16 files changed, 349 insertions, 164 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 3737a682cdf5..b6eadfe30e7b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -47,6 +47,7 @@
 #include <linux/hash.h>
 #include <linux/namei.h>
 #include <linux/smp_lock.h>
+#include <linux/pid_namespace.h>
 
 #include <asm/atomic.h>
 
@@ -734,16 +735,28 @@ static void cgroup_d_remove_dir(struct dentry *dentry)
  * reference to css->refcnt. In general, this refcnt is expected to goes down
  * to zero, soon.
  *
- * CGRP_WAIT_ON_RMDIR flag is modified under cgroup's inode->i_mutex;
+ * CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex;
  */
 DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
 
-static void cgroup_wakeup_rmdir_waiters(const struct cgroup *cgrp)
+static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp)
 {
-        if (unlikely(test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
+        if (unlikely(test_and_clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
                 wake_up_all(&cgroup_rmdir_waitq);
 }
 
+void cgroup_exclude_rmdir(struct cgroup_subsys_state *css)
+{
+        css_get(css);
+}
+
+void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css)
+{
+        cgroup_wakeup_rmdir_waiter(css->cgroup);
+        css_put(css);
+}
+
+
 static int rebind_subsystems(struct cgroupfs_root *root,
                               unsigned long final_bits)
 {
@@ -960,6 +973,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
         INIT_LIST_HEAD(&cgrp->children);
         INIT_LIST_HEAD(&cgrp->css_sets);
         INIT_LIST_HEAD(&cgrp->release_list);
+        INIT_LIST_HEAD(&cgrp->pids_list);
         init_rwsem(&cgrp->pids_mutex);
 }
 static void init_cgroup_root(struct cgroupfs_root *root)
@@ -1357,7 +1371,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
          * wake up rmdir() waiter. the rmdir should fail since the cgroup
          * is no longer empty.
          */
-        cgroup_wakeup_rmdir_waiters(cgrp);
+        cgroup_wakeup_rmdir_waiter(cgrp);
         return 0;
 }
 
@@ -2201,12 +2215,30 @@ err:
         return ret;
 }
 
+/*
+ * Cache pids for all threads in the same pid namespace that are
+ * opening the same "tasks" file.
+ */
+struct cgroup_pids {
+        /* The node in cgrp->pids_list */
+        struct list_head list;
+        /* The cgroup those pids belong to */
+        struct cgroup *cgrp;
+        /* The namepsace those pids belong to */
+        struct pid_namespace *ns;
+        /* Array of process ids in the cgroup */
+        pid_t *tasks_pids;
+        /* How many files are using the this tasks_pids array */
+        int use_count;
+        /* Length of the current tasks_pids array */
+        int length;
+};
+
 static int cmppid(const void *a, const void *b)
 {
         return *(pid_t *)a - *(pid_t *)b;
 }
 
-
 /*
  * seq_file methods for the "tasks" file. The seq_file position is the
  * next pid to display; the seq_file iterator is a pointer to the pid
@@ -2221,45 +2253,47 @@ static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos)
          * after a seek to the start). Use a binary-search to find the
          * next pid to display, if any
          */
-        struct cgroup *cgrp = s->private;
+        struct cgroup_pids *cp = s->private;
+        struct cgroup *cgrp = cp->cgrp;
         int index = 0, pid = *pos;
         int *iter;
 
         down_read(&cgrp->pids_mutex);
         if (pid) {
-                int end = cgrp->pids_length;
+                int end = cp->length;
 
                 while (index < end) {
                         int mid = (index + end) / 2;
-                        if (cgrp->tasks_pids[mid] == pid) {
+                        if (cp->tasks_pids[mid] == pid) {
                                 index = mid;
                                 break;
-                        } else if (cgrp->tasks_pids[mid] <= pid)
+                        } else if (cp->tasks_pids[mid] <= pid)
                                 index = mid + 1;
                         else
                                 end = mid;
                 }
         }
         /* If we're off the end of the array, we're done */
-        if (index >= cgrp->pids_length)
+        if (index >= cp->length)
                 return NULL;
         /* Update the abstract position to be the actual pid that we found */
-        iter = cgrp->tasks_pids + index;
+        iter = cp->tasks_pids + index;
         *pos = *iter;
         return iter;
 }
 
 static void cgroup_tasks_stop(struct seq_file *s, void *v)
 {
-        struct cgroup *cgrp = s->private;
+        struct cgroup_pids *cp = s->private;
+        struct cgroup *cgrp = cp->cgrp;
         up_read(&cgrp->pids_mutex);
 }
 
 static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
 {
-        struct cgroup *cgrp = s->private;
+        struct cgroup_pids *cp = s->private;
         int *p = v;
-        int *end = cgrp->tasks_pids + cgrp->pids_length;
+        int *end = cp->tasks_pids + cp->length;
 
