Merge branch 'master' into gfs2

41 files changed, 1380 insertions, 734 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index d62ec66c1af..aacaafb28b9 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -8,7 +8,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
 	    signal.o sys.o kmod.o workqueue.o pid.o \
 	    rcupdate.o extable.o params.o posix-timers.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
-	    hrtimer.o rwsem.o
+	    hrtimer.o rwsem.o latency.o
 
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
 obj-y += time/
@@ -49,7 +49,7 @@ obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
-obj-$(CONFIG_TASKSTATS) += taskstats.o
+obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
 
 ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/acct.c b/kernel/acct.c
index 2a7c933651c..0aad5ca36a8 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -483,10 +483,14 @@ static void do_acct_process(struct file *file)
 	ac.ac_ppid = current->parent->tgid;
 #endif
 
-	read_lock(&tasklist_lock);	/* pin current->signal */
+	mutex_lock(&tty_mutex);
+	/* FIXME: Whoever is responsible for current->signal locking needs
+	   to use the same locking all over the kernel and document it */
+	read_lock(&tasklist_lock);
 	ac.ac_tty = current->signal->tty ?
 		old_encode_dev(tty_devnum(current->signal->tty)) : 0;
 	read_unlock(&tasklist_lock);
+	mutex_unlock(&tty_mutex);
 
 	spin_lock_irq(&current->sighand->siglock);
 	ac.ac_utime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_utime)));
@@ -598,33 +602,3 @@ void acct_process(void)
 	do_acct_process(file);
 	fput(file);
 }
-
-
-/**
- * acct_update_integrals - update mm integral fields in task_struct
- * @tsk: task_struct for accounting
- */
-void acct_update_integrals(struct task_struct *tsk)
-{
-	if (likely(tsk->mm)) {
-		long delta =
-			cputime_to_jiffies(tsk->stime) - tsk->acct_stimexpd;
-
-		if (delta == 0)
-			return;
-		tsk->acct_stimexpd = tsk->stime;
-		tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
-		tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
-	}
-}
-
-/**
- * acct_clear_integrals - clear the mm integral fields in task_struct
- * @tsk: task_struct whose accounting fields are cleared
- */
-void acct_clear_integrals(struct task_struct *tsk)
-{
-	tsk->acct_stimexpd = 0;
-	tsk->acct_rss_mem1 = 0;
-	tsk->acct_vm_mem1 = 0;
-}
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index fb83c5cb8c3..10514763175 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -817,6 +817,8 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 		audit_log_format(ab, " success=%s exit=%ld", 
 				 (context->return_valid==AUDITSC_SUCCESS)?"yes":"no",
 				 context->return_code);
+
+	mutex_lock(&tty_mutex);
 	if (tsk->signal && tsk->signal->tty && tsk->signal->tty->name)
 		tty = tsk->signal->tty->name;
 	else
@@ -838,6 +840,9 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 		  context->gid,
 		  context->euid, context->suid, context->fsuid,
 		  context->egid, context->sgid, context->fsgid, tty);
+
+	mutex_unlock(&tty_mutex);
+
 	audit_log_task_info(ab, tsk);
 	if (context->filterkey) {
 		audit_log_format(ab, " key=");
diff --git a/kernel/capability.c b/kernel/capability.c
index c7685ad00a9..edb845a6e84 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -133,7 +133,7 @@ static inline int cap_set_all(kernel_cap_t *effective,
      int found = 0;
 
      do_each_thread(g, target) {
-             if (target == current || target->pid == 1)
+             if (target == current || is_init(target))
                      continue;
              found = 1;
 	     if (security_capset_check(target, effective, inheritable,
diff --git a/kernel/compat.c b/kernel/compat.c
index 126dee9530a..b4fbd838cd7 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -22,9 +22,12 @@
 #include <linux/security.h>
 #include <linux/timex.h>
 #include <linux/migrate.h>
+#include <linux/posix-timers.h>
 
 #include <asm/uaccess.h>
 
+extern void sigset_from_compat(sigset_t *set, compat_sigset_t *compat);
+
 int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts)
 {
 	return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) ||
@@ -601,6 +604,30 @@ long compat_sys_clock_getres(clockid_t which_clock,
 	return err;
 } 
 
