Merge branch 'fixes-2.6.39' into for-2.6.40

13 files changed, 88 insertions, 60 deletions

diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index bd3e8e29caa3..6bc6e3bc4f9c 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -78,7 +78,7 @@ static unsigned int kdb_continue_catastrophic;
 static kdbtab_t *kdb_commands;
 #define KDB_BASE_CMD_MAX 50
 static int kdb_max_commands = KDB_BASE_CMD_MAX;
-static kdbtab_t kdb_base_commands[50];
+static kdbtab_t kdb_base_commands[KDB_BASE_CMD_MAX];
 #define for_each_kdbcmd(cmd, num)					\
 	for ((cmd) = kdb_base_commands, (num) = 0;			\
 	     num < kdb_max_commands;					\
@@ -2892,7 +2892,7 @@ static void __init kdb_inittab(void)
 	  "Send a signal to a process", 0, KDB_REPEAT_NONE);
 	kdb_register_repeat("summary", kdb_summary, "",
 	  "Summarize the system", 4, KDB_REPEAT_NONE);
-	kdb_register_repeat("per_cpu", kdb_per_cpu, "",
+	kdb_register_repeat("per_cpu", kdb_per_cpu, "<sym> [<bytes>] [<cpu>]",
 	  "Display per_cpu variables", 3, KDB_REPEAT_NONE);
 	kdb_register_repeat("grephelp", kdb_grep_help, "",
 	  "Display help on | grep", 0, KDB_REPEAT_NONE);
diff --git a/kernel/futex.c b/kernel/futex.c
index 6570c459f31c..dfb924ffe65b 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -782,8 +782,8 @@ static void __unqueue_futex(struct futex_q *q)
 {
 	struct futex_hash_bucket *hb;
 
-	if (WARN_ON(!q->lock_ptr || !spin_is_locked(q->lock_ptr)
-			|| plist_node_empty(&q->list)))
+	if (WARN_ON_SMP(!q->lock_ptr || !spin_is_locked(q->lock_ptr))
+	    || WARN_ON(plist_node_empty(&q->list)))
 		return;
 
 	hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock);
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 09bef82d74cb..00f2c037267a 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -31,6 +31,10 @@ config GENERIC_IRQ_PROBE
 config GENERIC_IRQ_SHOW
        bool
 
+# Print level/edge extra information
+config GENERIC_IRQ_SHOW_LEVEL
+       bool
+
 # Support for delayed migration from interrupt context
 config GENERIC_PENDING_IRQ
 	bool
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index dbccc799407f..6fb014f172f7 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -198,15 +198,6 @@ err:
 	return -ENOMEM;
 }
 
-struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
-{
-	int res = irq_alloc_descs(irq, irq, 1, node);
-
-	if (res == -EEXIST || res == irq)
-		return irq_to_desc(irq);
-	return NULL;
-}
-
 static int irq_expand_nr_irqs(unsigned int nr)
 {
 	if (nr > IRQ_BITMAP_BITS)
@@ -283,11 +274,6 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 	return (irq < NR_IRQS) ? irq_desc + irq : NULL;
 }
 
-struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node)
-{
-	return irq_to_desc(irq);
-}
-
 static void free_desc(unsigned int irq)
 {
 	dynamic_irq_cleanup(irq);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 760248de109d..626d092eed9a 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -404,7 +404,20 @@ int show_interrupts(struct seq_file *p, void *v)
 	seq_printf(p, "%*d: ", prec, i);
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
-	seq_printf(p, " %8s", desc->irq_data.chip->name);
+
+	if (desc->irq_data.chip) {
+		if (desc->irq_data.chip->irq_print_chip)
+			desc->irq_data.chip->irq_print_chip(&desc->irq_data, p);
+		else if (desc->irq_data.chip->name)
+			seq_printf(p, " %8s", desc->irq_data.chip->name);
+		else
+			seq_printf(p, " %8s", "-");
+	} else {
+		seq_printf(p, " %8s", "None");
+	}
+#ifdef CONFIG_GENIRC_IRQ_SHOW_LEVEL
+	seq_printf(p, " %-8s", irqd_is_level_type(&desc->irq_data) ? "Level" : "Edge");
+#endif
 	if (desc->name)
 		seq_printf(p, "-%-8s", desc->name);
 
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index a56aa58b9cb0..079f1d39a8b8 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -342,13 +342,15 @@ int lookup_symbol_attrs(unsigned long addr, unsigned long *size,
 }
 
