aboutsummaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/exit.c11
-rw-r--r--kernel/time/clocksource.c9
-rw-r--r--kernel/time/hrtimer.c2
-rw-r--r--kernel/time/namespace.c7
-rw-r--r--kernel/time/posix-cpu-timers.c148
-rw-r--r--kernel/time/posix-timers.c3
-rw-r--r--kernel/time/sched_clock.c9
-rw-r--r--kernel/time/timekeeping.c3
-rw-r--r--kernel/time/timer.c16
-rw-r--r--kernel/time/vsyscall.c12
10 files changed, 109 insertions, 111 deletions
diff --git a/kernel/exit.c b/kernel/exit.c
index 764960fabfa1..d70d47159640 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -103,17 +103,8 @@ static void __exit_signal(struct task_struct *tsk)
#ifdef CONFIG_POSIX_TIMERS
posix_cpu_timers_exit(tsk);
- if (group_dead) {
+ if (group_dead)
posix_cpu_timers_exit_group(tsk);
- } else {
- /*
- * This can only happen if the caller is de_thread().
- * FIXME: this is the temporary hack, we should teach
- * posix-cpu-timers to handle this case correctly.
- */
- if (unlikely(has_group_leader_pid(tsk)))
- posix_cpu_timers_exit_group(tsk);
- }
#endif
if (group_dead) {
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 428beb69426a..7cb09c4cf21c 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -928,6 +928,15 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
clocksource_arch_init(cs);
+#ifdef CONFIG_GENERIC_VDSO_CLOCK_MODE
+ if (cs->vdso_clock_mode < 0 ||
+ cs->vdso_clock_mode >= VDSO_CLOCKMODE_MAX) {
+ pr_warn("clocksource %s registered with invalid VDSO mode %d. Disabling VDSO support.\n",
+ cs->name, cs->vdso_clock_mode);
+ cs->vdso_clock_mode = VDSO_CLOCKMODE_NONE;
+ }
+#endif
+
/* Initialize mult/shift and max_idle_ns */
__clocksource_update_freq_scale(cs, scale, freq);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 8cce72501aea..d0a5ba37aff4 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -311,7 +311,7 @@ s64 __ktime_divns(const ktime_t kt, s64 div)
div >>= 1;
}
tmp >>= sft;
- do_div(tmp, (unsigned long) div);
+ do_div(tmp, (u32) div);
return dclc < 0 ? -tmp : tmp;
}
EXPORT_SYMBOL_GPL(__ktime_divns);
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index 12858507d75a..e6ba064ce773 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -8,6 +8,7 @@
#include <linux/user_namespace.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
+#include <linux/clocksource.h>
#include <linux/seq_file.h>
#include <linux/proc_ns.h>
#include <linux/export.h>
@@ -172,8 +173,8 @@ static struct timens_offset offset_from_ts(struct timespec64 off)
* for vdso_data->clock_mode is a non-issue. The task is spin waiting for the
* update to finish and for 'seq' to become even anyway.
*
- * Timens page has vdso_data->clock_mode set to VCLOCK_TIMENS which enforces
- * the time namespace handling path.
+ * Timens page has vdso_data->clock_mode set to VDSO_CLOCKMODE_TIMENS which
+ * enforces the time namespace handling path.
*/
static void timens_setup_vdso_data(struct vdso_data *vdata,
struct time_namespace *ns)
@@ -183,7 +184,7 @@ static void timens_setup_vdso_data(struct vdso_data *vdata,
struct timens_offset boottime = offset_from_ts(ns->offsets.boottime);
vdata->seq = 1;
- vdata->clock_mode = VCLOCK_TIMENS;
+ vdata->clock_mode = VDSO_CLOCKMODE_TIMENS;
offset[CLOCK_MONOTONIC] = monotonic;
offset[CLOCK_MONOTONIC_RAW] = monotonic;
offset[CLOCK_MONOTONIC_COARSE] = monotonic;
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 2c48a7233b19..2fd3b3fa68bf 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -118,6 +118,16 @@ static inline int validate_clock_permissions(const clockid_t clock)
return __get_task_for_clock(clock, false, false) ? 0 : -EINVAL;
}
+static inline enum pid_type cpu_timer_pid_type(struct k_itimer *timer)
+{
+ return CPUCLOCK_PERTHREAD(timer->it_clock) ? PIDTYPE_PID : PIDTYPE_TGID;
+}
+
+static inline struct task_struct *cpu_timer_task_rcu(struct k_itimer *timer)
+{
+ return pid_task(timer->it.cpu.pid, cpu_timer_pid_type(timer));
+}
+
/*
* Update expiry time from increment, and increase overrun count,
* given the current clock sample.
