aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Kconfig.locks202
-rw-r--r--kernel/Makefile5
-rw-r--r--kernel/capability.c15
-rw-r--r--kernel/cpu.c5
-rw-r--r--kernel/cpuset.c27
-rw-r--r--kernel/exit.c26
-rw-r--r--kernel/fork.c10
-rw-r--r--kernel/hrtimer.c3
-rw-r--r--kernel/hung_task.c2
-rw-r--r--kernel/irq/chip.c6
-rw-r--r--kernel/irq/manage.c2
-rw-r--r--kernel/irq/proc.c40
-rw-r--r--kernel/irq/spurious.c16
-rw-r--r--kernel/itimer.c7
-rw-r--r--kernel/kgdb.c58
-rw-r--r--kernel/kmod.c8
-rw-r--r--kernel/kprobes.c4
-rw-r--r--kernel/module.c5
-rw-r--r--kernel/mutex.c4
-rw-r--r--kernel/perf_event.c4
-rw-r--r--kernel/pm_qos_params.c20
-rw-r--r--kernel/posix-cpu-timers.c5
-rw-r--r--kernel/power/Makefile2
-rw-r--r--kernel/power/hibernate.c30
-rw-r--r--kernel/power/main.c1
-rw-r--r--kernel/power/process.c14
-rw-r--r--kernel/power/swap.c107
-rw-r--r--kernel/power/swsusp.c130
-rw-r--r--kernel/printk.c7
-rw-r--r--kernel/rcupdate.c122
-rw-r--r--kernel/rcutiny.c282
-rw-r--r--kernel/rcutorture.c65
-rw-r--r--kernel/rcutree.c465
-rw-r--r--kernel/rcutree.h69
-rw-r--r--kernel/rcutree_plugin.h309
-rw-r--r--kernel/rcutree_trace.c12
-rw-r--r--kernel/resource.c26
-rw-r--r--kernel/sched.c278
-rw-r--r--kernel/sched_debug.c4
-rw-r--r--kernel/sched_fair.c65
-rw-r--r--kernel/sched_rt.c61
-rw-r--r--kernel/signal.c46
-rw-r--r--kernel/slow-work-debugfs.c227
-rw-r--r--kernel/slow-work.c519
-rw-r--r--kernel/slow-work.h72
-rw-r--r--kernel/smp.c56
-rw-r--r--kernel/softirq.c2
-rw-r--r--kernel/spinlock.c310
-rw-r--r--kernel/srcu.c74
-rw-r--r--kernel/sys.c35
-rw-r--r--kernel/sys_ni.c3
-rw-r--r--kernel/sysctl.c896
-rw-r--r--kernel/sysctl_binary.c1507
-rw-r--r--kernel/sysctl_check.c1376
-rw-r--r--kernel/time.c31
-rw-r--r--kernel/time/clockevents.c13
-rw-r--r--kernel/time/clocksource.c105
-rw-r--r--kernel/time/tick-oneshot.c4
-rw-r--r--kernel/time/tick-sched.c141
-rw-r--r--kernel/time/timecompare.c6
-rw-r--r--kernel/time/timekeeping.c125
-rw-r--r--kernel/time/timer_list.c10
-rw-r--r--kernel/trace/ftrace.c11
-rw-r--r--kernel/trace/ring_buffer.c9
-rw-r--r--kernel/trace/ring_buffer_benchmark.c85
-rw-r--r--kernel/trace/trace.c41
-rw-r--r--kernel/trace/trace_clock.c8
-rw-r--r--kernel/trace/trace_export.c4
-rw-r--r--kernel/user-return-notifier.c44
-rw-r--r--kernel/utsname_sysctl.c31
-rw-r--r--kernel/workqueue.c159
71 files changed, 5105 insertions, 3368 deletions
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
new file mode 100644
index 00000000000..88c92fb4461
--- /dev/null
+++ b/kernel/Kconfig.locks
@@ -0,0 +1,202 @@
+#
+# The ARCH_INLINE foo is necessary because select ignores "depends on"
+#
+config ARCH_INLINE_SPIN_TRYLOCK
+ bool
+
+config ARCH_INLINE_SPIN_TRYLOCK_BH
+ bool
+
+config ARCH_INLINE_SPIN_LOCK
+ bool
+
+config ARCH_INLINE_SPIN_LOCK_BH
+ bool
+
+config ARCH_INLINE_SPIN_LOCK_IRQ
+ bool
+
+config ARCH_INLINE_SPIN_LOCK_IRQSAVE
+ bool
+
+config ARCH_INLINE_SPIN_UNLOCK
+ bool
+
+config ARCH_INLINE_SPIN_UNLOCK_BH
+ bool
+
+config ARCH_INLINE_SPIN_UNLOCK_IRQ
+ bool
+
+config ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE
+ bool
+
+
+config ARCH_INLINE_READ_TRYLOCK
+ bool
+
+config ARCH_INLINE_READ_LOCK
+ bool
+
+config ARCH_INLINE_READ_LOCK_BH
+ bool
+
+config ARCH_INLINE_READ_LOCK_IRQ
+ bool
+
+config ARCH_INLINE_READ_LOCK_IRQSAVE
+ bool
+
+config ARCH_INLINE_READ_UNLOCK
+ bool
+
+config ARCH_INLINE_READ_UNLOCK_BH
+ bool
+
+config ARCH_INLINE_READ_UNLOCK_IRQ
+ bool
+
+config ARCH_INLINE_READ_UNLOCK_IRQRESTORE
+ bool
+
+
+config ARCH_INLINE_WRITE_TRYLOCK
+ bool
+
+config ARCH_INLINE_WRITE_LOCK
+ bool
+
+config ARCH_INLINE_WRITE_LOCK_BH
+ bool
+
+config ARCH_INLINE_WRITE_LOCK_IRQ
+ bool
+
+config ARCH_INLINE_WRITE_LOCK_IRQSAVE
+ bool
+
+config ARCH_INLINE_WRITE_UNLOCK
+ bool
+
+config ARCH_INLINE_WRITE_UNLOCK_BH
+ bool
+
+config ARCH_INLINE_WRITE_UNLOCK_IRQ
+ bool
+
+config ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
+ bool
+
+#
+# lock_* functions are inlined when:
+# - DEBUG_SPINLOCK=n and GENERIC_LOCKBREAK=n and ARCH_INLINE_*LOCK=y
+#
+# trylock_* functions are inlined when:
+# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
+#
+# unlock and unlock_irq functions are inlined when:
+# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
+# or
+# - DEBUG_SPINLOCK=n and PREEMPT=n
+#
+# unlock_bh and unlock_irqrestore functions are inlined when:
+# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
+#
+
+config INLINE_SPIN_TRYLOCK
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_TRYLOCK
+
+config INLINE_SPIN_TRYLOCK_BH
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_TRYLOCK_BH
+
+config INLINE_SPIN_LOCK
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK
+
+config INLINE_SPIN_LOCK_BH
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_SPIN_LOCK_BH
+
+config INLINE_SPIN_LOCK_IRQ
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_SPIN_LOCK_IRQ
+
+config INLINE_SPIN_LOCK_IRQSAVE
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_SPIN_LOCK_IRQSAVE
+
+config INLINE_SPIN_UNLOCK
+ def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK)
+
+config INLINE_SPIN_UNLOCK_BH
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_BH
+
+config INLINE_SPIN_UNLOCK_IRQ
+ def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK_BH)
+
+config INLINE_SPIN_UNLOCK_IRQRESTORE
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE
+
+
+config INLINE_READ_TRYLOCK
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_TRYLOCK
+
+config INLINE_READ_LOCK
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK
+
+config INLINE_READ_LOCK_BH
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_READ_LOCK_BH
+
+config INLINE_READ_LOCK_IRQ
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_READ_LOCK_IRQ
+
+config INLINE_READ_LOCK_IRQSAVE
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_READ_LOCK_IRQSAVE
+
+config INLINE_READ_UNLOCK
+ def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_READ_UNLOCK)
+
+config INLINE_READ_UNLOCK_BH
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_UNLOCK_BH
+
+config INLINE_READ_UNLOCK_IRQ
+ def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_READ_UNLOCK_BH)
+
+config INLINE_READ_UNLOCK_IRQRESTORE
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_UNLOCK_IRQRESTORE
+
+
+config INLINE_WRITE_TRYLOCK
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_TRYLOCK
+
+config INLINE_WRITE_LOCK
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK
+
+config INLINE_WRITE_LOCK_BH
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_WRITE_LOCK_BH
+
+config INLINE_WRITE_LOCK_IRQ
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_WRITE_LOCK_IRQ
+
+config INLINE_WRITE_LOCK_IRQSAVE
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_WRITE_LOCK_IRQSAVE
+
+config INLINE_WRITE_UNLOCK
+ def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_WRITE_UNLOCK)
+
+config INLINE_WRITE_UNLOCK_BH
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_BH
+
+config INLINE_WRITE_UNLOCK_IRQ
+ def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_WRITE_UNLOCK_BH)
+
+config INLINE_WRITE_UNLOCK_IRQRESTORE
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
+
+config MUTEX_SPIN_ON_OWNER
+ def_bool SMP && !DEBUG_MUTEXES && !HAVE_DEFAULT_NO_SPIN_MUTEXES
diff --git a/kernel/Makefile b/kernel/Makefile
index 6b7ce8173df..864ff75d65f 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 \
@@ -83,6 +83,7 @@ obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
obj-$(CONFIG_TREE_RCU) += rcutree.o
obj-$(CONFIG_TREE_PREEMPT_RCU) += rcutree.o
obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o
+obj-$(CONFIG_TINY_RCU) += rcutiny.o
obj-$(CONFIG_RELAY) += relay.o
obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
@@ -95,8 +96,10 @@ obj-$(CONFIG_X86_DS) += trace/
obj-$(CONFIG_RING_BUFFER) += trace/
obj-$(CONFIG_SMP) += sched_cpupri.o
obj-$(CONFIG_SLOW_WORK) += slow-work.o
+obj-$(CONFIG_SLOW_WORK_DEBUG) += slow-work-debugfs.o
obj-$(CONFIG_PERF_EVENTS) += perf_event.o
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
+obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/capability.c b/kernel/capability.c
index 4e17041963f..7f876e60521 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -29,7 +29,6 @@ EXPORT_SYMBOL(__cap_empty_set);
EXPORT_SYMBOL(__cap_full_set);
EXPORT_SYMBOL(__cap_init_eff_set);
-#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
int file_caps_enabled = 1;
static int __init file_caps_disable(char *str)
@@ -38,7 +37,6 @@ static int __init file_caps_disable(char *str)
return 1;
}
__setup("no_file_caps", file_caps_disable);
-#endif
/*
* More recent versions of libcap are available from:
@@ -169,8 +167,8 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr)
kernel_cap_t pE, pI, pP;
ret = cap_validate_magic(header, &tocopy);
- if (ret != 0)
- return ret;
+ if ((dataptr == NULL) || (ret != 0))
+ return ((dataptr == NULL) && (ret == -EINVAL)) ? 0 : ret;
if (get_user(pid, &header->pid))
return -EFAULT;
@@ -238,7 +236,7 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr)
SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
{
struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
- unsigned i, tocopy;
+ unsigned i, tocopy, copybytes;
kernel_cap_t inheritable, permitted, effective;
struct cred *new;
int ret;
@@ -255,8 +253,11 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
if (pid != 0 && pid != task_pid_vnr(current))
return -EPERM;
- if (copy_from_user(&kdata, data,
- tocopy * sizeof(struct __user_cap_data_struct)))
+ copybytes = tocopy * sizeof(struct __user_cap_data_struct);
+ if (copybytes > sizeof(kdata))
+ return -EFAULT;
+
+ if (copy_from_user(&kdata, data, copybytes))
return -EFAULT;
for (i = 0; i < tocopy; i++) {
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 6ba0f1ecb21..7c4e2713df0 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -392,10 +392,9 @@ int disable_nonboot_cpus(void)
if (cpu == first_cpu)
continue;
error = _cpu_down(cpu, 1);
- if (!error) {
+ if (!error)
cpumask_set_cpu(cpu, frozen_cpus);
- printk("CPU%d is down\n", cpu);
- } else {
+ else {
printk(KERN_ERR "Error taking CPU%d down: %d\n",
cpu, error);
break;
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index b5cb469d254..3cf2183b472 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -537,8 +537,7 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c)
* element of the partition (one sched domain) to be passed to
* partition_sched_domains().
