Merge branch 'perf/uprobes' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/uprobes

16 files changed, 506 insertions, 355 deletions

diff --git a/kernel/cred.c b/kernel/cred.c
index 97b36eeca4c9..e70683d9ec32 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -386,6 +386,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
         struct cred *new;
         int ret;
 
+        p->replacement_session_keyring = NULL;
+
         if (
 #ifdef CONFIG_KEYS
                 !p->cred->thread_keyring &&
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a6a9ec4cd8f5..e82c7a1face9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2039,8 +2039,8 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
  * accessing the event control register. If a NMI hits, then it will
  * not restart the event.
  */
-void __perf_event_task_sched_out(struct task_struct *task,
-                                 struct task_struct *next)
+static void __perf_event_task_sched_out(struct task_struct *task,
+                                        struct task_struct *next)
 {
         int ctxn;
 
@@ -2279,8 +2279,8 @@ static void perf_branch_stack_sched_in(struct task_struct *prev,
  * accessing the event control register. If a NMI hits, then it will
  * keep the event running.
  */
-void __perf_event_task_sched_in(struct task_struct *prev,
-                                struct task_struct *task)
+static void __perf_event_task_sched_in(struct task_struct *prev,
+                                       struct task_struct *task)
 {
         struct perf_event_context *ctx;
         int ctxn;
@@ -2305,6 +2305,12 @@ void __perf_event_task_sched_in(struct task_struct *prev,
                 perf_branch_stack_sched_in(prev, task);
 }
 
+void __perf_event_task_sched(struct task_struct *prev, struct task_struct *next)
+{
+        __perf_event_task_sched_out(prev, next);
+        __perf_event_task_sched_in(prev, next);
+}
+
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
 {
         u64 frequency = event->attr.sample_freq;
@@ -4957,7 +4963,7 @@ void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
         if (rctx < 0)
                 return;
 
-        perf_sample_data_init(&data, addr);
+        perf_sample_data_init(&data, addr, 0);
 
         do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, &data, regs);
 
@@ -5215,7 +5221,7 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
                 .data = record,
         };
 
-        perf_sample_data_init(&data, addr);
+        perf_sample_data_init(&data, addr, 0);
         data.raw = &raw;
 
         hlist_for_each_entry_rcu(event, node, head, hlist_entry) {
@@ -5318,7 +5324,7 @@ void perf_bp_event(struct perf_event *bp, void *data)
         struct perf_sample_data sample;
         struct pt_regs *regs = data;
 
-        perf_sample_data_init(&sample, bp->attr.bp_addr);
+        perf_sample_data_init(&sample, bp->attr.bp_addr, 0);
 
         if (!bp->hw.state && !perf_exclude_event(bp, regs))
                 perf_swevent_event(bp, 1, &sample, regs);
@@ -5344,13 +5350,12 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 
         event->pmu->read(event);
 
-        perf_sample_data_init(&data, 0);
-        data.period = event->hw.last_period;
+        perf_sample_data_init(&data, 0, event->hw.last_period);
         regs = get_irq_regs();
 
         if (regs && !perf_exclude_event(event, regs)) {
                 if (!(event->attr.exclude_idle && is_idle_task(current)))
-                        if (perf_event_overflow(event, &data, regs))
+                        if (__perf_event_overflow(event, 1, &data, regs))
                                 ret = HRTIMER_NORESTART;
         }
 
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index cf1a4a68ce44..d1a758bc972a 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -62,7 +62,7 @@ config IRQ_DOMAIN_DEBUG
         help
           This option will show the mapping relationship between hardware irq
           numbers and Linux irq numbers. The mapping is exposed via debugfs
-          in the file "virq_mapping".
+          in the file "irq_domain_mapping".
 
           If you don't know what this means you don't need it.
 
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 3601f3fbf67c..0e0ba5f840b2 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -23,7 +23,6 @@ static LIST_HEAD(irq_domain_list);
 static DEFINE_MUTEX(irq_domain_mutex);
 
 static DEFINE_MUTEX(revmap_trees_mutex);
-static unsigned int irq_virq_count = NR_IRQS;
 static struct irq_domain *irq_default_domain;
 
 /**
@@ -184,13 +183,16 @@ struct irq_domain *irq_domain_add_linear(struct device_node *of_node,
 }
 
 struct irq_domain *irq_domain_add_nomap(struct device_node *of_node,
+                                         unsigned int max_irq,
                                          const struct irq_domain_ops *ops,
                                          void *host_data)
 {
         struct irq_domain *domain = irq_domain_alloc(of_node,
                                         IRQ_DOMAIN_MAP_NOMAP, ops, host_data);
-        if (domain)
+        if (domain) {
+                domain->revmap_data.nomap.max_irq = max_irq ? max_irq : ~0;
                 irq_domain_add(domain);
+        }
         return domain;
 }
 
@@ -262,22 +264,6 @@ void irq_set_default_host(struct irq_domain *domain)
         irq_default_domain = domain;
 }
 
-/**
- * irq_set_virq_count() - Set the maximum number of linux irqs
- * @count: number of linux irqs, capped with NR_IRQS
- *
- * This is mainly for use by platforms like iSeries who want to program
- * the virtual irq number in the controller to avoid the reverse mapping
- */
-void irq_set_virq_count(unsigned int count)
-{
-        pr_debug("irq: Trying to set virq count to %d\n", count);
-
-        BUG_ON(count < NUM_ISA_INTERRUPTS);
-        if (count < NR_IRQS)
-                irq_virq_count = count;
-}
-
 static int irq_setup_virq(struct irq_domain *domain, unsigned int virq,
                             irq_hw_number_t hwirq)
 {
@@ -320,13 +306,12 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
                 pr_debug("irq: create_direct virq allocation failed\n");
                 return 0;
         }
-        if (virq >= irq_virq_count) {
+        if (virq >= domain->revmap_data.nomap.max_irq) {
                 pr_err("ERROR: no free irqs available below %i maximum\n",
-                        irq_virq_count);
+                        domain->revmap_data.nomap.max_irq);
                 irq_free_desc(virq);
                 return 0;
         }
-
         pr_debug("irq: create_direct obtained virq %d\n", virq);
 
         if (irq_setup_virq(domain, virq, virq)) {
@@ -350,7 +335,8 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
 unsigned int irq_create_mapping(struct irq_domain *domain,
                                 irq_hw_number_t hwirq)
 {
-        unsigned int virq, hint;
+        unsigned int hint;
+        int virq;
 
         pr_debug("irq: irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq);
 
@@ -377,13 +363,13 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
                 return irq_domain_legacy_revmap(domain, hwirq);
 
         /* Allocate a virtual interrupt number */
-        hint = hwirq % irq_virq_count;
+        hint = hwirq % nr_irqs;
         if (hint == 0)
                 hint++;
         virq = irq_alloc_desc_from(hint, 0);
-        if (!virq)
+        if (virq <= 0)
                 virq = irq_alloc_desc_from(1, 0);
-        if (!virq) {
+        if (virq <= 0) {
                 pr_debug("irq: -> virq allocation failed\n");
                 return 0;
         }
@@ -515,7 +501,7 @@ unsigned int irq_find_mapping(struct irq_domain *domain,
                               irq_hw_number_t hwirq)
 {
         unsigned int i;
-        unsigned int hint = hwirq % irq_virq_count;
+        unsigned int hint = hwirq % nr_irqs;
 
