14 files changed, 144 insertions, 63 deletions

diff --git a/kernel/capability.c b/kernel/capability.c
index 493d97259484..f6c2ce5701e1 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -393,6 +393,30 @@ bool ns_capable(struct user_namespace *ns, int cap)
 EXPORT_SYMBOL(ns_capable);
 
 /**
+ * file_ns_capable - Determine if the file's opener had a capability in effect
+ * @file:  The file we want to check
+ * @ns:  The usernamespace we want the capability in
+ * @cap: The capability to be tested for
+ *
+ * Return true if task that opened the file had a capability in effect
+ * when the file was opened.
+ *
+ * This does not set PF_SUPERPRIV because the caller may not
+ * actually be privileged.
+ */
+bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap)
+{
+        if (WARN_ON_ONCE(!cap_valid(cap)))
+                return false;
+
+        if (security_capable(file->f_cred, ns, cap) == 0)
+                return true;
+
+        return false;
+}
+EXPORT_SYMBOL(file_ns_capable);
+
+/**
  * capable - Determine if the current task has a superior capability in effect
  * @cap: The capability to be tested for
  *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 59412d037eed..7e0962ed7f8a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4737,7 +4737,8 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
         } else {
                 if (arch_vma_name(mmap_event->vma)) {
                         name = strncpy(tmp, arch_vma_name(mmap_event->vma),
-                                       sizeof(tmp));
+                                       sizeof(tmp) - 1);
+                        tmp[sizeof(tmp) - 1] = '\0';
                         goto got_name;
                 }
 
@@ -5986,6 +5987,7 @@ skip_type:
         if (pmu->pmu_cpu_context)
                 goto got_cpu_context;
 
+        ret = -ENOMEM;
         pmu->pmu_cpu_context = alloc_percpu(struct perf_cpu_context);
         if (!pmu->pmu_cpu_context)
                 goto free_dev;
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index d56a64c99a8b..eb675c4d59df 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -16,7 +16,7 @@ struct ring_buffer {
         int                             page_order;     /* allocation order  */
 #endif
         int                             nr_pages;       /* nr of data pages  */
-        int                             writable;       /* are we writable   */
+        int                             overwrite;      /* can overwrite itself */
 
         atomic_t                        poll;           /* POLL_ for wakeups */
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 23cb34ff3973..97fddb09762b 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -18,12 +18,24 @@
 static bool perf_output_space(struct ring_buffer *rb, unsigned long tail,
                               unsigned long offset, unsigned long head)
 {
-        unsigned long mask;
+        unsigned long sz = perf_data_size(rb);
+        unsigned long mask = sz - 1;
 
-        if (!rb->writable)
+        /*
+         * check if user-writable
+         * overwrite : over-write its own tail
+         * !overwrite: buffer possibly drops events.
+         */
+        if (rb->overwrite)
                 return true;
 
-        mask = perf_data_size(rb) - 1;
+        /*
+         * verify that payload is not bigger than buffer
+         * otherwise masking logic may fail to detect
+         * the "not enough space" condition
+         */
+        if ((head - offset) > sz)
+                return false;
 
         offset = (offset - tail) & mask;
         head   = (head   - tail) & mask;
@@ -212,7 +224,9 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
                 rb->watermark = max_size / 2;
 
         if (flags & RING_BUFFER_WRITABLE)
-                rb->writable = 1;
+                rb->overwrite = 0;
+        else
+                rb->overwrite = 1;
 
         atomic_set(&rb->refcount, 1);
 
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index cc47812d3feb..14be27feda49 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -63,6 +63,7 @@
 DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
 
+        .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
         .clock_base =
         {
                 {
@@ -1642,8 +1643,6 @@ static void __cpuinit init_hrtimers_cpu(int cpu)
         struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
         int i;
 
