aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/time
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/time')
-rw-r--r--kernel/time/Makefile1
-rw-r--r--kernel/time/alarmtimer.c121
-rw-r--r--kernel/time/hrtimer.c14
-rw-r--r--kernel/time/namespace.c468
-rw-r--r--kernel/time/posix-clock.c8
-rw-r--r--kernel/time/posix-cpu-timers.c32
-rw-r--r--kernel/time/posix-stubs.c18
-rw-r--r--kernel/time/posix-timers.c88
-rw-r--r--kernel/time/posix-timers.h7
-rw-r--r--kernel/time/sched_clock.c7
-rw-r--r--kernel/time/tick-common.c2
-rw-r--r--kernel/time/tick-sched.c14
-rw-r--r--kernel/time/vsyscall.c37
13 files changed, 685 insertions, 132 deletions
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 1867044800bb..c8f00168afe8 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -19,3 +19,4 @@ obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o tick-sched.o
obj-$(CONFIG_HAVE_GENERIC_VDSO) += vsyscall.o
obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o
obj-$(CONFIG_TEST_UDELAY) += test_udelay.o
+obj-$(CONFIG_TIME_NS) += namespace.o
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 451f9d05ccfe..2ffb466af77e 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -26,6 +26,7 @@
#include <linux/freezer.h>
#include <linux/compat.h>
#include <linux/module.h>
+#include <linux/time_namespace.h>
#include "posix-timers.h"
@@ -36,13 +37,15 @@
* struct alarm_base - Alarm timer bases
* @lock: Lock for syncrhonized access to the base
* @timerqueue: Timerqueue head managing the list of events
- * @gettime: Function to read the time correlating to the base
+ * @get_ktime: Function to read the time correlating to the base
+ * @get_timespec: Function to read the namespace time correlating to the base
* @base_clockid: clockid for the base
*/
static struct alarm_base {
spinlock_t lock;
struct timerqueue_head timerqueue;
- ktime_t (*gettime)(void);
+ ktime_t (*get_ktime)(void);
+ void (*get_timespec)(struct timespec64 *tp);
clockid_t base_clockid;
} alarm_bases[ALARM_NUMTYPE];
@@ -55,8 +58,6 @@ static DEFINE_SPINLOCK(freezer_delta_lock);
#endif
#ifdef CONFIG_RTC_CLASS
-static struct wakeup_source *ws;
-
/* rtc timer and device for setting alarm wakeups at suspend */
static struct rtc_timer rtctimer;
static struct rtc_device *rtcdev;
@@ -66,8 +67,6 @@ static DEFINE_SPINLOCK(rtcdev_lock);
* alarmtimer_get_rtcdev - Return selected rtcdevice
*
* This function returns the rtc device to use for wakealarms.
- * If one has not already been chosen, it checks to see if a
- * functional rtc device is available.
*/
struct rtc_device *alarmtimer_get_rtcdev(void)
{
@@ -87,7 +86,8 @@ static int alarmtimer_rtc_add_device(struct device *dev,
{
unsigned long flags;
struct rtc_device *rtc = to_rtc_device(dev);
- struct wakeup_source *__ws;
+ struct platform_device *pdev;
+ int ret = 0;
if (rtcdev)
return -EBUSY;
@@ -97,26 +97,31 @@ static int alarmtimer_rtc_add_device(struct device *dev,
if (!device_may_wakeup(rtc->dev.parent))
return -1;
- __ws = wakeup_source_register(dev, "alarmtimer");
+ pdev = platform_device_register_data(dev, "alarmtimer",
+ PLATFORM_DEVID_AUTO, NULL, 0);
+ if (!IS_ERR(pdev))
+ device_init_wakeup(&pdev->dev, true);
spin_lock_irqsave(&rtcdev_lock, flags);
- if (!rtcdev) {
+ if (!IS_ERR(pdev) && !rtcdev) {
if (!try_module_get(rtc->owner)) {
- spin_unlock_irqrestore(&rtcdev_lock, flags);
- return -1;
+ ret = -1;
+ goto unlock;
}
rtcdev = rtc;
/* hold a reference so it doesn't go away */
get_device(dev);
- ws = __ws;
- __ws = NULL;
+ pdev = NULL;
+ } else {
+ ret = -1;
}
+unlock:
spin_unlock_irqrestore(&rtcdev_lock, flags);
- wakeup_source_unregister(__ws);
+ platform_device_unregister(pdev);
- return 0;
+ return ret;
}
static inline void alarmtimer_rtc_timer_init(void)
@@ -138,11 +143,6 @@ static void alarmtimer_rtc_interface_remove(void)
class_interface_unregister(&alarmtimer_rtc_interface);
}
#else
-struct rtc_device *alarmtimer_get_rtcdev(void)
-{
- return NULL;
-}
-#define rtcdev (NULL)
static inline int alarmtimer_rtc_interface_setup(void) { return 0; }
static inline void alarmtimer_rtc_interface_remove(void) { }
static inline void alarmtimer_rtc_timer_init(void) { }
@@ -207,7 +207,7 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer)
spin_unlock_irqrestore(&base->lock, flags);
if (alarm->function)