         /* Look for default domain if nececssary */
         if (domain == NULL)
@@ -536,7 +522,7 @@ unsigned int irq_find_mapping(struct irq_domain *domain,
                 if (data && (data->domain == domain) && (data->hwirq == hwirq))
                         return i;
                 i++;
-                if (i >= irq_virq_count)
+                if (i >= nr_irqs)
                         i = 1;
         } while(i != hint);
         return 0;
@@ -642,8 +628,9 @@ static int virq_debug_show(struct seq_file *m, void *private)
         void *data;
         int i;
 
-        seq_printf(m, "%-5s  %-7s  %-15s  %-18s  %s\n", "virq", "hwirq",
-                      "chip name", "chip data", "domain name");
+        seq_printf(m, "%-5s  %-7s  %-15s  %-*s  %s\n", "irq", "hwirq",
+                      "chip name", (int)(2 * sizeof(void *) + 2), "chip data",
+                      "domain name");
 
         for (i = 1; i < nr_irqs; i++) {
                 desc = irq_to_desc(i);
@@ -666,7 +653,7 @@ static int virq_debug_show(struct seq_file *m, void *private)
                         seq_printf(m, "%-15s  ", p);
 
                         data = irq_desc_get_chip_data(desc);
-                        seq_printf(m, "0x%16p  ", data);
+                        seq_printf(m, data ? "0x%p  " : "  %p  ", data);
 
                         if (desc->irq_data.domain && desc->irq_data.domain->of_node)
                                 p = desc->irq_data.domain->of_node->full_name;
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 0c56d44b9fd5..1588e3b2871b 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -11,6 +11,7 @@
 #include <linux/irq_work.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
+#include <linux/irqflags.h>
 #include <asm/processor.h>
 
 /*
diff --git a/kernel/itimer.c b/kernel/itimer.c
index 22000c3db0dd..8d262b467573 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -284,8 +284,12 @@ SYSCALL_DEFINE3(setitimer, int, which, struct itimerval __user *, value,
         if (value) {
                 if(copy_from_user(&set_buffer, value, sizeof(set_buffer)))
                         return -EFAULT;
-        } else
-                memset((char *) &set_buffer, 0, sizeof(set_buffer));
+        } else {
+                memset(&set_buffer, 0, sizeof(set_buffer));
+                printk_once(KERN_WARNING "%s calls setitimer() with new_value NULL pointer."
+                            " Misfeature support will be removed\n",
+                            current->comm);
+        }
 
         error = do_setitimer(which, &set_buffer, ovalue ? &get_buffer : NULL);
         if (error || !ovalue)
diff --git a/kernel/panic.c b/kernel/panic.c
index 80aed44e345a..8ed89a175d79 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -97,7 +97,7 @@ void panic(const char *fmt, ...)
         /*
          * Avoid nested stack-dumping if a panic occurs during oops processing
          */
-        if (!oops_in_progress)
+        if (!test_taint(TAINT_DIE) && oops_in_progress <= 1)
                 dump_stack();
 #endif
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4603b9d8f30a..5c692a0a555d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1913,7 +1913,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
                     struct task_struct *next)
 {
         sched_info_switch(prev, next);
-        perf_event_task_sched_out(prev, next);
+        perf_event_task_sched(prev, next);
         fire_sched_out_preempt_notifiers(prev, next);
         prepare_lock_switch(rq, next);
         prepare_arch_switch(next);
@@ -1956,13 +1956,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
          */
         prev_state = prev->state;
         finish_arch_switch(prev);
-#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
-        local_irq_disable();
-#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
-        perf_event_task_sched_in(prev, current);
-#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
-        local_irq_enable();
-#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
         finish_lock_switch(rq, prev);
         finish_arch_post_lock_switch();
 
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 2cf9cc7aa103..a20dc8a3c949 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -1,6 +1,10 @@
 #
 # Timer subsystem related configuration options
 #
+
+# Core internal switch. Selected by NO_HZ / HIGH_RES_TIMERS. This is
+# only related to the tick functionality. Oneshot clockevent devices
+# are supported independ of this.
 config TICK_ONESHOT
         bool
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index e883f57a3cd3..bf57abdc7bd0 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -575,10 +575,12 @@ void tick_broadcast_switch_to_oneshot(void)
         unsigned long flags;
 
         raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+        tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT;
+
         if (cpumask_empty(tick_get_broadcast_mask()))
                 goto end;
 
-        tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT;
         bc = tick_broadcast_device.evtdev;
         if (bc)
                 tick_broadcast_setup_oneshot(bc);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 3526038f2836..6a3a5b9ff561 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -534,9 +534,9 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
                                 hrtimer_get_expires(&ts->sched_timer), 0))
                                 break;
                 }
-                /* Update jiffies and reread time */
-                tick_do_update_jiffies64(now);
+                /* Reread time and update jiffies */
                 now = ktime_get();
+                tick_do_update_jiffies64(now);
         }
 }
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0fa92f677c92..cf81f27ce6c6 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2469,57 +2469,35 @@ static int
 ftrace_avail_open(struct inode *inode, struct file *file)
 {
         struct ftrace_iterator *iter;
-        int ret;
 
         if (unlikely(ftrace_disabled))
                 return -ENODEV;
 
-        iter = kzalloc(sizeof(*iter), GFP_KERNEL);
-        if (!iter)
-                return -ENOMEM;
-
-        iter->pg = ftrace_pages_start;
-        iter->ops = &global_ops;
-
-        ret = seq_open(file, &show_ftrace_seq_ops);
-        if (!ret) {
-                struct seq_file *m = file->private_data;
-
-                m->private = iter;
-        } else {
-                kfree(iter);
+        iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter));
+        if (iter) {
+                iter->pg = ftrace_pages_start;
+                iter->ops = &global_ops;
         }
 
-        return ret;
+        return iter ? 0 : -ENOMEM;
 }
 
 static int
 ftrace_enabled_open(struct inode *inode, struct file *file)
 {
         struct ftrace_iterator *iter;
-        int ret;
 
         if (unlikely(ftrace_disabled))
                 return -ENODEV;
 
-        iter = kzalloc(sizeof(*iter), GFP_KERNEL);
-        if (!iter)
-                return -ENOMEM;
-
-        iter->pg = ftrace_pages_start;
-        iter->flags = FTRACE_ITER_ENABLED;
-        iter->ops = &global_ops;
-
-        ret = seq_open(file, &show_ftrace_seq_ops);
-        if (!ret) {
-                struct seq_file *m = file->private_data;
-
-                m->private = iter;
-        } else {
-                kfree(iter);
+        iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter));
+        if (iter) {
+                iter->pg = ftrace_pages_start;
+                iter->flags = FTRACE_ITER_ENABLED;
+                iter->ops = &global_ops;
         }
 
-        return ret;
+        return iter ? 0 : -ENOMEM;
 }
 
 static void ftrace_filter_reset(struct ftrace_hash *hash)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index cf8d11e91efd..2d5eb3320827 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -449,6 +449,7 @@ struct ring_buffer_per_cpu {
         raw_spinlock_t                  reader_lock;    /* serialize readers */
         arch_spinlock_t                 lock;
         struct lock_class_key           lock_key;
+        unsigned int                    nr_pages;
         struct list_head                *pages;
         struct buffer_page              *head_page;     /* read from head */
         struct buffer_page              *tail_page;     /* write to tail */
@@ -466,10 +467,12 @@ struct ring_buffer_per_cpu {
         unsigned long                   read_bytes;
         u64                             write_stamp;
         u64                             read_stamp;
+        /* ring buffer pages to update, > 0 to add, < 0 to remove */
+        int                             nr_pages_to_update;
+        struct list_head                new_pages; /* new pages to add */
 };
 
 struct ring_buffer {
-        unsigned                        pages;
         unsigned                        flags;
         int                             cpus;
         atomic_t                        record_disabled;
@@ -963,14 +966,10 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
         return 0;
 }
 
