Merge branch 'linus' into core/rcu

kernel/audit.c

@@ -572,16 +572,17 @@ void audit_send_reply(int pid, int seq, int type, int done, int multi,
 
 	skb = audit_make_reply(pid, seq, type, done, multi, payload, size);
 	if (!skb)
-		return;
+		goto out;
 
 	reply->pid = pid;
 	reply->skb = skb;
 
 	tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply");
-	if (IS_ERR(tsk)) {
-		kfree(reply);
-		kfree_skb(skb);
-	}
+	if (!IS_ERR(tsk))
+		return;
+	kfree_skb(skb);
+out:
+	kfree(reply);
 }
 
 /*

kernel/audit_tree.c

@@ -172,10 +172,9 @@ static void insert_hash(struct audit_chunk *chunk)
 struct audit_chunk *audit_tree_lookup(const struct inode *inode)
 {
 	struct list_head *list = chunk_hash(inode);
-	struct list_head *pos;
+	struct audit_chunk *p;
 
-	list_for_each_rcu(pos, list) {
-		struct audit_chunk *p = container_of(pos, struct audit_chunk, hash);
+	list_for_each_entry_rcu(p, list, hash) {
 		if (p->watch.inode == inode) {
 			get_inotify_watch(&p->watch);
 			return p;

kernel/capability.c

@@ -52,6 +52,69 @@ static void warn_legacy_capability_use(void)
 	}
 }
 
+/*
+ * Version 2 capabilities worked fine, but the linux/capability.h file
+ * that accompanied their introduction encouraged their use without
+ * the necessary user-space source code changes. As such, we have
+ * created a version 3 with equivalent functionality to version 2, but
+ * with a header change to protect legacy source code from using
+ * version 2 when it wanted to use version 1. If your system has code
+ * that trips the following warning, it is using version 2 specific
+ * capabilities and may be doing so insecurely.
+ *
+ * The remedy is to either upgrade your version of libcap (to 2.10+,
+ * if the application is linked against it), or recompile your
+ * application with modern kernel headers and this warning will go
+ * away.
+ */
+
+static void warn_deprecated_v2(void)
+{
+	static int warned;
+
+	if (!warned) {
+		char name[sizeof(current->comm)];
+
+		printk(KERN_INFO "warning: `%s' uses deprecated v2"
+		       " capabilities in a way that may be insecure.\n",
+		       get_task_comm(name, current));
+		warned = 1;
+	}
+}
+
+/*
+ * Version check. Return the number of u32s in each capability flag
+ * array, or a negative value on error.
+ */
+static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy)
+{
+	__u32 version;
+
+	if (get_user(version, &header->version))
+		return -EFAULT;
+
+	switch (version) {
+	case _LINUX_CAPABILITY_VERSION_1:
+		warn_legacy_capability_use();
+		*tocopy = _LINUX_CAPABILITY_U32S_1;
+		break;
+	case _LINUX_CAPABILITY_VERSION_2:
+		warn_deprecated_v2();
+		/*
+		 * fall through - v3 is otherwise equivalent to v2.
+		 */
+	case _LINUX_CAPABILITY_VERSION_3:
+		*tocopy = _LINUX_CAPABILITY_U32S_3;
+		break;
+	default:
+		if (put_user((u32)_KERNEL_CAPABILITY_VERSION, &header->version))
+			return -EFAULT;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /*
  * For sys_getproccap() and sys_setproccap(), any of the three
  * capability set pointers may be NULL -- indicating that that set is
@@ -71,27 +134,13 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr)
 {
 	int ret = 0;
 	pid_t pid;
-	__u32 version;
 	struct task_struct *target;
 	unsigned tocopy;
 	kernel_cap_t pE, pI, pP;
 
-	if (get_user(version, &header->version))
-		return -EFAULT;
-
-	switch (version) {
-	case _LINUX_CAPABILITY_VERSION_1:
-		warn_legacy_capability_use();
-		tocopy = _LINUX_CAPABILITY_U32S_1;
-		break;
-	case _LINUX_CAPABILITY_VERSION_2:
-		tocopy = _LINUX_CAPABILITY_U32S_2;
-		break;
-	default:
-		if (put_user(_LINUX_CAPABILITY_VERSION, &header->version))
-			return -EFAULT;
-		return -EINVAL;
-	}
+	ret = cap_validate_magic(header, &tocopy);
+	if (ret != 0)
+		return ret;
 
 	if (get_user(pid, &header->pid))
 		return -EFAULT;
@@ -118,7 +167,7 @@ out:
 	spin_unlock(&task_capability_lock);
 
 	if (!ret) {
-		struct __user_cap_data_struct kdata[_LINUX_CAPABILITY_U32S];
+		struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
 		unsigned i;
 
 		for (i = 0; i < tocopy; i++) {
@@ -128,7 +177,7 @@ out:
 		}
 
 		/*
-		 * Note, in the case, tocopy < _LINUX_CAPABILITY_U32S,
+		 * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S,
 		 * we silently drop the upper capabilities here. This
 		 * has the effect of making older libcap
 		 * implementations implicitly drop upper capability
@@ -240,30 +289,16 @@ static inline int cap_set_all(kernel_cap_t *effective,
  */
 asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
 {
-	struct __user_cap_data_struct kdata[_LINUX_CAPABILITY_U32S];
+	struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
 	unsigned i, tocopy;
 	kernel_cap_t inheritable, permitted, effective;
-	__u32 version;
 	struct task_struct *target;
 	int ret;
 	pid_t pid;
 