 /* Look up a kernel symbol and return it in a text buffer. */
-int sprint_symbol(char *buffer, unsigned long address)
+static int __sprint_symbol(char *buffer, unsigned long address,
+			   int symbol_offset)
 {
 	char *modname;
 	const char *name;
 	unsigned long offset, size;
 	int len;
 
+	address += symbol_offset;
 	name = kallsyms_lookup(address, &size, &offset, &modname, buffer);
 	if (!name)
 		return sprintf(buffer, "0x%lx", address);
@@ -357,17 +359,53 @@ int sprint_symbol(char *buffer, unsigned long address)
 		strcpy(buffer, name);
 	len = strlen(buffer);
 	buffer += len;
+	offset -= symbol_offset;
 
 	if (modname)
-		len += sprintf(buffer, "+%#lx/%#lx [%s]",
-						offset, size, modname);
+		len += sprintf(buffer, "+%#lx/%#lx [%s]", offset, size, modname);
 	else
 		len += sprintf(buffer, "+%#lx/%#lx", offset, size);
 
 	return len;
 }
+
+/**
+ * sprint_symbol - Look up a kernel symbol and return it in a text buffer
+ * @buffer: buffer to be stored
+ * @address: address to lookup
+ *
+ * This function looks up a kernel symbol with @address and stores its name,
+ * offset, size and module name to @buffer if possible. If no symbol was found,
+ * just saves its @address as is.
+ *
+ * This function returns the number of bytes stored in @buffer.
+ */
+int sprint_symbol(char *buffer, unsigned long address)
+{
+	return __sprint_symbol(buffer, address, 0);
+}
+
 EXPORT_SYMBOL_GPL(sprint_symbol);
 
+/**
+ * sprint_backtrace - Look up a backtrace symbol and return it in a text buffer
+ * @buffer: buffer to be stored
+ * @address: address to lookup
+ *
+ * This function is for stack backtrace and does the same thing as
+ * sprint_symbol() but with modified/decreased @address. If there is a
+ * tail-call to the function marked "noreturn", gcc optimized out code after
+ * the call so that the stack-saved return address could point outside of the
+ * caller. This function ensures that kallsyms will find the original caller
+ * by decreasing @address.
+ *
+ * This function returns the number of bytes stored in @buffer.
+ */
+int sprint_backtrace(char *buffer, unsigned long address)
+{
+	return __sprint_symbol(buffer, address, -1);
+}
+
 /* Look up a kernel symbol and print it to the kernel messages. */
 void __print_symbol(const char *fmt, unsigned long address)
 {
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index 1969d2fc4b36..71edd2f60c02 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -225,7 +225,7 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 		      nr_irq_read_safe = 0, nr_irq_read_unsafe = 0,
 		      nr_softirq_read_safe = 0, nr_softirq_read_unsafe = 0,
 		      nr_hardirq_read_safe = 0, nr_hardirq_read_unsafe = 0,
-		      sum_forward_deps = 0, factor = 0;
+		      sum_forward_deps = 0;
 
 	list_for_each_entry(class, &all_lock_classes, lock_entry) {
 
@@ -283,13 +283,6 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 			nr_hardirq_unsafe * nr_hardirq_safe +
 			nr_list_entries);
 
-	/*
-	 * Estimated factor between direct and indirect
-	 * dependencies:
-	 */
-	if (nr_list_entries)
-		factor = sum_forward_deps / nr_list_entries;
-
 #ifdef CONFIG_PROVE_LOCKING
 	seq_printf(m, " dependency chains:             %11lu [max: %lu]\n",
 			nr_lock_chains, MAX_LOCKDEP_CHAINS);
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 3472bb1a070c..c75925c4d1e2 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -145,7 +145,8 @@ static struct srcu_struct pmus_srcu;
  */
 int sysctl_perf_event_paranoid __read_mostly = 1;
 
-int sysctl_perf_event_mlock __read_mostly = 512; /* 'free' kb per user */
+/* Minimum for 128 pages + 1 for the user control page */
+int sysctl_perf_event_mlock __read_mostly = 516; /* 'free' kb per user */
 
 /*
  * max perf event sample rate
@@ -941,6 +942,7 @@ static void perf_group_attach(struct perf_event *event)
 static void
 list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 {
+	struct perf_cpu_context *cpuctx;
 	/*
 	 * We can have double detach due to exit/hot-unplug + close.
 	 */
@@ -949,8 +951,17 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 
 	event->attach_state &= ~PERF_ATTACH_CONTEXT;
 
