37 files changed, 5564 insertions, 2915 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index dcf6789bf547..9943202b4355 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -4,7 +4,7 @@
 
 obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
             cpu.o exit.o itimer.o time.o softirq.o resource.o \
-            sysctl.o capability.o ptrace.o timer.o user.o \
+            sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.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 \
@@ -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-$(CONFIG_FREEZER) += freezer.o
@@ -97,6 +98,7 @@ obj-$(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/cpuset.c b/kernel/cpuset.c
index b5cb469d2545..3cf2183b472d 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 f7864ac2ecc1..80ae941cfd2e 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;
@@ -978,6 +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.
          */
@@ -1205,6 +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
@@ -1220,20 +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 166b8c49257c..3d6f121bbe8a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -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/hw_breakpoint.c b/kernel/hw_breakpoint.c
new file mode 100644
index 000000000000..cf5ee1628411
--- /dev/null
+++ b/kernel/hw_breakpoint.c
@@ -0,0 +1,423 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) 2007 Alan Stern
+ * Copyright (C) IBM Corporation, 2009
+ * Copyright (C) 2009, Frederic Weisbecker <fweisbec@gmail.com>
+ *
+ * Thanks to Ingo Molnar for his many suggestions.
+ *
+ * Authors: Alan Stern <stern@rowland.harvard.edu>
+ *          K.Prasad <prasad@linux.vnet.ibm.com>
+ *          Frederic Weisbecker <fweisbec@gmail.com>
+ */
+
+/*
+ * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility,
+ * using the CPU's debug registers.
+ * This file contains the arch-independent routines.
+ */
+
+#include <linux/irqflags.h>
+#include <linux/kallsyms.h>
+#include <linux/notifier.h>
+#include <linux/kprobes.h>
+#include <linux/kdebug.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+
+#include <linux/hw_breakpoint.h>
+
+/*
+ * Constraints data
+ */
+
+/* Number of pinned cpu breakpoints in a cpu */
+static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned);
+
+/* Number of pinned task breakpoints in a cpu */
+static DEFINE_PER_CPU(unsigned int, task_bp_pinned[HBP_NUM]);
+
+/* Number of non-pinned cpu/task breakpoints in a cpu */
+static DEFINE_PER_CPU(unsigned int, nr_bp_flexible);
+
+/* Gather the number of total pinned and un-pinned bp in a cpuset */
+struct bp_busy_slots {
+        unsigned int pinned;
+        unsigned int flexible;
+};
+
+/* Serialize accesses to the above constraints */
+static DEFINE_MUTEX(nr_bp_mutex);
+
+/*
+ * Report the maximum number of pinned breakpoints a task
+ * have in this cpu
+ */
+static unsigned int max_task_bp_pinned(int cpu)
+{
+        int i;
+        unsigned int *tsk_pinned = per_cpu(task_bp_pinned, cpu);
+
+        for (i = HBP_NUM -1; i >= 0; i--) {
+                if (tsk_pinned[i] > 0)
+                        return i + 1;
+        }
+
+        return 0;
+}
+
+/*
+ * Report the number of pinned/un-pinned breakpoints we have in
+ * a given cpu (cpu > -1) or in all of them (cpu = -1).
+ */
+static void fetch_bp_busy_slots(struct bp_busy_slots *slots, int cpu)
+{
+        if (cpu >= 0) {
+                slots->pinned = per_cpu(nr_cpu_bp_pinned, cpu);
+                slots->pinned += max_task_bp_pinned(cpu);
+                slots->flexible = per_cpu(nr_bp_flexible, cpu);
+
+                return;
+        }
+
+        for_each_online_cpu(cpu) {
+                unsigned int nr;
+
+                nr = per_cpu(nr_cpu_bp_pinned, cpu);
+                nr += max_task_bp_pinned(cpu);
+
+                if (nr > slots->pinned)
+                        slots->pinned = nr;
+
+                nr = per_cpu(nr_bp_flexible, cpu);
+
+                if (nr > slots->flexible)
+                        slots->flexible = nr;
+        }
+}
+
+/*
+ * Add a pinned breakpoint for the given task in our constraint table
+ */
+static void toggle_bp_task_slot(struct task_struct *tsk, int cpu, bool enable)
+{
+        int count = 0;
+        struct perf_event *bp;
+        struct perf_event_context *ctx = tsk->perf_event_ctxp;
+        unsigned int *tsk_pinned;
+        struct list_head *list;
+        unsigned long flags;
+
+        if (WARN_ONCE(!ctx, "No perf context for this task"))
+                return;
+
+        list = &ctx->event_list;
+
+        spin_lock_irqsave(&ctx->lock, flags);
+
+        /*
+         * The current breakpoint counter is not included in the list
+         * at the open() callback time
+         */
+        list_for_each_entry(bp, list, event_entry) {
+                if (bp->attr.type == PERF_TYPE_BREAKPOINT)
+                        count++;
+        }
+
+        spin_unlock_irqrestore(&ctx->lock, flags);
+
+        if (WARN_ONCE(count < 0, "No breakpoint counter found in the counter list"))
+                return;
+
+        tsk_pinned = per_cpu(task_bp_pinned, cpu);
+        if (enable) {
+                tsk_pinned[count]++;
+                if (count > 0)
+                        tsk_pinned[count-1]--;
+        } else {
+                tsk_pinned[count]--;
+                if (count > 0)
+                        tsk_pinned[count-1]++;
+        }
+}
+
+/*
+ * Add/remove the given breakpoint in our constraint table
+ */
+static void toggle_bp_slot(struct perf_event *bp, bool enable)
+{
+        int cpu = bp->cpu;
+        struct task_struct *tsk = bp->ctx->task;
+
+        /* Pinned counter task profiling */
+        if (tsk) {
+                if (cpu >= 0) {
+                        toggle_bp_task_slot(tsk, cpu, enable);
+                        return;
+                }
+
+                for_each_online_cpu(cpu)
+                        toggle_bp_task_slot(tsk, cpu, enable);
+                return;
+        }
+
+        /* Pinned counter cpu profiling */
+        if (enable)
+                per_cpu(nr_cpu_bp_pinned, bp->cpu)++;
+        else
+                per_cpu(nr_cpu_bp_pinned, bp->cpu)--;
+}
+
+/*
+ * Contraints to check before allowing this new breakpoint counter:
+ *
+ *  == Non-pinned counter == (Considered as pinned for now)
+ *
+ *   - If attached to a single cpu, check:
+ *
+ *       (per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ *           + max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
+ *
+ *       -> If there are already non-pinned counters in this cpu, it means
+ *          there is already a free slot for them.
+ *          Otherwise, we check that the maximum number of per task
+ *          breakpoints (for this cpu) plus the number of per cpu breakpoint
+ *          (for this cpu) doesn't cover every registers.
+ *
+ *   - If attached to every cpus, check:
+ *
+ *       (per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ *           + max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
+ *
+ *       -> This is roughly the same, except we check the number of per cpu
+ *          bp for every cpu and we keep the max one. Same for the per tasks
+ *          breakpoints.
+ *
+ *
+ * == Pinned counter ==
+ *
+ *   - If attached to a single cpu, check:
+ *
+ *       ((per_cpu(nr_bp_flexible, cpu) > 1) + per_cpu(nr_cpu_bp_pinned, cpu)
+ *            + max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
+ *
+ *       -> Same checks as before. But now the nr_bp_flexible, if any, must keep
+ *          one register at least (or they will never be fed).
+ *
+ *   - If attached to every cpus, check:
+ *
+ *       ((per_cpu(nr_bp_flexible, *) > 1) + max(per_cpu(nr_cpu_bp_pinned, *))
+ *            + max(per_cpu(task_bp_pinned, *))) < HBP_NUM
+ */
+int reserve_bp_slot(struct perf_event *bp)
+{
+        struct bp_busy_slots slots = {0};
+        int ret = 0;
+
+        mutex_lock(&nr_bp_mutex);
+
+        fetch_bp_busy_slots(&slots, bp->cpu);
+
+        /* Flexible counters need to keep at least one slot */
+        if (slots.pinned + (!!slots.flexible) == HBP_NUM) {
+                ret = -ENOSPC;
+                goto end;
+        }
+
+        toggle_bp_slot(bp, true);
+
+end:
+        mutex_unlock(&nr_bp_mutex);
+
+        return ret;
+}
+
+void release_bp_slot(struct perf_event *bp)
+{
+        mutex_lock(&nr_bp_mutex);
+
+        toggle_bp_slot(bp, false);
+
+        mutex_unlock(&nr_bp_mutex);
+}
+
+
+int __register_perf_hw_breakpoint(struct perf_event *bp)
+{
+        int ret;
+
+        ret = reserve_bp_slot(bp);
+        if (ret)
+                return ret;
+
+        /*
+         * Ptrace breakpoints can be temporary perf events only
+         * meant to reserve a slot. In this case, it is created disabled and
+         * we don't want to check the params right now (as we put a null addr)
+         * But perf tools create events as disabled and we want to check
+         * the params for them.
+         * This is a quick hack that will be removed soon, once we remove
+         * the tmp breakpoints from ptrace
+         */
+        if (!bp->attr.disabled || bp->callback == perf_bp_event)
+                ret = arch_validate_hwbkpt_settings(bp, bp->ctx->task);
+
+        return ret;
+}
+
+int register_perf_hw_breakpoint(struct perf_event *bp)
+{
+        bp->callback = perf_bp_event;
+
+        return __register_perf_hw_breakpoint(bp);
+}
+
+/**
+ * register_user_hw_breakpoint - register a hardware breakpoint for user space
+ * @attr: breakpoint attributes
+ * @triggered: callback to trigger when we hit the breakpoint
+ * @tsk: pointer to 'task_struct' of the process to which the address belongs
+ */
+struct perf_event *
+register_user_hw_breakpoint(struct perf_event_attr *attr,
+                            perf_callback_t triggered,
+                            struct task_struct *tsk)
+{
+        return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered);
+}
+EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
+
+/**
+ * modify_user_hw_breakpoint - modify a user-space hardware breakpoint
+ * @bp: the breakpoint structure to modify
+ * @attr: new breakpoint attributes
+ * @triggered: callback to trigger when we hit the breakpoint
+ * @tsk: pointer to 'task_struct' of the process to which the address belongs
+ */
+struct perf_event *
+modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr,
+                          perf_callback_t triggered,
+                          struct task_struct *tsk)
+{
+        /*
+         * FIXME: do it without unregistering
+         * - We don't want to lose our slot
+         * - If the new bp is incorrect, don't lose the older one
+         */
+        unregister_hw_breakpoint(bp);
+
+        return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered);
+}
+EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint);
+
+/**
+ * unregister_hw_breakpoint - unregister a user-space hardware breakpoint
+ * @bp: the breakpoint structure to unregister
+ */
+void unregister_hw_breakpoint(struct perf_event *bp)
+{
+        if (!bp)
+                return;
+        perf_event_release_kernel(bp);
+}
+EXPORT_SYMBOL_GPL(unregister_hw_breakpoint);
+
+/**
+ * register_wide_hw_breakpoint - register a wide breakpoint in the kernel
+ * @attr: breakpoint attributes
+ * @triggered: callback to trigger when we hit the breakpoint
+ *
+ * @return a set of per_cpu pointers to perf events
+ */
+struct perf_event **
+register_wide_hw_breakpoint(struct perf_event_attr *attr,
+                            perf_callback_t triggered)
+{
+        struct perf_event **cpu_events, **pevent, *bp;
+        long err;
+        int cpu;
+
+        cpu_events = alloc_percpu(typeof(*cpu_events));
+        if (!cpu_events)
+                return ERR_PTR(-ENOMEM);
+
+        for_each_possible_cpu(cpu) {
+                pevent = per_cpu_ptr(cpu_events, cpu);
+                bp = perf_event_create_kernel_counter(attr, cpu, -1, triggered);
+
+                *pevent = bp;
+
+                if (IS_ERR(bp)) {
+                        err = PTR_ERR(bp);
+                        goto fail;
+                }
+        }
+
+        return cpu_events;
+
+fail:
+        for_each_possible_cpu(cpu) {
+                pevent = per_cpu_ptr(cpu_events, cpu);
+                if (IS_ERR(*pevent))
+                        break;
+                unregister_hw_breakpoint(*pevent);
+        }
+        free_percpu(cpu_events);
+        /* return the error if any */
+        return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint);
+
+/**
+ * unregister_wide_hw_breakpoint - unregister a wide breakpoint in the kernel
+ * @cpu_events: the per cpu set of events to unregister
+ */
+void unregister_wide_hw_breakpoint(struct perf_event **cpu_events)
+{
+        int cpu;
+        struct perf_event **pevent;
+
+        for_each_possible_cpu(cpu) {
+                pevent = per_cpu_ptr(cpu_events, cpu);
+                unregister_hw_breakpoint(*pevent);
+        }
+        free_percpu(cpu_events);
+}
+EXPORT_SYMBOL_GPL(unregister_wide_hw_breakpoint);
+
+static struct notifier_block hw_breakpoint_exceptions_nb = {
+        .notifier_call = hw_breakpoint_exceptions_notify,
+        /* we need to be notified first */
+        .priority = 0x7fffffff
+};
+
+static int __init init_hw_breakpoint(void)
+{
+        return register_die_notifier(&hw_breakpoint_exceptions_nb);
+}
+core_initcall(init_hw_breakpoint);
+
+
+struct pmu perf_ops_bp = {
+        .enable         = arch_install_hw_breakpoint,
+        .disable        = arch_uninstall_hw_breakpoint,
+        .read           = hw_breakpoint_pmu_read,
+        .unthrottle     = hw_breakpoint_pmu_unthrottle
+};
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 8b6b8b697c68..8e5288a8a355 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -181,6 +181,7 @@ unsigned long kallsyms_lookup_name(const char *name)
         }
         return module_kallsyms_lookup_name(name);
 }
+EXPORT_SYMBOL_GPL(kallsyms_lookup_name);
 
 int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
                                       unsigned long),
diff --git a/kernel/kgdb.c b/kernel/kgdb.c
index 9147a3190c9d..7d7014634022 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -870,7 +870,7 @@ static void gdb_cmd_getregs(struct kgdb_state *ks)
 
         /*
          * All threads that don't have debuggerinfo should be
-         * in __schedule() sleeping, since all other CPUs
+         * in schedule() sleeping, since all other CPUs
          * are in kgdb_wait, and thus have debuggerinfo.
          */
         if (local_debuggerinfo) {
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 1494e85b35f2..e5342a344c43 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -90,6 +90,9 @@ static spinlock_t *kretprobe_table_lock_ptr(unsigned long hash)
  */
 static struct kprobe_blackpoint kprobe_blacklist[] = {
         {"preempt_schedule",},
+        {"native_get_debugreg",},
+        {"irq_entries_start",},
+        {"common_interrupt",},
         {NULL}    /* Terminator */
 };
 
@@ -673,6 +676,40 @@ static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p)
         return (kprobe_opcode_t *)(((char *)addr) + p->offset);
 }
 
+/* Check passed kprobe is valid and return kprobe in kprobe_table. */
+static struct kprobe * __kprobes __get_valid_kprobe(struct kprobe *p)
+{
+        struct kprobe *old_p, *list_p;
+
+        old_p = get_kprobe(p->addr);
+        if (unlikely(!old_p))
+                return NULL;
+
+        if (p != old_p) {
+                list_for_each_entry_rcu(list_p, &old_p->list, list)
+                        if (list_p == p)
+                        /* kprobe p is a valid probe */
+                                goto valid;
+                return NULL;
+        }
+valid:
+        return old_p;
+}
+
+/* Return error if the kprobe is being re-registered */
+static inline int check_kprobe_rereg(struct kprobe *p)
+{
+        int ret = 0;
+        struct kprobe *old_p;
+
+        mutex_lock(&kprobe_mutex);
+        old_p = __get_valid_kprobe(p);
+        if (old_p)
+                ret = -EINVAL;
+        mutex_unlock(&kprobe_mutex);
+        return ret;
+}
+
 int __kprobes register_kprobe(struct kprobe *p)
 {
         int ret = 0;
@@ -685,6 +722,10 @@ int __kprobes register_kprobe(struct kprobe *p)
                 return -EINVAL;
         p->addr = addr;
 
+        ret = check_kprobe_rereg(p);
+        if (ret)
+                return ret;
+
         preempt_disable();
         if (!kernel_text_address((unsigned long) p->addr) ||
             in_kprobes_functions((unsigned long) p->addr)) {
@@ -754,26 +795,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(register_kprobe);
 
-/* Check passed kprobe is valid and return kprobe in kprobe_table. */
-static struct kprobe * __kprobes __get_valid_kprobe(struct kprobe *p)
-{
-        struct kprobe *old_p, *list_p;
-
-        old_p = get_kprobe(p->addr);
-        if (unlikely(!old_p))
-                return NULL;
-
-        if (p != old_p) {
-                list_for_each_entry_rcu(list_p, &old_p->list, list)
-                        if (list_p == p)
-                        /* kprobe p is a valid probe */
-                                goto valid;
-                return NULL;
-        }
-valid:
-        return old_p;
-}
-
 /*
  * Unregister a kprobe without a scheduler synchronization.
  */
@@ -1141,6 +1162,13 @@ static void __kprobes kill_kprobe(struct kprobe *p)
         arch_remove_kprobe(p);
 }
 
+void __kprobes dump_kprobe(struct kprobe *kp)
+{
+        printk(KERN_WARNING "Dumping kprobe:\n");
+        printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n",
+               kp->symbol_name, kp->addr, kp->offset);
+}
+
 /* Module notifier call back, checking kprobes on the module */
 static int __kprobes kprobes_module_callback(struct notifier_block *nb,
                                              unsigned long val, void *data)
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 9af56723c096..f5dcd36d3151 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -49,7 +49,7 @@
 #include "lockdep_internals.h"
 
 #define CREATE_TRACE_POINTS
-#include <trace/events/lockdep.h>
+#include <trace/events/lock.h>
 
 #ifdef CONFIG_PROVE_LOCKING
 int prove_locking = 1;
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 61d5aa5eced3..acd24e7643eb 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -558,7 +558,7 @@ EXPORT_SYMBOL(unregister_reboot_notifier);
 
 static ATOMIC_NOTIFIER_HEAD(die_chain);
 
-int notrace notify_die(enum die_val val, const char *str,
+int notrace __kprobes notify_die(enum die_val val, const char *str,
                struct pt_regs *regs, long err, int trap, int sig)
 {
         struct die_args args = {
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 7f29643c8985..6b7ddba1dd64 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -28,6 +28,8 @@
 #include <linux/anon_inodes.h>
 #include <linux/kernel_stat.h>
 #include <linux/perf_event.h>
+#include <linux/ftrace_event.h>
+#include <linux/hw_breakpoint.h>
 
 #include <asm/irq_regs.h>
 
@@ -244,6 +246,49 @@ static void perf_unpin_context(struct perf_event_context *ctx)
         put_ctx(ctx);
 }
 
+static inline u64 perf_clock(void)
+{
+        return cpu_clock(smp_processor_id());
+}
+
+/*
+ * Update the record of the current time in a context.
+ */
+static void update_context_time(struct perf_event_context *ctx)
+{
+        u64 now = perf_clock();
+
+        ctx->time += now - ctx->timestamp;
+        ctx->timestamp = now;
+}
+
+/*
+ * Update the total_time_enabled and total_time_running fields for a event.
+ */
+static void update_event_times(struct perf_event *event)
+{
+        struct perf_event_context *ctx = event->ctx;
+        u64 run_end;
+
+        if (event->state < PERF_EVENT_STATE_INACTIVE ||
+            event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
+                return;
+
+        if (ctx->is_active)
+                run_end = ctx->time;
+        else
+                run_end = event->tstamp_stopped;
+
+        event->total_time_enabled = run_end - event->tstamp_enabled;
+
+        if (event->state == PERF_EVENT_STATE_INACTIVE)
+                run_end = event->tstamp_stopped;
+        else
+                run_end = ctx->time;
+
+        event->total_time_running = run_end - event->tstamp_running;
+}
+
 /*
  * Add a event from the lists for its context.
  * Must be called with ctx->mutex and ctx->lock held.
@@ -292,6 +337,18 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
         if (event->group_leader != event)
                 event->group_leader->nr_siblings--;
 
+        update_event_times(event);
+
+        /*
+         * If event was in error state, then keep it
+         * that way, otherwise bogus counts will be
+         * returned on read(). The only way to get out
+         * of error state is by explicit re-enabling
+         * of the event
+         */
+        if (event->state > PERF_EVENT_STATE_OFF)
+                event->state = PERF_EVENT_STATE_OFF;
+
         /*
          * If this was a group event with sibling events then
          * upgrade the siblings to singleton events by adding them
@@ -445,50 +502,11 @@ retry:
          * can remove the event safely, if the call above did not
          * succeed.
          */
-        if (!list_empty(&event->group_entry)) {
+        if (!list_empty(&event->group_entry))
                 list_del_event(event, ctx);
-        }
         spin_unlock_irq(&ctx->lock);
 }
 
-static inline u64 perf_clock(void)
-{
-        return cpu_clock(smp_processor_id());
-}
-
-/*
- * Update the record of the current time in a context.
- */
-static void update_context_time(struct perf_event_context *ctx)
-{
-        u64 now = perf_clock();
-
-        ctx->time += now - ctx->timestamp;
-        ctx->timestamp = now;
-}
-
-/*
- * Update the total_time_enabled and total_time_running fields for a event.
- */
-static void update_event_times(struct perf_event *event)
-{
-        struct perf_event_context *ctx = event->ctx;
-        u64 run_end;
-
-        if (event->state < PERF_EVENT_STATE_INACTIVE ||
-            event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
-                return;
-
-        event->total_time_enabled = ctx->time - event->tstamp_enabled;
-
-        if (event->state == PERF_EVENT_STATE_INACTIVE)
-                run_end = event->tstamp_stopped;
-        else
-                run_end = ctx->time;
-
-        event->total_time_running = run_end - event->tstamp_running;
-}
-
 /*
  * Update total_time_enabled and total_time_running for all events in a group.
  */
@@ -1031,10 +1049,10 @@ void __perf_event_sched_out(struct perf_event_context *ctx,
         update_context_time(ctx);
 
         perf_disable();
-        if (ctx->nr_active)
+        if (ctx->nr_active) {
                 list_for_each_entry(event, &ctx->group_list, group_entry)
                         group_sched_out(event, cpuctx, ctx);
-
+        }
         perf_enable();
  out:
         spin_unlock(&ctx->lock);
@@ -1059,8 +1077,6 @@ static int context_equiv(struct perf_event_context *ctx1,
                 && !ctx1->pin_count && !ctx2->pin_count;
 }
 
-static void __perf_event_read(void *event);
-
 static void __perf_event_sync_stat(struct perf_event *event,
                                      struct perf_event *next_event)
 {
@@ -1078,8 +1094,8 @@ static void __perf_event_sync_stat(struct perf_event *event,
          */
         switch (event->state) {
         case PERF_EVENT_STATE_ACTIVE:
-                __perf_event_read(event);
-                break;
+                event->pmu->read(event);
+                /* fall-through */
 
         case PERF_EVENT_STATE_INACTIVE:
                 update_event_times(event);
@@ -1118,6 +1134,8 @@ static void perf_event_sync_stat(struct perf_event_context *ctx,
         if (!ctx->nr_stat)
                 return;
 
+        update_context_time(ctx);
+
         event = list_first_entry(&ctx->event_list,
                                    struct perf_event, event_entry);
 
@@ -1161,8 +1179,6 @@ void perf_event_task_sched_out(struct task_struct *task,
         if (likely(!ctx || !cpuctx->task_ctx))
                 return;
 
-        update_context_time(ctx);
-
         rcu_read_lock();
         parent = rcu_dereference(ctx->parent_ctx);
         next_ctx = next->perf_event_ctxp;
@@ -1515,7 +1531,6 @@ static void __perf_event_read(void *info)
         struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
         struct perf_event *event = info;
         struct perf_event_context *ctx = event->ctx;
-        unsigned long flags;
 
         /*
          * If this is a task context, we need to check whether it is
@@ -1527,12 +1542,12 @@ static void __perf_event_read(void *info)
         if (ctx->task && cpuctx->task_ctx != ctx)
                 return;
 
-        local_irq_save(flags);
-        if (ctx->is_active)
-                update_context_time(ctx);
-        event->pmu->read(event);
+        spin_lock(&ctx->lock);
+        update_context_time(ctx);
         update_event_times(event);
-        local_irq_restore(flags);
+        spin_unlock(&ctx->lock);
+
+        event->pmu->read(event);
 }
 
 static u64 perf_event_read(struct perf_event *event)
@@ -1545,7 +1560,13 @@ static u64 perf_event_read(struct perf_event *event)
                 smp_call_function_single(event->oncpu,
                                          __perf_event_read, event, 1);
         } else if (event->state == PERF_EVENT_STATE_INACTIVE) {
+                struct perf_event_context *ctx = event->ctx;
+                unsigned long flags;
+
+                spin_lock_irqsave(&ctx->lock, flags);
+                update_context_time(ctx);
                 update_event_times(event);
+                spin_unlock_irqrestore(&ctx->lock, flags);
         }
 
         return atomic64_read(&event->count);
@@ -1658,6 +1679,8 @@ static struct perf_event_context *find_get_context(pid_t pid, int cpu)
         return ERR_PTR(err);
 }
 
+static void perf_event_free_filter(struct perf_event *event);
+
 static void free_event_rcu(struct rcu_head *head)
 {
         struct perf_event *event;
@@ -1665,6 +1688,7 @@ static void free_event_rcu(struct rcu_head *head)
         event = container_of(head, struct perf_event, rcu_head);
         if (event->ns)
                 put_pid_ns(event->ns);
+        perf_event_free_filter(event);
         kfree(event);
 }
 
@@ -1696,16 +1720,10 @@ static void free_event(struct perf_event *event)
         call_rcu(&event->rcu_head, free_event_rcu);
 }
 
-/*
- * Called when the last reference to the file is gone.
- */
-static int perf_release(struct inode *inode, struct file *file)
+int perf_event_release_kernel(struct perf_event *event)
 {
-        struct perf_event *event = file->private_data;
         struct perf_event_context *ctx = event->ctx;
 
-        file->private_data = NULL;
-
         WARN_ON_ONCE(ctx->parent_ctx);
         mutex_lock(&ctx->mutex);
         perf_event_remove_from_context(event);
@@ -1720,6 +1738,19 @@ static int perf_release(struct inode *inode, struct file *file)
 
         return 0;
 }
+EXPORT_SYMBOL_GPL(perf_event_release_kernel);
+
+/*
+ * Called when the last reference to the file is gone.
+ */
+static int perf_release(struct inode *inode, struct file *file)
+{
+        struct perf_event *event = file->private_data;
+
+        file->private_data = NULL;
+
+        return perf_event_release_kernel(event);
+}
 
 static int perf_event_read_size(struct perf_event *event)
 {
@@ -1746,91 +1777,94 @@ static int perf_event_read_size(struct perf_event *event)
         return size;
 }
 
-static u64 perf_event_read_value(struct perf_event *event)
+u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
 {
         struct perf_event *child;
         u64 total = 0;
 
+        *enabled = 0;
+        *running = 0;
+
+        mutex_lock(&event->child_mutex);
         total += perf_event_read(event);
-        list_for_each_entry(child, &event->child_list, child_list)
+        *enabled += event->total_time_enabled +
+                        atomic64_read(&event->child_total_time_enabled);
+        *running += event->total_time_running +
+                        atomic64_read(&event->child_total_time_running);
+
+        list_for_each_entry(child, &event->child_list, child_list) {
                 total += perf_event_read(child);
+                *enabled += child->total_time_enabled;
+                *running += child->total_time_running;
+        }
+        mutex_unlock(&event->child_mutex);
 
         return total;
 }
-
-static int perf_event_read_entry(struct perf_event *event,
-                                   u64 read_format, char __user *buf)
-{
-        int n = 0, count = 0;
-        u64 values[2];
-
-        values[n++] = perf_event_read_value(event);
-        if (read_format & PERF_FORMAT_ID)
-                values[n++] = primary_event_id(event);
-
-        count = n * sizeof(u64);
-
-        if (copy_to_user(buf, values, count))
-                return -EFAULT;
-
-        return count;
-}
+EXPORT_SYMBOL_GPL(perf_event_read_value);
 
 static int perf_event_read_group(struct perf_event *event,
                                    u64 read_format, char __user *buf)
 {
         struct perf_event *leader = event->group_leader, *sub;
-        int n = 0, size = 0, err = -EFAULT;
-        u64 values[3];
+        int n = 0, size = 0, ret = -EFAULT;
+        struct perf_event_context *ctx = leader->ctx;
+        u64 values[5];
+        u64 count, enabled, running;
+
+        mutex_lock(&ctx->mutex);
+        count = perf_event_read_value(leader, &enabled, &running);
 
         values[n++] = 1 + leader->nr_siblings;
-        if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
-                values[n++] = leader->total_time_enabled +
-                        atomic64_read(&leader->child_total_time_enabled);
-        }
-        if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
-                values[n++] = leader->total_time_running +
-                        atomic64_read(&leader->child_total_time_running);
-        }
+        if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+                values[n++] = enabled;
+        if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+                values[n++] = running;
+        values[n++] = count;
+        if (read_format & PERF_FORMAT_ID)
+                values[n++] = primary_event_id(leader);
 
         size = n * sizeof(u64);
 
         if (copy_to_user(buf, values, size))
-                return -EFAULT;
-
-        err = perf_event_read_entry(leader, read_format, buf + size);
-        if (err < 0)
-                return err;
+                goto unlock;
 
-        size += err;
+        ret = size;
 
         list_for_each_entry(sub, &leader->sibling_list, group_entry) {
-                err = perf_event_read_entry(sub, read_format,
-                                buf + size);
-                if (err < 0)
-                        return err;
+                n = 0;
+
+                values[n++] = perf_event_read_value(sub, &enabled, &running);
+                if (read_format & PERF_FORMAT_ID)
+                        values[n++] = primary_event_id(sub);
+
+                size = n * sizeof(u64);
 
-                size += err;
+                if (copy_to_user(buf + ret, values, size)) {
+                        ret = -EFAULT;
+                        goto unlock;
+                }
+
+                ret += size;
         }
+unlock:
+        mutex_unlock(&ctx->mutex);
 
-        return size;
+        return ret;
 }
 
 static int perf_event_read_one(struct perf_event *event,
                                  u64 read_format, char __user *buf)
 {
+        u64 enabled, running;
         u64 values[4];
         int n = 0;
 
-        values[n++] = perf_event_read_value(event);
-        if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
-                values[n++] = event->total_time_enabled +
-                        atomic64_read(&event->child_total_time_enabled);
-        }
-        if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
-                values[n++] = event->total_time_running +
-                        atomic64_read(&event->child_total_time_running);
-        }
+        values[n++] = perf_event_read_value(event, &enabled, &running);
+        if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+                values[n++] = enabled;
+        if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+                values[n++] = running;
         if (read_format & PERF_FORMAT_ID)
                 values[n++] = primary_event_id(event);
 
@@ -1861,12 +1895,10 @@ perf_read_hw(struct perf_event *event, char __user *buf, size_t count)
                 return -ENOSPC;
 
         WARN_ON_ONCE(event->ctx->parent_ctx);
-        mutex_lock(&event->child_mutex);
         if (read_format & PERF_FORMAT_GROUP)
                 ret = perf_event_read_group(event, read_format, buf);
         else
                 ret = perf_event_read_one(event, read_format, buf);
-        mutex_unlock(&event->child_mutex);
 
         return ret;
 }
@@ -1974,7 +2006,8 @@ unlock:
         return ret;
 }
 
-int perf_event_set_output(struct perf_event *event, int output_fd);
+static int perf_event_set_output(struct perf_event *event, int output_fd);
+static int perf_event_set_filter(struct perf_event *event, void __user *arg);
 
 static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
@@ -2002,6 +2035,9 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
         case PERF_EVENT_IOC_SET_OUTPUT:
                 return perf_event_set_output(event, arg);
 
+        case PERF_EVENT_IOC_SET_FILTER:
+                return perf_event_set_filter(event, (void __user *)arg);
+
         default:
                 return -ENOTTY;
         }
@@ -2174,6 +2210,7 @@ static void perf_mmap_data_free(struct perf_mmap_data *data)
         perf_mmap_free_page((unsigned long)data->user_page);
         for (i = 0; i < data->nr_pages; i++)
                 perf_mmap_free_page((unsigned long)data->data_pages[i]);
+        kfree(data);
 }
 
 #else
@@ -2214,6 +2251,7 @@ static void perf_mmap_data_free_work(struct work_struct *work)
                 perf_mmap_unmark_page(base + (i * PAGE_SIZE));
 
         vfree(base);
+        kfree(data);
 }
 
 static void perf_mmap_data_free(struct perf_mmap_data *data)
@@ -2307,7 +2345,7 @@ perf_mmap_data_init(struct perf_event *event, struct perf_mmap_data *data)
         }
 
         if (!data->watermark)
-                data->watermark = max_t(long, PAGE_SIZE, max_size / 2);
+                data->watermark = max_size / 2;
 
 
         rcu_assign_pointer(event->data, data);
@@ -2319,7 +2357,6 @@ static void perf_mmap_data_free_rcu(struct rcu_head *rcu_head)
 
         data = container_of(rcu_head, struct perf_mmap_data, rcu_head);
         perf_mmap_data_free(data);
-        kfree(data);
 }
 
 static void perf_mmap_data_release(struct perf_event *event)
@@ -2666,20 +2703,21 @@ static void perf_output_wakeup(struct perf_output_handle *handle)
 static void perf_output_lock(struct perf_output_handle *handle)
 {
         struct perf_mmap_data *data = handle->data;
-        int cpu;
+        int cur, cpu = get_cpu();
 
         handle->locked = 0;
 
-        local_irq_save(handle->flags);
-        cpu = smp_processor_id();
-
-        if (in_nmi() && atomic_read(&data->lock) == cpu)
-                return;
+        for (;;) {
+                cur = atomic_cmpxchg(&data->lock, -1, cpu);
+                if (cur == -1) {
+                        handle->locked = 1;
+                        break;
+                }
+                if (cur == cpu)
+                        break;
 
-        while (atomic_cmpxchg(&data->lock, -1, cpu) != -1)
                 cpu_relax();
-
-        handle->locked = 1;
+        }
 }
 
 static void perf_output_unlock(struct perf_output_handle *handle)
@@ -2725,7 +2763,7 @@ again:
         if (atomic_xchg(&data->wakeup, 0))
                 perf_output_wakeup(handle);
 out:
-        local_irq_restore(handle->flags);
+        put_cpu();
 }
 
 void perf_output_copy(struct perf_output_handle *handle,
@@ -3236,15 +3274,10 @@ static void perf_event_task_ctx(struct perf_event_context *ctx,
 {
         struct perf_event *event;
 
-        if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
-                return;
-
-        rcu_read_lock();
         list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
                 if (perf_event_task_match(event))
                         perf_event_task_output(event, task_event);
         }
-        rcu_read_unlock();
 }
 
 static void perf_event_task_event(struct perf_task_event *task_event)
@@ -3252,11 +3285,11 @@ static void perf_event_task_event(struct perf_task_event *task_event)
         struct perf_cpu_context *cpuctx;
         struct perf_event_context *ctx = task_event->task_ctx;
 
+        rcu_read_lock();
         cpuctx = &get_cpu_var(perf_cpu_context);
         perf_event_task_ctx(&cpuctx->ctx, task_event);
         put_cpu_var(perf_cpu_context);
 
-        rcu_read_lock();
         if (!ctx)
                 ctx = rcu_dereference(task_event->task->perf_event_ctxp);
         if (ctx)
@@ -3348,15 +3381,10 @@ static void perf_event_comm_ctx(struct perf_event_context *ctx,
 {
         struct perf_event *event;
 
-        if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
-                return;
-
-        rcu_read_lock();
         list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
                 if (perf_event_comm_match(event))
                         perf_event_comm_output(event, comm_event);
         }
-        rcu_read_unlock();
 }
 
 static void perf_event_comm_event(struct perf_comm_event *comm_event)
@@ -3367,7 +3395,7 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
         char comm[TASK_COMM_LEN];
 
         memset(comm, 0, sizeof(comm));
-        strncpy(comm, comm_event->task->comm, sizeof(comm));
+        strlcpy(comm, comm_event->task->comm, sizeof(comm));
         size = ALIGN(strlen(comm)+1, sizeof(u64));
 
         comm_event->comm = comm;
@@ -3375,11 +3403,11 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 
         comm_event->event_id.header.size = sizeof(comm_event->event_id) + size;
 
+        rcu_read_lock();
         cpuctx = &get_cpu_var(perf_cpu_context);
         perf_event_comm_ctx(&cpuctx->ctx, comm_event);
         put_cpu_var(perf_cpu_context);
 
-        rcu_read_lock();
         /*
          * doesn't really matter which of the child contexts the
          * events ends up in.
@@ -3472,15 +3500,10 @@ static void perf_event_mmap_ctx(struct perf_event_context *ctx,
 {
         struct perf_event *event;
 
-        if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
-                return;
-
-        rcu_read_lock();
         list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
                 if (perf_event_mmap_match(event, mmap_event))
                         perf_event_mmap_output(event, mmap_event);
         }
-        rcu_read_unlock();
 }
 
 static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
@@ -3536,11 +3559,11 @@ got_name:
 
         mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
 
+        rcu_read_lock();
         cpuctx = &get_cpu_var(perf_cpu_context);
         perf_event_mmap_ctx(&cpuctx->ctx, mmap_event);
         put_cpu_var(perf_cpu_context);
 
-        rcu_read_lock();
         /*
          * doesn't really matter which of the child contexts the
          * events ends up in.
@@ -3679,7 +3702,11 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
                         perf_event_disable(event);
         }
 
-        perf_event_output(event, nmi, data, regs);
+        if (event->overflow_handler)
+                event->overflow_handler(event, nmi, data, regs);
+        else
+                perf_event_output(event, nmi, data, regs);
+
         return ret;
 }
 
@@ -3724,16 +3751,16 @@ again:
         return nr;
 }
 
-static void perf_swevent_overflow(struct perf_event *event,
+static void perf_swevent_overflow(struct perf_event *event, u64 overflow,
                                     int nmi, struct perf_sample_data *data,
                                     struct pt_regs *regs)
 {
         struct hw_perf_event *hwc = &event->hw;
         int throttle = 0;
-        u64 overflow;
 
         data->period = event->hw.last_period;
-        overflow = perf_swevent_set_period(event);
+        if (!overflow)
+                overflow = perf_swevent_set_period(event);
 
         if (hwc->interrupts == MAX_INTERRUPTS)
                 return;
@@ -3766,14 +3793,19 @@ static void perf_swevent_add(struct perf_event *event, u64 nr,
 
         atomic64_add(nr, &event->count);
 
+        if (!regs)
+                return;
+
         if (!hwc->sample_period)
                 return;
 
-        if (!regs)
+        if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq)
+                return perf_swevent_overflow(event, 1, nmi, data, regs);
+
+        if (atomic64_add_negative(nr, &hwc->period_left))
                 return;
 
-        if (!atomic64_add_negative(nr, &hwc->period_left))
-                perf_swevent_overflow(event, nmi, data, regs);
+        perf_swevent_overflow(event, 0, nmi, data, regs);
 }
 
 static int perf_swevent_is_counting(struct perf_event *event)
@@ -3806,25 +3838,44 @@ static int perf_swevent_is_counting(struct perf_event *event)
         return 1;
 }
 
+static int perf_tp_event_match(struct perf_event *event,
+                                struct perf_sample_data *data);
+
+static int perf_exclude_event(struct perf_event *event,
+                              struct pt_regs *regs)
+{
+        if (regs) {
+                if (event->attr.exclude_user && user_mode(regs))
+                        return 1;
+
+                if (event->attr.exclude_kernel && !user_mode(regs))
+                        return 1;
+        }
+
+        return 0;
+}
+
 static int perf_swevent_match(struct perf_event *event,
                                 enum perf_type_id type,
-                                u32 event_id, struct pt_regs *regs)
+                                u32 event_id,
+                                struct perf_sample_data *data,
+                                struct pt_regs *regs)
 {
         if (!perf_swevent_is_counting(event))
                 return 0;
 
         if (event->attr.type != type)
                 return 0;
+
         if (event->attr.config != event_id)
                 return 0;
 
-        if (regs) {
-                if (event->attr.exclude_user && user_mode(regs))
-                        return 0;
+        if (perf_exclude_event(event, regs))
+                return 0;
 
-                if (event->attr.exclude_kernel && !user_mode(regs))
-                        return 0;
-        }
+        if (event->attr.type == PERF_TYPE_TRACEPOINT &&
+            !perf_tp_event_match(event, data))
+                return 0;
 
         return 1;
 }
@@ -3837,49 +3888,59 @@ static void perf_swevent_ctx_event(struct perf_event_context *ctx,
 {
         struct perf_event *event;
 
-        if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
-                return;
-
-        rcu_read_lock();
         list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
-                if (perf_swevent_match(event, type, event_id, regs))
+                if (perf_swevent_match(event, type, event_id, data, regs))
                         perf_swevent_add(event, nr, nmi, data, regs);
         }
-        rcu_read_unlock();
 }
 
-static int *perf_swevent_recursion_context(struct perf_cpu_context *cpuctx)
+int perf_swevent_get_recursion_context(void)
 {
+        struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context);
+        int rctx;
+
         if (in_nmi())
-                return &cpuctx->recursion[3];
+                rctx = 3;
+        else if (in_irq())
+                rctx = 2;
+        else if (in_softirq())
+                rctx = 1;
+        else
+                rctx = 0;
+
+        if (cpuctx->recursion[rctx]) {
+                put_cpu_var(perf_cpu_context);
+                return -1;
+        }
 
-        if (in_irq())
-                return &cpuctx->recursion[2];
+        cpuctx->recursion[rctx]++;
+        barrier();
 
-        if (in_softirq())
-                return &cpuctx->recursion[1];
+        return rctx;
+}
+EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context);
 
-        return &cpuctx->recursion[0];
+void perf_swevent_put_recursion_context(int rctx)
+{
+        struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+        barrier();
+        cpuctx->recursion[rctx]--;
+        put_cpu_var(perf_cpu_context);
 }
+EXPORT_SYMBOL_GPL(perf_swevent_put_recursion_context);
 
 static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
                                     u64 nr, int nmi,
                                     struct perf_sample_data *data,
                                     struct pt_regs *regs)
 {
-        struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context);
-        int *recursion = perf_swevent_recursion_context(cpuctx);
+        struct perf_cpu_context *cpuctx;
         struct perf_event_context *ctx;
 
-        if (*recursion)
-                goto out;
-
-        (*recursion)++;
-        barrier();
-
+        cpuctx = &__get_cpu_var(perf_cpu_context);
+        rcu_read_lock();
         perf_swevent_ctx_event(&cpuctx->ctx, type, event_id,
                                  nr, nmi, data, regs);
-        rcu_read_lock();
         /*
          * doesn't really matter which of the child contexts the
          * events ends up in.
@@ -3888,23 +3949,24 @@ static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
         if (ctx)
                 perf_swevent_ctx_event(ctx, type, event_id, nr, nmi, data, regs);
         rcu_read_unlock();
-
-        barrier();
-        (*recursion)--;
-
-out:
-        put_cpu_var(perf_cpu_context);
 }
 
 void __perf_sw_event(u32 event_id, u64 nr, int nmi,
                             struct pt_regs *regs, u64 addr)
 {
-        struct perf_sample_data data = {
-                .addr = addr,
-        };
+        struct perf_sample_data data;
+        int rctx;
 
-        do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi,
-                                &data, regs);
+        rctx = perf_swevent_get_recursion_context();
+        if (rctx < 0)
+                return;
+
+        data.addr = addr;
+        data.raw  = NULL;
+
+        do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi, &data, regs);
+
+        perf_swevent_put_recursion_context(rctx);
 }
 
 static void perf_swevent_read(struct perf_event *event)
@@ -3949,6 +4011,7 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
         event->pmu->read(event);
 
         data.addr = 0;
+        data.period = event->hw.last_period;
         regs = get_irq_regs();
         /*
          * In case we exclude kernel IPs or are somehow not in interrupt
@@ -4108,6 +4171,7 @@ static const struct pmu perf_ops_task_clock = {
 };
 
 #ifdef CONFIG_EVENT_PROFILE
+
 void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
                           int entry_size)
 {
@@ -4126,13 +4190,21 @@ void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
         if (!regs)
                 regs = task_pt_regs(current);
 
+        /* Trace events already protected against recursion */
         do_perf_sw_event(PERF_TYPE_TRACEPOINT, event_id, count, 1,
                                 &data, regs);
 }
 EXPORT_SYMBOL_GPL(perf_tp_event);
 
-extern int ftrace_profile_enable(int);
-extern void ftrace_profile_disable(int);
+static int perf_tp_event_match(struct perf_event *event,
+                                struct perf_sample_data *data)
+{
+        void *record = data->raw->data;
+
+        if (likely(!event->filter) || filter_match_preds(event->filter, record))
+                return 1;
+        return 0;
+}
 
 static void tp_perf_event_destroy(struct perf_event *event)
 {
@@ -4157,11 +4229,99 @@ static const struct pmu *tp_perf_event_init(struct perf_event *event)
 
         return &perf_ops_generic;
 }
+
+static int perf_event_set_filter(struct perf_event *event, void __user *arg)
+{
+        char *filter_str;
+        int ret;
+
+        if (event->attr.type != PERF_TYPE_TRACEPOINT)
+                return -EINVAL;
+
+        filter_str = strndup_user(arg, PAGE_SIZE);
+        if (IS_ERR(filter_str))
+                return PTR_ERR(filter_str);
+
+        ret = ftrace_profile_set_filter(event, event->attr.config, filter_str);
+
+        kfree(filter_str);
+        return ret;
+}
+
+static void perf_event_free_filter(struct perf_event *event)
+{
+        ftrace_profile_free_filter(event);
+}
+
 #else
+
+static int perf_tp_event_match(struct perf_event *event,
+                                struct perf_sample_data *data)
+{
+        return 1;
+}
+
 static const struct pmu *tp_perf_event_init(struct perf_event *event)
 {
         return NULL;
 }
+
+static int perf_event_set_filter(struct perf_event *event, void __user *arg)
+{
+        return -ENOENT;
+}
+
+static void perf_event_free_filter(struct perf_event *event)
+{
+}
+
+#endif /* CONFIG_EVENT_PROFILE */
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+static void bp_perf_event_destroy(struct perf_event *event)
+{
+        release_bp_slot(event);
+}
+
+static const struct pmu *bp_perf_event_init(struct perf_event *bp)
+{
+        int err;
+        /*
+         * The breakpoint is already filled if we haven't created the counter
+         * through perf syscall
+         * FIXME: manage to get trigerred to NULL if it comes from syscalls
+         */
+        if (!bp->callback)
+                err = register_perf_hw_breakpoint(bp);
+        else
+                err = __register_perf_hw_breakpoint(bp);
+        if (err)
+                return ERR_PTR(err);
+
+        bp->destroy = bp_perf_event_destroy;
+
+        return &perf_ops_bp;
+}
+
+void perf_bp_event(struct perf_event *bp, void *data)
+{
+        struct perf_sample_data sample;
+        struct pt_regs *regs = data;
+
+        sample.addr = bp->attr.bp_addr;
+
+        if (!perf_exclude_event(bp, regs))
+                perf_swevent_add(bp, 1, 1, &sample, regs);
+}
+#else
+static const struct pmu *bp_perf_event_init(struct perf_event *bp)
+{
+        return NULL;
+}
+
+void perf_bp_event(struct perf_event *bp, void *regs)
+{
+}
 #endif
 
 atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
@@ -4208,6 +4368,8 @@ static const struct pmu *sw_perf_event_init(struct perf_event *event)
         case PERF_COUNT_SW_PAGE_FAULTS_MAJ:
         case PERF_COUNT_SW_CONTEXT_SWITCHES:
         case PERF_COUNT_SW_CPU_MIGRATIONS:
+        case PERF_COUNT_SW_ALIGNMENT_FAULTS:
+        case PERF_COUNT_SW_EMULATION_FAULTS:
                 if (!event->parent) {
                         atomic_inc(&perf_swevent_enabled[event_id]);
                         event->destroy = sw_perf_event_destroy;
@@ -4228,6 +4390,7 @@ perf_event_alloc(struct perf_event_attr *attr,
                    struct perf_event_context *ctx,
                    struct perf_event *group_leader,
                    struct perf_event *parent_event,
+                   perf_callback_t callback,
                    gfp_t gfpflags)
 {
         const struct pmu *pmu;
@@ -4270,6 +4433,11 @@ perf_event_alloc(struct perf_event_attr *attr,
 
         event->state            = PERF_EVENT_STATE_INACTIVE;
 
+        if (!callback && parent_event)
+                callback = parent_event->callback;
+        
+        event->callback = callback;
+
         if (attr->disabled)
                 event->state = PERF_EVENT_STATE_OFF;
 
@@ -4304,6 +4472,11 @@ perf_event_alloc(struct perf_event_attr *attr,
                 pmu = tp_perf_event_init(event);
                 break;
 
+        case PERF_TYPE_BREAKPOINT:
+                pmu = bp_perf_event_init(event);
+                break;
+
+
         default:
                 break;
         }
@@ -4416,7 +4589,7 @@ err_size:
         goto out;
 }
 
-int perf_event_set_output(struct perf_event *event, int output_fd)
+static int perf_event_set_output(struct perf_event *event, int output_fd)
 {
         struct perf_event *output_event = NULL;
         struct file *output_file = NULL;
@@ -4546,7 +4719,7 @@ SYSCALL_DEFINE5(perf_event_open,
         }
 
         event = perf_event_alloc(&attr, cpu, ctx, group_leader,
-                                     NULL, GFP_KERNEL);
+                                     NULL, NULL, GFP_KERNEL);
         err = PTR_ERR(event);
         if (IS_ERR(event))
                 goto err_put_context;
@@ -4594,6 +4767,60 @@ err_put_context:
         return err;
 }
 
+/**
+ * perf_event_create_kernel_counter
+ *
+ * @attr: attributes of the counter to create
+ * @cpu: cpu in which the counter is bound
+ * @pid: task to profile
+ */
+struct perf_event *
+perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
+                                 pid_t pid, perf_callback_t callback)
+{
+        struct perf_event *event;
+        struct perf_event_context *ctx;
+        int err;
+
+        /*
+         * Get the target context (task or percpu):
+         */
+
+        ctx = find_get_context(pid, cpu);
+        if (IS_ERR(ctx)) {
+                err = PTR_ERR(ctx);
+                goto err_exit;
+        }
+
+        event = perf_event_alloc(attr, cpu, ctx, NULL,
+                                     NULL, callback, GFP_KERNEL);
+        if (IS_ERR(event)) {
+                err = PTR_ERR(event);
+                goto err_put_context;
+        }
+
+        event->filp = NULL;
+        WARN_ON_ONCE(ctx->parent_ctx);
+        mutex_lock(&ctx->mutex);
+        perf_install_in_context(ctx, event, cpu);
+        ++ctx->generation;
+        mutex_unlock(&ctx->mutex);
+
+        event->owner = current;
+        get_task_struct(current);
+        mutex_lock(&current->perf_event_mutex);
+        list_add_tail(&event->owner_entry, &current->perf_event_list);
+        mutex_unlock(&current->perf_event_mutex);
+
+        return event;
+
+ err_put_context:
+        put_ctx(ctx);
+ err_exit:
+        return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter);
+
 /*
  * inherit a event from parent task to child task:
  */
@@ -4619,7 +4846,7 @@ inherit_event(struct perf_event *parent_event,
         child_event = perf_event_alloc(&parent_event->attr,
                                            parent_event->cpu, child_ctx,
                                            group_leader, parent_event,
-                                           GFP_KERNEL);
+                                           NULL, GFP_KERNEL);
         if (IS_ERR(child_event))
                 return child_event;
         get_ctx(child_ctx);
@@ -4637,6 +4864,8 @@ inherit_event(struct perf_event *parent_event,
         if (parent_event->attr.freq)
                 child_event->hw.sample_period = parent_event->hw.sample_period;
 