*/
-/* FIXME: see the FIXME in partition_sched_domains() */
-static int generate_sched_domains(struct cpumask **domains,
+static int generate_sched_domains(cpumask_var_t **domains,
struct sched_domain_attr **attributes)
{
LIST_HEAD(q); /* queue of cpusets to be scanned */
@@ -546,7 +545,7 @@ static int generate_sched_domains(struct cpumask **domains,
struct cpuset **csa; /* array of all cpuset ptrs */
int csn; /* how many cpuset ptrs in csa so far */
int i, j, k; /* indices for partition finding loops */
- struct cpumask *doms; /* resulting partition; i.e. sched domains */
+ cpumask_var_t *doms; /* resulting partition; i.e. sched domains */
struct sched_domain_attr *dattr; /* attributes for custom domains */
int ndoms = 0; /* number of sched domains in result */
int nslot; /* next empty doms[] struct cpumask slot */
@@ -557,7 +556,8 @@ static int generate_sched_domains(struct cpumask **domains,
/* Special case for the 99% of systems with one, full, sched domain */
if (is_sched_load_balance(&top_cpuset)) {
- doms = kmalloc(cpumask_size(), GFP_KERNEL);
+ ndoms = 1;
+ doms = alloc_sched_domains(ndoms);
if (!doms)
goto done;
@@ -566,9 +566,8 @@ static int generate_sched_domains(struct cpumask **domains,
*dattr = SD_ATTR_INIT;
update_domain_attr_tree(dattr, &top_cpuset);
}
- cpumask_copy(doms, top_cpuset.cpus_allowed);
+ cpumask_copy(doms[0], top_cpuset.cpus_allowed);
- ndoms = 1;
goto done;
}
@@ -636,7 +635,7 @@ restart:
* Now we know how many domains to create.
* Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
*/
- doms = kmalloc(ndoms * cpumask_size(), GFP_KERNEL);
+ doms = alloc_sched_domains(ndoms);
if (!doms)
goto done;
@@ -656,7 +655,7 @@ restart:
continue;
}
- dp = doms + nslot;
+ dp = doms[nslot];
if (nslot == ndoms) {
static int warnings = 10;
@@ -718,7 +717,7 @@ done:
static void do_rebuild_sched_domains(struct work_struct *unused)
{
struct sched_domain_attr *attr;
- struct cpumask *doms;
+ cpumask_var_t *doms;
int ndoms;
get_online_cpus();
@@ -2052,7 +2051,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
unsigned long phase, void *unused_cpu)
{
struct sched_domain_attr *attr;
- struct cpumask *doms;
+ cpumask_var_t *doms;
int ndoms;
switch (phase) {
@@ -2537,15 +2536,9 @@ const struct file_operations proc_cpuset_operations = {
};
#endif /* CONFIG_PROC_PID_CPUSET */
-/* Display task cpus_allowed, mems_allowed in /proc/<pid>/status file. */
+/* Display task mems_allowed in /proc/<pid>/status file. */
void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task)
{
- seq_printf(m, "Cpus_allowed:\t");
- seq_cpumask(m, &task->cpus_allowed);
- seq_printf(m, "\n");
- seq_printf(m, "Cpus_allowed_list:\t");
- seq_cpumask_list(m, &task->cpus_allowed);
- seq_printf(m, "\n");
seq_printf(m, "Mems_allowed:\t");
seq_nodemask(m, &task->mems_allowed);
seq_printf(m, "\n");
diff --git a/kernel/exit.c b/kernel/exit.c
index 3f45e3cf931..6f50ef55a6f 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -111,9 +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;
@@ -971,7 +971,7 @@ NORET_TYPE void do_exit(long code)
exit_thread();
cgroup_exit(tsk, 1);
- if (group_dead && tsk->signal->leader)
+ if (group_dead)
disassociate_ctty(1);
module_put(task_thread_info(tsk)->exec_domain->module);
@@ -1009,7 +1009,7 @@ NORET_TYPE void do_exit(long code)
tsk->flags |= PF_EXITPIDONE;
if (tsk->io_context)
- exit_io_context();
+ exit_io_context(tsk);
if (tsk->splice_pipe)
__free_pipe_info(tsk->splice_pipe);
@@ -1210,6 +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
@@ -1225,20 +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 166b8c49257..1415dc4598a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -64,6 +64,7 @@
#include <linux/magic.h>
#include <linux/perf_event.h>
#include <linux/posix-timers.h>
+#include <linux/user-return-notifier.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -249,6 +250,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
goto out;
setup_thread_stack(tsk, orig);
+ clear_user_return_notifier(tsk);
stackend = end_of_stack(tsk);
*stackend = STACK_END_MAGIC; /* for overflow detection */
@@ -884,6 +886,9 @@ 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 +1071,10 @@ 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;
@@ -1310,7 +1317,8 @@ bad_fork_free_pid:
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_io:
- put_io_context(p->io_context);
+ if (p->io_context)
+ exit_io_context(p);
bad_fork_cleanup_namespaces:
exit_task_namespaces(p);
bad_fork_cleanup_mm:
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 3e1c36e7998..ede52770812 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1238,7 +1238,8 @@ hrtimer_interrupt_hanging(struct clock_event_device *dev,
force_clock_reprogram = 1;
dev->min_delta_ns = (unsigned long)try_time.tv64 * 3;
printk(KERN_WARNING "hrtimer: interrupt too slow, "
- "forcing clock min delta to %lu ns\n", dev->min_delta_ns);
+ "forcing clock min delta to %llu ns\n",
+ (unsigned long long) dev->min_delta_ns);
}
/*
* High resolution timer interrupt
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index d4e84174740..0c642d51aac 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -144,7 +144,7 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
rcu_read_lock();
do_each_thread(g, t) {
- if (!--max_count)
+ if (!max_count--)
goto unlock;
if (!--batch_count) {
batch_count = HUNG_TASK_BATCHING;
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index c1660194d11..ba566c261ad 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -166,11 +166,11 @@ int set_irq_data(unsigned int irq, void *data)
EXPORT_SYMBOL(set_irq_data);
/**
- * set_irq_data - set irq type data for an irq
+ * set_irq_msi - set MSI descriptor data for an irq
* @irq: Interrupt number
* @entry: Pointer to MSI descriptor data
*
- * Set the hardware irq controller data for an irq
+ * Set the MSI descriptor entry for an irq
*/
int set_irq_msi(unsigned int irq, struct msi_desc *entry)
{
@@ -590,7 +590,7 @@ out_unlock:
}
/**
- * handle_percpu_IRQ - Per CPU local irq handler
+ * handle_percpu_irq - Per CPU local irq handler
* @irq: the interrupt number
* @desc: the interrupt description structure for this irq
*
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index bde4c667d24..7305b297d1e 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1067,7 +1067,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
kfree(action);
#ifdef CONFIG_DEBUG_SHIRQ
- if (irqflags & IRQF_SHARED) {
+ if (!retval && (irqflags & IRQF_SHARED)) {
/*
* It's a shared IRQ -- the driver ought to be prepared for it
* to happen immediately, so let's make sure....
