Merge remote branch 'tip/auto-latest'

25 files changed, 225 insertions, 73 deletions

diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h
index c1b475a941eb..a9b91ed3d4b9 100644
--- a/arch/powerpc/include/asm/asm-compat.h
+++ b/arch/powerpc/include/asm/asm-compat.h
@@ -28,6 +28,7 @@
 #define PPC_LLARX(t, a, b, eh)	PPC_LDARX(t, a, b, eh)
 #define PPC_STLCX	stringify_in_c(stdcx.)
 #define PPC_CNTLZL	stringify_in_c(cntlzd)
+#define PPC_LR_STKOFF	16
 
 /* Move to CR, single-entry optimized version. Only available
  * on POWER4 and later.
@@ -51,6 +52,7 @@
 #define PPC_STLCX	stringify_in_c(stwcx.)
 #define PPC_CNTLZL	stringify_in_c(cntlzw)
 #define PPC_MTOCRF	stringify_in_c(mtcrf)
+#define PPC_LR_STKOFF	4
 
 #endif
 
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 2d29752cbe16..b485a87c94e1 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -127,3 +127,31 @@ _GLOBAL(__setup_cpu_power7)
 _GLOBAL(__restore_cpu_power7)
 	/* place holder */
 	blr
+
+#ifdef CONFIG_EVENT_TRACING
+/*
+ * Get a minimal set of registers for our caller's nth caller.
+ * r3 = regs pointer, r5 = n.
+ *
+ * We only get R1 (stack pointer), NIP (next instruction pointer)
+ * and LR (link register).  These are all we can get in the
+ * general case without doing complicated stack unwinding, but
+ * fortunately they are enough to do a stack backtrace, which
+ * is all we need them for.
+ */
+_GLOBAL(perf_arch_fetch_caller_regs)
+	mr	r6,r1
+	cmpwi	r5,0
+	mflr	r4
+	ble	2f
+	mtctr	r5
+1:	PPC_LL	r6,0(r6)
+	bdnz	1b
+	PPC_LL	r4,PPC_LR_STKOFF(r6)
+2:	PPC_LL	r7,0(r6)
+	PPC_LL	r7,PPC_LR_STKOFF(r7)
+	PPC_STL	r6,GPR1-STACK_FRAME_OVERHEAD(r3)
+	PPC_STL	r4,_NIP-STACK_FRAME_OVERHEAD(r3)
+	PPC_STL	r7,_LINK-STACK_FRAME_OVERHEAD(r3)
+	blr
+#endif /* CONFIG_EVENT_TRACING */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 635f03bb4995..d07b44f7d1dc 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -82,6 +82,9 @@ enum fixed_addresses {
 #endif
 	FIX_DBGP_BASE,
 	FIX_EARLYCON_MEM_BASE,
+#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
+	FIX_OHCI1394_BASE,
+#endif
 #ifdef CONFIG_X86_LOCAL_APIC
 	FIX_APIC_BASE,	/* local (CPU) APIC) -- required for SMP or not */
 #endif
@@ -132,9 +135,6 @@ enum fixed_addresses {
 	   (__end_of_permanent_fixed_addresses & (TOTAL_FIX_BTMAPS - 1))
 	 : __end_of_permanent_fixed_addresses,
 	FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1,
-#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
-	FIX_OHCI1394_BASE,
-#endif
 #ifdef CONFIG_X86_32
 	FIX_WP_TEST,
 #endif
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index a929c9ede33d..46c0fe05f230 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -133,6 +133,7 @@ extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void);
 
 typedef int vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
+extern void setup_vector_irq(int cpu);
 
 #ifdef CONFIG_X86_IO_APIC
 extern void lock_vector_lock(void);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index e4e0ddcb1546..463de9a858ad 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1268,6 +1268,14 @@ void __setup_vector_irq(int cpu)
 	/* Mark the inuse vectors */
 	for_each_irq_desc(irq, desc) {
 		cfg = desc->chip_data;
+
+		/*
+		 * If it is a legacy IRQ handled by the legacy PIC, this cpu
+		 * will be part of the irq_cfg's domain.
+		 */
+		if (irq < legacy_pic->nr_legacy_irqs && !IO_APIC_IRQ(irq))
+			cpumask_set_cpu(cpu, cfg->domain);
+
 		if (!cpumask_test_cpu(cpu, cfg->domain))
 			continue;
 		vector = cfg->vector;
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index ef257fc2921b..f01d390f9c5b 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -141,6 +141,28 @@ void __init init_IRQ(void)
 	x86_init.irqs.intr_init();
 }
 