-        raw_spin_lock_init(&cpu_base->lock);
-
         for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
                 cpu_base->clock_base[i].cpu_base = cpu_base;
                 timerqueue_init_head(&cpu_base->clock_base[i].active);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 691dc2ef9baf..9eb7fed0bbaa 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -124,12 +124,12 @@ void *kthread_data(struct task_struct *task)
 
 static void __kthread_parkme(struct kthread *self)
 {
-        __set_current_state(TASK_INTERRUPTIBLE);
+        __set_current_state(TASK_PARKED);
         while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) {
                 if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags))
                         complete(&self->parked);
                 schedule();
-                __set_current_state(TASK_INTERRUPTIBLE);
+                __set_current_state(TASK_PARKED);
         }
         clear_bit(KTHREAD_IS_PARKED, &self->flags);
         __set_current_state(TASK_RUNNING);
@@ -256,8 +256,13 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 }
 EXPORT_SYMBOL(kthread_create_on_node);
 
-static void __kthread_bind(struct task_struct *p, unsigned int cpu)
+static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state)
 {
+        /* Must have done schedule() in kthread() before we set_task_cpu */
+        if (!wait_task_inactive(p, state)) {
+                WARN_ON(1);
+                return;
+        }
         /* It's safe because the task is inactive. */
         do_set_cpus_allowed(p, cpumask_of(cpu));
         p->flags |= PF_THREAD_BOUND;
@@ -274,12 +279,7 @@ static void __kthread_bind(struct task_struct *p, unsigned int cpu)
  */
 void kthread_bind(struct task_struct *p, unsigned int cpu)
 {
-        /* Must have done schedule() in kthread() before we set_task_cpu */
-        if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
-                WARN_ON(1);
-                return;
-        }
-        __kthread_bind(p, cpu);
+        __kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(kthread_bind);
 
@@ -324,6 +324,22 @@ static struct kthread *task_get_live_kthread(struct task_struct *k)
         return NULL;
 }
 
+static void __kthread_unpark(struct task_struct *k, struct kthread *kthread)
+{
+        clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+        /*
+         * We clear the IS_PARKED bit here as we don't wait
+         * until the task has left the park code. So if we'd
+         * park before that happens we'd see the IS_PARKED bit
+         * which might be about to be cleared.
+         */
+        if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
+                if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
+                        __kthread_bind(k, kthread->cpu, TASK_PARKED);
+                wake_up_state(k, TASK_PARKED);
+        }
+}
+
 /**
  * kthread_unpark - unpark a thread created by kthread_create().
  * @k:          thread created by kthread_create().
@@ -336,20 +352,8 @@ void kthread_unpark(struct task_struct *k)
 {
         struct kthread *kthread = task_get_live_kthread(k);
 
-        if (kthread) {
-                clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
-                /*
-                 * We clear the IS_PARKED bit here as we don't wait
-                 * until the task has left the park code. So if we'd
-                 * park before that happens we'd see the IS_PARKED bit
-                 * which might be about to be cleared.
-                 */
-                if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
-                        if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
-                                __kthread_bind(k, kthread->cpu);
-                        wake_up_process(k);
-                }
-        }
+        if (kthread)
+                __kthread_unpark(k, kthread);
         put_task_struct(k);
 }
 
@@ -407,7 +411,7 @@ int kthread_stop(struct task_struct *k)
         trace_sched_kthread_stop(k);
         if (kthread) {
                 set_bit(KTHREAD_SHOULD_STOP, &kthread->flags);
-                clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+                __kthread_unpark(k, kthread);
                 wake_up_process(k);
                 wait_for_completion(&kthread->exited);
         }
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c685e31492df..c3ae1446461c 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -176,10 +176,36 @@ static u64 sched_clock_remote(struct sched_clock_data *scd)
         u64 this_clock, remote_clock;
         u64 *ptr, old_val, val;
 