+static long compat_clock_nanosleep_restart(struct restart_block *restart)
+{
+	long err;
+	mm_segment_t oldfs;
+	struct timespec tu;
+	struct compat_timespec *rmtp = (struct compat_timespec *)(restart->arg1);
+
+	restart->arg1 = (unsigned long) &tu;
+	oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	err = clock_nanosleep_restart(restart);
+	set_fs(oldfs);
+
+	if ((err == -ERESTART_RESTARTBLOCK) && rmtp &&
+	    put_compat_timespec(&tu, rmtp))
+		return -EFAULT;
+
+	if (err == -ERESTART_RESTARTBLOCK) {
+		restart->fn = compat_clock_nanosleep_restart;
+		restart->arg1 = (unsigned long) rmtp;
+	}
+	return err;
+}
+
 long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
 			    struct compat_timespec __user *rqtp,
 			    struct compat_timespec __user *rmtp)
@@ -608,6 +635,7 @@ long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
 	long err;
 	mm_segment_t oldfs;
 	struct timespec in, out; 
+	struct restart_block *restart;
 
 	if (get_compat_timespec(&in, rqtp)) 
 		return -EFAULT;
@@ -618,9 +646,16 @@ long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
 				  (struct timespec __user *) &in,
 				  (struct timespec __user *) &out);
 	set_fs(oldfs);
+
 	if ((err == -ERESTART_RESTARTBLOCK) && rmtp &&
 	    put_compat_timespec(&out, rmtp))
 		return -EFAULT;
+
+	if (err == -ERESTART_RESTARTBLOCK) {
+		restart = &current_thread_info()->restart_block;
+		restart->fn = compat_clock_nanosleep_restart;
+		restart->arg1 = (unsigned long) rmtp;
+	}
 	return err;	
 } 
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 1b32c2c04c1..9d850ae13b1 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -240,7 +240,7 @@ static struct super_block *cpuset_sb;
  * A cpuset can only be deleted if both its 'count' of using tasks
  * is zero, and its list of 'children' cpusets is empty.  Since all
  * tasks in the system use _some_ cpuset, and since there is always at
- * least one task in the system (init, pid == 1), therefore, top_cpuset
+ * least one task in the system (init), therefore, top_cpuset
  * always has either children cpusets and/or using tasks.  So we don't
  * need a special hack to ensure that top_cpuset cannot be deleted.
  *
@@ -377,7 +377,7 @@ static int cpuset_fill_super(struct super_block *sb, void *unused_data,
 		inode->i_op = &simple_dir_inode_operations;
 		inode->i_fop = &simple_dir_operations;
 		/* directories start off with i_nlink == 2 (for "." entry) */
-		inode->i_nlink++;
+		inc_nlink(inode);
 	} else {
 		return -ENOMEM;
 	}
@@ -912,6 +912,10 @@ static int update_nodemask(struct cpuset *cs, char *buf)
 	int fudge;
 	int retval;
 
+	/* top_cpuset.mems_allowed tracks node_online_map; it's read-only */
+	if (cs == &top_cpuset)
+		return -EACCES;
+
 	trialcs = *cs;
 	retval = nodelist_parse(buf, trialcs.mems_allowed);
 	if (retval < 0)
@@ -1221,7 +1225,12 @@ static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf)
 
 	task_lock(tsk);
 	oldcs = tsk->cpuset;
-	if (!oldcs) {
+	/*
+	 * After getting 'oldcs' cpuset ptr, be sure still not exiting.
+	 * If 'oldcs' might be the top_cpuset due to the_top_cpuset_hack
+	 * then fail this attach_task(), to avoid breaking top_cpuset.count.
+	 */
+	if (tsk->flags & PF_EXITING) {
 		task_unlock(tsk);
 		mutex_unlock(&callback_mutex);
 		put_task_struct(tsk);
@@ -1556,7 +1565,7 @@ static int cpuset_create_file(struct dentry *dentry, int mode)
 		inode->i_fop = &simple_dir_operations;
 
 		/* start off with i_nlink == 2 (for "." entry) */
-		inode->i_nlink++;
+		inc_nlink(inode);
 	} else if (S_ISREG(mode)) {
 		inode->i_size = 0;
 		inode->i_fop = &cpuset_file_operations;
@@ -1589,7 +1598,7 @@ static int cpuset_create_dir(struct cpuset *cs, const char *name, int mode)
 	error = cpuset_create_file(dentry, S_IFDIR | mode);
 	if (!error) {
 		dentry->d_fsdata = cs;
-		parent->d_inode->i_nlink++;
+		inc_nlink(parent->d_inode);
 		cs->dentry = dentry;
 	}
 	dput(dentry);
@@ -2024,7 +2033,7 @@ int __init cpuset_init(void)
 	}
 	root = cpuset_mount->mnt_sb->s_root;
 	root->d_fsdata = &top_cpuset;
-	root->d_inode->i_nlink++;
+	inc_nlink(root->d_inode);
 	top_cpuset.dentry = root;
 	root->d_inode->i_op = &cpuset_dir_inode_operations;
 	number_of_cpusets = 1;
@@ -2036,33 +2045,104 @@ out:
 	return err;
 }
 
