Merge branch 'sched/core' into cpus4096

Conflicts:
	include/linux/ftrace.h
	kernel/sched.c

13 files changed, 149 insertions, 71 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index 4414e93d8750..ce6d8ea3131e 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -61,8 +61,11 @@
 
 #include "audit.h"
 
-/* No auditing will take place until audit_initialized != 0.
+/* No auditing will take place until audit_initialized == AUDIT_INITIALIZED.
  * (Initialization happens after skb_init is called.) */
+#define AUDIT_DISABLED          -1
+#define AUDIT_UNINITIALIZED     0
+#define AUDIT_INITIALIZED       1
 static int      audit_initialized;
 
 #define AUDIT_OFF       0
@@ -965,6 +968,9 @@ static int __init audit_init(void)
 {
         int i;
 
+        if (audit_initialized == AUDIT_DISABLED)
+                return 0;
+
         printk(KERN_INFO "audit: initializing netlink socket (%s)\n",
                audit_default ? "enabled" : "disabled");
         audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT, 0,
@@ -976,7 +982,7 @@ static int __init audit_init(void)
 
         skb_queue_head_init(&audit_skb_queue);
         skb_queue_head_init(&audit_skb_hold_queue);
-        audit_initialized = 1;
+        audit_initialized = AUDIT_INITIALIZED;
         audit_enabled = audit_default;
         audit_ever_enabled |= !!audit_default;
 
@@ -999,13 +1005,21 @@ __initcall(audit_init);
 static int __init audit_enable(char *str)
 {
         audit_default = !!simple_strtol(str, NULL, 0);
-        printk(KERN_INFO "audit: %s%s\n",
-               audit_default ? "enabled" : "disabled",
-               audit_initialized ? "" : " (after initialization)");
-        if (audit_initialized) {
+        if (!audit_default)
+                audit_initialized = AUDIT_DISABLED;
+
+        printk(KERN_INFO "audit: %s", audit_default ? "enabled" : "disabled");
+
+        if (audit_initialized == AUDIT_INITIALIZED) {
                 audit_enabled = audit_default;
                 audit_ever_enabled |= !!audit_default;
+        } else if (audit_initialized == AUDIT_UNINITIALIZED) {
+                printk(" (after initialization)");
+        } else {
+                printk(" (until reboot)");
         }
+        printk("\n");
+
         return 1;
 }
 
@@ -1107,9 +1121,7 @@ unsigned int audit_serial(void)
 static inline void audit_get_stamp(struct audit_context *ctx,
                                    struct timespec *t, unsigned int *serial)
 {
-        if (ctx)
-                auditsc_get_stamp(ctx, t, serial);
-        else {
+        if (!ctx || !auditsc_get_stamp(ctx, t, serial)) {
                 *t = CURRENT_TIME;
                 *serial = audit_serial();
         }
@@ -1146,7 +1158,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
         int reserve;
         unsigned long timeout_start = jiffies;
 
-        if (!audit_initialized)
+        if (audit_initialized != AUDIT_INITIALIZED)
                 return NULL;
 
         if (unlikely(audit_filter_type(type)))
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index cf5bc2f5f9c3..2a3f0afc4d2a 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1459,7 +1459,6 @@ void audit_free(struct task_struct *tsk)
 
 /**
  * audit_syscall_entry - fill in an audit record at syscall entry
- * @tsk: task being audited
  * @arch: architecture type
  * @major: major syscall type (function)
  * @a1: additional syscall register 1
@@ -1548,9 +1547,25 @@ void audit_syscall_entry(int arch, int major,
         context->ppid       = 0;
 }
 
