleg Nesterov 2024-01-23 16:33:57 +01:00 committed by Andrew Morton
parent 60f92acb60
commit 7601df8031
1 changed files with 32 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
fs/proc/array.c
View File

@ -477,13 +477,13 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
int permitted; int permitted;
struct mm_struct *mm; struct mm_struct *mm;
unsigned long long start_time; unsigned long long start_time;
unsigned long cmin_flt = 0, cmaj_flt = 0; unsigned long cmin_flt, cmaj_flt, min_flt, maj_flt;
unsigned long min_flt = 0, maj_flt = 0; u64 cutime, cstime, cgtime, utime, stime, gtime;
u64 cutime, cstime, utime, stime;
u64 cgtime, gtime;
unsigned long rsslim = 0; unsigned long rsslim = 0;
unsigned long flags; unsigned long flags;
int exit_code = task->exit_code; int exit_code = task->exit_code;
struct signal_struct *sig = task->signal;
unsigned int seq = 1;
state = *get_task_state(task); state = *get_task_state(task);
vsize = eip = esp = 0; vsize = eip = esp = 0;
@ -511,12 +511,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
sigemptyset(&sigign); sigemptyset(&sigign);
sigemptyset(&sigcatch); sigemptyset(&sigcatch);
cutime = cstime = 0;
cgtime = gtime = 0;
if (lock_task_sighand(task, &flags)) { if (lock_task_sighand(task, &flags)) {
struct signal_struct *sig = task->signal;
if (sig->tty) { if (sig->tty) {
struct pid *pgrp = tty_get_pgrp(sig->tty); struct pid *pgrp = tty_get_pgrp(sig->tty);
tty_pgrp = pid_nr_ns(pgrp, ns); tty_pgrp = pid_nr_ns(pgrp, ns);
@ -527,27 +523,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
num_threads = get_nr_threads(task); num_threads = get_nr_threads(task);
collect_sigign_sigcatch(task, &sigign, &sigcatch); collect_sigign_sigcatch(task, &sigign, &sigcatch);
cmin_flt = sig->cmin_flt;
cmaj_flt = sig->cmaj_flt;
cutime = sig->cutime;
cstime = sig->cstime;
cgtime = sig->cgtime;
rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur); rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur);
/* add up live thread stats at the group level */
if (whole) { if (whole) {
struct task_struct *t;
__for_each_thread(sig, t) {
min_flt += t->min_flt;
maj_flt += t->maj_flt;
gtime += task_gtime(t);
}
min_flt += sig->min_flt;
maj_flt += sig->maj_flt;
gtime += sig->gtime;
if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED)) if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED))
exit_code = sig->group_exit_code; exit_code = sig->group_exit_code;
} }
@ -562,6 +540,34 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
if (permitted && (!whole || num_threads < 2)) if (permitted && (!whole || num_threads < 2))
wchan = !task_is_running(task); wchan = !task_is_running(task);
do {
seq++; /* 2 on the 1st/lockless path, otherwise odd */
flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
cmin_flt = sig->cmin_flt;
cmaj_flt = sig->cmaj_flt;
cutime = sig->cutime;
cstime = sig->cstime;
cgtime = sig->cgtime;
if (whole) {
struct task_struct *t;
min_flt = sig->min_flt;
maj_flt = sig->maj_flt;
gtime = sig->gtime;
rcu_read_lock();
__for_each_thread(sig, t) {
min_flt += t->min_flt;
maj_flt += t->maj_flt;
gtime += task_gtime(t);
}
rcu_read_unlock();
}
} while (need_seqretry(&sig->stats_lock, seq));
done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
if (whole) { if (whole) {
thread_group_cputime_adjusted(task, &utime, &stime); thread_group_cputime_adjusted(task, &utime, &stime);
} else { } else {