Message-Id: <00000140bc5efaac-578e385d-d396-4b5f-9561-2baa4d2caa54-000000@email.amazonses.com>
Date:	Mon, 26 Aug 2013 20:44:35 +0000
From:	Christoph Lameter <cl@...ux.com>
To:	Tejun Heo <tj@...nel.org>
Cc:	linux-kernel@...r.kernel.org
Subject: [guv v2 05/31] time: Replace __get_cpu_var uses

__get_cpu_var() is used for multiple purposes in the kernel source. One of them is
address calculation via the form &__get_cpu_var(x). This calculates the address for
the instance of the percpu variable of the current processor based on an offset.

Others usage cases are for storing and retrieving data from the current processors percpu area.
__get_cpu_var() can be used as an lvalue when writing data or on the right side of an assignment.

__get_cpu_var() is defined as :


#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))



__get_cpu_var() always only does a address determination. However, store and retrieve operations
could use a segment prefix (or global register on other platforms) to avoid the address calculation.

this_cpu_write() and this_cpu_read() can directly take an offset into a percpu area and use
optimized assembly code to read and write per cpu variables.


This patch converts __get_cpu_var into either and explicit address calculation using this_cpu_ptr()
or into a use of this_cpu operations that use the offset. Thereby address calcualtions are avoided
and less registers are used when code is generated.

At the end of the patchset all uses of __get_cpu_var have been removed so the macro is removed too.

The patchset includes passes over all arches as well. Once these operations are used throughout then
specialized macros can be defined in non -x86 arches as well in order to optimize per cpu access by
f.e. using a global register that may be set to the per cpu base.




Transformations done to __get_cpu_var()


1. Determine the address of the percpu instance of the current processor.

	DEFINE_PER_CPU(int, y);
	int *x = &__get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(&y);


2. Same as #1 but this time an array structure is involved.

	DEFINE_PER_CPU(int, y[20]);
	int *x = __get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(y);


3. Retrieve the content of the current processors instance of a per cpu variable.

	DEFINE_PER_CPU(int, u);
	int x = __get_cpu_var(y)

   Converts to

	int x = __this_cpu_read(y);


4. Retrieve the content of a percpu struct

	DEFINE_PER_CPU(struct mystruct, y);
	struct mystruct x = __get_cpu_var(y);

   Converts to

	memcpy(this_cpu_ptr(&y), x, sizeof(x));


5. Assignment to a per cpu variable

	DEFINE_PER_CPU(int, y)
	__get_cpu_var(y) = x;

   Converts to

	this_cpu_write(y, x);


6. Increment/Decrement etc of a per cpu variable

	DEFINE_PER_CPU(int, y);
	__get_cpu_var(y)++

   Converts to

	this_cpu_inc(y)

Signed-off-by: Christoph Lameter <cl@...ux.com>

Index: linux/kernel/hrtimer.c
===================================================================
--- linux.orig/kernel/hrtimer.c	2013-08-26 14:19:14.000000000 -0500
+++ linux/kernel/hrtimer.c	2013-08-26 14:21:24.540227691 -0500
@@ -597,7 +597,7 @@ hrtimer_force_reprogram(struct hrtimer_c
 static int hrtimer_reprogram(struct hrtimer *timer,
 			     struct hrtimer_clock_base *base)
 {
-	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
 	ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
 	int res;
 
@@ -680,7 +680,7 @@ static inline ktime_t hrtimer_update_bas
  */
 static void retrigger_next_event(void *arg)
 {
-	struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases);
+	struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
 	if (!hrtimer_hres_active())
 		return;
@@ -954,7 +954,7 @@ remove_hrtimer(struct hrtimer *timer, st
 		 */
 		debug_deactivate(timer);
 		timer_stats_hrtimer_clear_start_info(timer);
-		reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
+		reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases);
 		/*
 		 * We must preserve the CALLBACK state flag here,
 		 * otherwise we could move the timer base in
@@ -1009,7 +1009,7 @@ int __hrtimer_start_range_ns(struct hrti
 	 *
 	 * XXX send_remote_softirq() ?
 	 */
-	if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)
+	if (leftmost && new_base->cpu_base == this_cpu_ptr(&hrtimer_bases)
 		&& hrtimer_enqueue_reprogram(timer, new_base)) {
 		if (wakeup) {
 			/*
@@ -1142,7 +1142,7 @@ EXPORT_SYMBOL_GPL(hrtimer_get_remaining)
  */
 ktime_t hrtimer_get_next_event(void)
 {
-	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
 	struct hrtimer_clock_base *base = cpu_base->clock_base;
 	ktime_t delta, mindelta = { .tv64 = KTIME_MAX };
 	unsigned long flags;
@@ -1183,7 +1183,7 @@ static void __hrtimer_init(struct hrtime
 
