Merge branches 'core-fixes-for-linus', 'x86-fixes-for-linus',...

Merge branches 'core-fixes-for-linus', 'x86-fixes-for-linus', 'timers-fixes-for-linus' and 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  rcu: avoid pointless blocked-task warnings
  rcu: demote SRCU_SYNCHRONIZE_DELAY from kernel-parameter status
  rtmutex: Fix comment about why new_owner can be NULL in wake_futex_pi()

* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, olpc: Add missing Kconfig dependencies
  x86, mrst: Set correct APB timer IRQ affinity for secondary cpu
  x86: tsc: Fix calibration refinement conditionals to avoid divide by zero
  x86, ia64, acpi: Clean up x86-ism in drivers/acpi/numa.c

* 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  timekeeping: Make local variables static
  time: Rename misnamed minsec argument of clocks_calc_mult_shift()

* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  tracing: Remove syscall_exit_fields
  tracing: Only process module tracepoints once
  perf record: Add "nodelay" mode, disabled by default
  perf sched: Fix list of events, dropping unsupported ':r' modifier
  Revert "perf tools: Emit clearer message for sys_perf_event_open ENOENT return"
  perf top: Fix annotate segv
  perf evsel: Fix order of event list deletion

arch/x86/Kconfig

@@ -2068,6 +2068,7 @@ config OLPC
 	bool "One Laptop Per Child support"
 	select GPIOLIB
 	select OLPC_OPENFIRMWARE
+	depends on !X86_64 && !X86_PAE
 	---help---
 	  Add support for detecting the unique features of the OLPC
 	  XO hardware.

arch/x86/kernel/apb_timer.c

@@ -313,14 +313,16 @@ static void apbt_setup_irq(struct apbt_dev *adev)
 	if (adev->irq == 0)
 		return;
 
+	irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
+	irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
+	/* APB timer irqs are set up as mp_irqs, timer is edge type */
+	__set_irq_handler(adev->irq, handle_edge_irq, 0, "edge");
+
 	if (system_state == SYSTEM_BOOTING) {
-		irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
-		irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
-		/* APB timer irqs are set up as mp_irqs, timer is edge type */
-		__set_irq_handler(adev->irq, handle_edge_irq, 0, "edge");
 		if (request_irq(adev->irq, apbt_interrupt_handler,
-				IRQF_TIMER | IRQF_DISABLED | IRQF_NOBALANCING,
-				adev->name, adev)) {
+					IRQF_TIMER | IRQF_DISABLED |
+					IRQF_NOBALANCING,
+					adev->name, adev)) {
 			printk(KERN_ERR "Failed request IRQ for APBT%d\n",
 			       adev->num);
 		}

arch/x86/kernel/tsc.c

@@ -464,7 +464,7 @@ unsigned long native_calibrate_tsc(void)
 		tsc_pit_min = min(tsc_pit_min, tsc_pit_khz);
 
 		/* hpet or pmtimer available ? */
-		if (!hpet && !ref1 && !ref2)
+		if (ref1 == ref2)
 			continue;
 
 		/* Check, whether the sampling was disturbed by an SMI */
@@ -935,7 +935,7 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 	tsc_stop = tsc_read_refs(&ref_stop, hpet);
 
 	/* hpet or pmtimer available ? */
-	if (!hpet && !ref_start && !ref_stop)
+	if (ref_start == ref_stop)
 		goto out;
 
 	/* Check, whether the sampling was disturbed by an SMI */

drivers/acpi/numa.c

@@ -275,23 +275,19 @@ acpi_table_parse_srat(enum acpi_srat_type id,
 int __init acpi_numa_init(void)
 {
 	int ret = 0;
-	int nr_cpu_entries = nr_cpu_ids;
 
-#ifdef CONFIG_X86
 	/*
 	 * Should not limit number with cpu num that is from NR_CPUS or nr_cpus=
 	 * SRAT cpu entries could have different order with that in MADT.
 	 * So go over all cpu entries in SRAT to get apicid to node mapping.
 	 */
-	nr_cpu_entries = MAX_LOCAL_APIC;
-#endif
 