         /*
          * Advance to the next pid in the array. If this goes off the
@@ -2286,26 +2320,33 @@ static struct seq_operations cgroup_tasks_seq_operations = {
         .show = cgroup_tasks_show,
 };
 
-static void release_cgroup_pid_array(struct cgroup *cgrp)
+static void release_cgroup_pid_array(struct cgroup_pids *cp)
 {
+        struct cgroup *cgrp = cp->cgrp;
+
         down_write(&cgrp->pids_mutex);
-        BUG_ON(!cgrp->pids_use_count);
-        if (!--cgrp->pids_use_count) {
-                kfree(cgrp->tasks_pids);
-                cgrp->tasks_pids = NULL;
-                cgrp->pids_length = 0;
+        BUG_ON(!cp->use_count);
+        if (!--cp->use_count) {
+                list_del(&cp->list);
+                put_pid_ns(cp->ns);
+                kfree(cp->tasks_pids);
+                kfree(cp);
         }
         up_write(&cgrp->pids_mutex);
 }
 
 static int cgroup_tasks_release(struct inode *inode, struct file *file)
 {
-        struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
+        struct seq_file *seq;
+        struct cgroup_pids *cp;
 
         if (!(file->f_mode & FMODE_READ))
                 return 0;
 
-        release_cgroup_pid_array(cgrp);
+        seq = file->private_data;
+        cp = seq->private;
+
+        release_cgroup_pid_array(cp);
         return seq_release(inode, file);
 }
 
@@ -2324,6 +2365,8 @@ static struct file_operations cgroup_tasks_operations = {
 static int cgroup_tasks_open(struct inode *unused, struct file *file)
 {
         struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
+        struct pid_namespace *ns = current->nsproxy->pid_ns;
+        struct cgroup_pids *cp;
         pid_t *pidarray;
         int npids;
         int retval;
@@ -2350,20 +2393,37 @@ static int cgroup_tasks_open(struct inode *unused, struct file *file)
          * array if necessary
          */
         down_write(&cgrp->pids_mutex);
-        kfree(cgrp->tasks_pids);
-        cgrp->tasks_pids = pidarray;
-        cgrp->pids_length = npids;
-        cgrp->pids_use_count++;
+
+        list_for_each_entry(cp, &cgrp->pids_list, list) {
+                if (ns == cp->ns)
+                        goto found;
+        }
+
+        cp = kzalloc(sizeof(*cp), GFP_KERNEL);
+        if (!cp) {
+                up_write(&cgrp->pids_mutex);
+                kfree(pidarray);
+                return -ENOMEM;
+        }
+        cp->cgrp = cgrp;
+        cp->ns = ns;
+        get_pid_ns(ns);
+        list_add(&cp->list, &cgrp->pids_list);
+found:
+        kfree(cp->tasks_pids);
+        cp->tasks_pids = pidarray;
+        cp->length = npids;
+        cp->use_count++;
         up_write(&cgrp->pids_mutex);
 
         file->f_op = &cgroup_tasks_operations;
 
         retval = seq_open(file, &cgroup_tasks_seq_operations);
         if (retval) {
-                release_cgroup_pid_array(cgrp);
+                release_cgroup_pid_array(cp);
                 return retval;
         }
-        ((struct seq_file *)file->private_data)->private = cgrp;
+        ((struct seq_file *)file->private_data)->private = cp;
         return 0;
 }
 
@@ -2696,33 +2756,42 @@ again:
         mutex_unlock(&cgroup_mutex);
 
         /*
+         * In general, subsystem has no css->refcnt after pre_destroy(). But
+         * in racy cases, subsystem may have to get css->refcnt after
+         * pre_destroy() and it makes rmdir return with -EBUSY. This sometimes
+         * make rmdir return -EBUSY too often. To avoid that, we use waitqueue
+         * for cgroup's rmdir. CGRP_WAIT_ON_RMDIR is for synchronizing rmdir
+         * and subsystem's reference count handling. Please see css_get/put
+         * and css_tryget() and cgroup_wakeup_rmdir_waiter() implementation.
+         */
+        set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
+
+        /*
          * Call pre_destroy handlers of subsys. Notify subsystems
          * that rmdir() request comes.
          */
         ret = cgroup_call_pre_destroy(cgrp);
-        if (ret)
+        if (ret) {
+                clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
                 return ret;
+        }
 
