9 files changed, 136 insertions, 102 deletions

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index bda9cb924276..eb2bfefa6dcc 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -32,7 +32,6 @@
  */
 
 #include <linux/cpu.h>
-#include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/hrtimer.h>
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 650ce4102a63..cc0f7321b8ce 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -40,9 +40,6 @@ unsigned long probe_irq_on(void)
          * flush such a longstanding irq before considering it as spurious.
          */
         for_each_irq_desc_reverse(i, desc) {
-                if (!desc)
-                        continue;
-
                 spin_lock_irq(&desc->lock);
                 if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
                         /*
@@ -71,9 +68,6 @@ unsigned long probe_irq_on(void)
          * happened in the previous stage, it may have masked itself)
          */
         for_each_irq_desc_reverse(i, desc) {
-                if (!desc)
-                        continue;
-
                 spin_lock_irq(&desc->lock);
                 if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
                         desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
@@ -92,9 +86,6 @@ unsigned long probe_irq_on(void)
          * Now filter out any obviously spurious interrupts
          */
         for_each_irq_desc(i, desc) {
-                if (!desc)
-                        continue;
-
                 spin_lock_irq(&desc->lock);
                 status = desc->status;
 
@@ -133,9 +124,6 @@ unsigned int probe_irq_mask(unsigned long val)
         int i;
 
         for_each_irq_desc(i, desc) {
-                if (!desc)
-                        continue;
-
                 spin_lock_irq(&desc->lock);
                 status = desc->status;
 
@@ -178,9 +166,6 @@ int probe_irq_off(unsigned long val)
         unsigned int status;
 
         for_each_irq_desc(i, desc) {
-                if (!desc)
-                        continue;
-
                 spin_lock_irq(&desc->lock);
                 status = desc->status;
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 6492400cb50d..c20db0be9173 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -56,10 +56,6 @@ void handle_bad_irq(unsigned int irq, struct irq_desc *desc)
 int nr_irqs = NR_IRQS;
 EXPORT_SYMBOL_GPL(nr_irqs);
 
-void __init __attribute__((weak)) arch_early_irq_init(void)
-{
-}
-
 #ifdef CONFIG_SPARSE_IRQ
 static struct irq_desc irq_desc_init = {
         .irq        = -1,
@@ -90,13 +86,11 @@ void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
                 desc->kstat_irqs = (unsigned int *)ptr;
 }
 
-void __attribute__((weak)) arch_init_chip_data(struct irq_desc *desc, int cpu)
-{
-}
-
 static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
 {
         memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
+
+        spin_lock_init(&desc->lock);
         desc->irq = irq;
 #ifdef CONFIG_SMP
         desc->cpu = cpu;
@@ -134,7 +128,7 @@ static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_sm
 /* FIXME: use bootmem alloc ...*/
 static unsigned int kstat_irqs_legacy[NR_IRQS_LEGACY][NR_CPUS];
 
-void __init early_irq_init(void)
+int __init early_irq_init(void)
 {
         struct irq_desc *desc;
         int legacy_count;
@@ -146,6 +140,7 @@ void __init early_irq_init(void)
         for (i = 0; i < legacy_count; i++) {
                 desc[i].irq = i;
                 desc[i].kstat_irqs = kstat_irqs_legacy[i];
+                lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
 
                 irq_desc_ptrs[i] = desc + i;
         }
@@ -153,7 +148,7 @@ void __init early_irq_init(void)
         for (i = legacy_count; i < NR_IRQS; i++)
                 irq_desc_ptrs[i] = NULL;
 
-        arch_early_irq_init();
+        return arch_early_irq_init();
 }
 
 struct irq_desc *irq_to_desc(unsigned int irq)
@@ -203,7 +198,7 @@ out_unlock:
         return desc;
 }
 
-#else
+#else /* !CONFIG_SPARSE_IRQ */
 
 struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
         [0 ... NR_IRQS-1] = {
@@ -218,7 +213,31 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
         }
 };
 