+/*
+ * Setup the vector to irq mappings.
+ */
+void setup_vector_irq(int cpu)
+{
+#ifndef CONFIG_X86_IO_APIC
+	int irq;
+
+	/*
+	 * On most of the platforms, legacy PIC delivers the interrupts on the
+	 * boot cpu. But there are certain platforms where PIC interrupts are
+	 * delivered to multiple cpu's. If the legacy IRQ is handled by the
+	 * legacy PIC, for the new cpu that is coming online, setup the static
+	 * legacy vector to irq mapping:
+	 */
+	for (irq = 0; irq < legacy_pic->nr_legacy_irqs; irq++)
+		per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq;
+#endif
+
+	__setup_vector_irq(cpu);
+}
+
 static void __init smp_intr_init(void)
 {
 #ifdef CONFIG_SMP
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a02e80c3c54b..06d98ae5a802 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -247,7 +247,7 @@ static void __cpuinit smp_callin(void)
 	/*
 	 * Need to setup vector mappings before we enable interrupts.
 	 */
-	__setup_vector_irq(smp_processor_id());
+	setup_vector_irq(smp_processor_id());
 	/*
 	 * Get our bogomips.
 	 *
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index 0cf725bdd2a1..fc53492b6ad7 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -73,6 +73,7 @@ enum clock_event_nofitiers {
  * @list:		list head for the management code
  * @mode:		operating mode assigned by the management code
  * @next_event:		local storage for the next event in oneshot mode
+ * @retries:		number of forced programming retries
  */
 struct clock_event_device {
 	const char		*name;
@@ -93,6 +94,7 @@ struct clock_event_device {
 	struct list_head	list;
 	enum clock_event_mode	mode;
 	ktime_t			next_event;
+	unsigned long		retries;
 };
 
 /*
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 3024050c82a1..e1bdc4bfd275 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -123,22 +123,11 @@ static inline int rcu_read_lock_held(void)
 	return lock_is_held(&rcu_lock_map);
 }
 
-/**
- * rcu_read_lock_bh_held - might we be in RCU-bh read-side critical section?
- *
- * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in
- * an RCU-bh read-side critical section.  In absence of CONFIG_PROVE_LOCKING,
- * this assumes we are in an RCU-bh read-side critical section unless it can
- * prove otherwise.
- *
- * Check rcu_scheduler_active to prevent false positives during boot.
+/*
+ * rcu_read_lock_bh_held() is defined out of line to avoid #include-file
+ * hell.
  */
-static inline int rcu_read_lock_bh_held(void)
-{
-	if (!debug_lockdep_rcu_enabled())
-		return 1;
-	return lock_is_held(&rcu_bh_lock_map);
-}
+extern int rcu_read_lock_bh_held(void);
 
 /**
  * rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section?
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index f59604ed0ec6..78b4bd3be496 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -49,7 +49,7 @@ struct tracepoint {
 		void **it_func;						\
 									\
 		rcu_read_lock_sched_notrace();				\
-		it_func = rcu_dereference((tp)->funcs);			\
+		it_func = rcu_dereference_sched((tp)->funcs);		\
 		if (it_func) {						\
 			do {						\
 				((void(*)(proto))(*it_func))(args);	\
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 42ec11b2af8a..bbba58564396 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -359,6 +359,23 @@ static inline void mask_ack_irq(struct irq_desc *desc, int irq)
 		if (desc->chip->ack)
 			desc->chip->ack(irq);
 	}
+	desc->status |= IRQ_MASKED;
+}
+
+static inline void mask_irq(struct irq_desc *desc, int irq)
+{
+	if (desc->chip->mask) {
+		desc->chip->mask(irq);
+		desc->status |= IRQ_MASKED;
+	}
+}
+
+static inline void unmask_irq(struct irq_desc *desc, int irq)
+{
+	if (desc->chip->unmask) {
+		desc->chip->unmask(irq);
+		desc->status &= ~IRQ_MASKED;
+	}
 }
 
 /*
@@ -484,10 +501,8 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 	raw_spin_lock(&desc->lock);
 	desc->status &= ~IRQ_INPROGRESS;
 