- restart = alarm->function(alarm, base->gettime());
+ restart = alarm->function(alarm, base->get_ktime());
spin_lock_irqsave(&base->lock, flags);
if (restart != ALARMTIMER_NORESTART) {
@@ -217,7 +217,7 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer)
}
spin_unlock_irqrestore(&base->lock, flags);
- trace_alarmtimer_fired(alarm, base->gettime());
+ trace_alarmtimer_fired(alarm, base->get_ktime());
return ret;
}
@@ -225,7 +225,7 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer)
ktime_t alarm_expires_remaining(const struct alarm *alarm)
{
struct alarm_base *base = &alarm_bases[alarm->type];
- return ktime_sub(alarm->node.expires, base->gettime());
+ return ktime_sub(alarm->node.expires, base->get_ktime());
}
EXPORT_SYMBOL_GPL(alarm_expires_remaining);
@@ -270,7 +270,7 @@ static int alarmtimer_suspend(struct device *dev)
spin_unlock_irqrestore(&base->lock, flags);
if (!next)
continue;
- delta = ktime_sub(next->expires, base->gettime());
+ delta = ktime_sub(next->expires, base->get_ktime());
if (!min || (delta < min)) {
expires = next->expires;
min = delta;
@@ -281,7 +281,7 @@ static int alarmtimer_suspend(struct device *dev)
return 0;
if (ktime_to_ns(min) < 2 * NSEC_PER_SEC) {
- __pm_wakeup_event(ws, 2 * MSEC_PER_SEC);
+ pm_wakeup_event(dev, 2 * MSEC_PER_SEC);
return -EBUSY;
}
@@ -296,7 +296,7 @@ static int alarmtimer_suspend(struct device *dev)
/* Set alarm, if in the past reject suspend briefly to handle */
ret = rtc_timer_start(rtc, &rtctimer, now, 0);
if (ret < 0)
- __pm_wakeup_event(ws, MSEC_PER_SEC);
+ pm_wakeup_event(dev, MSEC_PER_SEC);
return ret;
}
@@ -364,7 +364,7 @@ void alarm_start(struct alarm *alarm, ktime_t start)
hrtimer_start(&alarm->timer, alarm->node.expires, HRTIMER_MODE_ABS);
spin_unlock_irqrestore(&base->lock, flags);
- trace_alarmtimer_start(alarm, base->gettime());
+ trace_alarmtimer_start(alarm, base->get_ktime());
}
EXPORT_SYMBOL_GPL(alarm_start);
@@ -377,7 +377,7 @@ void alarm_start_relative(struct alarm *alarm, ktime_t start)
{
struct alarm_base *base = &alarm_bases[alarm->type];
- start = ktime_add_safe(start, base->gettime());
+ start = ktime_add_safe(start, base->get_ktime());
alarm_start(alarm, start);
}
EXPORT_SYMBOL_GPL(alarm_start_relative);
@@ -414,7 +414,7 @@ int alarm_try_to_cancel(struct alarm *alarm)
alarmtimer_dequeue(base, alarm);
spin_unlock_irqrestore(&base->lock, flags);
- trace_alarmtimer_cancel(alarm, base->gettime());
+ trace_alarmtimer_cancel(alarm, base->get_ktime());
return ret;
}
EXPORT_SYMBOL_GPL(alarm_try_to_cancel);
@@ -474,7 +474,7 @@ u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
{
struct alarm_base *base = &alarm_bases[alarm->type];
- return alarm_forward(alarm, base->gettime(), interval);
+ return alarm_forward(alarm, base->get_ktime(), interval);
}
EXPORT_SYMBOL_GPL(alarm_forward_now);
@@ -500,7 +500,7 @@ static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type)
return;
}
- delta = ktime_sub(absexp, base->gettime());
+ delta = ktime_sub(absexp, base->get_ktime());
spin_lock_irqsave(&freezer_delta_lock, flags);
if (!freezer_delta || (delta < freezer_delta)) {
@@ -632,7 +632,7 @@ static void alarm_timer_arm(struct k_itimer *timr, ktime_t expires,
struct alarm_base *base = &alarm_bases[alarm->type];
if (!absolute)
- expires = ktime_add_safe(expires, base->gettime());
+ expires = ktime_add_safe(expires, base->get_ktime());
if (sigev_none)
alarm->node.expires = expires;
else
@@ -657,24 +657,41 @@ static int alarm_clock_getres(const clockid_t which_clock, struct timespec64 *tp
}
/**
- * alarm_clock_get - posix clock_get interface
+ * alarm_clock_get_timespec - posix clock_get_timespec interface
* @which_clock: clockid
* @tp: timespec to fill.
*
- * Provides the underlying alarm base time.
+ * Provides the underlying alarm base time in a tasks time namespace.
*/
-static int alarm_clock_get(clockid_t which_clock, struct timespec64 *tp)
+static int alarm_clock_get_timespec(clockid_t which_clock, struct timespec64 *tp)
{
struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)];
if (!alarmtimer_get_rtcdev())
return -EINVAL;
- *tp = ktime_to_timespec64(base->gettime());
+ base->get_timespec(tp);
+
return 0;
}
/**
+ * alarm_clock_get_ktime - posix clock_get_ktime interface
+ * @which_clock: clockid
+ *
+ * Provides the underlying alarm base time in the root namespace.