-	if (get_user(version, &header->version))
-		return -EFAULT;
-
-	switch (version) {
-	case _LINUX_CAPABILITY_VERSION_1:
-		warn_legacy_capability_use();
-		tocopy = _LINUX_CAPABILITY_U32S_1;
-		break;
-	case _LINUX_CAPABILITY_VERSION_2:
-		tocopy = _LINUX_CAPABILITY_U32S_2;
-		break;
-	default:
-		if (put_user(_LINUX_CAPABILITY_VERSION, &header->version))
-			return -EFAULT;
-		return -EINVAL;
-	}
+	ret = cap_validate_magic(header, &tocopy);
+	if (ret != 0)
+		return ret;
 
 	if (get_user(pid, &header->pid))
 		return -EFAULT;
@@ -281,7 +316,7 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
 		permitted.cap[i] = kdata[i].permitted;
 		inheritable.cap[i] = kdata[i].inheritable;
 	}
-	while (i < _LINUX_CAPABILITY_U32S) {
+	while (i < _KERNEL_CAPABILITY_U32S) {
 		effective.cap[i] = 0;
 		permitted.cap[i] = 0;
 		inheritable.cap[i] = 0;

kernel/cgroup.c

@@ -2903,7 +2903,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys)
 	cg = tsk->cgroups;
 	parent = task_cgroup(tsk, subsys->subsys_id);
 
-	snprintf(nodename, MAX_CGROUP_TYPE_NAMELEN, "node_%d", tsk->pid);
+	snprintf(nodename, MAX_CGROUP_TYPE_NAMELEN, "%d", tsk->pid);
 
 	/* Pin the hierarchy */
 	atomic_inc(&parent->root->sb->s_active);

kernel/cpuset.c

@@ -797,8 +797,10 @@ static int update_cpumask(struct cpuset *cs, char *buf)
 		retval = cpulist_parse(buf, trialcs.cpus_allowed);
 		if (retval < 0)
 			return retval;
+
+		if (!cpus_subset(trialcs.cpus_allowed, cpu_online_map))
+			return -EINVAL;
 	}
-	cpus_and(trialcs.cpus_allowed, trialcs.cpus_allowed, cpu_online_map);
 	retval = validate_change(cs, &trialcs);
 	if (retval < 0)
 		return retval;
@@ -932,9 +934,11 @@ static int update_nodemask(struct cpuset *cs, char *buf)
 		retval = nodelist_parse(buf, trialcs.mems_allowed);
 		if (retval < 0)
 			goto done;
+
+		if (!nodes_subset(trialcs.mems_allowed,
+				node_states[N_HIGH_MEMORY]))
+			return -EINVAL;
 	}
-	nodes_and(trialcs.mems_allowed, trialcs.mems_allowed,
-						node_states[N_HIGH_MEMORY]);
 	oldmem = cs->mems_allowed;
 	if (nodes_equal(oldmem, trialcs.mems_allowed)) {
 		retval = 0;		/* Too easy - nothing to do */

kernel/exit.c

@@ -126,6 +126,12 @@ static void __exit_signal(struct task_struct *tsk)
 
 	__unhash_process(tsk);
 
+	/*
+	 * Do this under ->siglock, we can race with another thread
+	 * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals.
+	 */
+	flush_sigqueue(&tsk->pending);
+
 	tsk->signal = NULL;
 	tsk->sighand = NULL;
 	spin_unlock(&sighand->siglock);
@@ -133,7 +139,6 @@ static void __exit_signal(struct task_struct *tsk)
 
 	__cleanup_sighand(sighand);
 	clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
-	flush_sigqueue(&tsk->pending);
 	if (sig) {
 		flush_sigqueue(&sig->shared_pending);
 		taskstats_tgid_free(sig);

kernel/fork.c

@@ -660,136 +660,6 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
 	return 0;
 }
 