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 692363dd591..0832145fea9 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -136,7 +136,7 @@ out:
static int default_affinity_open(struct inode *inode, struct file *file)
{
- return single_open(file, default_affinity_show, NULL);
+ return single_open(file, default_affinity_show, PDE(inode)->data);
}
static const struct file_operations default_affinity_proc_fops = {
@@ -148,18 +148,28 @@ static const struct file_operations default_affinity_proc_fops = {
};
#endif
-static int irq_spurious_read(char *page, char **start, off_t off,
- int count, int *eof, void *data)
+static int irq_spurious_proc_show(struct seq_file *m, void *v)
{
- struct irq_desc *desc = irq_to_desc((long) data);
- return sprintf(page, "count %u\n"
- "unhandled %u\n"
- "last_unhandled %u ms\n",
- desc->irq_count,
- desc->irqs_unhandled,
- jiffies_to_msecs(desc->last_unhandled));
+ struct irq_desc *desc = irq_to_desc((long) m->private);
+
+ seq_printf(m, "count %u\n" "unhandled %u\n" "last_unhandled %u ms\n",
+ desc->irq_count, desc->irqs_unhandled,
+ jiffies_to_msecs(desc->last_unhandled));
+ return 0;
+}
+
+static int irq_spurious_proc_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, irq_spurious_proc_show, NULL);
}
+static const struct file_operations irq_spurious_proc_fops = {
+ .open = irq_spurious_proc_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
#define MAX_NAMELEN 128
static int name_unique(unsigned int irq, struct irqaction *new_action)
@@ -204,7 +214,6 @@ void register_handler_proc(unsigned int irq, struct irqaction *action)
void register_irq_proc(unsigned int irq, struct irq_desc *desc)
{
char name [MAX_NAMELEN];
- struct proc_dir_entry *entry;
if (!root_irq_dir || (desc->chip == &no_irq_chip) || desc->dir)
return;
@@ -214,6 +223,8 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
/* create /proc/irq/1234 */
desc->dir = proc_mkdir(name, root_irq_dir);
+ if (!desc->dir)
+ return;
#ifdef CONFIG_SMP
/* create /proc/irq/<irq>/smp_affinity */
@@ -221,11 +232,8 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
&irq_affinity_proc_fops, (void *)(long)irq);
#endif
- entry = create_proc_entry("spurious", 0444, desc->dir);
- if (entry) {
- entry->data = (void *)(long)irq;
- entry->read_proc = irq_spurious_read;
- }
+ proc_create_data("spurious", 0444, desc->dir,
+ &irq_spurious_proc_fops, (void *)(long)irq);
}
#undef MAX_NAMELEN
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index bd7273e6282..e49ea1c5232 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -104,7 +104,7 @@ static int misrouted_irq(int irq)
return ok;
}
-static void poll_all_shared_irqs(void)
+static void poll_spurious_irqs(unsigned long dummy)
{
struct irq_desc *desc;
int i;
@@ -125,23 +125,11 @@ static void poll_all_shared_irqs(void)
try_one_irq(i, desc);
local_irq_enable();
}
-}
-
-static void poll_spurious_irqs(unsigned long dummy)
-{
- poll_all_shared_irqs();
mod_timer(&poll_spurious_irq_timer,
jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
}
-#ifdef CONFIG_DEBUG_SHIRQ
-void debug_poll_all_shared_irqs(void)
-{
- poll_all_shared_irqs();
-}
-#endif
-
/*
* If 99,900 of the previous 100,000 interrupts have not been handled
* then assume that the IRQ is stuck in some manner. Drop a diagnostic
@@ -232,7 +220,7 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
/*
* If we are seeing only the odd spurious IRQ caused by
* bus asynchronicity then don't eventually trigger an error,
- * otherwise the couter becomes a doomsday timer for otherwise
+ * otherwise the counter becomes a doomsday timer for otherwise
* working systems
*/
if (time_after(jiffies, desc->last_unhandled + HZ/10))
diff --git a/kernel/itimer.c b/kernel/itimer.c
index b03451ede52..d802883153d 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -146,6 +146,7 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
{
cputime_t cval, nval, cinterval, ninterval;
s64 ns_ninterval, ns_nval;
+ u32 error, incr_error;
struct cpu_itimer *it = &tsk->signal->it[clock_id];
nval = timeval_to_cputime(&value->it_value);
@@ -153,8 +154,8 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
ninterval = timeval_to_cputime(&value->it_interval);
ns_ninterval = timeval_to_ns(&value->it_interval);
- it->incr_error = cputime_sub_ns(ninterval, ns_ninterval);
- it->error = cputime_sub_ns(nval, ns_nval);
+ error = cputime_sub_ns(nval, ns_nval);
+ incr_error = cputime_sub_ns(ninterval, ns_ninterval);
spin_lock_irq(&tsk->sighand->siglock);
@@ -168,6 +169,8 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
}
it->expires = nval;
it->incr = ninterval;
+ it->error = error;
+ it->incr_error = incr_error;
trace_itimer_state(clock_id == CPUCLOCK_VIRT ?
ITIMER_VIRTUAL : ITIMER_PROF, value, nval);
diff --git a/kernel/kgdb.c b/kernel/kgdb.c
index 9147a3190c9..2eb517e2351 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -129,6 +129,7 @@ struct task_struct *kgdb_usethread;
struct task_struct *kgdb_contthread;
int kgdb_single_step;
+pid_t kgdb_sstep_pid;
/* Our I/O buffers. */
static char remcom_in_buffer[BUFMAX];
@@ -541,12 +542,17 @@ static struct task_struct *getthread(struct pt_regs *regs, int tid)
*/
if (tid == 0 || tid == -1)
tid = -atomic_read(&kgdb_active) - 2;
- if (tid < 0) {
+ if (tid < -1 && tid > -NR_CPUS - 2) {
if (kgdb_info[-tid - 2].task)
return kgdb_info[-tid - 2].task;
else
return idle_task(-tid - 2);
}
+ if (tid <= 0) {
+ printk(KERN_ERR "KGDB: Internal thread select error\n");
+ dump_stack();
+ return NULL;
+ }
/*
* find_task_by_pid_ns() does not take the tasklist lock anymore
@@ -619,7 +625,8 @@ static void kgdb_flush_swbreak_addr(unsigned long addr)
static int kgdb_activate_sw_breakpoints(void)
{
unsigned long addr;
- int error = 0;
+ int error;
+ int ret = 0;
int i;
for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
@@ -629,13 +636,16 @@ static int kgdb_activate_sw_breakpoints(void)
addr = kgdb_break[i].bpt_addr;
error = kgdb_arch_set_breakpoint(addr,
kgdb_break[i].saved_instr);
- if (error)
- return error;
+ if (error) {
+ ret = error;
+ printk(KERN_INFO "KGDB: BP install failed: %lx", addr);
+ continue;
+ }
kgdb_flush_swbreak_addr(addr);
kgdb_break[i].state = BP_ACTIVE;
}
- return 0;
+ return ret;
}
static int kgdb_set_sw_break(unsigned long addr)
@@ -682,7 +692,8 @@ static int kgdb_set_sw_break(unsigned long addr)
static int kgdb_deactivate_sw_breakpoints(void)
{
unsigned long addr;
- int error = 0;
+ int error;
+ int ret = 0;
int i;
for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
@@ -691,13 +702,15 @@ static int kgdb_deactivate_sw_breakpoints(void)
addr = kgdb_break[i].bpt_addr;
error = kgdb_arch_remove_breakpoint(addr,
kgdb_break[i].saved_instr);
- if (error)
- return error;
+ if (error) {
+ printk(KERN_INFO "KGDB: BP remove failed: %lx\n", addr);
+ ret = error;
+ }
kgdb_flush_swbreak_addr(addr);
kgdb_break[i].state = BP_SET;
}
- return 0;
+ return ret;
}
static int kgdb_remove_sw_break(unsigned long addr)
@@ -870,7 +883,7 @@ 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) {
@@ -1204,8 +1217,10 @@ static int gdb_cmd_exception_pass(struct kgdb_state *ks)
return 1;
} else {
- error_packet(remcom_out_buffer, -EINVAL);
- return 0;
+ kgdb_msg_write("KGDB only knows signal 9 (pass)"
+ " and 15 (pass and disconnect)\n"
+ "Executing a continue without signal passing\n", 0);
+ remcom_in_buffer[0] = 'c';
}
/* Indicate fall through */
@@ -1395,6 +1410,7 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
struct kgdb_state kgdb_var;
struct kgdb_state *ks = &kgdb_var;
unsigned long flags;
+ int sstep_tries = 100;
int error = 0;
int i, cpu;
@@ -1425,13 +1441,14 @@ acquirelock:
cpu_relax();
/*
- * Do not start the debugger connection on this CPU if the last
- * instance of the exception handler wanted to come into the
- * debugger on a different CPU via a single step
+ * For single stepping, try to only enter on the processor
+ * that was single stepping. To gaurd against a deadlock, the
+ * kernel will only try for the value of sstep_tries before
+ * giving up and continuing on.
*/
if (atomic_read(&kgdb_cpu_doing_single_step) != -1 &&
- atomic_read(&kgdb_cpu_doing_single_step) != cpu) {
-
+ (kgdb_info[cpu].task &&
+ kgdb_info[cpu].task->pid != kgdb_sstep_pid) && --sstep_tries) {
atomic_set(&kgdb_active, -1);
touch_softlockup_watchdog();
clocksource_touch_watchdog();
@@ -1524,6 +1541,13 @@ acquirelock:
}
kgdb_restore:
+ if (atomic_read(&kgdb_cpu_doing_single_step) != -1) {
+ int sstep_cpu = atomic_read(&kgdb_cpu_doing_single_step);
+ if (kgdb_info[sstep_cpu].task)
+ kgdb_sstep_pid = kgdb_info[sstep_cpu].task->pid;
+ else
+ kgdb_sstep_pid = 0;
+ }
/* Free kgdb_active */
atomic_set(&kgdb_active, -1);
touch_softlockup_watchdog();
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 9fcb53a11f8..25b10319036 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -80,16 +80,16 @@ int __request_module(bool wait, const char *fmt, ...)