+ */
+static ktime_t alarm_clock_get_ktime(clockid_t which_clock)
+{
+ struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)];
+
+ if (!alarmtimer_get_rtcdev())
+ return -EINVAL;
+
+ return base->get_ktime();
+}
+
+/**
* alarm_timer_create - posix timer_create interface
* @new_timer: k_itimer pointer to manage
*
@@ -747,7 +764,7 @@ static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp,
struct timespec64 rmt;
ktime_t rem;
- rem = ktime_sub(absexp, alarm_bases[type].gettime());
+ rem = ktime_sub(absexp, alarm_bases[type].get_ktime());
if (rem <= 0)
return 0;
@@ -816,9 +833,11 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
exp = timespec64_to_ktime(*tsreq);
/* Convert (if necessary) to absolute time */
if (flags != TIMER_ABSTIME) {
- ktime_t now = alarm_bases[type].gettime();
+ ktime_t now = alarm_bases[type].get_ktime();
exp = ktime_add_safe(now, exp);
+ } else {
+ exp = timens_ktime_to_host(which_clock, exp);
}
ret = alarmtimer_do_nsleep(&alarm, exp, type);
@@ -837,7 +856,8 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
const struct k_clock alarm_clock = {
.clock_getres = alarm_clock_getres,
- .clock_get = alarm_clock_get,
+ .clock_get_ktime = alarm_clock_get_ktime,
+ .clock_get_timespec = alarm_clock_get_timespec,
.timer_create = alarm_timer_create,
.timer_set = common_timer_set,
.timer_del = common_timer_del,
@@ -866,6 +886,12 @@ static struct platform_driver alarmtimer_driver = {
}
};
+static void get_boottime_timespec(struct timespec64 *tp)
+{
+ ktime_get_boottime_ts64(tp);
+ timens_add_boottime(tp);
+}
+
/**
* alarmtimer_init - Initialize alarm timer code
*
@@ -874,17 +900,18 @@ static struct platform_driver alarmtimer_driver = {
*/
static int __init alarmtimer_init(void)
{
- struct platform_device *pdev;
- int error = 0;
+ int error;
int i;
alarmtimer_rtc_timer_init();
/* Initialize alarm bases */
alarm_bases[ALARM_REALTIME].base_clockid = CLOCK_REALTIME;
- alarm_bases[ALARM_REALTIME].gettime = &ktime_get_real;
+ alarm_bases[ALARM_REALTIME].get_ktime = &ktime_get_real;
+ alarm_bases[ALARM_REALTIME].get_timespec = ktime_get_real_ts64,
alarm_bases[ALARM_BOOTTIME].base_clockid = CLOCK_BOOTTIME;
- alarm_bases[ALARM_BOOTTIME].gettime = &ktime_get_boottime;
+ alarm_bases[ALARM_BOOTTIME].get_ktime = &ktime_get_boottime;
+ alarm_bases[ALARM_BOOTTIME].get_timespec = get_boottime_timespec;
for (i = 0; i < ALARM_NUMTYPE; i++) {
timerqueue_init_head(&alarm_bases[i].timerqueue);
spin_lock_init(&alarm_bases[i].lock);
@@ -898,15 +925,7 @@ static int __init alarmtimer_init(void)
if (error)
goto out_if;
- pdev = platform_device_register_simple("alarmtimer", -1, NULL, 0);
- if (IS_ERR(pdev)) {
- error = PTR_ERR(pdev);
- goto out_drv;
- }
return 0;
-
-out_drv:
- platform_driver_unregister(&alarmtimer_driver);
out_if:
alarmtimer_rtc_interface_remove();
return error;
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 8de90ea31280..3a609e7344f3 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1477,7 +1477,7 @@ EXPORT_SYMBOL_GPL(hrtimer_active);
static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
struct hrtimer_clock_base *base,
struct hrtimer *timer, ktime_t *now,
- unsigned long flags)
+ unsigned long flags) __must_hold(&cpu_base->lock)
{
enum hrtimer_restart (*fn)(struct hrtimer *);
int restart;
@@ -1910,8 +1910,8 @@ static long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
return ret;
}
-long hrtimer_nanosleep(const struct timespec64 *rqtp,
- const enum hrtimer_mode mode, const clockid_t clockid)
+long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode,
+ const clockid_t clockid)
{
struct restart_block *restart;
struct hrtimer_sleeper t;
@@ -1923,7 +1923,7 @@ long hrtimer_nanosleep(const struct timespec64 *rqtp,
slack = 0;
hrtimer_init_sleeper_on_stack(&t, clockid, mode);
- hrtimer_set_expires_range_ns(&t.timer, timespec64_to_ktime(*rqtp), slack);
+ hrtimer_set_expires_range_ns(&t.timer, rqtp, slack);
ret = do_nanosleep(&t, mode);
if (ret != -ERESTART_RESTARTBLOCK)
goto out;
@@ -1958,7 +1958,8 @@ SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp,
current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
current->restart_block.nanosleep.rmtp = rmtp;
- return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
+ return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL,
+ CLOCK_MONOTONIC);
}
#endif
@@ -1978,7 +1979,8 @@ SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp,
current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE;
current->restart_block.nanosleep.compat_rmtp = rmtp;
- return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
+ return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL,
+ CLOCK_MONOTONIC);
}
#endif
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
new file mode 100644
index 000000000000..12858507d75a
--- /dev/null
+++ b/kernel/time/namespace.c
@@ -0,0 +1,468 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author: Andrei Vagin <avagin@openvz.org>
+ * Author: Dmitry Safonov <dima@arista.com>
+ */
+
+#include <linux/time_namespace.h>
+#include <linux/user_namespace.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/seq_file.h>
+#include <linux/proc_ns.h>
+#include <linux/export.h>
+#include <linux/time.h>
+#include <linux/slab.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+#include <linux/mm.h>
+
+#include <vdso/datapage.h>
+
+ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim,
+ struct timens_offsets *ns_offsets)
+{
+ ktime_t offset;
+
+ switch (clockid) {
+ case CLOCK_MONOTONIC:
+ offset = timespec64_to_ktime(ns_offsets->monotonic);
+ break;
+ case CLOCK_BOOTTIME:
+ case CLOCK_BOOTTIME_ALARM:
+ offset = timespec64_to_ktime(ns_offsets->boottime);
+ break;
+ default:
+ return tim;
+ }
+
+ /*
+ * Check that @tim value is in [offset, KTIME_MAX + offset]
+ * and subtract offset.
+ */
+ if (tim < offset) {
+ /*
+ * User can specify @tim *absolute* value - if it's lesser than
+ * the time namespace's offset - it's already expired.
+ */
+ tim = 0;
+ } else {
+ tim = ktime_sub(tim, offset);
+ if (unlikely(tim > KTIME_MAX))
+ tim = KTIME_MAX;
+ }
+
+ return tim;
+}
+
+static struct ucounts *inc_time_namespaces(struct user_namespace *ns)
+{
+ return inc_ucount(ns, current_euid(), UCOUNT_TIME_NAMESPACES);
+}
+
+static void dec_time_namespaces(struct ucounts *ucounts)
+{
+ dec_ucount(ucounts, UCOUNT_TIME_NAMESPACES);
+}
+
+/**
+ * clone_time_ns - Clone a time namespace
+ * @user_ns: User namespace which owns a new namespace.
+ * @old_ns: Namespace to clone
+ *
+ * Clone @old_ns and set the clone refcount to 1
+ *
+ * Return: The new namespace or ERR_PTR.
