* [RFC][PATCH 1/2] timer: Convert timer_slack_ns from unsigned long to u64
2016-02-08 23:23 [RFC][PATCH 0/2] /proc/<pid>/timerslack_ns & changes to extend timer_slack_ns to u64 on 32bit systems John Stultz
@ 2016-02-08 23:23 ` John Stultz
2016-02-08 23:23 ` [RFC][PATCH 2/2] proc: Add /proc/<pid>/timerslack_ns interface John Stultz
1 sibling, 0 replies; 3+ messages in thread
From: John Stultz @ 2016-02-08 23:23 UTC (permalink / raw)
To: lkml
Cc: John Stultz, Arjan van de Ven, Thomas Gleixner, Oren Laadan,
Ruchi Kandoi, Rom Lemarchand, Kees Cook, Andrew Morton,
Android Kernel Team
The timer_slack_ns value in the task struct is currently a
unsigned long. This means that on 32bit applications, the
maximum slack is just over 4 seconds. However, on 64bit
machines, its much much larger (~500 years).
This disparity could make application development a little
difficult, so this patch extends the timer_slack_ns entry
(as well as the default_slack) to a u64. This means both 32bit
and 64bit systems have the same effective internal slack range.
Now the existing ABI via PR_GET_TIMERSLACK and PR_SET_TIMERSLACK
specify the interface as a unsigned long, so we preserve that
limitation on 32bit systems, where SET_TIMERSLACK can only set
the slack to a unsigned long value, and GET_TIMERSLACK will
return ULONG_MAX if the slack is actually larger then what can
be stored by an unsigned long.
This patch also modifies hrtimer functions which specified the
slack delta as a unsigned long.
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Oren Laadan <orenl@cellrox.com>
Cc: Ruchi Kandoi <kandoiruchi@google.com>
Cc: Rom Lemarchand <romlem@android.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Android Kernel Team <kernel-team@android.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
fs/eventpoll.c | 2 +-
fs/select.c | 8 ++++----
include/linux/freezer.h | 2 +-
include/linux/hrtimer.h | 12 +++++++-----
include/linux/poll.h | 2 +-
include/linux/sched.h | 4 ++--
kernel/sys.c | 5 ++++-
kernel/time/hrtimer.c | 8 ++++----
kernel/time/timer.c | 4 ++--
9 files changed, 26 insertions(+), 21 deletions(-)
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index ae1dbcf..344cd6d 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1596,7 +1596,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
{
int res = 0, eavail, timed_out = 0;
unsigned long flags;
- long slack = 0;
+ u64 slack = 0;
wait_queue_t wait;
ktime_t expires, *to = NULL;
diff --git a/fs/select.c b/fs/select.c
index 79d0d49..8692939 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -70,9 +70,9 @@ static long __estimate_accuracy(struct timespec *tv)
return slack;
}
-long select_estimate_accuracy(struct timespec *tv)
+u64 select_estimate_accuracy(struct timespec *tv)
{
- unsigned long ret;
+ u64 ret;
struct timespec now;
/*
@@ -402,7 +402,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
struct poll_wqueues table;
poll_table *wait;
int retval, i, timed_out = 0;
- unsigned long slack = 0;
+ u64 slack = 0;
unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
unsigned long busy_end = 0;
@@ -784,7 +784,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
poll_table* pt = &wait->pt;
ktime_t expire, *to = NULL;
int timed_out = 0, count = 0;
- unsigned long slack = 0;
+ u64 slack = 0;
unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
unsigned long busy_end = 0;
diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index 6b7fd9c..dd03e83 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -231,7 +231,7 @@ static inline long freezable_schedule_timeout_killable_unsafe(long timeout)
* call this with locks held.