-#endif
+int __init early_irq_init(void)
+{
+        struct irq_desc *desc;
+        int count;
+        int i;
+
+        desc = irq_desc;
+        count = ARRAY_SIZE(irq_desc);
+
+        for (i = 0; i < count; i++)
+                desc[i].irq = i;
+
+        return arch_early_irq_init();
+}
+
+struct irq_desc *irq_to_desc(unsigned int irq)
+{
+        return (irq < NR_IRQS) ? irq_desc + irq : NULL;
+}
+
+struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
+{
+        return irq_to_desc(irq);
+}
+#endif /* !CONFIG_SPARSE_IRQ */
 
 /*
  * What should we do if we get a hw irq event on an illegal vector?
@@ -428,9 +447,6 @@ void early_init_irq_lock_class(void)
         int i;
 
         for_each_irq_desc(i, desc) {
-                if (!desc)
-                        continue;
-
                 lockdep_set_class(&desc->lock, &irq_desc_lock_class);
         }
 }
@@ -439,7 +455,7 @@ void early_init_irq_lock_class(void)
 unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 {
         struct irq_desc *desc = irq_to_desc(irq);
-        return desc->kstat_irqs[cpu];
+        return desc ? desc->kstat_irqs[cpu] : 0;
 }
 #endif
 EXPORT_SYMBOL(kstat_irqs_cpu);
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index 089c3746358a..ecf765c6a77a 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -42,6 +42,7 @@ static void init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
                  struct irq_desc *desc, int cpu)
 {
         memcpy(desc, old_desc, sizeof(struct irq_desc));
+        spin_lock_init(&desc->lock);
         desc->cpu = cpu;
         lockdep_set_class(&desc->lock, &irq_desc_lock_class);
         init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids);
@@ -74,10 +75,8 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 
         node = cpu_to_node(cpu);
         desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
-        printk(KERN_DEBUG "  move irq_desc for %d to cpu %d node %d\n",
-                 irq, cpu, node);
         if (!desc) {
-                printk(KERN_ERR "can not get new irq_desc for moving\n");
+                printk(KERN_ERR "irq %d: can not get new irq_desc for migration.\n", irq);
                 /* still use old one */
                 desc = old_desc;
                 goto out_unlock;
@@ -106,8 +105,6 @@ struct irq_desc *move_irq_desc(struct irq_desc *desc, int cpu)
                 return desc;
 
         old_cpu = desc->cpu;
-        printk(KERN_DEBUG
-                 "try to move irq_desc from cpu %d to %d\n", old_cpu, cpu);
         if (old_cpu != cpu) {
                 node = cpu_to_node(cpu);
                 old_node = cpu_to_node(old_cpu);
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 3738107531fd..dd364c11e56e 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -91,9 +91,6 @@ static int misrouted_irq(int irq)
         int i, ok = 0;
 
         for_each_irq_desc(i, desc) {
-                if (!desc)
-                        continue;
-
                 if (!i)
                          continue;
 
@@ -115,8 +112,6 @@ static void poll_spurious_irqs(unsigned long dummy)
         for_each_irq_desc(i, desc) {
                 unsigned int status;
 
-                if (!desc)
-                        continue;
                 if (!i)
                          continue;
 
diff --git a/kernel/sched.c b/kernel/sched.c
index dd862d70e715..545c6fccd1dc 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4150,13 +4150,17 @@ unsigned long long task_delta_exec(struct task_struct *p)
  * Account user cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @cputime: the cpu time spent in user space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
  */
-void account_user_time(struct task_struct *p, cputime_t cputime)
+void account_user_time(struct task_struct *p, cputime_t cputime,
+                       cputime_t cputime_scaled)
 {
         struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
         cputime64_t tmp;
 
+        /* Add user time to process. */
         p->utime = cputime_add(p->utime, cputime);
+        p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
         account_group_user_time(p, cputime);
 
