From c57bef0287dd5deeabaea5727950559fb9037cd9 Mon Sep 17 00:00:00 2001 From: Barret Rhoden Date: Thu, 6 Jan 2022 12:20:40 -0500 Subject: prlimit: make do_prlimit() static There are no other callers in the kernel. Fixed up a comment format and whitespace issue when moving do_prlimit() higher in sys.c. Signed-off-by: Barret Rhoden Link: https://lkml.kernel.org/r/20220106172041.522167-3-brho@google.com Signed-off-by: Eric W. Biederman --- kernel/sys.c | 116 ++++++++++++++++++++++++++++++----------------------------- 1 file changed, 59 insertions(+), 57 deletions(-) (limited to 'kernel') diff --git a/kernel/sys.c b/kernel/sys.c index 5b0e172c4d47..d37d1f882b7d 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1424,6 +1424,65 @@ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len) return errno; } +/* make sure you are allowed to change @tsk limits before calling this */ +static int do_prlimit(struct task_struct *tsk, unsigned int resource, + struct rlimit *new_rlim, struct rlimit *old_rlim) +{ + struct rlimit *rlim; + int retval = 0; + + if (resource >= RLIM_NLIMITS) + return -EINVAL; + if (new_rlim) { + if (new_rlim->rlim_cur > new_rlim->rlim_max) + return -EINVAL; + if (resource == RLIMIT_NOFILE && + new_rlim->rlim_max > sysctl_nr_open) + return -EPERM; + } + + /* protect tsk->signal and tsk->sighand from disappearing */ + read_lock(&tasklist_lock); + if (!tsk->sighand) { + retval = -ESRCH; + goto out; + } + + rlim = tsk->signal->rlim + resource; + task_lock(tsk->group_leader); + if (new_rlim) { + /* + * Keep the capable check against init_user_ns until cgroups can + * contain all limits. + */ + if (new_rlim->rlim_max > rlim->rlim_max && + !capable(CAP_SYS_RESOURCE)) + retval = -EPERM; + if (!retval) + retval = security_task_setrlimit(tsk, resource, new_rlim); + } + if (!retval) { + if (old_rlim) + *old_rlim = *rlim; + if (new_rlim) + *rlim = *new_rlim; + } + task_unlock(tsk->group_leader); + + /* + * RLIMIT_CPU handling. Arm the posix CPU timer if the limit is not + * infinite. In case of RLIM_INFINITY the posix CPU timer code + * ignores the rlimit. + */ + if (!retval && new_rlim && resource == RLIMIT_CPU && + new_rlim->rlim_cur != RLIM_INFINITY && + IS_ENABLED(CONFIG_POSIX_TIMERS)) + update_rlimit_cpu(tsk, new_rlim->rlim_cur); +out: + read_unlock(&tasklist_lock); + return retval; +} + SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim) { struct rlimit value; @@ -1567,63 +1626,6 @@ static void rlim64_to_rlim(const struct rlimit64 *rlim64, struct rlimit *rlim) rlim->rlim_max = (unsigned long)rlim64->rlim_max; } -/* make sure you are allowed to change @tsk limits before calling this */ -int do_prlimit(struct task_struct *tsk, unsigned int resource, - struct rlimit *new_rlim, struct rlimit *old_rlim) -{ - struct rlimit *rlim; - int retval = 0; - - if (resource >= RLIM_NLIMITS) - return -EINVAL; - if (new_rlim) { - if (new_rlim->rlim_cur > new_rlim->rlim_max) - return -EINVAL; - if (resource == RLIMIT_NOFILE && - new_rlim->rlim_max > sysctl_nr_open) - return -EPERM; - } - - /* protect tsk->signal and tsk->sighand from disappearing */ - read_lock(&tasklist_lock); - if (!tsk->sighand) { - retval = -ESRCH; - goto out; - } - - rlim = tsk->signal->rlim + resource; - task_lock(tsk->group_leader); - if (new_rlim) { - /* Keep the capable check against init_user_ns until - cgroups can contain all limits */ - if (new_rlim->rlim_max > rlim->rlim_max && - !capable(CAP_SYS_RESOURCE)) - retval = -EPERM; - if (!retval) - retval = security_task_setrlimit(tsk, resource, new_rlim); - } - if (!retval) { - if (old_rlim) - *old_rlim = *rlim; - if (new_rlim) - *rlim = *new_rlim; - } - task_unlock(tsk->group_leader); - - /* - * RLIMIT_CPU handling. Arm the posix CPU timer if the limit is not - * infinite. In case of RLIM_INFINITY the posix CPU timer code - * ignores the rlimit. - */ - if (!retval && new_rlim && resource == RLIMIT_CPU && - new_rlim->rlim_cur != RLIM_INFINITY && - IS_ENABLED(CONFIG_POSIX_TIMERS)) - update_rlimit_cpu(tsk, new_rlim->rlim_cur); -out: - read_unlock(&tasklist_lock); - return retval; -} - /* rcu lock must be held */ static int check_prlimit_permission(struct task_struct *task, unsigned int flags) -- cgit v1.2.3 From 18c91bb2d87268d23868bf13508f5bc9cf04e89a Mon Sep 17 00:00:00 2001 From: Barret Rhoden Date: Thu, 6 Jan 2022 12:20:41 -0500 Subject: prlimit: do not grab the tasklist_lock Unnecessarily grabbing the