Patches contributed by Eötvös Lorand University


commit bc26c31d446bc9c24cd6f7003777a05fe268ae48
Author: Ingo Molnar <mingo@elte.hu>
Date:   Sun Feb 22 12:17:36 2009 +0100

    time: ntp: refactor up ntp_update_frequency()
    
    Impact: cleanup, no functionality changed
    
    Change ntp_update_frequency() from a hard to follow code
    flow that uses global variables as temporaries, to a clean
    input+output flow.
    
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 7d281d9fbe30..f1abad738579 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -83,10 +83,8 @@ static long			ntp_tick_adj;
  */
 static void ntp_update_frequency(void)
 {
-	u64 prev_base;
 	u64 second_length;
-
-	prev_base = tick_length_base;
+	u64 new_base;
 
 	second_length		 = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ)
 						<< NTP_SCALE_SHIFT;
@@ -94,16 +92,15 @@ static void ntp_update_frequency(void)
 	second_length		+= (s64)ntp_tick_adj << NTP_SCALE_SHIFT;
 	second_length		+= time_freq;
 
-	tick_length_base	 = second_length;
-
 	tick_nsec		 = div_u64(second_length, HZ) >> NTP_SCALE_SHIFT;
-	tick_length_base	 = div_u64(tick_length_base, NTP_INTERVAL_FREQ);
+	new_base		 = div_u64(second_length, NTP_INTERVAL_FREQ);
 
 	/*
 	 * Don't wait for the next second_overflow, apply
-	 * the change to the tick length immediately
+	 * the change to the tick length immediately:
 	 */
-	tick_length		+= tick_length_base - prev_base;
+	tick_length		+= new_base - tick_length_base;
+	tick_length_base	 = new_base;
 }
 
 static void ntp_update_offset(long offset)

commit 9ce616aaefcb9309cb9c49a36310ebda6061b98b
Author: Ingo Molnar <mingo@elte.hu>
Date:   Sun Feb 22 12:42:59 2009 +0100

    time: ntp: clean up ntp_update_frequency()
    
    Impact: cleanup, no functionality changed
    
    Prepare a refactoring of ntp_update_frequency().
    
    kernel/time/ntp.o:
    
       text    data     bss     dec     hex filename
       2504     114     136    2754     ac2 ntp.o.before
       2504     114     136    2754     ac2 ntp.o.after
    
    md5:
       41f3009debc9b397d7394dd77d912f0a  ntp.o.before.asm
       41f3009debc9b397d7394dd77d912f0a  ntp.o.after.asm
    
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 2b758c935c65..7d281d9fbe30 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -77,24 +77,33 @@ static long			ntp_tick_adj;
  * NTP methods:
  */
 
+/*
+ * Update (tick_length, tick_length_base, tick_nsec), based
+ * on (tick_usec, ntp_tick_adj, time_freq):
+ */
 static void ntp_update_frequency(void)
 {
-	u64 old_tick_length_base = tick_length_base;
-	u64 second_length = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ)
-				<< NTP_SCALE_SHIFT;
-	second_length += (s64)ntp_tick_adj << NTP_SCALE_SHIFT;
-	second_length += time_freq;
+	u64 prev_base;
+	u64 second_length;
+
+	prev_base = tick_length_base;
+
+	second_length		 = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ)
+						<< NTP_SCALE_SHIFT;
+
+	second_length		+= (s64)ntp_tick_adj << NTP_SCALE_SHIFT;
+	second_length		+= time_freq;
 
-	tick_length_base = second_length;
+	tick_length_base	 = second_length;
 
-	tick_nsec = div_u64(second_length, HZ) >> NTP_SCALE_SHIFT;
-	tick_length_base = div_u64(tick_length_base, NTP_INTERVAL_FREQ);
+	tick_nsec		 = div_u64(second_length, HZ) >> NTP_SCALE_SHIFT;
+	tick_length_base	 = div_u64(tick_length_base, NTP_INTERVAL_FREQ);
 