-	if (unlikely(desc->status & IRQ_ONESHOT))
-		desc->status |= IRQ_MASKED;
-	else if (!(desc->status & IRQ_DISABLED) && desc->chip->unmask)
-		desc->chip->unmask(irq);
+	if (!(desc->status & (IRQ_DISABLED | IRQ_ONESHOT)))
+		unmask_irq(desc, irq);
 out_unlock:
 	raw_spin_unlock(&desc->lock);
 }
@@ -524,8 +539,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	action = desc->action;
 	if (unlikely(!action || (desc->status & IRQ_DISABLED))) {
 		desc->status |= IRQ_PENDING;
-		if (desc->chip->mask)
-			desc->chip->mask(irq);
+		mask_irq(desc, irq);
 		goto out;
 	}
 
@@ -593,7 +607,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		irqreturn_t action_ret;
 
 		if (unlikely(!action)) {
-			desc->chip->mask(irq);
+			mask_irq(desc, irq);
 			goto out_unlock;
 		}
 
@@ -605,8 +619,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		if (unlikely((desc->status &
 			       (IRQ_PENDING | IRQ_MASKED | IRQ_DISABLED)) ==
 			      (IRQ_PENDING | IRQ_MASKED))) {
-			desc->chip->unmask(irq);
-			desc->status &= ~IRQ_MASKED;
+			unmask_irq(desc, irq);
 		}
 
 		desc->status &= ~IRQ_PENDING;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index eb6078ca60c7..69a3d7b9414c 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -483,8 +483,26 @@ static int irq_wait_for_interrupt(struct irqaction *action)
  */
 static void irq_finalize_oneshot(unsigned int irq, struct irq_desc *desc)
 {
+again:
 	chip_bus_lock(irq, desc);
 	raw_spin_lock_irq(&desc->lock);
+
+	/*
+	 * Implausible though it may be we need to protect us against
+	 * the following scenario:
+	 *
+	 * The thread is faster done than the hard interrupt handler
+	 * on the other CPU. If we unmask the irq line then the
+	 * interrupt can come in again and masks the line, leaves due
+	 * to IRQ_INPROGRESS and the irq line is masked forever.
+	 */
+	if (unlikely(desc->status & IRQ_INPROGRESS)) {
+		raw_spin_unlock_irq(&desc->lock);
+		chip_bus_sync_unlock(irq, desc);
+		cpu_relax();
+		goto again;
+	}
+
 	if (!(desc->status & IRQ_DISABLED) && (desc->status & IRQ_MASKED)) {
 		desc->status &= ~IRQ_MASKED;
 		desc->chip->unmask(irq);
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index ec48e1286db0..2807ef88acbe 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -1061,9 +1061,9 @@ static void check_thread_timers(struct task_struct *tsk,
 	}
 }
 
-static void stop_process_timers(struct task_struct *tsk)
+static void stop_process_timers(struct signal_struct *sig)
 {
-	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+	struct thread_group_cputimer *cputimer = &sig->cputimer;
 	unsigned long flags;
 
 	if (!cputimer->running)
@@ -1072,6 +1072,10 @@ static void stop_process_timers(struct task_struct *tsk)
 	spin_lock_irqsave(&cputimer->lock, flags);
 	cputimer->running = 0;
 	spin_unlock_irqrestore(&cputimer->lock, flags);
+
+	sig->cputime_expires.prof_exp = cputime_zero;
+	sig->cputime_expires.virt_exp = cputime_zero;
+	sig->cputime_expires.sched_exp = 0;
 }
 
 static u32 onecputick;
@@ -1133,7 +1137,7 @@ static void check_process_timers(struct task_struct *tsk,
 	    list_empty(&timers[CPUCLOCK_VIRT]) &&
 	    cputime_eq(sig->it[CPUCLOCK_VIRT].expires, cputime_zero) &&
 	    list_empty(&timers[CPUCLOCK_SCHED])) {
-		stop_process_timers(tsk);
+		stop_process_timers(sig);
 		return;
 	}
 