+void audit_finish_fork(struct task_struct *child)
+{
+        struct audit_context *ctx = current->audit_context;
+        struct audit_context *p = child->audit_context;
+        if (!p || !ctx || !ctx->auditable)
+                return;
+        p->arch = ctx->arch;
+        p->major = ctx->major;
+        memcpy(p->argv, ctx->argv, sizeof(ctx->argv));
+        p->ctime = ctx->ctime;
+        p->dummy = ctx->dummy;
+        p->auditable = ctx->auditable;
+        p->in_syscall = ctx->in_syscall;
+        p->filterkey = kstrdup(ctx->filterkey, GFP_KERNEL);
+        p->ppid = current->pid;
+}
+
 /**
  * audit_syscall_exit - deallocate audit context after a system call
- * @tsk: task being audited
  * @valid: success/failure flag
  * @return_code: syscall return value
  *
@@ -1942,15 +1957,18 @@ EXPORT_SYMBOL_GPL(__audit_inode_child);
  *
  * Also sets the context as auditable.
  */
-void auditsc_get_stamp(struct audit_context *ctx,
+int auditsc_get_stamp(struct audit_context *ctx,
                        struct timespec *t, unsigned int *serial)
 {
+        if (!ctx->in_syscall)
+                return 0;
         if (!ctx->serial)
                 ctx->serial = audit_serial();
         t->tv_sec  = ctx->ctime.tv_sec;
         t->tv_nsec = ctx->ctime.tv_nsec;
         *serial    = ctx->serial;
         ctx->auditable = 1;
+        return 1;
 }
 
 /* global counter which is incremented every time something logs in */
diff --git a/kernel/fork.c b/kernel/fork.c
index 7407ab319875..7b93da72d4a2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -319,17 +319,20 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
                 file = tmp->vm_file;
                 if (file) {
                         struct inode *inode = file->f_path.dentry->d_inode;
+                        struct address_space *mapping = file->f_mapping;
+
                         get_file(file);
                         if (tmp->vm_flags & VM_DENYWRITE)
                                 atomic_dec(&inode->i_writecount);
-
-                        /* insert tmp into the share list, just after mpnt */
-                        spin_lock(&file->f_mapping->i_mmap_lock);
+                        spin_lock(&mapping->i_mmap_lock);
+                        if (tmp->vm_flags & VM_SHARED)
+                                mapping->i_mmap_writable++;
                         tmp->vm_truncate_count = mpnt->vm_truncate_count;
-                        flush_dcache_mmap_lock(file->f_mapping);
+                        flush_dcache_mmap_lock(mapping);
+                        /* insert tmp into the share list, just after mpnt */
                         vma_prio_tree_add(tmp, mpnt);
-                        flush_dcache_mmap_unlock(file->f_mapping);
-                        spin_unlock(&file->f_mapping->i_mmap_lock);
+                        flush_dcache_mmap_unlock(mapping);
+                        spin_unlock(&mapping->i_mmap_lock);
                 }
 
                 /*
@@ -1406,6 +1409,7 @@ long do_fork(unsigned long clone_flags,
                         init_completion(&vfork);
                 }
 
+                audit_finish_fork(p);
                 tracehook_report_clone(trace, regs, clone_flags, nr, p);
 
                 /*
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index 5e7b45c56923..449db466bdbc 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -191,7 +191,7 @@ static int lstats_show(struct seq_file *m, void *v)
                                 latency_record[i].time,
                                 latency_record[i].max);
                         for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
-                                char sym[KSYM_NAME_LEN];
+                                char sym[KSYM_SYMBOL_LEN];
                                 char *c;
                                 if (!latency_record[i].backtrace[q])
                                         break;
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 3f4377e0aa04..157de3a47832 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -311,7 +311,7 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
         struct task_cputime cputime;
 
         thread_group_cputime(p, &cputime);
-        switch (which_clock) {
+        switch (CPUCLOCK_WHICH(which_clock)) {
         default:
                 return -EINVAL;
         case CPUCLOCK_PROF:
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index b7713b53d07a..6da14358537c 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -633,7 +633,7 @@ void swsusp_close(fmode_t mode)
                 return;
         }
 
-        blkdev_put(resume_bdev, mode); /* move up */
+        blkdev_put(resume_bdev, mode);
 }
 
 static int swsusp_header_init(void)
diff --git a/kernel/relay.c b/kernel/relay.c
index 32b0befdcb6a..09ac2008f77b 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1317,12 +1317,9 @@ static ssize_t relay_file_splice_read(struct file *in,
                 if (ret < 0)
                         break;
                 else if (!ret) {
-                        if (spliced)
-                                break;
-                        if (flags & SPLICE_F_NONBLOCK) {
+                        if (flags & SPLICE_F_NONBLOCK)
                                 ret = -EAGAIN;
-                                break;
-                        }
+                        break;
                 }
 