+        child_event->overflow_handler = parent_event->overflow_handler;
+
         /*
          * Link it up in the child's context:
          */
@@ -4726,7 +4955,6 @@ __perf_event_exit_task(struct perf_event *child_event,
 {
         struct perf_event *parent_event;
 
-        update_event_times(child_event);
         perf_event_remove_from_context(child_event);
 
         parent_event = child_event->parent;
@@ -4778,6 +5006,7 @@ void perf_event_exit_task(struct task_struct *child)
          * the events from it.
          */
         unclone_ctx(child_ctx);
+        update_context_time(child_ctx);
         spin_unlock_irqrestore(&child_ctx->lock, flags);
 
         /*
diff --git a/kernel/sched.c b/kernel/sched.c
index 6ae2739b8f19..e7f2cfa6a257 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -535,14 +535,12 @@ struct rq {
         #define CPU_LOAD_IDX_MAX 5
         unsigned long cpu_load[CPU_LOAD_IDX_MAX];
 #ifdef CONFIG_NO_HZ
-        unsigned long last_tick_seen;
         unsigned char in_nohz_recently;
 #endif
         /* capture load from *all* tasks on this cpu: */
         struct load_weight load;
         unsigned long nr_load_updates;
         u64 nr_switches;
-        u64 nr_migrations_in;
 
         struct cfs_rq cfs;
         struct rt_rq rt;
@@ -591,6 +589,8 @@ struct rq {
 
         u64 rt_avg;
         u64 age_stamp;
+        u64 idle_stamp;
+        u64 avg_idle;
 #endif
 
         /* calc_load related fields */
@@ -772,7 +772,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
         if (!sched_feat_names[i])
                 return -EINVAL;
 
-        filp->f_pos += cnt;
+        *ppos += cnt;
 
         return cnt;
 }
@@ -2017,6 +2017,7 @@ void kthread_bind(struct task_struct *p, unsigned int cpu)
         }
 
         spin_lock_irqsave(&rq->lock, flags);
+        update_rq_clock(rq);
         set_task_cpu(p, cpu);
         p->cpus_allowed = cpumask_of_cpu(cpu);
         p->rt.nr_cpus_allowed = 1;
@@ -2078,7 +2079,6 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 #endif
         if (old_cpu != new_cpu) {
                 p->se.nr_migrations++;
-                new_rq->nr_migrations_in++;
 #ifdef CONFIG_SCHEDSTATS
                 if (task_hot(p, old_rq->clock, NULL))
                         schedstat_inc(p, se.nr_forced2_migrations);
@@ -2115,6 +2115,7 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
          * it is sufficient to simply update the task's cpu field.
          */
         if (!p->se.on_rq && !task_running(rq, p)) {
+                update_rq_clock(rq);
                 set_task_cpu(p, dest_cpu);
                 return 0;
         }
@@ -2376,14 +2377,15 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
         task_rq_unlock(rq, &flags);
 
         cpu = p->sched_class->select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
-        if (cpu != orig_cpu)
+        if (cpu != orig_cpu) {
+                local_irq_save(flags);
+                rq = cpu_rq(cpu);
+                update_rq_clock(rq);
                 set_task_cpu(p, cpu);
-
+                local_irq_restore(flags);
+        }
         rq = task_rq_lock(p, &flags);
 
-        if (rq != orig_rq)
-                update_rq_clock(rq);
-
         WARN_ON(p->state != TASK_WAKING);
         cpu = task_cpu(p);
 
@@ -2440,6 +2442,17 @@ out_running:
 #ifdef CONFIG_SMP
         if (p->sched_class->task_wake_up)
                 p->sched_class->task_wake_up(rq, p);
+
+        if (unlikely(rq->idle_stamp)) {
+                u64 delta = rq->clock - rq->idle_stamp;
+                u64 max = 2*sysctl_sched_migration_cost;
+
+                if (delta > max)
+                        rq->avg_idle = max;
+                else
+                        update_avg(&rq->avg_idle, delta);
+                rq->idle_stamp = 0;
+        }
 #endif
 out:
         task_rq_unlock(rq, &flags);
@@ -2545,6 +2558,7 @@ static void __sched_fork(struct task_struct *p)
 void sched_fork(struct task_struct *p, int clone_flags)
 {
         int cpu = get_cpu();
+        unsigned long flags;
 
         __sched_fork(p);
 
@@ -2581,7 +2595,10 @@ void sched_fork(struct task_struct *p, int clone_flags)
 #ifdef CONFIG_SMP
         cpu = p->sched_class->select_task_rq(p, SD_BALANCE_FORK, 0);
 #endif
+        local_irq_save(flags);
+        update_rq_clock(cpu_rq(cpu));
         set_task_cpu(p, cpu);
+        local_irq_restore(flags);
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
         if (likely(sched_info_on()))
@@ -2848,14 +2865,14 @@ context_switch(struct rq *rq, struct task_struct *prev,
          */
         arch_start_context_switch(prev);
 
-        if (unlikely(!mm)) {
+        if (likely(!mm)) {
                 next->active_mm = oldmm;
                 atomic_inc(&oldmm->mm_count);
                 enter_lazy_tlb(oldmm, next);
         } else
                 switch_mm(oldmm, mm, next);
 
-        if (unlikely(!prev->mm)) {
+        if (likely(!prev->mm)) {
                 prev->active_mm = NULL;
                 rq->prev_mm = oldmm;
         }
@@ -3018,15 +3035,6 @@ static void calc_load_account_active(struct rq *this_rq)
 }
 
 /*
- * Externally visible per-cpu scheduler statistics:
- * cpu_nr_migrations(cpu) - number of migrations into that cpu
- */
-u64 cpu_nr_migrations(int cpu)
-{
-        return cpu_rq(cpu)->nr_migrations_in;
-}
-
-/*
  * Update rq->cpu_load[] statistics. This function is usually called every
  * scheduler tick (TICK_NSEC).
  */
@@ -4126,7 +4134,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
         unsigned long flags;
         struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
-        cpumask_setall(cpus);
+        cpumask_copy(cpus, cpu_online_mask);
 
         /*
          * When power savings policy is enabled for the parent domain, idle
@@ -4289,7 +4297,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
         int all_pinned = 0;
         struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
-        cpumask_setall(cpus);
+        cpumask_copy(cpus, cpu_online_mask);
 
         /*
          * When power savings policy is enabled for the parent domain, idle
@@ -4429,6 +4437,11 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
         int pulled_task = 0;
         unsigned long next_balance = jiffies + HZ;
 
+        this_rq->idle_stamp = this_rq->clock;
+
+        if (this_rq->avg_idle < sysctl_sched_migration_cost)
+                return;
+
         for_each_domain(this_cpu, sd) {
                 unsigned long interval;
 
@@ -4443,8 +4456,10 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
                 interval = msecs_to_jiffies(sd->balance_interval);
                 if (time_after(next_balance, sd->last_balance + interval))
                         next_balance = sd->last_balance + interval;
-                if (pulled_task)
+                if (pulled_task) {
+                        this_rq->idle_stamp = 0;
                         break;
+                }
         }
         if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
                 /*
@@ -5046,8 +5061,13 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime,
         p->gtime = cputime_add(p->gtime, cputime);
 
         /* Add guest time to cpustat. */
-        cpustat->user = cputime64_add(cpustat->user, tmp);
-        cpustat->guest = cputime64_add(cpustat->guest, tmp);
+        if (TASK_NICE(p) > 0) {
+                cpustat->nice = cputime64_add(cpustat->nice, tmp);
+                cpustat->guest_nice = cputime64_add(cpustat->guest_nice, tmp);
+        } else {
+                cpustat->user = cputime64_add(cpustat->user, tmp);
+                cpustat->guest = cputime64_add(cpustat->guest, tmp);
+        }
 }
 
 /*
@@ -5162,60 +5182,86 @@ void account_idle_ticks(unsigned long ticks)
  * Use precise platform statistics if available:
  */
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
-cputime_t task_utime(struct task_struct *p)
+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
-        return p->utime;
+        *ut = p->utime;
+        *st = p->stime;
 }
 
-cputime_t task_stime(struct task_struct *p)
+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
-        return p->stime;
+        struct task_cputime cputime;
+
+        thread_group_cputime(p, &cputime);
+
+        *ut = cputime.utime;
+        *st = cputime.stime;
 }
 #else
-cputime_t task_utime(struct task_struct *p)
+
+#ifndef nsecs_to_cputime
+# define nsecs_to_cputime(__nsecs)      nsecs_to_jiffies(__nsecs)
+#endif
+
+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
-        clock_t utime = cputime_to_clock_t(p->utime),
-                total = utime + cputime_to_clock_t(p->stime);
-        u64 temp;
+        cputime_t rtime, utime = p->utime, total = cputime_add(utime, p->stime);
 
         /*
          * Use CFS's precise accounting:
          */
-        temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);
+        rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
 
         if (total) {
-                temp *= utime;
+                u64 temp;
+
+                temp = (u64)(rtime * utime);
                 do_div(temp, total);
-        }
-        utime = (clock_t)temp;
+                utime = (cputime_t)temp;
+        } else
+                utime = rtime;
+
+        /*
+         * Compare with previous values, to keep monotonicity:
+         */
+        p->prev_utime = max(p->prev_utime, utime);
+        p->prev_stime = max(p->prev_stime, cputime_sub(rtime, p->prev_utime));
 
-        p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));
-        return p->prev_utime;
+        *ut = p->prev_utime;
+        *st = p->prev_stime;
 }
 
-cputime_t task_stime(struct task_struct *p)
+/*
+ * Must be called with siglock held.
+ */
+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
-        clock_t stime;
+        struct signal_struct *sig = p->signal;
+        struct task_cputime cputime;
+        cputime_t rtime, utime, total;
 
-        /*
-         * Use CFS's precise accounting. (we subtract utime from
-         * the total, to make sure the total observed by userspace
-         * grows monotonically - apps rely on that):
-         */
-        stime = nsec_to_clock_t(p->se.sum_exec_runtime) -
-                        cputime_to_clock_t(task_utime(p));
+        thread_group_cputime(p, &cputime);
 
-        if (stime >= 0)
-                p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime));
+        total = cputime_add(cputime.utime, cputime.stime);
+        rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
 
-        return p->prev_stime;
-}
-#endif
+        if (total) {
+                u64 temp;
 
-inline cputime_t task_gtime(struct task_struct *p)
-{
-        return p->gtime;
+                temp = (u64)(rtime * cputime.utime);
+                do_div(temp, total);
+                utime = (cputime_t)temp;
+        } else
+                utime = rtime;
+
+        sig->prev_utime = max(sig->prev_utime, utime);
+        sig->prev_stime = max(sig->prev_stime,
+                              cputime_sub(rtime, sig->prev_utime));
+
+        *ut = sig->prev_utime;
+        *st = sig->prev_stime;
 }
+#endif
 
 /*
  * This function gets called by the timer code, with HZ frequency.
@@ -6175,22 +6221,14 @@ __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
         BUG_ON(p->se.on_rq);
 
         p->policy = policy;
-        switch (p->policy) {
-        case SCHED_NORMAL:
-        case SCHED_BATCH:
-        case SCHED_IDLE:
-                p->sched_class = &fair_sched_class;
-                break;
-        case SCHED_FIFO:
-        case SCHED_RR:
-                p->sched_class = &rt_sched_class;
-                break;
-        }
-
         p->rt_priority = prio;
         p->normal_prio = normal_prio(p);
         /* we are holding p->pi_lock already */
         p->prio = rt_mutex_getprio(p);
+        if (rt_prio(p->prio))
+                p->sched_class = &rt_sched_class;
+        else
+                p->sched_class = &fair_sched_class;
         set_load_weight(p);
 }
 
@@ -6935,7 +6973,7 @@ void show_state_filter(unsigned long state_filter)
         /*
          * Only show locks if all tasks are dumped:
          */
-        if (state_filter == -1)
+        if (!state_filter)
                 debug_show_all_locks();
 }
 
@@ -7406,17 +7444,16 @@ static struct ctl_table sd_ctl_dir[] = {
                 .procname       = "sched_domain",
                 .mode           = 0555,
         },
-        {0, },
+        {}
 };
 
 static struct ctl_table sd_ctl_root[] = {
         {
-                .ctl_name       = CTL_KERN,
                 .procname       = "kernel",
                 .mode           = 0555,
                 .child          = sd_ctl_dir,
         },
-        {0, },
+        {}
 };
 
 static struct ctl_table *sd_alloc_ctl_entry(int n)
@@ -7740,6 +7777,16 @@ early_initcall(migration_init);
 
 #ifdef CONFIG_SCHED_DEBUG
 
+static __read_mostly int sched_domain_debug_enabled;
+
+static int __init sched_domain_debug_setup(char *str)
+{
+        sched_domain_debug_enabled = 1;
+
+        return 0;
+}
+early_param("sched_debug", sched_domain_debug_setup);
+
 static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
                                   struct cpumask *groupmask)
 {
@@ -7826,6 +7873,9 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
         cpumask_var_t groupmask;
         int level = 0;
 
+        if (!sched_domain_debug_enabled)
+                return;
+
         if (!sd) {
                 printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
                 return;
@@ -7905,6 +7955,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 
 static void free_rootdomain(struct root_domain *rd)
 {
+        synchronize_sched();
+
         cpupri_cleanup(&rd->cpupri);
 
         free_cpumask_var(rd->rto_mask);
@@ -8045,6 +8097,7 @@ static cpumask_var_t cpu_isolated_map;
 /* Setup the mask of cpus configured for isolated domains */
 static int __init isolated_cpu_setup(char *str)
 {
+        alloc_bootmem_cpumask_var(&cpu_isolated_map);
         cpulist_parse(str, cpu_isolated_map);
         return 1;
 }
@@ -8881,7 +8934,7 @@ static int build_sched_domains(const struct cpumask *cpu_map)
         return __build_sched_domains(cpu_map, NULL);
 }
 
-static struct cpumask *doms_cur;        /* current sched domains */
+static cpumask_var_t *doms_cur; /* current sched domains */
 static int ndoms_cur;           /* number of sched domains in 'doms_cur' */
 static struct sched_domain_attr *dattr_cur;
                                 /* attribues of custom domains in 'doms_cur' */
@@ -8903,6 +8956,31 @@ int __attribute__((weak)) arch_update_cpu_topology(void)
         return 0;
 }
 
+cpumask_var_t *alloc_sched_domains(unsigned int ndoms)
+{
+        int i;
+        cpumask_var_t *doms;
+
+        doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL);
+        if (!doms)
+                return NULL;
+        for (i = 0; i < ndoms; i++) {
+                if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) {
+                        free_sched_domains(doms, i);
+                        return NULL;
+                }
+        }
+        return doms;
+}
+
+void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
+{
+        unsigned int i;
+        for (i = 0; i < ndoms; i++)
+                free_cpumask_var(doms[i]);
+        kfree(doms);
+}
+
 /*
  * Set up scheduler domains and groups. Callers must hold the hotplug lock.
  * For now this just excludes isolated cpus, but could be used to
@@ -8914,12 +8992,12 @@ static int arch_init_sched_domains(const struct cpumask *cpu_map)
 
         arch_update_cpu_topology();
         ndoms_cur = 1;
-        doms_cur = kmalloc(cpumask_size(), GFP_KERNEL);
+        doms_cur = alloc_sched_domains(ndoms_cur);
         if (!doms_cur)
-                doms_cur = fallback_doms;
-        cpumask_andnot(doms_cur, cpu_map, cpu_isolated_map);
+                doms_cur = &fallback_doms;
+        cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
         dattr_cur = NULL;
-        err = build_sched_domains(doms_cur);
+        err = build_sched_domains(doms_cur[0]);
         register_sched_domain_sysctl();
 
         return err;
@@ -8969,19 +9047,19 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
  * doms_new[] to the current sched domain partitioning, doms_cur[].
  * It destroys each deleted domain and builds each new domain.
  *
- * 'doms_new' is an array of cpumask's of length 'ndoms_new'.
+ * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'.
  * The masks don't intersect (don't overlap.) We should setup one
  * sched domain for each mask. CPUs not in any of the cpumasks will
  * not be load balanced. If the same cpumask appears both in the
  * current 'doms_cur' domains and in the new 'doms_new', we can leave
  * it as it is.
  *
- * The passed in 'doms_new' should be kmalloc'd. This routine takes
- * ownership of it and will kfree it when done with it. If the caller
- * failed the kmalloc call, then it can pass in doms_new == NULL &&
- * ndoms_new == 1, and partition_sched_domains() will fallback to
- * the single partition 'fallback_doms', it also forces the domains
- * to be rebuilt.
+ * The passed in 'doms_new' should be allocated using
+ * alloc_sched_domains.  This routine takes ownership of it and will
+ * free_sched_domains it when done with it. If the caller failed the
+ * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1,
+ * and partition_sched_domains() will fallback to the single partition
+ * 'fallback_doms', it also forces the domains to be rebuilt.
  *
  * If doms_new == NULL it will be replaced with cpu_online_mask.
  * ndoms_new == 0 is a special case for destroying existing domains,
@@ -8989,8 +9067,7 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
  *
  * Call with hotplug lock held
  */
-/* FIXME: Change to struct cpumask *doms_new[] */
-void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
+void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
                              struct sched_domain_attr *dattr_new)
 {
         int i, j, n;
@@ -9009,40 +9086,40 @@ void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
         /* Destroy deleted domains */
         for (i = 0; i < ndoms_cur; i++) {
                 for (j = 0; j < n && !new_topology; j++) {
-                        if (cpumask_equal(&doms_cur[i], &doms_new[j])
+                        if (cpumask_equal(doms_cur[i], doms_new[j])
                             && dattrs_equal(dattr_cur, i, dattr_new, j))
                                 goto match1;
                 }
                 /* no match - a current sched domain not in new doms_new[] */
-                detach_destroy_domains(doms_cur + i);
+                detach_destroy_domains(doms_cur[i]);
 match1:
                 ;
         }
 
         if (doms_new == NULL) {
                 ndoms_cur = 0;
-                doms_new = fallback_doms;
-                cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map);
+                doms_new = &fallback_doms;
+                cpumask_andnot(doms_new[0], cpu_online_mask, cpu_isolated_map);
                 WARN_ON_ONCE(dattr_new);
         }
 
         /* Build new domains */
         for (i = 0; i < ndoms_new; i++) {
                 for (j = 0; j < ndoms_cur && !new_topology; j++) {
-                        if (cpumask_equal(&doms_new[i], &doms_cur[j])
+                        if (cpumask_equal(doms_new[i], doms_cur[j])
                             && dattrs_equal(dattr_new, i, dattr_cur, j))
                                 goto match2;
                 }
                 /* no match - add a new doms_new */
-                __build_sched_domains(doms_new + i,
+                __build_sched_domains(doms_new[i],
                                         dattr_new ? dattr_new + i : NULL);
 match2:
                 ;
         }
 
         /* Remember the new sched domains */
-        if (doms_cur != fallback_doms)
-                kfree(doms_cur);
+        if (doms_cur != &fallback_doms)
+                free_sched_domains(doms_cur, ndoms_cur);
         kfree(dattr_cur);       /* kfree(NULL) is safe */
         doms_cur = doms_new;
         dattr_cur = dattr_new;
@@ -9364,10 +9441,6 @@ void __init sched_init(void)
 #ifdef CONFIG_CPUMASK_OFFSTACK
         alloc_size += num_possible_cpus() * cpumask_size();
 #endif
-        /*
-         * As sched_init() is called before page_alloc is setup,
-         * we use alloc_bootmem().
-         */
         if (alloc_size) {
                 ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
 
@@ -9522,6 +9595,8 @@ void __init sched_init(void)
                 rq->cpu = i;
                 rq->online = 0;
                 rq->migration_thread = NULL;
+                rq->idle_stamp = 0;
+                rq->avg_idle = 2*sysctl_sched_migration_cost;
                 INIT_LIST_HEAD(&rq->migration_queue);
                 rq_attach_root(rq, &def_root_domain);
 #endif
@@ -9571,7 +9646,9 @@ void __init sched_init(void)
         zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
         alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
 #endif
-        zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
+        /* May be allocated at isolcpus cmdline parse time */
+        if (cpu_isolated_map == NULL)
+                zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
 #endif /* SMP */
 
         perf_event_init();
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index efb84409bc43..6988cf08f705 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -285,12 +285,16 @@ static void print_cpu(struct seq_file *m, int cpu)
 
 #ifdef CONFIG_SCHEDSTATS
 #define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, rq->n);
+#define P64(n) SEQ_printf(m, "  .%-30s: %Ld\n", #n, rq->n);
 
         P(yld_count);
 
         P(sched_switch);
         P(sched_count);
         P(sched_goidle);
+#ifdef CONFIG_SMP
+        P64(avg_idle);
+#endif
 
         P(ttwu_count);
         P(ttwu_local);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 37087a7fac22..f61837ad336d 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1345,6 +1345,37 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 }
 
 /*
+ * Try and locate an idle CPU in the sched_domain.
+ */
+static int
+select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target)
+{
+        int cpu = smp_processor_id();
+        int prev_cpu = task_cpu(p);
+        int i;
+
+        /*
+         * If this domain spans both cpu and prev_cpu (see the SD_WAKE_AFFINE
+         * test in select_task_rq_fair) and the prev_cpu is idle then that's
+         * always a better target than the current cpu.
+         */
+        if (target == cpu && !cpu_rq(prev_cpu)->cfs.nr_running)
+                return prev_cpu;
+
+        /*
+         * Otherwise, iterate the domain and find an elegible idle cpu.
+         */
+        for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
+                if (!cpu_rq(i)->cfs.nr_running) {
+                        target = i;
+                        break;
+                }
+        }
+
+        return target;
+}
+
+/*
  * sched_balance_self: balance the current task (running on cpu) in domains
  * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
  * SD_BALANCE_EXEC.
@@ -1398,11 +1429,35 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
                                 want_sd = 0;
                 }
 
-                if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
-                    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
+                /*
+                 * While iterating the domains looking for a spanning
+                 * WAKE_AFFINE domain, adjust the affine target to any idle cpu
+                 * in cache sharing domains along the way.
+                 */
+                if (want_affine) {
+                        int target = -1;
 
-                        affine_sd = tmp;
-                        want_affine = 0;
+                        /*
+                         * If both cpu and prev_cpu are part of this domain,
+                         * cpu is a valid SD_WAKE_AFFINE target.
+                         */
+                        if (cpumask_test_cpu(prev_cpu, sched_domain_span(tmp)))
+                                target = cpu;
+
+                        /*
+                         * If there's an idle sibling in this domain, make that
+                         * the wake_affine target instead of the current cpu.
+                         */
+                        if (tmp->flags & SD_PREFER_SIBLING)
+                                target = select_idle_sibling(p, tmp, target);
+
+                        if (target >= 0) {
+                                if (tmp->flags & SD_WAKE_AFFINE) {
+                                        affine_sd = tmp;
+                                        want_affine = 0;
+                                }
+                                cpu = target;
+                        }
                 }
 
                 if (!want_sd && !want_affine)
@@ -1679,7 +1734,7 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
         struct cfs_rq *cfs_rq = &rq->cfs;
         struct sched_entity *se;
 
-        if (unlikely(!cfs_rq->nr_running))
+        if (!cfs_rq->nr_running)
                 return NULL;
 
         do {
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index a4d790cddb19..5c5fef378415 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1153,29 +1153,12 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
 
 static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
 
-static inline int pick_optimal_cpu(int this_cpu,
-                                   const struct cpumask *mask)
-{
-        int first;
-
-        /* "this_cpu" is cheaper to preempt than a remote processor */
-        if ((this_cpu != -1) && cpumask_test_cpu(this_cpu, mask))
-                return this_cpu;
-
-        first = cpumask_first(mask);
-        if (first < nr_cpu_ids)
-                return first;
-
-        return -1;
-}
-
 static int find_lowest_rq(struct task_struct *task)
 {
         struct sched_domain *sd;
         struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask);
         int this_cpu = smp_processor_id();
         int cpu      = task_cpu(task);
-        cpumask_var_t domain_mask;
 
         if (task->rt.nr_cpus_allowed == 1)
                 return -1; /* No other targets possible */
@@ -1198,28 +1181,26 @@ static int find_lowest_rq(struct task_struct *task)
          * Otherwise, we consult the sched_domains span maps to figure
          * out which cpu is logically closest to our hot cache data.
          */
-        if (this_cpu == cpu)
-                this_cpu = -1; /* Skip this_cpu opt if the same */
-
-        if (alloc_cpumask_var(&domain_mask, GFP_ATOMIC)) {
-                for_each_domain(cpu, sd) {
-                        if (sd->flags & SD_WAKE_AFFINE) {
-                                int best_cpu;
+        if (!cpumask_test_cpu(this_cpu, lowest_mask))
+                this_cpu = -1; /* Skip this_cpu opt if not among lowest */
 
-                                cpumask_and(domain_mask,
-                                            sched_domain_span(sd),
-                                            lowest_mask);
+        for_each_domain(cpu, sd) {
+                if (sd->flags & SD_WAKE_AFFINE) {
+                        int best_cpu;
 
-                                best_cpu = pick_optimal_cpu(this_cpu,
-                                                            domain_mask);
-
-                                if (best_cpu != -1) {
-                                        free_cpumask_var(domain_mask);
-                                        return best_cpu;
-                                }
-                        }
+                        /*
+                         * "this_cpu" is cheaper to preempt than a
+                         * remote processor.
+                         */
+                        if (this_cpu != -1 &&
+                            cpumask_test_cpu(this_cpu, sched_domain_span(sd)))
+                                return this_cpu;
+
+                        best_cpu = cpumask_first_and(lowest_mask,
+                                                     sched_domain_span(sd));
+                        if (best_cpu < nr_cpu_ids)
+                                return best_cpu;
                 }
-                free_cpumask_var(domain_mask);
         }
 
         /*
@@ -1227,7 +1208,13 @@ static int find_lowest_rq(struct task_struct *task)
          * just give the caller *something* to work with from the compatible
          * locations.
          */
-        return pick_optimal_cpu(this_cpu, lowest_mask);
+        if (this_cpu != -1)
+                return this_cpu;
+
+        cpu = cpumask_any(lowest_mask);
+        if (cpu < nr_cpu_ids)
+                return cpu;
+        return -1;
 }
 
 /* Will lock the rq it finds */
diff --git a/kernel/signal.c b/kernel/signal.c
index fe08008133da..6b982f2cf524 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -28,7 +28,8 @@
 #include <linux/freezer.h>
 #include <linux/pid_namespace.h>
 #include <linux/nsproxy.h>
-#include <trace/events/sched.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/signal.h>
 
 #include <asm/param.h>
 #include <asm/uaccess.h>
@@ -856,7 +857,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
         struct sigqueue *q;
         int override_rlimit;
 
-        trace_sched_signal_send(sig, t);
+        trace_signal_generate(sig, info, t);
 
         assert_spin_locked(&t->sighand->siglock);
 
@@ -918,12 +919,21 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
                         break;
                 }
         } else if (!is_si_special(info)) {
-                if (sig >= SIGRTMIN && info->si_code != SI_USER)
-                /*
-                 * Queue overflow, abort.  We may abort if the signal was rt
-                 * and sent by user using something other than kill().
-                 */
+                if (sig >= SIGRTMIN && info->si_code != SI_USER) {
+                        /*
+                         * Queue overflow, abort.  We may abort if the
+                         * signal was rt and sent by user using something
+                         * other than kill().
+                         */
+                        trace_signal_overflow_fail(sig, group, info);
                         return -EAGAIN;
+                } else {
+                        /*
+                         * This is a silent loss of information.  We still
+                         * send the signal, but the *info bits are lost.
+                         */
+                        trace_signal_lose_info(sig, group, info);
+                }
         }
 
 out_set:
@@ -1859,6 +1869,9 @@ relock:
                         ka = &sighand->action[signr-1];
                 }
 
+                /* Trace actually delivered signals. */
+                trace_signal_deliver(signr, info, ka);
+
                 if (ka->sa.sa_handler == SIG_IGN) /* Do nothing.  */
                         continue;
                 if (ka->sa.sa_handler != SIG_DFL) {
diff --git a/kernel/slow-work.c b/kernel/slow-work.c
index 00889bd3c590..7494bbf5a270 100644
--- a/kernel/slow-work.c
+++ b/kernel/slow-work.c
@@ -49,7 +49,6 @@ static const int slow_work_max_vslow = 99;
 
 ctl_table slow_work_sysctls[] = {
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "min-threads",
                 .data           = &slow_work_min_threads,
                 .maxlen         = sizeof(unsigned),
@@ -59,7 +58,6 @@ ctl_table slow_work_sysctls[] = {
                 .extra2         = &slow_work_max_threads,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "max-threads",
                 .data           = &slow_work_max_threads,
                 .maxlen         = sizeof(unsigned),
@@ -69,16 +67,15 @@ ctl_table slow_work_sysctls[] = {
                 .extra2         = (void *) &slow_work_max_max_threads,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "vslow-percentage",
                 .data           = &vslow_work_proportion,
                 .maxlen         = sizeof(unsigned),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = (void *) &slow_work_min_vslow,
                 .extra2         = (void *) &slow_work_max_vslow,
         },
-        { .ctl_name = 0 }
+        {}
 };
 #endif
 
diff --git a/kernel/sys.c b/kernel/sys.c
index ce17760d9c51..9968c5fb55b9 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -911,16 +911,15 @@ change_okay:
 
 void do_sys_times(struct tms *tms)
 {
-        struct task_cputime cputime;
-        cputime_t cutime, cstime;
+        cputime_t tgutime, tgstime, cutime, cstime;
 
-        thread_group_cputime(current, &cputime);
         spin_lock_irq(&current->sighand->siglock);
+        thread_group_times(current, &tgutime, &tgstime);
         cutime = current->signal->cutime;
         cstime = current->signal->cstime;
         spin_unlock_irq(&current->sighand->siglock);
-        tms->tms_utime = cputime_to_clock_t(cputime.utime);
-        tms->tms_stime = cputime_to_clock_t(cputime.stime);
+        tms->tms_utime = cputime_to_clock_t(tgutime);
+        tms->tms_stime = cputime_to_clock_t(tgstime);
         tms->tms_cutime = cputime_to_clock_t(cutime);
         tms->tms_cstime = cputime_to_clock_t(cstime);
 }
@@ -1338,16 +1337,14 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 {
         struct task_struct *t;
         unsigned long flags;
-        cputime_t utime, stime;
-        struct task_cputime cputime;
+        cputime_t tgutime, tgstime, utime, stime;
         unsigned long maxrss = 0;
 
         memset((char *) r, 0, sizeof *r);
         utime = stime = cputime_zero;
 
         if (who == RUSAGE_THREAD) {
-                utime = task_utime(current);
-                stime = task_stime(current);
+                task_times(current, &utime, &stime);
                 accumulate_thread_rusage(p, r);
                 maxrss = p->signal->maxrss;
                 goto out;
@@ -1373,9 +1370,9 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
                                 break;
 
                 case RUSAGE_SELF:
-                        thread_group_cputime(p, &cputime);
-                        utime = cputime_add(utime, cputime.utime);
-                        stime = cputime_add(stime, cputime.stime);
+                        thread_group_times(p, &tgutime, &tgstime);
+                        utime = cputime_add(utime, tgutime);
+                        stime = cputime_add(stime, tgstime);
                         r->ru_nvcsw += p->signal->nvcsw;
                         r->ru_nivcsw += p->signal->nivcsw;
                         r->ru_minflt += p->signal->min_flt;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index f050ba85d420..695384f12a7d 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -141,7 +141,6 @@ cond_syscall(sys_pciconfig_read);
 cond_syscall(sys_pciconfig_write);
 cond_syscall(sys_pciconfig_iobase);
 cond_syscall(sys32_ipc);
-cond_syscall(sys32_sysctl);
 cond_syscall(ppc_rtas);
 cond_syscall(sys_spu_run);
 cond_syscall(sys_spu_create);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4dbf93a52ee9..9327a26765c5 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -27,7 +27,6 @@
 #include <linux/security.h>
 #include <linux/ctype.h>
 #include <linux/kmemcheck.h>
-#include <linux/smp_lock.h>
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -61,7 +60,6 @@
 #include <asm/io.h>
 #endif
 
-static int deprecated_sysctl_warning(struct __sysctl_args *args);
 
 #if defined(CONFIG_SYSCTL)
 
@@ -210,31 +208,26 @@ extern int lock_stat;
 
 static struct ctl_table root_table[] = {
         {
-                .ctl_name       = CTL_KERN,
                 .procname       = "kernel",
                 .mode           = 0555,
                 .child          = kern_table,
         },
         {
-                .ctl_name       = CTL_VM,
                 .procname       = "vm",
                 .mode           = 0555,
                 .child          = vm_table,
         },
         {
-                .ctl_name       = CTL_FS,
                 .procname       = "fs",
                 .mode           = 0555,
                 .child          = fs_table,
         },
         {
-                .ctl_name       = CTL_DEBUG,
                 .procname       = "debug",
                 .mode           = 0555,
                 .child          = debug_table,
         },
         {
-                .ctl_name       = CTL_DEV,
                 .procname       = "dev",
                 .mode           = 0555,
                 .child          = dev_table,
@@ -243,7 +236,7 @@ static struct ctl_table root_table[] = {
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
  */
-        { .ctl_name = 0 }
+        { }
 };
 
 #ifdef CONFIG_SCHED_DEBUG
@@ -255,192 +248,166 @@ static int max_wakeup_granularity_ns = NSEC_PER_SEC;	/* 1 second */
 
 static struct ctl_table kern_table[] = {
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "sched_child_runs_first",
                 .data           = &sysctl_sched_child_runs_first,
                 .maxlen         = sizeof(unsigned int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #ifdef CONFIG_SCHED_DEBUG
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "sched_min_granularity_ns",
                 .data           = &sysctl_sched_min_granularity,
                 .maxlen         = sizeof(unsigned int),
                 .mode           = 0644,
-                .proc_handler   = &sched_nr_latency_handler,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = sched_nr_latency_handler,
                 .extra1         = &min_sched_granularity_ns,
                 .extra2         = &max_sched_granularity_ns,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "sched_latency_ns",
                 .data           = &sysctl_sched_latency,
                 .maxlen         = sizeof(unsigned int),
                 .mode           = 0644,
-                .proc_handler   = &sched_nr_latency_handler,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = sched_nr_latency_handler,
                 .extra1         = &min_sched_granularity_ns,
                 .extra2         = &max_sched_granularity_ns,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "sched_wakeup_granularity_ns",
                 .data           = &sysctl_sched_wakeup_granularity,
                 .maxlen         = sizeof(unsigned int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &min_wakeup_granularity_ns,
                 .extra2         = &max_wakeup_granularity_ns,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "sched_shares_ratelimit",
                 .data           = &sysctl_sched_shares_ratelimit,
                 .maxlen         = sizeof(unsigned int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "sched_shares_thresh",
                 .data           = &sysctl_sched_shares_thresh,
                 .maxlen         = sizeof(unsigned int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &zero,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "sched_features",
                 .data           = &sysctl_sched_features,
                 .maxlen         = sizeof(unsigned int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "sched_migration_cost",
                 .data           = &sysctl_sched_migration_cost,
                 .maxlen         = sizeof(unsigned int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "sched_nr_migrate",
                 .data           = &sysctl_sched_nr_migrate,
                 .maxlen         = sizeof(unsigned int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "sched_time_avg",
                 .data           = &sysctl_sched_time_avg,
                 .maxlen         = sizeof(unsigned int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "timer_migration",
                 .data           = &sysctl_timer_migration,
                 .maxlen         = sizeof(unsigned int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &zero,
                 .extra2         = &one,
         },
 #endif
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "sched_rt_period_us",
                 .data           = &sysctl_sched_rt_period,
                 .maxlen         = sizeof(unsigned int),
                 .mode           = 0644,
-                .proc_handler   = &sched_rt_handler,
+                .proc_handler   = sched_rt_handler,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "sched_rt_runtime_us",
                 .data           = &sysctl_sched_rt_runtime,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &sched_rt_handler,
+                .proc_handler   = sched_rt_handler,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "sched_compat_yield",
                 .data           = &sysctl_sched_compat_yield,
                 .maxlen         = sizeof(unsigned int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #ifdef CONFIG_PROVE_LOCKING
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "prove_locking",
                 .data           = &prove_locking,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #ifdef CONFIG_LOCK_STAT
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "lock_stat",
                 .data           = &lock_stat,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
         {
-                .ctl_name       = KERN_PANIC,
                 .procname       = "panic",
                 .data           = &panic_timeout,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = KERN_CORE_USES_PID,
                 .procname       = "core_uses_pid",
                 .data           = &core_uses_pid,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = KERN_CORE_PATTERN,
                 .procname       = "core_pattern",
                 .data           = core_pattern,
                 .maxlen         = CORENAME_MAX_SIZE,
                 .mode           = 0644,
-                .proc_handler   = &proc_dostring,
-                .strategy       = &sysctl_string,
+                .proc_handler   = proc_dostring,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "core_pipe_limit",
                 .data           = &core_pipe_limit,
                 .maxlen         = sizeof(unsigned int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #ifdef CONFIG_PROC_SYSCTL
         {
                 .procname       = "tainted",
                 .maxlen         = sizeof(long),
                 .mode           = 0644,
-                .proc_handler   = &proc_taint,
+                .proc_handler   = proc_taint,
         },
 #endif
 #ifdef CONFIG_LATENCYTOP
@@ -449,181 +416,160 @@ static struct ctl_table kern_table[] = {
                 .data           = &latencytop_enabled,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #ifdef CONFIG_BLK_DEV_INITRD
         {
-                .ctl_name       = KERN_REALROOTDEV,
                 .procname       = "real-root-dev",
                 .data           = &real_root_dev,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "print-fatal-signals",
                 .data           = &print_fatal_signals,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #ifdef CONFIG_SPARC
         {
-                .ctl_name       = KERN_SPARC_REBOOT,
                 .procname       = "reboot-cmd",
                 .data           = reboot_command,
                 .maxlen         = 256,
                 .mode           = 0644,
-                .proc_handler   = &proc_dostring,
-                .strategy       = &sysctl_string,
+                .proc_handler   = proc_dostring,
         },
         {
-                .ctl_name       = KERN_SPARC_STOP_A,
                 .procname       = "stop-a",
                 .data           = &stop_a_enabled,
                 .maxlen         = sizeof (int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = KERN_SPARC_SCONS_PWROFF,
                 .procname       = "scons-poweroff",
                 .data           = &scons_pwroff,
                 .maxlen         = sizeof (int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #ifdef CONFIG_SPARC64
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "tsb-ratio",
                 .data           = &sysctl_tsb_ratio,
                 .maxlen         = sizeof (int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #ifdef __hppa__
         {
-                .ctl_name       = KERN_HPPA_PWRSW,
                 .procname       = "soft-power",
                 .data           = &pwrsw_enabled,
                 .maxlen         = sizeof (int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = KERN_HPPA_UNALIGNED,
                 .procname       = "unaligned-trap",
                 .data           = &unaligned_enabled,
                 .maxlen         = sizeof (int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
         {
-                .ctl_name       = KERN_CTLALTDEL,
                 .procname       = "ctrl-alt-del",
                 .data           = &C_A_D,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #ifdef CONFIG_FUNCTION_TRACER
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "ftrace_enabled",
                 .data           = &ftrace_enabled,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &ftrace_enable_sysctl,
+                .proc_handler   = ftrace_enable_sysctl,
         },
 #endif
 #ifdef CONFIG_STACK_TRACER
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "stack_tracer_enabled",
                 .data           = &stack_tracer_enabled,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &stack_trace_sysctl,
+                .proc_handler   = stack_trace_sysctl,
         },
 #endif
 #ifdef CONFIG_TRACING
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "ftrace_dump_on_oops",
                 .data           = &ftrace_dump_on_oops,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #ifdef CONFIG_MODULES
         {
-                .ctl_name       = KERN_MODPROBE,
                 .procname       = "modprobe",
                 .data           = &modprobe_path,
                 .maxlen         = KMOD_PATH_LEN,
                 .mode           = 0644,
-                .proc_handler   = &proc_dostring,
-                .strategy       = &sysctl_string,
+                .proc_handler   = proc_dostring,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "modules_disabled",
                 .data           = &modules_disabled,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
                 /* only handle a transition from default "0" to "1" */
-                .proc_handler   = &proc_dointvec_minmax,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &one,
                 .extra2         = &one,
         },
 #endif
 #if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET)
         {
-                .ctl_name       = KERN_HOTPLUG,
                 .procname       = "hotplug",
                 .data           = &uevent_helper,
                 .maxlen         = UEVENT_HELPER_PATH_LEN,
                 .mode           = 0644,
-                .proc_handler   = &proc_dostring,
-                .strategy       = &sysctl_string,
+                .proc_handler   = proc_dostring,
         },
 #endif
 #ifdef CONFIG_CHR_DEV_SG
         {
-                .ctl_name       = KERN_SG_BIG_BUFF,
                 .procname       = "sg-big-buff",
                 .data           = &sg_big_buff,
                 .maxlen         = sizeof (int),
                 .mode           = 0444,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #ifdef CONFIG_BSD_PROCESS_ACCT
         {
-                .ctl_name       = KERN_ACCT,
                 .procname       = "acct",
                 .data           = &acct_parm,
                 .maxlen         = 3*sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #ifdef CONFIG_MAGIC_SYSRQ
         {
-                .ctl_name       = KERN_SYSRQ,
                 .procname       = "sysrq",
                 .data           = &__sysrq_enabled,
                 .maxlen         = sizeof (int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #ifdef CONFIG_PROC_SYSCTL
@@ -632,215 +578,188 @@ static struct ctl_table kern_table[] = {
                 .data           = NULL,
                 .maxlen         = sizeof (int),
                 .mode           = 0600,
-                .proc_handler   = &proc_do_cad_pid,
+                .proc_handler   = proc_do_cad_pid,
         },
 #endif
         {
-                .ctl_name       = KERN_MAX_THREADS,
                 .procname       = "threads-max",
                 .data           = &max_threads,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = KERN_RANDOM,
                 .procname       = "random",
                 .mode           = 0555,
                 .child          = random_table,
         },
         {
-                .ctl_name       = KERN_OVERFLOWUID,
                 .procname       = "overflowuid",
                 .data           = &overflowuid,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &minolduid,
                 .extra2         = &maxolduid,
         },
         {
-                .ctl_name       = KERN_OVERFLOWGID,
                 .procname       = "overflowgid",
                 .data           = &overflowgid,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &minolduid,
                 .extra2         = &maxolduid,
         },
 #ifdef CONFIG_S390
 #ifdef CONFIG_MATHEMU
         {
-                .ctl_name       = KERN_IEEE_EMULATION_WARNINGS,
                 .procname       = "ieee_emulation_warnings",
                 .data           = &sysctl_ieee_emulation_warnings,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
         {
-                .ctl_name       = KERN_S390_USER_DEBUG_LOGGING,
                 .procname       = "userprocess_debug",
                 .data           = &sysctl_userprocess_debug,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
         {
-                .ctl_name       = KERN_PIDMAX,
                 .procname       = "pid_max",
                 .data           = &pid_max,
                 .maxlen         = sizeof (int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &pid_max_min,
                 .extra2         = &pid_max_max,
         },
         {
-                .ctl_name       = KERN_PANIC_ON_OOPS,
                 .procname       = "panic_on_oops",
                 .data           = &panic_on_oops,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #if defined CONFIG_PRINTK
         {
-                .ctl_name       = KERN_PRINTK,
                 .procname       = "printk",
                 .data           = &console_loglevel,
                 .maxlen         = 4*sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = KERN_PRINTK_RATELIMIT,
                 .procname       = "printk_ratelimit",
                 .data           = &printk_ratelimit_state.interval,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_jiffies,
-                .strategy       = &sysctl_jiffies,
+                .proc_handler   = proc_dointvec_jiffies,
         },
         {
-                .ctl_name       = KERN_PRINTK_RATELIMIT_BURST,
                 .procname       = "printk_ratelimit_burst",
                 .data           = &printk_ratelimit_state.burst,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "printk_delay",
                 .data           = &printk_delay_msec,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &zero,
                 .extra2         = &ten_thousand,
         },
 #endif
         {
-                .ctl_name       = KERN_NGROUPS_MAX,
                 .procname       = "ngroups_max",
                 .data           = &ngroups_max,
                 .maxlen         = sizeof (int),
                 .mode           = 0444,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
         {
-                .ctl_name       = KERN_UNKNOWN_NMI_PANIC,
                 .procname       = "unknown_nmi_panic",
                 .data           = &unknown_nmi_panic,
                 .maxlen         = sizeof (int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
                 .procname       = "nmi_watchdog",
                 .data           = &nmi_watchdog_enabled,
                 .maxlen         = sizeof (int),
                 .mode           = 0644,
-                .proc_handler   = &proc_nmi_enabled,
+                .proc_handler   = proc_nmi_enabled,
         },
 #endif
 #if defined(CONFIG_X86)
         {
-                .ctl_name       = KERN_PANIC_ON_NMI,
                 .procname       = "panic_on_unrecovered_nmi",
                 .data           = &panic_on_unrecovered_nmi,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "panic_on_io_nmi",
                 .data           = &panic_on_io_nmi,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = KERN_BOOTLOADER_TYPE,
                 .procname       = "bootloader_type",
                 .data           = &bootloader_type,
                 .maxlen         = sizeof (int),
                 .mode           = 0444,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "bootloader_version",
                 .data           = &bootloader_version,
                 .maxlen         = sizeof (int),
                 .mode           = 0444,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "kstack_depth_to_print",
                 .data           = &kstack_depth_to_print,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "io_delay_type",
                 .data           = &io_delay_type,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #if defined(CONFIG_MMU)
         {
-                .ctl_name       = KERN_RANDOMIZE,
                 .procname       = "randomize_va_space",
                 .data           = &randomize_va_space,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #if defined(CONFIG_S390) && defined(CONFIG_SMP)
         {
-                .ctl_name       = KERN_SPIN_RETRY,
                 .procname       = "spin_retry",
                 .data           = &spin_retry,
                 .maxlen         = sizeof (int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #if     defined(CONFIG_ACPI_SLEEP) && defined(CONFIG_X86)
@@ -849,123 +768,104 @@ static struct ctl_table kern_table[] = {
                 .data           = &acpi_realmode_flags,
                 .maxlen         = sizeof (unsigned long),
                 .mode           = 0644,
-                .proc_handler   = &proc_doulongvec_minmax,
+                .proc_handler   = proc_doulongvec_minmax,
         },
 #endif
 #ifdef CONFIG_IA64
         {
-                .ctl_name       = KERN_IA64_UNALIGNED,
                 .procname       = "ignore-unaligned-usertrap",
                 .data           = &no_unaligned_warning,
                 .maxlen         = sizeof (int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "unaligned-dump-stack",
                 .data           = &unaligned_dump_stack,
                 .maxlen         = sizeof (int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #ifdef CONFIG_DETECT_SOFTLOCKUP
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "softlockup_panic",
                 .data           = &softlockup_panic,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &zero,
                 .extra2         = &one,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "softlockup_thresh",
                 .data           = &softlockup_thresh,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dosoftlockup_thresh,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dosoftlockup_thresh,
                 .extra1         = &neg_one,
                 .extra2         = &sixty,
         },
 #endif
 #ifdef CONFIG_DETECT_HUNG_TASK
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "hung_task_panic",
                 .data           = &sysctl_hung_task_panic,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &zero,
                 .extra2         = &one,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "hung_task_check_count",
                 .data           = &sysctl_hung_task_check_count,
                 .maxlen         = sizeof(unsigned long),
                 .mode           = 0644,
-                .proc_handler   = &proc_doulongvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_doulongvec_minmax,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "hung_task_timeout_secs",
                 .data           = &sysctl_hung_task_timeout_secs,
                 .maxlen         = sizeof(unsigned long),
                 .mode           = 0644,
-                .proc_handler   = &proc_dohung_task_timeout_secs,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dohung_task_timeout_secs,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "hung_task_warnings",
                 .data           = &sysctl_hung_task_warnings,
                 .maxlen         = sizeof(unsigned long),
                 .mode           = 0644,
-                .proc_handler   = &proc_doulongvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_doulongvec_minmax,
         },
 #endif
 #ifdef CONFIG_COMPAT
         {
-                .ctl_name       = KERN_COMPAT_LOG,
                 .procname       = "compat-log",
                 .data           = &compat_log,
                 .maxlen         = sizeof (int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #ifdef CONFIG_RT_MUTEXES
         {
-                .ctl_name       = KERN_MAX_LOCK_DEPTH,
                 .procname       = "max_lock_depth",
                 .data           = &max_lock_depth,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "poweroff_cmd",
                 .data           = &poweroff_cmd,
                 .maxlen         = POWEROFF_CMD_PATH_LEN,
                 .mode           = 0644,
-                .proc_handler   = &proc_dostring,
-                .strategy       = &sysctl_string,
+                .proc_handler   = proc_dostring,
         },
 #ifdef CONFIG_KEYS
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "keys",
                 .mode           = 0555,
                 .child          = key_sysctls,
@@ -973,17 +873,15 @@ static struct ctl_table kern_table[] = {
 #endif
 #ifdef CONFIG_RCU_TORTURE_TEST
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "rcutorture_runnable",
                 .data           = &rcutorture_runnable,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #ifdef CONFIG_SLOW_WORK
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "slow-work",
                 .mode           = 0555,
                 .child          = slow_work_sysctls,
@@ -991,146 +889,127 @@ static struct ctl_table kern_table[] = {
 #endif
 #ifdef CONFIG_PERF_EVENTS
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "perf_event_paranoid",
                 .data           = &sysctl_perf_event_paranoid,
                 .maxlen         = sizeof(sysctl_perf_event_paranoid),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "perf_event_mlock_kb",
                 .data           = &sysctl_perf_event_mlock,
                 .maxlen         = sizeof(sysctl_perf_event_mlock),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "perf_event_max_sample_rate",
                 .data           = &sysctl_perf_event_sample_rate,
                 .maxlen         = sizeof(sysctl_perf_event_sample_rate),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #ifdef CONFIG_KMEMCHECK
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "kmemcheck",
                 .data           = &kmemcheck_enabled,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #ifdef CONFIG_BLOCK
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "blk_iopoll",
                 .data           = &blk_iopoll_enabled,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
  */
-        { .ctl_name = 0 }
+        { }
 };
 