-static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
-                             unsigned nr_pages)
+static int __rb_allocate_pages(int nr_pages, struct list_head *pages, int cpu)
 {
+        int i;
         struct buffer_page *bpage, *tmp;
-        LIST_HEAD(pages);
-        unsigned i;
-
-        WARN_ON(!nr_pages);
 
         for (i = 0; i < nr_pages; i++) {
                 struct page *page;
@@ -981,15 +980,13 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
                  */
                 bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
                                     GFP_KERNEL | __GFP_NORETRY,
-                                    cpu_to_node(cpu_buffer->cpu));
+                                    cpu_to_node(cpu));
                 if (!bpage)
                         goto free_pages;
 
-                rb_check_bpage(cpu_buffer, bpage);
+                list_add(&bpage->list, pages);
 
-                list_add(&bpage->list, &pages);
-
-                page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu),
+                page = alloc_pages_node(cpu_to_node(cpu),
                                         GFP_KERNEL | __GFP_NORETRY, 0);
                 if (!page)
                         goto free_pages;
@@ -997,6 +994,27 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
                 rb_init_page(bpage->page);
         }
 
+        return 0;
+
+free_pages:
+        list_for_each_entry_safe(bpage, tmp, pages, list) {
+                list_del_init(&bpage->list);
+                free_buffer_page(bpage);
+        }
+
+        return -ENOMEM;
+}
+
+static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
+                             unsigned nr_pages)
+{
+        LIST_HEAD(pages);
+
+        WARN_ON(!nr_pages);
+
+        if (__rb_allocate_pages(nr_pages, &pages, cpu_buffer->cpu))
+                return -ENOMEM;
+
         /*
          * The ring buffer page list is a circular list that does not
          * start and end with a list head. All page list items point to
@@ -1005,20 +1023,15 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
         cpu_buffer->pages = pages.next;
         list_del(&pages);
 
+        cpu_buffer->nr_pages = nr_pages;
+
         rb_check_pages(cpu_buffer);
 
         return 0;
-
- free_pages:
-        list_for_each_entry_safe(bpage, tmp, &pages, list) {
-                list_del_init(&bpage->list);
-                free_buffer_page(bpage);
-        }
-        return -ENOMEM;
 }
 
 static struct ring_buffer_per_cpu *
-rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
+rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu)
 {
         struct ring_buffer_per_cpu *cpu_buffer;
         struct buffer_page *bpage;
@@ -1052,7 +1065,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 
         INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
 
-        ret = rb_allocate_pages(cpu_buffer, buffer->pages);
+        ret = rb_allocate_pages(cpu_buffer, nr_pages);
         if (ret < 0)
                 goto fail_free_reader;
 
@@ -1113,7 +1126,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 {
         struct ring_buffer *buffer;
         int bsize;
-        int cpu;
+        int cpu, nr_pages;
 
         /* keep it in its own cache line */
         buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()),
@@ -1124,14 +1137,14 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
         if (!alloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
                 goto fail_free_buffer;
 
-        buffer->pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+        nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
         buffer->flags = flags;
         buffer->clock = trace_clock_local;
         buffer->reader_lock_key = key;
 
         /* need at least two pages */
-        if (buffer->pages < 2)
-                buffer->pages = 2;
+        if (nr_pages < 2)
+                nr_pages = 2;
 
         /*
          * In case of non-hotplug cpu, if the ring-buffer is allocated
@@ -1154,7 +1167,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 
         for_each_buffer_cpu(buffer, cpu) {
                 buffer->buffers[cpu] =
-                        rb_allocate_cpu_buffer(buffer, cpu);
+                        rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
                 if (!buffer->buffers[cpu])
                         goto fail_free_buffers;
         }
@@ -1276,6 +1289,18 @@ out:
         raw_spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
+static void update_pages_handler(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        if (cpu_buffer->nr_pages_to_update > 0)
+                rb_insert_pages(cpu_buffer, &cpu_buffer->new_pages,
+                                cpu_buffer->nr_pages_to_update);
+        else
+                rb_remove_pages(cpu_buffer, -cpu_buffer->nr_pages_to_update);
+        cpu_buffer->nr_pages += cpu_buffer->nr_pages_to_update;
+        /* reset this value */
+        cpu_buffer->nr_pages_to_update = 0;
+}
+
 /**
  * ring_buffer_resize - resize the ring buffer
  * @buffer: the buffer to resize.
@@ -1285,14 +1310,12 @@ out:
  *
  * Returns -1 on failure.
  */
-int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
+int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
+                        int cpu_id)
 {
         struct ring_buffer_per_cpu *cpu_buffer;
-        unsigned nr_pages, rm_pages, new_pages;
-        struct buffer_page *bpage, *tmp;
-        unsigned long buffer_size;
-        LIST_HEAD(pages);
-        int i, cpu;
+        unsigned nr_pages;
+        int cpu;
 
         /*
          * Always succeed at resizing a non-existent buffer:
@@ -1302,15 +1325,11 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 
         size = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
         size *= BUF_PAGE_SIZE;
-        buffer_size = buffer->pages * BUF_PAGE_SIZE;
 
         /* we need a minimum of two pages */
         if (size < BUF_PAGE_SIZE * 2)
                 size = BUF_PAGE_SIZE * 2;
 
-        if (size == buffer_size)
-                return size;
-
         atomic_inc(&buffer->record_disabled);
 
         /* Make sure all writers are done with this buffer. */
@@ -1321,68 +1340,56 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 
         nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
 
-        if (size < buffer_size) {
-
-                /* easy case, just free pages */
-                if (RB_WARN_ON(buffer, nr_pages >= buffer->pages))
-                        goto out_fail;
-
-                rm_pages = buffer->pages - nr_pages;
-
+        if (cpu_id == RING_BUFFER_ALL_CPUS) {
+                /* calculate the pages to update */
                 for_each_buffer_cpu(buffer, cpu) {
                         cpu_buffer = buffer->buffers[cpu];
-                        rb_remove_pages(cpu_buffer, rm_pages);
-                }
-                goto out;
-        }
 
-        /*
-         * This is a bit more difficult. We only want to add pages
-         * when we can allocate enough for all CPUs. We do this
-         * by allocating all the pages and storing them on a local
-         * link list. If we succeed in our allocation, then we
-         * add these pages to the cpu_buffers. Otherwise we just free
-         * them all and return -ENOMEM;
-         */
-        if (RB_WARN_ON(buffer, nr_pages <= buffer->pages))
-                goto out_fail;
+                        cpu_buffer->nr_pages_to_update = nr_pages -
+                                                        cpu_buffer->nr_pages;
 
-        new_pages = nr_pages - buffer->pages;
+                        /*
+                         * nothing more to do for removing pages or no update
+                         */
+                        if (cpu_buffer->nr_pages_to_update <= 0)
+                                continue;
 