-static int count_open_files(struct fdtable *fdt)
-{
-	int size = fdt->max_fds;
-	int i;
-
-	/* Find the last open fd */
-	for (i = size/(8*sizeof(long)); i > 0; ) {
-		if (fdt->open_fds->fds_bits[--i])
-			break;
-	}
-	i = (i+1) * 8 * sizeof(long);
-	return i;
-}
-
-static struct files_struct *alloc_files(void)
-{
-	struct files_struct *newf;
-	struct fdtable *fdt;
-
-	newf = kmem_cache_alloc(files_cachep, GFP_KERNEL);
-	if (!newf)
-		goto out;
-
-	atomic_set(&newf->count, 1);
-
-	spin_lock_init(&newf->file_lock);
-	newf->next_fd = 0;
-	fdt = &newf->fdtab;
-	fdt->max_fds = NR_OPEN_DEFAULT;
-	fdt->close_on_exec = (fd_set *)&newf->close_on_exec_init;
-	fdt->open_fds = (fd_set *)&newf->open_fds_init;
-	fdt->fd = &newf->fd_array[0];
-	INIT_RCU_HEAD(&fdt->rcu);
-	fdt->next = NULL;
-	rcu_assign_pointer(newf->fdt, fdt);
-out:
-	return newf;
-}
-
-/*
- * Allocate a new files structure and copy contents from the
- * passed in files structure.
- * errorp will be valid only when the returned files_struct is NULL.
- */
-static struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
-{
-	struct files_struct *newf;
-	struct file **old_fds, **new_fds;
-	int open_files, size, i;
-	struct fdtable *old_fdt, *new_fdt;
-
-	*errorp = -ENOMEM;
-	newf = alloc_files();
-	if (!newf)
-		goto out;
-
-	spin_lock(&oldf->file_lock);
-	old_fdt = files_fdtable(oldf);
-	new_fdt = files_fdtable(newf);
-	open_files = count_open_files(old_fdt);
-
-	/*
-	 * Check whether we need to allocate a larger fd array and fd set.
-	 * Note: we're not a clone task, so the open count won't change.
-	 */
-	if (open_files > new_fdt->max_fds) {
-		new_fdt->max_fds = 0;
-		spin_unlock(&oldf->file_lock);
-		spin_lock(&newf->file_lock);
-		*errorp = expand_files(newf, open_files-1);
-		spin_unlock(&newf->file_lock);
-		if (*errorp < 0)
-			goto out_release;
-		new_fdt = files_fdtable(newf);
-		/*
-		 * Reacquire the oldf lock and a pointer to its fd table
-		 * who knows it may have a new bigger fd table. We need
-		 * the latest pointer.
-		 */
-		spin_lock(&oldf->file_lock);
-		old_fdt = files_fdtable(oldf);
-	}
-
-	old_fds = old_fdt->fd;
-	new_fds = new_fdt->fd;
-
-	memcpy(new_fdt->open_fds->fds_bits,
-		old_fdt->open_fds->fds_bits, open_files/8);
-	memcpy(new_fdt->close_on_exec->fds_bits,
-		old_fdt->close_on_exec->fds_bits, open_files/8);
-
-	for (i = open_files; i != 0; i--) {
-		struct file *f = *old_fds++;
-		if (f) {
-			get_file(f);
-		} else {
-			/*
-			 * The fd may be claimed in the fd bitmap but not yet
-			 * instantiated in the files array if a sibling thread
-			 * is partway through open().  So make sure that this
-			 * fd is available to the new process.
-			 */
-			FD_CLR(open_files - i, new_fdt->open_fds);
-		}
-		rcu_assign_pointer(*new_fds++, f);
-	}
-	spin_unlock(&oldf->file_lock);
-
-	/* compute the remainder to be cleared */
-	size = (new_fdt->max_fds - open_files) * sizeof(struct file *);
-
-	/* This is long word aligned thus could use a optimized version */
-	memset(new_fds, 0, size);
-
-	if (new_fdt->max_fds > open_files) {
-		int left = (new_fdt->max_fds-open_files)/8;
-		int start = open_files / (8 * sizeof(unsigned long));
-
-		memset(&new_fdt->open_fds->fds_bits[start], 0, left);
-		memset(&new_fdt->close_on_exec->fds_bits[start], 0, left);
-	}
-
-	return newf;
-
-out_release:
-	kmem_cache_free(files_cachep, newf);
-out:
-	return NULL;
-}
-
 static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
 {
 	struct files_struct *oldf, *newf;

kernel/kgdb.c

@@ -52,6 +52,7 @@
 #include <asm/byteorder.h>
 #include <asm/atomic.h>
 #include <asm/system.h>
+#include <asm/unaligned.h>
 
 static int kgdb_break_asap;
 
@@ -227,8 +228,6 @@ void __weak kgdb_disable_hw_debug(struct pt_regs *regs)
  * GDB remote protocol parser:
  */
 