 	memset(timer, 0, sizeof(struct hrtimer));
 
-	cpu_base = &__raw_get_cpu_var(hrtimer_bases);
+	cpu_base = __this_cpu_ptr(&hrtimer_bases);
 
 	if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
 		clock_id = CLOCK_MONOTONIC;
@@ -1226,7 +1226,7 @@ int hrtimer_get_res(const clockid_t whic
 	struct hrtimer_cpu_base *cpu_base;
 	int base = hrtimer_clockid_to_base(which_clock);
 
-	cpu_base = &__raw_get_cpu_var(hrtimer_bases);
+	cpu_base = __this_cpu_ptr(&hrtimer_bases);
 	*tp = ktime_to_timespec(cpu_base->clock_base[base].resolution);
 
 	return 0;
@@ -1281,7 +1281,7 @@ static void __run_hrtimer(struct hrtimer
  */
 void hrtimer_interrupt(struct clock_event_device *dev)
 {
-	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
 	ktime_t expires_next, now, entry_time, delta;
 	int i, retries = 0;
 
@@ -1415,7 +1415,7 @@ static void __hrtimer_peek_ahead_timers(
 	if (!hrtimer_hres_active())
 		return;
 
-	td = &__get_cpu_var(tick_cpu_device);
+	td = this_cpu_ptr(&tick_cpu_device);
 	if (td && td->evtdev)
 		hrtimer_interrupt(td->evtdev);
 }
@@ -1479,7 +1479,7 @@ void hrtimer_run_pending(void)
 void hrtimer_run_queues(void)
 {
 	struct timerqueue_node *node;
-	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
 	struct hrtimer_clock_base *base;
 	int index, gettime = 1;
 
@@ -1717,7 +1717,7 @@ static void migrate_hrtimers(int scpu)
 
 	local_irq_disable();
 	old_base = &per_cpu(hrtimer_bases, scpu);
-	new_base = &__get_cpu_var(hrtimer_bases);
+	new_base = this_cpu_ptr(&hrtimer_bases);
 	/*
 	 * The caller is globally serialized and nobody else
 	 * takes two locks at once, deadlock is not possible.
Index: linux/kernel/irq_work.c
===================================================================
--- linux.orig/kernel/irq_work.c	2013-08-26 14:19:14.000000000 -0500
+++ linux/kernel/irq_work.c	2013-08-26 14:21:24.540227691 -0500
@@ -70,7 +70,7 @@ void irq_work_queue(struct irq_work *wor
 	/* Queue the entry and raise the IPI if needed. */
 	preempt_disable();
 
-	llist_add(&work->llnode, &__get_cpu_var(irq_work_list));
+	llist_add(&work->llnode, this_cpu_ptr(&irq_work_list));
 
 	/*
 	 * If the work is not "lazy" or the tick is stopped, raise the irq
@@ -90,7 +90,7 @@ bool irq_work_needs_cpu(void)
 {
 	struct llist_head *this_list;
 
-	this_list = &__get_cpu_var(irq_work_list);
+	this_list = this_cpu_ptr(&irq_work_list);
 	if (llist_empty(this_list))
 		return false;
 
@@ -115,7 +115,7 @@ static void __irq_work_run(void)
 	__this_cpu_write(irq_work_raised, 0);
 	barrier();
 