-        for_each_buffer_cpu(buffer, cpu) {
-                for (i = 0; i < new_pages; i++) {
-                        struct page *page;
                         /*
-                         * __GFP_NORETRY flag makes sure that the allocation
-                         * fails gracefully without invoking oom-killer and
-                         * the system is not destabilized.
+                         * to add pages, make sure all new pages can be
+                         * allocated without receiving ENOMEM
                          */
-                        bpage = kzalloc_node(ALIGN(sizeof(*bpage),
-                                                  cache_line_size()),
-                                            GFP_KERNEL | __GFP_NORETRY,
-                                            cpu_to_node(cpu));
-                        if (!bpage)
-                                goto free_pages;
-                        list_add(&bpage->list, &pages);
-                        page = alloc_pages_node(cpu_to_node(cpu),
-                                                GFP_KERNEL | __GFP_NORETRY, 0);
-                        if (!page)
-                                goto free_pages;
-                        bpage->page = page_address(page);
-                        rb_init_page(bpage->page);
+                        INIT_LIST_HEAD(&cpu_buffer->new_pages);
+                        if (__rb_allocate_pages(cpu_buffer->nr_pages_to_update,
+                                                &cpu_buffer->new_pages, cpu))
+                                /* not enough memory for new pages */
+                                goto no_mem;
                 }
-        }
 
-        for_each_buffer_cpu(buffer, cpu) {
-                cpu_buffer = buffer->buffers[cpu];
-                rb_insert_pages(cpu_buffer, &pages, new_pages);
-        }
+                /* wait for all the updates to complete */
+                for_each_buffer_cpu(buffer, cpu) {
+                        cpu_buffer = buffer->buffers[cpu];
+                        if (cpu_buffer->nr_pages_to_update) {
+                                update_pages_handler(cpu_buffer);
+                        }
+                }
+        } else {
+                cpu_buffer = buffer->buffers[cpu_id];
+                if (nr_pages == cpu_buffer->nr_pages)
+                        goto out;
 
-        if (RB_WARN_ON(buffer, !list_empty(&pages)))
-                goto out_fail;
+                cpu_buffer->nr_pages_to_update = nr_pages -
+                                                cpu_buffer->nr_pages;
+
+                INIT_LIST_HEAD(&cpu_buffer->new_pages);
+                if (cpu_buffer->nr_pages_to_update > 0 &&
+                        __rb_allocate_pages(cpu_buffer->nr_pages_to_update,
+                                                &cpu_buffer->new_pages, cpu_id))
+                        goto no_mem;
+
+                update_pages_handler(cpu_buffer);
+        }
 
  out:
-        buffer->pages = nr_pages;
         put_online_cpus();
         mutex_unlock(&buffer->mutex);
 
@@ -1390,25 +1397,24 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 
         return size;
 
- free_pages:
-        list_for_each_entry_safe(bpage, tmp, &pages, list) {
-                list_del_init(&bpage->list);
-                free_buffer_page(bpage);
+ no_mem:
+        for_each_buffer_cpu(buffer, cpu) {
+                struct buffer_page *bpage, *tmp;
+                cpu_buffer = buffer->buffers[cpu];
+                /* reset this number regardless */
+                cpu_buffer->nr_pages_to_update = 0;
+                if (list_empty(&cpu_buffer->new_pages))
+                        continue;
+                list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages,
+                                        list) {
+                        list_del_init(&bpage->list);
+                        free_buffer_page(bpage);
+                }
         }
         put_online_cpus();
         mutex_unlock(&buffer->mutex);
         atomic_dec(&buffer->record_disabled);
         return -ENOMEM;
-
-        /*
-         * Something went totally wrong, and we are too paranoid
-         * to even clean up the mess.
-         */
- out_fail:
-        put_online_cpus();
-        mutex_unlock(&buffer->mutex);
-        atomic_dec(&buffer->record_disabled);
-        return -1;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_resize);
 
@@ -1510,7 +1516,7 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
          * assign the commit to the tail.
          */
  again:
-        max_count = cpu_buffer->buffer->pages * 100;
+        max_count = cpu_buffer->nr_pages * 100;
 
         while (cpu_buffer->commit_page != cpu_buffer->tail_page) {
                 if (RB_WARN_ON(cpu_buffer, !(--max_count)))
@@ -3588,9 +3594,18 @@ EXPORT_SYMBOL_GPL(ring_buffer_read);
  * ring_buffer_size - return the size of the ring buffer (in bytes)
  * @buffer: The ring buffer.
  */
-unsigned long ring_buffer_size(struct ring_buffer *buffer)
+unsigned long ring_buffer_size(struct ring_buffer *buffer, int cpu)
 {
-        return BUF_PAGE_SIZE * buffer->pages;
+        /*
+         * Earlier, this method returned
+         *      BUF_PAGE_SIZE * buffer->nr_pages
+         * Since the nr_pages field is now removed, we have converted this to
+         * return the per cpu buffer value.
+         */
+        if (!cpumask_test_cpu(cpu, buffer->cpumask))
+                return 0;
+
+        return BUF_PAGE_SIZE * buffer->buffers[cpu]->nr_pages;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_size);
 
@@ -3765,8 +3780,11 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
             !cpumask_test_cpu(cpu, buffer_b->cpumask))
                 goto out;
 
+        cpu_buffer_a = buffer_a->buffers[cpu];
+        cpu_buffer_b = buffer_b->buffers[cpu];
+
         /* At least make sure the two buffers are somewhat the same */
-        if (buffer_a->pages != buffer_b->pages)
+        if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages)
                 goto out;
 
         ret = -EAGAIN;
@@ -3780,9 +3798,6 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
         if (atomic_read(&buffer_b->record_disabled))
                 goto out;
 
-        cpu_buffer_a = buffer_a->buffers[cpu];
-        cpu_buffer_b = buffer_b->buffers[cpu];
-
         if (atomic_read(&cpu_buffer_a->record_disabled))
                 goto out;
 
@@ -4071,6 +4086,8 @@ static int rb_cpu_notify(struct notifier_block *self,
         struct ring_buffer *buffer =
                 container_of(self, struct ring_buffer, cpu_notify);
         long cpu = (long)hcpu;
+        int cpu_i, nr_pages_same;
+        unsigned int nr_pages;
 
         switch (action) {
         case CPU_UP_PREPARE:
@@ -4078,8 +4095,23 @@ static int rb_cpu_notify(struct notifier_block *self,
                 if (cpumask_test_cpu(cpu, buffer->cpumask))
                         return NOTIFY_OK;
 
+                nr_pages = 0;
+                nr_pages_same = 1;
+                /* check if all cpu sizes are same */
+                for_each_buffer_cpu(buffer, cpu_i) {
+                        /* fill in the size from first enabled cpu */
+                        if (nr_pages == 0)
+                                nr_pages = buffer->buffers[cpu_i]->nr_pages;
+                        if (nr_pages != buffer->buffers[cpu_i]->nr_pages) {
+                                nr_pages_same = 0;
+                                break;
+                        }
+                }
+                /* allocate minimum pages, user can later expand it */
+                if (!nr_pages_same)
+                        nr_pages = 2;
                 buffer->buffers[cpu] =
-                        rb_allocate_cpu_buffer(buffer, cpu);
+                        rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
                 if (!buffer->buffers[cpu]) {
                         WARN(1, "failed to allocate ring buffer on CPU %ld\n",
                              cpu);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ed7b5d1e12f4..48ef4960ec90 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -87,18 +87,6 @@ static int tracing_disabled = 1;
 
 DEFINE_PER_CPU(int, ftrace_cpu_disabled);
 
-static inline void ftrace_disable_cpu(void)
-{
-        preempt_disable();
-        __this_cpu_inc(ftrace_cpu_disabled);
-}
-
-static inline void ftrace_enable_cpu(void)
-{
-        __this_cpu_dec(ftrace_cpu_disabled);
-        preempt_enable();
-}
-
 cpumask_var_t __read_mostly     tracing_buffer_mask;
 