-	if (is_cgroup_event(event))
+	if (is_cgroup_event(event)) {
 		ctx->nr_cgroups--;
+		cpuctx = __get_cpu_context(ctx);
+		/*
+		 * if there are no more cgroup events
+		 * then cler cgrp to avoid stale pointer
+		 * in update_cgrp_time_from_cpuctx()
+		 */
+		if (!ctx->nr_cgroups)
+			cpuctx->cgrp = NULL;
+	}
 
 	ctx->nr_events--;
 	if (event->attr.inherit_stat)
diff --git a/kernel/sched.c b/kernel/sched.c
index ae659b99ce73..f592ce6f8616 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5473,6 +5473,8 @@ EXPORT_SYMBOL(yield);
  * yield_to - yield the current processor to another thread in
  * your thread group, or accelerate that thread toward the
  * processor it's on.
+ * @p: target task
+ * @preempt: whether task preemption is allowed or not
  *
  * It's the caller's job to ensure that the target task struct
  * can't go away on us before we can do any checks.
@@ -8449,7 +8451,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se;
-	struct rq *rq;
 	int i;
 
 	tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
@@ -8462,8 +8463,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	tg->shares = NICE_0_LOAD;
 
 	for_each_possible_cpu(i) {
-		rq = cpu_rq(i);
-
 		cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
 				      GFP_KERNEL, cpu_to_node(i));
 		if (!cfs_rq)
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index c82f26c1b7c3..a776a6396427 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -94,6 +94,4 @@ static const struct sched_class idle_sched_class = {
 
 	.prio_changed		= prio_changed_idle,
 	.switched_to		= switched_to_idle,
-
-	/* no .task_new for idle tasks */
 };
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
index 84ec9bcf82d9..1ba2bd40fdac 100644
--- a/kernel/sched_stoptask.c
+++ b/kernel/sched_stoptask.c
@@ -102,6 +102,4 @@ static const struct sched_class stop_sched_class = {
 
 	.prio_changed		= prio_changed_stop,
 	.switched_to		= switched_to_stop,
-
-	/* no .task_new for stop tasks */
 };
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 3bd7e3d5c632..8ad5d576755e 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -14,7 +14,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/clocksource.h>
 #include <linux/jiffies.h>
 #include <linux/time.h>
@@ -597,13 +597,12 @@ static struct timespec timekeeping_suspend_time;
 
 /**
  * timekeeping_resume - Resumes the generic timekeeping subsystem.
- * @dev:	unused
  *
  * This is for the generic clocksource timekeeping.
  * xtime/wall_to_monotonic/jiffies/etc are
  * still managed by arch specific suspend/resume code.
  */
-static int timekeeping_resume(struct sys_device *dev)
+static void timekeeping_resume(void)
 {
 	unsigned long flags;
 	struct timespec ts;
@@ -632,11 +631,9 @@ static int timekeeping_resume(struct sys_device *dev)
 
 	/* Resume hrtimers */
 	hres_timers_resume();
-
-	return 0;
 }
 
-static int timekeeping_suspend(struct sys_device *dev, pm_message_t state)
+static int timekeeping_suspend(void)
 {
 	unsigned long flags;
 
@@ -654,26 +651,18 @@ static int timekeeping_suspend(struct sys_device *dev, pm_message_t state)
 }
 
 /* sysfs resume/suspend bits for timekeeping */
-static struct sysdev_class timekeeping_sysclass = {
-	.name		= "timekeeping",
+static struct syscore_ops timekeeping_syscore_ops = {
 	.resume		= timekeeping_resume,
 	.suspend	= timekeeping_suspend,
 };
 
-static struct sys_device device_timer = {
-	.id		= 0,
-	.cls		= &timekeeping_sysclass,
-};
-
-static int __init timekeeping_init_device(void)
+static int __init timekeeping_init_ops(void)
 {
-	int error = sysdev_class_register(&timekeeping_sysclass);
-	if (!error)
-		error = sysdev_register(&device_timer);
-	return error;
+	register_syscore_ops(&timekeeping_syscore_ops);
+	return 0;
 }
 
-device_initcall(timekeeping_init_device);
+device_initcall(timekeeping_init_ops);
 
 /*
  * If the error is already larger, we look ahead even further
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 888b611897d3..c075f4ea6b94 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1467,7 +1467,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 		return t_hash_next(m, pos);
 
 	(*pos)++;
-	iter->pos = *pos;
+	iter->pos = iter->func_pos = *pos;
 
 	if (iter->flags & FTRACE_ITER_PRINTALL)
 		return t_hash_start(m, pos);
@@ -1502,7 +1502,6 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 	if (!rec)
 		return t_hash_start(m, pos);
 
-	iter->func_pos = *pos;
 	iter->func = rec;
 
 	return iter;