@@ -336,9 +346,7 @@ static void __thread_group_cputime(struct task_struct *tsk, u64 *samples)
/*
* Sample a process (thread group) clock for the given task clkid. If the
* group's cputime accounting is already enabled, read the atomic
- * store. Otherwise a full update is required. Task's sighand lock must be
- * held to protect the task traversal on a full update. clkid is already
- * validated.
+ * store. Otherwise a full update is required. clkid is already validated.
*/
static u64 cpu_clock_sample_group(const clockid_t clkid, struct task_struct *p,
bool start)
@@ -393,7 +401,12 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
new_timer->kclock = &clock_posix_cpu;
timerqueue_init(&new_timer->it.cpu.node);
- new_timer->it.cpu.task = p;
+ new_timer->it.cpu.pid = get_task_pid(p, cpu_timer_pid_type(new_timer));
+ /*
+ * get_task_for_clock() took a reference on @p. Drop it as the timer
+ * holds a reference on the pid of @p.
+ */
+ put_task_struct(p);
return 0;
}
@@ -406,13 +419,15 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
static int posix_cpu_timer_del(struct k_itimer *timer)
{
struct cpu_timer *ctmr = &timer->it.cpu;
- struct task_struct *p = ctmr->task;
struct sighand_struct *sighand;
+ struct task_struct *p;
unsigned long flags;
int ret = 0;
- if (WARN_ON_ONCE(!p))
- return -EINVAL;
+ rcu_read_lock();
+ p = cpu_timer_task_rcu(timer);
+ if (!p)
+ goto out;
/*
* Protect against sighand release/switch in exit/exec and process/
@@ -434,8 +449,10 @@ static int posix_cpu_timer_del(struct k_itimer *timer)
unlock_task_sighand(p, &flags);
}
+out:
+ rcu_read_unlock();
if (!ret)
- put_task_struct(p);
+ put_pid(ctmr->pid);
return ret;
}
@@ -484,12 +501,11 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk)
* Insert the timer on the appropriate list before any timers that
* expire later. This must be called with the sighand lock held.
*/
-static void arm_timer(struct k_itimer *timer)
+static void arm_timer(struct k_itimer *timer, struct task_struct *p)
{
int clkidx = CPUCLOCK_WHICH(timer->it_clock);
struct cpu_timer *ctmr = &timer->it.cpu;
u64 newexp = cpu_timer_getexpires(ctmr);
- struct task_struct *p = ctmr->task;
struct posix_cputimer_base *base;
if (CPUCLOCK_PERTHREAD(timer->it_clock))
@@ -564,13 +580,21 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
u64 old_expires, new_expires, old_incr, val;
struct cpu_timer *ctmr = &timer->it.cpu;
- struct task_struct *p = ctmr->task;
struct sighand_struct *sighand;
+ struct task_struct *p;
unsigned long flags;
int ret = 0;
- if (WARN_ON_ONCE(!p))
- return -EINVAL;
+ rcu_read_lock();
+ p = cpu_timer_task_rcu(timer);
+ if (!p) {
+ /*
+ * If p has just been reaped, we can no
+ * longer get any information about it at all.
+ */
+ rcu_read_unlock();
+ return -ESRCH;
+ }
/*
* Use the to_ktime conversion because that clamps the maximum
@@ -587,8 +611,10 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
* If p has just been reaped, we can no
* longer get any information about it at all.
*/
- if (unlikely(sighand == NULL))
+ if (unlikely(sighand == NULL)) {
+ rcu_read_unlock();
return -ESRCH;
+ }
/*
* Disarm any old timer after extracting its expiry time.
@@ -662,7 +688,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
*/
cpu_timer_setexpires(ctmr, new_expires);
if (new_expires != 0 && val < new_expires) {
- arm_timer(timer);
+ arm_timer(timer, p);
}
unlock_task_sighand(p, &flags);
@@ -693,6 +719,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
ret = 0;
out:
+ rcu_read_unlock();
if (old)
old->it_interval = ns_to_timespec64(old_incr);
@@ -704,10 +731,12 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp
clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
struct cpu_timer *ctmr = &timer->it.cpu;
u64 now, expires = cpu_timer_getexpires(ctmr);
- struct task_struct *p = ctmr->task;
+ struct task_struct *p;
- if (WARN_ON_ONCE(!p))
- return;
+ rcu_read_lock();
+ p = cpu_timer_task_rcu(timer);
+ if (!p)
+ goto out;
/*
* Easy part: convert the reload time.