 /*
@@ -629,7 +617,6 @@ ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt)
 static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 {
         int len;
-        void *ret;
 
         if (s->len <= s->readpos)
                 return -EBUSY;
@@ -637,9 +624,7 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
         len = s->len - s->readpos;
         if (cnt > len)
                 cnt = len;
-        ret = memcpy(buf, s->buffer + s->readpos, cnt);
-        if (!ret)
-                return -EFAULT;
+        memcpy(buf, s->buffer + s->readpos, cnt);
 
         s->readpos += cnt;
         return cnt;
@@ -751,8 +736,6 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
         arch_spin_lock(&ftrace_max_lock);
 
-        ftrace_disable_cpu();
-
         ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu);
 
         if (ret == -EBUSY) {
@@ -766,8 +749,6 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
                         "Failed to swap buffers due to commit in progress\n");
         }
 
-        ftrace_enable_cpu();
-
         WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY);
 
         __update_max_tr(tr, tsk, cpu);
@@ -841,7 +822,8 @@ __acquires(kernel_lock)
 
                 /* If we expanded the buffers, make sure the max is expanded too */
                 if (ring_buffer_expanded && type->use_max_tr)
-                        ring_buffer_resize(max_tr.buffer, trace_buf_size);
+                        ring_buffer_resize(max_tr.buffer, trace_buf_size,
+                                                RING_BUFFER_ALL_CPUS);
 
                 /* the test is responsible for initializing and enabling */
                 pr_info("Testing tracer %s: ", type->name);
@@ -857,7 +839,8 @@ __acquires(kernel_lock)
 
                 /* Shrink the max buffer again */
                 if (ring_buffer_expanded && type->use_max_tr)
-                        ring_buffer_resize(max_tr.buffer, 1);
+                        ring_buffer_resize(max_tr.buffer, 1,
+                                                RING_BUFFER_ALL_CPUS);
 
                 printk(KERN_CONT "PASSED\n");
         }
@@ -917,13 +900,6 @@ out:
         mutex_unlock(&trace_types_lock);
 }
 
-static void __tracing_reset(struct ring_buffer *buffer, int cpu)
-{
-        ftrace_disable_cpu();
-        ring_buffer_reset_cpu(buffer, cpu);
-        ftrace_enable_cpu();
-}
-
 void tracing_reset(struct trace_array *tr, int cpu)
 {
         struct ring_buffer *buffer = tr->buffer;
@@ -932,7 +908,7 @@ void tracing_reset(struct trace_array *tr, int cpu)
 
         /* Make sure all commits have finished */
         synchronize_sched();
-        __tracing_reset(buffer, cpu);
+        ring_buffer_reset_cpu(buffer, cpu);
 
         ring_buffer_record_enable(buffer);
 }
@@ -950,7 +926,7 @@ void tracing_reset_online_cpus(struct trace_array *tr)
         tr->time_start = ftrace_now(tr->cpu);
 
         for_each_online_cpu(cpu)
-                __tracing_reset(buffer, cpu);
+                ring_buffer_reset_cpu(buffer, cpu);
 
         ring_buffer_record_enable(buffer);
 }
@@ -1498,25 +1474,119 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags)
 
 #endif /* CONFIG_STACKTRACE */
 
+/* created for use with alloc_percpu */
+struct trace_buffer_struct {
+        char buffer[TRACE_BUF_SIZE];
+};
+
+static struct trace_buffer_struct *trace_percpu_buffer;
+static struct trace_buffer_struct *trace_percpu_sirq_buffer;
+static struct trace_buffer_struct *trace_percpu_irq_buffer;
+static struct trace_buffer_struct *trace_percpu_nmi_buffer;
+
+/*
+ * The buffer used is dependent on the context. There is a per cpu
+ * buffer for normal context, softirq contex, hard irq context and
+ * for NMI context. Thise allows for lockless recording.
+ *
+ * Note, if the buffers failed to be allocated, then this returns NULL
+ */
+static char *get_trace_buf(void)
+{
+        struct trace_buffer_struct *percpu_buffer;
+        struct trace_buffer_struct *buffer;
+
+        /*
+         * If we have allocated per cpu buffers, then we do not
+         * need to do any locking.
+         */
+        if (in_nmi())
+                percpu_buffer = trace_percpu_nmi_buffer;
+        else if (in_irq())
+                percpu_buffer = trace_percpu_irq_buffer;
+        else if (in_softirq())
+                percpu_buffer = trace_percpu_sirq_buffer;
+        else
+                percpu_buffer = trace_percpu_buffer;
+
+        if (!percpu_buffer)
+                return NULL;
+
+        buffer = per_cpu_ptr(percpu_buffer, smp_processor_id());
+
+        return buffer->buffer;
+}
+
+static int alloc_percpu_trace_buffer(void)
+{
+        struct trace_buffer_struct *buffers;
+        struct trace_buffer_struct *sirq_buffers;
+        struct trace_buffer_struct *irq_buffers;
+        struct trace_buffer_struct *nmi_buffers;
+
+        buffers = alloc_percpu(struct trace_buffer_struct);
+        if (!buffers)
+                goto err_warn;
+
+        sirq_buffers = alloc_percpu(struct trace_buffer_struct);
+        if (!sirq_buffers)
+                goto err_sirq;
+
+        irq_buffers = alloc_percpu(struct trace_buffer_struct);
+        if (!irq_buffers)
+                goto err_irq;
+
+        nmi_buffers = alloc_percpu(struct trace_buffer_struct);
+        if (!nmi_buffers)
+                goto err_nmi;
+
+        trace_percpu_buffer = buffers;
+        trace_percpu_sirq_buffer = sirq_buffers;
+        trace_percpu_irq_buffer = irq_buffers;
+        trace_percpu_nmi_buffer = nmi_buffers;
+
+        return 0;
+
+ err_nmi:
+        free_percpu(irq_buffers);
+ err_irq:
+        free_percpu(sirq_buffers);
+ err_sirq:
+        free_percpu(buffers);
+ err_warn:
+        WARN(1, "Could not allocate percpu trace_printk buffer");
+        return -ENOMEM;
+}
+
+void trace_printk_init_buffers(void)
+{
+        static int buffers_allocated;
+
+        if (buffers_allocated)
+                return;
+
+        if (alloc_percpu_trace_buffer())
+                return;
+
+        pr_info("ftrace: Allocated trace_printk buffers\n");
+
+        buffers_allocated = 1;
+}
+
 /**
  * trace_vbprintk - write binary msg to tracing buffer
  *
  */
 int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 {
-        static arch_spinlock_t trace_buf_lock =
-                (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
-        static u32 trace_buf[TRACE_BUF_SIZE];
-
         struct ftrace_event_call *call = &event_bprint;
         struct ring_buffer_event *event;
         struct ring_buffer *buffer;
         struct trace_array *tr = &global_trace;
-        struct trace_array_cpu *data;
         struct bprint_entry *entry;
         unsigned long flags;
-        int disable;
-        int cpu, len = 0, size, pc;
+        char *tbuffer;
+        int len = 0, size, pc;
 
         if (unlikely(tracing_selftest_running || tracing_disabled))
                 return 0;
@@ -1526,43 +1596,36 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 
         pc = preempt_count();
         preempt_disable_notrace();
-        cpu = raw_smp_processor_id();
-        data = tr->data[cpu];
 
-        disable = atomic_inc_return(&data->disabled);
-        if (unlikely(disable != 1))
+        tbuffer = get_trace_buf();
+        if (!tbuffer) {
+                len = 0;
                 goto out;
+        }
 