*/
static inline int freezable_schedule_hrtimeout_range(ktime_t *expires,
- unsigned long delta, const enum hrtimer_mode mode)
+ u64 delta, const enum hrtimer_mode mode)
{
int __retval;
freezer_do_not_count();
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 2ead22d..c98c653 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -220,7 +220,7 @@ static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time
timer->node.expires = ktime_add_safe(time, delta);
}
-static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, unsigned long delta)
+static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, u64 delta)
{
timer->_softexpires = time;
timer->node.expires = ktime_add_safe(time, ns_to_ktime(delta));
@@ -378,7 +378,7 @@ static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { }
/* Basic timer operations: */
extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
- unsigned long range_ns, const enum hrtimer_mode mode);
+ u64 range_ns, const enum hrtimer_mode mode);
/**
* hrtimer_start - (re)start an hrtimer on the current CPU
@@ -399,7 +399,7 @@ extern int hrtimer_try_to_cancel(struct hrtimer *timer);
static inline void hrtimer_start_expires(struct hrtimer *timer,
enum hrtimer_mode mode)
{
- unsigned long delta;
+ u64 delta;
ktime_t soft, hard;
soft = hrtimer_get_softexpires(timer);
hard = hrtimer_get_expires(timer);
@@ -477,10 +477,12 @@ extern long hrtimer_nanosleep_restart(struct restart_block *restart_block);
extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
struct task_struct *tsk);
-extern int schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
+extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta,
const enum hrtimer_mode mode);
extern int schedule_hrtimeout_range_clock(ktime_t *expires,
- unsigned long delta, const enum hrtimer_mode mode, int clock);
+ u64 delta,
+ const enum hrtimer_mode mode,
+ int clock);
extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
/* Soft interrupt function to run the hrtimer queues: */
diff --git a/include/linux/poll.h b/include/linux/poll.h
index c08386f..9fb4f40 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -96,7 +96,7 @@ extern void poll_initwait(struct poll_wqueues *pwq);
extern void poll_freewait(struct poll_wqueues *pwq);
extern int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
ktime_t *expires, unsigned long slack);
-extern long select_estimate_accuracy(struct timespec *tv);
+extern u64 select_estimate_accuracy(struct timespec *tv);
static inline int poll_schedule(struct poll_wqueues *pwq, int state)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a10494a..1cc4a4f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1784,8 +1784,8 @@ struct task_struct {
* time slack values; these are used to round up poll() and
* select() etc timeout values. These are in nanoseconds.
*/
- unsigned long timer_slack_ns;
- unsigned long default_timer_slack_ns;
+ u64 timer_slack_ns;
+ u64 default_timer_slack_ns;
#ifdef CONFIG_KASAN
unsigned int kasan_depth;
diff --git a/kernel/sys.c b/kernel/sys.c
index 78947de..cf8ba54 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2169,7 +2169,10 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
error = perf_event_task_enable();
break;
case PR_GET_TIMERSLACK:
- error = current->timer_slack_ns;
+ if (current->timer_slack_ns > ULONG_MAX)
+ error = ULONG_MAX;
+ else
+ error = current->timer_slack_ns;
break;
case PR_SET_TIMERSLACK:
if (arg2 <= 0)
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index fa909f9..58a321c 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -979,7 +979,7 @@ static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim,
* relative (HRTIMER_MODE_REL)
*/
void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
- unsigned long delta_ns, const enum hrtimer_mode mode)
+ u64 delta_ns, const enum hrtimer_mode mode)
{
struct hrtimer_clock_base *base, *new_base;
unsigned long flags;
@@ -1548,7 +1548,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
struct restart_block *restart;
struct hrtimer_sleeper t;
int ret = 0;
- unsigned long slack;
+ u64 slack;
slack = current->timer_slack_ns;
if (dl_task(current) || rt_task(current))
@@ -1724,7 +1724,7 @@ void __init hrtimers_init(void)
* @clock: timer clock, CLOCK_MONOTONIC or CLOCK_REALTIME
*/
int __sched
-schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
+schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
const enum hrtimer_mode mode, int clock)
{
struct hrtimer_sleeper t;
@@ -1792,7 +1792,7 @@ schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
*
* Returns 0 when the timer has expired otherwise -EINTR
*/
-int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
+int __sched schedule_hrtimeout_range(ktime_t *expires, u64 delta,
const enum hrtimer_mode mode)
{
return schedule_hrtimeout_range_clock(expires, delta, mode,
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index bbc5d11..d1798fa 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1698,10 +1698,10 @@ EXPORT_SYMBOL(msleep_interruptible);
static void __sched do_usleep_range(unsigned long min, unsigned long max)
{
ktime_t kmin;
- unsigned long delta;
+ u64 delta;
kmin = ktime_set(0, min * NSEC_PER_USEC);
- delta = (max - min) * NSEC_PER_USEC;
+ delta = (u64)(max - min) * NSEC_PER_USEC;
schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL);
}
--
1.9.1
^ permalink raw reply [flat|nested] 3+ messages in thread* [RFC][PATCH 2/2] proc: Add /proc/<pid>/timerslack_ns interface
2016-02-08 23:23 [RFC][PATCH 0/2] /proc/<pid>/timerslack_ns & changes to extend timer_slack_ns to u64 on 32bit systems John Stultz
2016-02-08 23:23 ` [RFC][PATCH 1/2] timer: Convert timer_slack_ns from unsigned long to u64 John Stultz
@ 2016-02-08 23:23 ` John Stultz
1 sibling, 0 replies; 3+ messages in thread
From: John Stultz @ 2016-02-08 23:23 UTC (permalink / raw)
To: lkml
Cc: John Stultz, Arjan van de Ven, Thomas Gleixner, Oren Laadan,
Ruchi Kandoi, Rom Lemarchand, Kees Cook, Andrew Morton,
Android Kernel Team
This patch provides a proc/PID/timerslack_ns interface which
exposes a task's timerslack value in nanoseconds and allows it
to be changed.