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index f1125c1a6321..63fe25433980 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -45,6 +45,7 @@
 #include <linux/mutex.h>
 #include <linux/module.h>
 #include <linux/kernel_stat.h>
+#include <linux/hardirq.h>
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 static struct lock_class_key rcu_lock_key;
@@ -66,6 +67,28 @@ EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
 int rcu_scheduler_active __read_mostly;
 EXPORT_SYMBOL_GPL(rcu_scheduler_active);
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+/**
+ * rcu_read_lock_bh_held - might we be in RCU-bh read-side critical section?
+ *
+ * Check for bottom half being disabled, which covers both the
+ * CONFIG_PROVE_RCU and not cases.  Note that if someone uses
+ * rcu_read_lock_bh(), but then later enables BH, lockdep (if enabled)
+ * will show the situation.
+ *
+ * Check debug_lockdep_rcu_enabled() to prevent false positives during boot.
+ */
+int rcu_read_lock_bh_held(void)
+{
+	if (!debug_lockdep_rcu_enabled())
+		return 1;
+	return in_softirq();
+}
+EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
+
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
 /*
  * This function is invoked towards the end of the scheduler's initialization
  * process.  Before this is called, the idle task might contain
diff --git a/kernel/sched.c b/kernel/sched.c
index 1894d4048ebb..425f1ae589b6 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2650,7 +2650,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 {
 	unsigned long flags;
 	struct rq *rq;
-	int cpu = get_cpu();
+	int cpu __maybe_unused = get_cpu();
 
 #ifdef CONFIG_SMP
 	/*
@@ -4902,7 +4902,9 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
 	int ret;
 	cpumask_var_t mask;
 
-	if (len < cpumask_size())
+	if (len < nr_cpu_ids)
+		return -EINVAL;
+	if (len & (sizeof(unsigned long)-1))
 		return -EINVAL;
 
 	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
@@ -4910,10 +4912,12 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
 
 	ret = sched_getaffinity(pid, mask);
 	if (ret == 0) {
-		if (copy_to_user(user_mask_ptr, mask, cpumask_size()))
+		size_t retlen = min_t(size_t, len, cpumask_size());
+
+		if (copy_to_user(user_mask_ptr, mask, retlen))
 			ret = -EFAULT;
 		else
-			ret = cpumask_size();
+			ret = retlen;
 	}
 	free_cpumask_var(mask);
 
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 0a8a213016f0..aada0e52680a 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -22,6 +22,29 @@
 
 #include "tick-internal.h"
 
+/* Limit min_delta to a jiffie */
+#define MIN_DELTA_LIMIT		(NSEC_PER_SEC / HZ)
+
+static int tick_increase_min_delta(struct clock_event_device *dev)
+{
+	/* Nothing to do if we already reached the limit */
+	if (dev->min_delta_ns >= MIN_DELTA_LIMIT)
+		return -ETIME;
+
+	if (dev->min_delta_ns < 5000)
+		dev->min_delta_ns = 5000;
+	else
+		dev->min_delta_ns += dev->min_delta_ns >> 1;
+
+	if (dev->min_delta_ns > MIN_DELTA_LIMIT)
+		dev->min_delta_ns = MIN_DELTA_LIMIT;
+
+	printk(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n",
+	       dev->name ? dev->name : "?",
+	       (unsigned long long) dev->min_delta_ns);
+	return 0;
+}
+
 /**
  * tick_program_event internal worker function
  */
@@ -37,23 +60,28 @@ int tick_dev_program_event(struct clock_event_device *dev, ktime_t expires,
 		if (!ret || !force)
 			return ret;
 
+		dev->retries++;
 		/*
-		 * We tried 2 times to program the device with the given
-		 * min_delta_ns. If that's not working then we double it
+		 * We tried 3 times to program the device with the given
+		 * min_delta_ns. If that's not working then we increase it
 		 * and emit a warning.
 		 */
 		if (++i > 2) {
 			/* Increase the min. delta and try again */
-			if (!dev->min_delta_ns)
-				dev->min_delta_ns = 5000;
-			else
-				dev->min_delta_ns += dev->min_delta_ns >> 1;
-
-			printk(KERN_WARNING
-			       "CE: %s increasing min_delta_ns to %llu nsec\n",
-			       dev->name ? dev->name : "?",
-			       (unsigned long long) dev->min_delta_ns << 1);
-
+			if (tick_increase_min_delta(dev)) {
+				/*
+				 * Get out of the loop if min_delta_ns
+				 * hit the limit already. That's
+				 * better than staying here forever.
+				 *
+				 * We clear next_event so we have a
+				 * chance that the box survives.
+				 */
+				printk(KERN_WARNING
+				       "CE: Reprogramming failure. Giving up\n");
+				dev->next_event.tv64 = KTIME_MAX;
+				return -ETIME;
+			}
 			i = 0;
 		}
 