 	/*
 	 * Don't wait for the next second_overflow, apply
 	 * the change to the tick length immediately
 	 */
-	tick_length += tick_length_base - old_tick_length_base;
+	tick_length		+= tick_length_base - prev_base;
 }
 
 static void ntp_update_offset(long offset)

commit bbd1267690bb6940d0722dd33e929442c0409c01
Author: Ingo Molnar <mingo@elte.hu>
Date:   Sun Feb 22 12:11:11 2009 +0100

    time: ntp: simplify the MAX_TICKADJ_SCALED definition
    
    Impact: cleanup, no functionality changed
    
    There's an ugly u64 typecase in the MAX_TICKADJ_SCALED definition,
    this can be eliminated by making the MAX_TICKADJ constant's type
    64-bit (signed).
    
    kernel/time/ntp.o:
    
       text    data     bss     dec     hex filename
       2504     114     136    2754     ac2 ntp.o.before
       2504     114     136    2754     ac2 ntp.o.after
    
    md5:
       41f3009debc9b397d7394dd77d912f0a  ntp.o.before.asm
       41f3009debc9b397d7394dd77d912f0a  ntp.o.after.asm
    
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 1fa6615b317a..2b758c935c65 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -30,9 +30,9 @@ static u64			tick_length_base;
 
 static struct hrtimer		leap_timer;
 
-#define MAX_TICKADJ		500		/* usecs */
+#define MAX_TICKADJ		500LL		/* usecs */
 #define MAX_TICKADJ_SCALED \
-  (((u64)(MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
+	(((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
 
 /*
  * phase-lock loop variables

commit 3c972c2444dcb7088999c32b8c5a7ab3b8a6c0b6
Author: Ingo Molnar <mingo@elte.hu>
Date:   Sun Feb 22 12:06:57 2009 +0100

    time: ntp: simplify the second_overflow() code flow
    
    Impact: cleanup, no functionality changed
    
    Instead of a hierarchy of conditions, transform them to clean
    gradual conditions and return's.
    
    This makes the flow easier to read and makes the purpose of
    the function easier to understand.
    
    kernel/time/ntp.o:
    
       text    data     bss     dec     hex filename
       2552     170     168    2890     b4a ntp.o.before
       2552     170     168    2890     b4a ntp.o.after
    
    md5:
       eae1275df0b7d6290c13f6f6f8f05c8c  ntp.o.before.asm
       eae1275df0b7d6290c13f6f6f8f05c8c  ntp.o.after.asm
    
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 3479ec48e604..1fa6615b317a 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -232,19 +232,24 @@ void second_overflow(void)
 	time_offset	-= time_adj;
 	tick_length	+= time_adj;
 
-	if (unlikely(time_adjust)) {
-		if (time_adjust > MAX_TICKADJ) {
-			time_adjust -= MAX_TICKADJ;
-			tick_length += MAX_TICKADJ_SCALED;
-		} else if (time_adjust < -MAX_TICKADJ) {
-			time_adjust += MAX_TICKADJ;
-			tick_length -= MAX_TICKADJ_SCALED;
-		} else {
-			tick_length += (s64)(time_adjust * NSEC_PER_USEC /
-					NTP_INTERVAL_FREQ) << NTP_SCALE_SHIFT;
-			time_adjust = 0;
-		}
+	if (!time_adjust)
+		return;
+
+	if (time_adjust > MAX_TICKADJ) {
+		time_adjust -= MAX_TICKADJ;
+		tick_length += MAX_TICKADJ_SCALED;
+		return;
 	}
+
+	if (time_adjust < -MAX_TICKADJ) {
+		time_adjust += MAX_TICKADJ;
+		tick_length -= MAX_TICKADJ_SCALED;
+		return;
+	}
+
+	tick_length += (s64)(time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ)
+							 << NTP_SCALE_SHIFT;
+	time_adjust = 0;
 }
 
 #ifdef CONFIG_GENERIC_CMOS_UPDATE

commit 53bbfa9e9437e70b322368e82c723112d690e304
Author: Ingo Molnar <mingo@elte.hu>
Date:   Wed Feb 20 07:58:42 2008 +0100

    time: ntp: clean up kernel/time/ntp.c
    
    Impact: cleanup, no functionality changed
    
    Make this file a bit more readable by applying a consistent coding style.
    