         mutex_lock(&cgroup_mutex);
         parent = cgrp->parent;
         if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
+                clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
                 mutex_unlock(&cgroup_mutex);
                 return -EBUSY;
         }
-        /*
-         * css_put/get is provided for subsys to grab refcnt to css. In typical
-         * case, subsystem has no reference after pre_destroy(). But, under
-         * hierarchy management, some *temporal* refcnt can be hold.
-         * To avoid returning -EBUSY to a user, waitqueue is used. If subsys
-         * is really busy, it should return -EBUSY at pre_destroy(). wake_up
-         * is called when css_put() is called and refcnt goes down to 0.
-         */
-        set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
         prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE);
-
         if (!cgroup_clear_css_refs(cgrp)) {
                 mutex_unlock(&cgroup_mutex);
-                schedule();
+                /*
+                 * Because someone may call cgroup_wakeup_rmdir_waiter() before
+                 * prepare_to_wait(), we need to check this flag.
+                 */
+                if (test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags))
+                        schedule();
                 finish_wait(&cgroup_rmdir_waitq, &wait);
                 clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
                 if (signal_pending(current))
@@ -3294,7 +3363,7 @@ void __css_put(struct cgroup_subsys_state *css)
                         set_bit(CGRP_RELEASABLE, &cgrp->flags);
                         check_for_release(cgrp);
                 }
-                cgroup_wakeup_rmdir_waiters(cgrp);
+                cgroup_wakeup_rmdir_waiter(cgrp);
         }
         rcu_read_unlock();
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index bd2959228871..29b532e718f7 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -426,6 +426,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
         init_rwsem(&mm->mmap_sem);
         INIT_LIST_HEAD(&mm->mmlist);
         mm->flags = (current->mm) ? current->mm->flags : default_dump_filter;
+        mm->oom_adj = (current->mm) ? current->mm->oom_adj : 0;
         mm->core_state = NULL;
         mm->nr_ptes = 0;
         set_mm_counter(mm, file_rss, 0);
@@ -1407,14 +1408,11 @@ long do_fork(unsigned long clone_flags,
                 if (clone_flags & CLONE_VFORK) {
                         p->vfork_done = &vfork;
                         init_completion(&vfork);
-                } else if (!(clone_flags & CLONE_VM)) {
-                        /*
-                         * vfork will do an exec which will call
-                         * set_task_comm()
-                         */
-                        perf_counter_fork(p);
                 }
 
+                if (!(clone_flags & CLONE_THREAD))
+                        perf_counter_fork(p);
+
                 audit_finish_fork(p);
                 tracehook_report_clone(regs, clone_flags, nr, p);
 
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 2f4936cf7083..bd1d42b17cb2 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -44,12 +44,19 @@ void refrigerator(void)
         recalc_sigpending(); /* We sent fake signal, clean it up */
         spin_unlock_irq(&current->sighand->siglock);
 
+        /* prevent accounting of that task to load */
+        current->flags |= PF_FREEZING;
+
         for (;;) {
                 set_current_state(TASK_UNINTERRUPTIBLE);
                 if (!frozen(current))
                         break;
                 schedule();
         }
+
+        /* Remove the accounting blocker */
+        current->flags &= ~PF_FREEZING;
+
         pr_debug("%s left refrigerator\n", current->comm);
         __set_current_state(save);
 }
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 73468253143b..e70ed5592eb9 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -42,8 +42,7 @@ static inline void unregister_handler_proc(unsigned int irq,
 
 extern int irq_select_affinity_usr(unsigned int irq);
 
-extern void
-irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask);
+extern void irq_set_thread_affinity(struct irq_desc *desc);
 
 /*
  * Debugging printout:
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 50da67672901..61c679db4687 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -80,14 +80,22 @@ int irq_can_set_affinity(unsigned int irq)
         return 1;
 }
 
-void
-irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask)
+/**
+ *      irq_set_thread_affinity - Notify irq threads to adjust affinity
+ *      @desc:          irq descriptor which has affitnity changed
+ *
+ *      We just set IRQTF_AFFINITY and delegate the affinity setting
+ *      to the interrupt thread itself. We can not call
+ *      set_cpus_allowed_ptr() here as we hold desc->lock and this
+ *      code can be called from hard interrupt context.
+ */
+void irq_set_thread_affinity(struct irq_desc *desc)
 {
         struct irqaction *action = desc->action;
 
