Merge branch 'master' into for-linus

70 files changed, 7091 insertions, 1734 deletions

diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
new file mode 100644
index 00000000000..88c92fb4461
--- /dev/null
+++ b/kernel/Kconfig.locks
@@ -0,0 +1,202 @@
+#
+# The ARCH_INLINE foo is necessary because select ignores "depends on"
+#
+config ARCH_INLINE_SPIN_TRYLOCK
+	bool
+
+config ARCH_INLINE_SPIN_TRYLOCK_BH
+	bool
+
+config ARCH_INLINE_SPIN_LOCK
+	bool
+
+config ARCH_INLINE_SPIN_LOCK_BH
+	bool
+
+config ARCH_INLINE_SPIN_LOCK_IRQ
+	bool
+
+config ARCH_INLINE_SPIN_LOCK_IRQSAVE
+	bool
+
+config ARCH_INLINE_SPIN_UNLOCK
+	bool
+
+config ARCH_INLINE_SPIN_UNLOCK_BH
+	bool
+
+config ARCH_INLINE_SPIN_UNLOCK_IRQ
+	bool
+
+config ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE
+	bool
+
+
+config ARCH_INLINE_READ_TRYLOCK
+	bool
+
+config ARCH_INLINE_READ_LOCK
+	bool
+
+config ARCH_INLINE_READ_LOCK_BH
+	bool
+
+config ARCH_INLINE_READ_LOCK_IRQ
+	bool
+
+config ARCH_INLINE_READ_LOCK_IRQSAVE
+	bool
+
+config ARCH_INLINE_READ_UNLOCK
+	bool
+
+config ARCH_INLINE_READ_UNLOCK_BH
+	bool
+
+config ARCH_INLINE_READ_UNLOCK_IRQ
+	bool
+
+config ARCH_INLINE_READ_UNLOCK_IRQRESTORE
+	bool
+
+
+config ARCH_INLINE_WRITE_TRYLOCK
+	bool
+
+config ARCH_INLINE_WRITE_LOCK
+	bool
+
+config ARCH_INLINE_WRITE_LOCK_BH
+	bool
+
+config ARCH_INLINE_WRITE_LOCK_IRQ
+	bool
+
+config ARCH_INLINE_WRITE_LOCK_IRQSAVE
+	bool
+
+config ARCH_INLINE_WRITE_UNLOCK
+	bool
+
+config ARCH_INLINE_WRITE_UNLOCK_BH
+	bool
+
+config ARCH_INLINE_WRITE_UNLOCK_IRQ
+	bool
+
+config ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
+	bool
+
+#
+# lock_* functions are inlined when:
+#   - DEBUG_SPINLOCK=n and GENERIC_LOCKBREAK=n and ARCH_INLINE_*LOCK=y
+#
+# trylock_* functions are inlined when:
+#   - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
+#
+# unlock and unlock_irq functions are inlined when:
+#   - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
+#  or
+#   - DEBUG_SPINLOCK=n and PREEMPT=n
+#
+# unlock_bh and unlock_irqrestore functions are inlined when:
+#   - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
+#
+
+config INLINE_SPIN_TRYLOCK
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_TRYLOCK
+
+config INLINE_SPIN_TRYLOCK_BH
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_TRYLOCK_BH
+
+config INLINE_SPIN_LOCK
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK
+
+config INLINE_SPIN_LOCK_BH
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_SPIN_LOCK_BH
+
+config INLINE_SPIN_LOCK_IRQ
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_SPIN_LOCK_IRQ
+
+config INLINE_SPIN_LOCK_IRQSAVE
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_SPIN_LOCK_IRQSAVE
+
+config INLINE_SPIN_UNLOCK
+	def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK)
+
+config INLINE_SPIN_UNLOCK_BH
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_BH
+
+config INLINE_SPIN_UNLOCK_IRQ
+	def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK_BH)
+
+config INLINE_SPIN_UNLOCK_IRQRESTORE
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE
+
+
+config INLINE_READ_TRYLOCK
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_TRYLOCK
+
+config INLINE_READ_LOCK
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK
+
+config INLINE_READ_LOCK_BH
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_READ_LOCK_BH
+
+config INLINE_READ_LOCK_IRQ
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_READ_LOCK_IRQ
+
+config INLINE_READ_LOCK_IRQSAVE
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_READ_LOCK_IRQSAVE
+
+config INLINE_READ_UNLOCK
+	def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_READ_UNLOCK)
+
+config INLINE_READ_UNLOCK_BH
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_UNLOCK_BH
+
+config INLINE_READ_UNLOCK_IRQ
+	def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_READ_UNLOCK_BH)
+
+config INLINE_READ_UNLOCK_IRQRESTORE
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_UNLOCK_IRQRESTORE
+
+
+config INLINE_WRITE_TRYLOCK
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_TRYLOCK
+
+config INLINE_WRITE_LOCK
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK
+
+config INLINE_WRITE_LOCK_BH
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_WRITE_LOCK_BH
+
+config INLINE_WRITE_LOCK_IRQ
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_WRITE_LOCK_IRQ
+
+config INLINE_WRITE_LOCK_IRQSAVE
+	def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+		 ARCH_INLINE_WRITE_LOCK_IRQSAVE
+
+config INLINE_WRITE_UNLOCK
+	def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_WRITE_UNLOCK)
+
+config INLINE_WRITE_UNLOCK_BH
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_BH
+
+config INLINE_WRITE_UNLOCK_IRQ
+	def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_WRITE_UNLOCK_BH)
+
+config INLINE_WRITE_UNLOCK_IRQRESTORE
+	def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
+
+config MUTEX_SPIN_ON_OWNER
+	def_bool SMP && !DEBUG_MUTEXES && !HAVE_DEFAULT_NO_SPIN_MUTEXES
diff --git a/kernel/Makefile b/kernel/Makefile
index b8d4cd8ac0b..982c50e2ce5 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -21,6 +21,7 @@ CFLAGS_REMOVE_mutex-debug.o = -pg
 CFLAGS_REMOVE_rtmutex-debug.o = -pg
 CFLAGS_REMOVE_cgroup-debug.o = -pg
 CFLAGS_REMOVE_sched_clock.o = -pg
+CFLAGS_REMOVE_perf_event.o = -pg
 endif
 