-static const char	hexchars[] = "0123456789abcdef";
-
 static int hex(char ch)
 {
 	if ((ch >= 'a') && (ch <= 'f'))
@@ -316,8 +315,8 @@ static void put_packet(char *buffer)
 		}
 
 		kgdb_io_ops->write_char('#');
-		kgdb_io_ops->write_char(hexchars[checksum >> 4]);
-		kgdb_io_ops->write_char(hexchars[checksum & 0xf]);
+		kgdb_io_ops->write_char(hex_asc_hi(checksum));
+		kgdb_io_ops->write_char(hex_asc_lo(checksum));
 		if (kgdb_io_ops->flush)
 			kgdb_io_ops->flush();
 
@@ -478,8 +477,8 @@ static void error_packet(char *pkt, int error)
 {
 	error = -error;
 	pkt[0] = 'E';
-	pkt[1] = hexchars[(error / 10)];
-	pkt[2] = hexchars[(error % 10)];
+	pkt[1] = hex_asc[(error / 10)];
+	pkt[2] = hex_asc[(error % 10)];
 	pkt[3] = '\0';
 }
 
@@ -510,10 +509,7 @@ static void int_to_threadref(unsigned char *id, int value)
 	scan = (unsigned char *)id;
 	while (i--)
 		*scan++ = 0;
-	*scan++ = (value >> 24) & 0xff;
-	*scan++ = (value >> 16) & 0xff;
-	*scan++ = (value >> 8) & 0xff;
-	*scan++ = (value & 0xff);
+	put_unaligned_be32(value, scan);
 }
 
 static struct task_struct *getthread(struct pt_regs *regs, int tid)

kernel/kprobes.c

@@ -699,8 +699,9 @@ static int __register_kprobes(struct kprobe **kps, int num,
 		return -EINVAL;
 	for (i = 0; i < num; i++) {
 		ret = __register_kprobe(kps[i], called_from);
-		if (ret < 0 && i > 0) {
-			unregister_kprobes(kps, i);
+		if (ret < 0) {
+			if (i > 0)
+				unregister_kprobes(kps, i);
 			break;
 		}
 	}
@@ -776,8 +777,9 @@ static int __register_jprobes(struct jprobe **jps, int num,
 			jp->kp.break_handler = longjmp_break_handler;
 			ret = __register_kprobe(&jp->kp, called_from);
 		}
-		if (ret < 0 && i > 0) {
-			unregister_jprobes(jps, i);
+		if (ret < 0) {
+			if (i > 0)
+				unregister_jprobes(jps, i);
 			break;
 		}
 	}
@@ -920,8 +922,9 @@ static int __register_kretprobes(struct kretprobe **rps, int num,
 		return -EINVAL;
 	for (i = 0; i < num; i++) {
 		ret = __register_kretprobe(rps[i], called_from);
-		if (ret < 0 && i > 0) {
-			unregister_kretprobes(rps, i);
+		if (ret < 0) {
+			if (i > 0)
+				unregister_kretprobes(rps, i);
 			break;
 		}
 	}

kernel/module.c

@@ -1337,7 +1337,19 @@ out_unreg:
 	kobject_put(&mod->mkobj.kobj);
 	return err;
 }
-#endif
+
+static void mod_sysfs_fini(struct module *mod)
+{
+	kobject_put(&mod->mkobj.kobj);
+}
+
+#else /* CONFIG_SYSFS */
+
+static void mod_sysfs_fini(struct module *mod)
+{
+}
+
+#endif /* CONFIG_SYSFS */
 
 static void mod_kobject_remove(struct module *mod)
 {
@@ -1345,7 +1357,7 @@ static void mod_kobject_remove(struct module *mod)
 	module_param_sysfs_remove(mod);
 	kobject_put(mod->mkobj.drivers_dir);
 	kobject_put(mod->holders_dir);
-	kobject_put(&mod->mkobj.kobj);
+	mod_sysfs_fini(mod);
 }
 
 /*
@@ -1780,7 +1792,7 @@ static struct module *load_module(void __user *umod,
 
 	/* Sanity checks against insmoding binaries or wrong arch,
            weird elf version */
-	if (memcmp(hdr->e_ident, ELFMAG, 4) != 0
+	if (memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0
 	    || hdr->e_type != ET_REL
 	    || !elf_check_arch(hdr)
 	    || hdr->e_shentsize != sizeof(*sechdrs)) {

kernel/relay.c

@@ -1191,7 +1191,7 @@ static ssize_t relay_file_splice_read(struct file *in,
 	ret = 0;
 	spliced = 0;
 
-	while (len) {
+	while (len && !spliced) {
 		ret = subbuf_splice_actor(in, ppos, pipe, len, flags, &nonpad_ret);
 		if (ret < 0)
 			break;

kernel/sched_clock.c

@@ -59,22 +59,26 @@ static inline struct sched_clock_data *cpu_sdc(int cpu)
 	return &per_cpu(sched_clock_data, cpu);
 }
 