-        /* Lockdep uses trace_printk for lock tracing */
-        local_irq_save(flags);
-        arch_spin_lock(&trace_buf_lock);
-        len = vbin_printf(trace_buf, TRACE_BUF_SIZE, fmt, args);
+        len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args);
 
-        if (len > TRACE_BUF_SIZE || len < 0)
-                goto out_unlock;
+        if (len > TRACE_BUF_SIZE/sizeof(int) || len < 0)
+                goto out;
 
+        local_save_flags(flags);
         size = sizeof(*entry) + sizeof(u32) * len;
         buffer = tr->buffer;
         event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
                                           flags, pc);
         if (!event)
-                goto out_unlock;
+                goto out;
         entry = ring_buffer_event_data(event);
         entry->ip                       = ip;
         entry->fmt                      = fmt;
 
-        memcpy(entry->buf, trace_buf, sizeof(u32) * len);
+        memcpy(entry->buf, tbuffer, sizeof(u32) * len);
         if (!filter_check_discard(call, entry, buffer, event)) {
                 ring_buffer_unlock_commit(buffer, event);
                 ftrace_trace_stack(buffer, flags, 6, pc);
         }
 
-out_unlock:
-        arch_spin_unlock(&trace_buf_lock);
-        local_irq_restore(flags);
-
 out:
-        atomic_dec_return(&data->disabled);
         preempt_enable_notrace();
         unpause_graph_tracing();
 
@@ -1588,58 +1651,53 @@ int trace_array_printk(struct trace_array *tr,
 int trace_array_vprintk(struct trace_array *tr,
                         unsigned long ip, const char *fmt, va_list args)
 {
-        static arch_spinlock_t trace_buf_lock = __ARCH_SPIN_LOCK_UNLOCKED;
-        static char trace_buf[TRACE_BUF_SIZE];
-
         struct ftrace_event_call *call = &event_print;
         struct ring_buffer_event *event;
         struct ring_buffer *buffer;
-        struct trace_array_cpu *data;
-        int cpu, len = 0, size, pc;
+        int len = 0, size, pc;
         struct print_entry *entry;
-        unsigned long irq_flags;
-        int disable;
+        unsigned long flags;
+        char *tbuffer;
 
         if (tracing_disabled || tracing_selftest_running)
                 return 0;
 
+        /* Don't pollute graph traces with trace_vprintk internals */
+        pause_graph_tracing();
+
         pc = preempt_count();
         preempt_disable_notrace();
-        cpu = raw_smp_processor_id();
-        data = tr->data[cpu];
 
-        disable = atomic_inc_return(&data->disabled);
-        if (unlikely(disable != 1))
+
+        tbuffer = get_trace_buf();
+        if (!tbuffer) {
+                len = 0;
                 goto out;
+        }
 
-        pause_graph_tracing();
-        raw_local_irq_save(irq_flags);
-        arch_spin_lock(&trace_buf_lock);
-        len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args);
+        len = vsnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args);
+        if (len > TRACE_BUF_SIZE)
+                goto out;
 
+        local_save_flags(flags);
         size = sizeof(*entry) + len + 1;
         buffer = tr->buffer;
         event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
-                                          irq_flags, pc);
+                                          flags, pc);
         if (!event)
-                goto out_unlock;
+                goto out;
         entry = ring_buffer_event_data(event);
         entry->ip = ip;
 
-        memcpy(&entry->buf, trace_buf, len);
+        memcpy(&entry->buf, tbuffer, len);
         entry->buf[len] = '\0';
         if (!filter_check_discard(call, entry, buffer, event)) {
                 ring_buffer_unlock_commit(buffer, event);
-                ftrace_trace_stack(buffer, irq_flags, 6, pc);
+                ftrace_trace_stack(buffer, flags, 6, pc);
         }
-
- out_unlock:
-        arch_spin_unlock(&trace_buf_lock);
-        raw_local_irq_restore(irq_flags);
-        unpause_graph_tracing();
  out:
-        atomic_dec_return(&data->disabled);
         preempt_enable_notrace();
+        unpause_graph_tracing();
 
         return len;
 }
@@ -1652,14 +1710,9 @@ EXPORT_SYMBOL_GPL(trace_vprintk);
 
 static void trace_iterator_increment(struct trace_iterator *iter)
 {
-        /* Don't allow ftrace to trace into the ring buffers */
-        ftrace_disable_cpu();
-
         iter->idx++;
         if (iter->buffer_iter[iter->cpu])
                 ring_buffer_read(iter->buffer_iter[iter->cpu], NULL);
-
-        ftrace_enable_cpu();
 }
 
 static struct trace_entry *
@@ -1669,17 +1722,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
         struct ring_buffer_event *event;
         struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu];
 
-        /* Don't allow ftrace to trace into the ring buffers */
-        ftrace_disable_cpu();
-
         if (buf_iter)
                 event = ring_buffer_iter_peek(buf_iter, ts);
         else
                 event = ring_buffer_peek(iter->tr->buffer, cpu, ts,
                                          lost_events);
 
-        ftrace_enable_cpu();
-
         if (event) {
                 iter->ent_size = ring_buffer_event_length(event);
                 return ring_buffer_event_data(event);
@@ -1769,11 +1817,8 @@ void *trace_find_next_entry_inc(struct trace_iterator *iter)
 
 static void trace_consume(struct trace_iterator *iter)
 {
-        /* Don't allow ftrace to trace into the ring buffers */
-        ftrace_disable_cpu();
         ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts,
                             &iter->lost_events);
-        ftrace_enable_cpu();
 }
 
 static void *s_next(struct seq_file *m, void *v, loff_t *pos)
@@ -1862,16 +1907,12 @@ static void *s_start(struct seq_file *m, loff_t *pos)
                 iter->cpu = 0;
                 iter->idx = -1;
 
-                ftrace_disable_cpu();
-
                 if (cpu_file == TRACE_PIPE_ALL_CPU) {
                         for_each_tracing_cpu(cpu)
                                 tracing_iter_reset(iter, cpu);
                 } else
                         tracing_iter_reset(iter, cpu_file);
 
-                ftrace_enable_cpu();
-
                 iter->leftover = 0;
                 for (p = iter; p && l < *pos; p = s_next(m, p, &l))
                         ;
@@ -2332,15 +2373,13 @@ static struct trace_iterator *
 __tracing_open(struct inode *inode, struct file *file)
 {
         long cpu_file = (long) inode->i_private;
-        void *fail_ret = ERR_PTR(-ENOMEM);
         struct trace_iterator *iter;
-        struct seq_file *m;
-        int cpu, ret;
+        int cpu;
 
         if (tracing_disabled)
                 return ERR_PTR(-ENODEV);
 
-        iter = kzalloc(sizeof(*iter), GFP_KERNEL);
+        iter = __seq_open_private(file, &tracer_seq_ops, sizeof(*iter));
         if (!iter)
                 return ERR_PTR(-ENOMEM);
 
@@ -2397,32 +2436,15 @@ __tracing_open(struct inode *inode, struct file *file)
                 tracing_iter_reset(iter, cpu);
         }
 
-        ret = seq_open(file, &tracer_seq_ops);
-        if (ret < 0) {
-                fail_ret = ERR_PTR(ret);
-                goto fail_buffer;
-        }
-
-        m = file->private_data;
-        m->private = iter;
-
         mutex_unlock(&trace_types_lock);
 
         return iter;
 