This allows power/performance management software to set timer
slack for other threads according to its policy for the thread
(such as when the thread is designated foreground vs. background
activity)
If the value written is non-zero, slack is set to that value.
Otherwise sets it to the default for the thread.
This interface checks that the calling task has permissions to
to use PTRACE_MODE_ATTACH_FSCREDS on the target task, so that we
can ensure arbitrary apps do not change the timer slack for other
apps.
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Oren Laadan <orenl@cellrox.com>
Cc: Ruchi Kandoi <kandoiruchi@google.com>
Cc: Rom Lemarchand <romlem@android.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Android Kernel Team <kernel-team@android.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
Documentation/filesystems/proc.txt | 18 ++++++++++
fs/proc/base.c | 69 ++++++++++++++++++++++++++++++++++++++
2 files changed, 87 insertions(+)
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index fde9fd0..047184a 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -43,6 +43,7 @@ Table of Contents
3.7 /proc/<pid>/task/<tid>/children - Information about task children
3.8 /proc/<pid>/fdinfo/<fd> - Information about opened file
3.9 /proc/<pid>/map_files - Information about memory mapped files
+ 3.10 /proc/<pid>/timerslack_ns - Task timerslack value
4 Configuring procfs
4.1 Mount options
@@ -1865,6 +1866,23 @@ time one can open(2) mappings from the listings of two processes and
comparing their inode numbers to figure out which anonymous memory areas
are actually shared.
+3.10 /proc/<pid>/timerslack_ns - Task timerslack value
+---------------------------------------------------------
+This file provides the value of the task's timerslack value in nanoseconds.
+This value specifies a amount of time that normal timers may be deferred
+in order to coalesce timers and avoid unnecessary wakeups.
+
+This allows a task's interactivity vs power consumption trade off to be
+adjusted.
+
+Writing 0 to the file will set the tasks timerslack to the default value.
+
+Valid values are from 0 - ULLONG_MAX
+
+An application setting the value must have PTRACE_MODE_ATTACH_FSCREDS level
+permissions on the task specified to change its timerslack_ns value.
+
+
------------------------------------------------------------------------------
Configuring procfs
------------------------------------------------------------------------------
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 4f764c2..d7c51ca 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2257,6 +2257,74 @@ static const struct file_operations proc_timers_operations = {
.release = seq_release_private,
};
+static ssize_t timerslack_ns_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *offset)
+{
+ struct inode *inode = file_inode(file);
+ struct task_struct *p;
+ char buffer[PROC_NUMBUF];
+ u64 slack_ns;
+ int err;
+
+ memset(buffer, 0, sizeof(buffer));
+ if (count > sizeof(buffer) - 1)
+ count = sizeof(buffer) - 1;
+
+ if (copy_from_user(buffer, buf, count))
+ return -EFAULT;
+
+ err = kstrtoull(strstrip(buffer), 10, &slack_ns);
+ if (err < 0)
+ return err;
+
+ p = get_proc_task(inode);
+ if (!p)
+ return -ESRCH;
+
+ if (ptrace_may_access(p, PTRACE_MODE_ATTACH_FSCREDS)) {
+ if (slack_ns == 0)
+ p->timer_slack_ns = p->default_timer_slack_ns;
+ else
+ p->timer_slack_ns = slack_ns;
+ } else
+ count = -EINVAL;
+
+ put_task_struct(p);
+
+ return count;
+}
+
+static int timerslack_ns_show(struct seq_file *m, void *v)
+{
+ struct inode *inode = m->private;
+ struct task_struct *p;
+
+ p = get_proc_task(inode);
+ if (!p)
+ return -ESRCH;
+
+ task_lock(p);
+ seq_printf(m, "%llu\n", p->timer_slack_ns);
+ task_unlock(p);
+
+ put_task_struct(p);
+
+ return 0;
+}
+
+static int timerslack_ns_open(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, timerslack_ns_show, inode);
+}
+
+static const struct file_operations proc_pid_set_timerslack_ns_operations = {
+ .open = timerslack_ns_open,
+ .read = seq_read,
+ .write = timerslack_ns_write,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
static int proc_pident_instantiate(struct inode *dir,
struct dentry *dentry, struct task_struct *task, const void *ptr)
{
@@ -2831,6 +2899,7 @@ static const struct pid_entry tgid_base_stuff[] = {
#ifdef CONFIG_CHECKPOINT_RESTORE
REG("timers", S_IRUGO, proc_timers_operations),
#endif
+ REG("timerslack_ns", S_IRUGO|S_IWUSR, proc_pid_set_timerslack_ns_operations),
};
static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)
--
1.9.1
^ permalink raw reply [flat|nested] 3+ messages in thread