 static struct ctl_table vm_table[] = {
         {
-                .ctl_name       = VM_OVERCOMMIT_MEMORY,
                 .procname       = "overcommit_memory",
                 .data           = &sysctl_overcommit_memory,
                 .maxlen         = sizeof(sysctl_overcommit_memory),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = VM_PANIC_ON_OOM,
                 .procname       = "panic_on_oom",
                 .data           = &sysctl_panic_on_oom,
                 .maxlen         = sizeof(sysctl_panic_on_oom),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "oom_kill_allocating_task",
                 .data           = &sysctl_oom_kill_allocating_task,
                 .maxlen         = sizeof(sysctl_oom_kill_allocating_task),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "oom_dump_tasks",
                 .data           = &sysctl_oom_dump_tasks,
                 .maxlen         = sizeof(sysctl_oom_dump_tasks),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = VM_OVERCOMMIT_RATIO,
                 .procname       = "overcommit_ratio",
                 .data           = &sysctl_overcommit_ratio,
                 .maxlen         = sizeof(sysctl_overcommit_ratio),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = VM_PAGE_CLUSTER,
                 .procname       = "page-cluster", 
                 .data           = &page_cluster,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = VM_DIRTY_BACKGROUND,
                 .procname       = "dirty_background_ratio",
                 .data           = &dirty_background_ratio,
                 .maxlen         = sizeof(dirty_background_ratio),
                 .mode           = 0644,
-                .proc_handler   = &dirty_background_ratio_handler,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = dirty_background_ratio_handler,
                 .extra1         = &zero,
                 .extra2         = &one_hundred,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "dirty_background_bytes",
                 .data           = &dirty_background_bytes,
                 .maxlen         = sizeof(dirty_background_bytes),
                 .mode           = 0644,
-                .proc_handler   = &dirty_background_bytes_handler,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = dirty_background_bytes_handler,
                 .extra1         = &one_ul,
         },
         {
-                .ctl_name       = VM_DIRTY_RATIO,
                 .procname       = "dirty_ratio",
                 .data           = &vm_dirty_ratio,
                 .maxlen         = sizeof(vm_dirty_ratio),
                 .mode           = 0644,
-                .proc_handler   = &dirty_ratio_handler,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = dirty_ratio_handler,
                 .extra1         = &zero,
                 .extra2         = &one_hundred,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "dirty_bytes",
                 .data           = &vm_dirty_bytes,
                 .maxlen         = sizeof(vm_dirty_bytes),
                 .mode           = 0644,
-                .proc_handler   = &dirty_bytes_handler,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = dirty_bytes_handler,
                 .extra1         = &dirty_bytes_min,
         },
         {
@@ -1138,31 +1017,28 @@ static struct ctl_table vm_table[] = {
                 .data           = &dirty_writeback_interval,
                 .maxlen         = sizeof(dirty_writeback_interval),
                 .mode           = 0644,
-                .proc_handler   = &dirty_writeback_centisecs_handler,
+                .proc_handler   = dirty_writeback_centisecs_handler,
         },
         {
                 .procname       = "dirty_expire_centisecs",
                 .data           = &dirty_expire_interval,
                 .maxlen         = sizeof(dirty_expire_interval),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = VM_NR_PDFLUSH_THREADS,
                 .procname       = "nr_pdflush_threads",
                 .data           = &nr_pdflush_threads,
                 .maxlen         = sizeof nr_pdflush_threads,
                 .mode           = 0444 /* read-only*/,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = VM_SWAPPINESS,
                 .procname       = "swappiness",
                 .data           = &vm_swappiness,
                 .maxlen         = sizeof(vm_swappiness),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &zero,
                 .extra2         = &one_hundred,
         },
@@ -1172,255 +1048,213 @@ static struct ctl_table vm_table[] = {
                 .data           = NULL,
                 .maxlen         = sizeof(unsigned long),
                 .mode           = 0644,
-                .proc_handler   = &hugetlb_sysctl_handler,
+                .proc_handler   = hugetlb_sysctl_handler,
                 .extra1         = (void *)&hugetlb_zero,
                 .extra2         = (void *)&hugetlb_infinity,
          },
          {
-                .ctl_name       = VM_HUGETLB_GROUP,
                 .procname       = "hugetlb_shm_group",
                 .data           = &sysctl_hugetlb_shm_group,
                 .maxlen         = sizeof(gid_t),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
          },
          {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "hugepages_treat_as_movable",
                 .data           = &hugepages_treat_as_movable,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &hugetlb_treat_movable_handler,
+                .proc_handler   = hugetlb_treat_movable_handler,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "nr_overcommit_hugepages",
                 .data           = NULL,
                 .maxlen         = sizeof(unsigned long),
                 .mode           = 0644,
-                .proc_handler   = &hugetlb_overcommit_handler,
+                .proc_handler   = hugetlb_overcommit_handler,
                 .extra1         = (void *)&hugetlb_zero,
                 .extra2         = (void *)&hugetlb_infinity,
         },
 #endif
         {
-                .ctl_name       = VM_LOWMEM_RESERVE_RATIO,
                 .procname       = "lowmem_reserve_ratio",
                 .data           = &sysctl_lowmem_reserve_ratio,
                 .maxlen         = sizeof(sysctl_lowmem_reserve_ratio),
                 .mode           = 0644,
-                .proc_handler   = &lowmem_reserve_ratio_sysctl_handler,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = lowmem_reserve_ratio_sysctl_handler,
         },
         {
-                .ctl_name       = VM_DROP_PAGECACHE,
                 .procname       = "drop_caches",
                 .data           = &sysctl_drop_caches,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
                 .proc_handler   = drop_caches_sysctl_handler,
-                .strategy       = &sysctl_intvec,
         },
         {
-                .ctl_name       = VM_MIN_FREE_KBYTES,
                 .procname       = "min_free_kbytes",
                 .data           = &min_free_kbytes,
                 .maxlen         = sizeof(min_free_kbytes),
                 .mode           = 0644,
-                .proc_handler   = &min_free_kbytes_sysctl_handler,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = min_free_kbytes_sysctl_handler,
                 .extra1         = &zero,
         },
         {
-                .ctl_name       = VM_PERCPU_PAGELIST_FRACTION,
                 .procname       = "percpu_pagelist_fraction",
                 .data           = &percpu_pagelist_fraction,
                 .maxlen         = sizeof(percpu_pagelist_fraction),
                 .mode           = 0644,
-                .proc_handler   = &percpu_pagelist_fraction_sysctl_handler,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = percpu_pagelist_fraction_sysctl_handler,
                 .extra1         = &min_percpu_pagelist_fract,
         },
 #ifdef CONFIG_MMU
         {
-                .ctl_name       = VM_MAX_MAP_COUNT,
                 .procname       = "max_map_count",
                 .data           = &sysctl_max_map_count,
                 .maxlen         = sizeof(sysctl_max_map_count),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec
+                .proc_handler   = proc_dointvec
         },
 #else
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "nr_trim_pages",
                 .data           = &sysctl_nr_trim_pages,
                 .maxlen         = sizeof(sysctl_nr_trim_pages),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &zero,
         },
 #endif
         {
-                .ctl_name       = VM_LAPTOP_MODE,
                 .procname       = "laptop_mode",
                 .data           = &laptop_mode,
                 .maxlen         = sizeof(laptop_mode),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_jiffies,
-                .strategy       = &sysctl_jiffies,
+                .proc_handler   = proc_dointvec_jiffies,
         },
         {
-                .ctl_name       = VM_BLOCK_DUMP,
                 .procname       = "block_dump",
                 .data           = &block_dump,
                 .maxlen         = sizeof(block_dump),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec,
                 .extra1         = &zero,
         },
         {
-                .ctl_name       = VM_VFS_CACHE_PRESSURE,
                 .procname       = "vfs_cache_pressure",
                 .data           = &sysctl_vfs_cache_pressure,
                 .maxlen         = sizeof(sysctl_vfs_cache_pressure),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec,
                 .extra1         = &zero,
         },
 #ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
         {
-                .ctl_name       = VM_LEGACY_VA_LAYOUT,
                 .procname       = "legacy_va_layout",
                 .data           = &sysctl_legacy_va_layout,
                 .maxlen         = sizeof(sysctl_legacy_va_layout),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec,
                 .extra1         = &zero,
         },
 #endif
 #ifdef CONFIG_NUMA
         {
-                .ctl_name       = VM_ZONE_RECLAIM_MODE,
                 .procname       = "zone_reclaim_mode",
                 .data           = &zone_reclaim_mode,
                 .maxlen         = sizeof(zone_reclaim_mode),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec,
                 .extra1         = &zero,
         },
         {
-                .ctl_name       = VM_MIN_UNMAPPED,
                 .procname       = "min_unmapped_ratio",
                 .data           = &sysctl_min_unmapped_ratio,
                 .maxlen         = sizeof(sysctl_min_unmapped_ratio),
                 .mode           = 0644,
-                .proc_handler   = &sysctl_min_unmapped_ratio_sysctl_handler,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = sysctl_min_unmapped_ratio_sysctl_handler,
                 .extra1         = &zero,
                 .extra2         = &one_hundred,
         },
         {
-                .ctl_name       = VM_MIN_SLAB,
                 .procname       = "min_slab_ratio",
                 .data           = &sysctl_min_slab_ratio,
                 .maxlen         = sizeof(sysctl_min_slab_ratio),
                 .mode           = 0644,
-                .proc_handler   = &sysctl_min_slab_ratio_sysctl_handler,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = sysctl_min_slab_ratio_sysctl_handler,
                 .extra1         = &zero,
                 .extra2         = &one_hundred,
         },
 #endif
 #ifdef CONFIG_SMP
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "stat_interval",
                 .data           = &sysctl_stat_interval,
                 .maxlen         = sizeof(sysctl_stat_interval),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_jiffies,
-                .strategy       = &sysctl_jiffies,
+                .proc_handler   = proc_dointvec_jiffies,
         },
 #endif
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "mmap_min_addr",
                 .data           = &dac_mmap_min_addr,
                 .maxlen         = sizeof(unsigned long),
                 .mode           = 0644,
-                .proc_handler   = &mmap_min_addr_handler,
+                .proc_handler   = mmap_min_addr_handler,
         },
 #ifdef CONFIG_NUMA
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "numa_zonelist_order",
                 .data           = &numa_zonelist_order,
                 .maxlen         = NUMA_ZONELIST_ORDER_LEN,
                 .mode           = 0644,
-                .proc_handler   = &numa_zonelist_order_handler,
-                .strategy       = &sysctl_string,
+                .proc_handler   = numa_zonelist_order_handler,
         },
 #endif
 #if (defined(CONFIG_X86_32) && !defined(CONFIG_UML))|| \
    (defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL))
         {
-                .ctl_name       = VM_VDSO_ENABLED,
                 .procname       = "vdso_enabled",
                 .data           = &vdso_enabled,
                 .maxlen         = sizeof(vdso_enabled),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec,
                 .extra1         = &zero,
         },
 #endif
 #ifdef CONFIG_HIGHMEM
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "highmem_is_dirtyable",
                 .data           = &vm_highmem_is_dirtyable,
                 .maxlen         = sizeof(vm_highmem_is_dirtyable),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &zero,
                 .extra2         = &one,
         },
 #endif
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "scan_unevictable_pages",
                 .data           = &scan_unevictable_pages,
                 .maxlen         = sizeof(scan_unevictable_pages),
                 .mode           = 0644,
-                .proc_handler   = &scan_unevictable_handler,
+                .proc_handler   = scan_unevictable_handler,
         },
 #ifdef CONFIG_MEMORY_FAILURE
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "memory_failure_early_kill",
                 .data           = &sysctl_memory_failure_early_kill,
                 .maxlen         = sizeof(sysctl_memory_failure_early_kill),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &zero,
                 .extra2         = &one,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "memory_failure_recovery",
                 .data           = &sysctl_memory_failure_recovery,
                 .maxlen         = sizeof(sysctl_memory_failure_recovery),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &zero,
                 .extra2         = &one,
         },
@@ -1430,116 +1264,104 @@ static struct ctl_table vm_table[] = {
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
  */
-        { .ctl_name = 0 }
+        { }
 };
 
 #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
 static struct ctl_table binfmt_misc_table[] = {
-        { .ctl_name = 0 }
+        { }
 };
 #endif
 
 static struct ctl_table fs_table[] = {
         {
-                .ctl_name       = FS_NRINODE,
                 .procname       = "inode-nr",
                 .data           = &inodes_stat,
                 .maxlen         = 2*sizeof(int),
                 .mode           = 0444,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = FS_STATINODE,
                 .procname       = "inode-state",
                 .data           = &inodes_stat,
                 .maxlen         = 7*sizeof(int),
                 .mode           = 0444,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
                 .procname       = "file-nr",
                 .data           = &files_stat,
                 .maxlen         = 3*sizeof(int),
                 .mode           = 0444,
-                .proc_handler   = &proc_nr_files,
+                .proc_handler   = proc_nr_files,
         },
         {
-                .ctl_name       = FS_MAXFILE,
                 .procname       = "file-max",
                 .data           = &files_stat.max_files,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "nr_open",
                 .data           = &sysctl_nr_open,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &sysctl_nr_open_min,
                 .extra2         = &sysctl_nr_open_max,
         },
         {
-                .ctl_name       = FS_DENTRY,
                 .procname       = "dentry-state",
                 .data           = &dentry_stat,
                 .maxlen         = 6*sizeof(int),
                 .mode           = 0444,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
         {
-                .ctl_name       = FS_OVERFLOWUID,
                 .procname       = "overflowuid",
                 .data           = &fs_overflowuid,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &minolduid,
                 .extra2         = &maxolduid,
         },
         {
-                .ctl_name       = FS_OVERFLOWGID,
                 .procname       = "overflowgid",
                 .data           = &fs_overflowgid,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &minolduid,
                 .extra2         = &maxolduid,
         },
 #ifdef CONFIG_FILE_LOCKING
         {
-                .ctl_name       = FS_LEASES,
                 .procname       = "leases-enable",
                 .data           = &leases_enable,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #ifdef CONFIG_DNOTIFY
         {
-                .ctl_name       = FS_DIR_NOTIFY,
                 .procname       = "dir-notify-enable",
                 .data           = &dir_notify_enable,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #ifdef CONFIG_MMU
 #ifdef CONFIG_FILE_LOCKING
         {
-                .ctl_name       = FS_LEASE_TIME,
                 .procname       = "lease-break-time",
                 .data           = &lease_break_time,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
 #endif
 #ifdef CONFIG_AIO
@@ -1548,19 +1370,18 @@ static struct ctl_table fs_table[] = {
                 .data           = &aio_nr,
                 .maxlen         = sizeof(aio_nr),
                 .mode           = 0444,
-                .proc_handler   = &proc_doulongvec_minmax,
+                .proc_handler   = proc_doulongvec_minmax,
         },
         {
                 .procname       = "aio-max-nr",
                 .data           = &aio_max_nr,
                 .maxlen         = sizeof(aio_max_nr),
                 .mode           = 0644,
-                .proc_handler   = &proc_doulongvec_minmax,
+                .proc_handler   = proc_doulongvec_minmax,
         },
 #endif /* CONFIG_AIO */
 #ifdef CONFIG_INOTIFY_USER
         {
-                .ctl_name       = FS_INOTIFY,
                 .procname       = "inotify",
                 .mode           = 0555,
                 .child          = inotify_table,
@@ -1575,19 +1396,16 @@ static struct ctl_table fs_table[] = {
 #endif
 #endif
         {
-                .ctl_name       = KERN_SETUID_DUMPABLE,
                 .procname       = "suid_dumpable",
                 .data           = &suid_dumpable,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &zero,
                 .extra2         = &two,
         },
 #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "binfmt_misc",
                 .mode           = 0555,
                 .child          = binfmt_misc_table,
@@ -1597,13 +1415,12 @@ static struct ctl_table fs_table[] = {
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
  */
-        { .ctl_name = 0 }
+        { }
 };
 
 static struct ctl_table debug_table[] = {
 #if defined(CONFIG_X86) || defined(CONFIG_PPC)
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "exception-trace",
                 .data           = &show_unhandled_signals,
                 .maxlen         = sizeof(int),
@@ -1611,11 +1428,11 @@ static struct ctl_table debug_table[] = {
                 .proc_handler   = proc_dointvec
         },
 #endif
-        { .ctl_name = 0 }
+        { }
 };
 
 static struct ctl_table dev_table[] = {
-        { .ctl_name = 0 }
+        { }
 };
 
 static DEFINE_SPINLOCK(sysctl_lock);
@@ -1769,122 +1586,6 @@ void register_sysctl_root(struct ctl_table_root *root)
         spin_unlock(&sysctl_lock);
 }
 
-#ifdef CONFIG_SYSCTL_SYSCALL
-/* Perform the actual read/write of a sysctl table entry. */
-static int do_sysctl_strategy(struct ctl_table_root *root,
-                        struct ctl_table *table,
-                        void __user *oldval, size_t __user *oldlenp,
-                        void __user *newval, size_t newlen)
-{
-        int op = 0, rc;
-
-        if (oldval)
-                op |= MAY_READ;
-        if (newval)
-                op |= MAY_WRITE;
-        if (sysctl_perm(root, table, op))
-                return -EPERM;
-
-        if (table->strategy) {
-                rc = table->strategy(table, oldval, oldlenp, newval, newlen);
-                if (rc < 0)
-                        return rc;
-                if (rc > 0)
-                        return 0;
-        }
-
-        /* If there is no strategy routine, or if the strategy returns
-         * zero, proceed with automatic r/w */
-        if (table->data && table->maxlen) {
-                rc = sysctl_data(table, oldval, oldlenp, newval, newlen);
-                if (rc < 0)
-                        return rc;
-        }
-        return 0;
-}
-
-static int parse_table(int __user *name, int nlen,
-                       void __user *oldval, size_t __user *oldlenp,
-                       void __user *newval, size_t newlen,
-                       struct ctl_table_root *root,
-                       struct ctl_table *table)
-{
-        int n;
-repeat:
-        if (!nlen)
-                return -ENOTDIR;
-        if (get_user(n, name))
-                return -EFAULT;
-        for ( ; table->ctl_name || table->procname; table++) {
-                if (!table->ctl_name)
-                        continue;
-                if (n == table->ctl_name) {
-                        int error;
-                        if (table->child) {
-                                if (sysctl_perm(root, table, MAY_EXEC))
-                                        return -EPERM;
-                                name++;
-                                nlen--;
-                                table = table->child;
-                                goto repeat;
-                        }
-                        error = do_sysctl_strategy(root, table,
-                                                   oldval, oldlenp,
-                                                   newval, newlen);
-                        return error;
-                }
-        }
-        return -ENOTDIR;
-}
-
-int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp,
-               void __user *newval, size_t newlen)
-{
-        struct ctl_table_header *head;
-        int error = -ENOTDIR;
-
-        if (nlen <= 0 || nlen >= CTL_MAXNAME)
-                return -ENOTDIR;
-        if (oldval) {
-                int old_len;
-                if (!oldlenp || get_user(old_len, oldlenp))
-                        return -EFAULT;
-        }
-
-        for (head = sysctl_head_next(NULL); head;
-                        head = sysctl_head_next(head)) {
-                error = parse_table(name, nlen, oldval, oldlenp, 
-                                        newval, newlen,
-                                        head->root, head->ctl_table);
-                if (error != -ENOTDIR) {
-                        sysctl_head_finish(head);
-                        break;
-                }
-        }
-        return error;
-}
-
-SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args)
-{
-        struct __sysctl_args tmp;
-        int error;
-
-        if (copy_from_user(&tmp, args, sizeof(tmp)))
-                return -EFAULT;
-
-        error = deprecated_sysctl_warning(&tmp);
-        if (error)
-                goto out;
-
-        lock_kernel();
-        error = do_sysctl(tmp.name, tmp.nlen, tmp.oldval, tmp.oldlenp,
-                          tmp.newval, tmp.newlen);
-        unlock_kernel();
-out:
-        return error;
-}
-#endif /* CONFIG_SYSCTL_SYSCALL */
-
 /*
  * sysctl_perm does NOT grant the superuser all rights automatically, because
  * some sysctl variables are readonly even to root.
@@ -1920,7 +1621,7 @@ int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
 
 static void sysctl_set_parent(struct ctl_table *parent, struct ctl_table *table)
 {
-        for (; table->ctl_name || table->procname; table++) {
+        for (; table->procname; table++) {
                 table->parent = parent;
                 if (table->child)
                         sysctl_set_parent(table, table->child);
@@ -1952,11 +1653,11 @@ static struct ctl_table *is_branch_in(struct ctl_table *branch,
                 return NULL;
 
         /* ... and nothing else */
-        if (branch[1].procname || branch[1].ctl_name)
+        if (branch[1].procname)
                 return NULL;
 
         /* table should contain subdirectory with the same name */
-        for (p = table; p->procname || p->ctl_name; p++) {
+        for (p = table; p->procname; p++) {
                 if (!p->child)
                         continue;
                 if (p->procname && strcmp(p->procname, s) == 0)
@@ -2001,9 +1702,6 @@ static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q)
  *
  * The members of the &struct ctl_table structure are used as follows:
  *
- * ctl_name - This is the numeric sysctl value used by sysctl(2). The number
- *            must be unique within that level of sysctl
- *
  * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not
  *            enter a sysctl file
  *
@@ -2018,8 +1716,6 @@ static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q)
  *
  * proc_handler - the text handler routine (described below)
  *
- * strategy - the strategy routine (described below)
- *
  * de - for internal use by the sysctl routines
  *
  * extra1, extra2 - extra pointers usable by the proc handler routines
@@ -2032,19 +1728,6 @@ static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q)
  * struct enable minimal validation of the values being written to be
  * performed, and the mode field allows minimal authentication.
  *
- * More sophisticated management can be enabled by the provision of a
- * strategy routine with the table entry.  This will be called before
- * any automatic read or write of the data is performed.
- *
- * The strategy routine may return
- *
- * < 0 - Error occurred (error is passed to user process)
- *
- * 0   - OK - proceed with automatic read or write.
- *
- * > 0 - OK - read or write has been done by the strategy routine, so
- *       return immediately.
- *
  * There must be a proc_handler routine for any terminal nodes
  * mirrored under /proc/sys (non-terminals are handled by a built-in
  * directory handler).  Several default handlers are available to
@@ -2071,13 +1754,13 @@ struct ctl_table_header *__register_sysctl_paths(
         struct ctl_table_set *set;
 
         /* Count the path components */
-        for (npath = 0; path[npath].ctl_name || path[npath].procname; ++npath)
+        for (npath = 0; path[npath].procname; ++npath)
                 ;
 
         /*
          * For each path component, allocate a 2-element ctl_table array.
          * The first array element will be filled with the sysctl entry
-         * for this, the second will be the sentinel (ctl_name == 0).
+         * for this, the second will be the sentinel (procname == 0).
          *
          * We allocate everything in one go so that we don't have to
          * worry about freeing additional memory in unregister_sysctl_table.
@@ -2094,7 +1777,6 @@ struct ctl_table_header *__register_sysctl_paths(
         for (n = 0; n < npath; ++n, ++path) {
                 /* Copy the procname */
                 new->procname = path->procname;
-                new->ctl_name = path->ctl_name;
                 new->mode     = 0555;
 
                 *prevp = new;
@@ -2956,286 +2638,6 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
 
 #endif /* CONFIG_PROC_FS */
 
-
-#ifdef CONFIG_SYSCTL_SYSCALL
-/*
- * General sysctl support routines 
- */
-
-/* The generic sysctl data routine (used if no strategy routine supplied) */
-int sysctl_data(struct ctl_table *table,
-                void __user *oldval, size_t __user *oldlenp,
-                void __user *newval, size_t newlen)
-{
-        size_t len;
-
-        /* Get out of I don't have a variable */
-        if (!table->data || !table->maxlen)
-                return -ENOTDIR;
-
-        if (oldval && oldlenp) {
-                if (get_user(len, oldlenp))
-                        return -EFAULT;
-                if (len) {
-                        if (len > table->maxlen)
-                                len = table->maxlen;
-                        if (copy_to_user(oldval, table->data, len))
-                                return -EFAULT;
-                        if (put_user(len, oldlenp))
-                                return -EFAULT;
-                }
-        }
-
-        if (newval && newlen) {
-                if (newlen > table->maxlen)
-                        newlen = table->maxlen;
-
-                if (copy_from_user(table->data, newval, newlen))
-                        return -EFAULT;
-        }
-        return 1;
-}
-
-/* The generic string strategy routine: */
-int sysctl_string(struct ctl_table *table,
-                  void __user *oldval, size_t __user *oldlenp,
-                  void __user *newval, size_t newlen)
-{
-        if (!table->data || !table->maxlen) 
-                return -ENOTDIR;
-        
-        if (oldval && oldlenp) {
-                size_t bufsize;
-                if (get_user(bufsize, oldlenp))
-                        return -EFAULT;
-                if (bufsize) {
-                        size_t len = strlen(table->data), copied;
-
-                        /* This shouldn't trigger for a well-formed sysctl */
-                        if (len > table->maxlen)
-                                len = table->maxlen;
-
-                        /* Copy up to a max of bufsize-1 bytes of the string */
-                        copied = (len >= bufsize) ? bufsize - 1 : len;
-
-                        if (copy_to_user(oldval, table->data, copied) ||
-                            put_user(0, (char __user *)(oldval + copied)))
-                                return -EFAULT;
-                        if (put_user(len, oldlenp))
-                                return -EFAULT;
-                }
-        }
-        if (newval && newlen) {
-                size_t len = newlen;
-                if (len > table->maxlen)
-                        len = table->maxlen;
-                if(copy_from_user(table->data, newval, len))
-                        return -EFAULT;
-                if (len == table->maxlen)
-                        len--;
-                ((char *) table->data)[len] = 0;
-        }
-        return 1;
-}
-
-/*
- * This function makes sure that all of the integers in the vector
- * are between the minimum and maximum values given in the arrays
- * table->extra1 and table->extra2, respectively.
- */
-int sysctl_intvec(struct ctl_table *table,
-                void __user *oldval, size_t __user *oldlenp,
-                void __user *newval, size_t newlen)
-{
-
-        if (newval && newlen) {
-                int __user *vec = (int __user *) newval;
-                int *min = (int *) table->extra1;
-                int *max = (int *) table->extra2;
-                size_t length;
-                int i;
-
-                if (newlen % sizeof(int) != 0)
-                        return -EINVAL;
-
-                if (!table->extra1 && !table->extra2)
-                        return 0;
-
-                if (newlen > table->maxlen)
-                        newlen = table->maxlen;
-                length = newlen / sizeof(int);
-
-                for (i = 0; i < length; i++) {
-                        int value;
-                        if (get_user(value, vec + i))
-                                return -EFAULT;
-                        if (min && value < min[i])
-                                return -EINVAL;
-                        if (max && value > max[i])
-                                return -EINVAL;
-                }
-        }
-        return 0;
-}
-
-/* Strategy function to convert jiffies to seconds */ 
-int sysctl_jiffies(struct ctl_table *table,
-                void __user *oldval, size_t __user *oldlenp,
-                void __user *newval, size_t newlen)
-{
-        if (oldval && oldlenp) {
-                size_t olen;
-
-                if (get_user(olen, oldlenp))
-                        return -EFAULT;
-                if (olen) {
-                        int val;
-
-                        if (olen < sizeof(int))
-                                return -EINVAL;
-
-                        val = *(int *)(table->data) / HZ;
-                        if (put_user(val, (int __user *)oldval))
-                                return -EFAULT;
-                        if (put_user(sizeof(int), oldlenp))
-                                return -EFAULT;
-                }
-        }
-        if (newval && newlen) { 
-                int new;
-                if (newlen != sizeof(int))
-                        return -EINVAL; 
-                if (get_user(new, (int __user *)newval))
-                        return -EFAULT;
-                *(int *)(table->data) = new*HZ; 
-        }
-        return 1;
-}
-
-/* Strategy function to convert jiffies to seconds */ 
-int sysctl_ms_jiffies(struct ctl_table *table,
-                void __user *oldval, size_t __user *oldlenp,
-                void __user *newval, size_t newlen)
-{
-        if (oldval && oldlenp) {
-                size_t olen;
-
-                if (get_user(olen, oldlenp))
-                        return -EFAULT;
-                if (olen) {
-                        int val;
-
-                        if (olen < sizeof(int))
-                                return -EINVAL;
-
-                        val = jiffies_to_msecs(*(int *)(table->data));
-                        if (put_user(val, (int __user *)oldval))
-                                return -EFAULT;
-                        if (put_user(sizeof(int), oldlenp))
-                                return -EFAULT;
-                }
-        }
-        if (newval && newlen) { 
-                int new;
-                if (newlen != sizeof(int))
-                        return -EINVAL; 
-                if (get_user(new, (int __user *)newval))
-                        return -EFAULT;
-                *(int *)(table->data) = msecs_to_jiffies(new);
-        }
-        return 1;
-}
-
-
-
-#else /* CONFIG_SYSCTL_SYSCALL */
-
-
-SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args)
-{
-        struct __sysctl_args tmp;
-        int error;
-
-        if (copy_from_user(&tmp, args, sizeof(tmp)))
-                return -EFAULT;
-
-        error = deprecated_sysctl_warning(&tmp);
-
-        /* If no error reading the parameters then just -ENOSYS ... */
-        if (!error)
-                error = -ENOSYS;
-
-        return error;
-}
-
-int sysctl_data(struct ctl_table *table,
-                  void __user *oldval, size_t __user *oldlenp,
-                  void __user *newval, size_t newlen)
-{
-        return -ENOSYS;
-}
-
-int sysctl_string(struct ctl_table *table,
-                  void __user *oldval, size_t __user *oldlenp,
-                  void __user *newval, size_t newlen)
-{
-        return -ENOSYS;
-}
-
-int sysctl_intvec(struct ctl_table *table,
-                void __user *oldval, size_t __user *oldlenp,
-                void __user *newval, size_t newlen)
-{
-        return -ENOSYS;
-}
-
-int sysctl_jiffies(struct ctl_table *table,
-                void __user *oldval, size_t __user *oldlenp,
-                void __user *newval, size_t newlen)
-{
-        return -ENOSYS;
-}
-
-int sysctl_ms_jiffies(struct ctl_table *table,
-                void __user *oldval, size_t __user *oldlenp,
-                void __user *newval, size_t newlen)
-{
-        return -ENOSYS;
-}
-
-#endif /* CONFIG_SYSCTL_SYSCALL */
-
-static int deprecated_sysctl_warning(struct __sysctl_args *args)
-{
-        static int msg_count;
-        int name[CTL_MAXNAME];
-        int i;
-
-        /* Check args->nlen. */
-        if (args->nlen < 0 || args->nlen > CTL_MAXNAME)
-                return -ENOTDIR;
-
-        /* Read in the sysctl name for better debug message logging */
-        for (i = 0; i < args->nlen; i++)
-                if (get_user(name[i], args->name + i))
-                        return -EFAULT;
-
-        /* Ignore accesses to kernel.version */
-        if ((args->nlen == 2) && (name[0] == CTL_KERN) && (name[1] == KERN_VERSION))
-                return 0;
-
-        if (msg_count < 5) {
-                msg_count++;
-                printk(KERN_INFO
-                        "warning: process `%s' used the deprecated sysctl "
-                        "system call with ", current->comm);
-                for (i = 0; i < args->nlen; i++)
-                        printk("%d.", name[i]);
-                printk("\n");
-        }
-        return 0;
-}
-
 /*
  * No sense putting this after each symbol definition, twice,
  * exception granted :-)
@@ -3250,9 +2652,4 @@ EXPORT_SYMBOL(proc_doulongvec_minmax);
 EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax);
 EXPORT_SYMBOL(register_sysctl_table);
 EXPORT_SYMBOL(register_sysctl_paths);
-EXPORT_SYMBOL(sysctl_intvec);
-EXPORT_SYMBOL(sysctl_jiffies);
-EXPORT_SYMBOL(sysctl_ms_jiffies);
-EXPORT_SYMBOL(sysctl_string);
-EXPORT_SYMBOL(sysctl_data);
 EXPORT_SYMBOL(unregister_sysctl_table);
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
new file mode 100644
index 000000000000..b75dbf40f573
--- /dev/null
+++ b/kernel/sysctl_binary.c
@@ -0,0 +1,1507 @@
+#include <linux/stat.h>
+#include <linux/sysctl.h>
+#include "../fs/xfs/linux-2.6/xfs_sysctl.h"
+#include <linux/sunrpc/debug.h>
+#include <linux/string.h>
+#include <net/ip_vs.h>
+#include <linux/syscalls.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
+#include <linux/fs.h>
+#include <linux/nsproxy.h>
+#include <linux/pid_namespace.h>
+#include <linux/file.h>
+#include <linux/ctype.h>
+#include <linux/netdevice.h>
+
+#ifdef CONFIG_SYSCTL_SYSCALL
+
+struct bin_table;
+typedef ssize_t bin_convert_t(struct file *file,
+        void __user *oldval, size_t oldlen, void __user *newval, size_t newlen);
+
+static bin_convert_t bin_dir;
+static bin_convert_t bin_string;
+static bin_convert_t bin_intvec;
+static bin_convert_t bin_ulongvec;
+static bin_convert_t bin_uuid;
+static bin_convert_t bin_dn_node_address;
+
+#define CTL_DIR   bin_dir
+#define CTL_STR   bin_string
+#define CTL_INT   bin_intvec
+#define CTL_ULONG bin_ulongvec
+#define CTL_UUID  bin_uuid
+#define CTL_DNADR bin_dn_node_address
+
+#define BUFSZ 256
+
+struct bin_table {
+        bin_convert_t           *convert;
+        int                     ctl_name;
+        const char              *procname;
+        const struct bin_table  *child;
+};
+
+static const struct bin_table bin_random_table[] = {
+        { CTL_INT,      RANDOM_POOLSIZE,        "poolsize" },
+        { CTL_INT,      RANDOM_ENTROPY_COUNT,   "entropy_avail" },
+        { CTL_INT,      RANDOM_READ_THRESH,     "read_wakeup_threshold" },
+        { CTL_INT,      RANDOM_WRITE_THRESH,    "write_wakeup_threshold" },
+        { CTL_UUID,     RANDOM_BOOT_ID,         "boot_id" },
+        { CTL_UUID,     RANDOM_UUID,            "uuid" },
+        {}
+};
+
+static const struct bin_table bin_pty_table[] = {
+        { CTL_INT,      PTY_MAX,        "max" },
+        { CTL_INT,      PTY_NR,         "nr" },
+        {}
+};
+
+static const struct bin_table bin_kern_table[] = {
+        { CTL_STR,      KERN_OSTYPE,                    "ostype" },
+        { CTL_STR,      KERN_OSRELEASE,                 "osrelease" },
+        /* KERN_OSREV not used */
+        { CTL_STR,      KERN_VERSION,                   "version" },
+        /* KERN_SECUREMASK not used */
+        /* KERN_PROF not used */
+        { CTL_STR,      KERN_NODENAME,                  "hostname" },
+        { CTL_STR,      KERN_DOMAINNAME,                "domainname" },
+
+        { CTL_INT,      KERN_PANIC,                     "panic" },
+        { CTL_INT,      KERN_REALROOTDEV,               "real-root-dev" },
+
+        { CTL_STR,      KERN_SPARC_REBOOT,              "reboot-cmd" },
+        { CTL_INT,      KERN_CTLALTDEL,                 "ctrl-alt-del" },
+        { CTL_INT,      KERN_PRINTK,                    "printk" },
+
+        /* KERN_NAMETRANS not used */
+        /* KERN_PPC_HTABRECLAIM not used */
+        /* KERN_PPC_ZEROPAGED not used */
+        { CTL_INT,      KERN_PPC_POWERSAVE_NAP,         "powersave-nap" },
+
+        { CTL_STR,      KERN_MODPROBE,                  "modprobe" },
+        { CTL_INT,      KERN_SG_BIG_BUFF,               "sg-big-buff" },
+        { CTL_INT,      KERN_ACCT,                      "acct" },
+        /* KERN_PPC_L2CR "l2cr" no longer used */
+
+        /* KERN_RTSIGNR not used */
+        /* KERN_RTSIGMAX not used */
+
+        { CTL_ULONG,    KERN_SHMMAX,                    "shmmax" },
+        { CTL_INT,      KERN_MSGMAX,                    "msgmax" },
+        { CTL_INT,      KERN_MSGMNB,                    "msgmnb" },
+        /* KERN_MSGPOOL not used*/
+        { CTL_INT,      KERN_SYSRQ,                     "sysrq" },
+        { CTL_INT,      KERN_MAX_THREADS,               "threads-max" },
+        { CTL_DIR,      KERN_RANDOM,                    "random",       bin_random_table },
+        { CTL_ULONG,    KERN_SHMALL,                    "shmall" },
+        { CTL_INT,      KERN_MSGMNI,                    "msgmni" },
+        { CTL_INT,      KERN_SEM,                       "sem" },
+        { CTL_INT,      KERN_SPARC_STOP_A,              "stop-a" },
+        { CTL_INT,      KERN_SHMMNI,                    "shmmni" },
+
+        { CTL_INT,      KERN_OVERFLOWUID,               "overflowuid" },
+        { CTL_INT,      KERN_OVERFLOWGID,               "overflowgid" },
+
+        { CTL_STR,      KERN_HOTPLUG,                   "hotplug", },
+        { CTL_INT,      KERN_IEEE_EMULATION_WARNINGS,   "ieee_emulation_warnings" },
+
+        { CTL_INT,      KERN_S390_USER_DEBUG_LOGGING,   "userprocess_debug" },
+        { CTL_INT,      KERN_CORE_USES_PID,             "core_uses_pid" },
+        /* KERN_TAINTED "tainted" no longer used */
+        { CTL_INT,      KERN_CADPID,                    "cad_pid" },
+        { CTL_INT,      KERN_PIDMAX,                    "pid_max" },
+        { CTL_STR,      KERN_CORE_PATTERN,              "core_pattern" },
+        { CTL_INT,      KERN_PANIC_ON_OOPS,             "panic_on_oops" },
+        { CTL_INT,      KERN_HPPA_PWRSW,                "soft-power" },
+        { CTL_INT,      KERN_HPPA_UNALIGNED,            "unaligned-trap" },
+
+        { CTL_INT,      KERN_PRINTK_RATELIMIT,          "printk_ratelimit" },
+        { CTL_INT,      KERN_PRINTK_RATELIMIT_BURST,    "printk_ratelimit_burst" },
+
+        { CTL_DIR,      KERN_PTY,                       "pty",          bin_pty_table },
+        { CTL_INT,      KERN_NGROUPS_MAX,               "ngroups_max" },
+        { CTL_INT,      KERN_SPARC_SCONS_PWROFF,        "scons-poweroff" },
+        /* KERN_HZ_TIMER "hz_timer" no longer used */
+        { CTL_INT,      KERN_UNKNOWN_NMI_PANIC,         "unknown_nmi_panic" },
+        { CTL_INT,      KERN_BOOTLOADER_TYPE,           "bootloader_type" },
+        { CTL_INT,      KERN_RANDOMIZE,                 "randomize_va_space" },
+
+        { CTL_INT,      KERN_SPIN_RETRY,                "spin_retry" },
+        /* KERN_ACPI_VIDEO_FLAGS "acpi_video_flags" no longer used */
+        { CTL_INT,      KERN_IA64_UNALIGNED,            "ignore-unaligned-usertrap" },
+        { CTL_INT,      KERN_COMPAT_LOG,                "compat-log" },
+        { CTL_INT,      KERN_MAX_LOCK_DEPTH,            "max_lock_depth" },
+        { CTL_INT,      KERN_NMI_WATCHDOG,              "nmi_watchdog" },
+        { CTL_INT,      KERN_PANIC_ON_NMI,              "panic_on_unrecovered_nmi" },
+        {}
+};
+
+static const struct bin_table bin_vm_table[] = {
+        { CTL_INT,      VM_OVERCOMMIT_MEMORY,           "overcommit_memory" },
+        { CTL_INT,      VM_PAGE_CLUSTER,                "page-cluster" },
+        { CTL_INT,      VM_DIRTY_BACKGROUND,            "dirty_background_ratio" },
+        { CTL_INT,      VM_DIRTY_RATIO,                 "dirty_ratio" },
+        /* VM_DIRTY_WB_CS "dirty_writeback_centisecs" no longer used */
+        /* VM_DIRTY_EXPIRE_CS "dirty_expire_centisecs" no longer used */
+        { CTL_INT,      VM_NR_PDFLUSH_THREADS,          "nr_pdflush_threads" },
+        { CTL_INT,      VM_OVERCOMMIT_RATIO,            "overcommit_ratio" },
+        /* VM_PAGEBUF unused */
+        /* VM_HUGETLB_PAGES "nr_hugepages" no longer used */
+        { CTL_INT,      VM_SWAPPINESS,                  "swappiness" },
+        { CTL_INT,      VM_LOWMEM_RESERVE_RATIO,        "lowmem_reserve_ratio" },
+        { CTL_INT,      VM_MIN_FREE_KBYTES,             "min_free_kbytes" },
+        { CTL_INT,      VM_MAX_MAP_COUNT,               "max_map_count" },
+        { CTL_INT,      VM_LAPTOP_MODE,                 "laptop_mode" },
+        { CTL_INT,      VM_BLOCK_DUMP,                  "block_dump" },
+        { CTL_INT,      VM_HUGETLB_GROUP,               "hugetlb_shm_group" },
+        { CTL_INT,      VM_VFS_CACHE_PRESSURE,  "vfs_cache_pressure" },
+        { CTL_INT,      VM_LEGACY_VA_LAYOUT,            "legacy_va_layout" },
+        /* VM_SWAP_TOKEN_TIMEOUT unused */
+        { CTL_INT,      VM_DROP_PAGECACHE,              "drop_caches" },
+        { CTL_INT,      VM_PERCPU_PAGELIST_FRACTION,    "percpu_pagelist_fraction" },
+        { CTL_INT,      VM_ZONE_RECLAIM_MODE,           "zone_reclaim_mode" },
+        { CTL_INT,      VM_MIN_UNMAPPED,                "min_unmapped_ratio" },
+        { CTL_INT,      VM_PANIC_ON_OOM,                "panic_on_oom" },
+        { CTL_INT,      VM_VDSO_ENABLED,                "vdso_enabled" },
+        { CTL_INT,      VM_MIN_SLAB,                    "min_slab_ratio" },
+
+        {}
+};
+
+static const struct bin_table bin_net_core_table[] = {
+        { CTL_INT,      NET_CORE_WMEM_MAX,      "wmem_max" },
+        { CTL_INT,      NET_CORE_RMEM_MAX,      "rmem_max" },
+        { CTL_INT,      NET_CORE_WMEM_DEFAULT,  "wmem_default" },
+        { CTL_INT,      NET_CORE_RMEM_DEFAULT,  "rmem_default" },
+        /* NET_CORE_DESTROY_DELAY unused */
+        { CTL_INT,      NET_CORE_MAX_BACKLOG,   "netdev_max_backlog" },
+        /* NET_CORE_FASTROUTE unused */
+        { CTL_INT,      NET_CORE_MSG_COST,      "message_cost" },
+        { CTL_INT,      NET_CORE_MSG_BURST,     "message_burst" },
+        { CTL_INT,      NET_CORE_OPTMEM_MAX,    "optmem_max" },
+        /* NET_CORE_HOT_LIST_LENGTH unused */
+        /* NET_CORE_DIVERT_VERSION unused */
+        /* NET_CORE_NO_CONG_THRESH unused */
+        /* NET_CORE_NO_CONG unused */
+        /* NET_CORE_LO_CONG unused */
+        /* NET_CORE_MOD_CONG unused */
+        { CTL_INT,      NET_CORE_DEV_WEIGHT,    "dev_weight" },
+        { CTL_INT,      NET_CORE_SOMAXCONN,     "somaxconn" },
+        { CTL_INT,      NET_CORE_BUDGET,        "netdev_budget" },
+        { CTL_INT,      NET_CORE_AEVENT_ETIME,  "xfrm_aevent_etime" },
+        { CTL_INT,      NET_CORE_AEVENT_RSEQTH, "xfrm_aevent_rseqth" },
+        { CTL_INT,      NET_CORE_WARNINGS,      "warnings" },
+        {},
+};
+
+static const struct bin_table bin_net_unix_table[] = {
+        /* NET_UNIX_DESTROY_DELAY unused */
+        /* NET_UNIX_DELETE_DELAY unused */
+        { CTL_INT,      NET_UNIX_MAX_DGRAM_QLEN,        "max_dgram_qlen" },
+        {}
+};
+
+static const struct bin_table bin_net_ipv4_route_table[] = {
+        { CTL_INT,      NET_IPV4_ROUTE_FLUSH,                   "flush" },
+        /* NET_IPV4_ROUTE_MIN_DELAY "min_delay" no longer used */
+        /* NET_IPV4_ROUTE_MAX_DELAY "max_delay" no longer used */
+        { CTL_INT,      NET_IPV4_ROUTE_GC_THRESH,               "gc_thresh" },
+        { CTL_INT,      NET_IPV4_ROUTE_MAX_SIZE,                "max_size" },
+        { CTL_INT,      NET_IPV4_ROUTE_GC_MIN_INTERVAL,         "gc_min_interval" },
+        { CTL_INT,      NET_IPV4_ROUTE_GC_MIN_INTERVAL_MS,      "gc_min_interval_ms" },
+        { CTL_INT,      NET_IPV4_ROUTE_GC_TIMEOUT,              "gc_timeout" },
+        { CTL_INT,      NET_IPV4_ROUTE_GC_INTERVAL,             "gc_interval" },
+        { CTL_INT,      NET_IPV4_ROUTE_REDIRECT_LOAD,           "redirect_load" },
+        { CTL_INT,      NET_IPV4_ROUTE_REDIRECT_NUMBER,         "redirect_number" },
+        { CTL_INT,      NET_IPV4_ROUTE_REDIRECT_SILENCE,        "redirect_silence" },
+        { CTL_INT,      NET_IPV4_ROUTE_ERROR_COST,              "error_cost" },
+        { CTL_INT,      NET_IPV4_ROUTE_ERROR_BURST,             "error_burst" },
+        { CTL_INT,      NET_IPV4_ROUTE_GC_ELASTICITY,           "gc_elasticity" },
+        { CTL_INT,      NET_IPV4_ROUTE_MTU_EXPIRES,             "mtu_expires" },
+        { CTL_INT,      NET_IPV4_ROUTE_MIN_PMTU,                "min_pmtu" },
+        { CTL_INT,      NET_IPV4_ROUTE_MIN_ADVMSS,              "min_adv_mss" },
+        { CTL_INT,      NET_IPV4_ROUTE_SECRET_INTERVAL,         "secret_interval" },
+        {}
+};
+
+static const struct bin_table bin_net_ipv4_conf_vars_table[] = {
+        { CTL_INT,      NET_IPV4_CONF_FORWARDING,               "forwarding" },
+        { CTL_INT,      NET_IPV4_CONF_MC_FORWARDING,            "mc_forwarding" },
+
+        { CTL_INT,      NET_IPV4_CONF_ACCEPT_REDIRECTS,         "accept_redirects" },
+        { CTL_INT,      NET_IPV4_CONF_SECURE_REDIRECTS,         "secure_redirects" },
+        { CTL_INT,      NET_IPV4_CONF_SEND_REDIRECTS,           "send_redirects" },
+        { CTL_INT,      NET_IPV4_CONF_SHARED_MEDIA,             "shared_media" },
+        { CTL_INT,      NET_IPV4_CONF_RP_FILTER,                "rp_filter" },
+        { CTL_INT,      NET_IPV4_CONF_ACCEPT_SOURCE_ROUTE,      "accept_source_route" },
+        { CTL_INT,      NET_IPV4_CONF_PROXY_ARP,                "proxy_arp" },
+        { CTL_INT,      NET_IPV4_CONF_MEDIUM_ID,                "medium_id" },
+        { CTL_INT,      NET_IPV4_CONF_BOOTP_RELAY,              "bootp_relay" },
+        { CTL_INT,      NET_IPV4_CONF_LOG_MARTIANS,             "log_martians" },
+        { CTL_INT,      NET_IPV4_CONF_TAG,                      "tag" },
+        { CTL_INT,      NET_IPV4_CONF_ARPFILTER,                "arp_filter" },
+        { CTL_INT,      NET_IPV4_CONF_ARP_ANNOUNCE,             "arp_announce" },
+        { CTL_INT,      NET_IPV4_CONF_ARP_IGNORE,               "arp_ignore" },
+        { CTL_INT,      NET_IPV4_CONF_ARP_ACCEPT,               "arp_accept" },
+        { CTL_INT,      NET_IPV4_CONF_ARP_NOTIFY,               "arp_notify" },
+
+        { CTL_INT,      NET_IPV4_CONF_NOXFRM,                   "disable_xfrm" },
+        { CTL_INT,      NET_IPV4_CONF_NOPOLICY,                 "disable_policy" },
+        { CTL_INT,      NET_IPV4_CONF_FORCE_IGMP_VERSION,       "force_igmp_version" },
+        { CTL_INT,      NET_IPV4_CONF_PROMOTE_SECONDARIES,      "promote_secondaries" },
+        {}
+};
+
+static const struct bin_table bin_net_ipv4_conf_table[] = {
+        { CTL_DIR,      NET_PROTO_CONF_ALL,     "all",          bin_net_ipv4_conf_vars_table },
+        { CTL_DIR,      NET_PROTO_CONF_DEFAULT, "default",      bin_net_ipv4_conf_vars_table },
+        { CTL_DIR,      0, NULL, bin_net_ipv4_conf_vars_table },
+        {}
+};
+
+static const struct bin_table bin_net_neigh_vars_table[] = {
+        { CTL_INT,      NET_NEIGH_MCAST_SOLICIT,        "mcast_solicit" },
+        { CTL_INT,      NET_NEIGH_UCAST_SOLICIT,        "ucast_solicit" },
+        { CTL_INT,      NET_NEIGH_APP_SOLICIT,          "app_solicit" },
+        /* NET_NEIGH_RETRANS_TIME "retrans_time" no longer used */
+        { CTL_INT,      NET_NEIGH_REACHABLE_TIME,       "base_reachable_time" },
+        { CTL_INT,      NET_NEIGH_DELAY_PROBE_TIME,     "delay_first_probe_time" },
+        { CTL_INT,      NET_NEIGH_GC_STALE_TIME,        "gc_stale_time" },
+        { CTL_INT,      NET_NEIGH_UNRES_QLEN,           "unres_qlen" },
+        { CTL_INT,      NET_NEIGH_PROXY_QLEN,           "proxy_qlen" },
+        /* NET_NEIGH_ANYCAST_DELAY "anycast_delay" no longer used */
+        /* NET_NEIGH_PROXY_DELAY "proxy_delay" no longer used */
+        /* NET_NEIGH_LOCKTIME "locktime" no longer used */
+        { CTL_INT,      NET_NEIGH_GC_INTERVAL,          "gc_interval" },
+        { CTL_INT,      NET_NEIGH_GC_THRESH1,           "gc_thresh1" },
+        { CTL_INT,      NET_NEIGH_GC_THRESH2,           "gc_thresh2" },
+        { CTL_INT,      NET_NEIGH_GC_THRESH3,           "gc_thresh3" },
+        { CTL_INT,      NET_NEIGH_RETRANS_TIME_MS,      "retrans_time_ms" },
+        { CTL_INT,      NET_NEIGH_REACHABLE_TIME_MS,    "base_reachable_time_ms" },
+        {}
+};
+
+static const struct bin_table bin_net_neigh_table[] = {
+        { CTL_DIR,      NET_PROTO_CONF_DEFAULT, "default", bin_net_neigh_vars_table },
+        { CTL_DIR,      0, NULL, bin_net_neigh_vars_table },
+        {}
+};
+
+static const struct bin_table bin_net_ipv4_netfilter_table[] = {
+        { CTL_INT,      NET_IPV4_NF_CONNTRACK_MAX,              "ip_conntrack_max" },
+
+        /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT "ip_conntrack_tcp_timeout_syn_sent" no longer used */
+        /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV "ip_conntrack_tcp_timeout_syn_recv" no longer used */
+        /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED "ip_conntrack_tcp_timeout_established" no longer used */
+        /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT "ip_conntrack_tcp_timeout_fin_wait" no longer used */
+        /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT "ip_conntrack_tcp_timeout_close_wait" no longer used */
+        /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK "ip_conntrack_tcp_timeout_last_ack" no longer used */
+        /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT "ip_conntrack_tcp_timeout_time_wait" no longer used */
+        /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE "ip_conntrack_tcp_timeout_close" no longer used */
+
+        /* NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT "ip_conntrack_udp_timeout" no longer used */
+        /* NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT_STREAM "ip_conntrack_udp_timeout_stream" no longer used */
+        /* NET_IPV4_NF_CONNTRACK_ICMP_TIMEOUT "ip_conntrack_icmp_timeout" no longer used */
+        /* NET_IPV4_NF_CONNTRACK_GENERIC_TIMEOUT "ip_conntrack_generic_timeout" no longer used */
+
+        { CTL_INT,      NET_IPV4_NF_CONNTRACK_BUCKETS,          "ip_conntrack_buckets" },
+        { CTL_INT,      NET_IPV4_NF_CONNTRACK_LOG_INVALID,      "ip_conntrack_log_invalid" },
+        /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS "ip_conntrack_tcp_timeout_max_retrans" no longer used */
+        { CTL_INT,      NET_IPV4_NF_CONNTRACK_TCP_LOOSE,        "ip_conntrack_tcp_loose" },
+        { CTL_INT,      NET_IPV4_NF_CONNTRACK_TCP_BE_LIBERAL,   "ip_conntrack_tcp_be_liberal" },
+        { CTL_INT,      NET_IPV4_NF_CONNTRACK_TCP_MAX_RETRANS,  "ip_conntrack_tcp_max_retrans" },
+
+        /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED "ip_conntrack_sctp_timeout_closed" no longer used */
+        /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT "ip_conntrack_sctp_timeout_cookie_wait" no longer used */
+        /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED "ip_conntrack_sctp_timeout_cookie_echoed" no longer used */
+        /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED "ip_conntrack_sctp_timeout_established" no longer used */
+        /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT "ip_conntrack_sctp_timeout_shutdown_sent" no longer used */
+        /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD "ip_conntrack_sctp_timeout_shutdown_recd" no longer used */
+        /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT "ip_conntrack_sctp_timeout_shutdown_ack_sent" no longer used */
+
+        { CTL_INT,      NET_IPV4_NF_CONNTRACK_COUNT,            "ip_conntrack_count" },
+        { CTL_INT,      NET_IPV4_NF_CONNTRACK_CHECKSUM,         "ip_conntrack_checksum" },
+        {}
+};
+
+static const struct bin_table bin_net_ipv4_table[] = {
+        {CTL_INT,       NET_IPV4_FORWARD,                       "ip_forward" },
+
+        { CTL_DIR,      NET_IPV4_CONF,          "conf",         bin_net_ipv4_conf_table },
+        { CTL_DIR,      NET_IPV4_NEIGH,         "neigh",        bin_net_neigh_table },
+        { CTL_DIR,      NET_IPV4_ROUTE,         "route",        bin_net_ipv4_route_table },
+        /* NET_IPV4_FIB_HASH unused */
+        { CTL_DIR,      NET_IPV4_NETFILTER,     "netfilter",    bin_net_ipv4_netfilter_table },
+
+        { CTL_INT,      NET_IPV4_TCP_TIMESTAMPS,                "tcp_timestamps" },
+        { CTL_INT,      NET_IPV4_TCP_WINDOW_SCALING,            "tcp_window_scaling" },
+        { CTL_INT,      NET_IPV4_TCP_SACK,                      "tcp_sack" },
+        { CTL_INT,      NET_IPV4_TCP_RETRANS_COLLAPSE,          "tcp_retrans_collapse" },
+        { CTL_INT,      NET_IPV4_DEFAULT_TTL,                   "ip_default_ttl" },
+        /* NET_IPV4_AUTOCONFIG unused */
+        { CTL_INT,      NET_IPV4_NO_PMTU_DISC,                  "ip_no_pmtu_disc" },
+        { CTL_INT,      NET_IPV4_NONLOCAL_BIND,                 "ip_nonlocal_bind" },
+        { CTL_INT,      NET_IPV4_TCP_SYN_RETRIES,               "tcp_syn_retries" },
+        { CTL_INT,      NET_TCP_SYNACK_RETRIES,                 "tcp_synack_retries" },
+        { CTL_INT,      NET_TCP_MAX_ORPHANS,                    "tcp_max_orphans" },
+        { CTL_INT,      NET_TCP_MAX_TW_BUCKETS,                 "tcp_max_tw_buckets" },
+        { CTL_INT,      NET_IPV4_DYNADDR,                       "ip_dynaddr" },
+        { CTL_INT,      NET_IPV4_TCP_KEEPALIVE_TIME,            "tcp_keepalive_time" },
+        { CTL_INT,      NET_IPV4_TCP_KEEPALIVE_PROBES,          "tcp_keepalive_probes" },
+        { CTL_INT,      NET_IPV4_TCP_KEEPALIVE_INTVL,           "tcp_keepalive_intvl" },
+        { CTL_INT,      NET_IPV4_TCP_RETRIES1,                  "tcp_retries1" },
+        { CTL_INT,      NET_IPV4_TCP_RETRIES2,                  "tcp_retries2" },
+        { CTL_INT,      NET_IPV4_TCP_FIN_TIMEOUT,               "tcp_fin_timeout" },
+        { CTL_INT,      NET_TCP_SYNCOOKIES,                     "tcp_syncookies" },
+        { CTL_INT,      NET_TCP_TW_RECYCLE,                     "tcp_tw_recycle" },
+        { CTL_INT,      NET_TCP_ABORT_ON_OVERFLOW,              "tcp_abort_on_overflow" },
+        { CTL_INT,      NET_TCP_STDURG,                         "tcp_stdurg" },
+        { CTL_INT,      NET_TCP_RFC1337,                        "tcp_rfc1337" },
+        { CTL_INT,      NET_TCP_MAX_SYN_BACKLOG,                "tcp_max_syn_backlog" },
+        { CTL_INT,      NET_IPV4_LOCAL_PORT_RANGE,              "ip_local_port_range" },
+        { CTL_INT,      NET_IPV4_IGMP_MAX_MEMBERSHIPS,          "igmp_max_memberships" },
+        { CTL_INT,      NET_IPV4_IGMP_MAX_MSF,                  "igmp_max_msf" },
+        { CTL_INT,      NET_IPV4_INET_PEER_THRESHOLD,           "inet_peer_threshold" },
+        { CTL_INT,      NET_IPV4_INET_PEER_MINTTL,              "inet_peer_minttl" },
+        { CTL_INT,      NET_IPV4_INET_PEER_MAXTTL,              "inet_peer_maxttl" },
+        { CTL_INT,      NET_IPV4_INET_PEER_GC_MINTIME,          "inet_peer_gc_mintime" },
+        { CTL_INT,      NET_IPV4_INET_PEER_GC_MAXTIME,          "inet_peer_gc_maxtime" },
+        { CTL_INT,      NET_TCP_ORPHAN_RETRIES,                 "tcp_orphan_retries" },
+        { CTL_INT,      NET_TCP_FACK,                           "tcp_fack" },
+        { CTL_INT,      NET_TCP_REORDERING,                     "tcp_reordering" },
+        { CTL_INT,      NET_TCP_ECN,                            "tcp_ecn" },
+        { CTL_INT,      NET_TCP_DSACK,                          "tcp_dsack" },
+        { CTL_INT,      NET_TCP_MEM,                            "tcp_mem" },
+        { CTL_INT,      NET_TCP_WMEM,                           "tcp_wmem" },
+        { CTL_INT,      NET_TCP_RMEM,                           "tcp_rmem" },
+        { CTL_INT,      NET_TCP_APP_WIN,                        "tcp_app_win" },
+        { CTL_INT,      NET_TCP_ADV_WIN_SCALE,                  "tcp_adv_win_scale" },
+        { CTL_INT,      NET_TCP_TW_REUSE,                       "tcp_tw_reuse" },
+        { CTL_INT,      NET_TCP_FRTO,                           "tcp_frto" },
+        { CTL_INT,      NET_TCP_FRTO_RESPONSE,                  "tcp_frto_response" },
+        { CTL_INT,      NET_TCP_LOW_LATENCY,                    "tcp_low_latency" },
+        { CTL_INT,      NET_TCP_NO_METRICS_SAVE,                "tcp_no_metrics_save" },
+        { CTL_INT,      NET_TCP_MODERATE_RCVBUF,                "tcp_moderate_rcvbuf" },
+        { CTL_INT,      NET_TCP_TSO_WIN_DIVISOR,                "tcp_tso_win_divisor" },
+        { CTL_STR,      NET_TCP_CONG_CONTROL,                   "tcp_congestion_control" },
+        { CTL_INT,      NET_TCP_ABC,                            "tcp_abc" },
+        { CTL_INT,      NET_TCP_MTU_PROBING,                    "tcp_mtu_probing" },
+        { CTL_INT,      NET_TCP_BASE_MSS,                       "tcp_base_mss" },
+        { CTL_INT,      NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS, "tcp_workaround_signed_windows" },
+        { CTL_INT,      NET_TCP_DMA_COPYBREAK,                  "tcp_dma_copybreak" },
+        { CTL_INT,      NET_TCP_SLOW_START_AFTER_IDLE,          "tcp_slow_start_after_idle" },
+        { CTL_INT,      NET_CIPSOV4_CACHE_ENABLE,               "cipso_cache_enable" },
+        { CTL_INT,      NET_CIPSOV4_CACHE_BUCKET_SIZE,          "cipso_cache_bucket_size" },
+        { CTL_INT,      NET_CIPSOV4_RBM_OPTFMT,                 "cipso_rbm_optfmt" },
+        { CTL_INT,      NET_CIPSOV4_RBM_STRICTVALID,            "cipso_rbm_strictvalid" },
+        /* NET_TCP_AVAIL_CONG_CONTROL "tcp_available_congestion_control" no longer used */
+        { CTL_STR,      NET_TCP_ALLOWED_CONG_CONTROL,           "tcp_allowed_congestion_control" },
+        { CTL_INT,      NET_TCP_MAX_SSTHRESH,                   "tcp_max_ssthresh" },
+
+        { CTL_INT,      NET_IPV4_ICMP_ECHO_IGNORE_ALL,          "icmp_echo_ignore_all" },
+        { CTL_INT,      NET_IPV4_ICMP_ECHO_IGNORE_BROADCASTS,   "icmp_echo_ignore_broadcasts" },
+        { CTL_INT,      NET_IPV4_ICMP_IGNORE_BOGUS_ERROR_RESPONSES,     "icmp_ignore_bogus_error_responses" },
+        { CTL_INT,      NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR,        "icmp_errors_use_inbound_ifaddr" },
+        { CTL_INT,      NET_IPV4_ICMP_RATELIMIT,                "icmp_ratelimit" },
+        { CTL_INT,      NET_IPV4_ICMP_RATEMASK,                 "icmp_ratemask" },
+
+        { CTL_INT,      NET_IPV4_IPFRAG_HIGH_THRESH,            "ipfrag_high_thresh" },
+        { CTL_INT,      NET_IPV4_IPFRAG_LOW_THRESH,             "ipfrag_low_thresh" },
+        { CTL_INT,      NET_IPV4_IPFRAG_TIME,                   "ipfrag_time" },
+
+        { CTL_INT,      NET_IPV4_IPFRAG_SECRET_INTERVAL,        "ipfrag_secret_interval" },
+        /* NET_IPV4_IPFRAG_MAX_DIST "ipfrag_max_dist" no longer used */
+
+        { CTL_INT,      2088 /* NET_IPQ_QMAX */,                "ip_queue_maxlen" },
+
+        /* NET_TCP_DEFAULT_WIN_SCALE unused */
+        /* NET_TCP_BIC_BETA unused */
+        /* NET_IPV4_TCP_MAX_KA_PROBES unused */
+        /* NET_IPV4_IP_MASQ_DEBUG unused */
+        /* NET_TCP_SYN_TAILDROP unused */
+        /* NET_IPV4_ICMP_SOURCEQUENCH_RATE unused */
+        /* NET_IPV4_ICMP_DESTUNREACH_RATE unused */
+        /* NET_IPV4_ICMP_TIMEEXCEED_RATE unused */
+        /* NET_IPV4_ICMP_PARAMPROB_RATE unused */
+        /* NET_IPV4_ICMP_ECHOREPLY_RATE unused */
+        /* NET_IPV4_ALWAYS_DEFRAG unused */
+        {}
+};
+
+static const struct bin_table bin_net_ipx_table[] = {
+        { CTL_INT,      NET_IPX_PPROP_BROADCASTING,     "ipx_pprop_broadcasting" },
+        /* NET_IPX_FORWARDING unused */
+        {}
+};
+
+static const struct bin_table bin_net_atalk_table[] = {
+        { CTL_INT,      NET_ATALK_AARP_EXPIRY_TIME,             "aarp-expiry-time" },
+        { CTL_INT,      NET_ATALK_AARP_TICK_TIME,               "aarp-tick-time" },
+        { CTL_INT,      NET_ATALK_AARP_RETRANSMIT_LIMIT,        "aarp-retransmit-limit" },
+        { CTL_INT,      NET_ATALK_AARP_RESOLVE_TIME,            "aarp-resolve-time" },
+        {},
+};
+
+static const struct bin_table bin_net_netrom_table[] = {
+        { CTL_INT,      NET_NETROM_DEFAULT_PATH_QUALITY,                "default_path_quality" },
+        { CTL_INT,      NET_NETROM_OBSOLESCENCE_COUNT_INITIALISER,      "obsolescence_count_initialiser" },
+        { CTL_INT,      NET_NETROM_NETWORK_TTL_INITIALISER,             "network_ttl_initialiser" },
+        { CTL_INT,      NET_NETROM_TRANSPORT_TIMEOUT,                   "transport_timeout" },
+        { CTL_INT,      NET_NETROM_TRANSPORT_MAXIMUM_TRIES,             "transport_maximum_tries" },
+        { CTL_INT,      NET_NETROM_TRANSPORT_ACKNOWLEDGE_DELAY,         "transport_acknowledge_delay" },
+        { CTL_INT,      NET_NETROM_TRANSPORT_BUSY_DELAY,                "transport_busy_delay" },
+        { CTL_INT,      NET_NETROM_TRANSPORT_REQUESTED_WINDOW_SIZE,     "transport_requested_window_size" },
+        { CTL_INT,      NET_NETROM_TRANSPORT_NO_ACTIVITY_TIMEOUT,       "transport_no_activity_timeout" },
+        { CTL_INT,      NET_NETROM_ROUTING_CONTROL,                     "routing_control" },
+        { CTL_INT,      NET_NETROM_LINK_FAILS_COUNT,                    "link_fails_count" },
+        { CTL_INT,      NET_NETROM_RESET,                               "reset" },
+        {}
+};
+
+static const struct bin_table bin_net_ax25_param_table[] = {
+        { CTL_INT,      NET_AX25_IP_DEFAULT_MODE,       "ip_default_mode" },
+        { CTL_INT,      NET_AX25_DEFAULT_MODE,          "ax25_default_mode" },
+        { CTL_INT,      NET_AX25_BACKOFF_TYPE,          "backoff_type" },
+        { CTL_INT,      NET_AX25_CONNECT_MODE,          "connect_mode" },
+        { CTL_INT,      NET_AX25_STANDARD_WINDOW,       "standard_window_size" },
+        { CTL_INT,      NET_AX25_EXTENDED_WINDOW,       "extended_window_size" },
+        { CTL_INT,      NET_AX25_T1_TIMEOUT,            "t1_timeout" },
+        { CTL_INT,      NET_AX25_T2_TIMEOUT,            "t2_timeout" },
+        { CTL_INT,      NET_AX25_T3_TIMEOUT,            "t3_timeout" },
+        { CTL_INT,      NET_AX25_IDLE_TIMEOUT,          "idle_timeout" },
+        { CTL_INT,      NET_AX25_N2,                    "maximum_retry_count" },
+        { CTL_INT,      NET_AX25_PACLEN,                "maximum_packet_length" },
+        { CTL_INT,      NET_AX25_PROTOCOL,              "protocol" },
+        { CTL_INT,      NET_AX25_DAMA_SLAVE_TIMEOUT,    "dama_slave_timeout" },
+        {}
+};
+
+static const struct bin_table bin_net_ax25_table[] = {
+        { CTL_DIR,      0, NULL, bin_net_ax25_param_table },
+        {}
+};
+
+static const struct bin_table bin_net_rose_table[] = {
+        { CTL_INT,      NET_ROSE_RESTART_REQUEST_TIMEOUT,       "restart_request_timeout" },
+        { CTL_INT,      NET_ROSE_CALL_REQUEST_TIMEOUT,          "call_request_timeout" },
+        { CTL_INT,      NET_ROSE_RESET_REQUEST_TIMEOUT,         "reset_request_timeout" },
+        { CTL_INT,      NET_ROSE_CLEAR_REQUEST_TIMEOUT,         "clear_request_timeout" },
+        { CTL_INT,      NET_ROSE_ACK_HOLD_BACK_TIMEOUT,         "acknowledge_hold_back_timeout" },
+        { CTL_INT,      NET_ROSE_ROUTING_CONTROL,               "routing_control" },
+        { CTL_INT,      NET_ROSE_LINK_FAIL_TIMEOUT,             "link_fail_timeout" },
+        { CTL_INT,      NET_ROSE_MAX_VCS,                       "maximum_virtual_circuits" },
+        { CTL_INT,      NET_ROSE_WINDOW_SIZE,                   "window_size" },
+        { CTL_INT,      NET_ROSE_NO_ACTIVITY_TIMEOUT,           "no_activity_timeout" },
+        {}
+};
+
+static const struct bin_table bin_net_ipv6_conf_var_table[] = {
+        { CTL_INT,      NET_IPV6_FORWARDING,                    "forwarding" },
+        { CTL_INT,      NET_IPV6_HOP_LIMIT,                     "hop_limit" },
+        { CTL_INT,      NET_IPV6_MTU,                           "mtu" },
+        { CTL_INT,      NET_IPV6_ACCEPT_RA,                     "accept_ra" },
+        { CTL_INT,      NET_IPV6_ACCEPT_REDIRECTS,              "accept_redirects" },
+        { CTL_INT,      NET_IPV6_AUTOCONF,                      "autoconf" },
+        { CTL_INT,      NET_IPV6_DAD_TRANSMITS,                 "dad_transmits" },
+        { CTL_INT,      NET_IPV6_RTR_SOLICITS,                  "router_solicitations" },
+        { CTL_INT,      NET_IPV6_RTR_SOLICIT_INTERVAL,          "router_solicitation_interval" },
+        { CTL_INT,      NET_IPV6_RTR_SOLICIT_DELAY,             "router_solicitation_delay" },
+        { CTL_INT,      NET_IPV6_USE_TEMPADDR,                  "use_tempaddr" },
+        { CTL_INT,      NET_IPV6_TEMP_VALID_LFT,                "temp_valid_lft" },
+        { CTL_INT,      NET_IPV6_TEMP_PREFERED_LFT,             "temp_prefered_lft" },
+        { CTL_INT,      NET_IPV6_REGEN_MAX_RETRY,               "regen_max_retry" },
+        { CTL_INT,      NET_IPV6_MAX_DESYNC_FACTOR,             "max_desync_factor" },
+        { CTL_INT,      NET_IPV6_MAX_ADDRESSES,                 "max_addresses" },
+        { CTL_INT,      NET_IPV6_FORCE_MLD_VERSION,             "force_mld_version" },
+        { CTL_INT,      NET_IPV6_ACCEPT_RA_DEFRTR,              "accept_ra_defrtr" },
+        { CTL_INT,      NET_IPV6_ACCEPT_RA_PINFO,               "accept_ra_pinfo" },
+        { CTL_INT,      NET_IPV6_ACCEPT_RA_RTR_PREF,            "accept_ra_rtr_pref" },
+        { CTL_INT,      NET_IPV6_RTR_PROBE_INTERVAL,            "router_probe_interval" },
+        { CTL_INT,      NET_IPV6_ACCEPT_RA_RT_INFO_MAX_PLEN,    "accept_ra_rt_info_max_plen" },
+        { CTL_INT,      NET_IPV6_PROXY_NDP,                     "proxy_ndp" },
+        { CTL_INT,      NET_IPV6_ACCEPT_SOURCE_ROUTE,           "accept_source_route" },
+        {}
+};
+
+static const struct bin_table bin_net_ipv6_conf_table[] = {
+        { CTL_DIR,      NET_PROTO_CONF_ALL,             "all",  bin_net_ipv6_conf_var_table },
+        { CTL_DIR,      NET_PROTO_CONF_DEFAULT,         "default", bin_net_ipv6_conf_var_table },
+        { CTL_DIR,      0, NULL, bin_net_ipv6_conf_var_table },
+        {}
+};
+
+static const struct bin_table bin_net_ipv6_route_table[] = {
+        /* NET_IPV6_ROUTE_FLUSH "flush"  no longer used */
+        { CTL_INT,      NET_IPV6_ROUTE_GC_THRESH,               "gc_thresh" },
+        { CTL_INT,      NET_IPV6_ROUTE_MAX_SIZE,                "max_size" },
+        { CTL_INT,      NET_IPV6_ROUTE_GC_MIN_INTERVAL,         "gc_min_interval" },
+        { CTL_INT,      NET_IPV6_ROUTE_GC_TIMEOUT,              "gc_timeout" },
+        { CTL_INT,      NET_IPV6_ROUTE_GC_INTERVAL,             "gc_interval" },
+        { CTL_INT,      NET_IPV6_ROUTE_GC_ELASTICITY,           "gc_elasticity" },
+        { CTL_INT,      NET_IPV6_ROUTE_MTU_EXPIRES,             "mtu_expires" },
+        { CTL_INT,      NET_IPV6_ROUTE_MIN_ADVMSS,              "min_adv_mss" },
+        { CTL_INT,      NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS,      "gc_min_interval_ms" },
+        {}
+};
+
+static const struct bin_table bin_net_ipv6_icmp_table[] = {
+        { CTL_INT,      NET_IPV6_ICMP_RATELIMIT,        "ratelimit" },
+        {}
+};
+
+static const struct bin_table bin_net_ipv6_table[] = {
+        { CTL_DIR,      NET_IPV6_CONF,          "conf",         bin_net_ipv6_conf_table },
+        { CTL_DIR,      NET_IPV6_NEIGH,         "neigh",        bin_net_neigh_table },
+        { CTL_DIR,      NET_IPV6_ROUTE,         "route",        bin_net_ipv6_route_table },
+        { CTL_DIR,      NET_IPV6_ICMP,          "icmp",         bin_net_ipv6_icmp_table },
+        { CTL_INT,      NET_IPV6_BINDV6ONLY,            "bindv6only" },
+        { CTL_INT,      NET_IPV6_IP6FRAG_HIGH_THRESH,   "ip6frag_high_thresh" },
+        { CTL_INT,      NET_IPV6_IP6FRAG_LOW_THRESH,    "ip6frag_low_thresh" },
+        { CTL_INT,      NET_IPV6_IP6FRAG_TIME,          "ip6frag_time" },
+        { CTL_INT,      NET_IPV6_IP6FRAG_SECRET_INTERVAL,       "ip6frag_secret_interval" },
+        { CTL_INT,      NET_IPV6_MLD_MAX_MSF,           "mld_max_msf" },
+        { CTL_INT,      2088 /* IPQ_QMAX */,            "ip6_queue_maxlen" },
+        {}
+};
+
+static const struct bin_table bin_net_x25_table[] = {
+        { CTL_INT,      NET_X25_RESTART_REQUEST_TIMEOUT,        "restart_request_timeout" },
+        { CTL_INT,      NET_X25_CALL_REQUEST_TIMEOUT,           "call_request_timeout" },
+        { CTL_INT,      NET_X25_RESET_REQUEST_TIMEOUT,  "reset_request_timeout" },
+        { CTL_INT,      NET_X25_CLEAR_REQUEST_TIMEOUT,  "clear_request_timeout" },
+        { CTL_INT,      NET_X25_ACK_HOLD_BACK_TIMEOUT,  "acknowledgement_hold_back_timeout" },
+        { CTL_INT,      NET_X25_FORWARD,                        "x25_forward" },
+        {}
+};
+
+static const struct bin_table bin_net_tr_table[] = {
+        { CTL_INT,      NET_TR_RIF_TIMEOUT,     "rif_timeout" },
+        {}
+};
+
+
+static const struct bin_table bin_net_decnet_conf_vars[] = {
+        { CTL_INT,      NET_DECNET_CONF_DEV_FORWARDING, "forwarding" },
+        { CTL_INT,      NET_DECNET_CONF_DEV_PRIORITY,   "priority" },
+        { CTL_INT,      NET_DECNET_CONF_DEV_T2,         "t2" },
+        { CTL_INT,      NET_DECNET_CONF_DEV_T3,         "t3" },
+        {}
+};
+
+static const struct bin_table bin_net_decnet_conf[] = {
+        { CTL_DIR, NET_DECNET_CONF_ETHER,    "ethernet", bin_net_decnet_conf_vars },
+        { CTL_DIR, NET_DECNET_CONF_GRE,      "ipgre",    bin_net_decnet_conf_vars },
+        { CTL_DIR, NET_DECNET_CONF_X25,      "x25",      bin_net_decnet_conf_vars },
+        { CTL_DIR, NET_DECNET_CONF_PPP,      "ppp",      bin_net_decnet_conf_vars },
+        { CTL_DIR, NET_DECNET_CONF_DDCMP,    "ddcmp",    bin_net_decnet_conf_vars },
+        { CTL_DIR, NET_DECNET_CONF_LOOPBACK, "loopback", bin_net_decnet_conf_vars },
+        { CTL_DIR, 0,                        NULL,       bin_net_decnet_conf_vars },
+        {}
+};
+
+static const struct bin_table bin_net_decnet_table[] = {
+        { CTL_DIR,      NET_DECNET_CONF,                "conf", bin_net_decnet_conf },
+        { CTL_DNADR,    NET_DECNET_NODE_ADDRESS,        "node_address" },
+        { CTL_STR,      NET_DECNET_NODE_NAME,           "node_name" },
+        { CTL_STR,      NET_DECNET_DEFAULT_DEVICE,      "default_device" },
+        { CTL_INT,      NET_DECNET_TIME_WAIT,           "time_wait" },
+        { CTL_INT,      NET_DECNET_DN_COUNT,            "dn_count" },
+        { CTL_INT,      NET_DECNET_DI_COUNT,            "di_count" },
+        { CTL_INT,      NET_DECNET_DR_COUNT,            "dr_count" },
+        { CTL_INT,      NET_DECNET_DST_GC_INTERVAL,     "dst_gc_interval" },
+        { CTL_INT,      NET_DECNET_NO_FC_MAX_CWND,      "no_fc_max_cwnd" },
+        { CTL_INT,      NET_DECNET_MEM,         "decnet_mem" },
+        { CTL_INT,      NET_DECNET_RMEM,                "decnet_rmem" },
+        { CTL_INT,      NET_DECNET_WMEM,                "decnet_wmem" },
+        { CTL_INT,      NET_DECNET_DEBUG_LEVEL, "debug" },
+        {}
+};
+
+static const struct bin_table bin_net_sctp_table[] = {
+        { CTL_INT,      NET_SCTP_RTO_INITIAL,           "rto_initial" },
+        { CTL_INT,      NET_SCTP_RTO_MIN,               "rto_min" },
+        { CTL_INT,      NET_SCTP_RTO_MAX,               "rto_max" },
+        { CTL_INT,      NET_SCTP_RTO_ALPHA,             "rto_alpha_exp_divisor" },
+        { CTL_INT,      NET_SCTP_RTO_BETA,              "rto_beta_exp_divisor" },
+        { CTL_INT,      NET_SCTP_VALID_COOKIE_LIFE,     "valid_cookie_life" },
+        { CTL_INT,      NET_SCTP_ASSOCIATION_MAX_RETRANS,       "association_max_retrans" },
+        { CTL_INT,      NET_SCTP_PATH_MAX_RETRANS,      "path_max_retrans" },
+        { CTL_INT,      NET_SCTP_MAX_INIT_RETRANSMITS,  "max_init_retransmits" },
+        { CTL_INT,      NET_SCTP_HB_INTERVAL,           "hb_interval" },
+        { CTL_INT,      NET_SCTP_PRESERVE_ENABLE,       "cookie_preserve_enable" },
+        { CTL_INT,      NET_SCTP_MAX_BURST,             "max_burst" },
+        { CTL_INT,      NET_SCTP_ADDIP_ENABLE,          "addip_enable" },
+        { CTL_INT,      NET_SCTP_PRSCTP_ENABLE,         "prsctp_enable" },
+        { CTL_INT,      NET_SCTP_SNDBUF_POLICY,         "sndbuf_policy" },
+        { CTL_INT,      NET_SCTP_SACK_TIMEOUT,          "sack_timeout" },
+        { CTL_INT,      NET_SCTP_RCVBUF_POLICY,         "rcvbuf_policy" },
+        {}
+};
+
+static const struct bin_table bin_net_llc_llc2_timeout_table[] = {
+        { CTL_INT,      NET_LLC2_ACK_TIMEOUT,   "ack" },
+        { CTL_INT,      NET_LLC2_P_TIMEOUT,     "p" },
+        { CTL_INT,      NET_LLC2_REJ_TIMEOUT,   "rej" },
+        { CTL_INT,      NET_LLC2_BUSY_TIMEOUT,  "busy" },
+        {}
+};
+
+static const struct bin_table bin_net_llc_station_table[] = {
+        { CTL_INT,      NET_LLC_STATION_ACK_TIMEOUT,    "ack_timeout" },
+        {}
+};
+
+static const struct bin_table bin_net_llc_llc2_table[] = {
+        { CTL_DIR,      NET_LLC2,               "timeout",      bin_net_llc_llc2_timeout_table },
+        {}
+};
+
+static const struct bin_table bin_net_llc_table[] = {
+        { CTL_DIR,      NET_LLC2,               "llc2",         bin_net_llc_llc2_table },
+        { CTL_DIR,      NET_LLC_STATION,        "station",      bin_net_llc_station_table },
+        {}
+};
+
+static const struct bin_table bin_net_netfilter_table[] = {
+        { CTL_INT,      NET_NF_CONNTRACK_MAX,                   "nf_conntrack_max" },
+        /* NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT "nf_conntrack_tcp_timeout_syn_sent" no longer used */
+        /* NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV "nf_conntrack_tcp_timeout_syn_recv" no longer used */
+        /* NET_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED "nf_conntrack_tcp_timeout_established" no longer used */
+        /* NET_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT "nf_conntrack_tcp_timeout_fin_wait" no longer used */
+        /* NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT "nf_conntrack_tcp_timeout_close_wait" no longer used */
+        /* NET_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK "nf_conntrack_tcp_timeout_last_ack" no longer used */
+        /* NET_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT "nf_conntrack_tcp_timeout_time_wait" no longer used */
+        /* NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE "nf_conntrack_tcp_timeout_close" no longer used */
+        /* NET_NF_CONNTRACK_UDP_TIMEOUT "nf_conntrack_udp_timeout" no longer used */
+        /* NET_NF_CONNTRACK_UDP_TIMEOUT_STREAM "nf_conntrack_udp_timeout_stream" no longer used */
+        /* NET_NF_CONNTRACK_ICMP_TIMEOUT "nf_conntrack_icmp_timeout" no longer used */
+        /* NET_NF_CONNTRACK_GENERIC_TIMEOUT "nf_conntrack_generic_timeout" no longer used */
+        { CTL_INT,      NET_NF_CONNTRACK_BUCKETS,               "nf_conntrack_buckets" },
+        { CTL_INT,      NET_NF_CONNTRACK_LOG_INVALID,           "nf_conntrack_log_invalid" },
+        /* NET_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS "nf_conntrack_tcp_timeout_max_retrans" no longer used */
+        { CTL_INT,      NET_NF_CONNTRACK_TCP_LOOSE,             "nf_conntrack_tcp_loose" },
+        { CTL_INT,      NET_NF_CONNTRACK_TCP_BE_LIBERAL,        "nf_conntrack_tcp_be_liberal" },
+        { CTL_INT,      NET_NF_CONNTRACK_TCP_MAX_RETRANS,       "nf_conntrack_tcp_max_retrans" },
+        /* NET_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED "nf_conntrack_sctp_timeout_closed" no longer used */
+        /* NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT "nf_conntrack_sctp_timeout_cookie_wait" no longer used */
+        /* NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED "nf_conntrack_sctp_timeout_cookie_echoed" no longer used */
+        /* NET_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED "nf_conntrack_sctp_timeout_established" no longer used */
+        /* NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT "nf_conntrack_sctp_timeout_shutdown_sent" no longer used */
+        /* NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD "nf_conntrack_sctp_timeout_shutdown_recd" no longer used */
+        /* NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT "nf_conntrack_sctp_timeout_shutdown_ack_sent" no longer used */
+        { CTL_INT,      NET_NF_CONNTRACK_COUNT,                 "nf_conntrack_count" },
+        /* NET_NF_CONNTRACK_ICMPV6_TIMEOUT "nf_conntrack_icmpv6_timeout" no longer used */
+        /* NET_NF_CONNTRACK_FRAG6_TIMEOUT "nf_conntrack_frag6_timeout" no longer used */
+        { CTL_INT,      NET_NF_CONNTRACK_FRAG6_LOW_THRESH,      "nf_conntrack_frag6_low_thresh" },
+        { CTL_INT,      NET_NF_CONNTRACK_FRAG6_HIGH_THRESH,     "nf_conntrack_frag6_high_thresh" },
+        { CTL_INT,      NET_NF_CONNTRACK_CHECKSUM,              "nf_conntrack_checksum" },
+
+        {}
+};
+
+static const struct bin_table bin_net_irda_table[] = {
+        { CTL_INT,      NET_IRDA_DISCOVERY,             "discovery" },
+        { CTL_STR,      NET_IRDA_DEVNAME,               "devname" },
+        { CTL_INT,      NET_IRDA_DEBUG,                 "debug" },
+        { CTL_INT,      NET_IRDA_FAST_POLL,             "fast_poll_increase" },
+        { CTL_INT,      NET_IRDA_DISCOVERY_SLOTS,       "discovery_slots" },
+        { CTL_INT,      NET_IRDA_DISCOVERY_TIMEOUT,     "discovery_timeout" },
+        { CTL_INT,      NET_IRDA_SLOT_TIMEOUT,          "slot_timeout" },
+        { CTL_INT,      NET_IRDA_MAX_BAUD_RATE,         "max_baud_rate" },
+        { CTL_INT,      NET_IRDA_MIN_TX_TURN_TIME,      "min_tx_turn_time" },
+        { CTL_INT,      NET_IRDA_MAX_TX_DATA_SIZE,      "max_tx_data_size" },
+        { CTL_INT,      NET_IRDA_MAX_TX_WINDOW,         "max_tx_window" },
+        { CTL_INT,      NET_IRDA_MAX_NOREPLY_TIME,      "max_noreply_time" },
+        { CTL_INT,      NET_IRDA_WARN_NOREPLY_TIME,     "warn_noreply_time" },
+        { CTL_INT,      NET_IRDA_LAP_KEEPALIVE_TIME,    "lap_keepalive_time" },
+        {}
+};
+
+static const struct bin_table bin_net_table[] = {
+        { CTL_DIR,      NET_CORE,               "core",         bin_net_core_table },
+        /* NET_ETHER not used */
+        /* NET_802 not used */
+        { CTL_DIR,      NET_UNIX,               "unix",         bin_net_unix_table },
+        { CTL_DIR,      NET_IPV4,               "ipv4",         bin_net_ipv4_table },
+        { CTL_DIR,      NET_IPX,                "ipx",          bin_net_ipx_table },
+        { CTL_DIR,      NET_ATALK,              "appletalk",    bin_net_atalk_table },
+        { CTL_DIR,      NET_NETROM,             "netrom",       bin_net_netrom_table },
+        { CTL_DIR,      NET_AX25,               "ax25",         bin_net_ax25_table },
+        /*  NET_BRIDGE "bridge" no longer used */
+        { CTL_DIR,      NET_ROSE,               "rose",         bin_net_rose_table },
+        { CTL_DIR,      NET_IPV6,               "ipv6",         bin_net_ipv6_table },
+        { CTL_DIR,      NET_X25,                "x25",          bin_net_x25_table },
+        { CTL_DIR,      NET_TR,                 "token-ring",   bin_net_tr_table },
+        { CTL_DIR,      NET_DECNET,             "decnet",       bin_net_decnet_table },
+        /*  NET_ECONET not used */
+        { CTL_DIR,      NET_SCTP,               "sctp",         bin_net_sctp_table },
+        { CTL_DIR,      NET_LLC,                "llc",          bin_net_llc_table },
+        { CTL_DIR,      NET_NETFILTER,          "netfilter",    bin_net_netfilter_table },
+        /* NET_DCCP "dccp" no longer used */
+        { CTL_DIR,      NET_IRDA,               "irda",         bin_net_irda_table },
+        { CTL_INT,      2089,                   "nf_conntrack_max" },
+        {}
+};
+
+static const struct bin_table bin_fs_quota_table[] = {
+        { CTL_INT,      FS_DQ_LOOKUPS,          "lookups" },
+        { CTL_INT,      FS_DQ_DROPS,            "drops" },
+        { CTL_INT,      FS_DQ_READS,            "reads" },
+        { CTL_INT,      FS_DQ_WRITES,           "writes" },
+        { CTL_INT,      FS_DQ_CACHE_HITS,       "cache_hits" },
+        { CTL_INT,      FS_DQ_ALLOCATED,        "allocated_dquots" },
+        { CTL_INT,      FS_DQ_FREE,             "free_dquots" },
+        { CTL_INT,      FS_DQ_SYNCS,            "syncs" },
+        { CTL_INT,      FS_DQ_WARNINGS,         "warnings" },
+        {}
+};
+
+static const struct bin_table bin_fs_xfs_table[] = {
+        { CTL_INT,      XFS_SGID_INHERIT,       "irix_sgid_inherit" },
+        { CTL_INT,      XFS_SYMLINK_MODE,       "irix_symlink_mode" },
+        { CTL_INT,      XFS_PANIC_MASK,         "panic_mask" },
+
+        { CTL_INT,      XFS_ERRLEVEL,           "error_level" },
+        { CTL_INT,      XFS_SYNCD_TIMER,        "xfssyncd_centisecs" },
+        { CTL_INT,      XFS_INHERIT_SYNC,       "inherit_sync" },
+        { CTL_INT,      XFS_INHERIT_NODUMP,     "inherit_nodump" },
+        { CTL_INT,      XFS_INHERIT_NOATIME,    "inherit_noatime" },
+        { CTL_INT,      XFS_BUF_TIMER,          "xfsbufd_centisecs" },
+        { CTL_INT,      XFS_BUF_AGE,            "age_buffer_centisecs" },
+        { CTL_INT,      XFS_INHERIT_NOSYM,      "inherit_nosymlinks" },
+        { CTL_INT,      XFS_ROTORSTEP,  "rotorstep" },
+        { CTL_INT,      XFS_INHERIT_NODFRG,     "inherit_nodefrag" },
+        { CTL_INT,      XFS_FILESTREAM_TIMER,   "filestream_centisecs" },
+        { CTL_INT,      XFS_STATS_CLEAR,        "stats_clear" },
+        {}
+};
+
+static const struct bin_table bin_fs_ocfs2_nm_table[] = {
+        { CTL_STR,      1, "hb_ctl_path" },
+        {}
+};
+
+static const struct bin_table bin_fs_ocfs2_table[] = {
+        { CTL_DIR,      1,      "nm",   bin_fs_ocfs2_nm_table },
+        {}
+};
+
+static const struct bin_table bin_inotify_table[] = {
+        { CTL_INT,      INOTIFY_MAX_USER_INSTANCES,     "max_user_instances" },
+        { CTL_INT,      INOTIFY_MAX_USER_WATCHES,       "max_user_watches" },
+        { CTL_INT,      INOTIFY_MAX_QUEUED_EVENTS,      "max_queued_events" },
+        {}
+};
+
+static const struct bin_table bin_fs_table[] = {
+        { CTL_INT,      FS_NRINODE,             "inode-nr" },
+        { CTL_INT,      FS_STATINODE,           "inode-state" },
+        /* FS_MAXINODE unused */
+        /* FS_NRDQUOT unused */
+        /* FS_MAXDQUOT unused */
+        /* FS_NRFILE "file-nr" no longer used */
+        { CTL_INT,      FS_MAXFILE,             "file-max" },
+        { CTL_INT,      FS_DENTRY,              "dentry-state" },
+        /* FS_NRSUPER unused */
+        /* FS_MAXUPSER unused */
+        { CTL_INT,      FS_OVERFLOWUID,         "overflowuid" },
+        { CTL_INT,      FS_OVERFLOWGID,         "overflowgid" },
+        { CTL_INT,      FS_LEASES,              "leases-enable" },
+        { CTL_INT,      FS_DIR_NOTIFY,          "dir-notify-enable" },
+        { CTL_INT,      FS_LEASE_TIME,          "lease-break-time" },
+        { CTL_DIR,      FS_DQSTATS,             "quota",        bin_fs_quota_table },
+        { CTL_DIR,      FS_XFS,                 "xfs",          bin_fs_xfs_table },
+        { CTL_ULONG,    FS_AIO_NR,              "aio-nr" },
+        { CTL_ULONG,    FS_AIO_MAX_NR,          "aio-max-nr" },
+        { CTL_DIR,      FS_INOTIFY,             "inotify",      bin_inotify_table },
+        { CTL_DIR,      FS_OCFS2,               "ocfs2",        bin_fs_ocfs2_table },
+        { CTL_INT,      KERN_SETUID_DUMPABLE,   "suid_dumpable" },
+        {}
+};
+
+static const struct bin_table bin_ipmi_table[] = {
+        { CTL_INT,      DEV_IPMI_POWEROFF_POWERCYCLE,   "poweroff_powercycle" },
+        {}
+};
+
+static const struct bin_table bin_mac_hid_files[] = {
+        /* DEV_MAC_HID_KEYBOARD_SENDS_LINUX_KEYCODES unused */
+        /* DEV_MAC_HID_KEYBOARD_LOCK_KEYCODES unused */
+        { CTL_INT,      DEV_MAC_HID_MOUSE_BUTTON_EMULATION,     "mouse_button_emulation" },
+        { CTL_INT,      DEV_MAC_HID_MOUSE_BUTTON2_KEYCODE,      "mouse_button2_keycode" },
+        { CTL_INT,      DEV_MAC_HID_MOUSE_BUTTON3_KEYCODE,      "mouse_button3_keycode" },
+        /* DEV_MAC_HID_ADB_MOUSE_SENDS_KEYCODES unused */
+        {}
+};
+
+static const struct bin_table bin_raid_table[] = {
+        { CTL_INT,      DEV_RAID_SPEED_LIMIT_MIN,       "speed_limit_min" },
+        { CTL_INT,      DEV_RAID_SPEED_LIMIT_MAX,       "speed_limit_max" },
+        {}
+};
+
+static const struct bin_table bin_scsi_table[] = {
+        { CTL_INT, DEV_SCSI_LOGGING_LEVEL, "logging_level" },
+        {}
+};
+
+static const struct bin_table bin_dev_table[] = {
+        /* DEV_CDROM    "cdrom" no longer used */
+        /* DEV_HWMON unused */
+        /* DEV_PARPORT  "parport" no longer used */
+        { CTL_DIR,      DEV_RAID,       "raid",         bin_raid_table },
+        { CTL_DIR,      DEV_MAC_HID,    "mac_hid",      bin_mac_hid_files },
+        { CTL_DIR,      DEV_SCSI,       "scsi",         bin_scsi_table },
+        { CTL_DIR,      DEV_IPMI,       "ipmi",         bin_ipmi_table },
+        {}
+};
+
+static const struct bin_table bin_bus_isa_table[] = {
+        { CTL_INT,      BUS_ISA_MEM_BASE,       "membase" },
+        { CTL_INT,      BUS_ISA_PORT_BASE,      "portbase" },
+        { CTL_INT,      BUS_ISA_PORT_SHIFT,     "portshift" },
+        {}
+};
+
+static const struct bin_table bin_bus_table[] = {
+        { CTL_DIR,      CTL_BUS_ISA,    "isa",  bin_bus_isa_table },
+        {}
+};
+
+
+static const struct bin_table bin_s390dbf_table[] = {
+        { CTL_INT,      5678 /* CTL_S390DBF_STOPPABLE */, "debug_stoppable" },
+        { CTL_INT,      5679 /* CTL_S390DBF_ACTIVE */,    "debug_active" },
+        {}
+};
+
+static const struct bin_table bin_sunrpc_table[] = {
+        /* CTL_RPCDEBUG "rpc_debug"  no longer used */
+        /* CTL_NFSDEBUG "nfs_debug"  no longer used */
+        /* CTL_NFSDDEBUG "nfsd_debug" no longer used  */
+        /* CTL_NLMDEBUG "nlm_debug" no longer used */
+
+        { CTL_INT,      CTL_SLOTTABLE_UDP,      "udp_slot_table_entries" },
+        { CTL_INT,      CTL_SLOTTABLE_TCP,      "tcp_slot_table_entries" },
+        { CTL_INT,      CTL_MIN_RESVPORT,       "min_resvport" },
+        { CTL_INT,      CTL_MAX_RESVPORT,       "max_resvport" },
+        {}
+};
+
+static const struct bin_table bin_pm_table[] = {
+        /* frv specific */
+        /* 1 == CTL_PM_SUSPEND  "suspend"  no longer used" */
+        { CTL_INT,      2 /* CTL_PM_CMODE */,           "cmode" },
+        { CTL_INT,      3 /* CTL_PM_P0 */,              "p0" },
+        { CTL_INT,      4 /* CTL_PM_CM */,              "cm" },
+        {}
+};
+
+static const struct bin_table bin_root_table[] = {
+        { CTL_DIR,      CTL_KERN,       "kernel",       bin_kern_table },
+        { CTL_DIR,      CTL_VM,         "vm",           bin_vm_table },
+        { CTL_DIR,      CTL_NET,        "net",          bin_net_table },
+        /* CTL_PROC not used */
+        { CTL_DIR,      CTL_FS,         "fs",           bin_fs_table },
+        /* CTL_DEBUG "debug" no longer used */
+        { CTL_DIR,      CTL_DEV,        "dev",          bin_dev_table },
+        { CTL_DIR,      CTL_BUS,        "bus",          bin_bus_table },
+        { CTL_DIR,      CTL_ABI,        "abi" },
+        /* CTL_CPU not used */
+        /* CTL_ARLAN "arlan" no longer used */
+        { CTL_DIR,      CTL_S390DBF,    "s390dbf",      bin_s390dbf_table },
+        { CTL_DIR,      CTL_SUNRPC,     "sunrpc",       bin_sunrpc_table },
+        { CTL_DIR,      CTL_PM,         "pm",           bin_pm_table },
+        {}
+};
+
+static ssize_t bin_dir(struct file *file,
+        void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+        return -ENOTDIR;
+}
+
+
+static ssize_t bin_string(struct file *file,
+        void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+        ssize_t result, copied = 0;
+
+        if (oldval && oldlen) {
+                char __user *lastp;
+                loff_t pos = 0;
+                int ch;
+
+                result = vfs_read(file, oldval, oldlen, &pos);
+                if (result < 0)
+                        goto out;
+
+                copied = result;
+                lastp = oldval + copied - 1;
+
+                result = -EFAULT;
+                if (get_user(ch, lastp))
+                        goto out;
+
+                /* Trim off the trailing newline */
+                if (ch == '\n') {
+                        result = -EFAULT;
+                        if (put_user('\0', lastp))
+                                goto out;
+                        copied -= 1;
+                }
+        }
+
+        if (newval && newlen) {
+                loff_t pos = 0;
+
+                result = vfs_write(file, newval, newlen, &pos);
+                if (result < 0)
+                        goto out;
+        }
+
+        result = copied;
+out:
+        return result;
+}
+
+static ssize_t bin_intvec(struct file *file,
+        void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+        mm_segment_t old_fs = get_fs();
+        ssize_t copied = 0;
+        char *buffer;
+        ssize_t result;
+
+        result = -ENOMEM;
+        buffer = kmalloc(BUFSZ, GFP_KERNEL);
+        if (!buffer)
+                goto out;
+
+        if (oldval && oldlen) {
+                unsigned __user *vec = oldval;
+                size_t length = oldlen / sizeof(*vec);
+                loff_t pos = 0;
+                char *str, *end;
+                int i;
+
+                set_fs(KERNEL_DS);
+                result = vfs_read(file, buffer, BUFSZ - 1, &pos);
+                set_fs(old_fs);
+                if (result < 0)
+                        goto out_kfree;
+
+                str = buffer;
+                end = str + result;
+                *end++ = '\0';
+                for (i = 0; i < length; i++) {
+                        unsigned long value;
+
+                        value = simple_strtoul(str, &str, 10);
+                        while (isspace(*str))
+                                str++;
+                        
+                        result = -EFAULT;
+                        if (put_user(value, vec + i))
+                                goto out_kfree;
+
+                        copied += sizeof(*vec);
+                        if (!isdigit(*str))
+                                break;
+                }
+        }
+
+        if (newval && newlen) {
+                unsigned __user *vec = newval;
+                size_t length = newlen / sizeof(*vec);
+                loff_t pos = 0;
+                char *str, *end;
+                int i;
+
+                str = buffer;
+                end = str + BUFSZ;
+                for (i = 0; i < length; i++) {
+                        unsigned long value;
+
+                        result = -EFAULT;
+                        if (get_user(value, vec + i))
+                                goto out_kfree;
+
+                        str += snprintf(str, end - str, "%lu\t", value);
+                }
+
+                set_fs(KERNEL_DS);
+                result = vfs_write(file, buffer, str - buffer, &pos);
+                set_fs(old_fs);
+                if (result < 0)
+                        goto out_kfree;
+        }
+        result = copied;
+out_kfree:
+        kfree(buffer);
+out:
+        return result;
+}
+
+static ssize_t bin_ulongvec(struct file *file,
+        void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+        mm_segment_t old_fs = get_fs();
+        ssize_t copied = 0;
+        char *buffer;
+        ssize_t result;
+
+        result = -ENOMEM;
+        buffer = kmalloc(BUFSZ, GFP_KERNEL);
+        if (!buffer)
+                goto out;
+
+        if (oldval && oldlen) {
+                unsigned long __user *vec = oldval;
+                size_t length = oldlen / sizeof(*vec);
+                loff_t pos = 0;
+                char *str, *end;
+                int i;
+
+                set_fs(KERNEL_DS);
+                result = vfs_read(file, buffer, BUFSZ - 1, &pos);
+                set_fs(old_fs);
+                if (result < 0)
+                        goto out_kfree;
+
+                str = buffer;
+                end = str + result;
+                *end++ = '\0';
+                for (i = 0; i < length; i++) {
+                        unsigned long value;
+
+                        value = simple_strtoul(str, &str, 10);
+                        while (isspace(*str))
+                                str++;
+                        
+                        result = -EFAULT;
+                        if (put_user(value, vec + i))
+                                goto out_kfree;
+
+                        copied += sizeof(*vec);
+                        if (!isdigit(*str))
+                                break;
+                }
+        }
+
+        if (newval && newlen) {
+                unsigned long __user *vec = newval;
+                size_t length = newlen / sizeof(*vec);
+                loff_t pos = 0;
+                char *str, *end;
+                int i;
+
+                str = buffer;
+                end = str + BUFSZ;
+                for (i = 0; i < length; i++) {
+                        unsigned long value;
+
+                        result = -EFAULT;
+                        if (get_user(value, vec + i))
+                                goto out_kfree;
+
+                        str += snprintf(str, end - str, "%lu\t", value);
+                }
+
+                set_fs(KERNEL_DS);
+                result = vfs_write(file, buffer, str - buffer, &pos);
+                set_fs(old_fs);
+                if (result < 0)
+                        goto out_kfree;
+        }
+        result = copied;
+out_kfree:
+        kfree(buffer);
+out:
+        return result;
+}
+
+static unsigned hex_value(int ch)
+{
+        return isdigit(ch) ? ch - '0' : ((ch | 0x20) - 'a') + 10;
+}
+
+static ssize_t bin_uuid(struct file *file,
+        void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+        mm_segment_t old_fs = get_fs();
+        ssize_t result, copied = 0;
+
+        /* Only supports reads */
+        if (oldval && oldlen) {
+                loff_t pos = 0;
+                char buf[40], *str = buf;
+                unsigned char uuid[16];
+                int i;
+
+                set_fs(KERNEL_DS);
+                result = vfs_read(file, buf, sizeof(buf) - 1, &pos);
+                set_fs(old_fs);
+                if (result < 0)
+                        goto out;
+
+                buf[result] = '\0';
+
+                /* Convert the uuid to from a string to binary */
+                for (i = 0; i < 16; i++) {
+                        result = -EIO;
+                        if (!isxdigit(str[0]) || !isxdigit(str[1]))
+                                goto out;
+
+                        uuid[i] = (hex_value(str[0]) << 4) | hex_value(str[1]);
+                        str += 2;
+                        if (*str == '-')
+                                str++;
+                }
+
+                if (oldlen > 16)
+                        oldlen = 16;
+
+                result = -EFAULT;
+                if (copy_to_user(oldval, uuid, oldlen))
+                        goto out;
+
+                copied = oldlen;
+        }
+        result = copied;
+out:
+        return result;
+}
+
+static ssize_t bin_dn_node_address(struct file *file,
+        void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+        mm_segment_t old_fs = get_fs();
+        ssize_t result, copied = 0;
+
+        if (oldval && oldlen) {
+                loff_t pos = 0;
+                char buf[15], *nodep;
+                unsigned long area, node;
+                __le16 dnaddr;
+
+                set_fs(KERNEL_DS);
+                result = vfs_read(file, buf, sizeof(buf) - 1, &pos);
+                set_fs(old_fs);
+                if (result < 0)
+                        goto out;
+
+                buf[result] = '\0';
+
+                /* Convert the decnet addresss to binary */
+                result = -EIO;
+                nodep = strchr(buf, '.') + 1;
+                if (!nodep)
+                        goto out;
+
+                area = simple_strtoul(buf, NULL, 10);
+                node = simple_strtoul(nodep, NULL, 10);
+
+                result = -EIO;
+                if ((area > 63)||(node > 1023))
+                        goto out;
+
+                dnaddr = cpu_to_le16((area << 10) | node);
+
+                result = -EFAULT;
+                if (put_user(dnaddr, (__le16 __user *)oldval))
+                        goto out;
+
+                copied = sizeof(dnaddr);
+        }
+
+        if (newval && newlen) {
+                loff_t pos = 0;
+                __le16 dnaddr;
+                char buf[15];
+                int len;
+
+                result = -EINVAL;
+                if (newlen != sizeof(dnaddr))
+                        goto out;
+
+                result = -EFAULT;
+                if (get_user(dnaddr, (__le16 __user *)newval))
+                        goto out;
+
+                len = snprintf(buf, sizeof(buf), "%hu.%hu",
+                                le16_to_cpu(dnaddr) >> 10,
+                                le16_to_cpu(dnaddr) & 0x3ff);
+
+                set_fs(KERNEL_DS);
+                result = vfs_write(file, buf, len, &pos);
+                set_fs(old_fs);
+                if (result < 0)
+                        goto out;
+        }
+
+        result = copied;
+out:
+        return result;
+}
+
+static const struct bin_table *get_sysctl(const int *name, int nlen, char *path)
+{
+        const struct bin_table *table = &bin_root_table[0];
+        int ctl_name;
+
+        /* The binary sysctl tables have a small maximum depth so
+         * there is no danger of overflowing our path as it PATH_MAX
+         * bytes long.
+         */
+        memcpy(path, "sys/", 4);
+        path += 4;
+
+repeat:
+        if (!nlen)
+                return ERR_PTR(-ENOTDIR);
+        ctl_name = *name;
+        name++;
+        nlen--;
+        for ( ; table->convert; table++) {
+                int len = 0;
+
+                /*
+                 * For a wild card entry map from ifindex to network
+                 * device name.
+                 */
+                if (!table->ctl_name) {
+#ifdef CONFIG_NET
+                        struct net *net = current->nsproxy->net_ns;
+                        struct net_device *dev;
+                        dev = dev_get_by_index(net, ctl_name);
+                        if (dev) {
+                                len = strlen(dev->name);
+                                memcpy(path, dev->name, len);
+                                dev_put(dev);
+                        }
+#endif
+                /* Use the well known sysctl number to proc name mapping */
+                } else if (ctl_name == table->ctl_name) {
+                        len = strlen(table->procname);
+                        memcpy(path, table->procname, len);
+                }
+                if (len) {
+                        path += len;
+                        if (table->child) {
+                                *path++ = '/';
+                                table = table->child;
+                                goto repeat;
+                        }
+                        *path = '\0';
+                        return table;
+                }
+        }
+        return ERR_PTR(-ENOTDIR);
+}
+
+static char *sysctl_getname(const int *name, int nlen, const struct bin_table **tablep)
+{
+        char *tmp, *result;
+
+        result = ERR_PTR(-ENOMEM);
+        tmp = __getname();
+        if (tmp) {
+                const struct bin_table *table = get_sysctl(name, nlen, tmp);
+                result = tmp;
+                *tablep = table;
+                if (IS_ERR(table)) {
+                        __putname(tmp);
+                        result = ERR_CAST(table);
+                }
+        }
+        return result;
+}
+
+static ssize_t binary_sysctl(const int *name, int nlen,
+        void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+        const struct bin_table *table = NULL;
+        struct nameidata nd;
+        struct vfsmount *mnt;
+        struct file *file;
+        ssize_t result;
+        char *pathname;
+        int flags;
+        int acc_mode, fmode;
+
+        pathname = sysctl_getname(name, nlen, &table);
+        result = PTR_ERR(pathname);
+        if (IS_ERR(pathname))
+                goto out;
+
+        /* How should the sysctl be accessed? */
+        if (oldval && oldlen && newval && newlen) {
+                flags = O_RDWR;
+                acc_mode = MAY_READ | MAY_WRITE;
+                fmode = FMODE_READ | FMODE_WRITE;
+        } else if (newval && newlen) {
+                flags = O_WRONLY;
+                acc_mode = MAY_WRITE;
+                fmode = FMODE_WRITE;
+        } else if (oldval && oldlen) {
+                flags = O_RDONLY;
+                acc_mode = MAY_READ;
+                fmode = FMODE_READ;
+        } else {
+                result = 0;
+                goto out_putname;
+        }
+
+        mnt = current->nsproxy->pid_ns->proc_mnt;
+        result = vfs_path_lookup(mnt->mnt_root, mnt, pathname, 0, &nd);
+        if (result)
+                goto out_putname;
+
+        result = may_open(&nd.path, acc_mode, fmode);
+        if (result)
+                goto out_putpath;
+
+        file = dentry_open(nd.path.dentry, nd.path.mnt, flags, current_cred());
+        result = PTR_ERR(file);
+        if (IS_ERR(file))
+                goto out_putname;
+
+        result = table->convert(file, oldval, oldlen, newval, newlen);
+
+        fput(file);
+out_putname:
+        putname(pathname);
+out:
+        return result;
+
+out_putpath:
+        path_put(&nd.path);
+        goto out_putname;
+}
+
+
+#else /* CONFIG_SYSCTL_SYSCALL */
+
+static ssize_t binary_sysctl(const int *name, int nlen,
+        void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+        return -ENOSYS;
+}
+
+#endif /* CONFIG_SYSCTL_SYSCALL */
+
+
+static void deprecated_sysctl_warning(const int *name, int nlen)
+{
+        int i;
+
+        if (printk_ratelimit()) {
+                printk(KERN_INFO
+                        "warning: process `%s' used the deprecated sysctl "
+                        "system call with ", current->comm);
+                for (i = 0; i < nlen; i++)
+                        printk("%d.", name[i]);
+                printk("\n");
+        }
+        return;
+}
+
+static ssize_t do_sysctl(int __user *args_name, int nlen,
+        void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+        int name[CTL_MAXNAME];
+        int i;
+
+        /* Check args->nlen. */
+        if (nlen < 0 || nlen > CTL_MAXNAME)
+                return -ENOTDIR;
+        /* Read in the sysctl name for simplicity */
+        for (i = 0; i < nlen; i++)
+                if (get_user(name[i], args_name + i))
+                        return -EFAULT;
+
+        deprecated_sysctl_warning(name, nlen);
+
+        return binary_sysctl(name, nlen, oldval, oldlen, newval, newlen);
+}
+
+SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args)
+{
+        struct __sysctl_args tmp;
+        size_t oldlen = 0;
+        ssize_t result;
+
+        if (copy_from_user(&tmp, args, sizeof(tmp)))
+                return -EFAULT;
+
+        if (tmp.oldval && !tmp.oldlenp)
+                return -EFAULT;
+
+        if (tmp.oldlenp && get_user(oldlen, tmp.oldlenp))
+                return -EFAULT;
+
+        result = do_sysctl(tmp.name, tmp.nlen, tmp.oldval, oldlen,
+                           tmp.newval, tmp.newlen);
+
+        if (result >= 0) {
+                oldlen = result;
+                result = 0;
+        }
+
+        if (tmp.oldlenp && put_user(oldlen, tmp.oldlenp))
+                return -EFAULT;
+
+        return result;
+}
+
+
+#ifdef CONFIG_COMPAT
+#include <asm/compat.h>
+
+struct compat_sysctl_args {
+        compat_uptr_t   name;
+        int             nlen;
+        compat_uptr_t   oldval;
+        compat_uptr_t   oldlenp;
+        compat_uptr_t   newval;
+        compat_size_t   newlen;
+        compat_ulong_t  __unused[4];
+};
+
+asmlinkage long compat_sys_sysctl(struct compat_sysctl_args __user *args)
+{
+        struct compat_sysctl_args tmp;
+        compat_size_t __user *compat_oldlenp;
+        size_t oldlen = 0;
+        ssize_t result;
+
+        if (copy_from_user(&tmp, args, sizeof(tmp)))
+                return -EFAULT;
+
+        if (tmp.oldval && !tmp.oldlenp)
+                return -EFAULT;
+
+        compat_oldlenp = compat_ptr(tmp.oldlenp);
+        if (compat_oldlenp && get_user(oldlen, compat_oldlenp))
+                return -EFAULT;
+
+        result = do_sysctl(compat_ptr(tmp.name), tmp.nlen,
+                           compat_ptr(tmp.oldval), oldlen,
+                           compat_ptr(tmp.newval), tmp.newlen);
+
+        if (result >= 0) {
+                oldlen = result;
+                result = 0;
+        }
+
+        if (compat_oldlenp && put_user(oldlen, compat_oldlenp))
+                return -EFAULT;
+
+        return result;
+}
+
+#endif /* CONFIG_COMPAT */
diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c
index f1d676e4b368..04cdcf72c827 100644
--- a/kernel/sysctl_check.c
+++ b/kernel/sysctl_check.c
@@ -5,1240 +5,6 @@
 #include <linux/string.h>
 #include <net/ip_vs.h>
 
-struct trans_ctl_table {
-        int                     ctl_name;
-        const char              *procname;
-        const struct trans_ctl_table *child;
-};
-
-static const struct trans_ctl_table trans_random_table[] = {
-        { RANDOM_POOLSIZE,      "poolsize" },
-        { RANDOM_ENTROPY_COUNT, "entropy_avail" },
-        { RANDOM_READ_THRESH,   "read_wakeup_threshold" },
-        { RANDOM_WRITE_THRESH,  "write_wakeup_threshold" },
-        { RANDOM_BOOT_ID,       "boot_id" },
-        { RANDOM_UUID,          "uuid" },
-        {}
-};
-
-static const struct trans_ctl_table trans_pty_table[] = {
-        { PTY_MAX,              "max" },
-        { PTY_NR,               "nr" },
-        {}
-};
-
-static const struct trans_ctl_table trans_kern_table[] = {
-        { KERN_OSTYPE,                  "ostype" },
-        { KERN_OSRELEASE,               "osrelease" },
-        /* KERN_OSREV not used */
-        { KERN_VERSION,                 "version" },
-        /* KERN_SECUREMASK not used */
-        /* KERN_PROF not used */
-        { KERN_NODENAME,                "hostname" },
-        { KERN_DOMAINNAME,              "domainname" },
-
-        { KERN_PANIC,                   "panic" },
-        { KERN_REALROOTDEV,             "real-root-dev" },
-
-        { KERN_SPARC_REBOOT,            "reboot-cmd" },
-        { KERN_CTLALTDEL,               "ctrl-alt-del" },
-        { KERN_PRINTK,                  "printk" },
-
-        /* KERN_NAMETRANS not used */
-        /* KERN_PPC_HTABRECLAIM not used */
-        /* KERN_PPC_ZEROPAGED not used */
-        { KERN_PPC_POWERSAVE_NAP,       "powersave-nap" },
-
-        { KERN_MODPROBE,                "modprobe" },
-        { KERN_SG_BIG_BUFF,             "sg-big-buff" },
-        { KERN_ACCT,                    "acct" },
-        { KERN_PPC_L2CR,                "l2cr" },
-
-        /* KERN_RTSIGNR not used */
-        /* KERN_RTSIGMAX not used */
-
-        { KERN_SHMMAX,                  "shmmax" },
-        { KERN_MSGMAX,                  "msgmax" },
-        { KERN_MSGMNB,                  "msgmnb" },
-        /* KERN_MSGPOOL not used*/
-        { KERN_SYSRQ,                   "sysrq" },
-        { KERN_MAX_THREADS,             "threads-max" },
-        { KERN_RANDOM,                  "random",       trans_random_table },
-        { KERN_SHMALL,                  "shmall" },
-        { KERN_MSGMNI,                  "msgmni" },
-        { KERN_SEM,                     "sem" },
-        { KERN_SPARC_STOP_A,            "stop-a" },
-        { KERN_SHMMNI,                  "shmmni" },
-
-        { KERN_OVERFLOWUID,             "overflowuid" },
-        { KERN_OVERFLOWGID,             "overflowgid" },
-
-        { KERN_HOTPLUG,                 "hotplug", },
-        { KERN_IEEE_EMULATION_WARNINGS, "ieee_emulation_warnings" },
-
-        { KERN_S390_USER_DEBUG_LOGGING, "userprocess_debug" },
-        { KERN_CORE_USES_PID,           "core_uses_pid" },
-        { KERN_TAINTED,                 "tainted" },
-        { KERN_CADPID,                  "cad_pid" },
-        { KERN_PIDMAX,                  "pid_max" },
-        { KERN_CORE_PATTERN,            "core_pattern" },
-        { KERN_PANIC_ON_OOPS,           "panic_on_oops" },
-        { KERN_HPPA_PWRSW,              "soft-power" },
-        { KERN_HPPA_UNALIGNED,          "unaligned-trap" },
-
-        { KERN_PRINTK_RATELIMIT,        "printk_ratelimit" },
-        { KERN_PRINTK_RATELIMIT_BURST,  "printk_ratelimit_burst" },
-
-        { KERN_PTY,                     "pty",          trans_pty_table },
-        { KERN_NGROUPS_MAX,             "ngroups_max" },
-        { KERN_SPARC_SCONS_PWROFF,      "scons-poweroff" },
-        { KERN_HZ_TIMER,                "hz_timer" },
-        { KERN_UNKNOWN_NMI_PANIC,       "unknown_nmi_panic" },
-        { KERN_BOOTLOADER_TYPE,         "bootloader_type" },
-        { KERN_RANDOMIZE,               "randomize_va_space" },
-
-        { KERN_SPIN_RETRY,              "spin_retry" },
-        { KERN_ACPI_VIDEO_FLAGS,        "acpi_video_flags" },
-        { KERN_IA64_UNALIGNED,          "ignore-unaligned-usertrap" },
-        { KERN_COMPAT_LOG,              "compat-log" },
-        { KERN_MAX_LOCK_DEPTH,          "max_lock_depth" },
-        { KERN_NMI_WATCHDOG,            "nmi_watchdog" },
-        { KERN_PANIC_ON_NMI,            "panic_on_unrecovered_nmi" },
-        {}
-};
-
-static const struct trans_ctl_table trans_vm_table[] = {
-        { VM_OVERCOMMIT_MEMORY,         "overcommit_memory" },
-        { VM_PAGE_CLUSTER,              "page-cluster" },
-        { VM_DIRTY_BACKGROUND,          "dirty_background_ratio" },
-        { VM_DIRTY_RATIO,               "dirty_ratio" },
-        { VM_DIRTY_WB_CS,               "dirty_writeback_centisecs" },
-        { VM_DIRTY_EXPIRE_CS,           "dirty_expire_centisecs" },
-        { VM_NR_PDFLUSH_THREADS,        "nr_pdflush_threads" },
-        { VM_OVERCOMMIT_RATIO,          "overcommit_ratio" },
-        /* VM_PAGEBUF unused */
-        { VM_HUGETLB_PAGES,             "nr_hugepages" },
-        { VM_SWAPPINESS,                "swappiness" },
-        { VM_LOWMEM_RESERVE_RATIO,      "lowmem_reserve_ratio" },
-        { VM_MIN_FREE_KBYTES,           "min_free_kbytes" },
-        { VM_MAX_MAP_COUNT,             "max_map_count" },
-        { VM_LAPTOP_MODE,               "laptop_mode" },
-        { VM_BLOCK_DUMP,                "block_dump" },
-        { VM_HUGETLB_GROUP,             "hugetlb_shm_group" },
-        { VM_VFS_CACHE_PRESSURE,        "vfs_cache_pressure" },
-        { VM_LEGACY_VA_LAYOUT,          "legacy_va_layout" },
-        /* VM_SWAP_TOKEN_TIMEOUT unused */
-        { VM_DROP_PAGECACHE,            "drop_caches" },
-        { VM_PERCPU_PAGELIST_FRACTION,  "percpu_pagelist_fraction" },
-        { VM_ZONE_RECLAIM_MODE,         "zone_reclaim_mode" },
-        { VM_MIN_UNMAPPED,              "min_unmapped_ratio" },
-        { VM_PANIC_ON_OOM,              "panic_on_oom" },
-        { VM_VDSO_ENABLED,              "vdso_enabled" },
-        { VM_MIN_SLAB,                  "min_slab_ratio" },
-
-        {}
-};
-
-static const struct trans_ctl_table trans_net_core_table[] = {
-        { NET_CORE_WMEM_MAX,            "wmem_max" },
-        { NET_CORE_RMEM_MAX,            "rmem_max" },
-        { NET_CORE_WMEM_DEFAULT,        "wmem_default" },
-        { NET_CORE_RMEM_DEFAULT,        "rmem_default" },
-        /* NET_CORE_DESTROY_DELAY unused */
-        { NET_CORE_MAX_BACKLOG,         "netdev_max_backlog" },
-        /* NET_CORE_FASTROUTE unused */
-        { NET_CORE_MSG_COST,            "message_cost" },
-        { NET_CORE_MSG_BURST,           "message_burst" },
-        { NET_CORE_OPTMEM_MAX,          "optmem_max" },
-        /* NET_CORE_HOT_LIST_LENGTH unused */
-        /* NET_CORE_DIVERT_VERSION unused */
-        /* NET_CORE_NO_CONG_THRESH unused */
-        /* NET_CORE_NO_CONG unused */
-        /* NET_CORE_LO_CONG unused */
-        /* NET_CORE_MOD_CONG unused */
-        { NET_CORE_DEV_WEIGHT,          "dev_weight" },
-        { NET_CORE_SOMAXCONN,           "somaxconn" },
-        { NET_CORE_BUDGET,              "netdev_budget" },
-        { NET_CORE_AEVENT_ETIME,        "xfrm_aevent_etime" },
-        { NET_CORE_AEVENT_RSEQTH,       "xfrm_aevent_rseqth" },
-        { NET_CORE_WARNINGS,            "warnings" },
-        {},
-};
-
-static const struct trans_ctl_table trans_net_unix_table[] = {
-        /* NET_UNIX_DESTROY_DELAY unused */
-        /* NET_UNIX_DELETE_DELAY unused */
-        { NET_UNIX_MAX_DGRAM_QLEN,      "max_dgram_qlen" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_ipv4_route_table[] = {
-        { NET_IPV4_ROUTE_FLUSH,                 "flush" },
-        { NET_IPV4_ROUTE_MIN_DELAY,             "min_delay" },
-        { NET_IPV4_ROUTE_MAX_DELAY,             "max_delay" },
-        { NET_IPV4_ROUTE_GC_THRESH,             "gc_thresh" },
-        { NET_IPV4_ROUTE_MAX_SIZE,              "max_size" },
-        { NET_IPV4_ROUTE_GC_MIN_INTERVAL,       "gc_min_interval" },
-        { NET_IPV4_ROUTE_GC_TIMEOUT,            "gc_timeout" },
-        { NET_IPV4_ROUTE_GC_INTERVAL,           "gc_interval" },
-        { NET_IPV4_ROUTE_REDIRECT_LOAD,         "redirect_load" },
-        { NET_IPV4_ROUTE_REDIRECT_NUMBER,       "redirect_number" },
-        { NET_IPV4_ROUTE_REDIRECT_SILENCE,      "redirect_silence" },
-        { NET_IPV4_ROUTE_ERROR_COST,            "error_cost" },
-        { NET_IPV4_ROUTE_ERROR_BURST,           "error_burst" },
-        { NET_IPV4_ROUTE_GC_ELASTICITY,         "gc_elasticity" },
-        { NET_IPV4_ROUTE_MTU_EXPIRES,           "mtu_expires" },
-        { NET_IPV4_ROUTE_MIN_PMTU,              "min_pmtu" },
-        { NET_IPV4_ROUTE_MIN_ADVMSS,            "min_adv_mss" },
-        { NET_IPV4_ROUTE_SECRET_INTERVAL,       "secret_interval" },
-        { NET_IPV4_ROUTE_GC_MIN_INTERVAL_MS,    "gc_min_interval_ms" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_ipv4_conf_vars_table[] = {
-        { NET_IPV4_CONF_FORWARDING,             "forwarding" },
-        { NET_IPV4_CONF_MC_FORWARDING,          "mc_forwarding" },
-
-        { NET_IPV4_CONF_PROXY_ARP,              "proxy_arp" },
-        { NET_IPV4_CONF_ACCEPT_REDIRECTS,       "accept_redirects" },
-        { NET_IPV4_CONF_SECURE_REDIRECTS,       "secure_redirects" },
-        { NET_IPV4_CONF_SEND_REDIRECTS,         "send_redirects" },
-        { NET_IPV4_CONF_SHARED_MEDIA,           "shared_media" },
-        { NET_IPV4_CONF_RP_FILTER,              "rp_filter" },
-        { NET_IPV4_CONF_ACCEPT_SOURCE_ROUTE,    "accept_source_route" },
-        { NET_IPV4_CONF_BOOTP_RELAY,            "bootp_relay" },
-        { NET_IPV4_CONF_LOG_MARTIANS,           "log_martians" },
-        { NET_IPV4_CONF_TAG,                    "tag" },
-        { NET_IPV4_CONF_ARPFILTER,              "arp_filter" },
-        { NET_IPV4_CONF_MEDIUM_ID,              "medium_id" },
-        { NET_IPV4_CONF_NOXFRM,                 "disable_xfrm" },
-        { NET_IPV4_CONF_NOPOLICY,               "disable_policy" },
-        { NET_IPV4_CONF_FORCE_IGMP_VERSION,     "force_igmp_version" },
-
-        { NET_IPV4_CONF_ARP_ANNOUNCE,           "arp_announce" },
-        { NET_IPV4_CONF_ARP_IGNORE,             "arp_ignore" },
-        { NET_IPV4_CONF_PROMOTE_SECONDARIES,    "promote_secondaries" },
-        { NET_IPV4_CONF_ARP_ACCEPT,             "arp_accept" },
-        { NET_IPV4_CONF_ARP_NOTIFY,             "arp_notify" },
-        { NET_IPV4_CONF_ACCEPT_LOCAL,           "accept_local" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_ipv4_conf_table[] = {
-        { NET_PROTO_CONF_ALL,           "all",          trans_net_ipv4_conf_vars_table },
-        { NET_PROTO_CONF_DEFAULT,       "default",      trans_net_ipv4_conf_vars_table },
-        { 0, NULL, trans_net_ipv4_conf_vars_table },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_neigh_vars_table[] = {
-        { NET_NEIGH_MCAST_SOLICIT,      "mcast_solicit" },
-        { NET_NEIGH_UCAST_SOLICIT,      "ucast_solicit" },
-        { NET_NEIGH_APP_SOLICIT,        "app_solicit" },
-        { NET_NEIGH_RETRANS_TIME,       "retrans_time" },
-        { NET_NEIGH_REACHABLE_TIME,     "base_reachable_time" },
-        { NET_NEIGH_DELAY_PROBE_TIME,   "delay_first_probe_time" },
-        { NET_NEIGH_GC_STALE_TIME,      "gc_stale_time" },
-        { NET_NEIGH_UNRES_QLEN,         "unres_qlen" },
-        { NET_NEIGH_PROXY_QLEN,         "proxy_qlen" },
-        { NET_NEIGH_ANYCAST_DELAY,      "anycast_delay" },
-        { NET_NEIGH_PROXY_DELAY,        "proxy_delay" },
-        { NET_NEIGH_LOCKTIME,           "locktime" },
-        { NET_NEIGH_GC_INTERVAL,        "gc_interval" },
-        { NET_NEIGH_GC_THRESH1,         "gc_thresh1" },
-        { NET_NEIGH_GC_THRESH2,         "gc_thresh2" },
-        { NET_NEIGH_GC_THRESH3,         "gc_thresh3" },
-        { NET_NEIGH_RETRANS_TIME_MS,    "retrans_time_ms" },
-        { NET_NEIGH_REACHABLE_TIME_MS,  "base_reachable_time_ms" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_neigh_table[] = {
-        { NET_PROTO_CONF_DEFAULT, "default", trans_net_neigh_vars_table },
-        { 0, NULL, trans_net_neigh_vars_table },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_ipv4_netfilter_table[] = {
-        { NET_IPV4_NF_CONNTRACK_MAX,                            "ip_conntrack_max" },
-
-        { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT,           "ip_conntrack_tcp_timeout_syn_sent" },
-        { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV,           "ip_conntrack_tcp_timeout_syn_recv" },
-        { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED,        "ip_conntrack_tcp_timeout_established" },
-        { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT,           "ip_conntrack_tcp_timeout_fin_wait" },
-        { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT,         "ip_conntrack_tcp_timeout_close_wait" },
-        { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK,           "ip_conntrack_tcp_timeout_last_ack" },
-        { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT,          "ip_conntrack_tcp_timeout_time_wait" },
-        { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE,              "ip_conntrack_tcp_timeout_close" },
-
-        { NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT,                    "ip_conntrack_udp_timeout" },
-        { NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT_STREAM,             "ip_conntrack_udp_timeout_stream" },
-        { NET_IPV4_NF_CONNTRACK_ICMP_TIMEOUT,                   "ip_conntrack_icmp_timeout" },
-        { NET_IPV4_NF_CONNTRACK_GENERIC_TIMEOUT,                "ip_conntrack_generic_timeout" },
-
-        { NET_IPV4_NF_CONNTRACK_BUCKETS,                        "ip_conntrack_buckets" },
-        { NET_IPV4_NF_CONNTRACK_LOG_INVALID,                    "ip_conntrack_log_invalid" },
-        { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS,        "ip_conntrack_tcp_timeout_max_retrans" },
-        { NET_IPV4_NF_CONNTRACK_TCP_LOOSE,                      "ip_conntrack_tcp_loose" },
-        { NET_IPV4_NF_CONNTRACK_TCP_BE_LIBERAL,                 "ip_conntrack_tcp_be_liberal" },
-        { NET_IPV4_NF_CONNTRACK_TCP_MAX_RETRANS,                "ip_conntrack_tcp_max_retrans" },
-
-        { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED,            "ip_conntrack_sctp_timeout_closed" },
-        { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT,       "ip_conntrack_sctp_timeout_cookie_wait" },
-        { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED,     "ip_conntrack_sctp_timeout_cookie_echoed" },
-        { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED,       "ip_conntrack_sctp_timeout_established" },
-        { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT,     "ip_conntrack_sctp_timeout_shutdown_sent" },
-        { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD,     "ip_conntrack_sctp_timeout_shutdown_recd" },
-        { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT, "ip_conntrack_sctp_timeout_shutdown_ack_sent" },
-
-        { NET_IPV4_NF_CONNTRACK_COUNT,          "ip_conntrack_count" },
-        { NET_IPV4_NF_CONNTRACK_CHECKSUM,       "ip_conntrack_checksum" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_ipv4_table[] = {
-        { NET_IPV4_FORWARD,                     "ip_forward" },
-        { NET_IPV4_DYNADDR,                     "ip_dynaddr" },
-
-        { NET_IPV4_CONF,                "conf",         trans_net_ipv4_conf_table },
-        { NET_IPV4_NEIGH,               "neigh",        trans_net_neigh_table },
-        { NET_IPV4_ROUTE,               "route",        trans_net_ipv4_route_table },
-        /* NET_IPV4_FIB_HASH unused */
-        { NET_IPV4_NETFILTER,           "netfilter",    trans_net_ipv4_netfilter_table },
-
-        { NET_IPV4_TCP_TIMESTAMPS,              "tcp_timestamps" },
-        { NET_IPV4_TCP_WINDOW_SCALING,          "tcp_window_scaling" },
-        { NET_IPV4_TCP_SACK,                    "tcp_sack" },
-        { NET_IPV4_TCP_RETRANS_COLLAPSE,        "tcp_retrans_collapse" },
-        { NET_IPV4_DEFAULT_TTL,                 "ip_default_ttl" },
-        /* NET_IPV4_AUTOCONFIG unused */
-        { NET_IPV4_NO_PMTU_DISC,                "ip_no_pmtu_disc" },
-        { NET_IPV4_TCP_SYN_RETRIES,             "tcp_syn_retries" },
-        { NET_IPV4_IPFRAG_HIGH_THRESH,          "ipfrag_high_thresh" },
-        { NET_IPV4_IPFRAG_LOW_THRESH,           "ipfrag_low_thresh" },
-        { NET_IPV4_IPFRAG_TIME,                 "ipfrag_time" },
-        /* NET_IPV4_TCP_MAX_KA_PROBES unused */
-        { NET_IPV4_TCP_KEEPALIVE_TIME,          "tcp_keepalive_time" },
-        { NET_IPV4_TCP_KEEPALIVE_PROBES,        "tcp_keepalive_probes" },
-        { NET_IPV4_TCP_RETRIES1,                "tcp_retries1" },
-        { NET_IPV4_TCP_RETRIES2,                "tcp_retries2" },
-        { NET_IPV4_TCP_FIN_TIMEOUT,             "tcp_fin_timeout" },
-        /* NET_IPV4_IP_MASQ_DEBUG unused */
-        { NET_TCP_SYNCOOKIES,                   "tcp_syncookies" },
-        { NET_TCP_STDURG,                       "tcp_stdurg" },
-        { NET_TCP_RFC1337,                      "tcp_rfc1337" },
-        /* NET_TCP_SYN_TAILDROP unused */
-        { NET_TCP_MAX_SYN_BACKLOG,              "tcp_max_syn_backlog" },
-        { NET_IPV4_LOCAL_PORT_RANGE,            "ip_local_port_range" },
-        { NET_IPV4_ICMP_ECHO_IGNORE_ALL,        "icmp_echo_ignore_all" },
-        { NET_IPV4_ICMP_ECHO_IGNORE_BROADCASTS, "icmp_echo_ignore_broadcasts" },
-        /* NET_IPV4_ICMP_SOURCEQUENCH_RATE unused */
-        /* NET_IPV4_ICMP_DESTUNREACH_RATE unused */
-        /* NET_IPV4_ICMP_TIMEEXCEED_RATE unused */
-        /* NET_IPV4_ICMP_PARAMPROB_RATE unused */
-        /* NET_IPV4_ICMP_ECHOREPLY_RATE unused */
-        { NET_IPV4_ICMP_IGNORE_BOGUS_ERROR_RESPONSES,   "icmp_ignore_bogus_error_responses" },
-        { NET_IPV4_IGMP_MAX_MEMBERSHIPS,        "igmp_max_memberships" },
-        { NET_TCP_TW_RECYCLE,                   "tcp_tw_recycle" },
-        /* NET_IPV4_ALWAYS_DEFRAG unused */
-        { NET_IPV4_TCP_KEEPALIVE_INTVL,         "tcp_keepalive_intvl" },
-        { NET_IPV4_INET_PEER_THRESHOLD,         "inet_peer_threshold" },
-        { NET_IPV4_INET_PEER_MINTTL,            "inet_peer_minttl" },
-        { NET_IPV4_INET_PEER_MAXTTL,            "inet_peer_maxttl" },
-        { NET_IPV4_INET_PEER_GC_MINTIME,        "inet_peer_gc_mintime" },
-        { NET_IPV4_INET_PEER_GC_MAXTIME,        "inet_peer_gc_maxtime" },
-        { NET_TCP_ORPHAN_RETRIES,               "tcp_orphan_retries" },
-        { NET_TCP_ABORT_ON_OVERFLOW,            "tcp_abort_on_overflow" },
-        { NET_TCP_SYNACK_RETRIES,               "tcp_synack_retries" },
-        { NET_TCP_MAX_ORPHANS,                  "tcp_max_orphans" },
-        { NET_TCP_MAX_TW_BUCKETS,               "tcp_max_tw_buckets" },
-        { NET_TCP_FACK,                         "tcp_fack" },
-        { NET_TCP_REORDERING,                   "tcp_reordering" },
-        { NET_TCP_ECN,                          "tcp_ecn" },
-        { NET_TCP_DSACK,                        "tcp_dsack" },
-        { NET_TCP_MEM,                          "tcp_mem" },
-        { NET_TCP_WMEM,                         "tcp_wmem" },
-        { NET_TCP_RMEM,                         "tcp_rmem" },
-        { NET_TCP_APP_WIN,                      "tcp_app_win" },
-        { NET_TCP_ADV_WIN_SCALE,                "tcp_adv_win_scale" },
-        { NET_IPV4_NONLOCAL_BIND,               "ip_nonlocal_bind" },
-        { NET_IPV4_ICMP_RATELIMIT,              "icmp_ratelimit" },
-        { NET_IPV4_ICMP_RATEMASK,               "icmp_ratemask" },
-        { NET_TCP_TW_REUSE,                     "tcp_tw_reuse" },
-        { NET_TCP_FRTO,                         "tcp_frto" },
-        { NET_TCP_LOW_LATENCY,                  "tcp_low_latency" },
-        { NET_IPV4_IPFRAG_SECRET_INTERVAL,      "ipfrag_secret_interval" },
-        { NET_IPV4_IGMP_MAX_MSF,                "igmp_max_msf" },
-        { NET_TCP_NO_METRICS_SAVE,              "tcp_no_metrics_save" },
-        /* NET_TCP_DEFAULT_WIN_SCALE unused */
-        { NET_TCP_MODERATE_RCVBUF,              "tcp_moderate_rcvbuf" },
-        { NET_TCP_TSO_WIN_DIVISOR,              "tcp_tso_win_divisor" },
-        /* NET_TCP_BIC_BETA unused */
-        { NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR,      "icmp_errors_use_inbound_ifaddr" },
-        { NET_TCP_CONG_CONTROL,                 "tcp_congestion_control" },
-        { NET_TCP_ABC,                          "tcp_abc" },
-        { NET_IPV4_IPFRAG_MAX_DIST,             "ipfrag_max_dist" },
-        { NET_TCP_MTU_PROBING,                  "tcp_mtu_probing" },
-        { NET_TCP_BASE_MSS,                     "tcp_base_mss" },
-        { NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS,       "tcp_workaround_signed_windows" },
-        { NET_TCP_DMA_COPYBREAK,                "tcp_dma_copybreak" },
-        { NET_TCP_SLOW_START_AFTER_IDLE,        "tcp_slow_start_after_idle" },
-        { NET_CIPSOV4_CACHE_ENABLE,             "cipso_cache_enable" },
-        { NET_CIPSOV4_CACHE_BUCKET_SIZE,        "cipso_cache_bucket_size" },
-        { NET_CIPSOV4_RBM_OPTFMT,               "cipso_rbm_optfmt" },
-        { NET_CIPSOV4_RBM_STRICTVALID,          "cipso_rbm_strictvalid" },
-        { NET_TCP_AVAIL_CONG_CONTROL,           "tcp_available_congestion_control" },
-        { NET_TCP_ALLOWED_CONG_CONTROL,         "tcp_allowed_congestion_control" },
-        { NET_TCP_MAX_SSTHRESH,                 "tcp_max_ssthresh" },
-        { NET_TCP_FRTO_RESPONSE,                "tcp_frto_response" },
-        { 2088 /* NET_IPQ_QMAX */,              "ip_queue_maxlen" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_ipx_table[] = {
-        { NET_IPX_PPROP_BROADCASTING,   "ipx_pprop_broadcasting" },
-        /* NET_IPX_FORWARDING unused */
-        {}
-};
-
-static const struct trans_ctl_table trans_net_atalk_table[] = {
-        { NET_ATALK_AARP_EXPIRY_TIME,           "aarp-expiry-time" },
-        { NET_ATALK_AARP_TICK_TIME,             "aarp-tick-time" },
-        { NET_ATALK_AARP_RETRANSMIT_LIMIT,      "aarp-retransmit-limit" },
-        { NET_ATALK_AARP_RESOLVE_TIME,          "aarp-resolve-time" },
-        {},
-};
-
-static const struct trans_ctl_table trans_net_netrom_table[] = {
-        { NET_NETROM_DEFAULT_PATH_QUALITY,              "default_path_quality" },
-        { NET_NETROM_OBSOLESCENCE_COUNT_INITIALISER,    "obsolescence_count_initialiser" },
-        { NET_NETROM_NETWORK_TTL_INITIALISER,           "network_ttl_initialiser" },
-        { NET_NETROM_TRANSPORT_TIMEOUT,                 "transport_timeout" },
-        { NET_NETROM_TRANSPORT_MAXIMUM_TRIES,           "transport_maximum_tries" },
-        { NET_NETROM_TRANSPORT_ACKNOWLEDGE_DELAY,       "transport_acknowledge_delay" },
-        { NET_NETROM_TRANSPORT_BUSY_DELAY,              "transport_busy_delay" },
-        { NET_NETROM_TRANSPORT_REQUESTED_WINDOW_SIZE,   "transport_requested_window_size" },
-        { NET_NETROM_TRANSPORT_NO_ACTIVITY_TIMEOUT,     "transport_no_activity_timeout" },
-        { NET_NETROM_ROUTING_CONTROL,                   "routing_control" },
-        { NET_NETROM_LINK_FAILS_COUNT,                  "link_fails_count" },
-        { NET_NETROM_RESET,                             "reset" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_ax25_param_table[] = {
-        { NET_AX25_IP_DEFAULT_MODE,     "ip_default_mode" },
-        { NET_AX25_DEFAULT_MODE,        "ax25_default_mode" },
-        { NET_AX25_BACKOFF_TYPE,        "backoff_type" },
-        { NET_AX25_CONNECT_MODE,        "connect_mode" },
-        { NET_AX25_STANDARD_WINDOW,     "standard_window_size" },
-        { NET_AX25_EXTENDED_WINDOW,     "extended_window_size" },
-        { NET_AX25_T1_TIMEOUT,          "t1_timeout" },
-        { NET_AX25_T2_TIMEOUT,          "t2_timeout" },
-        { NET_AX25_T3_TIMEOUT,          "t3_timeout" },
-        { NET_AX25_IDLE_TIMEOUT,        "idle_timeout" },
-        { NET_AX25_N2,                  "maximum_retry_count" },
-        { NET_AX25_PACLEN,              "maximum_packet_length" },
-        { NET_AX25_PROTOCOL,            "protocol" },
-        { NET_AX25_DAMA_SLAVE_TIMEOUT,  "dama_slave_timeout" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_ax25_table[] = {
-        { 0, NULL, trans_net_ax25_param_table },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_bridge_table[] = {
-        { NET_BRIDGE_NF_CALL_ARPTABLES,         "bridge-nf-call-arptables" },
-        { NET_BRIDGE_NF_CALL_IPTABLES,          "bridge-nf-call-iptables" },
-        { NET_BRIDGE_NF_CALL_IP6TABLES,         "bridge-nf-call-ip6tables" },
-        { NET_BRIDGE_NF_FILTER_VLAN_TAGGED,     "bridge-nf-filter-vlan-tagged" },
-        { NET_BRIDGE_NF_FILTER_PPPOE_TAGGED,    "bridge-nf-filter-pppoe-tagged" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_rose_table[] = {
-        { NET_ROSE_RESTART_REQUEST_TIMEOUT,     "restart_request_timeout" },
-        { NET_ROSE_CALL_REQUEST_TIMEOUT,        "call_request_timeout" },
-        { NET_ROSE_RESET_REQUEST_TIMEOUT,       "reset_request_timeout" },
-        { NET_ROSE_CLEAR_REQUEST_TIMEOUT,       "clear_request_timeout" },
-        { NET_ROSE_ACK_HOLD_BACK_TIMEOUT,       "acknowledge_hold_back_timeout" },
-        { NET_ROSE_ROUTING_CONTROL,             "routing_control" },
-        { NET_ROSE_LINK_FAIL_TIMEOUT,           "link_fail_timeout" },
-        { NET_ROSE_MAX_VCS,                     "maximum_virtual_circuits" },
-        { NET_ROSE_WINDOW_SIZE,                 "window_size" },
-        { NET_ROSE_NO_ACTIVITY_TIMEOUT,         "no_activity_timeout" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_ipv6_conf_var_table[] = {
-        { NET_IPV6_FORWARDING,                  "forwarding" },
-        { NET_IPV6_HOP_LIMIT,                   "hop_limit" },
-        { NET_IPV6_MTU,                         "mtu" },
-        { NET_IPV6_ACCEPT_RA,                   "accept_ra" },
-        { NET_IPV6_ACCEPT_REDIRECTS,            "accept_redirects" },
-        { NET_IPV6_AUTOCONF,                    "autoconf" },
-        { NET_IPV6_DAD_TRANSMITS,               "dad_transmits" },
-        { NET_IPV6_RTR_SOLICITS,                "router_solicitations" },
-        { NET_IPV6_RTR_SOLICIT_INTERVAL,        "router_solicitation_interval" },
-        { NET_IPV6_RTR_SOLICIT_DELAY,           "router_solicitation_delay" },
-        { NET_IPV6_USE_TEMPADDR,                "use_tempaddr" },
-        { NET_IPV6_TEMP_VALID_LFT,              "temp_valid_lft" },
-        { NET_IPV6_TEMP_PREFERED_LFT,           "temp_prefered_lft" },
-        { NET_IPV6_REGEN_MAX_RETRY,             "regen_max_retry" },
-        { NET_IPV6_MAX_DESYNC_FACTOR,           "max_desync_factor" },
-        { NET_IPV6_MAX_ADDRESSES,               "max_addresses" },
-        { NET_IPV6_FORCE_MLD_VERSION,           "force_mld_version" },
-        { NET_IPV6_ACCEPT_RA_DEFRTR,            "accept_ra_defrtr" },
-        { NET_IPV6_ACCEPT_RA_PINFO,             "accept_ra_pinfo" },
-        { NET_IPV6_ACCEPT_RA_RTR_PREF,          "accept_ra_rtr_pref" },
-        { NET_IPV6_RTR_PROBE_INTERVAL,          "router_probe_interval" },
-        { NET_IPV6_ACCEPT_RA_RT_INFO_MAX_PLEN,  "accept_ra_rt_info_max_plen" },
-        { NET_IPV6_PROXY_NDP,                   "proxy_ndp" },
-        { NET_IPV6_ACCEPT_SOURCE_ROUTE,         "accept_source_route" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_ipv6_conf_table[] = {
-        { NET_PROTO_CONF_ALL,           "all",  trans_net_ipv6_conf_var_table },
-        { NET_PROTO_CONF_DEFAULT,       "default", trans_net_ipv6_conf_var_table },
-        { 0, NULL, trans_net_ipv6_conf_var_table },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_ipv6_route_table[] = {
-        { NET_IPV6_ROUTE_FLUSH,                 "flush" },
-        { NET_IPV6_ROUTE_GC_THRESH,             "gc_thresh" },
-        { NET_IPV6_ROUTE_MAX_SIZE,              "max_size" },
-        { NET_IPV6_ROUTE_GC_MIN_INTERVAL,       "gc_min_interval" },
-        { NET_IPV6_ROUTE_GC_TIMEOUT,            "gc_timeout" },
-        { NET_IPV6_ROUTE_GC_INTERVAL,           "gc_interval" },
-        { NET_IPV6_ROUTE_GC_ELASTICITY,         "gc_elasticity" },
-        { NET_IPV6_ROUTE_MTU_EXPIRES,           "mtu_expires" },
-        { NET_IPV6_ROUTE_MIN_ADVMSS,            "min_adv_mss" },
-        { NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS,    "gc_min_interval_ms" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_ipv6_icmp_table[] = {
-        { NET_IPV6_ICMP_RATELIMIT,      "ratelimit" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_ipv6_table[] = {
-        { NET_IPV6_CONF,                "conf",         trans_net_ipv6_conf_table },
-        { NET_IPV6_NEIGH,               "neigh",        trans_net_neigh_table },
-        { NET_IPV6_ROUTE,               "route",        trans_net_ipv6_route_table },
-        { NET_IPV6_ICMP,                "icmp",         trans_net_ipv6_icmp_table },
-        { NET_IPV6_BINDV6ONLY,          "bindv6only" },
-        { NET_IPV6_IP6FRAG_HIGH_THRESH, "ip6frag_high_thresh" },
-        { NET_IPV6_IP6FRAG_LOW_THRESH,  "ip6frag_low_thresh" },
-        { NET_IPV6_IP6FRAG_TIME,        "ip6frag_time" },
-        { NET_IPV6_IP6FRAG_SECRET_INTERVAL,     "ip6frag_secret_interval" },
-        { NET_IPV6_MLD_MAX_MSF,         "mld_max_msf" },
-        { 2088 /* IPQ_QMAX */,          "ip6_queue_maxlen" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_x25_table[] = {
-        { NET_X25_RESTART_REQUEST_TIMEOUT,      "restart_request_timeout" },
-        { NET_X25_CALL_REQUEST_TIMEOUT,         "call_request_timeout" },
-        { NET_X25_RESET_REQUEST_TIMEOUT,        "reset_request_timeout" },
-        { NET_X25_CLEAR_REQUEST_TIMEOUT,        "clear_request_timeout" },
-        { NET_X25_ACK_HOLD_BACK_TIMEOUT,        "acknowledgement_hold_back_timeout" },
-        { NET_X25_FORWARD,                      "x25_forward" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_tr_table[] = {
-        { NET_TR_RIF_TIMEOUT,   "rif_timeout" },
-        {}
-};
-
-
-static const struct trans_ctl_table trans_net_decnet_conf_vars[] = {
-        { NET_DECNET_CONF_DEV_FORWARDING,       "forwarding" },
-        { NET_DECNET_CONF_DEV_PRIORITY,         "priority" },
-        { NET_DECNET_CONF_DEV_T2,               "t2" },
-        { NET_DECNET_CONF_DEV_T3,               "t3" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_decnet_conf[] = {
-        { 0, NULL, trans_net_decnet_conf_vars },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_decnet_table[] = {
-        { NET_DECNET_CONF,              "conf", trans_net_decnet_conf },
-        { NET_DECNET_NODE_ADDRESS,      "node_address" },
-        { NET_DECNET_NODE_NAME,         "node_name" },
-        { NET_DECNET_DEFAULT_DEVICE,    "default_device" },
-        { NET_DECNET_TIME_WAIT,         "time_wait" },
-        { NET_DECNET_DN_COUNT,          "dn_count" },
-        { NET_DECNET_DI_COUNT,          "di_count" },
-        { NET_DECNET_DR_COUNT,          "dr_count" },
-        { NET_DECNET_DST_GC_INTERVAL,   "dst_gc_interval" },
-        { NET_DECNET_NO_FC_MAX_CWND,    "no_fc_max_cwnd" },
-        { NET_DECNET_MEM,               "decnet_mem" },
-        { NET_DECNET_RMEM,              "decnet_rmem" },
-        { NET_DECNET_WMEM,              "decnet_wmem" },
-        { NET_DECNET_DEBUG_LEVEL,       "debug" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_sctp_table[] = {
-        { NET_SCTP_RTO_INITIAL,         "rto_initial" },
-        { NET_SCTP_RTO_MIN,             "rto_min" },
-        { NET_SCTP_RTO_MAX,             "rto_max" },
-        { NET_SCTP_RTO_ALPHA,           "rto_alpha_exp_divisor" },
-        { NET_SCTP_RTO_BETA,            "rto_beta_exp_divisor" },
-        { NET_SCTP_VALID_COOKIE_LIFE,   "valid_cookie_life" },
-        { NET_SCTP_ASSOCIATION_MAX_RETRANS,     "association_max_retrans" },
-        { NET_SCTP_PATH_MAX_RETRANS,    "path_max_retrans" },
-        { NET_SCTP_MAX_INIT_RETRANSMITS,        "max_init_retransmits" },
-        { NET_SCTP_HB_INTERVAL,         "hb_interval" },
-        { NET_SCTP_PRESERVE_ENABLE,     "cookie_preserve_enable" },
-        { NET_SCTP_MAX_BURST,           "max_burst" },
-        { NET_SCTP_ADDIP_ENABLE,        "addip_enable" },
-        { NET_SCTP_PRSCTP_ENABLE,       "prsctp_enable" },
-        { NET_SCTP_SNDBUF_POLICY,       "sndbuf_policy" },
-        { NET_SCTP_SACK_TIMEOUT,        "sack_timeout" },
-        { NET_SCTP_RCVBUF_POLICY,       "rcvbuf_policy" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_llc_llc2_timeout_table[] = {
-        { NET_LLC2_ACK_TIMEOUT,         "ack" },
-        { NET_LLC2_P_TIMEOUT,           "p" },
-        { NET_LLC2_REJ_TIMEOUT,         "rej" },
-        { NET_LLC2_BUSY_TIMEOUT,        "busy" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_llc_station_table[] = {
-        { NET_LLC_STATION_ACK_TIMEOUT,  "ack_timeout" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_llc_llc2_table[] = {
-        { NET_LLC2,             "timeout",      trans_net_llc_llc2_timeout_table },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_llc_table[] = {
-        { NET_LLC2,             "llc2",         trans_net_llc_llc2_table },
-        { NET_LLC_STATION,      "station",      trans_net_llc_station_table },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_netfilter_table[] = {
-        { NET_NF_CONNTRACK_MAX,                         "nf_conntrack_max" },
-        { NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT,        "nf_conntrack_tcp_timeout_syn_sent" },
-        { NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV,        "nf_conntrack_tcp_timeout_syn_recv" },
-        { NET_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED,     "nf_conntrack_tcp_timeout_established" },
-        { NET_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT,        "nf_conntrack_tcp_timeout_fin_wait" },
-        { NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT,      "nf_conntrack_tcp_timeout_close_wait" },
-        { NET_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK,        "nf_conntrack_tcp_timeout_last_ack" },
-        { NET_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT,       "nf_conntrack_tcp_timeout_time_wait" },
-        { NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE,           "nf_conntrack_tcp_timeout_close" },
-        { NET_NF_CONNTRACK_UDP_TIMEOUT,                 "nf_conntrack_udp_timeout" },
-        { NET_NF_CONNTRACK_UDP_TIMEOUT_STREAM,          "nf_conntrack_udp_timeout_stream" },
-        { NET_NF_CONNTRACK_ICMP_TIMEOUT,        "nf_conntrack_icmp_timeout" },
-        { NET_NF_CONNTRACK_GENERIC_TIMEOUT,             "nf_conntrack_generic_timeout" },
-        { NET_NF_CONNTRACK_BUCKETS,                     "nf_conntrack_buckets" },
-        { NET_NF_CONNTRACK_LOG_INVALID,                 "nf_conntrack_log_invalid" },
-        { NET_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS,     "nf_conntrack_tcp_timeout_max_retrans" },
-        { NET_NF_CONNTRACK_TCP_LOOSE,                   "nf_conntrack_tcp_loose" },
-        { NET_NF_CONNTRACK_TCP_BE_LIBERAL,              "nf_conntrack_tcp_be_liberal" },
-        { NET_NF_CONNTRACK_TCP_MAX_RETRANS,             "nf_conntrack_tcp_max_retrans" },
-        { NET_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED,         "nf_conntrack_sctp_timeout_closed" },
-        { NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT,    "nf_conntrack_sctp_timeout_cookie_wait" },
-        { NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED,  "nf_conntrack_sctp_timeout_cookie_echoed" },
-        { NET_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED,    "nf_conntrack_sctp_timeout_established" },
-        { NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT,  "nf_conntrack_sctp_timeout_shutdown_sent" },
-        { NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD,  "nf_conntrack_sctp_timeout_shutdown_recd" },
-        { NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT,      "nf_conntrack_sctp_timeout_shutdown_ack_sent" },
-        { NET_NF_CONNTRACK_COUNT,                       "nf_conntrack_count" },
-        { NET_NF_CONNTRACK_ICMPV6_TIMEOUT,      "nf_conntrack_icmpv6_timeout" },
-        { NET_NF_CONNTRACK_FRAG6_TIMEOUT,               "nf_conntrack_frag6_timeout" },
-        { NET_NF_CONNTRACK_FRAG6_LOW_THRESH,            "nf_conntrack_frag6_low_thresh" },
-        { NET_NF_CONNTRACK_FRAG6_HIGH_THRESH,           "nf_conntrack_frag6_high_thresh" },
-        { NET_NF_CONNTRACK_CHECKSUM,                    "nf_conntrack_checksum" },
-
-        {}
-};
-
-static const struct trans_ctl_table trans_net_dccp_table[] = {
-        { NET_DCCP_DEFAULT,     "default" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_irda_table[] = {
-        { NET_IRDA_DISCOVERY,           "discovery" },
-        { NET_IRDA_DEVNAME,             "devname" },
-        { NET_IRDA_DEBUG,               "debug" },
-        { NET_IRDA_FAST_POLL,           "fast_poll_increase" },
-        { NET_IRDA_DISCOVERY_SLOTS,     "discovery_slots" },
-        { NET_IRDA_DISCOVERY_TIMEOUT,   "discovery_timeout" },
-        { NET_IRDA_SLOT_TIMEOUT,        "slot_timeout" },
-        { NET_IRDA_MAX_BAUD_RATE,       "max_baud_rate" },
-        { NET_IRDA_MIN_TX_TURN_TIME,    "min_tx_turn_time" },
-        { NET_IRDA_MAX_TX_DATA_SIZE,    "max_tx_data_size" },
-        { NET_IRDA_MAX_TX_WINDOW,       "max_tx_window" },
-        { NET_IRDA_MAX_NOREPLY_TIME,    "max_noreply_time" },
-        { NET_IRDA_WARN_NOREPLY_TIME,   "warn_noreply_time" },
-        { NET_IRDA_LAP_KEEPALIVE_TIME,  "lap_keepalive_time" },
-        {}
-};
-
-static const struct trans_ctl_table trans_net_table[] = {
-        { NET_CORE,             "core",         trans_net_core_table },
-        /* NET_ETHER not used */
-        /* NET_802 not used */
-        { NET_UNIX,             "unix",         trans_net_unix_table },
-        { NET_IPV4,             "ipv4",         trans_net_ipv4_table },
-        { NET_IPX,              "ipx",          trans_net_ipx_table },
-        { NET_ATALK,            "appletalk",    trans_net_atalk_table },
-        { NET_NETROM,           "netrom",       trans_net_netrom_table },
-        { NET_AX25,             "ax25",         trans_net_ax25_table },
-        { NET_BRIDGE,           "bridge",       trans_net_bridge_table },
-        { NET_ROSE,             "rose",         trans_net_rose_table },
-        { NET_IPV6,             "ipv6",         trans_net_ipv6_table },
-        { NET_X25,              "x25",          trans_net_x25_table },
-        { NET_TR,               "token-ring",   trans_net_tr_table },
-        { NET_DECNET,           "decnet",       trans_net_decnet_table },
-        /*  NET_ECONET not used */
-        { NET_SCTP,             "sctp",         trans_net_sctp_table },
-        { NET_LLC,              "llc",          trans_net_llc_table },
-        { NET_NETFILTER,        "netfilter",    trans_net_netfilter_table },
-        { NET_DCCP,             "dccp",         trans_net_dccp_table },
-        { NET_IRDA,             "irda",         trans_net_irda_table },
-        { 2089,                 "nf_conntrack_max" },
-        {}
-};
-
-static const struct trans_ctl_table trans_fs_quota_table[] = {
-        { FS_DQ_LOOKUPS,        "lookups" },
-        { FS_DQ_DROPS,          "drops" },
-        { FS_DQ_READS,          "reads" },
-        { FS_DQ_WRITES,         "writes" },
-        { FS_DQ_CACHE_HITS,     "cache_hits" },
-        { FS_DQ_ALLOCATED,      "allocated_dquots" },
-        { FS_DQ_FREE,           "free_dquots" },
-        { FS_DQ_SYNCS,          "syncs" },
-        { FS_DQ_WARNINGS,       "warnings" },
-        {}
-};
-
-static const struct trans_ctl_table trans_fs_xfs_table[] = {
-        { XFS_SGID_INHERIT,     "irix_sgid_inherit" },
-        { XFS_SYMLINK_MODE,     "irix_symlink_mode" },
-        { XFS_PANIC_MASK,       "panic_mask" },
-
-        { XFS_ERRLEVEL,         "error_level" },
-        { XFS_SYNCD_TIMER,      "xfssyncd_centisecs" },
-        { XFS_INHERIT_SYNC,     "inherit_sync" },
-        { XFS_INHERIT_NODUMP,   "inherit_nodump" },
-        { XFS_INHERIT_NOATIME,  "inherit_noatime" },
-        { XFS_BUF_TIMER,        "xfsbufd_centisecs" },
-        { XFS_BUF_AGE,          "age_buffer_centisecs" },
-        { XFS_INHERIT_NOSYM,    "inherit_nosymlinks" },
-        { XFS_ROTORSTEP,        "rotorstep" },
-        { XFS_INHERIT_NODFRG,   "inherit_nodefrag" },
-        { XFS_FILESTREAM_TIMER, "filestream_centisecs" },
-        { XFS_STATS_CLEAR,      "stats_clear" },
-        {}
-};
-
-static const struct trans_ctl_table trans_fs_ocfs2_nm_table[] = {
-        { 1, "hb_ctl_path" },
-        {}
-};
-
-static const struct trans_ctl_table trans_fs_ocfs2_table[] = {
-        { 1,    "nm",   trans_fs_ocfs2_nm_table },
-        {}
-};
-
-static const struct trans_ctl_table trans_inotify_table[] = {
-        { INOTIFY_MAX_USER_INSTANCES,   "max_user_instances" },
-        { INOTIFY_MAX_USER_WATCHES,     "max_user_watches" },
-        { INOTIFY_MAX_QUEUED_EVENTS,    "max_queued_events" },
-        {}
-};
-
-static const struct trans_ctl_table trans_fs_table[] = {
-        { FS_NRINODE,           "inode-nr" },
-        { FS_STATINODE,         "inode-state" },
-        /* FS_MAXINODE unused */
-        /* FS_NRDQUOT unused */
-        /* FS_MAXDQUOT unused */
-        { FS_NRFILE,            "file-nr" },
-        { FS_MAXFILE,           "file-max" },
-        { FS_DENTRY,            "dentry-state" },
-        /* FS_NRSUPER unused */
-        /* FS_MAXUPSER unused */
-        { FS_OVERFLOWUID,       "overflowuid" },
-        { FS_OVERFLOWGID,       "overflowgid" },
-        { FS_LEASES,            "leases-enable" },
-        { FS_DIR_NOTIFY,        "dir-notify-enable" },
-        { FS_LEASE_TIME,        "lease-break-time" },
-        { FS_DQSTATS,           "quota",                trans_fs_quota_table },
-        { FS_XFS,               "xfs",                  trans_fs_xfs_table },
-        { FS_AIO_NR,            "aio-nr" },
-        { FS_AIO_MAX_NR,        "aio-max-nr" },
-        { FS_INOTIFY,           "inotify",              trans_inotify_table },
-        { FS_OCFS2,             "ocfs2",                trans_fs_ocfs2_table },
-        { KERN_SETUID_DUMPABLE, "suid_dumpable" },
-        {}
-};
-
-static const struct trans_ctl_table trans_debug_table[] = {
-        {}
-};
-
-static const struct trans_ctl_table trans_cdrom_table[] = {
-        { DEV_CDROM_INFO,               "info" },
-        { DEV_CDROM_AUTOCLOSE,          "autoclose" },
-        { DEV_CDROM_AUTOEJECT,          "autoeject" },
-        { DEV_CDROM_DEBUG,              "debug" },
-        { DEV_CDROM_LOCK,               "lock" },
-        { DEV_CDROM_CHECK_MEDIA,        "check_media" },
-        {}
-};
-
-static const struct trans_ctl_table trans_ipmi_table[] = {
-        { DEV_IPMI_POWEROFF_POWERCYCLE, "poweroff_powercycle" },
-        {}
-};
-
-static const struct trans_ctl_table trans_mac_hid_files[] = {
-        /* DEV_MAC_HID_KEYBOARD_SENDS_LINUX_KEYCODES unused */
-        /* DEV_MAC_HID_KEYBOARD_LOCK_KEYCODES unused */
-        { DEV_MAC_HID_MOUSE_BUTTON_EMULATION,   "mouse_button_emulation" },
-        { DEV_MAC_HID_MOUSE_BUTTON2_KEYCODE,    "mouse_button2_keycode" },
-        { DEV_MAC_HID_MOUSE_BUTTON3_KEYCODE,    "mouse_button3_keycode" },
-        /* DEV_MAC_HID_ADB_MOUSE_SENDS_KEYCODES unused */
-        {}
-};
-
-static const struct trans_ctl_table trans_raid_table[] = {
-        { DEV_RAID_SPEED_LIMIT_MIN,     "speed_limit_min" },
-        { DEV_RAID_SPEED_LIMIT_MAX,     "speed_limit_max" },
-        {}
-};
-
-static const struct trans_ctl_table trans_scsi_table[] = {
-        { DEV_SCSI_LOGGING_LEVEL, "logging_level" },
-        {}
-};
-
-static const struct trans_ctl_table trans_parport_default_table[] = {
-        { DEV_PARPORT_DEFAULT_TIMESLICE,        "timeslice" },
-        { DEV_PARPORT_DEFAULT_SPINTIME,         "spintime" },
-        {}
-};
-
-static const struct trans_ctl_table trans_parport_device_table[] = {
-        { DEV_PARPORT_DEVICE_TIMESLICE,         "timeslice" },
-        {}
-};
-
-static const struct trans_ctl_table trans_parport_devices_table[] = {
-        { DEV_PARPORT_DEVICES_ACTIVE,           "active" },
-        { 0, NULL, trans_parport_device_table },
-        {}
-};
-
-static const struct trans_ctl_table trans_parport_parport_table[] = {
-        { DEV_PARPORT_SPINTIME,         "spintime" },
-        { DEV_PARPORT_BASE_ADDR,        "base-addr" },
-        { DEV_PARPORT_IRQ,              "irq" },
-        { DEV_PARPORT_DMA,              "dma" },
-        { DEV_PARPORT_MODES,            "modes" },
-        { DEV_PARPORT_DEVICES,          "devices",      trans_parport_devices_table },
-        { DEV_PARPORT_AUTOPROBE,        "autoprobe" },
-        { DEV_PARPORT_AUTOPROBE + 1,    "autoprobe0" },
-        { DEV_PARPORT_AUTOPROBE + 2,    "autoprobe1" },
-        { DEV_PARPORT_AUTOPROBE + 3,    "autoprobe2" },
-        { DEV_PARPORT_AUTOPROBE + 4,    "autoprobe3" },
-        {}
-};
-static const struct trans_ctl_table trans_parport_table[] = {
-        { DEV_PARPORT_DEFAULT,  "default",      trans_parport_default_table },
-        { 0, NULL, trans_parport_parport_table },
-        {}
-};
-
-static const struct trans_ctl_table trans_dev_table[] = {
-        { DEV_CDROM,    "cdrom",        trans_cdrom_table },
-        /* DEV_HWMON unused */
-        { DEV_PARPORT,  "parport",      trans_parport_table },
-        { DEV_RAID,     "raid",         trans_raid_table },
-        { DEV_MAC_HID,  "mac_hid",      trans_mac_hid_files },
-        { DEV_SCSI,     "scsi",         trans_scsi_table },
-        { DEV_IPMI,     "ipmi",         trans_ipmi_table },
-        {}
-};
-
-static const struct trans_ctl_table trans_bus_isa_table[] = {
-        { BUS_ISA_MEM_BASE,     "membase" },
-        { BUS_ISA_PORT_BASE,    "portbase" },
-        { BUS_ISA_PORT_SHIFT,   "portshift" },
-        {}
-};
-
-static const struct trans_ctl_table trans_bus_table[] = {
-        { CTL_BUS_ISA,  "isa",  trans_bus_isa_table },
-        {}
-};
-
-static const struct trans_ctl_table trans_arlan_conf_table0[] = {
-        { 1,    "spreadingCode" },
-        { 2,    "channelNumber" },
-        { 3,    "scramblingDisable" },
-        { 4,    "txAttenuation" },
-        { 5,    "systemId" },
-        { 6,    "maxDatagramSize" },
-        { 7,    "maxFrameSize" },
-        { 8,    "maxRetries" },
-        { 9,    "receiveMode" },
-        { 10,   "priority" },
-        { 11,   "rootOrRepeater" },
-        { 12,   "SID" },
-        { 13,   "registrationMode" },
-        { 14,   "registrationFill" },
-        { 15,   "localTalkAddress" },
-        { 16,   "codeFormat" },
-        { 17,   "numChannels" },
-        { 18,   "channel1" },
-        { 19,   "channel2" },
-        { 20,   "channel3" },
-        { 21,   "channel4" },
-        { 22,   "txClear" },
-        { 23,   "txRetries" },
-        { 24,   "txRouting" },
-        { 25,   "txScrambled" },
-        { 26,   "rxParameter" },
-        { 27,   "txTimeoutMs" },
-        { 28,   "waitCardTimeout" },
-        { 29,   "channelSet" },
-        { 30,   "name" },
-        { 31,   "waitTime" },
-        { 32,   "lParameter" },
-        { 33,   "_15" },
-        { 34,   "headerSize" },
-        { 36,   "tx_delay_ms" },
-        { 37,   "retries" },
-        { 38,   "ReTransmitPacketMaxSize" },
-        { 39,   "waitReTransmitPacketMaxSize" },
-        { 40,   "fastReTransCount" },
-        { 41,   "driverRetransmissions" },
-        { 42,   "txAckTimeoutMs" },
-        { 43,   "registrationInterrupts" },
-        { 44,   "hardwareType" },
-        { 45,   "radioType" },
-        { 46,   "writeEEPROM" },
-        { 47,   "writeRadioType" },
-        { 48,   "entry_exit_debug" },
-        { 49,   "debug" },
-        { 50,   "in_speed" },
-        { 51,   "out_speed" },
-        { 52,   "in_speed10" },
-        { 53,   "out_speed10" },
-        { 54,   "in_speed_max" },
-        { 55,   "out_speed_max" },
-        { 56,   "measure_rate" },
-        { 57,   "pre_Command_Wait" },
-        { 58,   "rx_tweak1" },
-        { 59,   "rx_tweak2" },
-        { 60,   "tx_queue_len" },
-
-        { 150,  "arlan0-txRing" },
-        { 151,  "arlan0-rxRing" },
-        { 152,  "arlan0-18" },
-        { 153,  "arlan0-ring" },
-        { 154,  "arlan0-shm-cpy" },
-        { 155,  "config0" },
-        { 156,  "reset0" },
-        {}
-};
-
-static const struct trans_ctl_table trans_arlan_conf_table1[] = {
-        { 1,    "spreadingCode" },
-        { 2,    "channelNumber" },
-        { 3,    "scramblingDisable" },
-        { 4,    "txAttenuation" },
-        { 5,    "systemId" },
-        { 6,    "maxDatagramSize" },
-        { 7,    "maxFrameSize" },
-        { 8,    "maxRetries" },
-        { 9,    "receiveMode" },
-        { 10,   "priority" },
-        { 11,   "rootOrRepeater" },
-        { 12,   "SID" },
-        { 13,   "registrationMode" },
-        { 14,   "registrationFill" },
-        { 15,   "localTalkAddress" },
-        { 16,   "codeFormat" },
-        { 17,   "numChannels" },
-        { 18,   "channel1" },
-        { 19,   "channel2" },
-        { 20,   "channel3" },
-        { 21,   "channel4" },
-        { 22,   "txClear" },
-        { 23,   "txRetries" },
-        { 24,   "txRouting" },
-        { 25,   "txScrambled" },
-        { 26,   "rxParameter" },
-        { 27,   "txTimeoutMs" },
-        { 28,   "waitCardTimeout" },
-        { 29,   "channelSet" },
-        { 30,   "name" },
-        { 31,   "waitTime" },
-        { 32,   "lParameter" },
-        { 33,   "_15" },
-        { 34,   "headerSize" },
-        { 36,   "tx_delay_ms" },
-        { 37,   "retries" },
-        { 38,   "ReTransmitPacketMaxSize" },
-        { 39,   "waitReTransmitPacketMaxSize" },
-        { 40,   "fastReTransCount" },
-        { 41,   "driverRetransmissions" },
-        { 42,   "txAckTimeoutMs" },
-        { 43,   "registrationInterrupts" },
-        { 44,   "hardwareType" },
-        { 45,   "radioType" },
-        { 46,   "writeEEPROM" },
-        { 47,   "writeRadioType" },
-        { 48,   "entry_exit_debug" },
-        { 49,   "debug" },
-        { 50,   "in_speed" },
-        { 51,   "out_speed" },
-        { 52,   "in_speed10" },
-        { 53,   "out_speed10" },
-        { 54,   "in_speed_max" },
-        { 55,   "out_speed_max" },
-        { 56,   "measure_rate" },
-        { 57,   "pre_Command_Wait" },
-        { 58,   "rx_tweak1" },
-        { 59,   "rx_tweak2" },
-        { 60,   "tx_queue_len" },
-
-        { 150,  "arlan1-txRing" },
-        { 151,  "arlan1-rxRing" },
-        { 152,  "arlan1-18" },
-        { 153,  "arlan1-ring" },
-        { 154,  "arlan1-shm-cpy" },
-        { 155,  "config1" },
-        { 156,  "reset1" },
-        {}
-};
-
-static const struct trans_ctl_table trans_arlan_conf_table2[] = {
-        { 1,    "spreadingCode" },
-        { 2,    "channelNumber" },
-        { 3,    "scramblingDisable" },
-        { 4,    "txAttenuation" },
-        { 5,    "systemId" },
-        { 6,    "maxDatagramSize" },
-        { 7,    "maxFrameSize" },
-        { 8,    "maxRetries" },
-        { 9,    "receiveMode" },
-        { 10,   "priority" },
-        { 11,   "rootOrRepeater" },
-        { 12,   "SID" },
-        { 13,   "registrationMode" },
-        { 14,   "registrationFill" },
-        { 15,   "localTalkAddress" },
-        { 16,   "codeFormat" },
-        { 17,   "numChannels" },
-        { 18,   "channel1" },
-        { 19,   "channel2" },
-        { 20,   "channel3" },
-        { 21,   "channel4" },
-        { 22,   "txClear" },
-        { 23,   "txRetries" },
-        { 24,   "txRouting" },
-        { 25,   "txScrambled" },
-        { 26,   "rxParameter" },
-        { 27,   "txTimeoutMs" },
-        { 28,   "waitCardTimeout" },
-        { 29,   "channelSet" },
-        { 30,   "name" },
-        { 31,   "waitTime" },
-        { 32,   "lParameter" },
-        { 33,   "_15" },
-        { 34,   "headerSize" },
-        { 36,   "tx_delay_ms" },
-        { 37,   "retries" },
-        { 38,   "ReTransmitPacketMaxSize" },
-        { 39,   "waitReTransmitPacketMaxSize" },
-        { 40,   "fastReTransCount" },
-        { 41,   "driverRetransmissions" },
-        { 42,   "txAckTimeoutMs" },
-        { 43,   "registrationInterrupts" },
-        { 44,   "hardwareType" },
-        { 45,   "radioType" },
-        { 46,   "writeEEPROM" },
-        { 47,   "writeRadioType" },
-        { 48,   "entry_exit_debug" },
-        { 49,   "debug" },
-        { 50,   "in_speed" },
-        { 51,   "out_speed" },
-        { 52,   "in_speed10" },
-        { 53,   "out_speed10" },
-        { 54,   "in_speed_max" },
-        { 55,   "out_speed_max" },
-        { 56,   "measure_rate" },
-        { 57,   "pre_Command_Wait" },
-        { 58,   "rx_tweak1" },
-        { 59,   "rx_tweak2" },
-        { 60,   "tx_queue_len" },
-
-        { 150,  "arlan2-txRing" },
-        { 151,  "arlan2-rxRing" },
-        { 152,  "arlan2-18" },
-        { 153,  "arlan2-ring" },
-        { 154,  "arlan2-shm-cpy" },
-        { 155,  "config2" },
-        { 156,  "reset2" },
-        {}
-};
-
-static const struct trans_ctl_table trans_arlan_conf_table3[] = {
-        { 1,    "spreadingCode" },
-        { 2,    "channelNumber" },
-        { 3,    "scramblingDisable" },
-        { 4,    "txAttenuation" },
-        { 5,    "systemId" },
-        { 6,    "maxDatagramSize" },
-        { 7,    "maxFrameSize" },
-        { 8,    "maxRetries" },
-        { 9,    "receiveMode" },
-        { 10,   "priority" },
-        { 11,   "rootOrRepeater" },
-        { 12,   "SID" },
-        { 13,   "registrationMode" },
-        { 14,   "registrationFill" },
-        { 15,   "localTalkAddress" },
-        { 16,   "codeFormat" },
-        { 17,   "numChannels" },
-        { 18,   "channel1" },
-        { 19,   "channel2" },
-        { 20,   "channel3" },
-        { 21,   "channel4" },
-        { 22,   "txClear" },
-        { 23,   "txRetries" },
-        { 24,   "txRouting" },
-        { 25,   "txScrambled" },
-        { 26,   "rxParameter" },
-        { 27,   "txTimeoutMs" },
-        { 28,   "waitCardTimeout" },
-        { 29,   "channelSet" },
-        { 30,   "name" },
-        { 31,   "waitTime" },
-        { 32,   "lParameter" },
-        { 33,   "_15" },
-        { 34,   "headerSize" },
-        { 36,   "tx_delay_ms" },
-        { 37,   "retries" },
-        { 38,   "ReTransmitPacketMaxSize" },
-        { 39,   "waitReTransmitPacketMaxSize" },
-        { 40,   "fastReTransCount" },
-        { 41,   "driverRetransmissions" },
-        { 42,   "txAckTimeoutMs" },
-        { 43,   "registrationInterrupts" },
-        { 44,   "hardwareType" },
-        { 45,   "radioType" },
-        { 46,   "writeEEPROM" },
-        { 47,   "writeRadioType" },
-        { 48,   "entry_exit_debug" },
-        { 49,   "debug" },
-        { 50,   "in_speed" },
-        { 51,   "out_speed" },
-        { 52,   "in_speed10" },
-        { 53,   "out_speed10" },
-        { 54,   "in_speed_max" },
-        { 55,   "out_speed_max" },
-        { 56,   "measure_rate" },
-        { 57,   "pre_Command_Wait" },
-        { 58,   "rx_tweak1" },
-        { 59,   "rx_tweak2" },
-        { 60,   "tx_queue_len" },
-
-        { 150,  "arlan3-txRing" },
-        { 151,  "arlan3-rxRing" },
-        { 152,  "arlan3-18" },
-        { 153,  "arlan3-ring" },
-        { 154,  "arlan3-shm-cpy" },
-        { 155,  "config3" },
-        { 156,  "reset3" },
-        {}
-};
-
-static const struct trans_ctl_table trans_arlan_table[] = {
-        { 1,            "arlan0",       trans_arlan_conf_table0 },
-        { 2,            "arlan1",       trans_arlan_conf_table1 },
-        { 3,            "arlan2",       trans_arlan_conf_table2 },
-        { 4,            "arlan3",       trans_arlan_conf_table3 },
-        {}
-};
-
-static const struct trans_ctl_table trans_s390dbf_table[] = {
-        { 5678 /* CTL_S390DBF_STOPPABLE */,     "debug_stoppable" },
-        { 5679 /* CTL_S390DBF_ACTIVE */,        "debug_active" },
-        {}
-};
-
-static const struct trans_ctl_table trans_sunrpc_table[] = {
-        { CTL_RPCDEBUG,         "rpc_debug" },
-        { CTL_NFSDEBUG,         "nfs_debug" },
-        { CTL_NFSDDEBUG,        "nfsd_debug" },
-        { CTL_NLMDEBUG,         "nlm_debug" },
-        { CTL_SLOTTABLE_UDP,    "udp_slot_table_entries" },
-        { CTL_SLOTTABLE_TCP,    "tcp_slot_table_entries" },
-        { CTL_MIN_RESVPORT,     "min_resvport" },
-        { CTL_MAX_RESVPORT,     "max_resvport" },
-        {}
-};
-
-static const struct trans_ctl_table trans_pm_table[] = {
-        { 1 /* CTL_PM_SUSPEND */,       "suspend" },
-        { 2 /* CTL_PM_CMODE */,         "cmode" },
-        { 3 /* CTL_PM_P0 */,            "p0" },
-        { 4 /* CTL_PM_CM */,            "cm" },
-        {}
-};
-
-static const struct trans_ctl_table trans_frv_table[] = {
-        { 1,    "cache-mode" },
-        { 2,    "pin-cxnr" },
-        {}
-};
-
-static const struct trans_ctl_table trans_root_table[] = {
-        { CTL_KERN,     "kernel",       trans_kern_table },
-        { CTL_VM,       "vm",           trans_vm_table },
-        { CTL_NET,      "net",          trans_net_table },
-        /* CTL_PROC not used */
-        { CTL_FS,       "fs",           trans_fs_table },
-        { CTL_DEBUG,    "debug",        trans_debug_table },
-        { CTL_DEV,      "dev",          trans_dev_table },
-        { CTL_BUS,      "bus",          trans_bus_table },
-        { CTL_ABI,      "abi" },
-        /* CTL_CPU not used */
-        { CTL_ARLAN,    "arlan",        trans_arlan_table },
-        { CTL_S390DBF,  "s390dbf",      trans_s390dbf_table },
-        { CTL_SUNRPC,   "sunrpc",       trans_sunrpc_table },
-        { CTL_PM,       "pm",           trans_pm_table },
-        { CTL_FRV,      "frv",          trans_frv_table },
-        {}
-};
-
-
-
 
 static int sysctl_depth(struct ctl_table *table)
 {
@@ -1262,47 +28,6 @@ static struct ctl_table *sysctl_parent(struct ctl_table *table, int n)
         return table;
 }
 
-static const struct trans_ctl_table *sysctl_binary_lookup(struct ctl_table *table)
-{
-        struct ctl_table *test;
-        const struct trans_ctl_table *ref;
-        int cur_depth;
-
-        cur_depth = sysctl_depth(table);
-
-        ref = trans_root_table;
-repeat:
-        test = sysctl_parent(table, cur_depth);
-        for (; ref->ctl_name || ref->procname || ref->child; ref++) {
-                int match = 0;
-
-                if (cur_depth && !ref->child)
-                        continue;
-
-                if (test->procname && ref->procname &&
-                        (strcmp(test->procname, ref->procname) == 0))
-                        match++;
-
-                if (test->ctl_name && ref->ctl_name &&
-                        (test->ctl_name == ref->ctl_name))
-                        match++;
-
-                if (!ref->ctl_name && !ref->procname)
-                        match++;
-
-                if (match) {
-                        if (cur_depth != 0) {
-                                cur_depth--;
-                                ref = ref->child;
-                                goto repeat;
-                        }
-                        goto out;
-                }
-        }
-        ref = NULL;
-out:
-        return ref;
-}
 
 static void sysctl_print_path(struct ctl_table *table)
 {
@@ -1316,26 +41,6 @@ static void sysctl_print_path(struct ctl_table *table)
                 }
         }
         printk(" ");
-        if (table->ctl_name) {
-                for (i = depth; i >= 0; i--) {
-                        tmp = sysctl_parent(table, i);
-                        printk(".%d", tmp->ctl_name);
-                }
-        }
-}
-
-static void sysctl_repair_table(struct ctl_table *table)
-{
-        /* Don't complain about the classic default
-         * sysctl strategy routine.  Maybe later we
-         * can get the tables fixed and complain about
-         * this.
-         */
-        if (table->ctl_name && table->procname &&
-                (table->proc_handler == proc_dointvec) &&
-                (!table->strategy)) {
-                table->strategy = sysctl_data;
-        }
 }
 
 static struct ctl_table *sysctl_check_lookup(struct nsproxy *namespaces,
@@ -1353,7 +58,7 @@ static struct ctl_table *sysctl_check_lookup(struct nsproxy *namespaces,
                 ref = head->ctl_table;
 repeat:
                 test = sysctl_parent(table, cur_depth);
-                for (; ref->ctl_name || ref->procname; ref++) {
+                for (; ref->procname; ref++) {
                         int match = 0;
                         if (cur_depth && !ref->child)
                                 continue;
@@ -1362,10 +67,6 @@ repeat:
                             (strcmp(test->procname, ref->procname) == 0))
                                         match++;
 
-                        if (test->ctl_name && ref->ctl_name &&
-                            (test->ctl_name == ref->ctl_name))
-                                match++;
-
                         if (match) {
                                 if (cur_depth != 0) {
                                         cur_depth--;
@@ -1393,38 +94,6 @@ static void set_fail(const char **fail, struct ctl_table *table, const char *str
         *fail = str;
 }
 
-static int sysctl_check_dir(struct nsproxy *namespaces,
-                                struct ctl_table *table)
-{
-        struct ctl_table *ref;
-        int error;
-
-        error = 0;
-        ref = sysctl_check_lookup(namespaces, table);
-        if (ref) {
-                int match = 0;
-                if ((!table->procname && !ref->procname) ||
-                    (table->procname && ref->procname &&
-                     (strcmp(table->procname, ref->procname) == 0)))
-                        match++;
-
-                if ((!table->ctl_name && !ref->ctl_name) ||
-                    (table->ctl_name && ref->ctl_name &&
-                     (table->ctl_name == ref->ctl_name)))
-                        match++;
-
-                if (match != 2) {
-                        printk(KERN_ERR "%s: failed: ", __func__);
-                        sysctl_print_path(table);
-                        printk(" ref: ");
-                        sysctl_print_path(ref);
-                        printk("\n");
-                        error = -EINVAL;
-                }
-        }
-        return error;
-}
-
 static void sysctl_check_leaf(struct nsproxy *namespaces,
                                 struct ctl_table *table, const char **fail)
 {
@@ -1435,37 +104,15 @@ static void sysctl_check_leaf(struct nsproxy *namespaces,
                 set_fail(fail, table, "Sysctl already exists");
 }
 
-static void sysctl_check_bin_path(struct ctl_table *table, const char **fail)
-{
-        const struct trans_ctl_table *ref;
-
-        ref = sysctl_binary_lookup(table);
-        if (table->ctl_name && !ref)
-                set_fail(fail, table, "Unknown sysctl binary path");
-        if (ref) {
-                if (ref->procname &&
-                    (!table->procname ||
-                     (strcmp(table->procname, ref->procname) != 0)))
-                        set_fail(fail, table, "procname does not match binary path procname");
-
-                if (ref->ctl_name && table->ctl_name &&
-                    (table->ctl_name != ref->ctl_name))
-                        set_fail(fail, table, "ctl_name does not match binary path ctl_name");
-        }
-}
-
 int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
 {
         int error = 0;
-        for (; table->ctl_name || table->procname; table++) {
+        for (; table->procname; table++) {
                 const char *fail = NULL;
 
-                sysctl_repair_table(table);
                 if (table->parent) {
                         if (table->procname && !table->parent->procname)
                                 set_fail(&fail, table, "Parent without procname");
-                        if (table->ctl_name && !table->parent->ctl_name)
-                                set_fail(&fail, table, "Parent without ctl_name");
                 }
                 if (!table->procname)
                         set_fail(&fail, table, "No procname");
@@ -1478,21 +125,12 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
                                 set_fail(&fail, table, "Writable sysctl directory");
                         if (table->proc_handler)
                                 set_fail(&fail, table, "Directory with proc_handler");
-                        if (table->strategy)
-                                set_fail(&fail, table, "Directory with strategy");
                         if (table->extra1)
                                 set_fail(&fail, table, "Directory with extra1");
                         if (table->extra2)
                                 set_fail(&fail, table, "Directory with extra2");
-                        if (sysctl_check_dir(namespaces, table))
-                                set_fail(&fail, table, "Inconsistent directory names");
                 } else {
-                        if ((table->strategy == sysctl_data) ||
-                            (table->strategy == sysctl_string) ||
-                            (table->strategy == sysctl_intvec) ||
-                            (table->strategy == sysctl_jiffies) ||
-                            (table->strategy == sysctl_ms_jiffies) ||
-                            (table->proc_handler == proc_dostring) ||
+                        if ((table->proc_handler == proc_dostring) ||
                             (table->proc_handler == proc_dointvec) ||
                             (table->proc_handler == proc_dointvec_minmax) ||
                             (table->proc_handler == proc_dointvec_jiffies) ||
@@ -1514,14 +152,6 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
                                                 set_fail(&fail, table, "No max");
                                 }
                         }
-#ifdef CONFIG_SYSCTL_SYSCALL
-                        if (table->ctl_name && !table->strategy)
-                                set_fail(&fail, table, "Missing strategy");
-#endif
-#if 0
-                        if (!table->ctl_name && table->strategy)
-                                set_fail(&fail, table, "Strategy without ctl_name");
-#endif
 #ifdef CONFIG_PROC_SYSCTL
                         if (table->procname && !table->proc_handler)
                                 set_fail(&fail, table, "No proc_handler");
@@ -1532,7 +162,6 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
 #endif
                         sysctl_check_leaf(namespaces, table, &fail);
                 }
-                sysctl_check_bin_path(table, &fail);
                 if (table->mode > 0777)
                         set_fail(&fail, table, "bogus .mode");
                 if (fail) {
diff --git a/kernel/time.c b/kernel/time.c
index 2e2e469a7fec..804798005d19 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -662,6 +662,36 @@ u64 nsec_to_clock_t(u64 x)
 #endif
 }
 
+/**
+ * nsecs_to_jiffies - Convert nsecs in u64 to jiffies
+ *
+ * @n:  nsecs in u64
+ *
+ * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64.
+ * And this doesn't return MAX_JIFFY_OFFSET since this function is designed
+ * for scheduler, not for use in device drivers to calculate timeout value.
+ *
+ * note:
+ *   NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
+ *   ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
+ */
+unsigned long nsecs_to_jiffies(u64 n)
+{
+#if (NSEC_PER_SEC % HZ) == 0
+        /* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */
+        return div_u64(n, NSEC_PER_SEC / HZ);
+#elif (HZ % 512) == 0
+        /* overflow after 292 years if HZ = 1024 */
+        return div_u64(n * HZ / 512, NSEC_PER_SEC / 512);
+#else
+        /*
+         * Generic case - optimized for cases where HZ is a multiple of 3.
+         * overflow after 64.99 years, exact for HZ = 60, 72, 90, 120 etc.
+         */
+        return div_u64(n * 9, (9ull * NSEC_PER_SEC + HZ / 2) / HZ);
+#endif
+}
+
 #if (BITS_PER_LONG < 64)
 u64 get_jiffies_64(void)
 {
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index b416512ad17f..d006554888dc 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -339,6 +339,27 @@ config POWER_TRACER
           power management decisions, specifically the C-state and P-state
           behavior.
 
+config KSYM_TRACER
+        bool "Trace read and write access on kernel memory locations"
+        depends on HAVE_HW_BREAKPOINT
+        select TRACING
+        help
+          This tracer helps find read and write operations on any given kernel
+          symbol i.e. /proc/kallsyms.
+
+config PROFILE_KSYM_TRACER
+        bool "Profile all kernel memory accesses on 'watched' variables"
+        depends on KSYM_TRACER
+        help
+          This tracer profiles kernel accesses on variables watched through the
+          ksym tracer ftrace plugin. Depending upon the hardware, all read
+          and write operations on kernel variables can be monitored for
+          accesses.
+
+          The results will be displayed in:
+          /debugfs/tracing/profile_ksym
+
+          Say N if unsure.
 
 config STACK_TRACER
         bool "Trace max stack"
@@ -428,6 +449,23 @@ config BLK_DEV_IO_TRACE
 
           If unsure, say N.
 
+config KPROBE_EVENT
+        depends on KPROBES
+        depends on X86
+        bool "Enable kprobes-based dynamic events"
+        select TRACING
+        default y
+        help
+          This allows the user to add tracing events (similar to tracepoints) on the fly
+          via the ftrace interface. See Documentation/trace/kprobetrace.txt
+          for more details.
+
+          Those events can be inserted wherever kprobes can probe, and record
+          various register and memory values.
+
+          This option is also required by perf-probe subcommand of perf tools. If
+          you want to use perf tools, this option is strongly recommended.
+
 config DYNAMIC_FTRACE
         bool "enable/disable ftrace tracepoints dynamically"
         depends on FUNCTION_TRACER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 26f03ac07c2b..cd9ecd89ec77 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -53,6 +53,8 @@ obj-$(CONFIG_EVENT_TRACING) += trace_export.o
 obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
 obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
+obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
+obj-$(CONFIG_KSYM_TRACER) += trace_ksym.o
 obj-$(CONFIG_EVENT_TRACING) += power-traces.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index a72c6e03deec..a1ca4956ab5e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -397,18 +397,21 @@ int ring_buffer_print_page_header(struct trace_seq *s)
         int ret;
 
         ret = trace_seq_printf(s, "\tfield: u64 timestamp;\t"
-                               "offset:0;\tsize:%u;\n",
-                               (unsigned int)sizeof(field.time_stamp));
+                               "offset:0;\tsize:%u;\tsigned:%u;\n",
+                               (unsigned int)sizeof(field.time_stamp),
+                               (unsigned int)is_signed_type(u64));
 
         ret = trace_seq_printf(s, "\tfield: local_t commit;\t"
-                               "offset:%u;\tsize:%u;\n",
+                               "offset:%u;\tsize:%u;\tsigned:%u;\n",
                                (unsigned int)offsetof(typeof(field), commit),
-                               (unsigned int)sizeof(field.commit));
+                               (unsigned int)sizeof(field.commit),
+                               (unsigned int)is_signed_type(long));
 
         ret = trace_seq_printf(s, "\tfield: char data;\t"
-                               "offset:%u;\tsize:%u;\n",
+                               "offset:%u;\tsize:%u;\tsigned:%u;\n",
                                (unsigned int)offsetof(typeof(field), data),
-                               (unsigned int)BUF_PAGE_SIZE);
+                               (unsigned int)BUF_PAGE_SIZE,
+                               (unsigned int)is_signed_type(char));
 
         return ret;
 }
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index acef8b4636f0..1d7f4830a80d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -11,6 +11,7 @@
 #include <linux/ftrace.h>
 #include <trace/boot.h>
 #include <linux/kmemtrace.h>
+#include <linux/hw_breakpoint.h>
 
 #include <linux/trace_seq.h>
 #include <linux/ftrace_event.h>
@@ -37,6 +38,7 @@ enum trace_type {
         TRACE_KMEM_ALLOC,
         TRACE_KMEM_FREE,
         TRACE_BLK,
+        TRACE_KSYM,
 
         __TRACE_LAST_TYPE,
 };
@@ -98,9 +100,32 @@ struct syscall_trace_enter {
 struct syscall_trace_exit {
         struct trace_entry      ent;
         int                     nr;
-        unsigned long           ret;
+        long                    ret;
 };
 
+struct kprobe_trace_entry {
+        struct trace_entry      ent;
+        unsigned long           ip;
+        int                     nargs;
+        unsigned long           args[];
+};
+
+#define SIZEOF_KPROBE_TRACE_ENTRY(n)                    \
+        (offsetof(struct kprobe_trace_entry, args) +    \
+        (sizeof(unsigned long) * (n)))
+
+struct kretprobe_trace_entry {
+        struct trace_entry      ent;
+        unsigned long           func;
+        unsigned long           ret_ip;
+        int                     nargs;
+        unsigned long           args[];
+};
+
+#define SIZEOF_KRETPROBE_TRACE_ENTRY(n)                 \
+        (offsetof(struct kretprobe_trace_entry, args) + \
+        (sizeof(unsigned long) * (n)))
+
 /*
  * trace_flag_type is an enumeration that holds different
  * states when a trace occurs. These are:
@@ -209,6 +234,7 @@ extern void __ftrace_bad_type(void);
                           TRACE_KMEM_ALLOC);    \
                 IF_ASSIGN(var, ent, struct kmemtrace_free_entry,        \
                           TRACE_KMEM_FREE);     \
+                IF_ASSIGN(var, ent, struct ksym_trace_entry, TRACE_KSYM);\
                 __ftrace_bad_type();                                    \
         } while (0)
 
@@ -364,6 +390,8 @@ int register_tracer(struct tracer *type);
 void unregister_tracer(struct tracer *type);
 int is_tracing_stopped(void);
 
+extern int process_new_ksym_entry(char *ksymname, int op, unsigned long addr);
+
 extern unsigned long nsecs_to_usecs(unsigned long nsecs);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
@@ -438,6 +466,8 @@ extern int trace_selftest_startup_branch(struct tracer *trace,
                                          struct trace_array *tr);
 extern int trace_selftest_startup_hw_branches(struct tracer *trace,
                                               struct trace_array *tr);
+extern int trace_selftest_startup_ksym(struct tracer *trace,
+                                         struct trace_array *tr);
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 extern void *head_page(struct trace_array_cpu *data);
@@ -683,7 +713,6 @@ struct event_filter {
         int                     n_preds;
         struct filter_pred      **preds;
         char                    *filter_string;
-        bool                    no_reset;
 };
 
 struct event_subsystem {
@@ -703,7 +732,7 @@ typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event,
 typedef int (*regex_match_func)(char *str, struct regex *r, int len);
 
 enum regex_type {
-        MATCH_FULL,
+        MATCH_FULL = 0,
         MATCH_FRONT_ONLY,
         MATCH_MIDDLE_ONLY,
         MATCH_END_ONLY,
@@ -744,7 +773,8 @@ filter_check_discard(struct ftrace_event_call *call, void *rec,
                      struct ring_buffer *buffer,
                      struct ring_buffer_event *event)
 {
-        if (unlikely(call->filter_active) && !filter_match_preds(call, rec)) {
+        if (unlikely(call->filter_active) &&
+            !filter_match_preds(call->filter, rec)) {
                 ring_buffer_discard_commit(buffer, event);
                 return 1;
         }
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index ead3d724599d..c16a08f399df 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -364,3 +364,19 @@ FTRACE_ENTRY(kmem_free, kmemtrace_free_entry,
         F_printk("type:%u call_site:%lx ptr:%p",
                  __entry->type_id, __entry->call_site, __entry->ptr)
 );
+
+FTRACE_ENTRY(ksym_trace, ksym_trace_entry,
+
+        TRACE_KSYM,
+
+        F_STRUCT(
+                __field(        unsigned long,  ip                        )
+                __field(        unsigned char,  type                      )
+                __array(        char         ,  cmd,       TASK_COMM_LEN  )
+                __field(        unsigned long,  addr                      )
+        ),
+
+        F_printk("ip: %pF type: %d ksym_name: %pS cmd: %s",
+                (void *)__entry->ip, (unsigned int)__entry->type,
+                (void *)__entry->addr,  __entry->cmd)
+);
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c
index 8d5c171cc998..d9c60f80aa0d 100644
--- a/kernel/trace/trace_event_profile.c
+++ b/kernel/trace/trace_event_profile.c
@@ -8,17 +8,14 @@
 #include <linux/module.h>
 #include "trace.h"
 
-/*
- * We can't use a size but a type in alloc_percpu()
- * So let's create a dummy type that matches the desired size
- */
-typedef struct {char buf[FTRACE_MAX_PROFILE_SIZE];} profile_buf_t;
 
-char            *trace_profile_buf;
-EXPORT_SYMBOL_GPL(trace_profile_buf);
+char *perf_trace_buf;
+EXPORT_SYMBOL_GPL(perf_trace_buf);
+
+char *perf_trace_buf_nmi;
+EXPORT_SYMBOL_GPL(perf_trace_buf_nmi);
 
-char            *trace_profile_buf_nmi;
-EXPORT_SYMBOL_GPL(trace_profile_buf_nmi);
+typedef typeof(char [FTRACE_MAX_PROFILE_SIZE]) perf_trace_t ;
 
 /* Count the events in use (per event id, not per instance) */
 static int      total_profile_count;
@@ -32,20 +29,20 @@ static int ftrace_profile_enable_event(struct ftrace_event_call *event)
                 return 0;
 
         if (!total_profile_count) {
-                buf = (char *)alloc_percpu(profile_buf_t);
+                buf = (char *)alloc_percpu(perf_trace_t);
                 if (!buf)
                         goto fail_buf;
 
-                rcu_assign_pointer(trace_profile_buf, buf);
+                rcu_assign_pointer(perf_trace_buf, buf);
 
-                buf = (char *)alloc_percpu(profile_buf_t);
+                buf = (char *)alloc_percpu(perf_trace_t);
                 if (!buf)
                         goto fail_buf_nmi;
 
-                rcu_assign_pointer(trace_profile_buf_nmi, buf);
+                rcu_assign_pointer(perf_trace_buf_nmi, buf);
         }
 
-        ret = event->profile_enable();
+        ret = event->profile_enable(event);
         if (!ret) {
                 total_profile_count++;
                 return 0;
@@ -53,10 +50,10 @@ static int ftrace_profile_enable_event(struct ftrace_event_call *event)
 
 fail_buf_nmi:
         if (!total_profile_count) {
-                free_percpu(trace_profile_buf_nmi);
-                free_percpu(trace_profile_buf);
-                trace_profile_buf_nmi = NULL;
-                trace_profile_buf = NULL;
+                free_percpu(perf_trace_buf_nmi);
+                free_percpu(perf_trace_buf);
+                perf_trace_buf_nmi = NULL;
+                perf_trace_buf = NULL;
         }
 fail_buf:
         atomic_dec(&event->profile_count);
@@ -89,14 +86,14 @@ static void ftrace_profile_disable_event(struct ftrace_event_call *event)
         if (!atomic_add_negative(-1, &event->profile_count))
                 return;
 
-        event->profile_disable();
+        event->profile_disable(event);
 
         if (!--total_profile_count) {
-                buf = trace_profile_buf;
-                rcu_assign_pointer(trace_profile_buf, NULL);
+                buf = perf_trace_buf;
+                rcu_assign_pointer(perf_trace_buf, NULL);
 
-                nmi_buf = trace_profile_buf_nmi;
-                rcu_assign_pointer(trace_profile_buf_nmi, NULL);
+                nmi_buf = perf_trace_buf_nmi;
+                rcu_assign_pointer(perf_trace_buf_nmi, NULL);
 
                 /*
                  * Ensure every events in profiling have finished before
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 5e9ffc33f6db..1d18315dc836 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -93,9 +93,7 @@ int trace_define_common_fields(struct ftrace_event_call *call)
 }
 EXPORT_SYMBOL_GPL(trace_define_common_fields);
 
-#ifdef CONFIG_MODULES
-
-static void trace_destroy_fields(struct ftrace_event_call *call)
+void trace_destroy_fields(struct ftrace_event_call *call)
 {
         struct ftrace_event_field *field, *next;
 
@@ -107,8 +105,6 @@ static void trace_destroy_fields(struct ftrace_event_call *call)
         }
 }
 
-#endif /* CONFIG_MODULES */
-
 static void ftrace_event_enable_disable(struct ftrace_event_call *call,
                                         int enable)
 {
@@ -117,14 +113,14 @@ static void ftrace_event_enable_disable(struct ftrace_event_call *call,
                 if (call->enabled) {
                         call->enabled = 0;
                         tracing_stop_cmdline_record();
-                        call->unregfunc(call->data);
+                        call->unregfunc(call);
                 }
                 break;
         case 1:
                 if (!call->enabled) {
                         call->enabled = 1;
                         tracing_start_cmdline_record();
-                        call->regfunc(call->data);
+                        call->regfunc(call);
                 }
                 break;
         }
@@ -507,7 +503,7 @@ extern char *__bad_type_size(void);
 #define FIELD(type, name)                                               \
         sizeof(type) != sizeof(field.name) ? __bad_type_size() :        \
         #type, "common_" #name, offsetof(typeof(field), name),          \
-                sizeof(field.name)
+                sizeof(field.name), is_signed_type(type)
 
 static int trace_write_header(struct trace_seq *s)
 {
@@ -515,17 +511,17 @@ static int trace_write_header(struct trace_seq *s)
 
         /* struct trace_entry */
         return trace_seq_printf(s,
-                                "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-                                "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-                                "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-                                "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-                                "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-                                "\n",
-                                FIELD(unsigned short, type),
-                                FIELD(unsigned char, flags),
-                                FIELD(unsigned char, preempt_count),
-                                FIELD(int, pid),
-                                FIELD(int, lock_depth));
+                        "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+                        "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+                        "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+                        "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+                        "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+                        "\n",
+                        FIELD(unsigned short, type),
+                        FIELD(unsigned char, flags),
+                        FIELD(unsigned char, preempt_count),
+                        FIELD(int, pid),
+                        FIELD(int, lock_depth));
 }
 
 static ssize_t
@@ -937,27 +933,46 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
         return 0;
 }
 
-#define for_each_event(event, start, end)                       \
-        for (event = start;                                     \
-             (unsigned long)event < (unsigned long)end;         \
-             event++)
+static int __trace_add_event_call(struct ftrace_event_call *call)
+{
+        struct dentry *d_events;
+        int ret;
 
-#ifdef CONFIG_MODULES
+        if (!call->name)
+                return -EINVAL;
 
-static LIST_HEAD(ftrace_module_file_list);
+        if (call->raw_init) {
+                ret = call->raw_init(call);
+                if (ret < 0) {
+                        if (ret != -ENOSYS)
+                                pr_warning("Could not initialize trace "
+                                "events/%s\n", call->name);
+                        return ret;
+                }
+        }
 
-/*
- * Modules must own their file_operations to keep up with
- * reference counting.
- */
-struct ftrace_module_file_ops {
-        struct list_head                list;
-        struct module                   *mod;
-        struct file_operations          id;
-        struct file_operations          enable;
-        struct file_operations          format;
-        struct file_operations          filter;
-};
+        d_events = event_trace_events_dir();
+        if (!d_events)
+                return -ENOENT;
+
+        ret = event_create_dir(call, d_events, &ftrace_event_id_fops,
+                                &ftrace_enable_fops, &ftrace_event_filter_fops,
+                                &ftrace_event_format_fops);
+        if (!ret)
+                list_add(&call->list, &ftrace_events);
+
+        return ret;
+}
+
+/* Add an additional event_call dynamically */
+int trace_add_event_call(struct ftrace_event_call *call)
+{
+        int ret;
+        mutex_lock(&event_mutex);
+        ret = __trace_add_event_call(call);
+        mutex_unlock(&event_mutex);
+        return ret;
+}
 
 static void remove_subsystem_dir(const char *name)
 {
@@ -985,6 +1000,53 @@ static void remove_subsystem_dir(const char *name)
         }
 }
 
+/*
+ * Must be called under locking both of event_mutex and trace_event_mutex.
+ */
+static void __trace_remove_event_call(struct ftrace_event_call *call)
+{
+        ftrace_event_enable_disable(call, 0);
+        if (call->event)
+                __unregister_ftrace_event(call->event);
+        debugfs_remove_recursive(call->dir);
+        list_del(&call->list);
+        trace_destroy_fields(call);
+        destroy_preds(call);
+        remove_subsystem_dir(call->system);
+}
+
+/* Remove an event_call */
+void trace_remove_event_call(struct ftrace_event_call *call)
+{
+        mutex_lock(&event_mutex);
+        down_write(&trace_event_mutex);
+        __trace_remove_event_call(call);
+        up_write(&trace_event_mutex);
+        mutex_unlock(&event_mutex);
+}
+
+#define for_each_event(event, start, end)                       \
+        for (event = start;                                     \
+             (unsigned long)event < (unsigned long)end;         \
+             event++)
+
+#ifdef CONFIG_MODULES
+
+static LIST_HEAD(ftrace_module_file_list);
+
+/*
+ * Modules must own their file_operations to keep up with
+ * reference counting.
+ */
+struct ftrace_module_file_ops {
+        struct list_head                list;
+        struct module                   *mod;
+        struct file_operations          id;
+        struct file_operations          enable;
+        struct file_operations          format;
+        struct file_operations          filter;
+};
+
 static struct ftrace_module_file_ops *
 trace_create_file_ops(struct module *mod)
 {
@@ -1042,7 +1104,7 @@ static void trace_module_add_events(struct module *mod)
                 if (!call->name)
                         continue;
                 if (call->raw_init) {
-                        ret = call->raw_init();
+                        ret = call->raw_init(call);
                         if (ret < 0) {
                                 if (ret != -ENOSYS)
                                         pr_warning("Could not initialize trace "
@@ -1060,10 +1122,11 @@ static void trace_module_add_events(struct module *mod)
                                 return;
                 }
                 call->mod = mod;
-                list_add(&call->list, &ftrace_events);
-                event_create_dir(call, d_events,
-                                 &file_ops->id, &file_ops->enable,
-                                 &file_ops->filter, &file_ops->format);
+                ret = event_create_dir(call, d_events,
+                                       &file_ops->id, &file_ops->enable,
+                                       &file_ops->filter, &file_ops->format);
+                if (!ret)
+                        list_add(&call->list, &ftrace_events);
         }
 }
 
@@ -1077,14 +1140,7 @@ static void trace_module_remove_events(struct module *mod)
         list_for_each_entry_safe(call, p, &ftrace_events, list) {
                 if (call->mod == mod) {
                         found = true;
-                        ftrace_event_enable_disable(call, 0);
-                        if (call->event)
-                                __unregister_ftrace_event(call->event);
-                        debugfs_remove_recursive(call->dir);
-                        list_del(&call->list);
-                        trace_destroy_fields(call);
-                        destroy_preds(call);
-                        remove_subsystem_dir(call->system);
+                        __trace_remove_event_call(call);
                 }
         }
 
@@ -1202,7 +1258,7 @@ static __init int event_trace_init(void)
                 if (!call->name)
                         continue;
                 if (call->raw_init) {
-                        ret = call->raw_init();
+                        ret = call->raw_init(call);
                         if (ret < 0) {
                                 if (ret != -ENOSYS)
                                         pr_warning("Could not initialize trace "
@@ -1210,10 +1266,12 @@ static __init int event_trace_init(void)
                                 continue;
                         }
                 }
-                list_add(&call->list, &ftrace_events);
-                event_create_dir(call, d_events, &ftrace_event_id_fops,
-                                 &ftrace_enable_fops, &ftrace_event_filter_fops,
-                                 &ftrace_event_format_fops);
+                ret = event_create_dir(call, d_events, &ftrace_event_id_fops,
+                                       &ftrace_enable_fops,
+                                       &ftrace_event_filter_fops,
+                                       &ftrace_event_format_fops);
+                if (!ret)
+                        list_add(&call->list, &ftrace_events);
         }
 
         while (true) {
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 92672016da28..50504cb228de 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/mutex.h>
+#include <linux/perf_event.h>
 
 #include "trace.h"
 #include "trace_output.h"
@@ -29,6 +30,7 @@ enum filter_op_ids
 {
         OP_OR,
         OP_AND,
+        OP_GLOB,
         OP_NE,
         OP_EQ,
         OP_LT,
@@ -46,16 +48,17 @@ struct filter_op {
 };
 
 static struct filter_op filter_ops[] = {
-        { OP_OR, "||", 1 },
-        { OP_AND, "&&", 2 },
-        { OP_NE, "!=", 4 },
-        { OP_EQ, "==", 4 },
-        { OP_LT, "<", 5 },
-        { OP_LE, "<=", 5 },
-        { OP_GT, ">", 5 },
-        { OP_GE, ">=", 5 },
-        { OP_NONE, "OP_NONE", 0 },
-        { OP_OPEN_PAREN, "(", 0 },
+        { OP_OR,        "||",           1 },
+        { OP_AND,       "&&",           2 },
+        { OP_GLOB,      "~",            4 },
+        { OP_NE,        "!=",           4 },
+        { OP_EQ,        "==",           4 },
+        { OP_LT,        "<",            5 },
+        { OP_LE,        "<=",           5 },
+        { OP_GT,        ">",            5 },
+        { OP_GE,        ">=",           5 },
+        { OP_NONE,      "OP_NONE",      0 },
+        { OP_OPEN_PAREN, "(",           0 },
 };
 
 enum {
@@ -329,22 +332,18 @@ enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not)
         return type;
 }
 
-static int filter_build_regex(struct filter_pred *pred)
+static void filter_build_regex(struct filter_pred *pred)
 {
         struct regex *r = &pred->regex;
-        char *search, *dup;
-        enum regex_type type;
-        int not;
-
-        type = filter_parse_regex(r->pattern, r->len, &search, &not);
-        dup = kstrdup(search, GFP_KERNEL);
-        if (!dup)
-                return -ENOMEM;
-
-        strcpy(r->pattern, dup);
-        kfree(dup);
-
-        r->len = strlen(r->pattern);
+        char *search;
+        enum regex_type type = MATCH_FULL;
+        int not = 0;
+
+        if (pred->op == OP_GLOB) {
+                type = filter_parse_regex(r->pattern, r->len, &search, &not);
+                r->len = strlen(search);
+                memmove(r->pattern, search, r->len+1);
+        }
 
         switch (type) {
         case MATCH_FULL:
@@ -362,14 +361,11 @@ static int filter_build_regex(struct filter_pred *pred)
         }
 
         pred->not ^= not;
-
-        return 0;
 }
 
 /* return 1 if event matches, 0 otherwise (discard) */
-int filter_match_preds(struct ftrace_event_call *call, void *rec)
+int filter_match_preds(struct event_filter *filter, void *rec)
 {
-        struct event_filter *filter = call->filter;
         int match, top = 0, val1 = 0, val2 = 0;
         int stack[MAX_FILTER_PRED];
         struct filter_pred *pred;
@@ -542,9 +538,8 @@ static void filter_disable_preds(struct ftrace_event_call *call)
                 filter->preds[i]->fn = filter_pred_none;
 }
 
-void destroy_preds(struct ftrace_event_call *call)
+static void __free_preds(struct event_filter *filter)
 {
-        struct event_filter *filter = call->filter;
         int i;
 
         if (!filter)
@@ -557,21 +552,24 @@ void destroy_preds(struct ftrace_event_call *call)
         kfree(filter->preds);
         kfree(filter->filter_string);
         kfree(filter);
+}
+
+void destroy_preds(struct ftrace_event_call *call)
+{
+        __free_preds(call->filter);
         call->filter = NULL;
+        call->filter_active = 0;
 }
 
-static int init_preds(struct ftrace_event_call *call)
+static struct event_filter *__alloc_preds(void)
 {
         struct event_filter *filter;
         struct filter_pred *pred;
         int i;
 
-        if (call->filter)
-                return 0;
-
-        filter = call->filter = kzalloc(sizeof(*filter), GFP_KERNEL);
-        if (!call->filter)
-                return -ENOMEM;
+        filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+        if (!filter)
+                return ERR_PTR(-ENOMEM);
 
         filter->n_preds = 0;
 
@@ -587,12 +585,24 @@ static int init_preds(struct ftrace_event_call *call)
                 filter->preds[i] = pred;
         }
 
-        return 0;
+        return filter;
 
 oom:
-        destroy_preds(call);
+        __free_preds(filter);
+        return ERR_PTR(-ENOMEM);
+}
+
+static int init_preds(struct ftrace_event_call *call)
+{
+        if (call->filter)
+                return 0;
 
-        return -ENOMEM;
+        call->filter_active = 0;
+        call->filter = __alloc_preds();
+        if (IS_ERR(call->filter))
+                return PTR_ERR(call->filter);
+
+        return 0;
 }
 
 static int init_subsystem_preds(struct event_subsystem *system)
@@ -615,14 +625,7 @@ static int init_subsystem_preds(struct event_subsystem *system)
         return 0;
 }
 
-enum {
-        FILTER_DISABLE_ALL,
-        FILTER_INIT_NO_RESET,
-        FILTER_SKIP_NO_RESET,
-};
-
-static void filter_free_subsystem_preds(struct event_subsystem *system,
-                                        int flag)
+static void filter_free_subsystem_preds(struct event_subsystem *system)
 {
         struct ftrace_event_call *call;
 
@@ -633,14 +636,6 @@ static void filter_free_subsystem_preds(struct event_subsystem *system,
                 if (strcmp(call->system, system->name) != 0)
                         continue;
 
-                if (flag == FILTER_INIT_NO_RESET) {
-                        call->filter->no_reset = false;
-                        continue;
-                }
-
-                if (flag == FILTER_SKIP_NO_RESET && call->filter->no_reset)
-                        continue;
-
                 filter_disable_preds(call);
                 remove_filter_string(call->filter);
         }
@@ -648,10 +643,10 @@ static void filter_free_subsystem_preds(struct event_subsystem *system,
 
 static int filter_add_pred_fn(struct filter_parse_state *ps,
                               struct ftrace_event_call *call,
+                              struct event_filter *filter,
                               struct filter_pred *pred,
                               filter_pred_fn_t fn)
 {
-        struct event_filter *filter = call->filter;
         int idx, err;
 
         if (filter->n_preds == MAX_FILTER_PRED) {
@@ -666,7 +661,6 @@ static int filter_add_pred_fn(struct filter_parse_state *ps,
                 return err;
 
         filter->n_preds++;
-        call->filter_active = 1;
 
         return 0;
 }
@@ -691,7 +685,10 @@ static bool is_string_field(struct ftrace_event_field *field)
 
 static int is_legal_op(struct ftrace_event_field *field, int op)
 {
-        if (is_string_field(field) && (op != OP_EQ && op != OP_NE))
+        if (is_string_field(field) &&
+            (op != OP_EQ && op != OP_NE && op != OP_GLOB))
+                return 0;
+        if (!is_string_field(field) && op == OP_GLOB)
                 return 0;
 
         return 1;
@@ -742,6 +739,7 @@ static filter_pred_fn_t select_comparison_fn(int op, int field_size,
 
 static int filter_add_pred(struct filter_parse_state *ps,
                            struct ftrace_event_call *call,
+                           struct event_filter *filter,
                            struct filter_pred *pred,
                            bool dry_run)
 {
@@ -776,15 +774,13 @@ static int filter_add_pred(struct filter_parse_state *ps,
         }
 
         if (is_string_field(field)) {
-                ret = filter_build_regex(pred);
-                if (ret)
-                        return ret;
+                filter_build_regex(pred);
 
                 if (field->filter_type == FILTER_STATIC_STRING) {
                         fn = filter_pred_string;
                         pred->regex.field_len = field->size;
                 } else if (field->filter_type == FILTER_DYN_STRING)
-                                fn = filter_pred_strloc;
+                        fn = filter_pred_strloc;
                 else {
                         fn = filter_pred_pchar;
                         pred->regex.field_len = strlen(pred->regex.pattern);
@@ -813,45 +809,7 @@ static int filter_add_pred(struct filter_parse_state *ps,
 
 add_pred_fn:
         if (!dry_run)
-                return filter_add_pred_fn(ps, call, pred, fn);
-        return 0;
-}
-
-static int filter_add_subsystem_pred(struct filter_parse_state *ps,
-                                     struct event_subsystem *system,
-                                     struct filter_pred *pred,
-                                     char *filter_string,
-                                     bool dry_run)
-{
-        struct ftrace_event_call *call;
-        int err = 0;
-        bool fail = true;
-
-        list_for_each_entry(call, &ftrace_events, list) {
-
-                if (!call->define_fields)
-                        continue;
-
-                if (strcmp(call->system, system->name))
-                        continue;
-
-                if (call->filter->no_reset)
-                        continue;
-
-                err = filter_add_pred(ps, call, pred, dry_run);
-                if (err)
-                        call->filter->no_reset = true;
-                else
-                        fail = false;
-
-                if (!dry_run)
-                        replace_filter_string(call->filter, filter_string);
-        }
-
-        if (fail) {
-                parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
-                return err;
-        }
+                return filter_add_pred_fn(ps, call, filter, pred, fn);
         return 0;
 }
 
@@ -1209,8 +1167,8 @@ static int check_preds(struct filter_parse_state *ps)
         return 0;
 }
 
-static int replace_preds(struct event_subsystem *system,
-                         struct ftrace_event_call *call,
+static int replace_preds(struct ftrace_event_call *call,
+                         struct event_filter *filter,
                          struct filter_parse_state *ps,
                          char *filter_string,
                          bool dry_run)
@@ -1257,11 +1215,7 @@ static int replace_preds(struct event_subsystem *system,
 add_pred:
                 if (!pred)
                         return -ENOMEM;
-                if (call)
-                        err = filter_add_pred(ps, call, pred, false);
-                else
-                        err = filter_add_subsystem_pred(ps, system, pred,
-                                                filter_string, dry_run);
+                err = filter_add_pred(ps, call, filter, pred, dry_run);
                 filter_free_pred(pred);
                 if (err)
                         return err;
@@ -1272,10 +1226,50 @@ add_pred:
         return 0;
 }
 
-int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
+static int replace_system_preds(struct event_subsystem *system,
+                                struct filter_parse_state *ps,
+                                char *filter_string)
 {
+        struct ftrace_event_call *call;
+        bool fail = true;
         int err;
 
+        list_for_each_entry(call, &ftrace_events, list) {
+                struct event_filter *filter = call->filter;
+
+                if (!call->define_fields)
+                        continue;
+
+                if (strcmp(call->system, system->name) != 0)
+                        continue;
+
+                /* try to see if the filter can be applied */
+                err = replace_preds(call, filter, ps, filter_string, true);
+                if (err)
+                        continue;
+
+                /* really apply the filter */
+                filter_disable_preds(call);
+                err = replace_preds(call, filter, ps, filter_string, false);
+                if (err)
+                        filter_disable_preds(call);
+                else {
+                        call->filter_active = 1;
+                        replace_filter_string(filter, filter_string);
+                }
+                fail = false;
+        }
+
+        if (fail) {
+                parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+                return -EINVAL;
+        }
+        return 0;
+}
+
+int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
+{
+        int err;
         struct filter_parse_state *ps;
 
         mutex_lock(&event_mutex);
@@ -1287,8 +1281,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
         if (!strcmp(strstrip(filter_string), "0")) {
                 filter_disable_preds(call);
                 remove_filter_string(call->filter);
-                mutex_unlock(&event_mutex);
-                return 0;
+                goto out_unlock;
         }
 
         err = -ENOMEM;
@@ -1306,10 +1299,11 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
                 goto out;
         }
 
-        err = replace_preds(NULL, call, ps, filter_string, false);
+        err = replace_preds(call, call->filter, ps, filter_string, false);
         if (err)
                 append_filter_err(ps, call->filter);
-
+        else
+                call->filter_active = 1;
 out:
         filter_opstack_clear(ps);
         postfix_clear(ps);
@@ -1324,7 +1318,6 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
                                  char *filter_string)
 {
         int err;
-
         struct filter_parse_state *ps;
 
         mutex_lock(&event_mutex);
@@ -1334,10 +1327,9 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
                 goto out_unlock;
 
         if (!strcmp(strstrip(filter_string), "0")) {
-                filter_free_subsystem_preds(system, FILTER_DISABLE_ALL);
+                filter_free_subsystem_preds(system);
                 remove_filter_string(system->filter);
-                mutex_unlock(&event_mutex);
-                return 0;
+                goto out_unlock;
         }
 
         err = -ENOMEM;
@@ -1354,31 +1346,87 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
                 goto out;
         }
 
-        filter_free_subsystem_preds(system, FILTER_INIT_NO_RESET);
-
-        /* try to see the filter can be applied to which events */
-        err = replace_preds(system, NULL, ps, filter_string, true);
-        if (err) {
+        err = replace_system_preds(system, ps, filter_string);
+        if (err)
                 append_filter_err(ps, system->filter);
-                goto out;
+
+out:
+        filter_opstack_clear(ps);
+        postfix_clear(ps);
+        kfree(ps);
+out_unlock:
+        mutex_unlock(&event_mutex);
+
+        return err;
+}
+
+#ifdef CONFIG_EVENT_PROFILE
+
+void ftrace_profile_free_filter(struct perf_event *event)
+{
+        struct event_filter *filter = event->filter;
+
+        event->filter = NULL;
+        __free_preds(filter);
+}
+
+int ftrace_profile_set_filter(struct perf_event *event, int event_id,
+                              char *filter_str)
+{
+        int err;
+        struct event_filter *filter;
+        struct filter_parse_state *ps;
+        struct ftrace_event_call *call = NULL;
+
+        mutex_lock(&event_mutex);
+
+        list_for_each_entry(call, &ftrace_events, list) {
+                if (call->id == event_id)
+                        break;
         }
 
-        filter_free_subsystem_preds(system, FILTER_SKIP_NO_RESET);
+        err = -EINVAL;
+        if (!call)
+                goto out_unlock;
 
-        /* really apply the filter to the events */
-        err = replace_preds(system, NULL, ps, filter_string, false);
-        if (err) {
-                append_filter_err(ps, system->filter);
-                filter_free_subsystem_preds(system, 2);
+        err = -EEXIST;
+        if (event->filter)
+                goto out_unlock;
+
+        filter = __alloc_preds();
+        if (IS_ERR(filter)) {
+                err = PTR_ERR(filter);
+                goto out_unlock;
         }
 
-out:
+        err = -ENOMEM;
+        ps = kzalloc(sizeof(*ps), GFP_KERNEL);
+        if (!ps)
+                goto free_preds;
+
+        parse_init(ps, filter_ops, filter_str);
+        err = filter_parse(ps);
+        if (err)
+                goto free_ps;
+
+        err = replace_preds(call, filter, ps, filter_str, false);
+        if (!err)
+                event->filter = filter;
+
+free_ps:
         filter_opstack_clear(ps);
         postfix_clear(ps);
         kfree(ps);
+
+free_preds:
+        if (err)
+                __free_preds(filter);
+
 out_unlock:
         mutex_unlock(&event_mutex);
 
         return err;
 }
 
+#endif /* CONFIG_EVENT_PROFILE */
+
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index c74848ddb85a..dff8c84ddf17 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -66,44 +66,47 @@ static void __always_unused ____ftrace_check_##name(void)	\
 #undef __field
 #define __field(type, item)                                             \
         ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"      \
-                               "offset:%zu;\tsize:%zu;\n",              \
+                               "offset:%zu;\tsize:%zu;\tsigned:%u;\n",  \
                                offsetof(typeof(field), item),           \
-                               sizeof(field.item));                     \
+                               sizeof(field.item), is_signed_type(type)); \
         if (!ret)                                                       \
                 return 0;
 
 #undef __field_desc
 #define __field_desc(type, container, item)                             \
         ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"      \
-                               "offset:%zu;\tsize:%zu;\n",              \
+                               "offset:%zu;\tsize:%zu;\tsigned:%u;\n",  \
                                offsetof(typeof(field), container.item), \
-                               sizeof(field.container.item));           \
+                               sizeof(field.container.item),            \
+                               is_signed_type(type));                   \
         if (!ret)                                                       \
                 return 0;
 
 #undef __array
 #define __array(type, item, len)                                        \
         ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
-                               "offset:%zu;\tsize:%zu;\n",              \
-                               offsetof(typeof(field), item),   \
-                               sizeof(field.item));             \
+                               "offset:%zu;\tsize:%zu;\tsigned:%u;\n",  \
+                               offsetof(typeof(field), item),           \
+                               sizeof(field.item), is_signed_type(type)); \
         if (!ret)                                                       \
                 return 0;
 
 #undef __array_desc
 #define __array_desc(type, container, item, len)                        \
         ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
-                               "offset:%zu;\tsize:%zu;\n",              \
+                               "offset:%zu;\tsize:%zu;\tsigned:%u;\n",  \
                                offsetof(typeof(field), container.item), \
-                               sizeof(field.container.item));           \
+                               sizeof(field.container.item),            \
+                               is_signed_type(type));                   \
         if (!ret)                                                       \
                 return 0;
 
 #undef __dynamic_array
 #define __dynamic_array(type, item)                                     \
         ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"      \
-                               "offset:%zu;\tsize:0;\n",                \
-                               offsetof(typeof(field), item));          \
+                               "offset:%zu;\tsize:0;\tsigned:%u;\n",    \
+                               offsetof(typeof(field), item),           \
+                               is_signed_type(type));                   \
         if (!ret)                                                       \
                 return 0;
 
@@ -131,7 +134,6 @@ ftrace_format_##name(struct ftrace_event_call *unused,			\
 
 #include "trace_entries.h"
 
-
 #undef __field
 #define __field(type, item)                                             \
         ret = trace_define_field(event_call, #type, #item,              \
@@ -193,6 +195,11 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 
 #include "trace_entries.h"
 
+static int ftrace_raw_init_event(struct ftrace_event_call *call)
+{
+        INIT_LIST_HEAD(&call->fields);
+        return 0;
+}
 
 #undef __field
 #define __field(type, item)
@@ -211,7 +218,6 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(call, struct_name, type, tstruct, print)           \
-static int ftrace_raw_init_event_##call(void);                          \
                                                                         \
 struct ftrace_event_call __used                                         \
 __attribute__((__aligned__(4)))                                         \
@@ -219,14 +225,9 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
         .name                   = #call,                                \
         .id                     = type,                                 \
         .system                 = __stringify(TRACE_SYSTEM),            \
-        .raw_init               = ftrace_raw_init_event_##call,         \
+        .raw_init               = ftrace_raw_init_event,                \
         .show_format            = ftrace_format_##call,                 \
         .define_fields          = ftrace_define_fields_##call,          \
 };                                                                      \
-static int ftrace_raw_init_event_##call(void)                           \
-{                                                                       \
-        INIT_LIST_HEAD(&event_##call.fields);                           \
-        return 0;                                                       \
-}                                                                       \
 