    No code changed:
    
    kernel/time/ntp.o:
    
       text    data     bss     dec     hex filename
       2552     170     168    2890     b4a ntp.o.before
       2552     170     168    2890     b4a ntp.o.after
    
    md5:
       eae1275df0b7d6290c13f6f6f8f05c8c  ntp.o.before.asm
       eae1275df0b7d6290c13f6f6f8f05c8c  ntp.o.after.asm
    
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index e1fa3689a903..3479ec48e604 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -1,53 +1,81 @@
 /*
- * linux/kernel/time/ntp.c
- *
  * NTP state machine interfaces and logic.
  *
  * This code was mainly moved from kernel/timer.c and kernel/time.c
  * Please see those files for relevant copyright info and historical
  * changelogs.
  */
-
-#include <linux/mm.h>
-#include <linux/time.h>
-#include <linux/timex.h>
-#include <linux/jiffies.h>
-#include <linux/hrtimer.h>
 #include <linux/capability.h>
-#include <linux/math64.h>
 #include <linux/clocksource.h>
 #include <linux/workqueue.h>
-#include <asm/timex.h>
+#include <linux/hrtimer.h>
+#include <linux/jiffies.h>
+#include <linux/math64.h>
+#include <linux/timex.h>
+#include <linux/time.h>
+#include <linux/mm.h>
 
 /*
- * Timekeeping variables
+ * NTP timekeeping variables:
  */
-unsigned long tick_usec = TICK_USEC; 		/* USER_HZ period (usec) */
-unsigned long tick_nsec;			/* ACTHZ period (nsec) */
-u64 tick_length;
-static u64 tick_length_base;
 
-static struct hrtimer leap_timer;
+/* USER_HZ period (usecs): */
+unsigned long			tick_usec = TICK_USEC;
+
+/* ACTHZ period (nsecs): */
+unsigned long			tick_nsec;
 
-#define MAX_TICKADJ		500		/* microsecs */
-#define MAX_TICKADJ_SCALED	(((u64)(MAX_TICKADJ * NSEC_PER_USEC) << \
-				  NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
+u64				tick_length;
+static u64			tick_length_base;
+
+static struct hrtimer		leap_timer;
+
+#define MAX_TICKADJ		500		/* usecs */
+#define MAX_TICKADJ_SCALED \
+  (((u64)(MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
 
 /*
  * phase-lock loop variables
  */
-/* TIME_ERROR prevents overwriting the CMOS clock */
-static int time_state = TIME_OK;	/* clock synchronization status	*/
-int time_status = STA_UNSYNC;		/* clock status bits		*/
-static long time_tai;			/* TAI offset (s)		*/
-static s64 time_offset;			/* time adjustment (ns)		*/
-static long time_constant = 2;		/* pll time constant		*/
-long time_maxerror = NTP_PHASE_LIMIT;	/* maximum error (us)		*/
-long time_esterror = NTP_PHASE_LIMIT;	/* estimated error (us)		*/
-static s64 time_freq;			/* frequency offset (scaled ns/s)*/
-static long time_reftime;		/* time at last adjustment (s)	*/
-long time_adjust;
-static long ntp_tick_adj;
+
+/*
+ * clock synchronization status
+ *
+ * (TIME_ERROR prevents overwriting the CMOS clock)
+ */
+static int			time_state = TIME_OK;
+
+/* clock status bits:							*/
+int				time_status = STA_UNSYNC;
+
+/* TAI offset (secs):							*/
+static long			time_tai;
+
+/* time adjustment (nsecs):						*/
+static s64			time_offset;
+
+/* pll time constant:							*/
+static long			time_constant = 2;
+
+/* maximum error (usecs):						*/
+long				time_maxerror = NTP_PHASE_LIMIT;
+
+/* estimated error (usecs):						*/
+long				time_esterror = NTP_PHASE_LIMIT;
+
+/* frequency offset (scaled nsecs/secs):				*/
+static s64			time_freq;
+
+/* time at last adjustment (secs):					*/
+static long			time_reftime;
+
+long				time_adjust;
+
+static long			ntp_tick_adj;
+
+/*
+ * NTP methods:
+ */
 
 static void ntp_update_frequency(void)
 {
@@ -118,15 +146,15 @@ static void ntp_update_offset(long offset)
  */
 void ntp_clear(void)
 {
-	time_adjust = 0;		/* stop active adjtime() */
-	time_status |= STA_UNSYNC;
-	time_maxerror = NTP_PHASE_LIMIT;
-	time_esterror = NTP_PHASE_LIMIT;
+	time_adjust	= 0;		/* stop active adjtime() */
+	time_status	|= STA_UNSYNC;
+	time_maxerror	= NTP_PHASE_LIMIT;
+	time_esterror	= NTP_PHASE_LIMIT;
 
 	ntp_update_frequency();
 