+static __read_mostly int sched_clock_running;
+
 void sched_clock_init(void)
 {
 	u64 ktime_now = ktime_to_ns(ktime_get());
-	u64 now = 0;
+	unsigned long now_jiffies = jiffies;
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
 		struct sched_clock_data *scd = cpu_sdc(cpu);
 
 		scd->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
-		scd->prev_jiffies = jiffies;
-		scd->prev_raw = now;
-		scd->tick_raw = now;
+		scd->prev_jiffies = now_jiffies;
+		scd->prev_raw = 0;
+		scd->tick_raw = 0;
 		scd->tick_gtod = ktime_now;
 		scd->clock = ktime_now;
 	}
+
+	sched_clock_running = 1;
 }
 
 /*
@@ -136,6 +140,9 @@ u64 sched_clock_cpu(int cpu)
 	struct sched_clock_data *scd = cpu_sdc(cpu);
 	u64 now, clock;
 
+	if (unlikely(!sched_clock_running))
+		return 0ull;
+
 	WARN_ON_ONCE(!irqs_disabled());
 	now = sched_clock();
 
@@ -174,6 +181,9 @@ void sched_clock_tick(void)
 	struct sched_clock_data *scd = this_scd();
 	u64 now, now_gtod;
 
+	if (unlikely(!sched_clock_running))
+		return;
+
 	WARN_ON_ONCE(!irqs_disabled());
 
 	now = sched_clock();

kernel/sched_debug.c

@@ -167,11 +167,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 #endif
 	SEQ_printf(m, "  .%-30s: %ld\n", "nr_spread_over",
 			cfs_rq->nr_spread_over);
-#ifdef CONFIG_FAIR_GROUP_SCHED
-#ifdef CONFIG_SMP
-	SEQ_printf(m, "  .%-30s: %lu\n", "shares", cfs_rq->shares);
-#endif
-#endif
 }
 
 static void print_cpu(struct seq_file *m, int cpu)

kernel/sched_fair.c

@@ -333,34 +333,6 @@ int sched_nr_latency_handler(struct ctl_table *table, int write,
 }
 #endif
 
-/*
- * delta *= w / rw
- */
-static inline unsigned long
-calc_delta_weight(unsigned long delta, struct sched_entity *se)
-{
-	for_each_sched_entity(se) {
-		delta = calc_delta_mine(delta,
-				se->load.weight, &cfs_rq_of(se)->load);
-	}
-
-	return delta;
-}
-
-/*
- * delta *= rw / w
- */
-static inline unsigned long
-calc_delta_fair(unsigned long delta, struct sched_entity *se)
-{
-	for_each_sched_entity(se) {
-		delta = calc_delta_mine(delta,
-				cfs_rq_of(se)->load.weight, &se->load);
-	}
-
-	return delta;
-}
-
 /*
  * The idea is to set a period in which each task runs once.
  *
@@ -390,54 +362,47 @@ static u64 __sched_period(unsigned long nr_running)
  */
 static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	return calc_delta_weight(__sched_period(cfs_rq->nr_running), se);
+	u64 slice = __sched_period(cfs_rq->nr_running);
+
+	for_each_sched_entity(se) {
+		cfs_rq = cfs_rq_of(se);
+
+		slice *= se->load.weight;
+		do_div(slice, cfs_rq->load.weight);
+	}
+
+
+	return slice;
 }
 
 /*
  * We calculate the vruntime slice of a to be inserted task
  *
- * vs = s*rw/w = p
+ * vs = s/w = p/rw
  */
 static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	unsigned long nr_running = cfs_rq->nr_running;
+	unsigned long weight;
+	u64 vslice;
 
 	if (!se->on_rq)
 		nr_running++;
 
-	return __sched_period(nr_running);
-}
-
-/*
- * The goal of calc_delta_asym() is to be asymmetrically around NICE_0_LOAD, in
- * that it favours >=0 over <0.
- *
- *   -20         |
- *               |
- *     0 --------+-------
- *             .'
- *    19     .'
- *
- */
-static unsigned long
-calc_delta_asym(unsigned long delta, struct sched_entity *se)
-{
-	struct load_weight lw = {
-		.weight = NICE_0_LOAD,
-		.inv_weight = 1UL << (WMULT_SHIFT-NICE_0_SHIFT)
-	};
+	vslice = __sched_period(nr_running);
 
 	for_each_sched_entity(se) {
-		struct load_weight *se_lw = &se->load;
+		cfs_rq = cfs_rq_of(se);
 
-		if (se->load.weight < NICE_0_LOAD)
-			se_lw = &lw;
+		weight = cfs_rq->load.weight;
+		if (!se->on_rq)
+			weight += se->load.weight;
 
-		delta = calc_delta_mine(delta,
-				cfs_rq_of(se)->load.weight, se_lw);
+		vslice *= NICE_0_LOAD;
+		do_div(vslice, weight);
 	}
 
-	return delta;
+	return vslice;
 }
 
 /*
@@ -454,7 +419,11 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 
 	curr->sum_exec_runtime += delta_exec;
 	schedstat_add(cfs_rq, exec_clock, delta_exec);
-	delta_exec_weighted = calc_delta_fair(delta_exec, curr);
+	delta_exec_weighted = delta_exec;
+	if (unlikely(curr->load.weight != NICE_0_LOAD)) {
+		delta_exec_weighted = calc_delta_fair(delta_exec_weighted,
+							&curr->load);
+	}
 	curr->vruntime += delta_exec_weighted;
 }
 
@@ -541,27 +510,10 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * Scheduling class queueing methods:
  */
 
-#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
-static void
-add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
-{
-	cfs_rq->task_weight += weight;
-}
-#else
-static inline void
-add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
-{
-}
-#endif
-
 static void
 account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	update_load_add(&cfs_rq->load, se->load.weight);
-	if (!parent_entity(se))
-		inc_cpu_load(rq_of(cfs_rq), se->load.weight);
-	if (entity_is_task(se))
-		add_cfs_task_weight(cfs_rq, se->load.weight);
 	cfs_rq->nr_running++;
 	se->on_rq = 1;
 	list_add(&se->group_node, &cfs_rq->tasks);
@@ -571,10 +523,6 @@ static void
 account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	update_load_sub(&cfs_rq->load, se->load.weight);
-	if (!parent_entity(se))
-		dec_cpu_load(rq_of(cfs_rq), se->load.weight);
-	if (entity_is_task(se))
-		add_cfs_task_weight(cfs_rq, -se->load.weight);
 	cfs_rq->nr_running--;
 	se->on_rq = 0;
 	list_del_init(&se->group_node);
@@ -661,17 +609,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
 	if (!initial) {
 		/* sleeps upto a single latency don't count. */
-		if (sched_feat(NEW_FAIR_SLEEPERS)) {
-			unsigned long thresh = sysctl_sched_latency;
-
-			/*
-			 * convert the sleeper threshold into virtual time
-			 */
-			if (sched_feat(NORMALIZED_SLEEPER))
-				thresh = calc_delta_fair(thresh, se);
-
-			vruntime -= thresh;
-		}
+		if (sched_feat(NEW_FAIR_SLEEPERS))
+			vruntime -= sysctl_sched_latency;
 
 		/* ensure we never gain time by being placed backwards. */
 		vruntime = max_vruntime(se->vruntime, vruntime);
@@ -1057,24 +996,11 @@ wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
 	struct task_struct *curr = this_rq->curr;
 	unsigned long tl = this_load;
 	unsigned long tl_per_task;
+	int balanced;
 
-	if (!(this_sd->flags & SD_WAKE_AFFINE))
+	if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
 		return 0;
 
-	/*
-	 * If the currently running task will sleep within
-	 * a reasonable amount of time then attract this newly
-	 * woken task:
-	 */
-	if (sync && curr->sched_class == &fair_sched_class) {
-		if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
-				p->se.avg_overlap < sysctl_sched_migration_cost)
-			return 1;
-	}
-
-	schedstat_inc(p, se.nr_wakeups_affine_attempts);
-	tl_per_task = cpu_avg_load_per_task(this_cpu);
-
 	/*
 	 * If sync wakeup then subtract the (maximum possible)
 	 * effect of the currently running task from the load
@@ -1083,8 +1009,24 @@ wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
 	if (sync)
 		tl -= current->se.load.weight;
 
+	balanced = 100*(tl + p->se.load.weight) <= imbalance*load;
+
+	/*
+	 * If the currently running task will sleep within
+	 * a reasonable amount of time then attract this newly
+	 * woken task:
+	 */
+	if (sync && balanced && curr->sched_class == &fair_sched_class) {
+		if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
+				p->se.avg_overlap < sysctl_sched_migration_cost)
+			return 1;
+	}
+
+	schedstat_inc(p, se.nr_wakeups_affine_attempts);
+	tl_per_task = cpu_avg_load_per_task(this_cpu);
+
 	if ((tl <= load && tl + target_load(prev_cpu, idx) <= tl_per_task) ||
-			100*(tl + p->se.load.weight) <= imbalance*load) {
+			balanced) {
 		/*
 		 * This domain has SD_WAKE_AFFINE and
 		 * p is cache cold in this domain, and
@@ -1169,10 +1111,11 @@ static unsigned long wakeup_gran(struct sched_entity *se)
 	unsigned long gran = sysctl_sched_wakeup_granularity;
 
 	/*
-	 * More easily preempt - nice tasks, while not making it harder for
-	 * + nice tasks.
+	 * More easily preempt - nice tasks, while not making
+	 * it harder for + nice tasks.
 	 */
-	gran = calc_delta_asym(sysctl_sched_wakeup_granularity, se);
+	if (unlikely(se->load.weight > NICE_0_LOAD))
+		gran = calc_delta_fair(gran, &se->load);
 
 	return gran;
 }
@@ -1366,90 +1309,75 @@ static struct task_struct *load_balance_next_fair(void *arg)
 	return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator);
 }
 
-static unsigned long
-__load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		unsigned long max_load_move, struct sched_domain *sd,
-		enum cpu_idle_type idle, int *all_pinned, int *this_best_prio,
-		struct cfs_rq *cfs_rq)
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static int cfs_rq_best_prio(struct cfs_rq *cfs_rq)
 {
+	struct sched_entity *curr;
+	struct task_struct *p;
+
+	if (!cfs_rq->nr_running || !first_fair(cfs_rq))
+		return MAX_PRIO;
+
+	curr = cfs_rq->curr;
+	if (!curr)
+		curr = __pick_next_entity(cfs_rq);
+
+	p = task_of(curr);
+
+	return p->prio;
+}
+#endif
+
+static unsigned long
+load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		  unsigned long max_load_move,
+		  struct sched_domain *sd, enum cpu_idle_type idle,
+		  int *all_pinned, int *this_best_prio)
+{
+	struct cfs_rq *busy_cfs_rq;
+	long rem_load_move = max_load_move;
 	struct rq_iterator cfs_rq_iterator;
 
 	cfs_rq_iterator.start = load_balance_start_fair;
 	cfs_rq_iterator.next = load_balance_next_fair;
-	cfs_rq_iterator.arg = cfs_rq;
-
-	return balance_tasks(this_rq, this_cpu, busiest,
-			max_load_move, sd, idle, all_pinned,
-			this_best_prio, &cfs_rq_iterator);
-}
 
+	for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
 #ifdef CONFIG_FAIR_GROUP_SCHED
-static unsigned long
-load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		  unsigned long max_load_move,
-		  struct sched_domain *sd, enum cpu_idle_type idle,
-		  int *all_pinned, int *this_best_prio)
-{
-	long rem_load_move = max_load_move;
-	int busiest_cpu = cpu_of(busiest);
-	struct task_group *tg;
-
-	rcu_read_lock();
-	list_for_each_entry(tg, &task_groups, list) {
+		struct cfs_rq *this_cfs_rq;
 		long imbalance;
-		unsigned long this_weight, busiest_weight;
-		long rem_load, max_load, moved_load;
+		unsigned long maxload;
 
+		this_cfs_rq = cpu_cfs_rq(busy_cfs_rq, this_cpu);
+
+		imbalance = busy_cfs_rq->load.weight - this_cfs_rq->load.weight;
+		/* Don't pull if this_cfs_rq has more load than busy_cfs_rq */
+		if (imbalance <= 0)
+			continue;
+
+		/* Don't pull more than imbalance/2 */
+		imbalance /= 2;
+		maxload = min(rem_load_move, imbalance);
+
+		*this_best_prio = cfs_rq_best_prio(this_cfs_rq);
+#else
+# define maxload rem_load_move
+#endif
 		/*
-		 * empty group
+		 * pass busy_cfs_rq argument into
+		 * load_balance_[start|next]_fair iterators
 		 */
-		if (!aggregate(tg, sd)->task_weight)
-			continue;
+		cfs_rq_iterator.arg = busy_cfs_rq;
+		rem_load_move -= balance_tasks(this_rq, this_cpu, busiest,
+					       maxload, sd, idle, all_pinned,
+					       this_best_prio,
+					       &cfs_rq_iterator);
 
-		rem_load = rem_load_move * aggregate(tg, sd)->rq_weight;
-		rem_load /= aggregate(tg, sd)->load + 1;
-
-		this_weight = tg->cfs_rq[this_cpu]->task_weight;
-		busiest_weight = tg->cfs_rq[busiest_cpu]->task_weight;
-
-		imbalance = (busiest_weight - this_weight) / 2;
-
-		if (imbalance < 0)
-			imbalance = busiest_weight;
-
-		max_load = max(rem_load, imbalance);
-		moved_load = __load_balance_fair(this_rq, this_cpu, busiest,
-				max_load, sd, idle, all_pinned, this_best_prio,
-				tg->cfs_rq[busiest_cpu]);
-
-		if (!moved_load)
-			continue;
-
-		move_group_shares(tg, sd, busiest_cpu, this_cpu);
-
-		moved_load *= aggregate(tg, sd)->load;
-		moved_load /= aggregate(tg, sd)->rq_weight + 1;
-
-		rem_load_move -= moved_load;
-		if (rem_load_move < 0)
+		if (rem_load_move <= 0)
 			break;
 	}
-	rcu_read_unlock();
 