@@ -715,36 +744,15 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp
itp->it_interval = ktime_to_timespec64(timer->it_interval);
if (!expires)
- return;
+ goto out;
/*
* Sample the clock to take the difference with the expiry time.
*/
- if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
+ if (CPUCLOCK_PERTHREAD(timer->it_clock))
now = cpu_clock_sample(clkid, p);
- } else {
- struct sighand_struct *sighand;
- unsigned long flags;
-
- /*
- * Protect against sighand release/switch in exit/exec and
- * also make timer sampling safe if it ends up calling
- * thread_group_cputime().
- */
- sighand = lock_task_sighand(p, &flags);
- if (unlikely(sighand == NULL)) {
- /*
- * The process has been reaped.
- * We can't even collect a sample any more.
- * Disarm the timer, nothing else to do.
- */
- cpu_timer_setexpires(ctmr, 0);
- return;
- } else {
- now = cpu_clock_sample_group(clkid, p, false);
- unlock_task_sighand(p, &flags);
- }
- }
+ else
+ now = cpu_clock_sample_group(clkid, p, false);
if (now < expires) {
itp->it_value = ns_to_timespec64(expires - now);
@@ -756,6 +764,8 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp
itp->it_value.tv_nsec = 1;
itp->it_value.tv_sec = 0;
}
+out:
+ rcu_read_unlock();
}
#define MAX_COLLECTED 20
@@ -976,56 +986,38 @@ static void check_process_timers(struct task_struct *tsk,
static void posix_cpu_timer_rearm(struct k_itimer *timer)
{
clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
- struct cpu_timer *ctmr = &timer->it.cpu;
- struct task_struct *p = ctmr->task;
+ struct task_struct *p;
struct sighand_struct *sighand;
unsigned long flags;
u64 now;
- if (WARN_ON_ONCE(!p))
- return;
+ rcu_read_lock();
+ p = cpu_timer_task_rcu(timer);
+ if (!p)
+ goto out;
/*
* Fetch the current sample and update the timer's expiry time.
*/
- if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
+ if (CPUCLOCK_PERTHREAD(timer->it_clock))
now = cpu_clock_sample(clkid, p);
- bump_cpu_timer(timer, now);
- if (unlikely(p->exit_state))
- return;
-
- /* Protect timer list r/w in arm_timer() */
- sighand = lock_task_sighand(p, &flags);
- if (!sighand)
- return;
- } else {
- /*
- * Protect arm_timer() and timer sampling in case of call to
- * thread_group_cputime().
- */
- sighand = lock_task_sighand(p, &flags);
- if (unlikely(sighand == NULL)) {
- /*
- * The process has been reaped.
- * We can't even collect a sample any more.
- */
- cpu_timer_setexpires(ctmr, 0);
- return;
- } else if (unlikely(p->exit_state) && thread_group_empty(p)) {
- /* If the process is dying, no need to rearm */
- goto unlock;
- }
+ else
now = cpu_clock_sample_group(clkid, p, true);
- bump_cpu_timer(timer, now);
- /* Leave the sighand locked for the call below. */
- }
+
+ bump_cpu_timer(timer, now);
+
+ /* Protect timer list r/w in arm_timer() */
+ sighand = lock_task_sighand(p, &flags);
+ if (unlikely(sighand == NULL))
+ goto out;
/*
* Now re-arm for the new expiry time.
*/
- arm_timer(timer);
-unlock:
+ arm_timer(timer, p);
unlock_task_sighand(p, &flags);
+out:
+ rcu_read_unlock();
}
/**
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index ff0eb30de346..07709ac30439 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -121,7 +121,8 @@ static struct k_itimer *__posix_timers_find(struct hlist_head *head,
{
struct k_itimer *timer;
- hlist_for_each_entry_rcu(timer, head, t_hash) {
+ hlist_for_each_entry_rcu(timer, head, t_hash,
+ lockdep_is_held(&hash_lock)) {
if ((timer->it_signal == sig) && (timer->it_id == id))
return timer;
}
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index e4332e3e2d56..fa3f800d7d76 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -208,7 +208,8 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
if (sched_clock_timer.function != NULL) {
/* update timeout for clock wrap */
- hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
+ hrtimer_start(&sched_clock_timer, cd.wrap_kt,
+ HRTIMER_MODE_REL_HARD);
}
r = rate;
@@ -254,9 +255,9 @@ void __init generic_sched_clock_init(void)
* Start the timer to keep sched_clock() properly updated and
* sets the initial epoch.