 	/* SRAT: Static Resource Affinity Table */
 	if (!acpi_table_parse(ACPI_SIG_SRAT, acpi_parse_srat)) {
 		acpi_table_parse_srat(ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY,
-				     acpi_parse_x2apic_affinity, nr_cpu_entries);
+				     acpi_parse_x2apic_affinity, 0);
 		acpi_table_parse_srat(ACPI_SRAT_TYPE_CPU_AFFINITY,
-				     acpi_parse_processor_affinity, nr_cpu_entries);
+				     acpi_parse_processor_affinity, 0);
 		ret = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY,
 					    acpi_parse_memory_affinity,
 					    NR_NODE_MEMBLKS);

include/trace/events/module.h

+/*
+ * Because linux/module.h has tracepoints in the header, and ftrace.h
+ * eventually includes this file, define_trace.h includes linux/module.h
+ * But we do not want the module.h to override the TRACE_SYSTEM macro
+ * variable that define_trace.h is processing, so we only set it
+ * when module events are being processed, which would happen when
+ * CREATE_TRACE_POINTS is defined.
+ */
+#ifdef CREATE_TRACE_POINTS
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM module
+#endif
 
 #if !defined(_TRACE_MODULE_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_MODULE_H

init/Kconfig

@@ -515,21 +515,6 @@ config RCU_BOOST_DELAY
 
 	  Accept the default if unsure.
 
-config SRCU_SYNCHRONIZE_DELAY
-	int "Microseconds to delay before waiting for readers"
-	range 0 20
-	default 10
-	help
-	  This option controls how long SRCU delays before entering its
-	  loop waiting on SRCU readers.  The purpose of this loop is
-	  to avoid the unconditional context-switch penalty that would
-	  otherwise be incurred if there was an active SRCU reader,
-	  in a manner similar to adaptive locking schemes.  This should
-	  be set to be a bit longer than the common-case SRCU read-side
-	  critical-section overhead.
-
-	  Accept the default if unsure.
-
 endmenu # "RCU Subsystem"
 
 config IKCONFIG

kernel/futex.c

@@ -826,10 +826,9 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
 
 	/*
-	 * This happens when we have stolen the lock and the original
-	 * pending owner did not enqueue itself back on the rt_mutex.
-	 * Thats not a tragedy. We know that way, that a lock waiter
-	 * is on the fly. We make the futex_q waiter the pending owner.
+	 * It is possible that the next waiter (the one that brought
+	 * this owner to the kernel) timed out and is no longer
+	 * waiting on the lock.
 	 */
 	if (!new_owner)
 		new_owner = this->task;

kernel/rcutiny.c

@@ -189,7 +189,8 @@ static int rcu_kthread(void *arg)
 	unsigned long flags;
 
 	for (;;) {
-		wait_event(rcu_kthread_wq, have_rcu_kthread_work != 0);
+		wait_event_interruptible(rcu_kthread_wq,
+					 have_rcu_kthread_work != 0);
 		morework = rcu_boost();
 		local_irq_save(flags);
 		work = have_rcu_kthread_work;

kernel/srcu.c

@@ -155,6 +155,16 @@ void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
+/*
+ * We use an adaptive strategy for synchronize_srcu() and especially for
+ * synchronize_srcu_expedited().  We spin for a fixed time period
+ * (defined below) to allow SRCU readers to exit their read-side critical
+ * sections.  If there are still some readers after 10 microseconds,
+ * we repeatedly block for 1-millisecond time periods.  This approach
+ * has done well in testing, so there is no need for a config parameter.
+ */
+#define SYNCHRONIZE_SRCU_READER_DELAY 10
+
 /*
  * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
  */
@@ -207,11 +217,12 @@ static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
 	 * will have finished executing.  We initially give readers
 	 * an arbitrarily chosen 10 microseconds to get out of their
 	 * SRCU read-side critical sections, then loop waiting 1/HZ
-	 * seconds per iteration.
+	 * seconds per iteration.  The 10-microsecond value has done
+	 * very well in testing.
 	 */
 
 	if (srcu_readers_active_idx(sp, idx))
-		udelay(CONFIG_SRCU_SYNCHRONIZE_DELAY);
+		udelay(SYNCHRONIZE_SRCU_READER_DELAY);
 	while (srcu_readers_active_idx(sp, idx))
 		schedule_timeout_interruptible(1);
 