                 *ppos += ret;
diff --git a/kernel/sched.c b/kernel/sched.c
index 4ed9f588faa6..e00c92d22655 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -267,6 +267,10 @@ struct task_group {
         struct cgroup_subsys_state css;
 #endif
 
+#ifdef CONFIG_USER_SCHED
+        uid_t uid;
+#endif
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
         /* schedulable entities of this group on each cpu */
         struct sched_entity **se;
@@ -292,6 +296,12 @@ struct task_group {
 
 #ifdef CONFIG_USER_SCHED
 
+/* Helper function to pass uid information to create_sched_user() */
+void set_tg_uid(struct user_struct *user)
+{
+        user->tg->uid = user->uid;
+}
+
 /*
  * Root task group.
  *      Every UID task group (including init_task_group aka UID-0) will
@@ -1587,6 +1597,39 @@ static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd)
 
 #endif
 
+/*
+ * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ */
+static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+        __releases(this_rq->lock)
+        __acquires(busiest->lock)
+        __acquires(this_rq->lock)
+{
+        int ret = 0;
+
+        if (unlikely(!irqs_disabled())) {
+                /* printk() doesn't work good under rq->lock */
+                spin_unlock(&this_rq->lock);
+                BUG_ON(1);
+        }
+        if (unlikely(!spin_trylock(&busiest->lock))) {
+                if (busiest < this_rq) {
+                        spin_unlock(&this_rq->lock);
+                        spin_lock(&busiest->lock);
+                        spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
+                        ret = 1;
+                } else
+                        spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
+        }
+        return ret;
+}
+
+static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
+        __releases(busiest->lock)
+{
+        spin_unlock(&busiest->lock);
+        lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
+}
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -2784,40 +2827,6 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 }
 
 /*
- * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
- */
-static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
-        __releases(this_rq->lock)
-        __acquires(busiest->lock)
-        __acquires(this_rq->lock)
-{
-        int ret = 0;
-
-        if (unlikely(!irqs_disabled())) {
-                /* printk() doesn't work good under rq->lock */
-                spin_unlock(&this_rq->lock);
-                BUG_ON(1);
-        }
-        if (unlikely(!spin_trylock(&busiest->lock))) {
-                if (busiest < this_rq) {
-                        spin_unlock(&this_rq->lock);
-                        spin_lock(&busiest->lock);
-                        spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
-                        ret = 1;
-                } else
-                        spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
-        }
-        return ret;
-}
-
-static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
-        __releases(busiest->lock)
-{
-        spin_unlock(&busiest->lock);
-        lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
-}
-
-/*
  * If dest_cpu is allowed for this process, migrate the task to it.
  * This is accomplished by forcing the cpu_allowed mask to only
  * allow dest_cpu, which will force the cpu onto dest_cpu. Then
@@ -3676,7 +3685,7 @@ out_balanced:
 static void idle_balance(int this_cpu, struct rq *this_rq)
 {
         struct sched_domain *sd;
-        int pulled_task = -1;
+        int pulled_task = 0;
         unsigned long next_balance = jiffies + HZ;
         cpumask_var_t tmpmask;
 
@@ -6577,7 +6586,9 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
                         req = list_entry(rq->migration_queue.next,
                                          struct migration_req, list);
                         list_del_init(&req->list);
+                        spin_unlock_irq(&rq->lock);
                         complete(&req->done);
+                        spin_lock_irq(&rq->lock);
                 }
                 spin_unlock_irq(&rq->lock);
                 break;
@@ -6781,6 +6792,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
                                 SD_BALANCE_EXEC |
                                 SD_SHARE_CPUPOWER |
                                 SD_SHARE_PKG_RESOURCES);
+                if (nr_node_ids == 1)
+                        pflags &= ~SD_SERIALIZE;
         }
         if (~cflags & pflags)
                 return 0;
@@ -7716,8 +7729,14 @@ static struct sched_domain_attr *dattr_cur;
  */
 static cpumask_var_t fallback_doms;
 
-void __attribute__((weak)) arch_update_cpu_topology(void)
+/*
+ * arch_update_cpu_topology lets virtualized architectures update the
+ * cpu core maps. It is supposed to return 1 if the topology changed
+ * or 0 if it stayed the same.
+ */
+int __attribute__((weak)) arch_update_cpu_topology(void)
 {
+        return 0;
 }
 