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_MEMORY_HOTPLUG)
 /*
- * The top_cpuset tracks what CPUs and Memory Nodes are online,
- * period.  This is necessary in order to make cpusets transparent
- * (of no affect) on systems that are actively using CPU hotplug
- * but making no active use of cpusets.
- *
- * This handles CPU hotplug (cpuhp) events.  If someday Memory
- * Nodes can be hotplugged (dynamically changing node_online_map)
- * then we should handle that too, perhaps in a similar way.
+ * If common_cpu_mem_hotplug_unplug(), below, unplugs any CPUs
+ * or memory nodes, we need to walk over the cpuset hierarchy,
+ * removing that CPU or node from all cpusets.  If this removes the
+ * last CPU or node from a cpuset, then the guarantee_online_cpus()
+ * or guarantee_online_mems() code will use that emptied cpusets
+ * parent online CPUs or nodes.  Cpusets that were already empty of
+ * CPUs or nodes are left empty.
+ *
+ * This routine is intentionally inefficient in a couple of regards.
+ * It will check all cpusets in a subtree even if the top cpuset of
+ * the subtree has no offline CPUs or nodes.  It checks both CPUs and
+ * nodes, even though the caller could have been coded to know that
+ * only one of CPUs or nodes needed to be checked on a given call.
+ * This was done to minimize text size rather than cpu cycles.
+ *
+ * Call with both manage_mutex and callback_mutex held.
+ *
+ * Recursive, on depth of cpuset subtree.
  */
 
-#ifdef CONFIG_HOTPLUG_CPU
-static int cpuset_handle_cpuhp(struct notifier_block *nb,
-				unsigned long phase, void *cpu)
+static void guarantee_online_cpus_mems_in_subtree(const struct cpuset *cur)
+{
+	struct cpuset *c;
+
+	/* Each of our child cpusets mems must be online */
+	list_for_each_entry(c, &cur->children, sibling) {
+		guarantee_online_cpus_mems_in_subtree(c);
+		if (!cpus_empty(c->cpus_allowed))
+			guarantee_online_cpus(c, &c->cpus_allowed);
+		if (!nodes_empty(c->mems_allowed))
+			guarantee_online_mems(c, &c->mems_allowed);
+	}
+}
+
+/*
+ * The cpus_allowed and mems_allowed nodemasks in the top_cpuset track
+ * cpu_online_map and node_online_map.  Force the top cpuset to track
+ * whats online after any CPU or memory node hotplug or unplug event.
+ *
+ * To ensure that we don't remove a CPU or node from the top cpuset
+ * that is currently in use by a child cpuset (which would violate
+ * the rule that cpusets must be subsets of their parent), we first
+ * call the recursive routine guarantee_online_cpus_mems_in_subtree().
+ *
+ * Since there are two callers of this routine, one for CPU hotplug
+ * events and one for memory node hotplug events, we could have coded
+ * two separate routines here.  We code it as a single common routine
+ * in order to minimize text size.
+ */
+
+static void common_cpu_mem_hotplug_unplug(void)
 {
 	mutex_lock(&manage_mutex);
 	mutex_lock(&callback_mutex);
 
+	guarantee_online_cpus_mems_in_subtree(&top_cpuset);
 	top_cpuset.cpus_allowed = cpu_online_map;
+	top_cpuset.mems_allowed = node_online_map;
 
 	mutex_unlock(&callback_mutex);
 	mutex_unlock(&manage_mutex);
+}
+#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * The top_cpuset tracks what CPUs and Memory Nodes are online,
+ * period.  This is necessary in order to make cpusets transparent
+ * (of no affect) on systems that are actively using CPU hotplug
+ * but making no active use of cpusets.
+ *
+ * This routine ensures that top_cpuset.cpus_allowed tracks
+ * cpu_online_map on each CPU hotplug (cpuhp) event.
+ */
 