#define MAX_KMOD_CONCURRENT 50 /* Completely arbitrary value - KAO */
static int kmod_loop_msg;
- ret = security_kernel_module_request();
- if (ret)
- return ret;
-
va_start(args, fmt);
ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args);
va_end(args);
if (ret >= MODULE_NAME_LEN)
return -ENAMETOOLONG;
+ ret = security_kernel_module_request(module_name);
+ if (ret)
+ return ret;
+
/* If modprobe needs a service that is in a module, we get a recursive
* loop. Limit the number of running kmod threads to max_threads/2 or
* MAX_KMOD_CONCURRENT, whichever is the smaller. A cleaner method
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 84495958e70..e5342a344c4 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1035,9 +1035,9 @@ int __kprobes register_kretprobe(struct kretprobe *rp)
/* Pre-allocate memory for max kretprobe instances */
if (rp->maxactive <= 0) {
#ifdef CONFIG_PREEMPT
- rp->maxactive = max(10, 2 * NR_CPUS);
+ rp->maxactive = max(10, 2 * num_possible_cpus());
#else
- rp->maxactive = NR_CPUS;
+ rp->maxactive = num_possible_cpus();
#endif
}
spin_lock_init(&rp->lock);
diff --git a/kernel/module.c b/kernel/module.c
index 8b7d8805819..5842a71cf05 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1187,7 +1187,8 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect,
/* Count loaded sections and allocate structures */
for (i = 0; i < nsect; i++)
- if (sechdrs[i].sh_flags & SHF_ALLOC)
+ if (sechdrs[i].sh_flags & SHF_ALLOC
+ && sechdrs[i].sh_size)
nloaded++;
size[0] = ALIGN(sizeof(*sect_attrs)
+ nloaded * sizeof(sect_attrs->attrs[0]),
@@ -1207,6 +1208,8 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect,
for (i = 0; i < nsect; i++) {
if (! (sechdrs[i].sh_flags & SHF_ALLOC))
continue;
+ if (!sechdrs[i].sh_size)
+ continue;
sattr->address = sechdrs[i].sh_addr;
sattr->name = kstrdup(secstrings + sechdrs[i].sh_name,
GFP_KERNEL);
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 947b3ad551f..632f04c57d8 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -148,8 +148,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
preempt_disable();
mutex_acquire(&lock->dep_map, subclass, 0, ip);
-#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES) && \
- !defined(CONFIG_HAVE_DEFAULT_NO_SPIN_MUTEXES)
+
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
/*
* Optimistic spinning.
*
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index d891ec4a810..e73e53c7582 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -476,7 +476,7 @@ static void perf_event_remove_from_context(struct perf_event *event)
if (!task) {
/*
* Per cpu events are removed via an smp call and
- * the removal is always sucessful.
+ * the removal is always successful.
*/
smp_call_function_single(event->cpu,
__perf_event_remove_from_context,
@@ -845,7 +845,7 @@ perf_install_in_context(struct perf_event_context *ctx,
if (!task) {
/*
* Per cpu events are installed via an smp call and
- * the install is always sucessful.
+ * the install is always successful.
*/
smp_call_function_single(cpu, __perf_install_in_context,
event, 1);
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index dfdec524d1b..3db49b9ca37 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -29,7 +29,6 @@
#include <linux/pm_qos_params.h>
#include <linux/sched.h>
-#include <linux/smp_lock.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/time.h>
@@ -344,37 +343,33 @@ int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier)
}
EXPORT_SYMBOL_GPL(pm_qos_remove_notifier);
-#define PID_NAME_LEN sizeof("process_1234567890")
-static char name[PID_NAME_LEN];
+#define PID_NAME_LEN 32
static int pm_qos_power_open(struct inode *inode, struct file *filp)
{
int ret;
long pm_qos_class;
+ char name[PID_NAME_LEN];
- lock_kernel();
pm_qos_class = find_pm_qos_object_by_minor(iminor(inode));
if (pm_qos_class >= 0) {
filp->private_data = (void *)pm_qos_class;
- sprintf(name, "process_%d", current->pid);
+ snprintf(name, PID_NAME_LEN, "process_%d", current->pid);
ret = pm_qos_add_requirement(pm_qos_class, name,
PM_QOS_DEFAULT_VALUE);
- if (ret >= 0) {
- unlock_kernel();
+ if (ret >= 0)
return 0;
- }
}
- unlock_kernel();
-
return -EPERM;
}
static int pm_qos_power_release(struct inode *inode, struct file *filp)
{
int pm_qos_class;
+ char name[PID_NAME_LEN];
pm_qos_class = (long)filp->private_data;
- sprintf(name, "process_%d", current->pid);
+ snprintf(name, PID_NAME_LEN, "process_%d", current->pid);
pm_qos_remove_requirement(pm_qos_class, name);
return 0;
@@ -385,13 +380,14 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
{
s32 value;
int pm_qos_class;
+ char name[PID_NAME_LEN];
pm_qos_class = (long)filp->private_data;
if (count != sizeof(s32))
return -EINVAL;
if (copy_from_user(&value, buf, sizeof(s32)))
return -EFAULT;
- sprintf(name, "process_%d", current->pid);
+ snprintf(name, PID_NAME_LEN, "process_%d", current->pid);
pm_qos_update_requirement(pm_qos_class, name, value);
return sizeof(s32);
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 5c9dc228747..438ff452351 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -384,7 +384,8 @@ int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
/*
* Validate the clockid_t for a new CPU-clock timer, and initialize the timer.
- * This is called from sys_timer_create with the new timer already locked.
+ * This is called from sys_timer_create() and do_cpu_nanosleep() with the
+ * new timer already all-zeros initialized.
*/
int posix_cpu_timer_create(struct k_itimer *new_timer)
{
@@ -396,8 +397,6 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
return -EINVAL;
INIT_LIST_HEAD(&new_timer->it.cpu.entry);
- new_timer->it.cpu.incr.sched = 0;
- new_timer->it.cpu.expires.sched = 0;
read_lock(&tasklist_lock);
if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) {
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index c3b81c30e5d..43191815f87 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -8,7 +8,7 @@ obj-$(CONFIG_PM_SLEEP) += console.o
obj-$(CONFIG_FREEZER) += process.o
obj-$(CONFIG_SUSPEND) += suspend.o
obj-$(CONFIG_PM_TEST_SUSPEND) += suspend_test.o
-obj-$(CONFIG_HIBERNATION) += swsusp.o hibernate.o snapshot.o swap.o user.o
+obj-$(CONFIG_HIBERNATION) += hibernate.o snapshot.o swap.o user.o
obj-$(CONFIG_HIBERNATION_NVS) += hibernate_nvs.o
obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 04a9e90d248..bbfe472d752 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -32,6 +32,7 @@ static int noresume = 0;
static char resume_file[256] = CONFIG_PM_STD_PARTITION;
dev_t swsusp_resume_device;
sector_t swsusp_resume_block;
+int in_suspend __nosavedata = 0;
enum {
HIBERNATION_INVALID,
@@ -202,6 +203,35 @@ static void platform_recover(int platform_mode)
}
/**
+ * swsusp_show_speed - print the time elapsed between two events.
+ * @start: Starting event.
+ * @stop: Final event.
+ * @nr_pages - number of pages processed between @start and @stop
+ * @msg - introductory message to print
+ */
+
+void swsusp_show_speed(struct timeval *start, struct timeval *stop,
+ unsigned nr_pages, char *msg)
+{
+ s64 elapsed_centisecs64;
+ int centisecs;
+ int k;
+ int kps;
+
+ elapsed_centisecs64 = timeval_to_ns(stop) - timeval_to_ns(start);
+ do_div(elapsed_centisecs64, NSEC_PER_SEC / 100);
+ centisecs = elapsed_centisecs64;
+ if (centisecs == 0)
+ centisecs = 1; /* avoid div-by-zero */
+ k = nr_pages * (PAGE_SIZE / 1024);
+ kps = (k * 100) / centisecs;
+ printk(KERN_INFO "PM: %s %d kbytes in %d.%02d seconds (%d.%02d MB/s)\n",
+ msg, k,
+ centisecs / 100, centisecs % 100,
+ kps / 1000, (kps % 1000) / 10);
+}
+
+/**
* create_image - freeze devices that need to be frozen with interrupts
* off, create the hibernation image and thaw those devices. Control
* reappears in this routine after a restore.
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 347d2cc88cd..0998c713905 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -220,6 +220,7 @@ static struct attribute_group attr_group = {
#ifdef CONFIG_PM_RUNTIME
struct workqueue_struct *pm_wq;
+EXPORT_SYMBOL_GPL(pm_wq);
static int __init pm_start_workqueue(void)
{
diff --git a/kernel/power/process.c b/kernel/power/process.c
index cc2e55373b6..5ade1bdcf36 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -14,6 +14,7 @@
#include <linux/module.h>
#include <linux/syscalls.h>
#include <linux/freezer.h>
+#include <linux/delay.h>
/*
* Timeout for stopping processes
@@ -41,7 +42,7 @@ static int try_to_freeze_tasks(bool sig_only)
do_gettimeofday(&start);
end_time = jiffies + TIMEOUT;
- do {
+ while (true) {
todo = 0;
read_lock(&tasklist_lock);
do_each_thread(g, p) {
@@ -62,10 +63,15 @@ static int try_to_freeze_tasks(bool sig_only)
todo++;
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
- yield(); /* Yield is okay here */
- if (time_after(jiffies, end_time))
+ if (!todo || time_after(jiffies, end_time))
break;
- } while (todo);
+
+ /*
+ * We need to retry, but first give the freezing tasks some
+ * time to enter the regrigerator.
+ */
+ msleep(10);
+ }
do_gettimeofday(&end);
elapsed_csecs64 = timeval_to_ns(&end) - timeval_to_ns(&start);
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 890f6b11b1d..09b2b0ae9e9 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -38,6 +38,107 @@ struct swsusp_header {
static struct swsusp_header *swsusp_header;
+/**
+ * The following functions are used for tracing the allocated
+ * swap pages, so that they can be freed in case of an error.