 /*
@@ -7811,17 +7830,21 @@ void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
                              struct sched_domain_attr *dattr_new)
 {
         int i, j, n;
+        int new_topology;
 
         mutex_lock(&sched_domains_mutex);
 
         /* always unregister in case we don't destroy any domains */
         unregister_sched_domain_sysctl();
 
+        /* Let architecture update cpu core mappings. */
+        new_topology = arch_update_cpu_topology();
+
         n = doms_new ? ndoms_new : 0;
 
         /* Destroy deleted domains */
         for (i = 0; i < ndoms_cur; i++) {
-                for (j = 0; j < n; j++) {
+                for (j = 0; j < n && !new_topology; j++) {
                         if (cpumask_equal(&doms_cur[i], &doms_new[j])
                             && dattrs_equal(dattr_cur, i, dattr_new, j))
                                 goto match1;
@@ -7841,7 +7864,7 @@ match1:
 
         /* Build new domains */
         for (i = 0; i < ndoms_new; i++) {
-                for (j = 0; j < ndoms_cur; j++) {
+                for (j = 0; j < ndoms_cur && !new_topology; j++) {
                         if (cpumask_equal(&doms_new[i], &doms_cur[j])
                             && dattrs_equal(dattr_new, i, dattr_cur, j))
                                 goto match2;
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index baf2f17af462..4293cfa9681d 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -160,10 +160,14 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
         cgroup_path(tg->css.cgroup, path, sizeof(path));
 
         SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path);
+#elif defined(CONFIG_USER_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
+        {
+                uid_t uid = cfs_rq->tg->uid;
+                SEQ_printf(m, "\ncfs_rq[%d] for UID: %u\n", cpu, uid);
+        }
 #else
         SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
 #endif
-
         SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "exec_clock",
                         SPLIT_NS(cfs_rq->exec_clock));
 
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 94aab72f6a02..1bbd99014011 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -914,10 +914,6 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 /* Only try algorithms three times */
 #define RT_MAX_TRIES 3
 
-static int double_lock_balance(struct rq *this_rq, struct rq *busiest);
-static inline void double_unlock_balance(struct rq *this_rq,
-                                                struct rq *busiest);
-
 static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep);
 
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 884e6cd2769c..1ab790c67b17 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -188,7 +188,7 @@ static void check_hung_task(struct task_struct *t, unsigned long now)
         if ((long)(now - t->last_switch_timestamp) <
                                         sysctl_hung_task_timeout_secs)
                 return;
-        if (sysctl_hung_task_warnings < 0)
+        if (!sysctl_hung_task_warnings)
                 return;
         sysctl_hung_task_warnings--;
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index e7acfb482a68..fa05e88aa76f 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -518,6 +518,28 @@ void update_wall_time(void)
         /* correct the clock when NTP error is too big */
         clocksource_adjust(offset);
 
+        /*
+         * Since in the loop above, we accumulate any amount of time
+         * in xtime_nsec over a second into xtime.tv_sec, its possible for
+         * xtime_nsec to be fairly small after the loop. Further, if we're
+         * slightly speeding the clocksource up in clocksource_adjust(),
+         * its possible the required corrective factor to xtime_nsec could
+         * cause it to underflow.
+         *
+         * Now, we cannot simply roll the accumulated second back, since
+         * the NTP subsystem has been notified via second_overflow. So
+         * instead we push xtime_nsec forward by the amount we underflowed,
+         * and add that amount into the error.
+         *
+         * We'll correct this error next time through this function, when
+         * xtime_nsec is not as small.
+         */
+        if (unlikely((s64)clock->xtime_nsec < 0)) {
+                s64 neg = -(s64)clock->xtime_nsec;
+                clock->xtime_nsec = 0;
+                clock->error += neg << (NTP_SCALE_SHIFT - clock->shift);
+        }
+
         /* store full nanoseconds into xtime after rounding it up and
          * add the remainder to the error difference.
          */
diff --git a/kernel/user.c b/kernel/user.c
index 39d6159fae43..cec2224bc9f5 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -101,6 +101,8 @@ static int sched_create_user(struct user_struct *up)
         if (IS_ERR(up->tg))
                 rc = -ENOMEM;
 
+        set_tg_uid(up);
+
         return rc;
 }