kernel/time/clocksource.c

@@ -113,7 +113,7 @@ EXPORT_SYMBOL_GPL(timecounter_cyc2time);
  * @shift:	pointer to shift variable
  * @from:	frequency to convert from
  * @to:		frequency to convert to
- * @minsec:	guaranteed runtime conversion range in seconds
+ * @maxsec:	guaranteed runtime conversion range in seconds
  *
  * The function evaluates the shift/mult pair for the scaled math
  * operations of clocksources and clockevents.
@@ -122,7 +122,7 @@ EXPORT_SYMBOL_GPL(timecounter_cyc2time);
  * NSEC_PER_SEC == 1GHz and @from is the counter frequency. For clock
  * event @to is the counter frequency and @from is NSEC_PER_SEC.
  *
- * The @minsec conversion range argument controls the time frame in
+ * The @maxsec conversion range argument controls the time frame in
  * seconds which must be covered by the runtime conversion with the
  * calculated mult and shift factors. This guarantees that no 64bit
  * overflow happens when the input value of the conversion is
@@ -131,7 +131,7 @@ EXPORT_SYMBOL_GPL(timecounter_cyc2time);
  * factors.
  */
 void
-clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec)
+clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 maxsec)
 {
 	u64 tmp;
 	u32 sft, sftacc= 32;
@@ -140,7 +140,7 @@ clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec)
 	 * Calculate the shift factor which is limiting the conversion
 	 * range:
 	 */
-	tmp = ((u64)minsec * from) >> 32;
+	tmp = ((u64)maxsec * from) >> 32;
 	while (tmp) {
 		tmp >>=1;
 		sftacc--;

kernel/time/timekeeping.c

@@ -49,7 +49,7 @@ struct timekeeper {
 	u32	mult;
 };
 
-struct timekeeper timekeeper;
+static struct timekeeper timekeeper;
 
 /**
  * timekeeper_setup_internals - Set up internals to use clocksource clock.
@@ -164,7 +164,7 @@ static struct timespec total_sleep_time;
 /*
  * The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock.
  */
-struct timespec raw_time;
+static struct timespec raw_time;
 
 /* flag for if timekeeping is suspended */
 int __read_mostly timekeeping_suspended;

kernel/trace/trace_syscalls.c

@@ -23,9 +23,6 @@ static int syscall_exit_register(struct ftrace_event_call *event,
 static int syscall_enter_define_fields(struct ftrace_event_call *call);
 static int syscall_exit_define_fields(struct ftrace_event_call *call);
 
-/* All syscall exit events have the same fields */
-static LIST_HEAD(syscall_exit_fields);
-
 static struct list_head *
 syscall_get_enter_fields(struct ftrace_event_call *call)
 {
@@ -34,34 +31,28 @@ syscall_get_enter_fields(struct ftrace_event_call *call)
 	return &entry->enter_fields;
 }
 
-static struct list_head *
-syscall_get_exit_fields(struct ftrace_event_call *call)
-{
-	return &syscall_exit_fields;
-}
-
 struct trace_event_functions enter_syscall_print_funcs = {
-	.trace                  = print_syscall_enter,
+	.trace		= print_syscall_enter,
 };
 
 struct trace_event_functions exit_syscall_print_funcs = {
-	.trace                  = print_syscall_exit,
+	.trace		= print_syscall_exit,
 };
 
 struct ftrace_event_class event_class_syscall_enter = {
-	.system			= "syscalls",
-	.reg			= syscall_enter_register,
-	.define_fields		= syscall_enter_define_fields,
-	.get_fields		= syscall_get_enter_fields,
-	.raw_init		= init_syscall_trace,
+	.system		= "syscalls",
+	.reg		= syscall_enter_register,
+	.define_fields	= syscall_enter_define_fields,
+	.get_fields	= syscall_get_enter_fields,
+	.raw_init	= init_syscall_trace,
 };
 
 struct ftrace_event_class event_class_syscall_exit = {
-	.system			= "syscalls",
-	.reg			= syscall_exit_register,
-	.define_fields		= syscall_exit_define_fields,
-	.get_fields		= syscall_get_exit_fields,
-	.raw_init		= init_syscall_trace,
+	.system		= "syscalls",
+	.reg		= syscall_exit_register,
+	.define_fields	= syscall_exit_define_fields,
+	.fields		= LIST_HEAD_INIT(event_class_syscall_exit.fields),
+	.raw_init	= init_syscall_trace,
 };
 
 extern unsigned long __start_syscalls_metadata[];

tools/perf/Documentation/perf-record.txt

@@ -61,6 +61,9 @@ OPTIONS
 -r::
 --realtime=::
 	Collect data with this RT SCHED_FIFO priority.
+-D::
+--no-delay::
+	Collect data without buffering.
 -A::
 --append::
 	Append to the output file to do incremental profiling.