+ */
+
+struct swsusp_extent {
+ struct rb_node node;
+ unsigned long start;
+ unsigned long end;
+};
+
+static struct rb_root swsusp_extents = RB_ROOT;
+
+static int swsusp_extents_insert(unsigned long swap_offset)
+{
+ struct rb_node **new = &(swsusp_extents.rb_node);
+ struct rb_node *parent = NULL;
+ struct swsusp_extent *ext;
+
+ /* Figure out where to put the new node */
+ while (*new) {
+ ext = container_of(*new, struct swsusp_extent, node);
+ parent = *new;
+ if (swap_offset < ext->start) {
+ /* Try to merge */
+ if (swap_offset == ext->start - 1) {
+ ext->start--;
+ return 0;
+ }
+ new = &((*new)->rb_left);
+ } else if (swap_offset > ext->end) {
+ /* Try to merge */
+ if (swap_offset == ext->end + 1) {
+ ext->end++;
+ return 0;
+ }
+ new = &((*new)->rb_right);
+ } else {
+ /* It already is in the tree */
+ return -EINVAL;
+ }
+ }
+ /* Add the new node and rebalance the tree. */
+ ext = kzalloc(sizeof(struct swsusp_extent), GFP_KERNEL);
+ if (!ext)
+ return -ENOMEM;
+
+ ext->start = swap_offset;
+ ext->end = swap_offset;
+ rb_link_node(&ext->node, parent, new);
+ rb_insert_color(&ext->node, &swsusp_extents);
+ return 0;
+}
+
+/**
+ * alloc_swapdev_block - allocate a swap page and register that it has
+ * been allocated, so that it can be freed in case of an error.
+ */
+
+sector_t alloc_swapdev_block(int swap)
+{
+ unsigned long offset;
+
+ offset = swp_offset(get_swap_page_of_type(swap));
+ if (offset) {
+ if (swsusp_extents_insert(offset))
+ swap_free(swp_entry(swap, offset));
+ else
+ return swapdev_block(swap, offset);
+ }
+ return 0;
+}
+
+/**
+ * free_all_swap_pages - free swap pages allocated for saving image data.
+ * It also frees the extents used to register which swap entres had been
+ * allocated.
+ */
+
+void free_all_swap_pages(int swap)
+{
+ struct rb_node *node;
+
+ while ((node = swsusp_extents.rb_node)) {
+ struct swsusp_extent *ext;
+ unsigned long offset;
+
+ ext = container_of(node, struct swsusp_extent, node);
+ rb_erase(node, &swsusp_extents);
+ for (offset = ext->start; offset <= ext->end; offset++)
+ swap_free(swp_entry(swap, offset));
+
+ kfree(ext);
+ }
+}
+
+int swsusp_swap_in_use(void)
+{
+ return (swsusp_extents.rb_node != NULL);
+}
+
/*
* General things
*/
@@ -336,7 +437,7 @@ static int save_image(struct swap_map_handle *handle,
if (ret)
break;
if (!(nr_pages % m))
- printk("\b\b\b\b%3d%%", nr_pages / m);
+ printk(KERN_CONT "\b\b\b\b%3d%%", nr_pages / m);
nr_pages++;
}
err2 = wait_on_bio_chain(&bio);
@@ -344,9 +445,9 @@ static int save_image(struct swap_map_handle *handle,
if (!ret)
ret = err2;
if (!ret)
- printk("\b\b\b\bdone\n");
+ printk(KERN_CONT "\b\b\b\bdone\n");
else
- printk("\n");
+ printk(KERN_CONT "\n");
swsusp_show_speed(&start, &stop, nr_to_write, "Wrote");
return ret;
}
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index 6a07f4dbf2f..5b3601bd189 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -56,133 +56,3 @@
#include "power.h"
int in_suspend __nosavedata = 0;
-
-/**
- * The following functions are used for tracing the allocated
- * swap pages, so that they can be freed in case of an error.
- */
-
-struct swsusp_extent {
- struct rb_node node;
- unsigned long start;
- unsigned long end;
-};
-
-static struct rb_root swsusp_extents = RB_ROOT;
-
-static int swsusp_extents_insert(unsigned long swap_offset)
-{
- struct rb_node **new = &(swsusp_extents.rb_node);
- struct rb_node *parent = NULL;
- struct swsusp_extent *ext;
-
- /* Figure out where to put the new node */
- while (*new) {
- ext = container_of(*new, struct swsusp_extent, node);
- parent = *new;
- if (swap_offset < ext->start) {
- /* Try to merge */
- if (swap_offset == ext->start - 1) {
- ext->start--;
- return 0;
- }
- new = &((*new)->rb_left);
- } else if (swap_offset > ext->end) {
- /* Try to merge */
- if (swap_offset == ext->end + 1) {
- ext->end++;
- return 0;
- }
- new = &((*new)->rb_right);
- } else {
- /* It already is in the tree */
- return -EINVAL;
- }
- }
- /* Add the new node and rebalance the tree. */
- ext = kzalloc(sizeof(struct swsusp_extent), GFP_KERNEL);
- if (!ext)
- return -ENOMEM;
-
- ext->start = swap_offset;
- ext->end = swap_offset;
- rb_link_node(&ext->node, parent, new);
- rb_insert_color(&ext->node, &swsusp_extents);
- return 0;
-}
-
-/**
- * alloc_swapdev_block - allocate a swap page and register that it has
- * been allocated, so that it can be freed in case of an error.
- */
-
-sector_t alloc_swapdev_block(int swap)
-{
- unsigned long offset;
-
- offset = swp_offset(get_swap_page_of_type(swap));
- if (offset) {
- if (swsusp_extents_insert(offset))
- swap_free(swp_entry(swap, offset));
- else
- return swapdev_block(swap, offset);
- }
- return 0;
-}
-
-/**
- * free_all_swap_pages - free swap pages allocated for saving image data.
- * It also frees the extents used to register which swap entres had been
- * allocated.
- */
-
-void free_all_swap_pages(int swap)
-{
- struct rb_node *node;
-
- while ((node = swsusp_extents.rb_node)) {
- struct swsusp_extent *ext;
- unsigned long offset;
-
- ext = container_of(node, struct swsusp_extent, node);
- rb_erase(node, &swsusp_extents);
- for (offset = ext->start; offset <= ext->end; offset++)
- swap_free(swp_entry(swap, offset));
-
- kfree(ext);
- }
-}
-
-int swsusp_swap_in_use(void)
-{
- return (swsusp_extents.rb_node != NULL);
-}
-
-/**
- * swsusp_show_speed - print the time elapsed between two events represented by
- * @start and @stop
- *
- * @nr_pages - number of pages processed between @start and @stop
- * @msg - introductory message to print
- */
-
-void swsusp_show_speed(struct timeval *start, struct timeval *stop,
- unsigned nr_pages, char *msg)
-{
- s64 elapsed_centisecs64;
- int centisecs;
- int k;
- int kps;
-
- elapsed_centisecs64 = timeval_to_ns(stop) - timeval_to_ns(start);
- do_div(elapsed_centisecs64, NSEC_PER_SEC / 100);
- centisecs = elapsed_centisecs64;
- if (centisecs == 0)
- centisecs = 1; /* avoid div-by-zero */
- k = nr_pages * (PAGE_SIZE / 1024);
- kps = (k * 100) / centisecs;
- printk(KERN_INFO "PM: %s %d kbytes in %d.%02d seconds (%d.%02d MB/s)\n",
- msg, k,
- centisecs / 100, centisecs % 100,
- kps / 1000, (kps % 1000) / 10);
-}
diff --git a/kernel/printk.c b/kernel/printk.c
index f38b07f78a4..b5ac4d99c66 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -33,6 +33,7 @@
#include <linux/bootmem.h>
#include <linux/syscalls.h>
#include <linux/kexec.h>
+#include <linux/ratelimit.h>
#include <asm/uaccess.h>
@@ -1376,11 +1377,11 @@ late_initcall(disable_boot_consoles);
*/
DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10);
-int printk_ratelimit(void)
+int __printk_ratelimit(const char *func)
{
- return __ratelimit(&printk_ratelimit_state);
+ return ___ratelimit(&printk_ratelimit_state, func);
}
-EXPORT_SYMBOL(printk_ratelimit);
+EXPORT_SYMBOL(__printk_ratelimit);
/**
* printk_timed_ratelimit - caller-controlled printk ratelimiting
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 400183346ad..9b7fd472387 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -44,7 +44,6 @@
#include <linux/cpu.h>
#include <linux/mutex.h>
#include <linux/module.h>
-#include <linux/kernel_stat.h>
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key rcu_lock_key;
@@ -53,8 +52,6 @@ struct lockdep_map rcu_lock_map =
EXPORT_SYMBOL_GPL(rcu_lock_map);
#endif
-int rcu_scheduler_active __read_mostly;
-
/*
* Awaken the corresponding synchronize_rcu() instance now that a
* grace period has elapsed.
@@ -66,122 +63,3 @@ void wakeme_after_rcu(struct rcu_head *head)
rcu = container_of(head, struct rcu_synchronize, head);
complete(&rcu->completion);
}
-
-#ifdef CONFIG_TREE_PREEMPT_RCU
-
-/**
- * synchronize_rcu - wait until a grace period has elapsed.
- *
- * Control will return to the caller some time after a full grace
- * period has elapsed, in other words after all currently executing RCU
- * read-side critical sections have completed. RCU read-side critical
- * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
- * and may be nested.
- */
-void synchronize_rcu(void)
-{
- struct rcu_synchronize rcu;
-
- if (!rcu_scheduler_active)
- return;
-
- init_completion(&rcu.completion);
- /* Will wake me after RCU finished. */
- call_rcu(&rcu.head, wakeme_after_rcu);
- /* Wait for it. */
- wait_for_completion(&rcu.completion);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu);
-
-#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-
-/**
- * synchronize_sched - wait until an rcu-sched grace period has elapsed.
- *
- * Control will return to the caller some time after a full rcu-sched
- * grace period has elapsed, in other words after all currently executing
- * rcu-sched read-side critical sections have completed. These read-side
- * critical sections are delimited by rcu_read_lock_sched() and
- * rcu_read_unlock_sched(), and may be nested. Note that preempt_disable(),
- * local_irq_disable(), and so on may be used in place of
- * rcu_read_lock_sched().