+#if BITS_PER_LONG != 64
+again:
+        /*
+         * Careful here: The local and the remote clock values need to
+         * be read out atomic as we need to compare the values and
+         * then update either the local or the remote side. So the
+         * cmpxchg64 below only protects one readout.
+         *
+         * We must reread via sched_clock_local() in the retry case on
+         * 32bit as an NMI could use sched_clock_local() via the
+         * tracer and hit between the readout of
+         * the low32bit and the high 32bit portion.
+         */
+        this_clock = sched_clock_local(my_scd);
+        /*
+         * We must enforce atomic readout on 32bit, otherwise the
+         * update on the remote cpu can hit inbetween the readout of
+         * the low32bit and the high 32bit portion.
+         */
+        remote_clock = cmpxchg64(&scd->clock, 0, 0);
+#else
+        /*
+         * On 64bit the read of [my]scd->clock is atomic versus the
+         * update, so we can avoid the above 32bit dance.
+         */
         sched_clock_local(my_scd);
 again:
         this_clock = my_scd->clock;
         remote_clock = scd->clock;
+#endif
 
         /*
          * Use the opportunity that we have both locks
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7f12624a393c..67d04651f44b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1498,8 +1498,10 @@ static void try_to_wake_up_local(struct task_struct *p)
 {
         struct rq *rq = task_rq(p);
 
-        BUG_ON(rq != this_rq());
-        BUG_ON(p == current);
+        if (WARN_ON_ONCE(rq != this_rq()) ||
+            WARN_ON_ONCE(p == current))
+                return;
+
         lockdep_assert_held(&rq->lock);
 
         if (!raw_spin_trylock(&p->pi_lock)) {
@@ -4999,7 +5001,7 @@ static void sd_free_ctl_entry(struct ctl_table **tablep)
 }
 
 static int min_load_idx = 0;
-static int max_load_idx = CPU_LOAD_IDX_MAX;
+static int max_load_idx = CPU_LOAD_IDX_MAX-1;
 
 static void
 set_table_entry(struct ctl_table *entry,
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index ed12cbb135f4..e93cca92f38b 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -310,7 +310,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 
         t = tsk;
         do {
-                task_cputime(tsk, &utime, &stime);
+                task_cputime(t, &utime, &stime);
                 times->utime += utime;
                 times->stime += stime;
                 times->sum_exec_runtime += task_sched_runtime(t);
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 8eaed9aa9cf0..02fc5c933673 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -185,8 +185,18 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
         }
         get_task_struct(tsk);
         *per_cpu_ptr(ht->store, cpu) = tsk;
-        if (ht->create)
-                ht->create(cpu);
+        if (ht->create) {
+                /*
+                 * Make sure that the task has actually scheduled out
+                 * into park position, before calling the create
+                 * callback. At least the migration thread callback
+                 * requires that the task is off the runqueue.
+                 */
+                if (!wait_task_inactive(tsk, TASK_PARKED))
+                        WARN_ON(1);
+                else
+                        ht->create(cpu);
+        }
         return 0;
 }
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 39c9c4a2949f..0da73cf73e60 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -324,7 +324,6 @@ void kernel_restart_prepare(char *cmd)
         system_state = SYSTEM_RESTART;
         usermodehelper_disable();
         device_shutdown();
-        syscore_shutdown();
 }
 
 /**
@@ -370,6 +369,7 @@ void kernel_restart(char *cmd)
 {
         kernel_restart_prepare(cmd);
         disable_nonboot_cpus();
+        syscore_shutdown();
         if (!cmd)
                 printk(KERN_EMERG "Restarting system.\n");
         else
@@ -395,6 +395,7 @@ static void kernel_shutdown_prepare(enum system_states state)
 void kernel_halt(void)
 {
         kernel_shutdown_prepare(SYSTEM_HALT);
+        disable_nonboot_cpus();
         syscore_shutdown();
         printk(KERN_EMERG "System halted.\n");
         kmsg_dump(KMSG_DUMP_HALT);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 7e897106b7e0..b3fde6d7b7fc 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -694,7 +694,6 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
                 free_page(tmp);
         }
 
-        free_page((unsigned long)stat->pages);
         stat->pages = NULL;
         stat->start = NULL;
 
@@ -1053,6 +1052,19 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
 
 static struct pid * const ftrace_swapper_pid = &init_struct_pid;
 
