From: Oleg Nesterov oleg@redhat.com
[ Upstream commit 7601df8031fd67310af891897ef6cc0df4209305 ]
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 Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: David Sauerwein dssauerw@amazon.de --- fs/proc/array.c | 52 ++++++++++++++++++++++++++++--------------------- 1 file changed, 30 insertions(+), 22 deletions(-)
diff --git a/fs/proc/array.c b/fs/proc/array.c index 18a4588c35be..8fba6d39e776 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -443,12 +443,12 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, int permitted; struct mm_struct *mm; unsigned long long start_time; - unsigned long cmin_flt = 0, cmaj_flt = 0; - unsigned long min_flt = 0, maj_flt = 0; - u64 cutime, cstime, utime, stime; - u64 cgtime, gtime; + unsigned long cmin_flt, cmaj_flt, min_flt, maj_flt; + u64 cutime, cstime, cgtime, utime, stime, gtime; unsigned long rsslim = 0; unsigned long flags; + struct signal_struct *sig = task->signal; + unsigned int seq = 1;
state = *get_task_state(task); vsize = eip = esp = 0; @@ -476,12 +476,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
sigemptyset(&sigign); sigemptyset(&sigcatch); - cutime = cstime = utime = stime = 0; - cgtime = gtime = 0; + utime = stime = 0;
if (lock_task_sighand(task, &flags)) { - struct signal_struct *sig = task->signal; - if (sig->tty) { struct pid *pgrp = tty_get_pgrp(sig->tty); tty_pgrp = pid_nr_ns(pgrp, ns); @@ -492,37 +489,48 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, num_threads = get_nr_threads(task); collect_sigign_sigcatch(task, &sigign, &sigcatch);
+ rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur); + + sid = task_session_nr_ns(task, ns); + ppid = task_tgid_nr_ns(task->real_parent, ns); + pgid = task_pgrp_nr_ns(task, ns); + + unlock_task_sighand(task, &flags); + } + + if (permitted && (!whole || num_threads < 2)) + wchan = get_wchan(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; - rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur);
- /* add up live thread stats at the group level */ if (whole) { struct task_struct *t = task; + + min_flt = sig->min_flt; + maj_flt = sig->maj_flt; + gtime = sig->gtime; + + rcu_read_lock(); do { min_flt += t->min_flt; maj_flt += t->maj_flt; gtime += task_gtime(t); } while_each_thread(task, t); + rcu_read_unlock();
- min_flt += sig->min_flt; - maj_flt += sig->maj_flt; thread_group_cputime_adjusted(task, &utime, &stime); - gtime += sig->gtime; } + } while (need_seqretry(&sig->stats_lock, seq)); + done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
- sid = task_session_nr_ns(task, ns); - ppid = task_tgid_nr_ns(task->real_parent, ns); - pgid = task_pgrp_nr_ns(task, ns); - - unlock_task_sighand(task, &flags); - } - - if (permitted && (!whole || num_threads < 2)) - wchan = get_wchan(task); if (!whole) { min_flt = task->min_flt; maj_flt = task->maj_flt;