- *
- * This means that all preempt_disable code sequences, including NMI and
- * hardware-interrupt handlers, in progress on entry will have completed
- * before this primitive returns. However, this does not guarantee that
- * softirq handlers will have completed, since in some kernels, these
- * handlers can run in process context, and can block.
- *
- * This primitive provides the guarantees made by the (now removed)
- * synchronize_kernel() API. In contrast, synchronize_rcu() only
- * guarantees that rcu_read_lock() sections will have completed.
- * In "classic RCU", these two guarantees happen to be one and
- * the same, but can differ in realtime RCU implementations.
- */
-void synchronize_sched(void)
-{
- struct rcu_synchronize rcu;
-
- if (rcu_blocking_is_gp())
- return;
-
- init_completion(&rcu.completion);
- /* Will wake me after RCU finished. */
- call_rcu_sched(&rcu.head, wakeme_after_rcu);
- /* Wait for it. */
- wait_for_completion(&rcu.completion);
-}
-EXPORT_SYMBOL_GPL(synchronize_sched);
-
-/**
- * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
- *
- * Control will return to the caller some time after a full rcu_bh grace
- * period has elapsed, in other words after all currently executing rcu_bh
- * read-side critical sections have completed. RCU read-side critical
- * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(),
- * and may be nested.
- */
-void synchronize_rcu_bh(void)
-{
- struct rcu_synchronize rcu;
-
- if (rcu_blocking_is_gp())
- return;
-
- init_completion(&rcu.completion);
- /* Will wake me after RCU finished. */
- call_rcu_bh(&rcu.head, wakeme_after_rcu);
- /* Wait for it. */
- wait_for_completion(&rcu.completion);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
-
-static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self,
- unsigned long action, void *hcpu)
-{
- return rcu_cpu_notify(self, action, hcpu);
-}
-
-void __init rcu_init(void)
-{
- int i;
-
- __rcu_init();
- cpu_notifier(rcu_barrier_cpu_hotplug, 0);
-
- /*
- * We don't need protection against CPU-hotplug here because
- * this is called early in boot, before either interrupts
- * or the scheduler are operational.
- */
- for_each_online_cpu(i)
- rcu_barrier_cpu_hotplug(NULL, CPU_UP_PREPARE, (void *)(long)i);
-}
-
-void rcu_scheduler_starting(void)
-{
- WARN_ON(num_online_cpus() != 1);
- WARN_ON(nr_context_switches() > 0);
- rcu_scheduler_active = 1;
-}
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
new file mode 100644
index 00000000000..9f6d9ff2572
--- /dev/null
+++ b/kernel/rcutiny.c
@@ -0,0 +1,282 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
+ *
+ * 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 IBM Corporation, 2008
+ *
+ * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ *
+ * For detailed explanation of Read-Copy Update mechanism see -
+ * Documentation/RCU
+ */
+#include <linux/moduleparam.h>
+#include <linux/completion.h>
+#include <linux/interrupt.h>
+#include <linux/notifier.h>
+#include <linux/rcupdate.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/time.h>
+#include <linux/cpu.h>
+
+/* Global control variables for rcupdate callback mechanism. */
+struct rcu_ctrlblk {
+ struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */
+ struct rcu_head **donetail; /* ->next pointer of last "done" CB. */
+ struct rcu_head **curtail; /* ->next pointer of last CB. */
+};
+
+/* Definition for rcupdate control block. */
+static struct rcu_ctrlblk rcu_ctrlblk = {
+ .donetail = &rcu_ctrlblk.rcucblist,
+ .curtail = &rcu_ctrlblk.rcucblist,
+};
+
+static struct rcu_ctrlblk rcu_bh_ctrlblk = {
+ .donetail = &rcu_bh_ctrlblk.rcucblist,
+ .curtail = &rcu_bh_ctrlblk.rcucblist,
+};
+
+#ifdef CONFIG_NO_HZ
+
+static long rcu_dynticks_nesting = 1;
+
+/*
+ * Enter dynticks-idle mode, which is an extended quiescent state
+ * if we have fully entered that mode (i.e., if the new value of
+ * dynticks_nesting is zero).
+ */
+void rcu_enter_nohz(void)
+{
+ if (--rcu_dynticks_nesting == 0)
+ rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */
+}
+
+/*
+ * Exit dynticks-idle mode, so that we are no longer in an extended
+ * quiescent state.
+ */
+void rcu_exit_nohz(void)
+{
+ rcu_dynticks_nesting++;
+}
+
+#endif /* #ifdef CONFIG_NO_HZ */
+
+/*
+ * Helper function for rcu_qsctr_inc() and rcu_bh_qsctr_inc().
+ * Also disable irqs to avoid confusion due to interrupt handlers
+ * invoking call_rcu().
+ */
+static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ if (rcp->rcucblist != NULL &&
+ rcp->donetail != rcp->curtail) {
+ rcp->donetail = rcp->curtail;
+ local_irq_restore(flags);
+ return 1;
+ }
+ local_irq_restore(flags);
+
+ return 0;
+}
+
+/*
+ * Record an rcu quiescent state. And an rcu_bh quiescent state while we
+ * are at it, given that any rcu quiescent state is also an rcu_bh
+ * quiescent state. Use "+" instead of "||" to defeat short circuiting.
+ */
+void rcu_sched_qs(int cpu)
+{
+ if (rcu_qsctr_help(&rcu_ctrlblk) + rcu_qsctr_help(&rcu_bh_ctrlblk))
+ raise_softirq(RCU_SOFTIRQ);
+}
+
+/*
+ * Record an rcu_bh quiescent state.
+ */
+void rcu_bh_qs(int cpu)
+{
+ if (rcu_qsctr_help(&rcu_bh_ctrlblk))
+ raise_softirq(RCU_SOFTIRQ);
+}
+
+/*
+ * Check to see if the scheduling-clock interrupt came from an extended
+ * quiescent state, and, if so, tell RCU about it.
+ */
+void rcu_check_callbacks(int cpu, int user)
+{
+ if (user ||
+ (idle_cpu(cpu) &&
+ !in_softirq() &&
+ hardirq_count() <= (1 << HARDIRQ_SHIFT)))
+ rcu_sched_qs(cpu);
+ else if (!in_softirq())
+ rcu_bh_qs(cpu);
+}
+
+/*
+ * Helper function for rcu_process_callbacks() that operates on the
+ * specified rcu_ctrlkblk structure.
+ */
+static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
+{
+ struct rcu_head *next, *list;
+ unsigned long flags;
+
+ /* If no RCU callbacks ready to invoke, just return. */
+ if (&rcp->rcucblist == rcp->donetail)
+ return;
+
+ /* Move the ready-to-invoke callbacks to a local list. */
+ local_irq_save(flags);
+ list = rcp->rcucblist;
+ rcp->rcucblist = *rcp->donetail;
+ *rcp->donetail = NULL;
+ if (rcp->curtail == rcp->donetail)
+ rcp->curtail = &rcp->rcucblist;
+ rcp->donetail = &rcp->rcucblist;
+ local_irq_restore(flags);
+
+ /* Invoke the callbacks on the local list. */
+ while (list) {
+ next = list->next;
+ prefetch(next);
+ list->func(list);
+ list = next;
+ }
+}
+
+/*
+ * Invoke any callbacks whose grace period has completed.
+ */
+static void rcu_process_callbacks(struct softirq_action *unused)
+{
+ __rcu_process_callbacks(&rcu_ctrlblk);
+ __rcu_process_callbacks(&rcu_bh_ctrlblk);
+}
+
+/*
+ * Wait for a grace period to elapse. But it is illegal to invoke
+ * synchronize_sched() from within an RCU read-side critical section.
+ * Therefore, any legal call to synchronize_sched() is a quiescent
+ * state, and so on a UP system, synchronize_sched() need do nothing.
+ * Ditto for synchronize_rcu_bh(). (But Lai Jiangshan points out the
+ * benefits of doing might_sleep() to reduce latency.)
+ *
+ * Cool, huh? (Due to Josh Triplett.)
+ *
+ * But we want to make this a static inline later.
+ */
+void synchronize_sched(void)
+{
+ cond_resched();
+}
+EXPORT_SYMBOL_GPL(synchronize_sched);
+
+void synchronize_rcu_bh(void)
+{
+ synchronize_sched();
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
+
+/*
+ * Helper function for call_rcu() and call_rcu_bh().
+ */
+static void __call_rcu(struct rcu_head *head,
+ void (*func)(struct rcu_head *rcu),
+ struct rcu_ctrlblk *rcp)
+{
+ unsigned long flags;
+
+ head->func = func;
+ head->next = NULL;
+
+ local_irq_save(flags);
+ *rcp->curtail = head;
+ rcp->curtail = &head->next;
+ local_irq_restore(flags);
+}
+
+/*
+ * Post an RCU callback to be invoked after the end of an RCU grace
+ * period. But since we have but one CPU, that would be after any
+ * quiescent state.
+ */
+void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+ __call_rcu(head, func, &rcu_ctrlblk);
+}
+EXPORT_SYMBOL_GPL(call_rcu);
+
+/*
+ * Post an RCU bottom-half callback to be invoked after any subsequent
+ * quiescent state.