 #include "trace_entries.h"
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
new file mode 100644
index 000000000000..aff5f80b59b8
--- /dev/null
+++ b/kernel/trace/trace_kprobe.c
@@ -0,0 +1,1523 @@
+/*
+ * Kprobes-based tracing events
+ *
+ * Created by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/kprobes.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/debugfs.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/ptrace.h>
+#include <linux/perf_event.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+#define MAX_TRACE_ARGS 128
+#define MAX_ARGSTR_LEN 63
+#define MAX_EVENT_NAME_LEN 64
+#define KPROBE_EVENT_SYSTEM "kprobes"
+
+/* Reserved field names */
+#define FIELD_STRING_IP "__probe_ip"
+#define FIELD_STRING_NARGS "__probe_nargs"
+#define FIELD_STRING_RETIP "__probe_ret_ip"
+#define FIELD_STRING_FUNC "__probe_func"
+
+const char *reserved_field_names[] = {
+        "common_type",
+        "common_flags",
+        "common_preempt_count",
+        "common_pid",
+        "common_tgid",
+        "common_lock_depth",
+        FIELD_STRING_IP,
+        FIELD_STRING_NARGS,
+        FIELD_STRING_RETIP,
+        FIELD_STRING_FUNC,
+};
+
+struct fetch_func {
+        unsigned long (*func)(struct pt_regs *, void *);
+        void *data;
+};
+
+static __kprobes unsigned long call_fetch(struct fetch_func *f,
+                                          struct pt_regs *regs)
+{
+        return f->func(regs, f->data);
+}
+
+/* fetch handlers */
+static __kprobes unsigned long fetch_register(struct pt_regs *regs,
+                                              void *offset)
+{
+        return regs_get_register(regs, (unsigned int)((unsigned long)offset));
+}
+
+static __kprobes unsigned long fetch_stack(struct pt_regs *regs,
+                                           void *num)
+{
+        return regs_get_kernel_stack_nth(regs,
+                                         (unsigned int)((unsigned long)num));
+}
+
+static __kprobes unsigned long fetch_memory(struct pt_regs *regs, void *addr)
+{
+        unsigned long retval;
+
+        if (probe_kernel_address(addr, retval))
+                return 0;
+        return retval;
+}
+
+static __kprobes unsigned long fetch_argument(struct pt_regs *regs, void *num)
+{
+        return regs_get_argument_nth(regs, (unsigned int)((unsigned long)num));
+}
+
+static __kprobes unsigned long fetch_retvalue(struct pt_regs *regs,
+                                              void *dummy)
+{
+        return regs_return_value(regs);
+}
+
+static __kprobes unsigned long fetch_stack_address(struct pt_regs *regs,
+                                                   void *dummy)
+{
+        return kernel_stack_pointer(regs);
+}
+
+/* Memory fetching by symbol */
+struct symbol_cache {
+        char *symbol;
+        long offset;
+        unsigned long addr;
+};
+
+static unsigned long update_symbol_cache(struct symbol_cache *sc)
+{
+        sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol);
+        if (sc->addr)
+                sc->addr += sc->offset;
+        return sc->addr;
+}
+
+static void free_symbol_cache(struct symbol_cache *sc)
+{
+        kfree(sc->symbol);
+        kfree(sc);
+}
+
+static struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
+{
+        struct symbol_cache *sc;
+
+        if (!sym || strlen(sym) == 0)
+                return NULL;
+        sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL);
+        if (!sc)
+                return NULL;
+
+        sc->symbol = kstrdup(sym, GFP_KERNEL);
+        if (!sc->symbol) {
+                kfree(sc);
+                return NULL;
+        }
+        sc->offset = offset;
+
+        update_symbol_cache(sc);
+        return sc;
+}
+
+static __kprobes unsigned long fetch_symbol(struct pt_regs *regs, void *data)
+{
+        struct symbol_cache *sc = data;
+
+        if (sc->addr)
+                return fetch_memory(regs, (void *)sc->addr);
+        else
+                return 0;
+}
+
+/* Special indirect memory access interface */
+struct indirect_fetch_data {
+        struct fetch_func orig;
+        long offset;
+};
+
+static __kprobes unsigned long fetch_indirect(struct pt_regs *regs, void *data)
+{
+        struct indirect_fetch_data *ind = data;
+        unsigned long addr;
+
+        addr = call_fetch(&ind->orig, regs);
+        if (addr) {
+                addr += ind->offset;
+                return fetch_memory(regs, (void *)addr);
+        } else
+                return 0;
+}
+
+static __kprobes void free_indirect_fetch_data(struct indirect_fetch_data *data)
+{
+        if (data->orig.func == fetch_indirect)
+                free_indirect_fetch_data(data->orig.data);
+        else if (data->orig.func == fetch_symbol)
+                free_symbol_cache(data->orig.data);
+        kfree(data);
+}
+
+/**
+ * Kprobe event core functions
+ */
+
+struct probe_arg {
+        struct fetch_func       fetch;
+        const char              *name;
+};
+
+/* Flags for trace_probe */
+#define TP_FLAG_TRACE   1
+#define TP_FLAG_PROFILE 2
+
+struct trace_probe {
+        struct list_head        list;
+        struct kretprobe        rp;     /* Use rp.kp for kprobe use */
+        unsigned long           nhit;
+        unsigned int            flags;  /* For TP_FLAG_* */
+        const char              *symbol;        /* symbol name */
+        struct ftrace_event_call        call;
+        struct trace_event              event;
+        unsigned int            nr_args;
+        struct probe_arg        args[];
+};
+
+#define SIZEOF_TRACE_PROBE(n)                   \
+        (offsetof(struct trace_probe, args) +   \
+        (sizeof(struct probe_arg) * (n)))
+
+static __kprobes int probe_is_return(struct trace_probe *tp)
+{
+        return tp->rp.handler != NULL;
+}
+
+static __kprobes const char *probe_symbol(struct trace_probe *tp)
+{
+        return tp->symbol ? tp->symbol : "unknown";
+}
+
+static int probe_arg_string(char *buf, size_t n, struct fetch_func *ff)
+{
+        int ret = -EINVAL;
+
+        if (ff->func == fetch_argument)
+                ret = snprintf(buf, n, "$arg%lu", (unsigned long)ff->data);
+        else if (ff->func == fetch_register) {
+                const char *name;
+                name = regs_query_register_name((unsigned int)((long)ff->data));
+                ret = snprintf(buf, n, "%%%s", name);
+        } else if (ff->func == fetch_stack)
+                ret = snprintf(buf, n, "$stack%lu", (unsigned long)ff->data);
+        else if (ff->func == fetch_memory)
+                ret = snprintf(buf, n, "@0x%p", ff->data);
+        else if (ff->func == fetch_symbol) {
+                struct symbol_cache *sc = ff->data;
+                if (sc->offset)
+                        ret = snprintf(buf, n, "@%s%+ld", sc->symbol,
+                                        sc->offset);
+                else
+                        ret = snprintf(buf, n, "@%s", sc->symbol);
+        } else if (ff->func == fetch_retvalue)
+                ret = snprintf(buf, n, "$retval");
+        else if (ff->func == fetch_stack_address)
+                ret = snprintf(buf, n, "$stack");
+        else if (ff->func == fetch_indirect) {
+                struct indirect_fetch_data *id = ff->data;
+                size_t l = 0;
+                ret = snprintf(buf, n, "%+ld(", id->offset);
+                if (ret >= n)
+                        goto end;
+                l += ret;
+                ret = probe_arg_string(buf + l, n - l, &id->orig);
+                if (ret < 0)
+                        goto end;
+                l += ret;
+                ret = snprintf(buf + l, n - l, ")");
+                ret += l;
+        }
+end:
+        if (ret >= n)
+                return -ENOSPC;
+        return ret;
+}
+
+static int register_probe_event(struct trace_probe *tp);
+static void unregister_probe_event(struct trace_probe *tp);
+
+static DEFINE_MUTEX(probe_lock);
+static LIST_HEAD(probe_list);
+
+static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
+static int kretprobe_dispatcher(struct kretprobe_instance *ri,
+                                struct pt_regs *regs);
+
+/*
+ * Allocate new trace_probe and initialize it (including kprobes).
+ */
+static struct trace_probe *alloc_trace_probe(const char *group,
+                                             const char *event,
+                                             void *addr,
+                                             const char *symbol,
+                                             unsigned long offs,
+                                             int nargs, int is_return)
+{
+        struct trace_probe *tp;
+
+        tp = kzalloc(SIZEOF_TRACE_PROBE(nargs), GFP_KERNEL);
+        if (!tp)
+                return ERR_PTR(-ENOMEM);
+
+        if (symbol) {
+                tp->symbol = kstrdup(symbol, GFP_KERNEL);
+                if (!tp->symbol)
+                        goto error;
+                tp->rp.kp.symbol_name = tp->symbol;
+                tp->rp.kp.offset = offs;
+        } else
+                tp->rp.kp.addr = addr;
+
+        if (is_return)
+                tp->rp.handler = kretprobe_dispatcher;
+        else
+                tp->rp.kp.pre_handler = kprobe_dispatcher;
+
+        if (!event)
+                goto error;
+        tp->call.name = kstrdup(event, GFP_KERNEL);
+        if (!tp->call.name)
+                goto error;
+
+        if (!group)
+                goto error;
+        tp->call.system = kstrdup(group, GFP_KERNEL);
+        if (!tp->call.system)
+                goto error;
+
+        INIT_LIST_HEAD(&tp->list);
+        return tp;
+error:
+        kfree(tp->call.name);
+        kfree(tp->symbol);
+        kfree(tp);
+        return ERR_PTR(-ENOMEM);
+}
+
+static void free_probe_arg(struct probe_arg *arg)
+{
+        if (arg->fetch.func == fetch_symbol)
+                free_symbol_cache(arg->fetch.data);
+        else if (arg->fetch.func == fetch_indirect)
+                free_indirect_fetch_data(arg->fetch.data);
+        kfree(arg->name);
+}
+
+static void free_trace_probe(struct trace_probe *tp)
+{
+        int i;
+
+        for (i = 0; i < tp->nr_args; i++)
+                free_probe_arg(&tp->args[i]);
+
+        kfree(tp->call.system);
+        kfree(tp->call.name);
+        kfree(tp->symbol);
+        kfree(tp);
+}
+
+static struct trace_probe *find_probe_event(const char *event,
+                                            const char *group)
+{
+        struct trace_probe *tp;
+
+        list_for_each_entry(tp, &probe_list, list)
+                if (strcmp(tp->call.name, event) == 0 &&
+                    strcmp(tp->call.system, group) == 0)
+                        return tp;
+        return NULL;
+}
+
+/* Unregister a trace_probe and probe_event: call with locking probe_lock */
+static void unregister_trace_probe(struct trace_probe *tp)
+{
+        if (probe_is_return(tp))
+                unregister_kretprobe(&tp->rp);
+        else
+                unregister_kprobe(&tp->rp.kp);
+        list_del(&tp->list);
+        unregister_probe_event(tp);
+}
+
+/* Register a trace_probe and probe_event */
+static int register_trace_probe(struct trace_probe *tp)
+{
+        struct trace_probe *old_tp;
+        int ret;
+
+        mutex_lock(&probe_lock);
+
+        /* register as an event */
+        old_tp = find_probe_event(tp->call.name, tp->call.system);
+        if (old_tp) {
+                /* delete old event */
+                unregister_trace_probe(old_tp);
+                free_trace_probe(old_tp);
+        }
+        ret = register_probe_event(tp);
+        if (ret) {
+                pr_warning("Faild to register probe event(%d)\n", ret);
+                goto end;
+        }
+
+        tp->rp.kp.flags |= KPROBE_FLAG_DISABLED;
+        if (probe_is_return(tp))
+                ret = register_kretprobe(&tp->rp);
+        else
+                ret = register_kprobe(&tp->rp.kp);
+
+        if (ret) {
+                pr_warning("Could not insert probe(%d)\n", ret);
+                if (ret == -EILSEQ) {
+                        pr_warning("Probing address(0x%p) is not an "
+                                   "instruction boundary.\n",
+                                   tp->rp.kp.addr);
+                        ret = -EINVAL;
+                }
+                unregister_probe_event(tp);
+        } else
+                list_add_tail(&tp->list, &probe_list);
+end:
+        mutex_unlock(&probe_lock);
+        return ret;
+}
+
+/* Split symbol and offset. */
+static int split_symbol_offset(char *symbol, unsigned long *offset)
+{
+        char *tmp;
+        int ret;
+
+        if (!offset)
+                return -EINVAL;
+
+        tmp = strchr(symbol, '+');
+        if (tmp) {
+                /* skip sign because strict_strtol doesn't accept '+' */
+                ret = strict_strtoul(tmp + 1, 0, offset);
+                if (ret)
+                        return ret;
+                *tmp = '\0';
+        } else
+                *offset = 0;
+        return 0;
+}
+
+#define PARAM_MAX_ARGS 16
+#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
+
+static int parse_probe_vars(char *arg, struct fetch_func *ff, int is_return)
+{
+        int ret = 0;
+        unsigned long param;
+
+        if (strcmp(arg, "retval") == 0) {
+                if (is_return) {
+                        ff->func = fetch_retvalue;
+                        ff->data = NULL;
+                } else
+                        ret = -EINVAL;
+        } else if (strncmp(arg, "stack", 5) == 0) {
+                if (arg[5] == '\0') {
+                        ff->func = fetch_stack_address;
+                        ff->data = NULL;
+                } else if (isdigit(arg[5])) {
+                        ret = strict_strtoul(arg + 5, 10, &param);
+                        if (ret || param > PARAM_MAX_STACK)
+                                ret = -EINVAL;
+                        else {
+                                ff->func = fetch_stack;
+                                ff->data = (void *)param;
+                        }
+                } else
+                        ret = -EINVAL;
+        } else if (strncmp(arg, "arg", 3) == 0 && isdigit(arg[3])) {
+                ret = strict_strtoul(arg + 3, 10, &param);
+                if (ret || param > PARAM_MAX_ARGS)
+                        ret = -EINVAL;
+                else {
+                        ff->func = fetch_argument;
+                        ff->data = (void *)param;
+                }
+        } else
+                ret = -EINVAL;
+        return ret;
+}
+
+/* Recursive argument parser */
+static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+{
+        int ret = 0;
+        unsigned long param;
+        long offset;
+        char *tmp;
+
+        switch (arg[0]) {
+        case '$':
+                ret = parse_probe_vars(arg + 1, ff, is_return);
+                break;
+        case '%':       /* named register */
+                ret = regs_query_register_offset(arg + 1);
+                if (ret >= 0) {
+                        ff->func = fetch_register;
+                        ff->data = (void *)(unsigned long)ret;
+                        ret = 0;
+                }
+                break;
+        case '@':       /* memory or symbol */
+                if (isdigit(arg[1])) {
+                        ret = strict_strtoul(arg + 1, 0, &param);
+                        if (ret)
+                                break;
+                        ff->func = fetch_memory;
+                        ff->data = (void *)param;
+                } else {
+                        ret = split_symbol_offset(arg + 1, &offset);
+                        if (ret)
+                                break;
+                        ff->data = alloc_symbol_cache(arg + 1, offset);
+                        if (ff->data)
+                                ff->func = fetch_symbol;
+                        else
+                                ret = -EINVAL;
+                }
+                break;
+        case '+':       /* indirect memory */
+        case '-':
+                tmp = strchr(arg, '(');
+                if (!tmp) {
+                        ret = -EINVAL;
+                        break;
+                }
+                *tmp = '\0';
+                ret = strict_strtol(arg + 1, 0, &offset);
+                if (ret)
+                        break;
+                if (arg[0] == '-')
+                        offset = -offset;
+                arg = tmp + 1;
+                tmp = strrchr(arg, ')');
+                if (tmp) {
+                        struct indirect_fetch_data *id;
+                        *tmp = '\0';
+                        id = kzalloc(sizeof(struct indirect_fetch_data),
+                                     GFP_KERNEL);
+                        if (!id)
+                                return -ENOMEM;
+                        id->offset = offset;
+                        ret = __parse_probe_arg(arg, &id->orig, is_return);
+                        if (ret)
+                                kfree(id);
+                        else {
+                                ff->func = fetch_indirect;
+                                ff->data = (void *)id;
+                        }
+                } else
+                        ret = -EINVAL;
+                break;
+        default:
+                /* TODO: support custom handler */
+                ret = -EINVAL;
+        }
+        return ret;
+}
+
+/* String length checking wrapper */
+static int parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+{
+        if (strlen(arg) > MAX_ARGSTR_LEN) {
+                pr_info("Argument is too long.: %s\n",  arg);
+                return -ENOSPC;
+        }
+        return __parse_probe_arg(arg, ff, is_return);
+}
+
+/* Return 1 if name is reserved or already used by another argument */
+static int conflict_field_name(const char *name,
+                               struct probe_arg *args, int narg)
+{
+        int i;
+        for (i = 0; i < ARRAY_SIZE(reserved_field_names); i++)
+                if (strcmp(reserved_field_names[i], name) == 0)
+                        return 1;
+        for (i = 0; i < narg; i++)
+                if (strcmp(args[i].name, name) == 0)
+                        return 1;
+        return 0;
+}
+
+static int create_trace_probe(int argc, char **argv)
+{
+        /*
+         * Argument syntax:
+         *  - Add kprobe: p[:[GRP/]EVENT] KSYM[+OFFS]|KADDR [FETCHARGS]
+         *  - Add kretprobe: r[:[GRP/]EVENT] KSYM[+0] [FETCHARGS]
+         * Fetch args:
+         *  $argN       : fetch Nth of function argument. (N:0-)
+         *  $retval     : fetch return value
+         *  $stack      : fetch stack address
+         *  $stackN     : fetch Nth of stack (N:0-)
+         *  @ADDR       : fetch memory at ADDR (ADDR should be in kernel)
+         *  @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol)
+         *  %REG        : fetch register REG
+         * Indirect memory fetch:
+         *  +|-offs(ARG) : fetch memory at ARG +|- offs address.
+         * Alias name of args:
+         *  NAME=FETCHARG : set NAME as alias of FETCHARG.
+         */
+        struct trace_probe *tp;
+        int i, ret = 0;
+        int is_return = 0;
+        char *symbol = NULL, *event = NULL, *arg = NULL, *group = NULL;
+        unsigned long offset = 0;
+        void *addr = NULL;
+        char buf[MAX_EVENT_NAME_LEN];
+
+        if (argc < 2) {
+                pr_info("Probe point is not specified.\n");
+                return -EINVAL;
+        }
+
+        if (argv[0][0] == 'p')
+                is_return = 0;
+        else if (argv[0][0] == 'r')
+                is_return = 1;
+        else {
+                pr_info("Probe definition must be started with 'p' or 'r'.\n");
+                return -EINVAL;
+        }
+
+        if (argv[0][1] == ':') {
+                event = &argv[0][2];
+                if (strchr(event, '/')) {
+                        group = event;
+                        event = strchr(group, '/') + 1;
+                        event[-1] = '\0';
+                        if (strlen(group) == 0) {
+                                pr_info("Group name is not specifiled\n");
+                                return -EINVAL;
+                        }
+                }
+                if (strlen(event) == 0) {
+                        pr_info("Event name is not specifiled\n");
+                        return -EINVAL;
+                }
+        }
+
+        if (isdigit(argv[1][0])) {
+                if (is_return) {
+                        pr_info("Return probe point must be a symbol.\n");
+                        return -EINVAL;
+                }
+                /* an address specified */
+                ret = strict_strtoul(&argv[0][2], 0, (unsigned long *)&addr);
+                if (ret) {
+                        pr_info("Failed to parse address.\n");
+                        return ret;
+                }
+        } else {
+                /* a symbol specified */
+                symbol = argv[1];
+                /* TODO: support .init module functions */
+                ret = split_symbol_offset(symbol, &offset);
+                if (ret) {
+                        pr_info("Failed to parse symbol.\n");
+                        return ret;
+                }
+                if (offset && is_return) {
+                        pr_info("Return probe must be used without offset.\n");
+                        return -EINVAL;
+                }
+        }
+        argc -= 2; argv += 2;
+
+        /* setup a probe */
+        if (!group)
+                group = KPROBE_EVENT_SYSTEM;
+        if (!event) {
+                /* Make a new event name */
+                if (symbol)
+                        snprintf(buf, MAX_EVENT_NAME_LEN, "%c@%s%+ld",
+                                 is_return ? 'r' : 'p', symbol, offset);
+                else
+                        snprintf(buf, MAX_EVENT_NAME_LEN, "%c@0x%p",
+                                 is_return ? 'r' : 'p', addr);
+                event = buf;
+        }
+        tp = alloc_trace_probe(group, event, addr, symbol, offset, argc,
+                               is_return);
+        if (IS_ERR(tp)) {
+                pr_info("Failed to allocate trace_probe.(%d)\n",
+                        (int)PTR_ERR(tp));
+                return PTR_ERR(tp);
+        }
+
+        /* parse arguments */
+        ret = 0;
+        for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+                /* Parse argument name */
+                arg = strchr(argv[i], '=');
+                if (arg)
+                        *arg++ = '\0';
+                else
+                        arg = argv[i];
+
+                if (conflict_field_name(argv[i], tp->args, i)) {
+                        pr_info("Argument%d name '%s' conflicts with "
+                                "another field.\n", i, argv[i]);
+                        ret = -EINVAL;
+                        goto error;
+                }
+
+                tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+                if (!tp->args[i].name) {
+                        pr_info("Failed to allocate argument%d name '%s'.\n",
+                                i, argv[i]);
+                        ret = -ENOMEM;
+                        goto error;
+                }
+
+                /* Parse fetch argument */
+                ret = parse_probe_arg(arg, &tp->args[i].fetch, is_return);
+                if (ret) {
+                        pr_info("Parse error at argument%d. (%d)\n", i, ret);
+                        kfree(tp->args[i].name);
+                        goto error;
+                }
+
+                tp->nr_args++;
+        }
+
+        ret = register_trace_probe(tp);
+        if (ret)
+                goto error;
+        return 0;
+
+error:
+        free_trace_probe(tp);
+        return ret;
+}
+
+static void cleanup_all_probes(void)
+{
+        struct trace_probe *tp;
+
+        mutex_lock(&probe_lock);
+        /* TODO: Use batch unregistration */
+        while (!list_empty(&probe_list)) {
+                tp = list_entry(probe_list.next, struct trace_probe, list);
+                unregister_trace_probe(tp);
+                free_trace_probe(tp);
+        }
+        mutex_unlock(&probe_lock);
+}
+
+
+/* Probes listing interfaces */
+static void *probes_seq_start(struct seq_file *m, loff_t *pos)
+{
+        mutex_lock(&probe_lock);
+        return seq_list_start(&probe_list, *pos);
+}
+
+static void *probes_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+        return seq_list_next(v, &probe_list, pos);
+}
+
+static void probes_seq_stop(struct seq_file *m, void *v)
+{
+        mutex_unlock(&probe_lock);
+}
+
+static int probes_seq_show(struct seq_file *m, void *v)
+{
+        struct trace_probe *tp = v;
+        int i, ret;
+        char buf[MAX_ARGSTR_LEN + 1];
+
+        seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
+        seq_printf(m, ":%s/%s", tp->call.system, tp->call.name);
+
+        if (!tp->symbol)
+                seq_printf(m, " 0x%p", tp->rp.kp.addr);
+        else if (tp->rp.kp.offset)
+                seq_printf(m, " %s+%u", probe_symbol(tp), tp->rp.kp.offset);
+        else
+                seq_printf(m, " %s", probe_symbol(tp));
+
+        for (i = 0; i < tp->nr_args; i++) {
+                ret = probe_arg_string(buf, MAX_ARGSTR_LEN, &tp->args[i].fetch);
+                if (ret < 0) {
+                        pr_warning("Argument%d decoding error(%d).\n", i, ret);
+                        return ret;
+                }
+                seq_printf(m, " %s=%s", tp->args[i].name, buf);
+        }
+        seq_printf(m, "\n");
+        return 0;
+}
+
+static const struct seq_operations probes_seq_op = {
+        .start  = probes_seq_start,
+        .next   = probes_seq_next,
+        .stop   = probes_seq_stop,
+        .show   = probes_seq_show
+};
+
+static int probes_open(struct inode *inode, struct file *file)
+{
+        if ((file->f_mode & FMODE_WRITE) &&
+            (file->f_flags & O_TRUNC))
+                cleanup_all_probes();
+
+        return seq_open(file, &probes_seq_op);
+}
+
+static int command_trace_probe(const char *buf)
+{
+        char **argv;
+        int argc = 0, ret = 0;
+
+        argv = argv_split(GFP_KERNEL, buf, &argc);
+        if (!argv)
+                return -ENOMEM;
+
+        if (argc)
+                ret = create_trace_probe(argc, argv);
+
+        argv_free(argv);
+        return ret;
+}
+
+#define WRITE_BUFSIZE 128
+
+static ssize_t probes_write(struct file *file, const char __user *buffer,
+                            size_t count, loff_t *ppos)
+{
+        char *kbuf, *tmp;
+        int ret;
+        size_t done;
+        size_t size;
+
+        kbuf = kmalloc(WRITE_BUFSIZE, GFP_KERNEL);
+        if (!kbuf)
+                return -ENOMEM;
+
+        ret = done = 0;
+        while (done < count) {
+                size = count - done;
+                if (size >= WRITE_BUFSIZE)
+                        size = WRITE_BUFSIZE - 1;
+                if (copy_from_user(kbuf, buffer + done, size)) {
+                        ret = -EFAULT;
+                        goto out;
+                }
+                kbuf[size] = '\0';
+                tmp = strchr(kbuf, '\n');
+                if (tmp) {
+                        *tmp = '\0';
+                        size = tmp - kbuf + 1;
+                } else if (done + size < count) {
+                        pr_warning("Line length is too long: "
+                                   "Should be less than %d.", WRITE_BUFSIZE);
+                        ret = -EINVAL;
+                        goto out;
+                }
+                done += size;
+                /* Remove comments */
+                tmp = strchr(kbuf, '#');
+                if (tmp)
+                        *tmp = '\0';
+
+                ret = command_trace_probe(kbuf);
+                if (ret)
+                        goto out;
+        }
+        ret = done;
+out:
+        kfree(kbuf);
+        return ret;
+}
+
+static const struct file_operations kprobe_events_ops = {
+        .owner          = THIS_MODULE,
+        .open           = probes_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = seq_release,
+        .write          = probes_write,
+};
+
+/* Probes profiling interfaces */
+static int probes_profile_seq_show(struct seq_file *m, void *v)
+{
+        struct trace_probe *tp = v;
+
+        seq_printf(m, "  %-44s %15lu %15lu\n", tp->call.name, tp->nhit,
+                   tp->rp.kp.nmissed);
+
+        return 0;
+}
+
+static const struct seq_operations profile_seq_op = {
+        .start  = probes_seq_start,
+        .next   = probes_seq_next,
+        .stop   = probes_seq_stop,
+        .show   = probes_profile_seq_show
+};
+
+static int profile_open(struct inode *inode, struct file *file)
+{
+        return seq_open(file, &profile_seq_op);
+}
+
+static const struct file_operations kprobe_profile_ops = {
+        .owner          = THIS_MODULE,
+        .open           = profile_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = seq_release,
+};
+
+/* Kprobe handler */
+static __kprobes int kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
+{
+        struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+        struct kprobe_trace_entry *entry;
+        struct ring_buffer_event *event;
+        struct ring_buffer *buffer;
+        int size, i, pc;
+        unsigned long irq_flags;
+        struct ftrace_event_call *call = &tp->call;
+
+        tp->nhit++;
+
+        local_save_flags(irq_flags);
+        pc = preempt_count();
+
+        size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+
+        event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
+                                                  irq_flags, pc);
+        if (!event)
+                return 0;
+
+        entry = ring_buffer_event_data(event);
+        entry->nargs = tp->nr_args;
+        entry->ip = (unsigned long)kp->addr;
+        for (i = 0; i < tp->nr_args; i++)
+                entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+
+        if (!filter_current_check_discard(buffer, call, entry, event))
+                trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
+        return 0;
+}
+
+/* Kretprobe handler */
+static __kprobes int kretprobe_trace_func(struct kretprobe_instance *ri,
+                                          struct pt_regs *regs)
+{
+        struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+        struct kretprobe_trace_entry *entry;
+        struct ring_buffer_event *event;
+        struct ring_buffer *buffer;
+        int size, i, pc;
+        unsigned long irq_flags;
+        struct ftrace_event_call *call = &tp->call;
+
+        local_save_flags(irq_flags);
+        pc = preempt_count();
+
+        size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+
+        event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
+                                                  irq_flags, pc);
+        if (!event)
+                return 0;
+
+        entry = ring_buffer_event_data(event);
+        entry->nargs = tp->nr_args;
+        entry->func = (unsigned long)tp->rp.kp.addr;
+        entry->ret_ip = (unsigned long)ri->ret_addr;
+        for (i = 0; i < tp->nr_args; i++)
+                entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+
+        if (!filter_current_check_discard(buffer, call, entry, event))
+                trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
+
+        return 0;
+}
+
+/* Event entry printers */
+enum print_line_t
+print_kprobe_event(struct trace_iterator *iter, int flags)
+{
+        struct kprobe_trace_entry *field;
+        struct trace_seq *s = &iter->seq;
+        struct trace_event *event;
+        struct trace_probe *tp;
+        int i;
+
+        field = (struct kprobe_trace_entry *)iter->ent;
+        event = ftrace_find_event(field->ent.type);
+        tp = container_of(event, struct trace_probe, event);
+
+        if (!trace_seq_printf(s, "%s: (", tp->call.name))
+                goto partial;
+
+        if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET))
+                goto partial;
+
+        if (!trace_seq_puts(s, ")"))
+                goto partial;
+
+        for (i = 0; i < field->nargs; i++)
+                if (!trace_seq_printf(s, " %s=%lx",
+                                      tp->args[i].name, field->args[i]))
+                        goto partial;
+
+        if (!trace_seq_puts(s, "\n"))
+                goto partial;
+
+        return TRACE_TYPE_HANDLED;
+partial:
+        return TRACE_TYPE_PARTIAL_LINE;
+}
+
+enum print_line_t
+print_kretprobe_event(struct trace_iterator *iter, int flags)
+{
+        struct kretprobe_trace_entry *field;
+        struct trace_seq *s = &iter->seq;
+        struct trace_event *event;
+        struct trace_probe *tp;
+        int i;
+
+        field = (struct kretprobe_trace_entry *)iter->ent;
+        event = ftrace_find_event(field->ent.type);
+        tp = container_of(event, struct trace_probe, event);
+
+        if (!trace_seq_printf(s, "%s: (", tp->call.name))
+                goto partial;
+
+        if (!seq_print_ip_sym(s, field->ret_ip, flags | TRACE_ITER_SYM_OFFSET))
+                goto partial;
+
+        if (!trace_seq_puts(s, " <- "))
+                goto partial;
+
+        if (!seq_print_ip_sym(s, field->func, flags & ~TRACE_ITER_SYM_OFFSET))
+                goto partial;
+
+        if (!trace_seq_puts(s, ")"))
+                goto partial;
+
+        for (i = 0; i < field->nargs; i++)
+                if (!trace_seq_printf(s, " %s=%lx",
+                                      tp->args[i].name, field->args[i]))
+                        goto partial;
+
+        if (!trace_seq_puts(s, "\n"))
+                goto partial;
+
+        return TRACE_TYPE_HANDLED;
+partial:
+        return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static int probe_event_enable(struct ftrace_event_call *call)
+{
+        struct trace_probe *tp = (struct trace_probe *)call->data;
+
+        tp->flags |= TP_FLAG_TRACE;
+        if (probe_is_return(tp))
+                return enable_kretprobe(&tp->rp);
+        else
+                return enable_kprobe(&tp->rp.kp);
+}
+
+static void probe_event_disable(struct ftrace_event_call *call)
+{
+        struct trace_probe *tp = (struct trace_probe *)call->data;
+
+        tp->flags &= ~TP_FLAG_TRACE;
+        if (!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE))) {
+                if (probe_is_return(tp))
+                        disable_kretprobe(&tp->rp);
+                else
+                        disable_kprobe(&tp->rp.kp);
+        }
+}
+
+static int probe_event_raw_init(struct ftrace_event_call *event_call)
+{
+        INIT_LIST_HEAD(&event_call->fields);
+
+        return 0;
+}
+
+#undef DEFINE_FIELD
+#define DEFINE_FIELD(type, item, name, is_signed)                       \
+        do {                                                            \
+                ret = trace_define_field(event_call, #type, name,       \
+                                         offsetof(typeof(field), item), \
+                                         sizeof(field.item), is_signed, \
+                                         FILTER_OTHER);                 \
+                if (ret)                                                \
+                        return ret;                                     \
+        } while (0)
+
+static int kprobe_event_define_fields(struct ftrace_event_call *event_call)
+{
+        int ret, i;
+        struct kprobe_trace_entry field;
+        struct trace_probe *tp = (struct trace_probe *)event_call->data;
+
+        ret = trace_define_common_fields(event_call);
+        if (!ret)
+                return ret;
+
+        DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
+        DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
+        /* Set argument names as fields */
+        for (i = 0; i < tp->nr_args; i++)
+                DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+        return 0;
+}
+
+static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
+{
+        int ret, i;
+        struct kretprobe_trace_entry field;
+        struct trace_probe *tp = (struct trace_probe *)event_call->data;
+
+        ret = trace_define_common_fields(event_call);
+        if (!ret)
+                return ret;
+
+        DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
+        DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
+        DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
+        /* Set argument names as fields */
+        for (i = 0; i < tp->nr_args; i++)
+                DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+        return 0;
+}
+
+static int __probe_event_show_format(struct trace_seq *s,
+                                     struct trace_probe *tp, const char *fmt,
+                                     const char *arg)
+{
+        int i;
+
+        /* Show format */
+        if (!trace_seq_printf(s, "\nprint fmt: \"%s", fmt))
+                return 0;
+
+        for (i = 0; i < tp->nr_args; i++)
+                if (!trace_seq_printf(s, " %s=%%lx", tp->args[i].name))
+                        return 0;
+
+        if (!trace_seq_printf(s, "\", %s", arg))
+                return 0;
+
+        for (i = 0; i < tp->nr_args; i++)
+                if (!trace_seq_printf(s, ", REC->%s", tp->args[i].name))
+                        return 0;
+
+        return trace_seq_puts(s, "\n");
+}
+
+#undef SHOW_FIELD
+#define SHOW_FIELD(type, item, name)                                    \
+        do {                                                            \
+                ret = trace_seq_printf(s, "\tfield: " #type " %s;\t"    \
+                                "offset:%u;\tsize:%u;\n", name,         \
+                                (unsigned int)offsetof(typeof(field), item),\
+                                (unsigned int)sizeof(type));            \
+                if (!ret)                                               \
+                        return 0;                                       \
+        } while (0)
+
+static int kprobe_event_show_format(struct ftrace_event_call *call,
+                                    struct trace_seq *s)
+{
+        struct kprobe_trace_entry field __attribute__((unused));
+        int ret, i;
+        struct trace_probe *tp = (struct trace_probe *)call->data;
+
+        SHOW_FIELD(unsigned long, ip, FIELD_STRING_IP);
+        SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
+
+        /* Show fields */
+        for (i = 0; i < tp->nr_args; i++)
+                SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
+        trace_seq_puts(s, "\n");
+
+        return __probe_event_show_format(s, tp, "(%lx)",
+                                         "REC->" FIELD_STRING_IP);
+}
+
+static int kretprobe_event_show_format(struct ftrace_event_call *call,
+                                       struct trace_seq *s)
+{
+        struct kretprobe_trace_entry field __attribute__((unused));
+        int ret, i;
+        struct trace_probe *tp = (struct trace_probe *)call->data;
+
+        SHOW_FIELD(unsigned long, func, FIELD_STRING_FUNC);
+        SHOW_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP);
+        SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
+
+        /* Show fields */
+        for (i = 0; i < tp->nr_args; i++)
+                SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
+        trace_seq_puts(s, "\n");
+
+        return __probe_event_show_format(s, tp, "(%lx <- %lx)",
+                                         "REC->" FIELD_STRING_FUNC
+                                         ", REC->" FIELD_STRING_RETIP);
+}
+
+#ifdef CONFIG_EVENT_PROFILE
+
+/* Kprobe profile handler */
+static __kprobes int kprobe_profile_func(struct kprobe *kp,
+                                         struct pt_regs *regs)
+{
+        struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+        struct ftrace_event_call *call = &tp->call;
+        struct kprobe_trace_entry *entry;
+        struct trace_entry *ent;
+        int size, __size, i, pc, __cpu;
+        unsigned long irq_flags;
+        char *trace_buf;
+        char *raw_data;
+        int rctx;
+
+        pc = preempt_count();
+        __size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+        size = ALIGN(__size + sizeof(u32), sizeof(u64));
+        size -= sizeof(u32);
+        if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+                     "profile buffer not large enough"))
+                return 0;
+
+        /*
+         * Protect the non nmi buffer
+         * This also protects the rcu read side
+         */
+        local_irq_save(irq_flags);
+
+        rctx = perf_swevent_get_recursion_context();
+        if (rctx < 0)
+                goto end_recursion;
+
+        __cpu = smp_processor_id();
+
+        if (in_nmi())
+                trace_buf = rcu_dereference(perf_trace_buf_nmi);
+        else
+                trace_buf = rcu_dereference(perf_trace_buf);
+
+        if (!trace_buf)
+                goto end;
+
+        raw_data = per_cpu_ptr(trace_buf, __cpu);
+
+        /* Zero dead bytes from alignment to avoid buffer leak to userspace */
+        *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+        entry = (struct kprobe_trace_entry *)raw_data;
+        ent = &entry->ent;
+
+        tracing_generic_entry_update(ent, irq_flags, pc);
+        ent->type = call->id;
+        entry->nargs = tp->nr_args;
+        entry->ip = (unsigned long)kp->addr;
+        for (i = 0; i < tp->nr_args; i++)
+                entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+        perf_tp_event(call->id, entry->ip, 1, entry, size);
+
+end:
+        perf_swevent_put_recursion_context(rctx);
+end_recursion:
+        local_irq_restore(irq_flags);
+
+        return 0;
+}
+
+/* Kretprobe profile handler */
+static __kprobes int kretprobe_profile_func(struct kretprobe_instance *ri,
+                                            struct pt_regs *regs)
+{
+        struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+        struct ftrace_event_call *call = &tp->call;
+        struct kretprobe_trace_entry *entry;
+        struct trace_entry *ent;
+        int size, __size, i, pc, __cpu;
+        unsigned long irq_flags;
+        char *trace_buf;
+        char *raw_data;
+        int rctx;
+
+        pc = preempt_count();
+        __size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+        size = ALIGN(__size + sizeof(u32), sizeof(u64));
+        size -= sizeof(u32);
+        if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+                     "profile buffer not large enough"))
+                return 0;
+
+        /*
+         * Protect the non nmi buffer
+         * This also protects the rcu read side
+         */
+        local_irq_save(irq_flags);
+
+        rctx = perf_swevent_get_recursion_context();
+        if (rctx < 0)
+                goto end_recursion;
+
+        __cpu = smp_processor_id();
+
+        if (in_nmi())
+                trace_buf = rcu_dereference(perf_trace_buf_nmi);
+        else
+                trace_buf = rcu_dereference(perf_trace_buf);
+
+        if (!trace_buf)
+                goto end;
+
+        raw_data = per_cpu_ptr(trace_buf, __cpu);
+
+        /* Zero dead bytes from alignment to avoid buffer leak to userspace */
+        *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+        entry = (struct kretprobe_trace_entry *)raw_data;
+        ent = &entry->ent;
+
+        tracing_generic_entry_update(ent, irq_flags, pc);
+        ent->type = call->id;
+        entry->nargs = tp->nr_args;
+        entry->func = (unsigned long)tp->rp.kp.addr;
+        entry->ret_ip = (unsigned long)ri->ret_addr;
+        for (i = 0; i < tp->nr_args; i++)
+                entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+        perf_tp_event(call->id, entry->ret_ip, 1, entry, size);
+
+end:
+        perf_swevent_put_recursion_context(rctx);
+end_recursion:
+        local_irq_restore(irq_flags);
+
+        return 0;
+}
+
+static int probe_profile_enable(struct ftrace_event_call *call)
+{
+        struct trace_probe *tp = (struct trace_probe *)call->data;
+
+        tp->flags |= TP_FLAG_PROFILE;
+
+        if (probe_is_return(tp))
+                return enable_kretprobe(&tp->rp);
+        else
+                return enable_kprobe(&tp->rp.kp);
+}
+
+static void probe_profile_disable(struct ftrace_event_call *call)
+{
+        struct trace_probe *tp = (struct trace_probe *)call->data;
+
+        tp->flags &= ~TP_FLAG_PROFILE;
+
+        if (!(tp->flags & TP_FLAG_TRACE)) {
+                if (probe_is_return(tp))
+                        disable_kretprobe(&tp->rp);
+                else
+                        disable_kprobe(&tp->rp.kp);
+        }
+}
+#endif  /* CONFIG_EVENT_PROFILE */
+
+
+static __kprobes
+int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
+{
+        struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+
+        if (tp->flags & TP_FLAG_TRACE)
+                kprobe_trace_func(kp, regs);
+#ifdef CONFIG_EVENT_PROFILE
+        if (tp->flags & TP_FLAG_PROFILE)
+                kprobe_profile_func(kp, regs);
+#endif  /* CONFIG_EVENT_PROFILE */
+        return 0;       /* We don't tweek kernel, so just return 0 */
+}
+
+static __kprobes
+int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
+{
+        struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+
+        if (tp->flags & TP_FLAG_TRACE)
+                kretprobe_trace_func(ri, regs);
+#ifdef CONFIG_EVENT_PROFILE
+        if (tp->flags & TP_FLAG_PROFILE)
+                kretprobe_profile_func(ri, regs);
+#endif  /* CONFIG_EVENT_PROFILE */
+        return 0;       /* We don't tweek kernel, so just return 0 */
+}
+
+static int register_probe_event(struct trace_probe *tp)
+{
+        struct ftrace_event_call *call = &tp->call;
+        int ret;
+
+        /* Initialize ftrace_event_call */
+        if (probe_is_return(tp)) {
+                tp->event.trace = print_kretprobe_event;
+                call->raw_init = probe_event_raw_init;
+                call->show_format = kretprobe_event_show_format;
+                call->define_fields = kretprobe_event_define_fields;
+        } else {
+                tp->event.trace = print_kprobe_event;
+                call->raw_init = probe_event_raw_init;
+                call->show_format = kprobe_event_show_format;
+                call->define_fields = kprobe_event_define_fields;
+        }
+        call->event = &tp->event;
+        call->id = register_ftrace_event(&tp->event);
+        if (!call->id)
+                return -ENODEV;
+        call->enabled = 0;
+        call->regfunc = probe_event_enable;
+        call->unregfunc = probe_event_disable;
+
+#ifdef CONFIG_EVENT_PROFILE
+        atomic_set(&call->profile_count, -1);
+        call->profile_enable = probe_profile_enable;
+        call->profile_disable = probe_profile_disable;
+#endif
+        call->data = tp;
+        ret = trace_add_event_call(call);
+        if (ret) {
+                pr_info("Failed to register kprobe event: %s\n", call->name);
+                unregister_ftrace_event(&tp->event);
+        }
+        return ret;
+}
+
+static void unregister_probe_event(struct trace_probe *tp)
+{
+        /* tp->event is unregistered in trace_remove_event_call() */
+        trace_remove_event_call(&tp->call);
+}
+
+/* Make a debugfs interface for controling probe points */
+static __init int init_kprobe_trace(void)
+{
+        struct dentry *d_tracer;
+        struct dentry *entry;
+
+        d_tracer = tracing_init_dentry();
+        if (!d_tracer)
+                return 0;
+
+        entry = debugfs_create_file("kprobe_events", 0644, d_tracer,
+                                    NULL, &kprobe_events_ops);
+
+        /* Event list interface */
+        if (!entry)
+                pr_warning("Could not create debugfs "
+                           "'kprobe_events' entry\n");
+
+        /* Profile interface */
+        entry = debugfs_create_file("kprobe_profile", 0444, d_tracer,
+                                    NULL, &kprobe_profile_ops);
+
+        if (!entry)
+                pr_warning("Could not create debugfs "
+                           "'kprobe_profile' entry\n");
+        return 0;
+}
+fs_initcall(init_kprobe_trace);
+
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+
+static int kprobe_trace_selftest_target(int a1, int a2, int a3,
+                                        int a4, int a5, int a6)
+{
+        return a1 + a2 + a3 + a4 + a5 + a6;
+}
+
+static __init int kprobe_trace_self_tests_init(void)
+{
+        int ret;
+        int (*target)(int, int, int, int, int, int);
+
+        target = kprobe_trace_selftest_target;
+
+        pr_info("Testing kprobe tracing: ");
+
+        ret = command_trace_probe("p:testprobe kprobe_trace_selftest_target "
+                                  "$arg1 $arg2 $arg3 $arg4 $stack $stack0");
+        if (WARN_ON_ONCE(ret))
+                pr_warning("error enabling function entry\n");
+
+        ret = command_trace_probe("r:testprobe2 kprobe_trace_selftest_target "
+                                  "$retval");
+        if (WARN_ON_ONCE(ret))
+                pr_warning("error enabling function return\n");
+
+        ret = target(1, 2, 3, 4, 5, 6);
+
+        cleanup_all_probes();
+
+        pr_cont("OK\n");
+        return 0;
+}
+
+late_initcall(kprobe_trace_self_tests_init);
+
+#endif
diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c
new file mode 100644
index 000000000000..ddfa0fd43bc0
--- /dev/null
+++ b/kernel/trace/trace_ksym.c
@@ -0,0 +1,550 @@
+/*
+ * trace_ksym.c - Kernel Symbol Tracer
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2009
+ */
+
+#include <linux/kallsyms.h>
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+
+#include "trace_output.h"
+#include "trace_stat.h"
+#include "trace.h"
+
+#include <linux/hw_breakpoint.h>
+#include <asm/hw_breakpoint.h>
+
+/*
+ * For now, let us restrict the no. of symbols traced simultaneously to number
+ * of available hardware breakpoint registers.
+ */
+#define KSYM_TRACER_MAX HBP_NUM
+
+#define KSYM_TRACER_OP_LEN 3 /* rw- */
+
+struct trace_ksym {
+        struct perf_event       **ksym_hbp;
+        struct perf_event_attr  attr;
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+        unsigned long           counter;
+#endif
+        struct hlist_node       ksym_hlist;
+};
+
+static struct trace_array *ksym_trace_array;
+
+static unsigned int ksym_filter_entry_count;
+static unsigned int ksym_tracing_enabled;
+
+static HLIST_HEAD(ksym_filter_head);
+
+static DEFINE_MUTEX(ksym_tracer_mutex);
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+
+#define MAX_UL_INT 0xffffffff
+
+void ksym_collect_stats(unsigned long hbp_hit_addr)
+{
+        struct hlist_node *node;
+        struct trace_ksym *entry;
+
+        rcu_read_lock();
+        hlist_for_each_entry_rcu(entry, node, &ksym_filter_head, ksym_hlist) {
+                if ((entry->attr.bp_addr == hbp_hit_addr) &&
+                    (entry->counter <= MAX_UL_INT)) {
+                        entry->counter++;
+                        break;
+                }
+        }
+        rcu_read_unlock();
+}
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
+
+void ksym_hbp_handler(struct perf_event *hbp, void *data)
+{
+        struct ring_buffer_event *event;
+        struct ksym_trace_entry *entry;
+        struct pt_regs *regs = data;
+        struct ring_buffer *buffer;
+        int pc;
+
+        if (!ksym_tracing_enabled)
+                return;
+
+        buffer = ksym_trace_array->buffer;
+
+        pc = preempt_count();
+
+        event = trace_buffer_lock_reserve(buffer, TRACE_KSYM,
+                                                        sizeof(*entry), 0, pc);
+        if (!event)
+                return;
+
+        entry           = ring_buffer_event_data(event);
+        entry->ip       = instruction_pointer(regs);
+        entry->type     = hw_breakpoint_type(hbp);
+        entry->addr     = hw_breakpoint_addr(hbp);
+        strlcpy(entry->cmd, current->comm, TASK_COMM_LEN);
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+        ksym_collect_stats(hw_breakpoint_addr(hbp));
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
+
+        trace_buffer_unlock_commit(buffer, event, 0, pc);
+}
+
+/* Valid access types are represented as
+ *
+ * rw- : Set Read/Write Access Breakpoint
+ * -w- : Set Write Access Breakpoint
+ * --- : Clear Breakpoints
+ * --x : Set Execution Break points (Not available yet)
+ *
+ */
+static int ksym_trace_get_access_type(char *str)
+{
+        int access = 0;
+
+        if (str[0] == 'r')
+                access |= HW_BREAKPOINT_R;
+
+        if (str[1] == 'w')
+                access |= HW_BREAKPOINT_W;
+
+        if (str[2] == 'x')
+                access |= HW_BREAKPOINT_X;
+
+        switch (access) {
+        case HW_BREAKPOINT_R:
+        case HW_BREAKPOINT_W:
+        case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
+                return access;
+        default:
+                return -EINVAL;
+        }
+}
+
+/*
+ * There can be several possible malformed requests and we attempt to capture
+ * all of them. We enumerate some of the rules
+ * 1. We will not allow kernel symbols with ':' since it is used as a delimiter.
+ *    i.e. multiple ':' symbols disallowed. Possible uses are of the form
+ *    <module>:<ksym_name>:<op>.
+ * 2. No delimiter symbol ':' in the input string
+ * 3. Spurious operator symbols or symbols not in their respective positions
+ * 4. <ksym_name>:--- i.e. clear breakpoint request when ksym_name not in file
+ * 5. Kernel symbol not a part of /proc/kallsyms
+ * 6. Duplicate requests
+ */
+static int parse_ksym_trace_str(char *input_string, char **ksymname,
+                                                        unsigned long *addr)
+{
+        int ret;
+
+        *ksymname = strsep(&input_string, ":");
+        *addr = kallsyms_lookup_name(*ksymname);
+
+        /* Check for malformed request: (2), (1) and (5) */
+        if ((!input_string) ||
+            (strlen(input_string) != KSYM_TRACER_OP_LEN) ||
+            (*addr == 0))
+                return -EINVAL;;
+
+        ret = ksym_trace_get_access_type(input_string);
+
+        return ret;
+}
+
+int process_new_ksym_entry(char *ksymname, int op, unsigned long addr)
+{
+        struct trace_ksym *entry;
+        int ret = -ENOMEM;
+
+        if (ksym_filter_entry_count >= KSYM_TRACER_MAX) {
+                printk(KERN_ERR "ksym_tracer: Maximum limit:(%d) reached. No"
+                " new requests for tracing can be accepted now.\n",
+                        KSYM_TRACER_MAX);
+                return -ENOSPC;
+        }
+
+        entry = kzalloc(sizeof(struct trace_ksym), GFP_KERNEL);
+        if (!entry)
+                return -ENOMEM;
+
+        hw_breakpoint_init(&entry->attr);
+
+        entry->attr.bp_type = op;
+        entry->attr.bp_addr = addr;
+        entry->attr.bp_len = HW_BREAKPOINT_LEN_4;
+
+        ret = -EAGAIN;
+        entry->ksym_hbp = register_wide_hw_breakpoint(&entry->attr,
+                                        ksym_hbp_handler);
+
+        if (IS_ERR(entry->ksym_hbp)) {
+                ret = PTR_ERR(entry->ksym_hbp);
+                printk(KERN_INFO "ksym_tracer request failed. Try again"
+                                        " later!!\n");
+                goto err;
+        }
+
+        hlist_add_head_rcu(&(entry->ksym_hlist), &ksym_filter_head);
+        ksym_filter_entry_count++;
+
+        return 0;
+
+err:
+        kfree(entry);
+
+        return ret;
+}
+
+static ssize_t ksym_trace_filter_read(struct file *filp, char __user *ubuf,
+                                                size_t count, loff_t *ppos)
+{
+        struct trace_ksym *entry;
+        struct hlist_node *node;
+        struct trace_seq *s;
+        ssize_t cnt = 0;
+        int ret;
+
+        s = kmalloc(sizeof(*s), GFP_KERNEL);
+        if (!s)
+                return -ENOMEM;
+        trace_seq_init(s);
+
+        mutex_lock(&ksym_tracer_mutex);
+
+        hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) {
+                ret = trace_seq_printf(s, "%pS:", (void *)entry->attr.bp_addr);
+                if (entry->attr.bp_type == HW_BREAKPOINT_R)
+                        ret = trace_seq_puts(s, "r--\n");
+                else if (entry->attr.bp_type == HW_BREAKPOINT_W)
+                        ret = trace_seq_puts(s, "-w-\n");
+                else if (entry->attr.bp_type == (HW_BREAKPOINT_W | HW_BREAKPOINT_R))
+                        ret = trace_seq_puts(s, "rw-\n");
+                WARN_ON_ONCE(!ret);
+        }
+
+        cnt = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
+
+        mutex_unlock(&ksym_tracer_mutex);
+
+        kfree(s);
+
+        return cnt;
+}
+
+static void __ksym_trace_reset(void)
+{
+        struct trace_ksym *entry;
+        struct hlist_node *node, *node1;
+
+        mutex_lock(&ksym_tracer_mutex);
+        hlist_for_each_entry_safe(entry, node, node1, &ksym_filter_head,
+                                                                ksym_hlist) {
+                unregister_wide_hw_breakpoint(entry->ksym_hbp);
+                ksym_filter_entry_count--;
+                hlist_del_rcu(&(entry->ksym_hlist));
+                synchronize_rcu();
+                kfree(entry);
+        }
+        mutex_unlock(&ksym_tracer_mutex);
+}
+
+static ssize_t ksym_trace_filter_write(struct file *file,
+                                        const char __user *buffer,
+                                                size_t count, loff_t *ppos)
+{
+        struct trace_ksym *entry;
+        struct hlist_node *node;
+        char *input_string, *ksymname = NULL;
+        unsigned long ksym_addr = 0;
+        int ret, op, changed = 0;
+
+        input_string = kzalloc(count + 1, GFP_KERNEL);
+        if (!input_string)
+                return -ENOMEM;
+
+        if (copy_from_user(input_string, buffer, count)) {
+                kfree(input_string);
+                return -EFAULT;
+        }
+        input_string[count] = '\0';
+
+        strstrip(input_string);
+
+        /*
+         * Clear all breakpoints if:
+         * 1: echo > ksym_trace_filter
+         * 2: echo 0 > ksym_trace_filter
+         * 3: echo "*:---" > ksym_trace_filter
+         */
+        if (!input_string[0] || !strcmp(input_string, "0") ||
+            !strcmp(input_string, "*:---")) {
+                __ksym_trace_reset();
+                kfree(input_string);
+                return count;
+        }
+
+        ret = op = parse_ksym_trace_str(input_string, &ksymname, &ksym_addr);
+        if (ret < 0) {
+                kfree(input_string);
+                return ret;
+        }
+
+        mutex_lock(&ksym_tracer_mutex);
+
+        ret = -EINVAL;
+        hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) {
+                if (entry->attr.bp_addr == ksym_addr) {
+                        /* Check for malformed request: (6) */
+                        if (entry->attr.bp_type != op)
+                                changed = 1;
+                        else
+                                goto out;
+                        break;
+                }
+        }
+        if (changed) {
+                unregister_wide_hw_breakpoint(entry->ksym_hbp);
+                entry->attr.bp_type = op;
+                ret = 0;
+                if (op > 0) {
+                        entry->ksym_hbp =
+                                register_wide_hw_breakpoint(&entry->attr,
+                                        ksym_hbp_handler);
+                        if (IS_ERR(entry->ksym_hbp))
+                                ret = PTR_ERR(entry->ksym_hbp);
+                        else
+                                goto out;
+                }
+                /* Error or "symbol:---" case: drop it */
+                ksym_filter_entry_count--;
+                hlist_del_rcu(&(entry->ksym_hlist));
+                synchronize_rcu();
+                kfree(entry);
+                goto out;
+        } else {
+                /* Check for malformed request: (4) */
+                if (op == 0)
+                        goto out;
+                ret = process_new_ksym_entry(ksymname, op, ksym_addr);
+        }
+out:
+        mutex_unlock(&ksym_tracer_mutex);
+
+        kfree(input_string);
+
+        if (!ret)
+                ret = count;
+        return ret;
+}
+
+static const struct file_operations ksym_tracing_fops = {
+        .open           = tracing_open_generic,
+        .read           = ksym_trace_filter_read,
+        .write          = ksym_trace_filter_write,
+};
+
+static void ksym_trace_reset(struct trace_array *tr)
+{
+        ksym_tracing_enabled = 0;
+        __ksym_trace_reset();
+}
+
+static int ksym_trace_init(struct trace_array *tr)
+{
+        int cpu, ret = 0;
+
+        for_each_online_cpu(cpu)
+                tracing_reset(tr, cpu);
+        ksym_tracing_enabled = 1;
+        ksym_trace_array = tr;
+
+        return ret;
+}
+
+static void ksym_trace_print_header(struct seq_file *m)
+{
+        seq_puts(m,
+                 "#       TASK-PID   CPU#      Symbol                    "
+                 "Type    Function\n");
+        seq_puts(m,
+                 "#          |        |          |                       "
+                 " |         |\n");
+}
+
+static enum print_line_t ksym_trace_output(struct trace_iterator *iter)
+{
+        struct trace_entry *entry = iter->ent;
+        struct trace_seq *s = &iter->seq;
+        struct ksym_trace_entry *field;
+        char str[KSYM_SYMBOL_LEN];
+        int ret;
+
+        if (entry->type != TRACE_KSYM)
+                return TRACE_TYPE_UNHANDLED;
+
+        trace_assign_type(field, entry);
+
+        ret = trace_seq_printf(s, "%11s-%-5d [%03d] %pS", field->cmd,
+                                entry->pid, iter->cpu, (char *)field->addr);
+        if (!ret)
+                return TRACE_TYPE_PARTIAL_LINE;
+
+        switch (field->type) {
+        case HW_BREAKPOINT_R:
+                ret = trace_seq_printf(s, " R  ");
+                break;
+        case HW_BREAKPOINT_W:
+                ret = trace_seq_printf(s, " W  ");
+                break;
+        case HW_BREAKPOINT_R | HW_BREAKPOINT_W:
+                ret = trace_seq_printf(s, " RW ");
+                break;
+        default:
+                return TRACE_TYPE_PARTIAL_LINE;
+        }
+
+        if (!ret)
+                return TRACE_TYPE_PARTIAL_LINE;
+
+        sprint_symbol(str, field->ip);
+        ret = trace_seq_printf(s, "%s\n", str);
+        if (!ret)
+                return TRACE_TYPE_PARTIAL_LINE;
+
+        return TRACE_TYPE_HANDLED;
+}
+
+struct tracer ksym_tracer __read_mostly =
+{
+        .name           = "ksym_tracer",
+        .init           = ksym_trace_init,
+        .reset          = ksym_trace_reset,
+#ifdef CONFIG_FTRACE_SELFTEST
+        .selftest       = trace_selftest_startup_ksym,
+#endif
+        .print_header   = ksym_trace_print_header,
+        .print_line     = ksym_trace_output
+};
+
+__init static int init_ksym_trace(void)
+{
+        struct dentry *d_tracer;
+        struct dentry *entry;
+
+        d_tracer = tracing_init_dentry();
+        ksym_filter_entry_count = 0;
+
+        entry = debugfs_create_file("ksym_trace_filter", 0644, d_tracer,
+                                    NULL, &ksym_tracing_fops);
+        if (!entry)
+                pr_warning("Could not create debugfs "
+                           "'ksym_trace_filter' file\n");
+
+        return register_tracer(&ksym_tracer);
+}
+device_initcall(init_ksym_trace);
+
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+static int ksym_tracer_stat_headers(struct seq_file *m)
+{
+        seq_puts(m, "  Access Type ");
+        seq_puts(m, "  Symbol                                       Counter\n");
+        seq_puts(m, "  ----------- ");
+        seq_puts(m, "  ------                                       -------\n");
+        return 0;
+}
+
+static int ksym_tracer_stat_show(struct seq_file *m, void *v)
+{
+        struct hlist_node *stat = v;
+        struct trace_ksym *entry;
+        int access_type = 0;
+        char fn_name[KSYM_NAME_LEN];
+
+        entry = hlist_entry(stat, struct trace_ksym, ksym_hlist);
+
+        access_type = entry->attr.bp_type;
+
+        switch (access_type) {
+        case HW_BREAKPOINT_R:
+                seq_puts(m, "  R           ");
+                break;
+        case HW_BREAKPOINT_W:
+                seq_puts(m, "  W           ");
+                break;
+        case HW_BREAKPOINT_R | HW_BREAKPOINT_W:
+                seq_puts(m, "  RW          ");
+                break;
+        default:
+                seq_puts(m, "  NA          ");
+        }
+
+        if (lookup_symbol_name(entry->attr.bp_addr, fn_name) >= 0)
+                seq_printf(m, "  %-36s", fn_name);
+        else
+                seq_printf(m, "  %-36s", "<NA>");
+        seq_printf(m, " %15lu\n", entry->counter);
+
+        return 0;
+}
+
+static void *ksym_tracer_stat_start(struct tracer_stat *trace)
+{
+        return ksym_filter_head.first;
+}
+
+static void *
+ksym_tracer_stat_next(void *v, int idx)
+{
+        struct hlist_node *stat = v;
+
+        return stat->next;
+}
+
+static struct tracer_stat ksym_tracer_stats = {
+        .name = "ksym_tracer",
+        .stat_start = ksym_tracer_stat_start,
+        .stat_next = ksym_tracer_stat_next,
+        .stat_headers = ksym_tracer_stat_headers,
+        .stat_show = ksym_tracer_stat_show
+};
+
+__init static int ksym_tracer_stat_init(void)
+{
+        int ret;
+
+        ret = register_stat_tracer(&ksym_tracer_stats);
+        if (ret) {
+                printk(KERN_WARNING "Warning: could not register "
+                                    "ksym tracer stats\n");
+                return 1;
+        }
+
+        return 0;
+}
+fs_initcall(ksym_tracer_stat_init);
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index d2cdbabb4ead..dc98309e839a 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -17,6 +17,7 @@ static inline int trace_valid_entry(struct trace_entry *entry)
         case TRACE_GRAPH_ENT:
         case TRACE_GRAPH_RET:
         case TRACE_HW_BRANCHES:
+        case TRACE_KSYM:
                 return 1;
         }
         return 0;
@@ -808,3 +809,57 @@ trace_selftest_startup_hw_branches(struct tracer *trace,
         return ret;
 }
 #endif /* CONFIG_HW_BRANCH_TRACER */
+
+#ifdef CONFIG_KSYM_TRACER
+static int ksym_selftest_dummy;
+
+int
+trace_selftest_startup_ksym(struct tracer *trace, struct trace_array *tr)
+{
+        unsigned long count;
+        int ret;
+
+        /* start the tracing */
+        ret = tracer_init(trace, tr);
+        if (ret) {
+                warn_failed_init_tracer(trace, ret);
+                return ret;
+        }
+
+        ksym_selftest_dummy = 0;
+        /* Register the read-write tracing request */
+
+        ret = process_new_ksym_entry("ksym_selftest_dummy",
+                                     HW_BREAKPOINT_R | HW_BREAKPOINT_W,
+                                        (unsigned long)(&ksym_selftest_dummy));
+
+        if (ret < 0) {
+                printk(KERN_CONT "ksym_trace read-write startup test failed\n");
+                goto ret_path;
+        }
+        /* Perform a read and a write operation over the dummy variable to
+         * trigger the tracer
+         */
+        if (ksym_selftest_dummy == 0)
+                ksym_selftest_dummy++;
+
+        /* stop the tracing. */
+        tracing_stop();
+        /* check the trace buffer */
+        ret = trace_test_buffer(tr, &count);
+        trace->reset(tr);
+        tracing_start();
+
+        /* read & write operations - one each is performed on the dummy variable
+         * triggering two entries in the trace buffer
+         */
+        if (!ret && count != 2) {
+                printk(KERN_CONT "Ksym tracer startup test failed");
+                ret = -1;
+        }
+
+ret_path:
+        return ret;
+}
+#endif /* CONFIG_KSYM_TRACER */
+
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index ddee9c593732..57501d90096a 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -51,32 +51,6 @@ static struct syscall_metadata *syscall_nr_to_meta(int nr)
         return syscalls_metadata[nr];
 }
 
-int syscall_name_to_nr(char *name)
-{
-        int i;
-
-        if (!syscalls_metadata)
-                return -1;
-
-        for (i = 0; i < NR_syscalls; i++) {
-                if (syscalls_metadata[i]) {
-                        if (!strcmp(syscalls_metadata[i]->name, name))
-                                return i;
-                }
-        }
-        return -1;
-}
-
-void set_syscall_enter_id(int num, int id)
-{
-        syscalls_metadata[num]->enter_id = id;
-}
-
-void set_syscall_exit_id(int num, int id)
-{
-        syscalls_metadata[num]->exit_id = id;
-}
-
 enum print_line_t
 print_syscall_enter(struct trace_iterator *iter, int flags)
 {
@@ -93,7 +67,7 @@ print_syscall_enter(struct trace_iterator *iter, int flags)
         if (!entry)
                 goto end;
 
-        if (entry->enter_id != ent->type) {
+        if (entry->enter_event->id != ent->type) {
                 WARN_ON_ONCE(1);
                 goto end;
         }
@@ -148,7 +122,7 @@ print_syscall_exit(struct trace_iterator *iter, int flags)
                 return TRACE_TYPE_HANDLED;
         }
 
-        if (entry->exit_id != ent->type) {
+        if (entry->exit_event->id != ent->type) {
                 WARN_ON_ONCE(1);
                 return TRACE_TYPE_UNHANDLED;
         }
@@ -166,24 +140,19 @@ extern char *__bad_type_size(void);
 #define SYSCALL_FIELD(type, name)                                       \
         sizeof(type) != sizeof(trace.name) ?                            \
                 __bad_type_size() :                                     \
-                #type, #name, offsetof(typeof(trace), name), sizeof(trace.name)
+                #type, #name, offsetof(typeof(trace), name),            \
+                sizeof(trace.name), is_signed_type(type)
 
 int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
 {
         int i;
-        int nr;
         int ret;
-        struct syscall_metadata *entry;
+        struct syscall_metadata *entry = call->data;
         struct syscall_trace_enter trace;
         int offset = offsetof(struct syscall_trace_enter, args);
 
-        nr = syscall_name_to_nr(call->data);
-        entry = syscall_nr_to_meta(nr);
-
-        if (!entry)
-                return 0;
-
-        ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
+        ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
+                               "\tsigned:%u;\n",
                                SYSCALL_FIELD(int, nr));
         if (!ret)
                 return 0;
@@ -193,8 +162,10 @@ int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
                                         entry->args[i]);
                 if (!ret)
                         return 0;
-                ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;\n", offset,
-                                       sizeof(unsigned long));
+                ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;"
+                                       "\tsigned:%u;\n", offset,
+                                       sizeof(unsigned long),
+                                       is_signed_type(unsigned long));
                 if (!ret)
                         return 0;
                 offset += sizeof(unsigned long);
@@ -226,8 +197,10 @@ int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
         struct syscall_trace_exit trace;
 
         ret = trace_seq_printf(s,
-                               "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-                               "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
+                               "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
+                               "\tsigned:%u;\n"
+                               "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
+                               "\tsigned:%u;\n",
                                SYSCALL_FIELD(int, nr),
                                SYSCALL_FIELD(long, ret));
         if (!ret)
@@ -239,22 +212,19 @@ int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
 int syscall_enter_define_fields(struct ftrace_event_call *call)
 {
         struct syscall_trace_enter trace;
-        struct syscall_metadata *meta;
+        struct syscall_metadata *meta = call->data;
         int ret;
-        int nr;
         int i;
         int offset = offsetof(typeof(trace), args);
 
-        nr = syscall_name_to_nr(call->data);
-        meta = syscall_nr_to_meta(nr);
-
-        if (!meta)
-                return 0;
-
         ret = trace_define_common_fields(call);
         if (ret)
                 return ret;
 
+        ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
+        if (ret)
+                return ret;
+
         for (i = 0; i < meta->nb_args; i++) {
                 ret = trace_define_field(call, meta->types[i],
                                          meta->args[i], offset,
@@ -275,7 +245,11 @@ int syscall_exit_define_fields(struct ftrace_event_call *call)
         if (ret)
                 return ret;
 
-        ret = trace_define_field(call, SYSCALL_FIELD(long, ret), 0,
+        ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
+        if (ret)
+                return ret;
+
+        ret = trace_define_field(call, SYSCALL_FIELD(long, ret),
                                  FILTER_OTHER);
 
         return ret;
@@ -302,8 +276,8 @@ void ftrace_syscall_enter(struct pt_regs *regs, long id)
 
         size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
 
-        event = trace_current_buffer_lock_reserve(&buffer, sys_data->enter_id,
-                                                  size, 0, 0);
+        event = trace_current_buffer_lock_reserve(&buffer,
+                        sys_data->enter_event->id, size, 0, 0);
         if (!event)
                 return;
 
@@ -334,8 +308,8 @@ void ftrace_syscall_exit(struct pt_regs *regs, long ret)
         if (!sys_data)
                 return;
 
-        event = trace_current_buffer_lock_reserve(&buffer, sys_data->exit_id,
-                                sizeof(*entry), 0, 0);
+        event = trace_current_buffer_lock_reserve(&buffer,
+                        sys_data->exit_event->id, sizeof(*entry), 0, 0);
         if (!event)
                 return;
 
@@ -348,14 +322,12 @@ void ftrace_syscall_exit(struct pt_regs *regs, long ret)
                 trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-int reg_event_syscall_enter(void *ptr)
+int reg_event_syscall_enter(struct ftrace_event_call *call)
 {
         int ret = 0;
         int num;
-        char *name;
 
-        name = (char *)ptr;
-        num = syscall_name_to_nr(name);
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
         if (num < 0 || num >= NR_syscalls)
                 return -ENOSYS;
         mutex_lock(&syscall_trace_lock);
@@ -372,13 +344,11 @@ int reg_event_syscall_enter(void *ptr)
         return ret;
 }
 
-void unreg_event_syscall_enter(void *ptr)
+void unreg_event_syscall_enter(struct ftrace_event_call *call)
 {
         int num;
-        char *name;
 
-        name = (char *)ptr;
-        num = syscall_name_to_nr(name);
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
         if (num < 0 || num >= NR_syscalls)
                 return;
         mutex_lock(&syscall_trace_lock);
@@ -389,14 +359,12 @@ void unreg_event_syscall_enter(void *ptr)
         mutex_unlock(&syscall_trace_lock);
 }
 
-int reg_event_syscall_exit(void *ptr)
+int reg_event_syscall_exit(struct ftrace_event_call *call)
 {
         int ret = 0;
         int num;
-        char *name;
 
-        name = (char *)ptr;
-        num = syscall_name_to_nr(name);
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
         if (num < 0 || num >= NR_syscalls)
                 return -ENOSYS;
         mutex_lock(&syscall_trace_lock);
@@ -413,13 +381,11 @@ int reg_event_syscall_exit(void *ptr)
         return ret;
 }
 
-void unreg_event_syscall_exit(void *ptr)
+void unreg_event_syscall_exit(struct ftrace_event_call *call)
 {
         int num;
-        char *name;
 
-        name = (char *)ptr;
-        num = syscall_name_to_nr(name);
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
         if (num < 0 || num >= NR_syscalls)
                 return;
         mutex_lock(&syscall_trace_lock);
@@ -430,13 +396,17 @@ void unreg_event_syscall_exit(void *ptr)
         mutex_unlock(&syscall_trace_lock);
 }
 
-struct trace_event event_syscall_enter = {
-        .trace                  = print_syscall_enter,
-};
+int init_syscall_trace(struct ftrace_event_call *call)
+{
+        int id;
 
-struct trace_event event_syscall_exit = {
-        .trace                  = print_syscall_exit,
-};
+        id = register_ftrace_event(call->event);
+        if (!id)
+                return -ENODEV;
+        call->id = id;
+        INIT_LIST_HEAD(&call->fields);
+        return 0;
+}
 
 int __init init_ftrace_syscalls(void)
 {
@@ -454,6 +424,10 @@ int __init init_ftrace_syscalls(void)
         for (i = 0; i < NR_syscalls; i++) {
                 addr = arch_syscall_addr(i);
                 meta = find_syscall_meta(addr);
+                if (!meta)
+                        continue;
+
+                meta->syscall_nr = i;
                 syscalls_metadata[i] = meta;
         }
 
@@ -473,8 +447,10 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
         struct syscall_metadata *sys_data;
         struct syscall_trace_enter *rec;
         unsigned long flags;
+        char *trace_buf;
         char *raw_data;
         int syscall_nr;
+        int rctx;
         int size;
         int cpu;
 
@@ -498,41 +474,42 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
         /* Protect the per cpu buffer, begin the rcu read side */
         local_irq_save(flags);
 
+        rctx = perf_swevent_get_recursion_context();
+        if (rctx < 0)
+                goto end_recursion;
+
         cpu = smp_processor_id();
 
-        if (in_nmi())
-                raw_data = rcu_dereference(trace_profile_buf_nmi);
-        else
-                raw_data = rcu_dereference(trace_profile_buf);
+        trace_buf = rcu_dereference(perf_trace_buf);
 
-        if (!raw_data)
+        if (!trace_buf)
                 goto end;
 
-        raw_data = per_cpu_ptr(raw_data, cpu);
+        raw_data = per_cpu_ptr(trace_buf, cpu);
 
         /* zero the dead bytes from align to not leak stack to user */
         *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
 
         rec = (struct syscall_trace_enter *) raw_data;
         tracing_generic_entry_update(&rec->ent, 0, 0);
-        rec->ent.type = sys_data->enter_id;
+        rec->ent.type = sys_data->enter_event->id;
         rec->nr = syscall_nr;
         syscall_get_arguments(current, regs, 0, sys_data->nb_args,
                                (unsigned long *)&rec->args);
-        perf_tp_event(sys_data->enter_id, 0, 1, rec, size);
+        perf_tp_event(sys_data->enter_event->id, 0, 1, rec, size);
 
 end:
+        perf_swevent_put_recursion_context(rctx);
+end_recursion:
         local_irq_restore(flags);
 }
 
-int reg_prof_syscall_enter(char *name)
+int prof_sysenter_enable(struct ftrace_event_call *call)
 {
         int ret = 0;
         int num;
 
-        num = syscall_name_to_nr(name);
-        if (num < 0 || num >= NR_syscalls)
-                return -ENOSYS;
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
         mutex_lock(&syscall_trace_lock);
         if (!sys_prof_refcount_enter)
@@ -548,13 +525,11 @@ int reg_prof_syscall_enter(char *name)
         return ret;
 }
 
-void unreg_prof_syscall_enter(char *name)
+void prof_sysenter_disable(struct ftrace_event_call *call)
 {
         int num;
 
-        num = syscall_name_to_nr(name);
-        if (num < 0 || num >= NR_syscalls)
-                return;
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
         mutex_lock(&syscall_trace_lock);
         sys_prof_refcount_enter--;
@@ -570,7 +545,9 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
         struct syscall_trace_exit *rec;
         unsigned long flags;
         int syscall_nr;
+        char *trace_buf;
         char *raw_data;
+        int rctx;
         int size;
         int cpu;
 
@@ -596,17 +573,19 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
 
         /* Protect the per cpu buffer, begin the rcu read side */
         local_irq_save(flags);
+
+        rctx = perf_swevent_get_recursion_context();
+        if (rctx < 0)
+                goto end_recursion;
+
         cpu = smp_processor_id();
 
-        if (in_nmi())
-                raw_data = rcu_dereference(trace_profile_buf_nmi);
-        else
-                raw_data = rcu_dereference(trace_profile_buf);
+        trace_buf = rcu_dereference(perf_trace_buf);
 
-        if (!raw_data)
+        if (!trace_buf)
                 goto end;
 
-        raw_data = per_cpu_ptr(raw_data, cpu);
+        raw_data = per_cpu_ptr(trace_buf, cpu);
 
         /* zero the dead bytes from align to not leak stack to user */
         *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
@@ -614,24 +593,24 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
         rec = (struct syscall_trace_exit *)raw_data;
 
         tracing_generic_entry_update(&rec->ent, 0, 0);
-        rec->ent.type = sys_data->exit_id;
+        rec->ent.type = sys_data->exit_event->id;
         rec->nr = syscall_nr;
         rec->ret = syscall_get_return_value(current, regs);
 
-        perf_tp_event(sys_data->exit_id, 0, 1, rec, size);
+        perf_tp_event(sys_data->exit_event->id, 0, 1, rec, size);
 
 end:
+        perf_swevent_put_recursion_context(rctx);
+end_recursion:
         local_irq_restore(flags);
 }
 
-int reg_prof_syscall_exit(char *name)
+int prof_sysexit_enable(struct ftrace_event_call *call)
 {
         int ret = 0;
         int num;
 
-        num = syscall_name_to_nr(name);
-        if (num < 0 || num >= NR_syscalls)
-                return -ENOSYS;
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
         mutex_lock(&syscall_trace_lock);
         if (!sys_prof_refcount_exit)
@@ -647,13 +626,11 @@ int reg_prof_syscall_exit(char *name)
         return ret;
 }
 
-void unreg_prof_syscall_exit(char *name)
+void prof_sysexit_disable(struct ftrace_event_call *call)
 {
         int num;
 
-        num = syscall_name_to_nr(name);
-        if (num < 0 || num >= NR_syscalls)
-                return;
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
         mutex_lock(&syscall_trace_lock);
         sys_prof_refcount_exit--;
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 69eae358a726..a2cd77e70d4d 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -57,78 +57,47 @@ static int proc_do_uts_string(ctl_table *table, int write,
 #define proc_do_uts_string NULL
 #endif
 
-
-#ifdef CONFIG_SYSCTL_SYSCALL
-/* The generic string strategy routine: */
-static int sysctl_uts_string(ctl_table *table,
-                  void __user *oldval, size_t __user *oldlenp,
-                  void __user *newval, size_t newlen)
-{
-        struct ctl_table uts_table;
-        int r, write;
-        write = newval && newlen;
-        memcpy(&uts_table, table, sizeof(uts_table));
-        uts_table.data = get_uts(table, write);
-        r = sysctl_string(&uts_table, oldval, oldlenp, newval, newlen);
-        put_uts(table, write, uts_table.data);
-        return r;
-}
-#else
-#define sysctl_uts_string NULL
-#endif
-
 static struct ctl_table uts_kern_table[] = {
         {
-                .ctl_name       = KERN_OSTYPE,
                 .procname       = "ostype",
                 .data           = init_uts_ns.name.sysname,
                 .maxlen         = sizeof(init_uts_ns.name.sysname),
                 .mode           = 0444,
                 .proc_handler   = proc_do_uts_string,
-                .strategy       = sysctl_uts_string,
         },
         {
-                .ctl_name       = KERN_OSRELEASE,
                 .procname       = "osrelease",
                 .data           = init_uts_ns.name.release,
                 .maxlen         = sizeof(init_uts_ns.name.release),
                 .mode           = 0444,
                 .proc_handler   = proc_do_uts_string,
-                .strategy       = sysctl_uts_string,
         },
         {
-                .ctl_name       = KERN_VERSION,
                 .procname       = "version",
                 .data           = init_uts_ns.name.version,
                 .maxlen         = sizeof(init_uts_ns.name.version),
                 .mode           = 0444,
                 .proc_handler   = proc_do_uts_string,
-                .strategy       = sysctl_uts_string,
         },
         {
-                .ctl_name       = KERN_NODENAME,
                 .procname       = "hostname",
                 .data           = init_uts_ns.name.nodename,
                 .maxlen         = sizeof(init_uts_ns.name.nodename),
                 .mode           = 0644,
                 .proc_handler   = proc_do_uts_string,
-                .strategy       = sysctl_uts_string,
         },
         {
-                .ctl_name       = KERN_DOMAINNAME,
                 .procname       = "domainname",
                 .data           = init_uts_ns.name.domainname,
                 .maxlen         = sizeof(init_uts_ns.name.domainname),
                 .mode           = 0644,
                 .proc_handler   = proc_do_uts_string,
-                .strategy       = sysctl_uts_string,
         },
         {}
 };
 
 static struct ctl_table uts_root_table[] = {
         {
-                .ctl_name       = CTL_KERN,
                 .procname       = "kernel",
                 .mode           = 0555,
                 .child          = uts_kern_table,