-	tick_length = tick_length_base;
-	time_offset = 0;
+	tick_length	= tick_length_base;
+	time_offset	= 0;
 }
 
 /*
@@ -147,8 +175,8 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
 		xtime.tv_sec--;
 		wall_to_monotonic.tv_sec++;
 		time_state = TIME_OOP;
-		printk(KERN_NOTICE "Clock: "
-		       "inserting leap second 23:59:60 UTC\n");
+		printk(KERN_NOTICE
+			"Clock: inserting leap second 23:59:60 UTC\n");
 		hrtimer_add_expires_ns(&leap_timer, NSEC_PER_SEC);
 		res = HRTIMER_RESTART;
 		break;
@@ -157,8 +185,8 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
 		time_tai--;
 		wall_to_monotonic.tv_sec--;
 		time_state = TIME_WAIT;
-		printk(KERN_NOTICE "Clock: "
-		       "deleting leap second 23:59:59 UTC\n");
+		printk(KERN_NOTICE
+			"Clock: deleting leap second 23:59:59 UTC\n");
 		break;
 	case TIME_OOP:
 		time_tai++;
@@ -199,10 +227,10 @@ void second_overflow(void)
 	 * Compute the phase adjustment for the next second. The offset is
 	 * reduced by a fixed factor times the time constant.
 	 */
-	tick_length = tick_length_base;
-	time_adj = shift_right(time_offset, SHIFT_PLL + time_constant);
-	time_offset -= time_adj;
-	tick_length += time_adj;
+	tick_length	= tick_length_base;
+	time_adj	= shift_right(time_offset, SHIFT_PLL + time_constant);
+	time_offset	-= time_adj;
+	tick_length	+= time_adj;
 
 	if (unlikely(time_adjust)) {
 		if (time_adjust > MAX_TICKADJ) {
@@ -240,12 +268,13 @@ static void sync_cmos_clock(struct work_struct *work)
 	 * This code is run on a timer.  If the clock is set, that timer
 	 * may not expire at the correct time.  Thus, we adjust...
 	 */
-	if (!ntp_synced())
+	if (!ntp_synced()) {
 		/*
 		 * Not synced, exit, do not restart a timer (if one is
 		 * running, let it run out).
 		 */
 		return;
+	}
 
 	getnstimeofday(&now);
 	if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2)
@@ -277,7 +306,8 @@ static void notify_cmos_timer(void)
 static inline void notify_cmos_timer(void) { }
 #endif
 
-/* adjtimex mainly allows reading (and writing, if superuser) of
+/*
+ * adjtimex mainly allows reading (and writing, if superuser) of
  * kernel time-keeping variables. used by xntpd.
  */
 int do_adjtimex(struct timex *txc)
@@ -298,7 +328,10 @@ int do_adjtimex(struct timex *txc)
 		 if (txc->modes && !capable(CAP_SYS_TIME))
 			return -EPERM;
 
-		/* if the quartz is off by more than 10% something is VERY wrong! */
+		/*
+		 * if the quartz is off by more than 10% then
+		 * something is VERY wrong!
+		 */
 		if (txc->modes & ADJ_TICK &&
 		    (txc->tick <  900000/USER_HZ ||
 		     txc->tick > 1100000/USER_HZ))

commit 0b13fda1e0936b3d64c4c407f183d33fa6bd2ad4
Author: Ingo Molnar <mingo@elte.hu>
Date:   Wed Feb 25 16:52:11 2009 +0100

    generic-ipi: cleanups
    
    Andrew pointed out that there's some small amount of
    style rot in kernel/smp.c.
    