+ */
+void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+ __call_rcu(head, func, &rcu_bh_ctrlblk);
+}
+EXPORT_SYMBOL_GPL(call_rcu_bh);
+
+void rcu_barrier(void)
+{
+ struct rcu_synchronize rcu;
+
+ init_completion(&rcu.completion);
+ /* Will wake me after RCU finished. */
+ call_rcu(&rcu.head, wakeme_after_rcu);
+ /* Wait for it. */
+ wait_for_completion(&rcu.completion);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier);
+
+void rcu_barrier_bh(void)
+{
+ struct rcu_synchronize rcu;
+
+ init_completion(&rcu.completion);
+ /* Will wake me after RCU finished. */
+ call_rcu_bh(&rcu.head, wakeme_after_rcu);
+ /* Wait for it. */
+ wait_for_completion(&rcu.completion);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_bh);
+
+void rcu_barrier_sched(void)
+{
+ struct rcu_synchronize rcu;
+
+ init_completion(&rcu.completion);
+ /* Will wake me after RCU finished. */
+ call_rcu_sched(&rcu.head, wakeme_after_rcu);
+ /* Wait for it. */
+ wait_for_completion(&rcu.completion);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_sched);
+
+void __init rcu_init(void)
+{
+ open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+}
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 697c0a0229d..a621a67ef4e 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -327,6 +327,11 @@ rcu_torture_cb(struct rcu_head *p)
cur_ops->deferred_free(rp);
}
+static int rcu_no_completed(void)
+{
+ return 0;
+}
+
static void rcu_torture_deferred_free(struct rcu_torture *p)
{
call_rcu(&p->rtort_rcu, rcu_torture_cb);
@@ -388,6 +393,21 @@ static struct rcu_torture_ops rcu_sync_ops = {
.name = "rcu_sync"
};
+static struct rcu_torture_ops rcu_expedited_ops = {
+ .init = rcu_sync_torture_init,
+ .cleanup = NULL,
+ .readlock = rcu_torture_read_lock,
+ .read_delay = rcu_read_delay, /* just reuse rcu's version. */
+ .readunlock = rcu_torture_read_unlock,
+ .completed = rcu_no_completed,
+ .deferred_free = rcu_sync_torture_deferred_free,
+ .sync = synchronize_rcu_expedited,
+ .cb_barrier = NULL,
+ .stats = NULL,
+ .irq_capable = 1,
+ .name = "rcu_expedited"
+};
+
/*
* Definitions for rcu_bh torture testing.
*/
@@ -547,6 +567,25 @@ static struct rcu_torture_ops srcu_ops = {
.name = "srcu"
};
+static void srcu_torture_synchronize_expedited(void)
+{
+ synchronize_srcu_expedited(&srcu_ctl);
+}
+
+static struct rcu_torture_ops srcu_expedited_ops = {
+ .init = srcu_torture_init,
+ .cleanup = srcu_torture_cleanup,
+ .readlock = srcu_torture_read_lock,
+ .read_delay = srcu_read_delay,
+ .readunlock = srcu_torture_read_unlock,
+ .completed = srcu_torture_completed,
+ .deferred_free = rcu_sync_torture_deferred_free,
+ .sync = srcu_torture_synchronize_expedited,
+ .cb_barrier = NULL,
+ .stats = srcu_torture_stats,
+ .name = "srcu_expedited"
+};
+
/*
* Definitions for sched torture testing.
*/
@@ -562,11 +601,6 @@ static void sched_torture_read_unlock(int idx)
preempt_enable();
}
-static int sched_torture_completed(void)
-{
- return 0;
-}
-
static void rcu_sched_torture_deferred_free(struct rcu_torture *p)
{
call_rcu_sched(&p->rtort_rcu, rcu_torture_cb);
@@ -583,7 +617,7 @@ static struct rcu_torture_ops sched_ops = {
.readlock = sched_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = sched_torture_read_unlock,
- .completed = sched_torture_completed,
+ .completed = rcu_no_completed,
.deferred_free = rcu_sched_torture_deferred_free,
.sync = sched_torture_synchronize,
.cb_barrier = rcu_barrier_sched,
@@ -592,13 +626,13 @@ static struct rcu_torture_ops sched_ops = {
.name = "sched"
};
-static struct rcu_torture_ops sched_ops_sync = {
+static struct rcu_torture_ops sched_sync_ops = {
.init = rcu_sync_torture_init,
.cleanup = NULL,
.readlock = sched_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = sched_torture_read_unlock,
- .completed = sched_torture_completed,
+ .completed = rcu_no_completed,
.deferred_free = rcu_sync_torture_deferred_free,
.sync = sched_torture_synchronize,
.cb_barrier = NULL,
@@ -612,7 +646,7 @@ static struct rcu_torture_ops sched_expedited_ops = {
.readlock = sched_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = sched_torture_read_unlock,
- .completed = sched_torture_completed,
+ .completed = rcu_no_completed,
.deferred_free = rcu_sync_torture_deferred_free,
.sync = synchronize_sched_expedited,
.cb_barrier = NULL,
@@ -1097,9 +1131,10 @@ rcu_torture_init(void)
int cpu;
int firsterr = 0;
static struct rcu_torture_ops *torture_ops[] =
- { &rcu_ops, &rcu_sync_ops, &rcu_bh_ops, &rcu_bh_sync_ops,
- &sched_expedited_ops,
- &srcu_ops, &sched_ops, &sched_ops_sync, };
+ { &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops,
+ &rcu_bh_ops, &rcu_bh_sync_ops,
+ &srcu_ops, &srcu_expedited_ops,
+ &sched_ops, &sched_sync_ops, &sched_expedited_ops, };
mutex_lock(&fullstop_mutex);
@@ -1110,8 +1145,12 @@ rcu_torture_init(void)
break;
}
if (i == ARRAY_SIZE(torture_ops)) {
- printk(KERN_ALERT "rcutorture: invalid torture type: \"%s\"\n",
+ printk(KERN_ALERT "rcu-torture: invalid torture type: \"%s\"\n",
torture_type);
+ printk(KERN_ALERT "rcu-torture types:");
+ for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
+ printk(KERN_ALERT " %s", torture_ops[i]->name);
+ printk(KERN_ALERT "\n");
mutex_unlock(&fullstop_mutex);
return -EINVAL;
}
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index f3077c0ab18..53ae9598f79 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -46,18 +46,22 @@
#include <linux/cpu.h>
#include <linux/mutex.h>
#include <linux/time.h>
+#include <linux/kernel_stat.h>
#include "rcutree.h"
/* Data structures. */
+static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
+
#define RCU_STATE_INITIALIZER(name) { \
.level = { &name.node[0] }, \
.levelcnt = { \
NUM_RCU_LVL_0, /* root of hierarchy. */ \
NUM_RCU_LVL_1, \
NUM_RCU_LVL_2, \
- NUM_RCU_LVL_3, /* == MAX_RCU_LVLS */ \
+ NUM_RCU_LVL_3, \
+ NUM_RCU_LVL_4, /* == MAX_RCU_LVLS */ \
}, \
.signaled = RCU_GP_IDLE, \
.gpnum = -300, \
@@ -77,6 +81,8 @@ DEFINE_PER_CPU(struct rcu_data, rcu_sched_data);
struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state);
DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
+static int rcu_scheduler_active __read_mostly;
+
/*
* Return true if an RCU grace period is in progress. The ACCESS_ONCE()s
@@ -98,7 +104,7 @@ void rcu_sched_qs(int cpu)
struct rcu_data *rdp;
rdp = &per_cpu(rcu_sched_data, cpu);
- rdp->passed_quiesc_completed = rdp->completed;
+ rdp->passed_quiesc_completed = rdp->gpnum - 1;
barrier();
rdp->passed_quiesc = 1;
rcu_preempt_note_context_switch(cpu);
@@ -109,7 +115,7 @@ void rcu_bh_qs(int cpu)
struct rcu_data *rdp;
rdp = &per_cpu(rcu_bh_data, cpu);
- rdp->passed_quiesc_completed = rdp->completed;
+ rdp->passed_quiesc_completed = rdp->gpnum - 1;
barrier();
rdp->passed_quiesc = 1;
}
@@ -335,28 +341,9 @@ void rcu_irq_exit(void)
set_need_resched();
}
-/*
- * Record the specified "completed" value, which is later used to validate
- * dynticks counter manipulations. Specify "rsp->completed - 1" to
- * unconditionally invalidate any future dynticks manipulations (which is
- * useful at the beginning of a grace period).
- */
-static void dyntick_record_completed(struct rcu_state *rsp, long comp)
-{
- rsp->dynticks_completed = comp;
-}
-
#ifdef CONFIG_SMP
/*
- * Recall the previously recorded value of the completion for dynticks.
- */
-static long dyntick_recall_completed(struct rcu_state *rsp)
-{
- return rsp->dynticks_completed;
-}
-
-/*
* Snapshot the specified CPU's dynticks counter so that we can later
* credit them with an implicit quiescent state. Return 1 if this CPU
* is in dynticks idle mode, which is an extended quiescent state.
@@ -419,24 +406,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
#else /* #ifdef CONFIG_NO_HZ */
-static void dyntick_record_completed(struct rcu_state *rsp, long comp)
-{
-}
-
#ifdef CONFIG_SMP
-/*
- * If there are no dynticks, then the only way that a CPU can passively
- * be in a quiescent state is to be offline. Unlike dynticks idle, which
- * is a point in time during the prior (already finished) grace period,
- * an offline CPU is always in a quiescent state, and thus can be
- * unconditionally applied. So just return the current value of completed.
- */
-static long dyntick_recall_completed(struct rcu_state *rsp)
-{
- return rsp->completed;
-}
-
static int dyntick_save_progress_counter(struct rcu_data *rdp)
{
return 0;
@@ -553,13 +524,33 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
/*
* Update CPU-local rcu_data state to record the newly noticed grace period.
* This is used both when we started the grace period and when we notice
- * that someone else started the grace period.
+ * that someone else started the grace period. The caller must hold the
+ * ->lock of the leaf rcu_node structure corresponding to the current CPU,
+ * and must have irqs disabled.
*/
+static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
+{
+ if (rdp->gpnum != rnp->gpnum) {
+ rdp->qs_pending = 1;
+ rdp->passed_quiesc = 0;
+ rdp->gpnum = rnp->gpnum;
+ }
+}
+
static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp)
{
- rdp->qs_pending = 1;
- rdp->passed_quiesc = 0;
- rdp->gpnum = rsp->gpnum;
+ unsigned long flags;
+ struct rcu_node *rnp;
+
+ local_irq_save(flags);
+ rnp = rdp->mynode;
+ if (rdp->gpnum == ACCESS_ONCE(rnp->gpnum) || /* outside lock. */
+ !spin_trylock(&rnp->lock)) { /* irqs already off, retry later. */
+ local_irq_restore(flags);
+ return;
+ }
+ __note_new_gpnum(rsp, rnp, rdp);
+ spin_unlock_irqrestore(&rnp->lock, flags);
}
/*
@@ -583,6 +574,79 @@ check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp)
}
/*
+ * Advance this CPU's callbacks, but only if the current grace period
+ * has ended. This may be called only from the CPU to whom the rdp
+ * belongs. In addition, the corresponding leaf rcu_node structure's
+ * ->lock must be held by the caller, with irqs disabled.