 obj-$(CONFIG_FREEZER) += freezer.o
@@ -82,6 +83,7 @@ obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_TREE_RCU) += rcutree.o
 obj-$(CONFIG_TREE_PREEMPT_RCU) += rcutree.o
 obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o
+obj-$(CONFIG_TINY_RCU) += rcutiny.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
@@ -94,7 +96,9 @@ obj-$(CONFIG_X86_DS) += trace/
 obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_SLOW_WORK) += slow-work.o
+obj-$(CONFIG_SLOW_WORK_DEBUG) += slow-work-debugfs.o
 obj-$(CONFIG_PERF_EVENTS) += perf_event.o
+obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/capability.c b/kernel/capability.c
index 4e17041963f..7f876e60521 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -29,7 +29,6 @@ EXPORT_SYMBOL(__cap_empty_set);
 EXPORT_SYMBOL(__cap_full_set);
 EXPORT_SYMBOL(__cap_init_eff_set);
 
-#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
 int file_caps_enabled = 1;
 
 static int __init file_caps_disable(char *str)
@@ -38,7 +37,6 @@ static int __init file_caps_disable(char *str)
 	return 1;
 }
 __setup("no_file_caps", file_caps_disable);
-#endif
 
 /*
  * More recent versions of libcap are available from:
@@ -169,8 +167,8 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr)
 	kernel_cap_t pE, pI, pP;
 
 	ret = cap_validate_magic(header, &tocopy);
-	if (ret != 0)
-		return ret;
+	if ((dataptr == NULL) || (ret != 0))
+		return ((dataptr == NULL) && (ret == -EINVAL)) ? 0 : ret;
 
 	if (get_user(pid, &header->pid))
 		return -EFAULT;
@@ -238,7 +236,7 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr)
 SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
 {
 	struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
-	unsigned i, tocopy;
+	unsigned i, tocopy, copybytes;
 	kernel_cap_t inheritable, permitted, effective;
 	struct cred *new;
 	int ret;
@@ -255,8 +253,11 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
 	if (pid != 0 && pid != task_pid_vnr(current))
 		return -EPERM;
 
-	if (copy_from_user(&kdata, data,
-			   tocopy * sizeof(struct __user_cap_data_struct)))
+	copybytes = tocopy * sizeof(struct __user_cap_data_struct);
+	if (copybytes > sizeof(kdata))
+		return -EFAULT;
+
+	if (copy_from_user(&kdata, data, copybytes))
 		return -EFAULT;
 
 	for (i = 0; i < tocopy; i++) {
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index ca83b73fba1..0249f4be9b5 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1710,14 +1710,13 @@ static ssize_t cgroup_write_X64(struct cgroup *cgrp, struct cftype *cft,
 		return -EFAULT;
 