         while (action) {
                 if (action->thread)
-                        set_cpus_allowed_ptr(action->thread, cpumask);
+                        set_bit(IRQTF_AFFINITY, &action->thread_flags);
                 action = action->next;
         }
 }
@@ -112,7 +120,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
         if (desc->status & IRQ_MOVE_PCNTXT) {
                 if (!desc->chip->set_affinity(irq, cpumask)) {
                         cpumask_copy(desc->affinity, cpumask);
-                        irq_set_thread_affinity(desc, cpumask);
+                        irq_set_thread_affinity(desc);
                 }
         }
         else {
@@ -122,7 +130,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 #else
         if (!desc->chip->set_affinity(irq, cpumask)) {
                 cpumask_copy(desc->affinity, cpumask);
-                irq_set_thread_affinity(desc, cpumask);
+                irq_set_thread_affinity(desc);
         }
 #endif
         desc->status |= IRQ_AFFINITY_SET;
@@ -176,7 +184,7 @@ int irq_select_affinity_usr(unsigned int irq)
         spin_lock_irqsave(&desc->lock, flags);
         ret = setup_affinity(irq, desc);
         if (!ret)
-                irq_set_thread_affinity(desc, desc->affinity);
+                irq_set_thread_affinity(desc);
         spin_unlock_irqrestore(&desc->lock, flags);
 
         return ret;
@@ -443,6 +451,39 @@ static int irq_wait_for_interrupt(struct irqaction *action)
         return -1;
 }
 
+#ifdef CONFIG_SMP
+/*
+ * Check whether we need to change the affinity of the interrupt thread.
+ */
+static void
+irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
+{
+        cpumask_var_t mask;
+
+        if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags))
+                return;
+
+        /*
+         * In case we are out of memory we set IRQTF_AFFINITY again and
+         * try again next time
+         */
+        if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
+                set_bit(IRQTF_AFFINITY, &action->thread_flags);
+                return;
+        }
+
+        spin_lock_irq(&desc->lock);
+        cpumask_copy(mask, desc->affinity);
+        spin_unlock_irq(&desc->lock);
+
+        set_cpus_allowed_ptr(current, mask);
+        free_cpumask_var(mask);
+}
+#else
+static inline void
+irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
+#endif
+
 /*
  * Interrupt handler thread
  */
@@ -458,6 +499,8 @@ static int irq_thread(void *data)
 
         while (!irq_wait_for_interrupt(action)) {
 
+                irq_thread_check_affinity(desc, action);
+
                 atomic_inc(&desc->threads_active);
 
                 spin_lock_irq(&desc->lock);
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index cfe767ca1545..fcb6c96f2627 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -45,7 +45,7 @@ void move_masked_irq(int irq)
                    < nr_cpu_ids))
                 if (!desc->chip->set_affinity(irq, desc->pending_mask)) {
                         cpumask_copy(desc->affinity, desc->pending_mask);
-                        irq_set_thread_affinity(desc, desc->pending_mask);
+                        irq_set_thread_affinity(desc);
                 }
 
         cpumask_clear(desc->pending_mask);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index ae1c35201cc8..f336e2107f98 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1228,7 +1228,7 @@ static int __init parse_crashkernel_mem(char 			*cmdline,
         } while (*cur++ == ',');
 
         if (*crash_size > 0) {
-                while (*cur != ' ' && *cur != '@')
+                while (*cur && *cur != ' ' && *cur != '@')
                         cur++;
                 if (*cur == '@') {
                         cur++;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 16b5739c516a..0540948e29ab 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -694,7 +694,7 @@ int __kprobes register_kprobe(struct kprobe *p)
         p->addr = addr;
 
         preempt_disable();
-        if (!__kernel_text_address((unsigned long) p->addr) ||
+        if (!kernel_text_address((unsigned long) p->addr) ||
             in_kprobes_functions((unsigned long) p->addr)) {
                 preempt_enable();
                 return -EINVAL;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 9b1a7de26979..eb8751aa0418 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -180,10 +180,12 @@ EXPORT_SYMBOL(kthread_bind);
  * @k: thread created by kthread_create().
  *
  * Sets kthread_should_stop() for @k to return true, wakes it, and
- * waits for it to exit.  Your threadfn() must not call do_exit()
- * itself if you use this function!  This can also be called after
- * kthread_create() instead of calling wake_up_process(): the thread
- * will exit without calling threadfn().
+ * waits for it to exit. This can also be called after kthread_create()
+ * instead of calling wake_up_process(): the thread will exit without
+ * calling threadfn().
+ *
+ * If threadfn() may call do_exit() itself, the caller must ensure
+ * task_struct can't go away.
  *
  * Returns the result of threadfn(), or %-EINTR if wake_up_process()
  * was never called.
diff --git a/kernel/module.c b/kernel/module.c
index 0a049837008e..fd1411403558 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1068,7 +1068,8 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs,
 {
         const unsigned long *crc;
 
-        if (!find_symbol("module_layout", NULL, &crc, true, false))
+        if (!find_symbol(MODULE_SYMBOL_PREFIX "module_layout", NULL,
+                         &crc, true, false))
                 BUG();
         return check_version(sechdrs, versindex, "module_layout", mod, crc);
 }
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index a641eb753b8c..950931041954 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -146,6 +146,28 @@ static void put_ctx(struct perf_counter_context *ctx)
         }
 }
 