    Clean it up.
    
    Reported-by: Andrew Morton <akpm@linux-foundation.org>
    Cc: Nick Piggin <npiggin@suse.de>
    Cc: Jens Axboe <jens.axboe@oracle.com>
    Cc: Peter Zijlstra <peterz@infradead.org>
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/smp.c b/kernel/smp.c
index f5308258891a..7ad2262d2eca 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -2,13 +2,12 @@
  * Generic helpers for smp ipi calls
  *
  * (C) Jens Axboe <jens.axboe@oracle.com> 2008
- *
  */
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/percpu.h>
 #include <linux/rcupdate.h>
 #include <linux/rculist.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/cpu.h>
 
@@ -17,29 +16,30 @@ static DEFINE_PER_CPU(struct call_single_queue, call_single_queue);
 static struct {
 	struct list_head	queue;
 	spinlock_t		lock;
-} call_function __cacheline_aligned_in_smp = {
-	.queue = LIST_HEAD_INIT(call_function.queue),
-	.lock  = __SPIN_LOCK_UNLOCKED(call_function.lock),
-};
+} call_function __cacheline_aligned_in_smp =
+	{
+		.queue		= LIST_HEAD_INIT(call_function.queue),
+		.lock		= __SPIN_LOCK_UNLOCKED(call_function.lock),
+	};
 
 enum {
 	CSD_FLAG_LOCK		= 0x01,
 };
 
 struct call_function_data {
-	struct call_single_data csd;
-	spinlock_t lock;
-	unsigned int refs;
-	cpumask_var_t cpumask;
+	struct call_single_data	csd;
+	spinlock_t		lock;
+	unsigned int		refs;
+	cpumask_var_t		cpumask;
 };
 
 struct call_single_queue {
-	struct list_head list;
-	spinlock_t lock;
+	struct list_head	list;
+	spinlock_t		lock;
 };
 
 static DEFINE_PER_CPU(struct call_function_data, cfd_data) = {
-	.lock = __SPIN_LOCK_UNLOCKED(cfd_data.lock),
+	.lock			= __SPIN_LOCK_UNLOCKED(cfd_data.lock),
 };
 
 static int
@@ -71,7 +71,7 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 }
 
 static struct notifier_block __cpuinitdata hotplug_cfd_notifier = {
-	.notifier_call = hotplug_cfd,
+	.notifier_call		= hotplug_cfd,
 };
 
 static int __cpuinit init_call_single_data(void)
@@ -96,9 +96,9 @@ early_initcall(init_call_single_data);
 /*
  * csd_lock/csd_unlock used to serialize access to per-cpu csd resources
  *
- * For non-synchronous ipi calls the csd can still be in use by the previous
- * function call. For multi-cpu calls its even more interesting as we'll have
- * to ensure no other cpu is observing our csd.
+ * For non-synchronous ipi calls the csd can still be in use by the
+ * previous function call. For multi-cpu calls its even more interesting
+ * as we'll have to ensure no other cpu is observing our csd.
  */
 static void csd_lock_wait(struct call_single_data *data)
 {
@@ -112,27 +112,29 @@ static void csd_lock(struct call_single_data *data)
 	data->flags = CSD_FLAG_LOCK;
 
 	/*
-	 * prevent CPU from reordering the above assignment to ->flags
-	 * with any subsequent assignments to other fields of the
-	 * specified call_single_data structure.
+	 * prevent CPU from reordering the above assignment
+	 * to ->flags with any subsequent assignments to other
+	 * fields of the specified call_single_data structure:
 	 */
-
 	smp_mb();
 }
 
 static void csd_unlock(struct call_single_data *data)
 {
 	WARN_ON(!(data->flags & CSD_FLAG_LOCK));
+
 	/*
-	 * ensure we're all done before releasing data
+	 * ensure we're all done before releasing data:
 	 */
 	smp_mb();
+
 	data->flags &= ~CSD_FLAG_LOCK;
 }
 