- fail_buffer:
-        for_each_tracing_cpu(cpu) {
-                if (iter->buffer_iter[cpu])
-                        ring_buffer_read_finish(iter->buffer_iter[cpu]);
-        }
-        free_cpumask_var(iter->started);
-        tracing_start();
  fail:
         mutex_unlock(&trace_types_lock);
         kfree(iter->trace);
-        kfree(iter);
-
-        return fail_ret;
+        seq_release_private(inode, file);
+        return ERR_PTR(-ENOMEM);
 }
 
 int tracing_open_generic(struct inode *inode, struct file *filp)
@@ -2458,11 +2480,10 @@ static int tracing_release(struct inode *inode, struct file *file)
         tracing_start();
         mutex_unlock(&trace_types_lock);
 
-        seq_release(inode, file);
         mutex_destroy(&iter->mutex);
         free_cpumask_var(iter->started);
         kfree(iter->trace);
-        kfree(iter);
+        seq_release_private(inode, file);
         return 0;
 }
 
@@ -2974,7 +2995,14 @@ int tracer_init(struct tracer *t, struct trace_array *tr)
         return t->init(tr);
 }
 
-static int __tracing_resize_ring_buffer(unsigned long size)
+static void set_buffer_entries(struct trace_array *tr, unsigned long val)
+{
+        int cpu;
+        for_each_tracing_cpu(cpu)
+                tr->data[cpu]->entries = val;
+}
+
+static int __tracing_resize_ring_buffer(unsigned long size, int cpu)
 {
         int ret;
 
@@ -2985,19 +3013,32 @@ static int __tracing_resize_ring_buffer(unsigned long size)
          */
         ring_buffer_expanded = 1;
 
-        ret = ring_buffer_resize(global_trace.buffer, size);
+        ret = ring_buffer_resize(global_trace.buffer, size, cpu);
         if (ret < 0)
                 return ret;
 
         if (!current_trace->use_max_tr)
                 goto out;
 
-        ret = ring_buffer_resize(max_tr.buffer, size);
+        ret = ring_buffer_resize(max_tr.buffer, size, cpu);
         if (ret < 0) {
-                int r;
+                int r = 0;
+
+                if (cpu == RING_BUFFER_ALL_CPUS) {
+                        int i;
+                        for_each_tracing_cpu(i) {
+                                r = ring_buffer_resize(global_trace.buffer,
+                                                global_trace.data[i]->entries,
+                                                i);
+                                if (r < 0)
+                                        break;
+                        }
+                } else {
+                        r = ring_buffer_resize(global_trace.buffer,
+                                                global_trace.data[cpu]->entries,
+                                                cpu);
+                }
 
-                r = ring_buffer_resize(global_trace.buffer,
-                                       global_trace.entries);
                 if (r < 0) {
                         /*
                          * AARGH! We are left with different
@@ -3019,14 +3060,21 @@ static int __tracing_resize_ring_buffer(unsigned long size)
                 return ret;
         }
 
-        max_tr.entries = size;
+        if (cpu == RING_BUFFER_ALL_CPUS)
+                set_buffer_entries(&max_tr, size);
+        else
+                max_tr.data[cpu]->entries = size;
+
  out:
-        global_trace.entries = size;
+        if (cpu == RING_BUFFER_ALL_CPUS)
+                set_buffer_entries(&global_trace, size);
+        else
+                global_trace.data[cpu]->entries = size;
 
         return ret;
 }
 
-static ssize_t tracing_resize_ring_buffer(unsigned long size)
+static ssize_t tracing_resize_ring_buffer(unsigned long size, int cpu_id)
 {
         int cpu, ret = size;
 
@@ -3042,12 +3090,19 @@ static ssize_t tracing_resize_ring_buffer(unsigned long size)
                         atomic_inc(&max_tr.data[cpu]->disabled);
         }
 
-        if (size != global_trace.entries)
-                ret = __tracing_resize_ring_buffer(size);
+        if (cpu_id != RING_BUFFER_ALL_CPUS) {
+                /* make sure, this cpu is enabled in the mask */
+                if (!cpumask_test_cpu(cpu_id, tracing_buffer_mask)) {
+                        ret = -EINVAL;
+                        goto out;
+                }
+        }
 
+        ret = __tracing_resize_ring_buffer(size, cpu_id);
         if (ret < 0)
                 ret = -ENOMEM;
 
+out:
         for_each_tracing_cpu(cpu) {
                 if (global_trace.data[cpu])
                         atomic_dec(&global_trace.data[cpu]->disabled);
@@ -3078,7 +3133,8 @@ int tracing_update_buffers(void)
 
         mutex_lock(&trace_types_lock);
         if (!ring_buffer_expanded)
-                ret = __tracing_resize_ring_buffer(trace_buf_size);
+                ret = __tracing_resize_ring_buffer(trace_buf_size,
+                                                RING_BUFFER_ALL_CPUS);
         mutex_unlock(&trace_types_lock);
 
         return ret;
@@ -3102,7 +3158,8 @@ static int tracing_set_tracer(const char *buf)
         mutex_lock(&trace_types_lock);
 
         if (!ring_buffer_expanded) {
-                ret = __tracing_resize_ring_buffer(trace_buf_size);
+                ret = __tracing_resize_ring_buffer(trace_buf_size,
+                                                RING_BUFFER_ALL_CPUS);
                 if (ret < 0)
                         goto out;
                 ret = 0;
@@ -3128,8 +3185,8 @@ static int tracing_set_tracer(const char *buf)
                  * The max_tr ring buffer has some state (e.g. ring->clock) and
                  * we want preserve it.
                  */
-                ring_buffer_resize(max_tr.buffer, 1);
-                max_tr.entries = 1;
+                ring_buffer_resize(max_tr.buffer, 1, RING_BUFFER_ALL_CPUS);
+                set_buffer_entries(&max_tr, 1);
         }
         destroy_trace_option_files(topts);
 
@@ -3137,10 +3194,17 @@ static int tracing_set_tracer(const char *buf)
 
         topts = create_trace_option_files(current_trace);
         if (current_trace->use_max_tr) {
-                ret = ring_buffer_resize(max_tr.buffer, global_trace.entries);
-                if (ret < 0)
-                        goto out;
-                max_tr.entries = global_trace.entries;
+                int cpu;
+                /* we need to make per cpu buffer sizes equivalent */
+                for_each_tracing_cpu(cpu) {
+                        ret = ring_buffer_resize(max_tr.buffer,
+                                                global_trace.data[cpu]->entries,
+                                                cpu);
+                        if (ret < 0)
+                                goto out;
+                        max_tr.data[cpu]->entries =
+                                        global_trace.data[cpu]->entries;
+                }
         }
 
         if (t->init) {
@@ -3642,30 +3706,82 @@ out_err:
         goto out;
 }
 
+struct ftrace_entries_info {
+        struct trace_array      *tr;
+        int                     cpu;
+};
+
+static int tracing_entries_open(struct inode *inode, struct file *filp)
+{
+        struct ftrace_entries_info *info;
+
+        if (tracing_disabled)
+                return -ENODEV;
+
+        info = kzalloc(sizeof(*info), GFP_KERNEL);
+        if (!info)
+                return -ENOMEM;
+
+        info->tr = &global_trace;
+        info->cpu = (unsigned long)inode->i_private;
+
+        filp->private_data = info;
+
+        return 0;
+}
+
 static ssize_t
 tracing_entries_read(struct file *filp, char __user *ubuf,
                      size_t cnt, loff_t *ppos)
 {
-        struct trace_array *tr = filp->private_data;
-        char buf[96];
-        int r;
+        struct ftrace_entries_info *info = filp->private_data;
+        struct trace_array *tr = info->tr;
+        char buf[64];
+        int r = 0;
+        ssize_t ret;
 