+static void unclone_ctx(struct perf_counter_context *ctx)
+{
+        if (ctx->parent_ctx) {
+                put_ctx(ctx->parent_ctx);
+                ctx->parent_ctx = NULL;
+        }
+}
+
+/*
+ * If we inherit counters we want to return the parent counter id
+ * to userspace.
+ */
+static u64 primary_counter_id(struct perf_counter *counter)
+{
+        u64 id = counter->id;
+
+        if (counter->parent)
+                id = counter->parent->id;
+
+        return id;
+}
+
 /*
  * Get the perf_counter_context for a task and lock it.
  * This has to cope with with the fact that until it is locked,
@@ -1288,7 +1310,6 @@ static void perf_counter_cpu_sched_in(struct perf_cpu_context *cpuctx, int cpu)
 #define MAX_INTERRUPTS (~0ULL)
 
 static void perf_log_throttle(struct perf_counter *counter, int enable);
-static void perf_log_period(struct perf_counter *counter, u64 period);
 
 static void perf_adjust_period(struct perf_counter *counter, u64 events)
 {
@@ -1307,8 +1328,6 @@ static void perf_adjust_period(struct perf_counter *counter, u64 events)
         if (!sample_period)
                 sample_period = 1;
 
-        perf_log_period(counter, sample_period);
-
         hwc->sample_period = sample_period;
 }
 
@@ -1463,10 +1482,8 @@ static void perf_counter_enable_on_exec(struct task_struct *task)
         /*
          * Unclone this context if we enabled any counter.
          */
-        if (enabled && ctx->parent_ctx) {
-                put_ctx(ctx->parent_ctx);
-                ctx->parent_ctx = NULL;
-        }
+        if (enabled)
+                unclone_ctx(ctx);
 
         spin_unlock(&ctx->lock);
 
@@ -1526,7 +1543,6 @@ __perf_counter_init_context(struct perf_counter_context *ctx,
 
 static struct perf_counter_context *find_get_context(pid_t pid, int cpu)
 {
-        struct perf_counter_context *parent_ctx;
         struct perf_counter_context *ctx;
         struct perf_cpu_context *cpuctx;
         struct task_struct *task;
@@ -1586,11 +1602,7 @@ static struct perf_counter_context *find_get_context(pid_t pid, int cpu)
  retry:
         ctx = perf_lock_task_context(task, &flags);
         if (ctx) {
-                parent_ctx = ctx->parent_ctx;
-                if (parent_ctx) {
-                        put_ctx(parent_ctx);
-                        ctx->parent_ctx = NULL;         /* no longer a clone */
-                }
+                unclone_ctx(ctx);
                 spin_unlock_irqrestore(&ctx->lock, flags);
         }
 
@@ -1704,7 +1716,7 @@ perf_read_hw(struct perf_counter *counter, char __user *buf, size_t count)
                 values[n++] = counter->total_time_running +
                         atomic64_read(&counter->child_total_time_running);
         if (counter->attr.read_format & PERF_FORMAT_ID)
-                values[n++] = counter->id;
+                values[n++] = primary_counter_id(counter);
         mutex_unlock(&counter->child_mutex);
 
         if (count < n * sizeof(u64))
@@ -1811,8 +1823,6 @@ static int perf_counter_period(struct perf_counter *counter, u64 __user *arg)
 
                 counter->attr.sample_freq = value;
         } else {
-                perf_log_period(counter, value);
-
                 counter->attr.sample_period = value;
                 counter->hw.sample_period = value;
         }
@@ -2661,10 +2671,14 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
         if (sample_type & PERF_SAMPLE_ID)
                 header.size += sizeof(u64);
 
+        if (sample_type & PERF_SAMPLE_STREAM_ID)
+                header.size += sizeof(u64);
+
         if (sample_type & PERF_SAMPLE_CPU) {
                 header.size += sizeof(cpu_entry);
 
                 cpu_entry.cpu = raw_smp_processor_id();
+                cpu_entry.reserved = 0;
         }
 
         if (sample_type & PERF_SAMPLE_PERIOD)
@@ -2703,7 +2717,13 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
         if (sample_type & PERF_SAMPLE_ADDR)
                 perf_output_put(&handle, data->addr);
 
-        if (sample_type & PERF_SAMPLE_ID)
+        if (sample_type & PERF_SAMPLE_ID) {
+                u64 id = primary_counter_id(counter);
+
+                perf_output_put(&handle, id);
+        }
+
+        if (sample_type & PERF_SAMPLE_STREAM_ID)
                 perf_output_put(&handle, counter->id);
 
         if (sample_type & PERF_SAMPLE_CPU)
@@ -2726,7 +2746,7 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
                         if (sub != counter)
                                 sub->pmu->read(sub);
 
-                        group_entry.id = sub->id;
+                        group_entry.id = primary_counter_id(sub);
                         group_entry.counter = atomic64_read(&sub->count);
 
                         perf_output_put(&handle, group_entry);
@@ -2786,15 +2806,8 @@ perf_counter_read_event(struct perf_counter *counter,
         }
 
         if (counter->attr.read_format & PERF_FORMAT_ID) {
-                u64 id;
-
                 event.header.size += sizeof(u64);
-                if (counter->parent)
-                        id = counter->parent->id;
-                else
-                        id = counter->id;
-
-                event.format[i++] = id;
+                event.format[i++] = primary_counter_id(counter);
         }
 
         ret = perf_output_begin(&handle, counter, event.header.size, 0, 0);
@@ -2895,8 +2908,11 @@ void perf_counter_fork(struct task_struct *task)
                 .event  = {
                         .header = {
                                 .type = PERF_EVENT_FORK,
+                                .misc = 0,
                                 .size = sizeof(fork_event.event),
                         },
+                        /* .pid  */
+                        /* .ppid */
                 },
         };
 
@@ -2968,8 +2984,10 @@ static void perf_counter_comm_event(struct perf_comm_event *comm_event)
         struct perf_cpu_context *cpuctx;
         struct perf_counter_context *ctx;
         unsigned int size;
-        char *comm = comm_event->task->comm;
+        char comm[TASK_COMM_LEN];
 
+        memset(comm, 0, sizeof(comm));
+        strncpy(comm, comm_event->task->comm, sizeof(comm));
         size = ALIGN(strlen(comm)+1, sizeof(u64));
 
         comm_event->comm = comm;
@@ -3004,8 +3022,16 @@ void perf_counter_comm(struct task_struct *task)
 
         comm_event = (struct perf_comm_event){
                 .task   = task,
+                /* .comm      */
+                /* .comm_size */
                 .event  = {
-                        .header = { .type = PERF_EVENT_COMM, },
+                        .header = {
+                                .type = PERF_EVENT_COMM,
+                                .misc = 0,
+                                /* .size */
+                        },
+                        /* .pid */
+                        /* .tid */
                 },
         };
 
@@ -3088,8 +3114,15 @@ static void perf_counter_mmap_event(struct perf_mmap_event *mmap_event)
         char *buf = NULL;
         const char *name;
 
+        memset(tmp, 0, sizeof(tmp));
+
         if (file) {
-                buf = kzalloc(PATH_MAX, GFP_KERNEL);
+                /*
+                 * d_path works from the end of the buffer backwards, so we
+                 * need to add enough zero bytes after the string to handle
+                 * the 64bit alignment we do later.
+                 */
+                buf = kzalloc(PATH_MAX + sizeof(u64), GFP_KERNEL);
                 if (!buf) {
                         name = strncpy(tmp, "//enomem", sizeof(tmp));
                         goto got_name;
@@ -3100,9 +3133,11 @@ static void perf_counter_mmap_event(struct perf_mmap_event *mmap_event)
                         goto got_name;
                 }
         } else {
-                name = arch_vma_name(mmap_event->vma);
-                if (name)
+                if (arch_vma_name(mmap_event->vma)) {
+                        name = strncpy(tmp, arch_vma_name(mmap_event->vma),
+                                       sizeof(tmp));
                         goto got_name;
+                }
 
                 if (!vma->vm_mm) {
                         name = strncpy(tmp, "[vdso]", sizeof(tmp));
@@ -3147,8 +3182,16 @@ void __perf_counter_mmap(struct vm_area_struct *vma)
 
         mmap_event = (struct perf_mmap_event){
                 .vma    = vma,
+                /* .file_name */
+                /* .file_size */
                 .event  = {
-                        .header = { .type = PERF_EVENT_MMAP, },
+                        .header = {
+                                .type = PERF_EVENT_MMAP,
+                                .misc = 0,
+                                /* .size */
+                        },
+                        /* .pid */
+                        /* .tid */
                         .start  = vma->vm_start,
                         .len    = vma->vm_end - vma->vm_start,
                         .pgoff  = vma->vm_pgoff,
@@ -3159,49 +3202,6 @@ void __perf_counter_mmap(struct vm_area_struct *vma)
 }
 
 /*
- * Log sample_period changes so that analyzing tools can re-normalize the
- * event flow.
- */
-
-struct freq_event {
-        struct perf_event_header        header;
-        u64                             time;
-        u64                             id;
-        u64                             period;
-};
-
-static void perf_log_period(struct perf_counter *counter, u64 period)
-{
-        struct perf_output_handle handle;
-        struct freq_event event;
-        int ret;
-
-        if (counter->hw.sample_period == period)
-                return;
-
-        if (counter->attr.sample_type & PERF_SAMPLE_PERIOD)
-                return;
-
-        event = (struct freq_event) {
-                .header = {
-                        .type = PERF_EVENT_PERIOD,
-                        .misc = 0,
-                        .size = sizeof(event),
-                },
-                .time = sched_clock(),
-                .id = counter->id,
-                .period = period,
-        };
-
-        ret = perf_output_begin(&handle, counter, sizeof(event), 1, 0);
-        if (ret)
-                return;
-
-        perf_output_put(&handle, event);
-        perf_output_end(&handle);
-}
-
-/*
  * IRQ throttle logging
  */
 
@@ -3214,16 +3214,21 @@ static void perf_log_throttle(struct perf_counter *counter, int enable)
                 struct perf_event_header        header;
                 u64                             time;
                 u64                             id;
+                u64                             stream_id;
         } throttle_event = {
                 .header = {
-                        .type = PERF_EVENT_THROTTLE + 1,
+                        .type = PERF_EVENT_THROTTLE,
                         .misc = 0,
                         .size = sizeof(throttle_event),
                 },
-                .time   = sched_clock(),
-                .id     = counter->id,
+                .time           = sched_clock(),
+                .id             = primary_counter_id(counter),
+                .stream_id      = counter->id,
         };
 
+        if (enable)
+                throttle_event.header.type = PERF_EVENT_UNTHROTTLE;
+
         ret = perf_output_begin(&handle, counter, sizeof(throttle_event), 1, 0);
         if (ret)
                 return;
@@ -3671,7 +3676,7 @@ static const struct pmu perf_ops_task_clock = {
 void perf_tpcounter_event(int event_id)
 {
         struct perf_sample_data data = {
-                .regs = get_irq_regs();
+                .regs = get_irq_regs(),
                 .addr = 0,
         };
 
@@ -3687,16 +3692,12 @@ extern void ftrace_profile_disable(int);
 
 static void tp_perf_counter_destroy(struct perf_counter *counter)
 {
-        ftrace_profile_disable(perf_event_id(&counter->attr));
+        ftrace_profile_disable(counter->attr.config);
 }
 
 static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
 {
-        int event_id = perf_event_id(&counter->attr);
-        int ret;
-
-        ret = ftrace_profile_enable(event_id);
-        if (ret)
+        if (ftrace_profile_enable(counter->attr.config))
                 return NULL;
 
         counter->destroy = tp_perf_counter_destroy;
@@ -4255,15 +4256,12 @@ void perf_counter_exit_task(struct task_struct *child)
          */
         spin_lock(&child_ctx->lock);
         child->perf_counter_ctxp = NULL;
-        if (child_ctx->parent_ctx) {
-                /*
-                 * This context is a clone; unclone it so it can't get
-                 * swapped to another process while we're removing all
-                 * the counters from it.
-                 */
-                put_ctx(child_ctx->parent_ctx);
-                child_ctx->parent_ctx = NULL;
-        }
+        /*
+         * If this context is a clone; unclone it so it can't get
+         * swapped to another process while we're removing all
+         * the counters from it.
+         */
+        unclone_ctx(child_ctx);
         spin_unlock(&child_ctx->lock);
         local_irq_restore(flags);
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 98972d366fdc..1b59e265273b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -7289,6 +7289,7 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
 static void calc_global_load_remove(struct rq *rq)
 {
         atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
+        rq->calc_load_active = 0;
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
@@ -7515,6 +7516,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
                 task_rq_unlock(rq, &flags);
                 get_task_struct(p);
                 cpu_rq(cpu)->migration_thread = p;
+                rq->calc_load_update = calc_load_update;
                 break;
 
         case CPU_ONLINE:
@@ -7525,8 +7527,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
                 /* Update our root-domain */
                 rq = cpu_rq(cpu);
                 spin_lock_irqsave(&rq->lock, flags);
-                rq->calc_load_update = calc_load_update;
-                rq->calc_load_active = 0;
                 if (rq->rd) {
                         BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 7c248dc30f41..9ffb2b2ceba4 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -266,6 +266,12 @@ static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
         return min_vruntime;
 }
 
+static inline int entity_before(struct sched_entity *a,
+                                struct sched_entity *b)
+{
+        return (s64)(a->vruntime - b->vruntime) < 0;
+}
+
 static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
         return se->vruntime - cfs_rq->min_vruntime;
@@ -1017,7 +1023,7 @@ static void yield_task_fair(struct rq *rq)
         /*
          * Already in the rightmost position?
          */
-        if (unlikely(!rightmost || rightmost->vruntime < se->vruntime))
+        if (unlikely(!rightmost || entity_before(rightmost, se)))
                 return;
 
         /*
@@ -1713,7 +1719,7 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
 
         /* 'curr' will be NULL if the child belongs to a different group */
         if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) &&
-                        curr && curr->vruntime < se->vruntime) {
+                        curr && entity_before(curr, se)) {
                 /*
                  * Upon rescheduling, sched_class::put_prev_task() will place
                  * 'current' within the tree based on its new key value.
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 3a94905fa5d2..eb5e131a0485 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -345,7 +345,9 @@ void open_softirq(int nr, void (*action)(struct softirq_action *))
         softirq_vec[nr].action = action;
 }
 
-/* Tasklets */
+/*
+ * Tasklets
+ */
 struct tasklet_head
 {
         struct tasklet_struct *head;
@@ -493,6 +495,66 @@ void tasklet_kill(struct tasklet_struct *t)
 
 EXPORT_SYMBOL(tasklet_kill);
 
+/*
+ * tasklet_hrtimer
+ */
+
+/*
+ * The trampoline is called when the hrtimer expires. If this is
+ * called from the hrtimer interrupt then we schedule the tasklet as
+ * the timer callback function expects to run in softirq context. If
+ * it's called in softirq context anyway (i.e. high resolution timers
+ * disabled) then the hrtimer callback is called right away.
+ */
+static enum hrtimer_restart __hrtimer_tasklet_trampoline(struct hrtimer *timer)
+{
+        struct tasklet_hrtimer *ttimer =
+                container_of(timer, struct tasklet_hrtimer, timer);
+
+        if (hrtimer_is_hres_active(timer)) {
+                tasklet_hi_schedule(&ttimer->tasklet);
+                return HRTIMER_NORESTART;
+        }
+        return ttimer->function(timer);
+}
+
+/*
+ * Helper function which calls the hrtimer callback from
+ * tasklet/softirq context
+ */
+static void __tasklet_hrtimer_trampoline(unsigned long data)
+{
+        struct tasklet_hrtimer *ttimer = (void *)data;
+        enum hrtimer_restart restart;
+
+        restart = ttimer->function(&ttimer->timer);
+        if (restart != HRTIMER_NORESTART)
+                hrtimer_restart(&ttimer->timer);
+}
+
+/**
+ * tasklet_hrtimer_init - Init a tasklet/hrtimer combo for softirq callbacks
+ * @ttimer:      tasklet_hrtimer which is initialized
+ * @function:    hrtimer callback funtion which gets called from softirq context
+ * @which_clock: clock id (CLOCK_MONOTONIC/CLOCK_REALTIME)
+ * @mode:        hrtimer mode (HRTIMER_MODE_ABS/HRTIMER_MODE_REL)
+ */
+void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
+                          enum hrtimer_restart (*function)(struct hrtimer *),
+                          clockid_t which_clock, enum hrtimer_mode mode)
+{
+        hrtimer_init(&ttimer->timer, which_clock, mode);
+        ttimer->timer.function = __hrtimer_tasklet_trampoline;
+        tasklet_init(&ttimer->tasklet, __tasklet_hrtimer_trampoline,
+                     (unsigned long)ttimer);
+        ttimer->function = function;
+}
+EXPORT_SYMBOL_GPL(tasklet_hrtimer_init);
+
+/*
+ * Remote softirq bits
+ */
+
 DEFINE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
 EXPORT_PER_CPU_SYMBOL(softirq_work_list);
 
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 592bf584d1d2..7466cb811251 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -513,7 +513,7 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev,
          * Check to make sure we don't switch to a non-highres capable
          * clocksource if the tick code is in oneshot mode (highres or nohz)
          */
-        if (tick_oneshot_mode_active() &&
+        if (tick_oneshot_mode_active() && ovr &&
             !(ovr->flags & CLOCK_SOURCE_VALID_FOR_HRES)) {
                 printk(KERN_WARNING "%s clocksource is not HRT compatible. "
                         "Cannot switch while in HRT/NOHZ mode\n", ovr->name);
diff --git a/kernel/timer.c b/kernel/timer.c
index 0b36b9e5cc8b..a7f07d5a6241 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -714,7 +714,7 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
          * networking code - if the timer is re-modified
          * to be the same thing then just return:
          */
-        if (timer->expires == expires && timer_pending(timer))
+        if (timer_pending(timer) && timer->expires == expires)
                 return 1;
 
         return __mod_timer(timer, expires, false, TIMER_NOT_PINNED);