 /*
- * Insert a previously allocated call_single_data element for execution
- * on the given CPU. data must already have ->func, ->info, and ->flags set.
+ * Insert a previously allocated call_single_data element
+ * for execution on the given CPU. data must already have
+ * ->func, ->info, and ->flags set.
  */
 static
 void generic_exec_single(int cpu, struct call_single_data *data, int wait)
@@ -154,10 +156,9 @@ void generic_exec_single(int cpu, struct call_single_data *data, int wait)
 	 * If IPIs can go out of order to the cache coherency protocol
 	 * in an architecture, sufficient synchronisation should be added
 	 * to arch code to make it appear to obey cache coherency WRT
-	 * locking and barrier primitives. Generic code isn't really equipped
-	 * to do the right thing...
+	 * locking and barrier primitives. Generic code isn't really
+	 * equipped to do the right thing...
 	 */
-
 	if (ipi)
 		arch_send_call_function_single_ipi(cpu);
 
@@ -183,8 +184,8 @@ void generic_smp_call_function_interrupt(void)
 	smp_mb();
 
 	/*
-	 * It's ok to use list_for_each_rcu() here even though we may delete
-	 * 'pos', since list_del_rcu() doesn't clear ->next
+	 * It's ok to use list_for_each_rcu() here even though we may
+	 * delete 'pos', since list_del_rcu() doesn't clear ->next
 	 */
 	list_for_each_entry_rcu(data, &call_function.queue, csd.list) {
 		int refs;
@@ -219,14 +220,14 @@ void generic_smp_call_function_interrupt(void)
 }
 
 /*
- * Invoked by arch to handle an IPI for call function single. Must be called
- * from the arch with interrupts disabled.
+ * Invoked by arch to handle an IPI for call function single. Must be
+ * called from the arch with interrupts disabled.
  */
 void generic_smp_call_function_single_interrupt(void)
 {
 	struct call_single_queue *q = &__get_cpu_var(call_single_queue);
-	LIST_HEAD(list);
 	unsigned int data_flags;
+	LIST_HEAD(list);
 
 	spin_lock(&q->lock);
 	list_replace_init(&q->list, &list);
@@ -235,22 +236,20 @@ void generic_smp_call_function_single_interrupt(void)
 	while (!list_empty(&list)) {
 		struct call_single_data *data;
 
-		data = list_entry(list.next, struct call_single_data,
-					list);
+		data = list_entry(list.next, struct call_single_data, list);
 		list_del(&data->list);
 
 		/*
-		 * 'data' can be invalid after this call if
-		 * flags == 0 (when called through
-		 * generic_exec_single(), so save them away before
-		 * making the call.
+		 * 'data' can be invalid after this call if flags == 0
+		 * (when called through generic_exec_single()),
+		 * so save them away before making the call:
 		 */
 		data_flags = data->flags;
 
 		data->func(data->info);
 
 		/*
-		 * Unlocked CSDs are valid through generic_exec_single()
+		 * Unlocked CSDs are valid through generic_exec_single():
 		 */
 		if (data_flags & CSD_FLAG_LOCK)
 			csd_unlock(data);
@@ -276,34 +275,41 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 		.flags = 0,
 	};
 	unsigned long flags;
-	/* prevent preemption and reschedule on another processor,
-	   as well as CPU removal */
-	int me = get_cpu();
+	int this_cpu;
 	int err = 0;
 
+	/*
+	 * prevent preemption and reschedule on another processor,
+	 * as well as CPU removal
+	 */
+	this_cpu = get_cpu();
+
 	/* Can deadlock when called with interrupts disabled */
 	WARN_ON(irqs_disabled());
 
-	if (cpu == me) {
+	if (cpu == this_cpu) {
 		local_irq_save(flags);
 		func(info);
 		local_irq_restore(flags);
-	} else if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
-		struct call_single_data *data = &d;
+	} else {
+		if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
+			struct call_single_data *data = &d;
 
-		if (!wait)
-			data = &__get_cpu_var(csd_data);
+			if (!wait)
+				data = &__get_cpu_var(csd_data);
 
-		csd_lock(data);
+			csd_lock(data);
 
-		data->func = func;
-		data->info = info;
-		generic_exec_single(cpu, data, wait);
-	} else {
-		err = -ENXIO;	/* CPU not online */
+			data->func = func;
+			data->info = info;
+			generic_exec_single(cpu, data, wait);
+		} else {
+			err = -ENXIO;	/* CPU not online */
+		}
 	}
 
 	put_cpu();
+
 	return err;
 }
 EXPORT_SYMBOL(smp_call_function_single);
@@ -313,10 +319,9 @@ EXPORT_SYMBOL(smp_call_function_single);
  * @cpu: The CPU to run on.
  * @data: Pre-allocated and setup data structure
  *
- * Like smp_call_function_single(), but allow caller to pass in a pre-allocated
- * data structure. Useful for embedding @data inside other structures, for
- * instance.
- *
+ * Like smp_call_function_single(), but allow caller to pass in a
+ * pre-allocated data structure. Useful for embedding @data inside
+ * other structures, for instance.
  */
 void __smp_call_function_single(int cpu, struct call_single_data *data,
 				int wait)
@@ -329,10 +334,11 @@ void __smp_call_function_single(int cpu, struct call_single_data *data,
 	generic_exec_single(cpu, data, wait);
 }
 
-/* FIXME: Shim for archs using old arch_send_call_function_ipi API. */
+/* Deprecated: shim for archs using old arch_send_call_function_ipi API. */
+
 #ifndef arch_send_call_function_ipi_mask
-#define arch_send_call_function_ipi_mask(maskp) \
-	arch_send_call_function_ipi(*(maskp))
+# define arch_send_call_function_ipi_mask(maskp) \
+	 arch_send_call_function_ipi(*(maskp))
 #endif
 
 /**
@@ -340,7 +346,8 @@ void __smp_call_function_single(int cpu, struct call_single_data *data,
  * @mask: The set of cpus to run on (only runs on online subset).
  * @func: The function to run. This must be fast and non-blocking.
  * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed on other CPUs.
+ * @wait: If true, wait (atomically) until function has completed
+ *        on other CPUs.
  *
  * If @wait is true, then returns once @func has returned. Note that @wait
  * will be implicitly turned on in case of allocation failures, since
@@ -351,27 +358,27 @@ void __smp_call_function_single(int cpu, struct call_single_data *data,
  * must be disabled when calling this function.
  */
 void smp_call_function_many(const struct cpumask *mask,
-			    void (*func)(void *), void *info,
-			    bool wait)
+			    void (*func)(void *), void *info, bool wait)
 {
 	struct call_function_data *data;
 	unsigned long flags;
-	int cpu, next_cpu, me = smp_processor_id();
+	int cpu, next_cpu, this_cpu = smp_processor_id();
 
 	/* Can deadlock when called with interrupts disabled */
 	WARN_ON(irqs_disabled());
 
-	/* So, what's a CPU they want?  Ignoring this one. */
+	/* So, what's a CPU they want? Ignoring this one. */
 	cpu = cpumask_first_and(mask, cpu_online_mask);
-	if (cpu == me)
+	if (cpu == this_cpu)
 		cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
+
 	/* No online cpus?  We're done. */
 	if (cpu >= nr_cpu_ids)
 		return;
 
 	/* Do we have another CPU which isn't us? */
 	next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
-	if (next_cpu == me)
+	if (next_cpu == this_cpu)
 		next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask);
 
 	/* Fastpath: do that cpu by itself. */
@@ -387,30 +394,31 @@ void smp_call_function_many(const struct cpumask *mask,
 	data->csd.func = func;
 	data->csd.info = info;
 	cpumask_and(data->cpumask, mask, cpu_online_mask);
-	cpumask_clear_cpu(me, data->cpumask);
+	cpumask_clear_cpu(this_cpu, data->cpumask);
 	data->refs = cpumask_weight(data->cpumask);
 
 	spin_lock(&call_function.lock);
 	/*
 	 * Place entry at the _HEAD_ of the list, so that any cpu still
-	 * observing the entry in generic_smp_call_function_interrupt() will
-	 * not miss any other list entries.
+	 * observing the entry in generic_smp_call_function_interrupt()
+	 * will not miss any other list entries:
 	 */
 	list_add_rcu(&data->csd.list, &call_function.queue);
 	spin_unlock(&call_function.lock);
+
 	spin_unlock_irqrestore(&data->lock, flags);
 