         /* Add user time to cpustat. */
@@ -4173,51 +4177,48 @@ void account_user_time(struct task_struct *p, cputime_t cputime)
  * Account guest cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @cputime: the cpu time spent in virtual machine since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
  */
-static void account_guest_time(struct task_struct *p, cputime_t cputime)
+static void account_guest_time(struct task_struct *p, cputime_t cputime,
+                               cputime_t cputime_scaled)
 {
         cputime64_t tmp;
         struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
 
         tmp = cputime_to_cputime64(cputime);
 
+        /* Add guest time to process. */
         p->utime = cputime_add(p->utime, cputime);
+        p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
         account_group_user_time(p, cputime);
         p->gtime = cputime_add(p->gtime, cputime);
 
+        /* Add guest time to cpustat. */
         cpustat->user = cputime64_add(cpustat->user, tmp);
         cpustat->guest = cputime64_add(cpustat->guest, tmp);
 }
 
 /*
- * Account scaled user cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @cputime: the cpu time spent in user space since the last update
- */
-void account_user_time_scaled(struct task_struct *p, cputime_t cputime)
-{
-        p->utimescaled = cputime_add(p->utimescaled, cputime);
-}
-
-/*
  * Account system cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @hardirq_offset: the offset to subtract from hardirq_count()
  * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
  */
 void account_system_time(struct task_struct *p, int hardirq_offset,
-                         cputime_t cputime)
+                         cputime_t cputime, cputime_t cputime_scaled)
 {
         struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
-        struct rq *rq = this_rq();
         cputime64_t tmp;
 
         if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
-                account_guest_time(p, cputime);
+                account_guest_time(p, cputime, cputime_scaled);
                 return;
         }
 
+        /* Add system time to process. */
         p->stime = cputime_add(p->stime, cputime);
+        p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
         account_group_system_time(p, cputime);
 
         /* Add system time to cpustat. */
@@ -4226,48 +4227,84 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
                 cpustat->irq = cputime64_add(cpustat->irq, tmp);
         else if (softirq_count())
                 cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
-        else if (p != rq->idle)
-                cpustat->system = cputime64_add(cpustat->system, tmp);
-        else if (atomic_read(&rq->nr_iowait) > 0)
-                cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
         else
-                cpustat->idle = cputime64_add(cpustat->idle, tmp);
+                cpustat->system = cputime64_add(cpustat->system, tmp);
+
         /* Account for system time used */
         acct_update_integrals(p);
 }
 
 /*
- * Account scaled system cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @hardirq_offset: the offset to subtract from hardirq_count()
- * @cputime: the cpu time spent in kernel space since the last update
+ * Account for involuntary wait time.
+ * @steal: the cpu time spent in involuntary wait
  */
-void account_system_time_scaled(struct task_struct *p, cputime_t cputime)
+void account_steal_time(cputime_t cputime)
 {
-        p->stimescaled = cputime_add(p->stimescaled, cputime);
+        struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+        cputime64_t cputime64 = cputime_to_cputime64(cputime);
+
+        cpustat->steal = cputime64_add(cpustat->steal, cputime64);
 }
 
 /*
- * Account for involuntary wait time.
- * @p: the process from which the cpu time has been stolen
- * @steal: the cpu time spent in involuntary wait
+ * Account for idle time.
+ * @cputime: the cpu time spent in idle wait
  */
-void account_steal_time(struct task_struct *p, cputime_t steal)
+void account_idle_time(cputime_t cputime)
 {
         struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
-        cputime64_t tmp = cputime_to_cputime64(steal);
+        cputime64_t cputime64 = cputime_to_cputime64(cputime);
         struct rq *rq = this_rq();
 
-        if (p == rq->idle) {
-                p->stime = cputime_add(p->stime, steal);
-                if (atomic_read(&rq->nr_iowait) > 0)
-                        cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
-                else
-                        cpustat->idle = cputime64_add(cpustat->idle, tmp);
-        } else
-                cpustat->steal = cputime64_add(cpustat->steal, tmp);
+        if (atomic_read(&rq->nr_iowait) > 0)
+                cpustat->iowait = cputime64_add(cpustat->iowait, cputime64);
+        else
+                cpustat->idle = cputime64_add(cpustat->idle, cputime64);
 }
 