         mutex_lock(&trace_types_lock);
-        if (!ring_buffer_expanded)
-                r = sprintf(buf, "%lu (expanded: %lu)\n",
-                            tr->entries >> 10,
-                            trace_buf_size >> 10);
-        else
-                r = sprintf(buf, "%lu\n", tr->entries >> 10);
+
+        if (info->cpu == RING_BUFFER_ALL_CPUS) {
+                int cpu, buf_size_same;
+                unsigned long size;
+
+                size = 0;
+                buf_size_same = 1;
+                /* check if all cpu sizes are same */
+                for_each_tracing_cpu(cpu) {
+                        /* fill in the size from first enabled cpu */
+                        if (size == 0)
+                                size = tr->data[cpu]->entries;
+                        if (size != tr->data[cpu]->entries) {
+                                buf_size_same = 0;
+                                break;
+                        }
+                }
+
+                if (buf_size_same) {
+                        if (!ring_buffer_expanded)
+                                r = sprintf(buf, "%lu (expanded: %lu)\n",
+                                            size >> 10,
+                                            trace_buf_size >> 10);
+                        else
+                                r = sprintf(buf, "%lu\n", size >> 10);
+                } else
+                        r = sprintf(buf, "X\n");
+        } else
+                r = sprintf(buf, "%lu\n", tr->data[info->cpu]->entries >> 10);
+
         mutex_unlock(&trace_types_lock);
 
-        return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+        ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+        return ret;
 }
 
 static ssize_t
 tracing_entries_write(struct file *filp, const char __user *ubuf,
                       size_t cnt, loff_t *ppos)
 {
+        struct ftrace_entries_info *info = filp->private_data;
         unsigned long val;
         int ret;
 
@@ -3680,7 +3796,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
         /* value is in KB */
         val <<= 10;
 
-        ret = tracing_resize_ring_buffer(val);
+        ret = tracing_resize_ring_buffer(val, info->cpu);
         if (ret < 0)
                 return ret;
 
@@ -3689,6 +3805,16 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
         return cnt;
 }
 
+static int
+tracing_entries_release(struct inode *inode, struct file *filp)
+{
+        struct ftrace_entries_info *info = filp->private_data;
+
+        kfree(info);
+
+        return 0;
+}
+
 static ssize_t
 tracing_total_entries_read(struct file *filp, char __user *ubuf,
                                 size_t cnt, loff_t *ppos)
@@ -3700,7 +3826,7 @@ tracing_total_entries_read(struct file *filp, char __user *ubuf,
 
         mutex_lock(&trace_types_lock);
         for_each_tracing_cpu(cpu) {
-                size += tr->entries >> 10;
+                size += tr->data[cpu]->entries >> 10;
                 if (!ring_buffer_expanded)
                         expanded_size += trace_buf_size >> 10;
         }
@@ -3734,7 +3860,7 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp)
         if (trace_flags & TRACE_ITER_STOP_ON_FREE)
                 tracing_off();
         /* resize the ring buffer to 0 */
-        tracing_resize_ring_buffer(0);
+        tracing_resize_ring_buffer(0, RING_BUFFER_ALL_CPUS);
 
         return 0;
 }
@@ -3933,9 +4059,10 @@ static const struct file_operations tracing_pipe_fops = {
 };
 
 static const struct file_operations tracing_entries_fops = {
-        .open           = tracing_open_generic,
+        .open           = tracing_entries_open,
         .read           = tracing_entries_read,
         .write          = tracing_entries_write,
+        .release        = tracing_entries_release,
         .llseek         = generic_file_llseek,
 };
 
@@ -4387,6 +4514,9 @@ static void tracing_init_debugfs_percpu(long cpu)
 
         trace_create_file("stats", 0444, d_cpu,
                         (void *) cpu, &tracing_stats_fops);
+
+        trace_create_file("buffer_size_kb", 0444, d_cpu,
+                        (void *) cpu, &tracing_entries_fops);
 }
 
 #ifdef CONFIG_FTRACE_SELFTEST
@@ -4716,7 +4846,7 @@ static __init int tracer_init_debugfs(void)
                         (void *) TRACE_PIPE_ALL_CPU, &tracing_pipe_fops);
 
         trace_create_file("buffer_size_kb", 0644, d_tracer,
-                        &global_trace, &tracing_entries_fops);
+                        (void *) RING_BUFFER_ALL_CPUS, &tracing_entries_fops);
 
         trace_create_file("buffer_total_size_kb", 0444, d_tracer,
                         &global_trace, &tracing_total_entries_fops);
@@ -4955,6 +5085,10 @@ __init static int tracer_alloc_buffers(void)
         if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
                 goto out_free_buffer_mask;
 
+        /* Only allocate trace_printk buffers if a trace_printk exists */
+        if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt)
+                trace_printk_init_buffers();
+
         /* To save memory, keep the ring buffer size to its minimum */
         if (ring_buffer_expanded)
                 ring_buf_size = trace_buf_size;
@@ -4973,7 +5107,6 @@ __init static int tracer_alloc_buffers(void)
                 WARN_ON(1);
                 goto out_free_cpumask;
         }
-        global_trace.entries = ring_buffer_size(global_trace.buffer);
         if (global_trace.buffer_disabled)
                 tracing_off();
 
@@ -4986,7 +5119,6 @@ __init static int tracer_alloc_buffers(void)
                 ring_buffer_free(global_trace.buffer);
                 goto out_free_cpumask;
         }
-        max_tr.entries = 1;
 #endif
 
         /* Allocate the first page for all buffers */
@@ -4995,6 +5127,11 @@ __init static int tracer_alloc_buffers(void)
                 max_tr.data[i] = &per_cpu(max_tr_data, i);
         }
 
+        set_buffer_entries(&global_trace, ring_buf_size);
+#ifdef CONFIG_TRACER_MAX_TRACE
+        set_buffer_entries(&max_tr, 1);
+#endif
+
         trace_init_cmdlines();
 
         register_tracer(&nop_trace);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 1bcdbec95a11..a7d28e033a96 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -136,6 +136,7 @@ struct trace_array_cpu {
         atomic_t                disabled;
         void                    *buffer_page;   /* ring buffer spare */
 
+        unsigned long           entries;
         unsigned long           saved_latency;
         unsigned long           critical_start;
         unsigned long           critical_end;
@@ -157,7 +158,6 @@ struct trace_array_cpu {
  */
 struct trace_array {
         struct ring_buffer      *buffer;
-        unsigned long           entries;
         int                     cpu;
         int                     buffer_disabled;
         cycle_t                 time_start;
@@ -831,6 +831,8 @@ extern struct list_head ftrace_events;
 extern const char *__start___trace_bprintk_fmt[];
 extern const char *__stop___trace_bprintk_fmt[];
 
+void trace_printk_init_buffers(void);
+
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter)     \
         extern struct ftrace_event_call                                 \
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 6fd4ffd042f9..a9077c1b4ad3 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -51,6 +51,10 @@ void hold_module_trace_bprintk_format(const char **start, const char **end)
         const char **iter;
         char *fmt;
 
+        /* allocate the trace_printk per cpu buffers */
+        if (start != end)
+                trace_printk_init_buffers();
+
         mutex_lock(&btrace_mutex);
         for (iter = start; iter < end; iter++) {
                 struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter);