7 files changed, 50 insertions, 91 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 5cf366965d0c..66a416b42c18 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1460,9 +1460,9 @@ static int cgroup_get_rootdir(struct super_block *sb)
         return 0;
 }
 
-static int cgroup_get_sb(struct file_system_type *fs_type,
+static struct dentry *cgroup_mount(struct file_system_type *fs_type,
                          int flags, const char *unused_dev_name,
-                         void *data, struct vfsmount *mnt)
+                         void *data)
 {
         struct cgroup_sb_opts opts;
         struct cgroupfs_root *root;
@@ -1596,10 +1596,9 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
                 drop_parsed_module_refcounts(opts.subsys_bits);
         }
 
-        simple_set_mnt(mnt, sb);
         kfree(opts.release_agent);
         kfree(opts.name);
-        return 0;
+        return dget(sb->s_root);
 
  drop_new_super:
         deactivate_locked_super(sb);
@@ -1608,7 +1607,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
  out_err:
         kfree(opts.release_agent);
         kfree(opts.name);
-        return ret;
+        return ERR_PTR(ret);
 }
 
 static void cgroup_kill_sb(struct super_block *sb) {
@@ -1658,7 +1657,7 @@ static void cgroup_kill_sb(struct super_block *sb) {
 
 static struct file_system_type cgroup_fs_type = {
         .name = "cgroup",
-        .get_sb = cgroup_get_sb,
+        .mount = cgroup_mount,
         .kill_sb = cgroup_kill_sb,
 };
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 51b143e2a07a..4349935c2ad8 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -231,18 +231,17 @@ static DEFINE_SPINLOCK(cpuset_buffer_lock);
  * users. If someone tries to mount the "cpuset" filesystem, we
  * silently switch it to mount "cgroup" instead
  */
-static int cpuset_get_sb(struct file_system_type *fs_type,
-                         int flags, const char *unused_dev_name,
-                         void *data, struct vfsmount *mnt)
+static struct dentry *cpuset_mount(struct file_system_type *fs_type,
+                         int flags, const char *unused_dev_name, void *data)
 {
         struct file_system_type *cgroup_fs = get_fs_type("cgroup");
-        int ret = -ENODEV;
+        struct dentry *ret = ERR_PTR(-ENODEV);
         if (cgroup_fs) {
                 char mountopts[] =
                         "cpuset,noprefix,"
                         "release_agent=/sbin/cpuset_release_agent";
-                ret = cgroup_fs->get_sb(cgroup_fs, flags,
-                                           unused_dev_name, mountopts, mnt);
+                ret = cgroup_fs->mount(cgroup_fs, flags,
+                                           unused_dev_name, mountopts);
                 put_filesystem(cgroup_fs);
         }
         return ret;
@@ -250,7 +249,7 @@ static int cpuset_get_sb(struct file_system_type *fs_type,
 
 static struct file_system_type cpuset_fs_type = {
         .name = "cpuset",
-        .get_sb = cpuset_get_sb,
+        .mount = cpuset_mount,
 };
 
 /*
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index fec596da9bd0..cefd4a11f6d9 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -209,18 +209,6 @@ int __weak kgdb_skipexception(int exception, struct pt_regs *regs)
         return 0;
 }
 
-/**
- *      kgdb_disable_hw_debug - Disable hardware debugging while we in kgdb.
- *      @regs: Current &struct pt_regs.
- *
- *      This function will be called if the particular architecture must
- *      disable hardware debugging while it is processing gdb packets or
- *      handling exception.
- */
-void __weak kgdb_disable_hw_debug(struct pt_regs *regs)
-{
-}
-
 /*
  * Some architectures need cache flushes when we set/clear a
  * breakpoint:
@@ -484,7 +472,9 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
                 atomic_inc(&masters_in_kgdb);
         else
                 atomic_inc(&slaves_in_kgdb);
-        kgdb_disable_hw_debug(ks->linux_regs);
+
+        if (arch_kgdb_ops.disable_hw_break)
+                arch_kgdb_ops.disable_hw_break(regs);
 
 acquirelock:
         /*
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index d7bda21a106b..37755d621924 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1127,7 +1127,7 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
                 /* special case below */
         } else {
                 kdb_printf("\nEntering kdb (current=0x%p, pid %d) ",
-                           kdb_current, kdb_current->pid);
+                           kdb_current, kdb_current ? kdb_current->pid : 0);
 #if defined(CONFIG_SMP)
                 kdb_printf("on processor %d ", raw_smp_processor_id());
 #endif
@@ -2603,20 +2603,17 @@ static int kdb_summary(int argc, const char **argv)
  */
 static int kdb_per_cpu(int argc, const char **argv)
 {
-        char buf[256], fmtstr[64];
-        kdb_symtab_t symtab;
-        cpumask_t suppress = CPU_MASK_NONE;
-        int cpu, diag;
-        unsigned long addr, val, bytesperword = 0, whichcpu = ~0UL;
+        char fmtstr[64];
+        int cpu, diag, nextarg = 1;
+        unsigned long addr, symaddr, val, bytesperword = 0, whichcpu = ~0UL;
 
         if (argc < 1 || argc > 3)
                 return KDB_ARGCOUNT;
 
-        snprintf(buf, sizeof(buf), "per_cpu__%s", argv[1]);
-        if (!kdbgetsymval(buf, &symtab)) {
-                kdb_printf("%s is not a per_cpu variable\n", argv[1]);
-                return KDB_BADADDR;
-        }
+        diag = kdbgetaddrarg(argc, argv, &nextarg, &symaddr, NULL, NULL);
+        if (diag)
+                return diag;
+
         if (argc >= 2) {
                 diag = kdbgetularg(argv[2], &bytesperword);
                 if (diag)
@@ -2649,46 +2646,25 @@ static int kdb_per_cpu(int argc, const char **argv)
 #define KDB_PCU(cpu) 0
 #endif
 #endif
-
         for_each_online_cpu(cpu) {
+                if (KDB_FLAG(CMD_INTERRUPT))
+                        return 0;
+
                 if (whichcpu != ~0UL && whichcpu != cpu)
                         continue;
-                addr = symtab.sym_start + KDB_PCU(cpu);
+                addr = symaddr + KDB_PCU(cpu);
                 diag = kdb_getword(&val, addr, bytesperword);
                 if (diag) {
                         kdb_printf("%5d " kdb_bfd_vma_fmt0 " - unable to "
                                    "read, diag=%d\n", cpu, addr, diag);
                         continue;
                 }
-#ifdef  CONFIG_SMP
-                if (!val) {
-                        cpu_set(cpu, suppress);
-                        continue;
-                }
-#endif  /* CONFIG_SMP */
                 kdb_printf("%5d ", cpu);
                 kdb_md_line(fmtstr, addr,
                         bytesperword == KDB_WORD_SIZE,
                         1, bytesperword, 1, 1, 0);
         }
-        if (cpus_weight(suppress) == 0)
-                return 0;
-        kdb_printf("Zero suppressed cpu(s):");
-        for (cpu = first_cpu(suppress); cpu < num_possible_cpus();
-             cpu = next_cpu(cpu, suppress)) {
-                kdb_printf(" %d", cpu);
-                if (cpu == num_possible_cpus() - 1 ||
-                    next_cpu(cpu, suppress) != cpu + 1)
-                        continue;
-                while (cpu < num_possible_cpus() &&
-                       next_cpu(cpu, suppress) == cpu + 1)
-                        ++cpu;
-                kdb_printf("-%d", cpu);
-        }
-        kdb_printf("\n");
-
 #undef KDB_PCU
-
         return 0;
 }
 
diff --git a/kernel/sched.c b/kernel/sched.c
index d42992bccdfa..aa14a56f9d03 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -8510,12 +8510,12 @@ void sched_move_task(struct task_struct *tsk)
         if (unlikely(running))
                 tsk->sched_class->put_prev_task(rq, tsk);
 
-        set_task_rq(tsk, task_cpu(tsk));
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
-        if (tsk->sched_class->moved_group)
-                tsk->sched_class->moved_group(tsk, on_rq);
+        if (tsk->sched_class->task_move_group)
+                tsk->sched_class->task_move_group(tsk, on_rq);
+        else
 #endif
+                set_task_rq(tsk, task_cpu(tsk));
 
         if (unlikely(running))
                 tsk->sched_class->set_curr_task(rq);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 933f3d1b62ea..f4f6a8326dd0 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -3869,13 +3869,26 @@ static void set_curr_task_fair(struct rq *rq)
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-static void moved_group_fair(struct task_struct *p, int on_rq)
+static void task_move_group_fair(struct task_struct *p, int on_rq)
 {
-        struct cfs_rq *cfs_rq = task_cfs_rq(p);
-
-        update_curr(cfs_rq);
+        /*
+         * If the task was not on the rq at the time of this cgroup movement
+         * it must have been asleep, sleeping tasks keep their ->vruntime
+         * absolute on their old rq until wakeup (needed for the fair sleeper
+         * bonus in place_entity()).
+         *
+         * If it was on the rq, we've just 'preempted' it, which does convert
+         * ->vruntime to a relative base.
+         *
+         * Make sure both cases convert their relative position when migrating
+         * to another cgroup's rq. This does somewhat interfere with the
+         * fair sleeper stuff for the first placement, but who cares.
+         */
+        if (!on_rq)
+                p->se.vruntime -= cfs_rq_of(&p->se)->min_vruntime;
+        set_task_rq(p, task_cpu(p));
         if (!on_rq)
-                place_entity(cfs_rq, &p->se, 1);
+                p->se.vruntime += cfs_rq_of(&p->se)->min_vruntime;
 }
 #endif
 
@@ -3927,7 +3940,7 @@ static const struct sched_class fair_sched_class = {
         .get_rr_interval        = get_rr_interval_fair,
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-        .moved_group            = moved_group_fair,
+        .task_move_group        = task_move_group_fair,
 #endif
 };
 
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index 25c2f962f6fc..48ddf431db0e 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -157,15 +157,7 @@ static inline void sched_info_reset_dequeued(struct task_struct *t)
 }
 
 /*
- * Called when a process is dequeued from the active array and given
- * the cpu.  We should note that with the exception of interactive
- * tasks, the expired queue will become the active queue after the active
- * queue is empty, without explicitly dequeuing and requeuing tasks in the
- * expired queue.  (Interactive tasks may be requeued directly to the
- * active queue, thus delaying tasks in the expired queue from running;
- * see scheduler_tick()).
- *
- * Though we are interested in knowing how long it was from the *first* time a
+ * We are interested in knowing how long it was from the *first* time a
  * task was queued to the time that it finally hit a cpu, we call this routine
  * from dequeue_task() to account for possible rq->clock skew across cpus. The
  * delta taken on each cpu would annul the skew.
@@ -203,16 +195,6 @@ static void sched_info_arrive(struct task_struct *t)
 }
 
 /*
- * Called when a process is queued into either the active or expired
- * array.  The time is noted and later used to determine how long we
- * had to wait for us to reach the cpu.  Since the expired queue will
- * become the active queue after active queue is empty, without dequeuing
- * and requeuing any tasks, we are interested in queuing to either. It
- * is unusual but not impossible for tasks to be dequeued and immediately
- * requeued in the same or another array: this can happen in sched_yield(),
- * set_user_nice(), and even load_balance() as it moves tasks from runqueue
- * to runqueue.
- *
  * This function is only called from enqueue_task(), but also only updates
  * the timestamp if it is already not set.  It's assumed that
  * sched_info_dequeued() will clear that stamp when appropriate.