The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable@xxxxxxxxxxxxxxx>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 7601df8031fd67310af891897ef6cc0df4209305 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable@xxxxxxxxxxxxxxx>' --in-reply-to '2024021918-unmanaged-rarity-ec6e@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: 7601df8031fd ("fs/proc: do_task_stat: use sig->stats_lock to gather the threads/children stats") 60f92acb60a9 ("fs/proc: do_task_stat: move thread_group_cputime_adjusted() outside of lock_task_sighand()") 7904e53ed5a2 ("fs/proc: do_task_stat: use __for_each_thread()") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 7601df8031fd67310af891897ef6cc0df4209305 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov <oleg@xxxxxxxxxx> Date: Tue, 23 Jan 2024 16:33:57 +0100 Subject: [PATCH] fs/proc: do_task_stat: use sig->stats_lock to gather the threads/children stats 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@xxxxxxxxxx Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx> Signed-off-by: Dylan Hatch <dylanbhatch@xxxxxxxxxx> Cc: Eric W. Biederman <ebiederm@xxxxxxxxxxxx> Cc: <stable@xxxxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> diff --git a/fs/proc/array.c b/fs/proc/array.c index 45ba91863808..34a47fb0c57f 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -477,13 +477,13 @@ 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; int exit_code = task->exit_code; + struct signal_struct *sig = task->signal; + unsigned int seq = 1; state = *get_task_state(task); vsize = eip = esp = 0; @@ -511,12 +511,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, sigemptyset(&sigign); sigemptyset(&sigcatch); - cutime = cstime = 0; - cgtime = gtime = 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); @@ -527,27 +523,9 @@ 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); - 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; - - __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)) 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)) 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) { thread_group_cputime_adjusted(task, &utime, &stime); } else {