 	buffer[nbytes] = 0;     /* nul-terminate */
-	strstrip(buffer);
 	if (cft->write_u64) {
-		u64 val = simple_strtoull(buffer, &end, 0);
+		u64 val = simple_strtoull(strstrip(buffer), &end, 0);
 		if (*end)
 			return -EINVAL;
 		retval = cft->write_u64(cgrp, cft, val);
 	} else {
-		s64 val = simple_strtoll(buffer, &end, 0);
+		s64 val = simple_strtoll(strstrip(buffer), &end, 0);
 		if (*end)
 			return -EINVAL;
 		retval = cft->write_s64(cgrp, cft, val);
@@ -1753,8 +1752,7 @@ static ssize_t cgroup_write_string(struct cgroup *cgrp, struct cftype *cft,
 	}
 
 	buffer[nbytes] = 0;     /* nul-terminate */
-	strstrip(buffer);
-	retval = cft->write_string(cgrp, cft, buffer);
+	retval = cft->write_string(cgrp, cft, strstrip(buffer));
 	if (!retval)
 		retval = nbytes;
 out:
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index b5cb469d254..3cf2183b472 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -537,8 +537,7 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c)
  *	element of the partition (one sched domain) to be passed to
  *	partition_sched_domains().
  */
-/* FIXME: see the FIXME in partition_sched_domains() */
-static int generate_sched_domains(struct cpumask **domains,
+static int generate_sched_domains(cpumask_var_t **domains,
 			struct sched_domain_attr **attributes)
 {
 	LIST_HEAD(q);		/* queue of cpusets to be scanned */
@@ -546,7 +545,7 @@ static int generate_sched_domains(struct cpumask **domains,
 	struct cpuset **csa;	/* array of all cpuset ptrs */
 	int csn;		/* how many cpuset ptrs in csa so far */
 	int i, j, k;		/* indices for partition finding loops */
-	struct cpumask *doms;	/* resulting partition; i.e. sched domains */
+	cpumask_var_t *doms;	/* resulting partition; i.e. sched domains */
 	struct sched_domain_attr *dattr;  /* attributes for custom domains */
 	int ndoms = 0;		/* number of sched domains in result */
 	int nslot;		/* next empty doms[] struct cpumask slot */
@@ -557,7 +556,8 @@ static int generate_sched_domains(struct cpumask **domains,
 
 	/* Special case for the 99% of systems with one, full, sched domain */
 	if (is_sched_load_balance(&top_cpuset)) {
-		doms = kmalloc(cpumask_size(), GFP_KERNEL);
+		ndoms = 1;
+		doms = alloc_sched_domains(ndoms);
 		if (!doms)
 			goto done;
 
@@ -566,9 +566,8 @@ static int generate_sched_domains(struct cpumask **domains,
 			*dattr = SD_ATTR_INIT;
 			update_domain_attr_tree(dattr, &top_cpuset);
 		}
-		cpumask_copy(doms, top_cpuset.cpus_allowed);
+		cpumask_copy(doms[0], top_cpuset.cpus_allowed);
 
-		ndoms = 1;
 		goto done;
 	}
 
@@ -636,7 +635,7 @@ restart:
 	 * Now we know how many domains to create.
 	 * Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
 	 */
-	doms = kmalloc(ndoms * cpumask_size(), GFP_KERNEL);
+	doms = alloc_sched_domains(ndoms);
 	if (!doms)
 		goto done;
 
@@ -656,7 +655,7 @@ restart:
 			continue;
 		}
 
-		dp = doms + nslot;
+		dp = doms[nslot];
 
 		if (nslot == ndoms) {
 			static int warnings = 10;
@@ -718,7 +717,7 @@ done:
 static void do_rebuild_sched_domains(struct work_struct *unused)
 {
 	struct sched_domain_attr *attr;
-	struct cpumask *doms;
+	cpumask_var_t *doms;
 	int ndoms;
 
 	get_online_cpus();
@@ -2052,7 +2051,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 				unsigned long phase, void *unused_cpu)
 {
 	struct sched_domain_attr *attr;
-	struct cpumask *doms;
+	cpumask_var_t *doms;
 	int ndoms;
 
 	switch (phase) {
@@ -2537,15 +2536,9 @@ const struct file_operations proc_cpuset_operations = {
 };
 #endif /* CONFIG_PROC_PID_CPUSET */
 