+static int cpuset_handle_cpuhp(struct notifier_block *nb,
+				unsigned long phase, void *cpu)
+{
+	common_cpu_mem_hotplug_unplug();
 	return 0;
 }
 #endif
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+/*
+ * Keep top_cpuset.mems_allowed tracking node_online_map.
+ * Call this routine anytime after you change node_online_map.
+ * See also the previous routine cpuset_handle_cpuhp().
+ */
+
+void cpuset_track_online_nodes()
+{
+	common_cpu_mem_hotplug_unplug();
+}
+#endif
+
 /**
  * cpuset_init_smp - initialize cpus_allowed
  *
diff --git a/kernel/exit.c b/kernel/exit.c
index d891883420f..3b47f26985f 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -18,6 +18,7 @@
 #include <linux/security.h>
 #include <linux/cpu.h>
 #include <linux/acct.h>
+#include <linux/tsacct_kern.h>
 #include <linux/file.h>
 #include <linux/binfmts.h>
 #include <linux/ptrace.h>
@@ -38,6 +39,7 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/audit.h> /* for audit_free() */
 #include <linux/resource.h>
+#include <linux/blkdev.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -219,7 +221,7 @@ static int will_become_orphaned_pgrp(int pgrp, struct task_struct *ignored_task)
 	do_each_task_pid(pgrp, PIDTYPE_PGID, p) {
 		if (p == ignored_task
 				|| p->exit_state
-				|| p->real_parent->pid == 1)
+				|| is_init(p->real_parent))
 			continue;
 		if (process_group(p->real_parent) != pgrp
 			    && p->real_parent->signal->session == p->signal->session) {
@@ -249,17 +251,6 @@ static int has_stopped_jobs(int pgrp)
 	do_each_task_pid(pgrp, PIDTYPE_PGID, p) {
 		if (p->state != TASK_STOPPED)
 			continue;
-
-		/* If p is stopped by a debugger on a signal that won't
-		   stop it, then don't count p as stopped.  This isn't
-		   perfect but it's a good approximation.  */
-		if (unlikely (p->ptrace)
-		    && p->exit_code != SIGSTOP
-		    && p->exit_code != SIGTSTP
-		    && p->exit_code != SIGTTOU
-		    && p->exit_code != SIGTTIN)
-			continue;
-
 		retval = 1;
 		break;
 	} while_each_task_pid(pgrp, PIDTYPE_PGID, p);
@@ -292,9 +283,7 @@ static void reparent_to_init(void)
 	/* Set the exit signal to SIGCHLD so we signal init on exit */
 	current->exit_signal = SIGCHLD;
 
-	if ((current->policy == SCHED_NORMAL ||
-			current->policy == SCHED_BATCH)
-				&& (task_nice(current) < 0))
+	if (!has_rt_policy(current) && (task_nice(current) < 0))
 		set_user_nice(current, 0);
 	/* cpus_allowed? */
 	/* rt_priority? */
@@ -487,6 +476,18 @@ void fastcall put_files_struct(struct files_struct *files)
 
 EXPORT_SYMBOL(put_files_struct);
 
+void reset_files_struct(struct task_struct *tsk, struct files_struct *files)
+{
+	struct files_struct *old;
+
+	old = tsk->files;
+	task_lock(tsk);
+	tsk->files = files;
+	task_unlock(tsk);
+	put_files_struct(old);
+}
+EXPORT_SYMBOL(reset_files_struct);
+
 static inline void __exit_files(struct task_struct *tsk)
 {
 	struct files_struct * files = tsk->files;
@@ -954,15 +955,15 @@ fastcall NORET_TYPE void do_exit(long code)
 	if (tsk->splice_pipe)
 		__free_pipe_info(tsk->splice_pipe);
 
-	/* PF_DEAD causes final put_task_struct after we schedule. */
 	preempt_disable();
-	BUG_ON(tsk->flags & PF_DEAD);
-	tsk->flags |= PF_DEAD;
+	/* causes final put_task_struct in finish_task_switch(). */
+	tsk->state = TASK_DEAD;
 
 	schedule();
 	BUG();
 	/* Avoid "noreturn function does return".  */
-	for (;;) ;
+	for (;;)
+		cpu_relax();	/* For when BUG is null */
 }
 
 EXPORT_SYMBOL_GPL(do_exit);
@@ -971,7 +972,7 @@ NORET_TYPE void complete_and_exit(struct completion *comp, long code)
 {
 	if (comp)
 		complete(comp);
-	
+
 	do_exit(code);
 }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index a0dad84567c..89f666491d1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -42,6 +42,7 @@
 #include <linux/profile.h>
 #include <linux/rmap.h>
 #include <linux/acct.h>
+#include <linux/tsacct_kern.h>
 #include <linux/cn_proc.h>
 #include <linux/delayacct.h>
 #include <linux/taskstats_kern.h>
@@ -183,7 +184,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 	/* One for us, one for whoever does the "release_task()" (usually parent) */
 	atomic_set(&tsk->usage,2);
 	atomic_set(&tsk->fs_excl, 0);
+#ifdef CONFIG_BLK_DEV_IO_TRACE
 	tsk->btrace_seq = 0;
+#endif
 	tsk->splice_pipe = NULL;
 	return tsk;
 }
@@ -1061,7 +1064,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
 	p->irq_events = 0;
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+	p->hardirqs_enabled = 1;
+#else
 	p->hardirqs_enabled = 0;
+#endif
 	p->hardirq_enable_ip = 0;
 	p->hardirq_enable_event = 0;
 	p->hardirq_disable_ip = _THIS_IP_;
@@ -1144,7 +1151,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	/* Our parent execution domain becomes current domain
 	   These must match for thread signalling to apply */
-	   
 	p->parent_exec_id = p->self_exec_id;
 
 	/* ok, now we should be set up.. */
@@ -1167,6 +1173,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	/* Need tasklist lock for parent etc handling! */
 	write_lock_irq(&tasklist_lock);
 
+	/* for sys_ioprio_set(IOPRIO_WHO_PGRP) */
+	p->ioprio = current->ioprio;
+
 	/*
 	 * The task hasn't been attached yet, so its cpus_allowed mask will
 	 * not be changed, nor will its assigned CPU.
@@ -1226,11 +1235,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		}
 	}
 
-	/*
-	 * inherit ioprio
-	 */
-	p->ioprio = current->ioprio;
-
 	if (likely(p->pid)) {
 		add_parent(p);
 		if (unlikely(p->ptrace & PT_PTRACED))
diff --git a/kernel/futex.c b/kernel/futex.c
index 9d260e838cf..4b6770e9806 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -389,7 +389,7 @@ static struct task_struct * futex_find_get_task(pid_t pid)
 {
 	struct task_struct *p;
 
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	p = find_task_by_pid(pid);
 	if (!p)
 		goto out_unlock;
@@ -403,7 +403,7 @@ static struct task_struct * futex_find_get_task(pid_t pid)
 	}
 	get_task_struct(p);
 out_unlock:
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 
 	return p;
 }
@@ -1624,7 +1624,7 @@ sys_get_robust_list(int pid, struct robust_list_head __user **head_ptr,
 		struct task_struct *p;
 
 		ret = -ESRCH;
-		read_lock(&tasklist_lock);
+		rcu_read_lock();
 		p = find_task_by_pid(pid);
 		if (!p)
 			goto err_unlock;
@@ -1633,7 +1633,7 @@ sys_get_robust_list(int pid, struct robust_list_head __user **head_ptr,
 				!capable(CAP_SYS_PTRACE))
 			goto err_unlock;
 		head = p->robust_list;
-		read_unlock(&tasklist_lock);
+		rcu_read_unlock();
 	}
 
 	if (put_user(sizeof(*head), len_ptr))
@@ -1641,7 +1641,7 @@ sys_get_robust_list(int pid, struct robust_list_head __user **head_ptr,
 	return put_user(head, head_ptr);
 
 err_unlock:
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 
 	return ret;
 }
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 21c38a7e666..d0ba190dfeb 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -693,7 +693,7 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
 	return t->task == NULL;
 }
 
-static long __sched nanosleep_restart(struct restart_block *restart)
+long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
 {
 	struct hrtimer_sleeper t;
 	struct timespec __user *rmtp;
@@ -702,13 +702,13 @@ static long __sched nanosleep_restart(struct restart_block *restart)
 
 	restart->fn = do_no_restart_syscall;
 
-	hrtimer_init(&t.timer, restart->arg3, HRTIMER_ABS);
-	t.timer.expires.tv64 = ((u64)restart->arg1 << 32) | (u64) restart->arg0;
+	hrtimer_init(&t.timer, restart->arg0, HRTIMER_ABS);
+	t.timer.expires.tv64 = ((u64)restart->arg3 << 32) | (u64) restart->arg2;
 
 	if (do_nanosleep(&t, HRTIMER_ABS))
 		return 0;
 