tasklist_lock can be a scalability bottleneck for workloads that also must grab the tasklist_lock for waiting, killing, and cloning. The tasklist_lock was grabbed to protect tsk->sighand from disappearing (becoming NULL). tsk->signal was already protected by holding a reference to tsk. update_rlimit_cpu() assumed tsk->sighand != NULL. With this commit, it attempts to lock_task_sighand(). However, this means that update_rlimit_cpu() can fail. This only happens when a task is exiting. Note that during exec, sighand may *change*, but it will not be NULL. Prior to this commit, the do_prlimit() ensured that update_rlimit_cpu() would not fail by read locking the tasklist_lock and checking tsk->sighand != NULL. If update_rlimit_cpu() fails, there may be other tasks that are not exiting that share tsk->signal. However, the group_leader is the last task to be released, so if we cannot update_rlimit_cpu(group_leader), then the entire process is exiting. The only other caller of update_rlimit_cpu() is selinux_bprm_committing_creds(). It has tsk == current, so update_rlimit_cpu() cannot fail (current->sighand cannot disappear until current exits). This change resulted in a 14% speedup on a microbenchmark where parents kill and wait on their children, and children getpriority, setpriority, and getrlimit. Signed-off-by: Barret Rhoden Link: https://lkml.kernel.org/r/20220106172041.522167-4-brho@google.com Signed-off-by: Eric W. Biederman --- include/linux/posix-timers.h | 2 +- kernel/sys.c | 25 ++++++++++++++----------- kernel/time/posix-cpu-timers.c | 12 +++++++++--- 3 files changed, 24 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 5bbcd280bfd2..9cf126c3b27f 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -253,7 +253,7 @@ void posix_cpu_timers_exit_group(struct task_struct *task); void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, u64 *newval, u64 *oldval); -void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); +int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); void posixtimer_rearm(struct kernel_siginfo *info); #endif diff --git a/kernel/sys.c b/kernel/sys.c index d37d1f882b7d..374f83e95239 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1441,13 +1441,7 @@ static int do_prlimit(struct task_struct *tsk, unsigned int resource, return -EPERM; } - /* protect tsk->signal and tsk->sighand from disappearing */ - read_lock(&tasklist_lock); - if (!tsk->sighand) { - retval = -ESRCH; - goto out; - } - + /* Holding a refcount on tsk protects tsk->signal from disappearing. */ rlim = tsk->signal->rlim + resource; task_lock(tsk->group_leader); if (new_rlim) { @@ -1476,10 +1470,19 @@ static int do_prlimit(struct task_struct *tsk, unsigned int resource, */ if (!retval && new_rlim && resource == RLIMIT_CPU && new_rlim->rlim_cur != RLIM_INFINITY && - IS_ENABLED(CONFIG_POSIX_TIMERS)) - update_rlimit_cpu(tsk, new_rlim->rlim_cur); -out: - read_unlock(&tasklist_lock); + IS_ENABLED(CONFIG_POSIX_TIMERS)) { + /* + * update_rlimit_cpu can fail if the task is exiting, but there + * may be other tasks in the thread group that are not exiting, + * and they need their cpu timers adjusted. + * + * The group_leader is the last task to be released, so if we + * cannot update_rlimit_cpu on it, then the entire process is + * exiting and we do not need to update at all. + */ + update_rlimit_cpu(tsk->group_leader, new_rlim->rlim_cur); + } + return retval; } diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 96b4e7810426..e13e628509fb 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -34,14 +34,20 @@ void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) * tsk->signal->posix_cputimers.bases[clock].nextevt expiration cache if * necessary. Needs siglock protection since other code may update the * expiration cache as well. + * + * Returns 0 on success, -ESRCH on failure. Can fail if the task is exiting and + * we cannot lock_task_sighand. Cannot fail if task is current. */ -void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new) +int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new) { u64 nsecs = rlim_new * NSEC_PER_SEC; + unsigned long irq_fl; - spin_lock_irq(&task->sighand->siglock); + if (!lock_task_sighand(task, &irq_fl)) + return -ESRCH; set_process_cpu_timer(task, CPUCLOCK_PROF, &nsecs, NULL); - spin_unlock_irq(&task->sighand->siglock); + unlock_task_sighand(task, &irq_fl); + return 0; } /* -- cgit v1.2.3