-/* Display task cpus_allowed, mems_allowed in /proc/<pid>/status file. */
+/* Display task mems_allowed in /proc/<pid>/status file. */
 void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task)
 {
-	seq_printf(m, "Cpus_allowed:\t");
-	seq_cpumask(m, &task->cpus_allowed);
-	seq_printf(m, "\n");
-	seq_printf(m, "Cpus_allowed_list:\t");
-	seq_cpumask_list(m, &task->cpus_allowed);
-	seq_printf(m, "\n");
 	seq_printf(m, "Mems_allowed:\t");
 	seq_nodemask(m, &task->mems_allowed);
 	seq_printf(m, "\n");
diff --git a/kernel/exit.c b/kernel/exit.c
index e61891f8012..80ae941cfd2 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -49,6 +49,7 @@
 #include <linux/init_task.h>
 #include <linux/perf_event.h>
 #include <trace/events/sched.h>
+#include <linux/hw_breakpoint.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -110,9 +111,9 @@ static void __exit_signal(struct task_struct *tsk)
 		 * We won't ever get here for the group leader, since it
 		 * will have been the last reference on the signal_struct.
 		 */
-		sig->utime = cputime_add(sig->utime, task_utime(tsk));
-		sig->stime = cputime_add(sig->stime, task_stime(tsk));
-		sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
+		sig->utime = cputime_add(sig->utime, tsk->utime);
+		sig->stime = cputime_add(sig->stime, tsk->stime);
+		sig->gtime = cputime_add(sig->gtime, tsk->gtime);
 		sig->min_flt += tsk->min_flt;
 		sig->maj_flt += tsk->maj_flt;
 		sig->nvcsw += tsk->nvcsw;
@@ -359,10 +360,8 @@ void __set_special_pids(struct pid *pid)
 {
 	struct task_struct *curr = current->group_leader;
 
-	if (task_session(curr) != pid) {
+	if (task_session(curr) != pid)
 		change_pid(curr, PIDTYPE_SID, pid);
-		proc_sid_connector(curr);
-	}
 
 	if (task_pgrp(curr) != pid)
 		change_pid(curr, PIDTYPE_PGID, pid);
@@ -980,6 +979,10 @@ NORET_TYPE void do_exit(long code)
 	proc_exit_connector(tsk);
 
 	/*
+	 * FIXME: do that only when needed, using sched_exit tracepoint
+	 */
+	flush_ptrace_hw_breakpoint(tsk);
+	/*
 	 * Flush inherited counters to the parent - before the parent
 	 * gets woken up by child-exit notifications.
 	 */
@@ -1207,6 +1210,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		struct signal_struct *psig;
 		struct signal_struct *sig;
 		unsigned long maxrss;
+		cputime_t tgutime, tgstime;
 
 		/*
 		 * The resource counters for the group leader are in its
@@ -1222,20 +1226,23 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		 * need to protect the access to parent->signal fields,
 		 * as other threads in the parent group can be right
 		 * here reaping other children at the same time.
+		 *
+		 * We use thread_group_times() to get times for the thread
+		 * group, which consolidates times for all threads in the
+		 * group including the group leader.
 		 */
+		thread_group_times(p, &tgutime, &tgstime);
 		spin_lock_irq(&p->real_parent->sighand->siglock);
 		psig = p->real_parent->signal;
 		sig = p->signal;
 		psig->cutime =
 			cputime_add(psig->cutime,
-			cputime_add(p->utime,
-			cputime_add(sig->utime,
-				    sig->cutime)));
+			cputime_add(tgutime,
+				    sig->cutime));
 		psig->cstime =
 			cputime_add(psig->cstime,
-			cputime_add(p->stime,
-			cputime_add(sig->stime,
-				    sig->cstime)));
+			cputime_add(tgstime,
+				    sig->cstime));
 		psig->cgtime =
 			cputime_add(psig->cgtime,
 			cputime_add(p->gtime,
diff --git a/kernel/fork.c b/kernel/fork.c
index 4c20fff8c13..3d6f121bbe8 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -91,7 +91,7 @@ int nr_processes(void)
 	int cpu;
 	int total = 0;
 
-	for_each_online_cpu(cpu)
+	for_each_possible_cpu(cpu)
 		total += per_cpu(process_counts, cpu);
 
 	return total;
@@ -884,6 +884,9 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
 	sig->gtime = cputime_zero;
 	sig->cgtime = cputime_zero;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+	sig->prev_utime = sig->prev_stime = cputime_zero;
+#endif
 	sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
 	sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
 	sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
@@ -1066,8 +1069,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->gtime = cputime_zero;
 	p->utimescaled = cputime_zero;
 	p->stimescaled = cputime_zero;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
 	p->prev_utime = cputime_zero;
 	p->prev_stime = cputime_zero;
+#endif
 
 	p->default_timer_slack_ns = current->timer_slack_ns;
 
diff --git a/kernel/futex.c b/kernel/futex.c
index 4949d336d88..fb65e822fc4 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -150,7 +150,8 @@ static struct futex_hash_bucket *hash_futex(union futex_key *key)
  */
 static inline int match_futex(union futex