-	this_list = &__get_cpu_var(irq_work_list);
+	this_list = this_cpu_ptr(&irq_work_list);
 	if (llist_empty(this_list))
 		return;
 
Index: linux/kernel/sched/clock.c
===================================================================
--- linux.orig/kernel/sched/clock.c	2013-08-26 14:19:14.000000000 -0500
+++ linux/kernel/sched/clock.c	2013-08-26 14:21:24.540227691 -0500
@@ -94,7 +94,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(str
 
 static inline struct sched_clock_data *this_scd(void)
 {
-	return &__get_cpu_var(sched_clock_data);
+	return this_cpu_ptr(&sched_clock_data);
 }
 
 static inline struct sched_clock_data *cpu_sdc(int cpu)
Index: linux/kernel/softirq.c
===================================================================
--- linux.orig/kernel/softirq.c	2013-08-26 14:19:14.000000000 -0500
+++ linux/kernel/softirq.c	2013-08-26 14:21:24.540227691 -0500
@@ -466,7 +466,7 @@ static void tasklet_action(struct softir
 	local_irq_disable();
 	list = __this_cpu_read(tasklet_vec.head);
 	__this_cpu_write(tasklet_vec.head, NULL);
-	__this_cpu_write(tasklet_vec.tail, &__get_cpu_var(tasklet_vec).head);
+	__this_cpu_write(tasklet_vec.tail, this_cpu_ptr(&tasklet_vec.head));
 	local_irq_enable();
 
 	while (list) {
@@ -501,7 +501,7 @@ static void tasklet_hi_action(struct sof
 	local_irq_disable();
 	list = __this_cpu_read(tasklet_hi_vec.head);
 	__this_cpu_write(tasklet_hi_vec.head, NULL);
-	__this_cpu_write(tasklet_hi_vec.tail, &__get_cpu_var(tasklet_hi_vec).head);
+	__this_cpu_write(tasklet_hi_vec.tail, this_cpu_ptr(&tasklet_hi_vec.head));
 	local_irq_enable();
 
 	while (list) {
@@ -618,7 +618,7 @@ EXPORT_PER_CPU_SYMBOL(softirq_work_list)
 
 static void __local_trigger(struct call_single_data *cp, int softirq)
 {
-	struct list_head *head = &__get_cpu_var(softirq_work_list[softirq]);
+	struct list_head *head = this_cpu_ptr(&softirq_work_list[softirq]);
 
 	list_add_tail(&cp->list, head);
 
@@ -718,7 +718,7 @@ static int remote_softirq_cpu_notify(str
 			if (list_empty(head))
 				continue;
 
-			local_head = &__get_cpu_var(softirq_work_list[i]);
+			local_head = this_cpu_ptr(&softirq_work_list[i]);
 			list_splice_init(head, local_head);
 			raise_softirq_irqoff(i);
 		}
Index: linux/kernel/time/tick-common.c
===================================================================
--- linux.orig/kernel/time/tick-common.c	2013-08-26 14:19:14.000000000 -0500
+++ linux/kernel/time/tick-common.c	2013-08-26 14:21:24.544227649 -0500
@@ -208,7 +208,7 @@ static void tick_setup_device(struct tic
 
 void tick_install_replacement(struct clock_event_device *newdev)
 {
-	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 	int cpu = smp_processor_id();
 
 	clockevents_exchange_device(td->evtdev, newdev);
@@ -358,14 +358,14 @@ void tick_shutdown(unsigned int *cpup)
 
 void tick_suspend(void)
 {
-	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 
 	clockevents_shutdown(td->evtdev);
 }
 
 void tick_resume(void)
 {
-	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 	int broadcast = tick_resume_broadcast();
 
 	clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME);
Index: linux/kernel/time/tick-oneshot.c
===================================================================
--- linux.orig/kernel/time/tick-oneshot.c	2013-08-26 14:19:14.000000000 -0500
+++ linux/kernel/time/tick-oneshot.c	2013-08-26 14:21:24.544227649 -0500
@@ -59,7 +59,7 @@ void tick_setup_oneshot(struct clock_eve
  */
 int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
 {
-	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 	struct clock_event_device *dev = td->evtdev;
 