tools/perf/builtin-record.c

@@ -49,6 +49,7 @@ static int			pipe_output			=      0;
 static const char		*output_name			= "perf.data";
 static int			group				=      0;
 static int			realtime_prio			=      0;
+static bool			nodelay				=  false;
 static bool			raw_samples			=  false;
 static bool			sample_id_all_avail		=   true;
 static bool			system_wide			=  false;
@@ -307,6 +308,11 @@ static void create_counter(struct perf_evsel *evsel, int cpu)
 		attr->sample_type	|= PERF_SAMPLE_CPU;
 	}
 
+	if (nodelay) {
+		attr->watermark = 0;
+		attr->wakeup_events = 1;
+	}
+
 	attr->mmap		= track;
 	attr->comm		= track;
 	attr->inherit		= !no_inherit;
@@ -331,9 +337,6 @@ static void create_counter(struct perf_evsel *evsel, int cpu)
 			else if (err ==  ENODEV && cpu_list) {
 				die("No such device - did you specify"
 					" an out-of-range profile CPU?\n");
-			} else if (err == ENOENT) {
-				die("%s event is not supported. ",
-				     event_name(evsel));
 			} else if (err == EINVAL && sample_id_all_avail) {
 				/*
 				 * Old kernel, no attr->sample_id_type_all field
@@ -480,6 +483,7 @@ static void atexit_header(void)
 			process_buildids();
 		perf_header__write(&session->header, output, true);
 		perf_session__delete(session);
+		perf_evsel_list__delete();
 		symbol__exit();
 	}
 }
@@ -845,6 +849,8 @@ const struct option record_options[] = {
 		    "record events on existing thread id"),
 	OPT_INTEGER('r', "realtime", &realtime_prio,
 		    "collect data with this RT SCHED_FIFO priority"),
+	OPT_BOOLEAN('D', "no-delay", &nodelay,
+		    "collect data without buffering"),
 	OPT_BOOLEAN('R', "raw-samples", &raw_samples,
 		    "collect raw sample records from all opened counters"),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,

tools/perf/builtin-sched.c

@@ -1843,15 +1843,15 @@ static const char *record_args[] = {
 	"-f",
 	"-m", "1024",
 	"-c", "1",
-	"-e", "sched:sched_switch:r",
-	"-e", "sched:sched_stat_wait:r",
-	"-e", "sched:sched_stat_sleep:r",
-	"-e", "sched:sched_stat_iowait:r",
-	"-e", "sched:sched_stat_runtime:r",
-	"-e", "sched:sched_process_exit:r",
-	"-e", "sched:sched_process_fork:r",
-	"-e", "sched:sched_wakeup:r",
-	"-e", "sched:sched_migrate_task:r",
+	"-e", "sched:sched_switch",
+	"-e", "sched:sched_stat_wait",
+	"-e", "sched:sched_stat_sleep",
+	"-e", "sched:sched_stat_iowait",
+	"-e", "sched:sched_stat_runtime",
+	"-e", "sched:sched_process_exit",
+	"-e", "sched:sched_process_fork",
+	"-e", "sched:sched_wakeup",
+	"-e", "sched:sched_migrate_task",
 };
 
 static int __cmd_record(int argc, const char **argv)

tools/perf/builtin-stat.c

@@ -743,6 +743,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 out_free_fd:
 	list_for_each_entry(pos, &evsel_list, node)
 		perf_evsel__free_stat_priv(pos);
+	perf_evsel_list__delete();
 out:
 	thread_map__delete(threads);
 	threads = NULL;

tools/perf/builtin-top.c

@@ -1247,8 +1247,6 @@ static void start_counter(int i, struct perf_evsel *evsel)
 				die("Permission error - are you root?\n"
 					"\t Consider tweaking"
 					" /proc/sys/kernel/perf_event_paranoid.\n");
-			if (err == ENOENT)
-				die("%s event is not supported. ", event_name(evsel));
 			/*
 			 * If it's cycles then fall back to hrtimer
 			 * based cpu-clock-tick sw counter, which
@@ -1473,6 +1471,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 		pos->attr.sample_period = default_interval;
 	}
 
+	sym_evsel = list_entry(evsel_list.next, struct perf_evsel, node);
+
 	symbol_conf.priv_size = (sizeof(struct sym_entry) +
 				 (nr_counters + 1) * sizeof(unsigned long));
 
@@ -1490,6 +1490,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 out_free_fd:
 	list_for_each_entry(pos, &evsel_list, node)
 		perf_evsel__free_mmap(pos);
+	perf_evsel_list__delete();
 
 	return status;
 }

tools/perf/perf.c

@@ -286,8 +286,6 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 	status = p->fn(argc, argv, prefix);
 	exit_browser(status);
 
-	perf_evsel_list__delete();
-
 	if (status)
 		return status & 0xff;