*/
- hrtimer_init(&sched_clock_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init(&sched_clock_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
sched_clock_timer.function = sched_clock_poll;
- hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
+ hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD);
}
/*
@@ -293,7 +294,7 @@ void sched_clock_resume(void)
struct clock_read_data *rd = &cd.read_data[0];
rd->epoch_cyc = cd.actual_read_sched_clock();
- hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
+ hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD);
rd->read_sched_clock = cd.actual_read_sched_clock;
}
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 856280d2cbd4..9ebaab13339d 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1005,9 +1005,8 @@ static int scale64_check_overflow(u64 mult, u64 div, u64 *base)
((int)sizeof(u64)*8 - fls64(mult) < fls64(rem)))
return -EOVERFLOW;
tmp *= mult;
- rem *= mult;
- do_div(rem, div);
+ rem = div64_u64(rem * mult, div);
*base = tmp + rem;
return 0;
}
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 568564ae3597..a5221abb4594 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1829,21 +1829,23 @@ static void process_timeout(struct timer_list *t)
* schedule_timeout - sleep until timeout
* @timeout: timeout value in jiffies
*
- * Make the current task sleep until @timeout jiffies have
- * elapsed. The routine will return immediately unless
- * the current task state has been set (see set_current_state()).
+ * Make the current task sleep until @timeout jiffies have elapsed.
+ * The function behavior depends on the current task state
+ * (see also set_current_state() description):
*
- * You can set the task state as follows -
+ * %TASK_RUNNING - the scheduler is called, but the task does not sleep
+ * at all. That happens because sched_submit_work() does nothing for
+ * tasks in %TASK_RUNNING state.
*
* %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to
* pass before the routine returns unless the current task is explicitly
- * woken up, (e.g. by wake_up_process())".
+ * woken up, (e.g. by wake_up_process()).
*
* %TASK_INTERRUPTIBLE - the routine may return early if a signal is
* delivered to the current task or the current task is explicitly woken
* up.
*
- * The current task state is guaranteed to be TASK_RUNNING when this
+ * The current task state is guaranteed to be %TASK_RUNNING when this
* routine returns.
*
* Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule
@@ -1851,7 +1853,7 @@ static void process_timeout(struct timer_list *t)
* value will be %MAX_SCHEDULE_TIMEOUT.
*
* Returns 0 when the timer has expired otherwise the remaining time in
- * jiffies will be returned. In all cases the return value is guaranteed
+ * jiffies will be returned. In all cases the return value is guaranteed
* to be non-negative.
*/
signed long __sched schedule_timeout(signed long timeout)
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 9577c89179cd..54ce6eb2ca36 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -71,13 +71,15 @@ void update_vsyscall(struct timekeeper *tk)
{
struct vdso_data *vdata = __arch_get_k_vdso_data();
struct vdso_timestamp *vdso_ts;
+ s32 clock_mode;
u64 nsec;
/* copy vsyscall data */
vdso_write_begin(vdata);
- vdata[CS_HRES_COARSE].clock_mode = __arch_get_clock_mode(tk);
- vdata[CS_RAW].clock_mode = __arch_get_clock_mode(tk);
+ clock_mode = tk->tkr_mono.clock->vdso_clock_mode;
+ vdata[CS_HRES_COARSE].clock_mode = clock_mode;
+ vdata[CS_RAW].clock_mode = clock_mode;
/* CLOCK_REALTIME also required for time() */
vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME];
@@ -103,10 +105,10 @@ void update_vsyscall(struct timekeeper *tk)
WRITE_ONCE(vdata[CS_HRES_COARSE].hrtimer_res, hrtimer_resolution);
/*
- * Architectures can opt out of updating the high resolution part
- * of the VDSO.
+ * If the current clocksource is not VDSO capable, then spare the
+ * update of the high reolution parts.
*/
- if (__arch_update_vdso_data())
+ if (clock_mode != VDSO_CLOCKMODE_NONE)
update_vdso_data(vdata, tk);
__arch_update_vsyscall(vdata, tk);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.