 	if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) ||
Index: linux/kernel/time/tick-sched.c
===================================================================
--- linux.orig/kernel/time/tick-sched.c	2013-08-26 14:19:14.000000000 -0500
+++ linux/kernel/time/tick-sched.c	2013-08-26 14:21:24.540227691 -0500
@@ -199,7 +199,7 @@ static void tick_nohz_restart_sched_tick
  */
 void tick_nohz_full_check(void)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
 	if (tick_nohz_full_cpu(smp_processor_id())) {
 		if (ts->tick_stopped && !is_idle_task(current)) {
@@ -225,7 +225,7 @@ static DEFINE_PER_CPU(struct irq_work, n
 void tick_nohz_full_kick(void)
 {
 	if (tick_nohz_full_cpu(smp_processor_id()))
-		irq_work_queue(&__get_cpu_var(nohz_full_kick_work));
+		irq_work_queue(this_cpu_ptr(&nohz_full_kick_work));
 }
 
 static void nohz_full_kick_ipi(void *info)
@@ -536,7 +536,7 @@ static ktime_t tick_nohz_stop_sched_tick
 	unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
 	ktime_t last_update, expires, ret = { .tv64 = 0 };
 	unsigned long rcu_delta_jiffies;
-	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 	u64 time_delta;
 
 	/* Read jiffies and the time when jiffies were updated last */
@@ -801,7 +801,7 @@ void tick_nohz_idle_enter(void)
 
 	local_irq_disable();
 
-	ts = &__get_cpu_var(tick_cpu_sched);
+	ts = this_cpu_ptr(&tick_cpu_sched);
 	/*
 	 * set ts->inidle unconditionally. even if the system did not
 	 * switch to nohz mode the cpu frequency governers rely on the
@@ -824,7 +824,7 @@ EXPORT_SYMBOL_GPL(tick_nohz_idle_enter);
  */
 void tick_nohz_irq_exit(void)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
 	if (ts->inidle)
 		__tick_nohz_idle_enter(ts);
@@ -839,7 +839,7 @@ void tick_nohz_irq_exit(void)
  */
 ktime_t tick_nohz_get_sleep_length(void)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
 	return ts->sleep_length;
 }
@@ -953,7 +953,7 @@ static int tick_nohz_reprogram(struct ti
  */
 static void tick_nohz_handler(struct clock_event_device *dev)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 	struct pt_regs *regs = get_irq_regs();
 	ktime_t now = ktime_get();
 
@@ -973,7 +973,7 @@ static void tick_nohz_handler(struct clo
  */
 static void tick_nohz_switch_to_nohz(void)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 	ktime_t next;
 
 	if (!tick_nohz_enabled)
@@ -1111,7 +1111,7 @@ early_param("skew_tick", skew_tick);
  */
 void tick_setup_sched_timer(void)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 	ktime_t now = ktime_get();
 
 	/*
@@ -1178,7 +1178,7 @@ void tick_clock_notify(void)
  */
 void tick_oneshot_notify(void)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
 	set_bit(0, &ts->check_clocks);
 }
@@ -1193,7 +1193,7 @@ void tick_oneshot_notify(void)
  */
 int tick_check_oneshot_change(int allow_nohz)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
 	if (!test_and_clear_bit(0, &ts->check_clocks))
 		return 0;
Index: linux/kernel/timer.c
===================================================================
--- linux.orig/kernel/timer.c	2013-08-26 14:19:14.000000000 -0500
+++ linux/kernel/timer.c	2013-08-26 14:21:24.544227649 -0500
@@ -621,7 +621,7 @@ static inline void debug_assert_init(str
 static void do_init_timer(struct timer_list *timer, unsigned int flags,
 			  const char *name, struct lock_class_key *key)
 {
-	struct tvec_base *base = __raw_get_cpu_var(tvec_bases);
+	struct tvec_base *base = __this_cpu_read(tvec_bases);
 
 	timer->entry.next = NULL;
 	timer->base = (void *)((unsigned long)base | flags);

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists