#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;
u64 rt_avg;
u64 age_stamp;
+ u64 idle_stamp;
+ u64 avg_idle;
#endif
/* calc_load related fields */
if (!sched_feat_names[i])
return -EINVAL;
- filp->f_pos += cnt;
+ *ppos += cnt;
return cnt;
}
}
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;
#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);
* 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;
}
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);
#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);
void sched_fork(struct task_struct *p, int clone_flags)
{
int cpu = get_cpu();
+ unsigned long flags;
__sched_fork(p);
#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()))
*/
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;
}
}
}
-/*
- * 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).
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
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
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;
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)) {
/*
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);
+ }
}
/*
* 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.
}
EXPORT_SYMBOL(schedule);
-#ifdef CONFIG_SMP
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
/*
* Look out! "owner" is an entirely speculative pointer
* access and not reliable.
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);
}
/*
* Only show locks if all tasks are dumped:
*/
- if (state_filter == -1)
+ if (!state_filter)
debug_show_all_locks();
}
.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)
#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)
{
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;
static void free_rootdomain(struct root_domain *rd)
{
+ synchronize_sched();
+
cpupri_cleanup(&rd->cpupri);
free_cpumask_var(rd->rto_mask);
/* 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;
}
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' */
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
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;
* 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,
*
* 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;
/* 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;
#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);
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
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();
spin_unlock_irqrestore(&rq->lock, flags);
}
rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
+ synchronize_sched_expedited_count++;
mutex_unlock(&rcu_sched_expedited_mutex);
put_online_cpus();
if (need_full_sync)
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/wait.h>
-
-#define SLOW_WORK_CULL_TIMEOUT (5 * HZ) /* cull threads 5s after running out of
- * things to do */
-#define SLOW_WORK_OOM_TIMEOUT (5 * HZ) /* can't start new threads for 5s after
- * OOM */
+#include <linux/debugfs.h>
+#include "slow-work.h"
static void slow_work_cull_timeout(unsigned long);
static void slow_work_oom_timeout(unsigned long);
#ifdef CONFIG_SYSCTL
static const int slow_work_min_min_threads = 2;
-static int slow_work_max_max_threads = 255;
+static int slow_work_max_max_threads = SLOW_WORK_THREAD_LIMIT;
static const int slow_work_min_vslow = 1;
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),
.extra2 = &slow_work_max_threads,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "max-threads",
.data = &slow_work_max_threads,
.maxlen = sizeof(unsigned),
.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
static DEFINE_TIMER(slow_work_oom_timer, slow_work_oom_timeout, 0, 0);
static struct slow_work slow_work_new_thread; /* new thread starter */
+/*
+ * slow work ID allocation (use slow_work_queue_lock)
+ */
+static DECLARE_BITMAP(slow_work_ids, SLOW_WORK_THREAD_LIMIT);
+
+/*
+ * Unregistration tracking to prevent put_ref() from disappearing during module
+ * unload
+ */
+#ifdef CONFIG_MODULES
+static struct module *slow_work_thread_processing[SLOW_WORK_THREAD_LIMIT];
+static struct module *slow_work_unreg_module;
+static struct slow_work *slow_work_unreg_work_item;
+static DECLARE_WAIT_QUEUE_HEAD(slow_work_unreg_wq);
+static DEFINE_MUTEX(slow_work_unreg_sync_lock);
+
+static void slow_work_set_thread_processing(int id, struct slow_work *work)
+{
+ if (work)
+ slow_work_thread_processing[id] = work->owner;
+}
+static void slow_work_done_thread_processing(int id, struct slow_work *work)
+{
+ struct module *module = slow_work_thread_processing[id];
+
+ slow_work_thread_processing[id] = NULL;
+ smp_mb();
+ if (slow_work_unreg_work_item == work ||
+ slow_work_unreg_module == module)
+ wake_up_all(&slow_work_unreg_wq);
+}
+static void slow_work_clear_thread_processing(int id)
+{
+ slow_work_thread_processing[id] = NULL;
+}
+#else
+static void slow_work_set_thread_processing(int id, struct slow_work *work) {}
+static void slow_work_done_thread_processing(int id, struct slow_work *work) {}
+static void slow_work_clear_thread_processing(int id) {}
+#endif
+
+/*
+ * Data for tracking currently executing items for indication through /proc
+ */
+#ifdef CONFIG_SLOW_WORK_DEBUG
+struct slow_work *slow_work_execs[SLOW_WORK_THREAD_LIMIT];
+pid_t slow_work_pids[SLOW_WORK_THREAD_LIMIT];
+DEFINE_RWLOCK(slow_work_execs_lock);
+#endif
+
/*
* The queues of work items and the lock governing access to them. These are
* shared between all the CPUs. It doesn't make sense to have per-CPU queues
* There are two queues of work items: one for slow work items, and one for
* very slow work items.
*/
-static LIST_HEAD(slow_work_queue);
-static LIST_HEAD(vslow_work_queue);
-static DEFINE_SPINLOCK(slow_work_queue_lock);
+LIST_HEAD(slow_work_queue);
+LIST_HEAD(vslow_work_queue);
+DEFINE_SPINLOCK(slow_work_queue_lock);
+
+/*
+ * The following are two wait queues that get pinged when a work item is placed
+ * on an empty queue. These allow work items that are hogging a thread by
+ * sleeping in a way that could be deferred to yield their thread and enqueue
+ * themselves.
+ */
+static DECLARE_WAIT_QUEUE_HEAD(slow_work_queue_waits_for_occupation);
+static DECLARE_WAIT_QUEUE_HEAD(vslow_work_queue_waits_for_occupation);
/*
* The thread controls. A variable used to signal to the threads that they
static int slow_work_user_count;
static DEFINE_MUTEX(slow_work_user_lock);
+static inline int slow_work_get_ref(struct slow_work *work)
+{
+ if (work->ops->get_ref)
+ return work->ops->get_ref(work);
+
+ return 0;
+}
+
+static inline void slow_work_put_ref(struct slow_work *work)
+{
+ if (work->ops->put_ref)
+ work->ops->put_ref(work);
+}
+
/*
* Calculate the maximum number of active threads in the pool that are
* permitted to process very slow work items.
* Attempt to execute stuff queued on a slow thread. Return true if we managed
* it, false if there was nothing to do.
*/
-static bool slow_work_execute(void)
+static noinline bool slow_work_execute(int id)
{
struct slow_work *work = NULL;
unsigned vsmax;
} else {
very_slow = false; /* avoid the compiler warning */
}
+
+ slow_work_set_thread_processing(id, work);
+ if (work) {
+ slow_work_mark_time(work);
+ slow_work_begin_exec(id, work);
+ }
+
spin_unlock_irq(&slow_work_queue_lock);
if (!work)
if (!test_and_clear_bit(SLOW_WORK_PENDING, &work->flags))
BUG();
- work->ops->execute(work);
+ /* don't execute if the work is in the process of being cancelled */
+ if (!test_bit(SLOW_WORK_CANCELLING, &work->flags))
+ work->ops->execute(work);
if (very_slow)
atomic_dec(&vslow_work_executing_count);
clear_bit_unlock(SLOW_WORK_EXECUTING, &work->flags);
+ /* wake up anyone waiting for this work to be complete */
+ wake_up_bit(&work->flags, SLOW_WORK_EXECUTING);
+
+ slow_work_end_exec(id, work);
+
/* if someone tried to enqueue the item whilst we were executing it,
* then it'll be left unenqueued to avoid multiple threads trying to
* execute it simultaneously
spin_unlock_irq(&slow_work_queue_lock);
}
- work->ops->put_ref(work);
+ /* sort out the race between module unloading and put_ref() */
+ slow_work_put_ref(work);
+ slow_work_done_thread_processing(id, work);
+
return true;
auto_requeue:
* - we transfer our ref on the item back to the appropriate queue
* - don't wake another thread up as we're awake already
*/
+ slow_work_mark_time(work);
if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags))
list_add_tail(&work->link, &vslow_work_queue);
else
list_add_tail(&work->link, &slow_work_queue);
spin_unlock_irq(&slow_work_queue_lock);
+ slow_work_clear_thread_processing(id);
return true;
}
+/**
+ * slow_work_sleep_till_thread_needed - Sleep till thread needed by other work
+ * work: The work item under execution that wants to sleep
+ * _timeout: Scheduler sleep timeout
+ *
+ * Allow a requeueable work item to sleep on a slow-work processor thread until
+ * that thread is needed to do some other work or the sleep is interrupted by
+ * some other event.
+ *
+ * The caller must set up a wake up event before calling this and must have set
+ * the appropriate sleep mode (such as TASK_UNINTERRUPTIBLE) and tested its own
+ * condition before calling this function as no test is made here.
+ *
+ * False is returned if there is nothing on the queue; true is returned if the
+ * work item should be requeued
+ */
+bool slow_work_sleep_till_thread_needed(struct slow_work *work,
+ signed long *_timeout)
+{
+ wait_queue_head_t *wfo_wq;
+ struct list_head *queue;
+
+ DEFINE_WAIT(wait);
+
+ if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) {
+ wfo_wq = &vslow_work_queue_waits_for_occupation;
+ queue = &vslow_work_queue;
+ } else {
+ wfo_wq = &slow_work_queue_waits_for_occupation;
+ queue = &slow_work_queue;
+ }
+
+ if (!list_empty(queue))
+ return true;
+
+ add_wait_queue_exclusive(wfo_wq, &wait);
+ if (list_empty(queue))
+ *_timeout = schedule_timeout(*_timeout);
+ finish_wait(wfo_wq, &wait);
+
+ return !list_empty(queue);
+}
+EXPORT_SYMBOL(slow_work_sleep_till_thread_needed);
+
/**
* slow_work_enqueue - Schedule a slow work item for processing
* @work: The work item to queue
* allowed to pick items to execute. This ensures that very slow items won't
* overly block ones that are just ordinarily slow.
*
- * Returns 0 if successful, -EAGAIN if not.
+ * Returns 0 if successful, -EAGAIN if not (or -ECANCELED if cancelled work is
+ * attempted queued)
*/
int slow_work_enqueue(struct slow_work *work)
{
+ wait_queue_head_t *wfo_wq;
+ struct list_head *queue;
unsigned long flags;
+ int ret;
+
+ if (test_bit(SLOW_WORK_CANCELLING, &work->flags))
+ return -ECANCELED;
BUG_ON(slow_work_user_count <= 0);
BUG_ON(!work);
BUG_ON(!work->ops);
- BUG_ON(!work->ops->get_ref);
/* when honouring an enqueue request, we only promise that we will run
* the work function in the future; we do not promise to run it once
* maintaining our promise
*/
if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) {
+ if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) {
+ wfo_wq = &vslow_work_queue_waits_for_occupation;
+ queue = &vslow_work_queue;
+ } else {
+ wfo_wq = &slow_work_queue_waits_for_occupation;
+ queue = &slow_work_queue;
+ }
+
spin_lock_irqsave(&slow_work_queue_lock, flags);
+ if (unlikely(test_bit(SLOW_WORK_CANCELLING, &work->flags)))
+ goto cancelled;
+
/* we promise that we will not attempt to execute the work
* function in more than one thread simultaneously
*
if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) {
set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags);
} else {
- if (work->ops->get_ref(work) < 0)
- goto cant_get_ref;
- if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags))
- list_add_tail(&work->link, &vslow_work_queue);
- else
- list_add_tail(&work->link, &slow_work_queue);
+ ret = slow_work_get_ref(work);
+ if (ret < 0)
+ goto failed;
+ slow_work_mark_time(work);
+ list_add_tail(&work->link, queue);
wake_up(&slow_work_thread_wq);
+
+ /* if someone who could be requeued is sleeping on a
+ * thread, then ask them to yield their thread */
+ if (work->link.prev == queue)
+ wake_up(wfo_wq);
}
spin_unlock_irqrestore(&slow_work_queue_lock, flags);
}
return 0;
-cant_get_ref:
+cancelled:
+ ret = -ECANCELED;
+failed:
spin_unlock_irqrestore(&slow_work_queue_lock, flags);
- return -EAGAIN;
+ return ret;
}
EXPORT_SYMBOL(slow_work_enqueue);
+static int slow_work_wait(void *word)
+{
+ schedule();
+ return 0;
+}
+
+/**
+ * slow_work_cancel - Cancel a slow work item
+ * @work: The work item to cancel
+ *
+ * This function will cancel a previously enqueued work item. If we cannot
+ * cancel the work item, it is guarenteed to have run when this function
+ * returns.
+ */
+void slow_work_cancel(struct slow_work *work)
+{
+ bool wait = true, put = false;
+
+ set_bit(SLOW_WORK_CANCELLING, &work->flags);
+ smp_mb();
+
+ /* if the work item is a delayed work item with an active timer, we
+ * need to wait for the timer to finish _before_ getting the spinlock,
+ * lest we deadlock against the timer routine
+ *
+ * the timer routine will leave DELAYED set if it notices the
+ * CANCELLING flag in time
+ */
+ if (test_bit(SLOW_WORK_DELAYED, &work->flags)) {
+ struct delayed_slow_work *dwork =
+ container_of(work, struct delayed_slow_work, work);
+ del_timer_sync(&dwork->timer);
+ }
+
+ spin_lock_irq(&slow_work_queue_lock);
+
+ if (test_bit(SLOW_WORK_DELAYED, &work->flags)) {
+ /* the timer routine aborted or never happened, so we are left
+ * holding the timer's reference on the item and should just
+ * drop the pending flag and wait for any ongoing execution to
+ * finish */
+ struct delayed_slow_work *dwork =
+ container_of(work, struct delayed_slow_work, work);
+
+ BUG_ON(timer_pending(&dwork->timer));
+ BUG_ON(!list_empty(&work->link));
+
+ clear_bit(SLOW_WORK_DELAYED, &work->flags);
+ put = true;
+ clear_bit(SLOW_WORK_PENDING, &work->flags);
+
+ } else if (test_bit(SLOW_WORK_PENDING, &work->flags) &&
+ !list_empty(&work->link)) {
+ /* the link in the pending queue holds a reference on the item
+ * that we will need to release */
+ list_del_init(&work->link);
+ wait = false;
+ put = true;
+ clear_bit(SLOW_WORK_PENDING, &work->flags);
+
+ } else if (test_and_clear_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags)) {
+ /* the executor is holding our only reference on the item, so
+ * we merely need to wait for it to finish executing */
+ clear_bit(SLOW_WORK_PENDING, &work->flags);
+ }
+
+ spin_unlock_irq(&slow_work_queue_lock);
+
+ /* the EXECUTING flag is set by the executor whilst the spinlock is set
+ * and before the item is dequeued - so assuming the above doesn't
+ * actually dequeue it, simply waiting for the EXECUTING flag to be
+ * released here should be sufficient */
+ if (wait)
+ wait_on_bit(&work->flags, SLOW_WORK_EXECUTING, slow_work_wait,
+ TASK_UNINTERRUPTIBLE);
+
+ clear_bit(SLOW_WORK_CANCELLING, &work->flags);
+ if (put)
+ slow_work_put_ref(work);
+}
+EXPORT_SYMBOL(slow_work_cancel);
+
+/*
+ * Handle expiry of the delay timer, indicating that a delayed slow work item
+ * should now be queued if not cancelled
+ */
+static void delayed_slow_work_timer(unsigned long data)
+{
+ wait_queue_head_t *wfo_wq;
+ struct list_head *queue;
+ struct slow_work *work = (struct slow_work *) data;
+ unsigned long flags;
+ bool queued = false, put = false, first = false;
+
+ if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) {
+ wfo_wq = &vslow_work_queue_waits_for_occupation;
+ queue = &vslow_work_queue;
+ } else {
+ wfo_wq = &slow_work_queue_waits_for_occupation;
+ queue = &slow_work_queue;
+ }
+
+ spin_lock_irqsave(&slow_work_queue_lock, flags);
+ if (likely(!test_bit(SLOW_WORK_CANCELLING, &work->flags))) {
+ clear_bit(SLOW_WORK_DELAYED, &work->flags);
+
+ if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) {
+ /* we discard the reference the timer was holding in
+ * favour of the one the executor holds */
+ set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags);
+ put = true;
+ } else {
+ slow_work_mark_time(work);
+ list_add_tail(&work->link, queue);
+ queued = true;
+ if (work->link.prev == queue)
+ first = true;
+ }
+ }
+
+ spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+ if (put)
+ slow_work_put_ref(work);
+ if (first)
+ wake_up(wfo_wq);
+ if (queued)
+ wake_up(&slow_work_thread_wq);
+}
+
+/**
+ * delayed_slow_work_enqueue - Schedule a delayed slow work item for processing
+ * @dwork: The delayed work item to queue
+ * @delay: When to start executing the work, in jiffies from now
+ *
+ * This is similar to slow_work_enqueue(), but it adds a delay before the work
+ * is actually queued for processing.
+ *
+ * The item can have delayed processing requested on it whilst it is being
+ * executed. The delay will begin immediately, and if it expires before the
+ * item finishes executing, the item will be placed back on the queue when it
+ * has done executing.
+ */
+int delayed_slow_work_enqueue(struct delayed_slow_work *dwork,
+ unsigned long delay)
+{
+ struct slow_work *work = &dwork->work;
+ unsigned long flags;
+ int ret;
+
+ if (delay == 0)
+ return slow_work_enqueue(&dwork->work);
+
+ BUG_ON(slow_work_user_count <= 0);
+ BUG_ON(!work);
+ BUG_ON(!work->ops);
+
+ if (test_bit(SLOW_WORK_CANCELLING, &work->flags))
+ return -ECANCELED;
+
+ if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) {
+ spin_lock_irqsave(&slow_work_queue_lock, flags);
+
+ if (test_bit(SLOW_WORK_CANCELLING, &work->flags))
+ goto cancelled;
+
+ /* the timer holds a reference whilst it is pending */
+ ret = work->ops->get_ref(work);
+ if (ret < 0)
+ goto cant_get_ref;
+
+ if (test_and_set_bit(SLOW_WORK_DELAYED, &work->flags))
+ BUG();
+ dwork->timer.expires = jiffies + delay;
+ dwork->timer.data = (unsigned long) work;
+ dwork->timer.function = delayed_slow_work_timer;
+ add_timer(&dwork->timer);
+
+ spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+ }
+
+ return 0;
+
+cancelled:
+ ret = -ECANCELED;
+cant_get_ref:
+ spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+ return ret;
+}
+EXPORT_SYMBOL(delayed_slow_work_enqueue);
+
/*
* Schedule a cull of the thread pool at some time in the near future
*/
*/
static int slow_work_thread(void *_data)
{
- int vsmax;
+ int vsmax, id;
DEFINE_WAIT(wait);
set_freezable();
set_user_nice(current, -5);
+ /* allocate ourselves an ID */
+ spin_lock_irq(&slow_work_queue_lock);
+ id = find_first_zero_bit(slow_work_ids, SLOW_WORK_THREAD_LIMIT);
+ BUG_ON(id < 0 || id >= SLOW_WORK_THREAD_LIMIT);
+ __set_bit(id, slow_work_ids);
+ slow_work_set_thread_pid(id, current->pid);
+ spin_unlock_irq(&slow_work_queue_lock);
+
+ sprintf(current->comm, "kslowd%03u", id);
+
for (;;) {
vsmax = vslow_work_proportion;
vsmax *= atomic_read(&slow_work_thread_count);
vsmax *= atomic_read(&slow_work_thread_count);
vsmax /= 100;
- if (slow_work_available(vsmax) && slow_work_execute()) {
+ if (slow_work_available(vsmax) && slow_work_execute(id)) {
cond_resched();
if (list_empty(&slow_work_queue) &&
list_empty(&vslow_work_queue) &&
break;
}
+ spin_lock_irq(&slow_work_queue_lock);
+ slow_work_set_thread_pid(id, 0);
+ __clear_bit(id, slow_work_ids);
+ spin_unlock_irq(&slow_work_queue_lock);
+
if (atomic_dec_and_test(&slow_work_thread_count))
complete_and_exit(&slow_work_last_thread_exited, 0);
return 0;
wake_up(&slow_work_thread_wq);
}
-/*
- * Get a reference on slow work thread starter
- */
-static int slow_work_new_thread_get_ref(struct slow_work *work)
-{
- return 0;
-}
-
-/*
- * Drop a reference on slow work thread starter
- */
-static void slow_work_new_thread_put_ref(struct slow_work *work)
-{
-}
-
/*
* Start a new slow work thread
*/
}
static const struct slow_work_ops slow_work_new_thread_ops = {
- .get_ref = slow_work_new_thread_get_ref,
- .put_ref = slow_work_new_thread_put_ref,
+ .owner = THIS_MODULE,
.execute = slow_work_new_thread_execute,
+#ifdef CONFIG_SLOW_WORK_DEBUG
+ .desc = slow_work_new_thread_desc,
+#endif
};
/*
/**
* slow_work_register_user - Register a user of the facility
+ * @module: The module about to make use of the facility
*
* Register a user of the facility, starting up the initial threads if there
* aren't any other users at this point. This will return 0 if successful, or
* an error if not.