 	return max_load_move - rem_load_move;
 }
-#else
-static unsigned long
-load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		  unsigned long max_load_move,
-		  struct sched_domain *sd, enum cpu_idle_type idle,
-		  int *all_pinned, int *this_best_prio)
-{
-	return __load_balance_fair(this_rq, this_cpu, busiest,
-			max_load_move, sd, idle, all_pinned,
-			this_best_prio, &busiest->cfs);
-}
-#endif
 
 static int
 move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,

kernel/sched_rt.c

@@ -513,8 +513,6 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
 	 */
 	for_each_sched_rt_entity(rt_se)
 		enqueue_rt_entity(rt_se);
-
-	inc_cpu_load(rq, p->se.load.weight);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
@@ -534,8 +532,6 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
 		if (rt_rq && rt_rq->rt_nr_running)
 			enqueue_rt_entity(rt_se);
 	}
-
-	dec_cpu_load(rq, p->se.load.weight);
 }
 
 /*

kernel/sched_stats.h

@@ -67,6 +67,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
 		preempt_enable();
 #endif
 	}
+	kfree(mask_str);
 	return 0;
 }
 

kernel/signal.c

@@ -231,6 +231,40 @@ void flush_signals(struct task_struct *t)
 	spin_unlock_irqrestore(&t->sighand->siglock, flags);
 }
 
+static void __flush_itimer_signals(struct sigpending *pending)
+{
+	sigset_t signal, retain;
+	struct sigqueue *q, *n;
+
+	signal = pending->signal;
+	sigemptyset(&retain);
+
+	list_for_each_entry_safe(q, n, &pending->list, list) {
+		int sig = q->info.si_signo;
+
+		if (likely(q->info.si_code != SI_TIMER)) {
+			sigaddset(&retain, sig);
+		} else {
+			sigdelset(&signal, sig);
+			list_del_init(&q->list);
+			__sigqueue_free(q);
+		}
+	}
+
+	sigorsets(&pending->signal, &signal, &retain);
+}
+
+void flush_itimer_signals(void)
+{
+	struct task_struct *tsk = current;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tsk->sighand->siglock, flags);
+	__flush_itimer_signals(&tsk->pending);
+	__flush_itimer_signals(&tsk->signal->shared_pending);
+	spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
+}
+
 void ignore_signals(struct task_struct *t)
 {
 	int i;
@@ -1240,17 +1274,22 @@ void sigqueue_free(struct sigqueue *q)
 
 	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
 	/*
-	 * If the signal is still pending remove it from the
-	 * pending queue. We must hold ->siglock while testing
-	 * q->list to serialize with collect_signal().
+	 * We must hold ->siglock while testing q->list
+	 * to serialize with collect_signal() or with
+	 * __exit_signal()->flush_sigqueue().
 	 */
 	spin_lock_irqsave(lock, flags);
+	q->flags &= ~SIGQUEUE_PREALLOC;
+	/*
+	 * If it is queued it will be freed when dequeued,
+	 * like the "regular" sigqueue.
+	 */
 	if (!list_empty(&q->list))
-		list_del_init(&q->list);
+		q = NULL;
 	spin_unlock_irqrestore(lock, flags);
 
-	q->flags &= ~SIGQUEUE_PREALLOC;
-	__sigqueue_free(q);
+	if (q)
+		__sigqueue_free(q);
 }
 
 int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)

kernel/stop_machine.c

@@ -62,8 +62,7 @@ static int stopmachine(void *cpu)
 		 * help our sisters onto their CPUs. */
 		if (!prepared && !irqs_disabled)
 			yield();
-		else
-			cpu_relax();
+		cpu_relax();
 	}
 
 	/* Ack: we are exiting. */
@@ -106,8 +105,10 @@ static int stop_machine(void)
 	}
 
 	/* Wait for them all to come to life. */
-	while (atomic_read(&stopmachine_thread_ack) != stopmachine_num_threads)
+	while (atomic_read(&stopmachine_thread_ack) != stopmachine_num_threads) {
 		yield();
+		cpu_relax();
+	}
 
 	/* If some failed, kill them all. */
 	if (ret < 0) {

kernel/sys.c

@@ -1652,7 +1652,7 @@ asmlinkage long sys_umask(int mask)
 asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
 			  unsigned long arg4, unsigned long arg5)
 {
-	long uninitialized_var(error);
+	long error = 0;
 
 	if (security_task_prctl(option, arg2, arg3, arg4, arg5, &error))
 		return error;
@@ -1701,9 +1701,7 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
 			error = PR_TIMING_STATISTICAL;
 			break;
 		case PR_SET_TIMING:
-			if (arg2 == PR_TIMING_STATISTICAL)
-				error = 0;
-			else
+			if (arg2 != PR_TIMING_STATISTICAL)
 				error = -EINVAL;
 			break;