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index bdfb8dd1050c..1a4a7dd78777 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -228,6 +228,7 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
 	SEQ_printf(m, " event_handler:  ");
 	print_name_offset(m, dev->event_handler);
 	SEQ_printf(m, "\n");
+	SEQ_printf(m, " retries:        %lu\n", dev->retries);
 }
 
 static void timer_list_show_tickdevices(struct seq_file *m)
@@ -257,7 +258,7 @@ static int timer_list_show(struct seq_file *m, void *v)
 	u64 now = ktime_to_ns(ktime_get());
 	int cpu;
 
-	SEQ_printf(m, "Timer List Version: v0.5\n");
+	SEQ_printf(m, "Timer List Version: v0.6\n");
 	SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
 	SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
 
diff --git a/kernel/timer.c b/kernel/timer.c
index c61a7949387f..fc965eae0e87 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -880,6 +880,7 @@ int try_to_del_timer_sync(struct timer_list *timer)
 	if (base->running_timer == timer)
 		goto out;
 
+	timer_stats_timer_clear_start_info(timer);
 	ret = 0;
 	if (timer_pending(timer)) {
 		detach_timer(timer, 1);
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index c30a33592340..152d6c9b1fa4 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -47,7 +47,6 @@
 #include "util/probe-event.h"
 
 #define MAX_PATH_LEN 256
-#define MAX_PROBES 128
 
 /* Session management structure */
 static struct {
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 0b719e3dde05..1f529321607e 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -455,7 +455,7 @@ static void print_sym_table(void)
 	struct sym_entry *syme, *n;
 	struct rb_root tmp = RB_ROOT;
 	struct rb_node *nd;
-	int sym_width = 0, dso_width = 0, max_dso_width;
+	int sym_width = 0, dso_width = 0, dso_short_width = 0;
 	const int win_width = winsize.ws_col - 1;
 
 	samples = userspace_samples = 0;
@@ -545,15 +545,20 @@ static void print_sym_table(void)
 		if (syme->map->dso->long_name_len > dso_width)
 			dso_width = syme->map->dso->long_name_len;
 
+		if (syme->map->dso->short_name_len > dso_short_width)
+			dso_short_width = syme->map->dso->short_name_len;
+
 		if (syme->name_len > sym_width)
 			sym_width = syme->name_len;
 	}
 
 	printed = 0;
 
-	max_dso_width = winsize.ws_col - sym_width - 29;
-	if (dso_width > max_dso_width)
-		dso_width = max_dso_width;
+	if (sym_width + dso_width > winsize.ws_col - 29) {
+		dso_width = dso_short_width;
+		if (sym_width + dso_width > winsize.ws_col - 29)
+			sym_width = winsize.ws_col - dso_width - 29;
+	}
 	putchar('\n');
 	if (nr_counters == 1)
 		printf("             samples  pcnt");
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 53181dbfe4a8..7c004b6ef24f 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -242,7 +242,7 @@ void parse_perf_probe_event(const char *str, struct probe_point *pp,
 
 	/* Parse probe point */
 	parse_perf_probe_probepoint(argv[0], pp);
-	if (pp->file || pp->line)
+	if (pp->file || pp->line || pp->lazy_line)
 		*need_dwarf = true;
 
 	/* Copy arguments and ensure return probe has no C argument */
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 1e6c65ebbd80..c171a243d05b 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -333,8 +333,8 @@ static void show_location(Dwarf_Op *op, struct probe_finder *pf)
 		die("%u exceeds max register number.", regn);
 
 	if (deref)
-		ret = snprintf(pf->buf, pf->len, " %s=+%ju(%s)",
-			       pf->var, (uintmax_t)offs, regs);
+		ret = snprintf(pf->buf, pf->len, " %s=%+jd(%s)",
+			       pf->var, (intmax_t)offs, regs);
 	else
 		ret = snprintf(pf->buf, pf->len, " %s=%s", pf->var, regs);
 	DIE_IF(ret < 0);
@@ -352,8 +352,7 @@ static void show_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 	if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
 		goto error;
 	/* TODO: handle more than 1 exprs */
-	ret = dwarf_getlocation_addr(&attr, (pf->addr - pf->cu_base),
-				     &expr, &nexpr, 1);
+	ret = dwarf_getlocation_addr(&attr, pf->addr, &expr, &nexpr, 1);
 	if (ret <= 0 || nexpr == 0)
 		goto error;
 
@@ -437,8 +436,7 @@ static void show_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
 
 	/* Get the frame base attribute/ops */
 	dwarf_attr(sp_die, DW_AT_frame_base, &fb_attr);
-	ret = dwarf_getlocation_addr(&fb_attr, (pf->addr - pf->cu_base),
-				     &pf->fb_ops, &nops, 1);
+	ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1);
 	if (ret <= 0 || nops == 0)
 		pf->fb_ops = NULL;
 
@@ -455,6 +453,9 @@ static void show_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
 	/* *pf->fb_ops will be cached in libdw. Don't free it. */
 	pf->fb_ops = NULL;
 
+	if (pp->found == MAX_PROBES)
+		die("Too many( > %d) probe point found.\n", MAX_PROBES);
+
 	pp->probes[pp->found] = strdup(tmp);
 	pp->found++;
 }
@@ -641,7 +642,6 @@ static void find_probe_point_by_func(struct probe_finder *pf)
 int find_probe_point(int fd, struct probe_point *pp)
 {
 	struct probe_finder pf = {.pp = pp};
-	int ret;
 	Dwarf_Off off, noff;
 	size_t cuhl;
 	Dwarf_Die *diep;
@@ -668,10 +668,6 @@ int find_probe_point(int fd, struct probe_point *pp)
 			pf.fname = NULL;
 
 		if (!pp->file || pf.fname) {
-			/* Save CU base address (for frame_base) */
-			ret = dwarf_lowpc(&pf.cu_die, &pf.cu_base);
-			if (ret != 0)
-				pf.cu_base = 0;
 			if (pp->function)
 				find_probe_point_by_func(&pf);
 			else if (pp->lazy_line)
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index d1a651793ba6..21f7354397b4 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -71,7 +71,6 @@ struct probe_finder {
 
 	/* For variable searching */
 	Dwarf_Op		*fb_ops;	/* Frame base attribute */
-	Dwarf_Addr		cu_base;	/* Current CU base address */
 	const char		*var;		/* Current variable name */
 	char			*buf;		/* Current output buffer */
 	int			len;		/* Length of output buffer */
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 323c0aea0a91..c458c4a371d1 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -163,9 +163,17 @@ void dso__set_long_name(struct dso *self, char *name)
 	self->long_name_len = strlen(name);
 }
 
+static void dso__set_short_name(struct dso *self, const char *name)
+{
+	if (name == NULL)
+		return;
+	self->short_name = name;
+	self->short_name_len = strlen(name);
+}
+
 static void dso__set_basename(struct dso *self)
 {
-	self->short_name = basename(self->long_name);
+	dso__set_short_name(self, basename(self->long_name));
 }
 
 struct dso *dso__new(const char *name)
@@ -176,7 +184,7 @@ struct dso *dso__new(const char *name)
 		int i;
 		strcpy(self->name, name);
 		dso__set_long_name(self, self->name);
-		self->short_name = self->name;
+		dso__set_short_name(self, self->name);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			self->symbols[i] = self->symbol_names[i] = RB_ROOT;
 		self->slen_calculated = 0;
@@ -897,7 +905,6 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 	struct kmap *kmap = self->kernel ? map__kmap(map) : NULL;
 	struct map *curr_map = map;
 	struct dso *curr_dso = self;
-	size_t dso_name_len = strlen(self->short_name);
 	Elf_Data *symstrs, *secstrs;
 	uint32_t nr_syms;
 	int err = -1;
@@ -987,7 +994,8 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 			char dso_name[PATH_MAX];
 
 			if (strcmp(section_name,
-				   curr_dso->short_name + dso_name_len) == 0)
+				   (curr_dso->short_name +
+				    self->short_name_len)) == 0)
 				goto new_symbol;
 
 			if (strcmp(section_name, ".text") == 0) {
@@ -1782,7 +1790,7 @@ struct dso *dso__new_kernel(const char *name)
 	struct dso *self = dso__new(name ?: "[kernel.kallsyms]");
 
 	if (self != NULL) {
-		self->short_name = "[kernel]";
+		dso__set_short_name(self, "[kernel]");
 		self->kernel	 = 1;
 	}
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 280dadd32a08..f30a37428919 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -110,9 +110,10 @@ struct dso {
 	u8		 sorted_by_name;
 	u8		 loaded;
 	u8		 build_id[BUILD_ID_SIZE];
-	u16		 long_name_len;
 	const char	 *short_name;
 	char	 	 *long_name;
+	u16		 long_name_len;
+	u16		 short_name_len;
 	char		 name[0];
 };