+loff_t
+ftrace_filter_lseek(struct file *file, loff_t offset, int whence)
+{
+        loff_t ret;
+
+        if (file->f_mode & FMODE_READ)
+                ret = seq_lseek(file, offset, whence);
+        else
+                file->f_pos = ret = 1;
+
+        return ret;
+}
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 #ifndef CONFIG_FTRACE_MCOUNT_RECORD
@@ -2613,7 +2625,7 @@ static void ftrace_filter_reset(struct ftrace_hash *hash)
  * routine, you can use ftrace_filter_write() for the write
  * routine if @flag has FTRACE_ITER_FILTER set, or
  * ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set.
- * ftrace_regex_lseek() should be used as the lseek routine, and
+ * ftrace_filter_lseek() should be used as the lseek routine, and
  * release must call ftrace_regex_release().
  */
 int
@@ -2697,19 +2709,6 @@ ftrace_notrace_open(struct inode *inode, struct file *file)
                                  inode, file);
 }
 
-loff_t
-ftrace_regex_lseek(struct file *file, loff_t offset, int whence)
-{
-        loff_t ret;
-
-        if (file->f_mode & FMODE_READ)
-                ret = seq_lseek(file, offset, whence);
-        else
-                file->f_pos = ret = 1;
-
-        return ret;
-}
-
 static int ftrace_match(char *str, char *regex, int len, int type)
 {
         int matched = 0;
@@ -3441,14 +3440,14 @@ static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata;
 
 static int __init set_ftrace_notrace(char *str)
 {
-        strncpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
+        strlcpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
         return 1;
 }
 __setup("ftrace_notrace=", set_ftrace_notrace);
 
 static int __init set_ftrace_filter(char *str)
 {
-        strncpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
+        strlcpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
         return 1;
 }
 __setup("ftrace_filter=", set_ftrace_filter);
@@ -3571,7 +3570,7 @@ static const struct file_operations ftrace_filter_fops = {
         .open = ftrace_filter_open,
         .read = seq_read,
         .write = ftrace_filter_write,
-        .llseek = ftrace_regex_lseek,
+        .llseek = ftrace_filter_lseek,
         .release = ftrace_regex_release,
 };
 
@@ -3579,7 +3578,7 @@ static const struct file_operations ftrace_notrace_fops = {
         .open = ftrace_notrace_open,
         .read = seq_read,
         .write = ftrace_notrace_write,
-        .llseek = ftrace_regex_lseek,
+        .llseek = ftrace_filter_lseek,
         .release = ftrace_regex_release,
 };
 
@@ -3784,8 +3783,8 @@ static const struct file_operations ftrace_graph_fops = {
         .open           = ftrace_graph_open,
         .read           = seq_read,
         .write          = ftrace_graph_write,
+        .llseek         = ftrace_filter_lseek,
         .release        = ftrace_graph_release,
-        .llseek         = seq_lseek,
 };
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
@@ -4440,7 +4439,7 @@ static const struct file_operations ftrace_pid_fops = {
         .open           = ftrace_pid_open,
         .write          = ftrace_pid_write,
         .read           = seq_read,
-        .llseek         = seq_lseek,
+        .llseek         = ftrace_filter_lseek,
         .release        = ftrace_pid_release,
 };
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7ba7fc76f9eb..66338c4f7f4b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -132,7 +132,7 @@ static char *default_bootup_tracer;
 
 static int __init set_cmdline_ftrace(char *str)
 {
-        strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
+        strlcpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
         default_bootup_tracer = bootup_tracer_buf;
         /* We are using ftrace early, expand it */
         ring_buffer_expanded = 1;
@@ -162,7 +162,7 @@ static char *trace_boot_options __initdata;
 
 static int __init set_trace_boot_options(char *str)
 {
-        strncpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
+        strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
         trace_boot_options = trace_boot_options_buf;
         return 0;
 }
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 42ca822fc701..83a8b5b7bd35 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -322,7 +322,7 @@ static const struct file_operations stack_trace_filter_fops = {
         .open = stack_trace_filter_open,
         .read = seq_read,
         .write = ftrace_filter_write,
-        .llseek = ftrace_regex_lseek,
+        .llseek = ftrace_filter_lseek,
         .release = ftrace_regex_release,
 };