+ */
+static struct time_namespace *clone_time_ns(struct user_namespace *user_ns,
+ struct time_namespace *old_ns)
+{
+ struct time_namespace *ns;
+ struct ucounts *ucounts;
+ int err;
+
+ err = -ENOSPC;
+ ucounts = inc_time_namespaces(user_ns);
+ if (!ucounts)
+ goto fail;
+
+ err = -ENOMEM;
+ ns = kmalloc(sizeof(*ns), GFP_KERNEL);
+ if (!ns)
+ goto fail_dec;
+
+ kref_init(&ns->kref);
+
+ ns->vvar_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!ns->vvar_page)
+ goto fail_free;
+
+ err = ns_alloc_inum(&ns->ns);
+ if (err)
+ goto fail_free_page;
+
+ ns->ucounts = ucounts;
+ ns->ns.ops = &timens_operations;
+ ns->user_ns = get_user_ns(user_ns);
+ ns->offsets = old_ns->offsets;
+ ns->frozen_offsets = false;
+ return ns;
+
+fail_free_page:
+ __free_page(ns->vvar_page);
+fail_free:
+ kfree(ns);
+fail_dec:
+ dec_time_namespaces(ucounts);
+fail:
+ return ERR_PTR(err);
+}
+
+/**
+ * copy_time_ns - Create timens_for_children from @old_ns
+ * @flags: Cloning flags
+ * @user_ns: User namespace which owns a new namespace.
+ * @old_ns: Namespace to clone
+ *
+ * If CLONE_NEWTIME specified in @flags, creates a new timens_for_children;
+ * adds a refcounter to @old_ns otherwise.
+ *
+ * Return: timens_for_children namespace or ERR_PTR.
+ */
+struct time_namespace *copy_time_ns(unsigned long flags,
+ struct user_namespace *user_ns, struct time_namespace *old_ns)
+{
+ if (!(flags & CLONE_NEWTIME))
+ return get_time_ns(old_ns);
+
+ return clone_time_ns(user_ns, old_ns);
+}
+
+static struct timens_offset offset_from_ts(struct timespec64 off)
+{
+ struct timens_offset ret;
+
+ ret.sec = off.tv_sec;
+ ret.nsec = off.tv_nsec;
+
+ return ret;
+}
+
+/*
+ * A time namespace VVAR page has the same layout as the VVAR page which
+ * contains the system wide VDSO data.
+ *
+ * For a normal task the VVAR pages are installed in the normal ordering:
+ * VVAR
+ * PVCLOCK
+ * HVCLOCK
+ * TIMENS <- Not really required
+ *
+ * Now for a timens task the pages are installed in the following order:
+ * TIMENS
+ * PVCLOCK
+ * HVCLOCK
+ * VVAR
+ *
+ * The check for vdso_data->clock_mode is in the unlikely path of
+ * the seq begin magic. So for the non-timens case most of the time
+ * 'seq' is even, so the branch is not taken.
+ *
+ * If 'seq' is odd, i.e. a concurrent update is in progress, the extra check
+ * 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.
+ */
+static void timens_setup_vdso_data(struct vdso_data *vdata,
+ struct time_namespace *ns)
+{
+ struct timens_offset *offset = vdata->offset;
+ struct timens_offset monotonic = offset_from_ts(ns->offsets.monotonic);
+ struct timens_offset boottime = offset_from_ts(ns->offsets.boottime);
+
+ vdata->seq = 1;
+ vdata->clock_mode = VCLOCK_TIMENS;
+ offset[CLOCK_MONOTONIC] = monotonic;
+ offset[CLOCK_MONOTONIC_RAW] = monotonic;
+ offset[CLOCK_MONOTONIC_COARSE] = monotonic;
+ offset[CLOCK_BOOTTIME] = boottime;
+ offset[CLOCK_BOOTTIME_ALARM] = boottime;
+}
+
+/*
+ * Protects possibly multiple offsets writers racing each other
+ * and tasks entering the namespace.
+ */
+static DEFINE_MUTEX(offset_lock);
+
+static void timens_set_vvar_page(struct task_struct *task,
+ struct time_namespace *ns)
+{
+ struct vdso_data *vdata;
+ unsigned int i;
+
+ if (ns == &init_time_ns)
+ return;
+
+ /* Fast-path, taken by every task in namespace except the first. */
+ if (likely(ns->frozen_offsets))
+ return;
+
+ mutex_lock(&offset_lock);
+ /* Nothing to-do: vvar_page has been already initialized. */
+ if (ns->frozen_offsets)
+ goto out;
+
+ ns->frozen_offsets = true;
+ vdata = arch_get_vdso_data(page_address(ns->vvar_page));
+
+ for (i = 0; i < CS_BASES; i++)
+ timens_setup_vdso_data(&vdata[i], ns);
+
+out:
+ mutex_unlock(&offset_lock);
+}
+
+void free_time_ns(struct kref *kref)
+{
+ struct time_namespace *ns;
+
+ ns = container_of(kref, struct time_namespace, kref);
+ dec_time_namespaces(ns->ucounts);
+ put_user_ns(ns->user_ns);
+ ns_free_inum(&ns->ns);
+ __free_page(ns->vvar_page);
+ kfree(ns);
+}
+
+static struct time_namespace *to_time_ns(struct ns_common *ns)
+{
+ return container_of(ns, struct time_namespace, ns);
+}
+
+static struct ns_common *timens_get(struct task_struct *task)
+{
+ struct time_namespace *ns = NULL;
+ struct nsproxy *nsproxy;
+
+ task_lock(task);
+ nsproxy = task->nsproxy;
+ if (nsproxy) {
+ ns = nsproxy->time_ns;
+ get_time_ns(ns);
+ }
+ task_unlock(task);
+
+ return ns ? &ns->ns : NULL;
+}
+
+static struct ns_common *timens_for_children_get(struct task_struct *task)
+{
+ struct time_namespace *ns = NULL;
+ struct nsproxy *nsproxy;
+
+ task_lock(task);
+ nsproxy = task->nsproxy;
+ if (nsproxy) {
+ ns = nsproxy->time_ns_for_children;
+ get_time_ns(ns);
+ }
+ task_unlock(task);
+
+ return ns ? &ns->ns : NULL;
+}
+
+static void timens_put(struct ns_common *ns)
+{
+ put_time_ns(to_time_ns(ns));
+}
+
+static int timens_install(struct nsproxy *nsproxy, struct ns_common *new)
+{
+ struct time_namespace *ns = to_time_ns(new);
+ int err;
+
+ if (!current_is_single_threaded())
+ return -EUSERS;
+
+ if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
+ !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
+ return -EPERM;
+
+ timens_set_vvar_page(current, ns);
+
+ err = vdso_join_timens(current, ns);
+ if (err)
+ return err;
+
+ get_time_ns(ns);
+ put_time_ns(nsproxy->time_ns);
+ nsproxy->time_ns = ns;
+
+ get_time_ns(ns);
+ put_time_ns(nsproxy->time_ns_for_children);
+ nsproxy->time_ns_for_children = ns;
+ return 0;
+}
+
+int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk)
+{
+ struct ns_common *nsc = &nsproxy->time_ns_for_children->ns;
+ struct time_namespace *ns = to_time_ns(nsc);
+ int err;
+
+ /* create_new_namespaces() already incremented the ref counter */
+ if (nsproxy->time_ns == nsproxy->time_ns_for_children)
+ return 0;
+
+ timens_set_vvar_page(tsk, ns);
+
+ err = vdso_join_timens(tsk, ns);
+ if (err)
+ return err;
+
+ get_time_ns(ns);
+ put_time_ns(nsproxy->time_ns);
+ nsproxy->time_ns = ns;
+
+ return 0;
+}
+
+static struct user_namespace *timens_owner(struct ns_common *ns)
+{
+ return to_time_ns(ns)->user_ns;
+}
+
+static void show_offset(struct seq_file *m, int clockid, struct timespec64 *ts)
+{
+ seq_printf(m, "%d %lld %ld\n", clockid, ts->tv_sec, ts->tv_nsec);
+}
+
+void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m)
+{
+ struct ns_common *ns;
+ struct time_namespace *time_ns;
+
+ ns = timens_for_children_get(p);
+ if (!ns)
+ return;
+ time_ns = to_time_ns(ns);
+
+ show_offset(m, CLOCK_MONOTONIC, &time_ns->offsets.monotonic);
+ show_offset(m, CLOCK_BOOTTIME, &time_ns->offsets.boottime);
+ put_time_ns(time_ns);
+}
+
+int proc_timens_set_offset(struct file *file, struct task_struct *p,
+ struct proc_timens_offset *offsets, int noffsets)
+{
+ struct ns_common *ns;
+ struct time_namespace *time_ns;
+ struct timespec64 tp;
+ int i, err;
+
+ ns = timens_for_children_get(p);
+ if (!ns)
+ return -ESRCH;
+ time_ns = to_time_ns(ns);
+
+ if (!file_ns_capable(file, time_ns->user_ns, CAP_SYS_TIME)) {
+ put_time_ns(time_ns);
+ return -EPERM;
+ }
+
+ for (i = 0; i < noffsets; i++) {
+ struct proc_timens_offset *off = &offsets[i];
+
+ switch (off->clockid) {
+ case CLOCK_MONOTONIC:
+ ktime_get_ts64(&tp);
+ break;
+ case CLOCK_BOOTTIME:
+ ktime_get_boottime_ts64(&tp);
+ break;
+ default:
+ err = -EINVAL;
+ goto out;
+ }
+
+ err = -ERANGE;
+
+ if (off->val.tv_sec > KTIME_SEC_MAX ||
+ off->val.tv_sec < -KTIME_SEC_MAX)
+ goto out;
+
+ tp = timespec64_add(tp, off->val);
+ /*
+ * KTIME_SEC_MAX is divided by 2 to be sure that KTIME_MAX is
+ * still unreachable.
+ */
+ if (tp.tv_sec < 0 || tp.tv_sec > KTIME_SEC_MAX / 2)
+ goto out;
+ }
+
+ mutex_lock(&offset_lock);
+ if (time_ns->frozen_offsets) {
+ err = -EACCES;
+ goto out_unlock;
+ }
+
+ err = 0;
+ /* Don't report errors after this line */
+ for (i = 0; i < noffsets; i++) {
+ struct proc_timens_offset *off = &offsets[i];
+ struct timespec64 *offset = NULL;
+
+ switch (off->clockid) {
+ case CLOCK_MONOTONIC:
+ offset = &time_ns->offsets.monotonic;
+ break;
+ case CLOCK_BOOTTIME:
+ offset = &time_ns->offsets.boottime;
+ break;
+ }
+
+ *offset = off->val;
+ }
+
+out_unlock:
+ mutex_unlock(&offset_lock);
+out:
+ put_time_ns(time_ns);
+
+ return err;
+}
+
+const struct proc_ns_operations timens_operations = {
+ .name = "time",
+ .type = CLONE_NEWTIME,
+ .get = timens_get,
+ .put = timens_put,
+ .install = timens_install,
+ .owner = timens_owner,
+};
+
+const struct proc_ns_operations timens_for_children_operations = {
+ .name = "time_for_children",
+ .type = CLONE_NEWTIME,
+ .get = timens_for_children_get,
+ .put = timens_put,
+ .install = timens_install,
+ .owner = timens_owner,
+};
+
+struct time_namespace init_time_ns = {
+ .kref = KREF_INIT(3),
+ .user_ns = &init_user_ns,
+ .ns.inum = PROC_TIME_INIT_INO,
+ .ns.ops = &timens_operations,
+ .frozen_offsets = true,
+};
+
+static int __init time_ns_init(void)
+{
+ return 0;
+}
+subsys_initcall(time_ns_init);
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index 200fb2d3be99..77c0c2370b6d 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -310,8 +310,8 @@ out:
}
const struct k_clock clock_posix_dynamic = {
- .clock_getres = pc_clock_getres,
- .clock_set = pc_clock_settime,
- .clock_get = pc_clock_gettime,
- .clock_adj = pc_clock_adjtime,
+ .clock_getres = pc_clock_getres,
+ .clock_set = pc_clock_settime,
+ .clock_get_timespec = pc_clock_gettime,
+ .clock_adj = pc_clock_adjtime,
};
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 42d512fcfda2..8ff6da77a01f 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1391,26 +1391,26 @@ static int thread_cpu_timer_create(struct k_itimer *timer)
}
const struct k_clock clock_posix_cpu = {
- .clock_getres = posix_cpu_clock_getres,
- .clock_set = posix_cpu_clock_set,
- .clock_get = posix_cpu_clock_get,
- .timer_create = posix_cpu_timer_create,
- .nsleep = posix_cpu_nsleep,
- .timer_set = posix_cpu_timer_set,
- .timer_del = posix_cpu_timer_del,
- .timer_get = posix_cpu_timer_get,
- .timer_rearm = posix_cpu_timer_rearm,
+ .clock_getres = posix_cpu_clock_getres,
+ .clock_set = posix_cpu_clock_set,
+ .clock_get_timespec = posix_cpu_clock_get,
+ .timer_create = posix_cpu_timer_create,
+ .nsleep = posix_cpu_nsleep,
+ .timer_set = posix_cpu_timer_set,
+ .timer_del = posix_cpu_timer_del,
+ .timer_get = posix_cpu_timer_get,
+ .timer_rearm = posix_cpu_timer_rearm,
};
const struct k_clock clock_process = {
- .clock_getres = process_cpu_clock_getres,
- .clock_get = process_cpu_clock_get,
- .timer_create = process_cpu_timer_create,
- .nsleep = process_cpu_nsleep,
+ .clock_getres = process_cpu_clock_getres,
+ .clock_get_timespec = process_cpu_clock_get,
+ .timer_create = process_cpu_timer_create,
+ .nsleep = process_cpu_nsleep,
};
const struct k_clock clock_thread = {
- .clock_getres = thread_cpu_clock_getres,
- .clock_get = thread_cpu_clock_get,
- .timer_create = thread_cpu_timer_create,
+ .clock_getres = thread_cpu_clock_getres,
+ .clock_get_timespec = thread_cpu_clock_get,
+ .timer_create = thread_cpu_timer_create,
};
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 67df65f887ac..fcb3b21d8bdc 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -14,6 +14,7 @@
#include <linux/ktime.h>
#include <linux/timekeeping.h>
#include <linux/posix-timers.h>
+#include <linux/time_namespace.h>
#include <linux/compat.h>
#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
@@ -77,9 +78,11 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
break;
case CLOCK_MONOTONIC:
ktime_get_ts64(tp);
+ timens_add_monotonic(tp);
break;
case CLOCK_BOOTTIME:
ktime_get_boottime_ts64(tp);
+ timens_add_boottime(tp);
break;
default:
return -EINVAL;
@@ -126,6 +129,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
struct __kernel_timespec __user *, rmtp)
{
struct timespec64 t;
+ ktime_t texp;
switch (which_clock) {
case CLOCK_REALTIME:
@@ -144,13 +148,19 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
rmtp = NULL;
current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
current->restart_block.nanosleep.rmtp = rmtp;
- return hrtimer_nanosleep(&t, flags & TIMER_ABSTIME ?
+ texp = timespec64_to_ktime(t);
+ if (flags & TIMER_ABSTIME)
+ texp = timens_ktime_to_host(which_clock, texp);
+ return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ?
HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
which_clock);
}
#ifdef CONFIG_COMPAT
COMPAT_SYS_NI(timer_create);
+#endif
+
+#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA)
COMPAT_SYS_NI(getitimer);
COMPAT_SYS_NI(setitimer);
#endif
@@ -212,6 +222,7 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags,
struct old_timespec32 __user *, rmtp)
{
struct timespec64 t;
+ ktime_t texp;
switch (which_clock) {
case CLOCK_REALTIME:
@@ -230,7 +241,10 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags,
rmtp = NULL;
current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE;
current->restart_block.nanosleep.compat_rmtp = rmtp;
- return hrtimer_nanosleep(&t, flags & TIMER_ABSTIME ?
+ texp = timespec64_to_ktime(t);
+ if (flags & TIMER_ABSTIME)
+ texp = timens_ktime_to_host(which_clock, texp);
+ return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ?
HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
which_clock);
}
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 0ec5b7a1d769..ff0eb30de346 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -30,6 +30,7 @@
#include <linux/hashtable.h>
#include <linux/compat.h>
#include <linux/nospec.h>
+#include <linux/time_namespace.h>
#include "timekeeping.h"
#include "posix-timers.h"
@@ -165,12 +166,17 @@ static inline void unlock_timer(struct k_itimer *timr, unsigned long flags)
}
/* Get clock_realtime */
-static int posix_clock_realtime_get(clockid_t which_clock, struct timespec64 *tp)
+static int posix_get_realtime_timespec(clockid_t which_clock, struct timespec64 *tp)
{
ktime_get_real_ts64(tp);
return 0;
}
+static ktime_t posix_get_realtime_ktime(clockid_t which_clock)
+{
+ return ktime_get_real();
+}
+
/* Set clock_realtime */
static int posix_clock_realtime_set(const clockid_t which_clock,
const struct timespec64 *tp)
@@ -187,18 +193,25 @@ static int posix_clock_realtime_adj(const clockid_t which_clock,
/*
* Get monotonic time for posix timers
*/
-static int posix_ktime_get_ts(clockid_t which_clock, struct timespec64 *tp)
+static int posix_get_monotonic_timespec(clockid_t which_clock, struct timespec64 *tp)
{
ktime_get_ts64(tp);
+ timens_add_monotonic(tp);
return 0;
}
+static ktime_t posix_get_monotonic_ktime(clockid_t which_clock)
+{
+ return ktime_get();
+}
+
/*
* Get monotonic-raw time for posix timers
*/
static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp)
{
ktime_get_raw_ts64(tp);
+ timens_add_monotonic(tp);
return 0;
}
@@ -213,6 +226,7 @@ static int posix_get_monotonic_coarse(clockid_t which_clock,
struct timespec64 *tp)
{
ktime_get_coarse_ts64(tp);
+ timens_add_monotonic(tp);
return 0;
}
@@ -222,18 +236,29 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 *
return 0;
}
-static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp)
+static int posix_get_boottime_timespec(const clockid_t which_clock, struct timespec64 *tp)
{
ktime_get_boottime_ts64(tp);
+ timens_add_boottime(tp);
return 0;
}
-static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
+static ktime_t posix_get_boottime_ktime(const clockid_t which_clock)
+{
+ return ktime_get_boottime();
+}
+
+static int posix_get_tai_timespec(clockid_t which_clock, struct timespec64 *tp)
{
ktime_get_clocktai_ts64(tp);
return 0;
}
+static ktime_t posix_get_tai_ktime(clockid_t which_clock)
+{
+ return ktime_get_clocktai();
+}
+
static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec64 *tp)
{
tp->tv_sec = 0;
@@ -645,7 +670,6 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting)
{
const struct k_clock *kc = timr->kclock;
ktime_t now, remaining, iv;
- struct timespec64 ts64;
bool sig_none;
sig_none = timr->it_sigev_notify == SIGEV_NONE;
@@ -663,12 +687,7 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting)
return;
}
- /*
- * The timespec64 based conversion is suboptimal, but it's not
- * worth to implement yet another callback.
- */
- kc->clock_get(timr->it_clock, &ts64);
- now = timespec64_to_ktime(ts64);
+ now = kc->clock_get_ktime(timr->it_clock);
/*
* When a requeue is pending or this is a SIGEV_NONE timer move the
@@ -781,7 +800,7 @@ static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires,
* Posix magic: Relative CLOCK_REALTIME timers are not affected by
* clock modifications, so they become CLOCK_MONOTONIC based under the
* hood. See hrtimer_init(). Update timr->kclock, so the generic
- * functions which use timr->kclock->clock_get() work.
+ * functions which use timr->kclock->clock_get_*() work.
*
* Note: it_clock stays unmodified, because the next timer_set() might
* use ABSTIME, so it needs to switch back.
@@ -866,6 +885,8 @@ int common_timer_set(struct k_itimer *timr, int flags,
timr->it_interval = timespec64_to_ktime(new_setting->it_interval);
expires = timespec64_to_ktime(new_setting->it_value);
+ if (flags & TIMER_ABSTIME)
+ expires = timens_ktime_to_host(timr->it_clock, expires);
sigev_none = timr->it_sigev_notify == SIGEV_NONE;
kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none);
@@ -1067,7 +1088,7 @@ SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
if (!kc)
return -EINVAL;
- error = kc->clock_get(which_clock, &kernel_tp);
+ error = kc->clock_get_timespec(which_clock, &kernel_tp);
if (!error && put_timespec64(&kernel_tp, tp))
error = -EFAULT;
@@ -1149,7 +1170,7 @@ SYSCALL_DEFINE2(clock_gettime32, clockid_t, which_clock,
if (!kc)
return -EINVAL;
- err = kc->clock_get(which_clock, &ts);
+ err = kc->clock_get_timespec(which_clock, &ts);
if (!err && put_old_timespec32(&ts, tp))
err = -EFAULT;
@@ -1200,7 +1221,22 @@ SYSCALL_DEFINE2(clock_getres_time32, clockid_t, which_clock,
static int common_nsleep(const clockid_t which_clock, int flags,
const struct timespec64 *rqtp)
{
- return hrtimer_nanosleep(rqtp, flags & TIMER_ABSTIME ?
+ ktime_t texp = timespec64_to_ktime(*rqtp);
+
+ return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ?
+ HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
+ which_clock);
+}
+
+static int common_nsleep_timens(const clockid_t which_clock, int flags,
+ const struct timespec64 *rqtp)
+{
+ ktime_t texp = timespec64_to_ktime(*rqtp);
+
+ if (flags & TIMER_ABSTIME)
+ texp = timens_ktime_to_host(which_clock, texp);
+
+ return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ?
HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
which_clock);
}
@@ -1261,7 +1297,8 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags,
static const struct k_clock clock_realtime = {
.clock_getres = posix_get_hrtimer_res,
- .clock_get = posix_clock_realtime_get,
+ .clock_get_timespec = posix_get_realtime_timespec,
+ .clock_get_ktime = posix_get_realtime_ktime,
.clock_set = posix_clock_realtime_set,
.clock_adj = posix_clock_realtime_adj,
.nsleep = common_nsleep,
@@ -1279,8 +1316,9 @@ static const struct k_clock clock_realtime = {
static const struct k_clock clock_monotonic = {
.clock_getres = posix_get_hrtimer_res,
- .clock_get = posix_ktime_get_ts,
- .nsleep = common_nsleep,
+ .clock_get_timespec = posix_get_monotonic_timespec,
+ .clock_get_ktime = posix_get_monotonic_ktime,
+ .nsleep = common_nsleep_timens,
.timer_create = common_timer_create,
.timer_set = common_timer_set,
.timer_get = common_timer_get,
@@ -1295,22 +1333,23 @@ static const struct k_clock clock_monotonic = {
static const struct k_clock clock_monotonic_raw = {
.clock_getres = posix_get_hrtimer_res,
- .clock_get = posix_get_monotonic_raw,
+ .clock_get_timespec = posix_get_monotonic_raw,
};
static const struct k_clock clock_realtime_coarse = {
.clock_getres = posix_get_coarse_res,
- .clock_get = posix_get_realtime_coarse,
+ .clock_get_timespec = posix_get_realtime_coarse,
};
static const struct k_clock clock_monotonic_coarse = {
.clock_getres = posix_get_coarse_res,
- .clock_get = posix_get_monotonic_coarse,
+ .clock_get_timespec = posix_get_monotonic_coarse,
};
static const struct k_clock clock_tai = {
.clock_getres = posix_get_hrtimer_res,
- .clock_get = posix_get_tai,
+ .clock_get_ktime = posix_get_tai_ktime,
+ .clock_get_timespec = posix_get_tai_timespec,
.nsleep = common_nsleep,
.timer_create = common_timer_create,
.timer_set = common_timer_set,
@@ -1326,8 +1365,9 @@ static const struct k_clock clock_tai = {
static const struct k_clock clock_boottime = {
.clock_getres = posix_get_hrtimer_res,
- .clock_get = posix_get_boottime,
- .nsleep = common_nsleep,
+ .clock_get_ktime = posix_get_boottime_ktime,
+ .clock_get_timespec = posix_get_boottime_timespec,
+ .nsleep = common_nsleep_timens,
.timer_create = common_timer_create,
.timer_set = common_timer_set,
.timer_get = common_timer_get,
diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h
index 897c29e162b9..f32a2ebba9b8 100644
--- a/kernel/time/posix-timers.h
+++ b/kernel/time/posix-timers.h
@@ -6,8 +6,11 @@ struct k_clock {
struct timespec64 *tp);
int (*clock_set)(const clockid_t which_clock,
const struct timespec64 *tp);
- int (*clock_get)(const clockid_t which_clock,
- struct timespec64 *tp);
+ /* Returns the clock value in the current time namespace. */
+ int (*clock_get_timespec)(const clockid_t which_clock,
+ struct timespec64 *tp);
+ /* Returns the clock value in the root time namespace. */
+ ktime_t (*clock_get_ktime)(const clockid_t which_clock);
int (*clock_adj)(const clockid_t which_clock, struct __kernel_timex *tx);
int (*timer_create)(struct k_itimer *timer);
int (*nsleep)(const clockid_t which_clock, int flags,
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index dbd69052eaa6..e4332e3e2d56 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -169,14 +169,15 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
{
u64 res, wrap, new_mask, new_epoch, cyc, ns;
u32 new_mult, new_shift;
- unsigned long r;
+ unsigned long r, flags;
char r_unit;
struct clock_read_data rd;
if (cd.rate > rate)
return;
- WARN_ON(!irqs_disabled());
+ /* Cannot register a sched_clock with interrupts on */
+ local_irq_save(flags);
/* Calculate the mult/shift to convert counter ticks to ns. */
clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
@@ -233,6 +234,8 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
enable_sched_clock_irqtime();
+ local_irq_restore(flags);
+
pr_debug("Registered %pS as sched_clock source\n", read);
}
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 59225b484e4e..7e5d3524e924 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -11,6 +11,7 @@
#include <linux/err.h>
#include <linux/hrtimer.h>
#include <linux/interrupt.h>
+#include <linux/nmi.h>
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
@@ -558,6 +559,7 @@ void tick_unfreeze(void)
trace_suspend_resume(TPS("timekeeping_freeze"),
smp_processor_id(), false);
} else {
+ touch_softlockup_watchdog();
tick_resume_local();
}
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 8b192e67aabc..a792d21cac64 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -58,8 +58,9 @@ static void tick_do_update_jiffies64(ktime_t now)
/*
* Do a quick check without holding jiffies_lock:
+ * The READ_ONCE() pairs with two updates done later in this function.
*/
- delta = ktime_sub(now, last_jiffies_update);
+ delta = ktime_sub(now, READ_ONCE(last_jiffies_update));
if (delta < tick_period)
return;
@@ -70,8 +71,9 @@ static void tick_do_update_jiffies64(ktime_t now)
if (delta >= tick_period) {
delta = ktime_sub(delta, tick_period);
- last_jiffies_update = ktime_add(last_jiffies_update,
- tick_period);
+ /* Pairs with the lockless read in this function. */
+ WRITE_ONCE(last_jiffies_update,
+ ktime_add(last_jiffies_update, tick_period));
/* Slow path for long timeouts */
if (unlikely(delta >= tick_period)) {
@@ -79,8 +81,10 @@ static void tick_do_update_jiffies64(ktime_t now)
ticks = ktime_divns(delta, incr);
- last_jiffies_update = ktime_add_ns(last_jiffies_update,
- incr * ticks);
+ /* Pairs with the lockless read in this function. */
+ WRITE_ONCE(last_jiffies_update,
+ ktime_add_ns(last_jiffies_update,
+ incr * ticks));
}
do_timer(++ticks);
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 5ee0f7709410..9577c89179cd 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -28,11 +28,6 @@ static inline void update_vdso_data(struct vdso_data *vdata,
vdata[CS_RAW].mult = tk->tkr_raw.mult;
vdata[CS_RAW].shift = tk->tkr_raw.shift;
- /* CLOCK_REALTIME */
- vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME];
- vdso_ts->sec = tk->xtime_sec;
- vdso_ts->nsec = tk->tkr_mono.xtime_nsec;
-
/* CLOCK_MONOTONIC */
vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC];
vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
@@ -70,12 +65,6 @@ static inline void update_vdso_data(struct vdso_data *vdata,
vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_TAI];
vdso_ts->sec = tk->xtime_sec + (s64)tk->tai_offset;
vdso_ts->nsec = tk->tkr_mono.xtime_nsec;
-
- /*
- * Read without the seqlock held by clock_getres().
- * Note: No need to have a second copy.
- */
- WRITE_ONCE(vdata[CS_HRES_COARSE].hrtimer_res, hrtimer_resolution);
}
void update_vsyscall(struct timekeeper *tk)
@@ -84,20 +73,17 @@ void update_vsyscall(struct timekeeper *tk)
struct vdso_timestamp *vdso_ts;
u64 nsec;
- if (__arch_update_vdso_data()) {
- /*
- * Some architectures might want to skip the update of the
- * data page.
- */
- return;
- }
-
/* 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_REALTIME also required for time() */
+ vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME];
+ vdso_ts->sec = tk->xtime_sec;
+ vdso_ts->nsec = tk->tkr_mono.xtime_nsec;
+
/* CLOCK_REALTIME_COARSE */
vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE];
vdso_ts->sec = tk->xtime_sec;
@@ -110,7 +96,18 @@ void update_vsyscall(struct timekeeper *tk)
nsec = nsec + tk->wall_to_monotonic.tv_nsec;
vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec);
- update_vdso_data(vdata, tk);
+ /*
+ * Read without the seqlock held by clock_getres().
+ * Note: No need to have a second copy.
+ */
+ WRITE_ONCE(vdata[CS_HRES_COARSE].hrtimer_res, hrtimer_resolution);
+
+ /*
+ * Architectures can opt out of updating the high resolution part
+ * of the VDSO.
+ */
+ if (__arch_update_vdso_data())
+ update_vdso_data(vdata, tk);
__arch_update_vsyscall(vdata, tk);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.