-	rmtp = (struct timespec __user *) restart->arg2;
+	rmtp = (struct timespec __user *) restart->arg1;
 	if (rmtp) {
 		time = ktime_sub(t.timer.expires, t.timer.base->get_time());
 		if (time.tv64 <= 0)
@@ -718,7 +718,7 @@ static long __sched nanosleep_restart(struct restart_block *restart)
 			return -EFAULT;
 	}
 
-	restart->fn = nanosleep_restart;
+	restart->fn = hrtimer_nanosleep_restart;
 
 	/* The other values in restart are already filled in */
 	return -ERESTART_RESTARTBLOCK;
@@ -751,11 +751,11 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 	}
 
 	restart = &current_thread_info()->restart_block;
-	restart->fn = nanosleep_restart;
-	restart->arg0 = t.timer.expires.tv64 & 0xFFFFFFFF;
-	restart->arg1 = t.timer.expires.tv64 >> 32;
-	restart->arg2 = (unsigned long) rmtp;
-	restart->arg3 = (unsigned long) t.timer.base->index;
+	restart->fn = hrtimer_nanosleep_restart;
+	restart->arg0 = (unsigned long) t.timer.base->index;
+	restart->arg1 = (unsigned long) rmtp;
+	restart->arg2 = t.timer.expires.tv64 & 0xFFFFFFFF;
+	restart->arg3 = t.timer.expires.tv64 >> 32;
 
 	return -ERESTART_RESTARTBLOCK;
 }
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index ac1f850d493..736cb0bd498 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -40,10 +40,6 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 	spin_lock_irqsave(&desc->lock, flags);
 	irq_chip_set_defaults(chip);
 	desc->chip = chip;
-	/*
-	 * For compatibility only:
-	 */
-	desc->chip = chip;
 	spin_unlock_irqrestore(&desc->lock, flags);
 
 	return 0;
@@ -146,7 +142,7 @@ static void default_disable(unsigned int irq)
 	struct irq_desc *desc = irq_desc + irq;
 
 	if (!(desc->status & IRQ_DELAYED_DISABLE))
-		irq_desc[irq].chip->mask(irq);
+		desc->chip->mask(irq);
 }
 
 /*
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 50087ecf337..fcdd5d2bc3f 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -40,7 +40,7 @@ struct resource crashk_res = {
 
 int kexec_should_crash(struct task_struct *p)
 {
-	if (in_interrupt() || !p->pid || p->pid == 1 || panic_on_oops)
+	if (in_interrupt() || !p->pid || is_init(p) || panic_on_oops)
 		return 1;
 	return 0;
 }
@@ -995,7 +995,8 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
 	image = xchg(dest_image, image);
 
 out:
-	xchg(&kexec_lock, 0); /* Release the mutex */
+	locked = xchg(&kexec_lock, 0); /* Release the mutex */
+	BUG_ON(!locked);
 	kimage_free(image);
 
 	return result;
@@ -1061,7 +1062,8 @@ void crash_kexec(struct pt_regs *regs)
 			machine_crash_shutdown(&fixed_regs);
 			machine_kexec(kexec_crash_image);
 		}
-		xchg(&kexec_lock, 0);
+		locked = xchg(&kexec_lock, 0);
+		BUG_ON(!locked);
 	}
 }
 
diff --git a/kernel/kfifo.c b/kernel/kfifo.c
index 64ab045c3d9..5d1d907378a 100644
--- a/kernel/kfifo.c
+++ b/kernel/kfifo.c
@@ -122,6 +122,13 @@ unsigned int __kfifo_put(struct kfifo *fifo,
 
 	len = min(len, fifo->size - fifo->in + fifo->out);
 
+	/*
+	 * Ensure that we sample the fifo->out index -before- we
+	 * start putting bytes into the kfifo.
+	 */
+
+	smp_mb();
+
 	/* first put the data starting from fifo->in to buffer end */
 	l = min(len, fifo->size - (fifo->in & (fifo->size - 1)));
 	memcpy(fifo->buffer + (fifo->in & (fifo->size - 1)), buffer, l);
@@ -129,6 +136,13 @@ unsigned int __kfifo_put(struct kfifo *fifo,
 	/* then put the rest (if any) at the beginning of the buffer */
 	memcpy(fifo->buffer, buffer + l, len - l);
 
+	/*
+	 * Ensure that we add the bytes to the kfifo -before-
+	 * we update the fifo->in index.
+	 */
+
+	smp_wmb();
+
 	fifo->in += len;