 	/*
 	 * Make the list addition visible before sending the ipi.
-	 * (IPIs must obey or appear to obey normal Linux cache coherency
-	 * rules -- see comment in generic_exec_single).
+	 * (IPIs must obey or appear to obey normal Linux cache
+	 * coherency rules -- see comment in generic_exec_single).
 	 */
 	smp_mb();
 
 	/* Send a message to all CPUs in the map */
 	arch_send_call_function_ipi_mask(data->cpumask);
 
-	/* optionally wait for the CPUs to complete */
+	/* Optionally wait for the CPUs to complete */
 	if (wait)
 		csd_lock_wait(&data->csd);
 }
@@ -420,7 +428,8 @@ EXPORT_SYMBOL(smp_call_function_many);
  * smp_call_function(): Run a function on all other CPUs.
  * @func: The function to run. This must be fast and non-blocking.
  * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed on other CPUs.
+ * @wait: If true, wait (atomically) until function has completed
+ *        on other CPUs.
  *
  * Returns 0.
  *
@@ -436,6 +445,7 @@ int smp_call_function(void (*func)(void *), void *info, int wait)
 	preempt_disable();
 	smp_call_function_many(cpu_online_mask, func, info, wait);
 	preempt_enable();
+
 	return 0;
 }
 EXPORT_SYMBOL(smp_call_function);

commit 2e31add2a7e2a15d07f592c21ba35870fa9a1d1f
Merge: d639bab8da86 17581ad812a9
Author: Ingo Molnar <mingo@elte.hu>
Date:   Wed Feb 25 16:40:10 2009 +0100

    Merge branch 'x86/urgent' into x86/pat

commit d2b0261506602bd969164879206027b30358ffdf
Author: Ingo Molnar <mingo@elte.hu>
Date:   Wed Feb 25 14:36:45 2009 +0100

    alloc_percpu: fix UP build
    
    Impact: build fix
    
    the !SMP branch had a 'gfp' leftover:
    
     include/linux/percpu.h: In function '__alloc_percpu':
     include/linux/percpu.h:160: error: 'gfp' undeclared (first use in this function)
     include/linux/percpu.h:160: error: (Each undeclared identifier is reported only once
     include/linux/percpu.h:160: error: for each function it appears in.)
    
    Use GFP_KERNEL like the SMP version does.
    
    Cc: Rusty Russell <rusty@rustcorp.com.au>
    Cc: Tejun Heo <tj@kernel.org>
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 910beb0abea2..d8e5a9abbce0 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -157,7 +157,7 @@ static inline void *__alloc_percpu(size_t size, size_t align)
 	 * percpu sections on SMP for which this path isn't used.
 	 */
 	WARN_ON_ONCE(align > __alignof__(unsigned long long));
-	return kzalloc(size, gfp);
+	return kzalloc(size, GFP_KERNEL);
 }
 
 static inline void free_percpu(void *p)

commit 0dcec8c27ba44cd11c6e68c46d5fd553818a3837
Author: Ingo Molnar <mingo@elte.hu>
Date:   Wed Feb 25 14:07:33 2009 +0100

    alloc_percpu: add align argument to __alloc_percpu, fix
    
    Impact: build fix
    
    API was changed, but not all usage sites were converted:
    
     net/ipv4/route.c: In function ‘ip_rt_init’:
     net/ipv4/route.c:3379: error: too few arguments to function ‘__alloc_percpu’
    
    Cc: Rusty Russell <rusty@rustcorp.com.au>
    Cc: Tejun Heo <tj@kernel.org>
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 97f71153584f..bf895401218f 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3376,7 +3376,7 @@ int __init ip_rt_init(void)
 	int rc = 0;
 
 #ifdef CONFIG_NET_CLS_ROUTE
-	ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct));
+	ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
 	if (!ip_rt_acct)
 		panic("IP: failed to allocate ip_rt_acct\n");
 #endif

commit 2b1b858f690d6369a59ad241335eeedec6eb0c8c
Merge: 886b5b73d71e 1473e4417c79
Author: Ingo Molnar <mingo@elte.hu>
Date:   Wed Feb 25 12:50:07 2009 +0100

    Merge branch 'tip/tracing/ftrace' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/ftrace