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+
+/*
+ * Account a single tick of cpu time.
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: indicates if the tick is a user or a system tick
+ */
+void account_process_tick(struct task_struct *p, int user_tick)
+{
+        cputime_t one_jiffy = jiffies_to_cputime(1);
+        cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy);
+        struct rq *rq = this_rq();
+
+        if (user_tick)
+                account_user_time(p, one_jiffy, one_jiffy_scaled);
+        else if (p != rq->idle)
+                account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
+                                    one_jiffy_scaled);
+        else
+                account_idle_time(one_jiffy);
+}
+
+/*
+ * Account multiple ticks of steal time.
+ * @p: the process from which the cpu time has been stolen
+ * @ticks: number of stolen ticks
+ */
+void account_steal_ticks(unsigned long ticks)
+{
+        account_steal_time(jiffies_to_cputime(ticks));
+}
+
+/*
+ * Account multiple ticks of idle time.
+ * @ticks: number of stolen ticks
+ */
+void account_idle_ticks(unsigned long ticks)
+{
+        account_idle_time(jiffies_to_cputime(ticks));
+}
+
+#endif
+
 /*
  * Use precise platform statistics if available:
  */
diff --git a/kernel/softirq.c b/kernel/softirq.c
index b7568d7def23..bdbe9de9cd8d 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -784,3 +784,23 @@ int on_each_cpu(void (*func) (void *info), void *info, int wait)
 }
 EXPORT_SYMBOL(on_each_cpu);
 #endif
+
+/*
+ * [ These __weak aliases are kept in a separate compilation unit, so that
+ *   GCC does not inline them incorrectly. ]
+ */
+
+int __init __weak early_irq_init(void)
+{
+        return 0;
+}
+
+int __init __weak arch_early_irq_init(void)
+{
+        return 0;
+}
+
+int __weak arch_init_chip_data(struct irq_desc *desc, int cpu)
+{
+        return 0;
+}
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 76a574bbef97..1b6c05bd0d0a 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -419,7 +419,9 @@ void tick_nohz_restart_sched_tick(void)
 {
         int cpu = smp_processor_id();
         struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
         unsigned long ticks;
+#endif
         ktime_t now;
 
         local_irq_disable();
@@ -441,6 +443,7 @@ void tick_nohz_restart_sched_tick(void)
         tick_do_update_jiffies64(now);
         cpumask_clear_cpu(cpu, nohz_cpu_mask);
 
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
         /*
          * We stopped the tick in idle. Update process times would miss the
          * time we slept as update_process_times does only a 1 tick
@@ -450,12 +453,9 @@ void tick_nohz_restart_sched_tick(void)
         /*
          * We might be one off. Do not randomly account a huge number of ticks!
          */
-        if (ticks && ticks < LONG_MAX) {
-                add_preempt_count(HARDIRQ_OFFSET);
-                account_system_time(current, HARDIRQ_OFFSET,
-                                    jiffies_to_cputime(ticks));
-                sub_preempt_count(HARDIRQ_OFFSET);
-        }
+        if (ticks && ticks < LONG_MAX)
+                account_idle_ticks(ticks);
+#endif
 
         touch_softlockup_watchdog();
         /*
diff --git a/kernel/timer.c b/kernel/timer.c
index 566257d1dc10..dee3f641a7a7 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1018,21 +1018,6 @@ unsigned long get_next_timer_interrupt(unsigned long now)
 }
 #endif
 
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-void account_process_tick(struct task_struct *p, int user_tick)
-{
-        cputime_t one_jiffy = jiffies_to_cputime(1);
-
-        if (user_tick) {
-                account_user_time(p, one_jiffy);
-                account_user_time_scaled(p, cputime_to_scaled(one_jiffy));
-        } else {
-                account_system_time(p, HARDIRQ_OFFSET, one_jiffy);
-                account_system_time_scaled(p, cputime_to_scaled(one_jiffy));
-        }
-}
-#endif
-
 /*
  * Called from the timer interrupt handler to charge one tick to the current
  * process.  user_tick is 1 if the tick is user time, 0 for system.