*/
-int slow_work_register_user(void)
+int slow_work_register_user(struct module *module)
{
struct task_struct *p;
int loop;
}
EXPORT_SYMBOL(slow_work_register_user);
+/*
+ * wait for all outstanding items from the calling module to complete
+ * - note that more items may be queued whilst we're waiting
+ */
+static void slow_work_wait_for_items(struct module *module)
+{
+#ifdef CONFIG_MODULES
+ DECLARE_WAITQUEUE(myself, current);
+ struct slow_work *work;
+ int loop;
+
+ mutex_lock(&slow_work_unreg_sync_lock);
+ add_wait_queue(&slow_work_unreg_wq, &myself);
+
+ for (;;) {
+ spin_lock_irq(&slow_work_queue_lock);
+
+ /* first of all, we wait for the last queued item in each list
+ * to be processed */
+ list_for_each_entry_reverse(work, &vslow_work_queue, link) {
+ if (work->owner == module) {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ slow_work_unreg_work_item = work;
+ goto do_wait;
+ }
+ }
+ list_for_each_entry_reverse(work, &slow_work_queue, link) {
+ if (work->owner == module) {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ slow_work_unreg_work_item = work;
+ goto do_wait;
+ }
+ }
+
+ /* then we wait for the items being processed to finish */
+ slow_work_unreg_module = module;
+ smp_mb();
+ for (loop = 0; loop < SLOW_WORK_THREAD_LIMIT; loop++) {
+ if (slow_work_thread_processing[loop] == module)
+ goto do_wait;
+ }
+ spin_unlock_irq(&slow_work_queue_lock);
+ break; /* okay, we're done */
+
+ do_wait:
+ spin_unlock_irq(&slow_work_queue_lock);
+ schedule();
+ slow_work_unreg_work_item = NULL;
+ slow_work_unreg_module = NULL;
+ }
+
+ remove_wait_queue(&slow_work_unreg_wq, &myself);
+ mutex_unlock(&slow_work_unreg_sync_lock);
+#endif /* CONFIG_MODULES */
+}
+
/**
* slow_work_unregister_user - Unregister a user of the facility
+ * @module: The module whose items should be cleared
*
* Unregister a user of the facility, killing all the threads if this was the
* last one.
+ *
+ * This waits for all the work items belonging to the nominated module to go
+ * away before proceeding.
*/
-void slow_work_unregister_user(void)
+void slow_work_unregister_user(struct module *module)
{
+ /* first of all, wait for all outstanding items from the calling module
+ * to complete */
+ if (module)
+ slow_work_wait_for_items(module);
+
+ /* then we can actually go about shutting down the facility if need
+ * be */
mutex_lock(&slow_work_user_lock);
BUG_ON(slow_work_user_count <= 0);
#ifdef CONFIG_SYSCTL
if (slow_work_max_max_threads < nr_cpus * 2)
slow_work_max_max_threads = nr_cpus * 2;
+#endif
+#ifdef CONFIG_SLOW_WORK_DEBUG
+ {
+ struct dentry *dbdir;
+
+ dbdir = debugfs_create_dir("slow_work", NULL);
+ if (dbdir && !IS_ERR(dbdir))
+ debugfs_create_file("runqueue", S_IFREG | 0400, dbdir,
+ NULL, &slow_work_runqueue_fops);
+ }
#endif
return 0;
}
#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>
#include <linux/sysrq.h>
#include <linux/highuid.h>
#include <linux/writeback.h>
+#include <linux/ratelimit.h>
#include <linux/hugetlb.h>
#include <linux/initrd.h>
#include <linux/key.h>
#include <asm/io.h>
#endif
- static int deprecated_sysctl_warning(struct __sysctl_args *args);
#if defined(CONFIG_SYSCTL)
extern int unaligned_dump_stack;
#endif
+extern struct ratelimit_state printk_ratelimit_state;
+
#ifdef CONFIG_RT_MUTEXES
extern int max_lock_depth;
#endif
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,
* 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
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
.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
.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)
.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,
#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,
#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,
},
{
.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,
},
.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,
},
* 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
.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,
#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,
* 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),
.proc_handler = proc_dointvec
},
#endif
- { .ctl_name = 0 }
+ { }
};
static struct ctl_table dev_table[] = {
- { .ctl_name = 0 }
+ { }
};
static DEFINE_SPINLOCK(sysctl_lock);
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.
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);
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)
*
* 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
*
*
* 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
* 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
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.
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;
#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 :-)
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);