+ */
+static void
+__rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
+{
+ /* Did another grace period end? */
+ if (rdp->completed != rnp->completed) {
+
+ /* Advance callbacks. No harm if list empty. */
+ rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL];
+ rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL];
+ rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+
+ /* Remember that we saw this grace-period completion. */
+ rdp->completed = rnp->completed;
+ }
+}
+
+/*
+ * Advance this CPU's callbacks, but only if the current grace period
+ * has ended. This may be called only from the CPU to whom the rdp
+ * belongs.
+ */
+static void
+rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+ unsigned long flags;
+ struct rcu_node *rnp;
+
+ local_irq_save(flags);
+ rnp = rdp->mynode;
+ if (rdp->completed == ACCESS_ONCE(rnp->completed) || /* outside lock. */
+ !spin_trylock(&rnp->lock)) { /* irqs already off, retry later. */
+ local_irq_restore(flags);
+ return;
+ }
+ __rcu_process_gp_end(rsp, rnp, rdp);
+ spin_unlock_irqrestore(&rnp->lock, flags);
+}
+
+/*
+ * Do per-CPU grace-period initialization for running CPU. The caller
+ * must hold the lock of the leaf rcu_node structure corresponding to
+ * this CPU.
+ */
+static void
+rcu_start_gp_per_cpu(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
+{
+ /* Prior grace period ended, so advance callbacks for current CPU. */
+ __rcu_process_gp_end(rsp, rnp, rdp);
+
+ /*
+ * Because this CPU just now started the new grace period, we know
+ * that all of its callbacks will be covered by this upcoming grace
+ * period, even the ones that were registered arbitrarily recently.
+ * Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL.
+ *
+ * Other CPUs cannot be sure exactly when the grace period started.
+ * Therefore, their recently registered callbacks must pass through
+ * an additional RCU_NEXT_READY stage, so that they will be handled
+ * by the next RCU grace period.
+ */
+ rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+ rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+
+ /* Set state so that this CPU will detect the next quiescent state. */
+ __note_new_gpnum(rsp, rnp, rdp);
+}
+
+/*
* Start a new RCU grace period if warranted, re-initializing the hierarchy
* in preparation for detecting the next grace period. The caller must hold
* the root node's ->lock, which is released before return. Hard irqs must
@@ -596,7 +660,23 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
struct rcu_node *rnp = rcu_get_root(rsp);
if (!cpu_needs_another_gp(rsp, rdp)) {
- spin_unlock_irqrestore(&rnp->lock, flags);
+ if (rnp->completed == rsp->completed) {
+ spin_unlock_irqrestore(&rnp->lock, flags);
+ return;
+ }
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
+
+ /*
+ * Propagate new ->completed value to rcu_node structures
+ * so that other CPUs don't have to wait until the start
+ * of the next grace period to process their callbacks.
+ */
+ rcu_for_each_node_breadth_first(rsp, rnp) {
+ spin_lock(&rnp->lock); /* irqs already disabled. */
+ rnp->completed = rsp->completed;
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
+ }
+ local_irq_restore(flags);
return;
}
@@ -606,29 +686,15 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
rsp->signaled = RCU_GP_INIT; /* Hold off force_quiescent_state. */
rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
record_gp_stall_check_time(rsp);
- dyntick_record_completed(rsp, rsp->completed - 1);
- note_new_gpnum(rsp, rdp);
-
- /*
- * Because this CPU just now started the new grace period, we know
- * that all of its callbacks will be covered by this upcoming grace
- * period, even the ones that were registered arbitrarily recently.
- * Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL.
- *
- * Other CPUs cannot be sure exactly when the grace period started.
- * Therefore, their recently registered callbacks must pass through
- * an additional RCU_NEXT_READY stage, so that they will be handled
- * by the next RCU grace period.
- */
- rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
- rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
/* Special-case the common single-level case. */
if (NUM_RCU_NODES == 1) {
rcu_preempt_check_blocked_tasks(rnp);
rnp->qsmask = rnp->qsmaskinit;
rnp->gpnum = rsp->gpnum;
+ rnp->completed = rsp->completed;
rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state OK. */
+ rcu_start_gp_per_cpu(rsp, rnp, rdp);
spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
@@ -661,6 +727,9 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
rcu_preempt_check_blocked_tasks(rnp);
rnp->qsmask = rnp->qsmaskinit;
rnp->gpnum = rsp->gpnum;
+ rnp->completed = rsp->completed;
+ if (rnp == rdp->mynode)
+ rcu_start_gp_per_cpu(rsp, rnp, rdp);
spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
@@ -672,58 +741,32 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
}
/*
- * Advance this CPU's callbacks, but only if the current grace period
- * has ended. This may be called only from the CPU to whom the rdp
- * belongs.
+ * Report a full set of quiescent states to the specified rcu_state
+ * data structure. This involves cleaning up after the prior grace
+ * period and letting rcu_start_gp() start up the next grace period
+ * if one is needed. Note that the caller must hold rnp->lock, as
+ * required by rcu_start_gp(), which will release it.
*/
-static void
-rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
-{
- long completed_snap;
- unsigned long flags;
-
- local_irq_save(flags);
- completed_snap = ACCESS_ONCE(rsp->completed); /* outside of lock. */
-
- /* Did another grace period end? */
- if (rdp->completed != completed_snap) {
-
- /* Advance callbacks. No harm if list empty. */
- rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL];
- rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL];
- rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
-
- /* Remember that we saw this grace-period completion. */
- rdp->completed = completed_snap;
- }
- local_irq_restore(flags);
-}
-
-/*
- * Clean up after the prior grace period and let rcu_start_gp() start up
- * the next grace period if one is needed. Note that the caller must
- * hold rnp->lock, as required by rcu_start_gp(), which will release it.
- */
-static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags)
+static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
__releases(rcu_get_root(rsp)->lock)
{
WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
rsp->completed = rsp->gpnum;
rsp->signaled = RCU_GP_IDLE;
- rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]);
rcu_start_gp(rsp, flags); /* releases root node's rnp->lock. */
}
/*
- * Similar to cpu_quiet(), for which it is a helper function. Allows
- * a group of CPUs to be quieted at one go, though all the CPUs in the
- * group must be represented by the same leaf rcu_node structure.
- * That structure's lock must be held upon entry, and it is released
- * before return.
+ * Similar to rcu_report_qs_rdp(), for which it is a helper function.
+ * Allows quiescent states for a group of CPUs to be reported at one go
+ * to the specified rcu_node structure, though all the CPUs in the group
+ * must be represented by the same rcu_node structure (which need not be
+ * a leaf rcu_node structure, though it often will be). That structure's
+ * lock must be held upon entry, and it is released before return.
*/
static void
-cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp,
- unsigned long flags)
+rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
+ struct rcu_node *rnp, unsigned long flags)
__releases(rnp->lock)
{
struct rcu_node *rnp_c;
@@ -759,21 +802,23 @@ cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp,
/*
* Get here if we are the last CPU to pass through a quiescent
- * state for this grace period. Invoke cpu_quiet_msk_finish()
+ * state for this grace period. Invoke rcu_report_qs_rsp()
* to clean up and start the next grace period if one is needed.
*/
- cpu_quiet_msk_finish(rsp, flags); /* releases rnp->lock. */
+ rcu_report_qs_rsp(rsp, flags); /* releases rnp->lock. */
}
/*
- * Record a quiescent state for the specified CPU, which must either be
- * the current CPU. The lastcomp argument is used to make sure we are
- * still in the grace period of interest. We don't want to end the current
- * grace period based on quiescent states detected in an earlier grace
- * period!
+ * Record a quiescent state for the specified CPU to that CPU's rcu_data
+ * structure. This must be either called from the specified CPU, or
+ * called when the specified CPU is known to be offline (and when it is
+ * also known that no other CPU is concurrently trying to help the offline
+ * CPU). The lastcomp argument is used to make sure we are still in the
+ * grace period of interest. We don't want to end the current grace period
+ * based on quiescent states detected in an earlier grace period!
*/
static void
-cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp)
+rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp)
{
unsigned long flags;
unsigned long mask;
@@ -781,15 +826,15 @@ cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp)
rnp = rdp->mynode;
spin_lock_irqsave(&rnp->lock, flags);
- if (lastcomp != ACCESS_ONCE(rsp->completed)) {
+ if (lastcomp != rnp->completed) {
/*
* Someone beat us to it for this grace period, so leave.
* The race with GP start is resolved by the fact that we
* hold the leaf rcu_node lock, so that the per-CPU bits
* cannot yet be initialized -- so we would simply find our
- * CPU's bit already cleared in cpu_quiet_msk() if this race
- * occurred.
+ * CPU's bit already cleared in rcu_report_qs_rnp() if this
+ * race occurred.
*/
rdp->passed_quiesc = 0; /* try again later! */
spin_unlock_irqrestore(&rnp->lock, flags);
@@ -807,7 +852,7 @@ cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp)
*/
rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
- cpu_quiet_msk(mask, rsp, rnp, flags); /* releases rnp->lock */
+ rcu_report_qs_rnp(mask, rsp, rnp, flags); /* rlses rnp->lock */
}
}
@@ -838,8 +883,11 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
if (!rdp->passed_quiesc)
return;
- /* Tell RCU we are done (but cpu_quiet() will be the judge of that). */
- cpu_quiet(rdp->cpu, rsp, rdp, rdp->passed_quiesc_completed);
+ /*
+ * Tell RCU we are done (but rcu_report_qs_rdp() will be the
+ * judge of that).
+ */
+ rcu_report_qs_rdp(rdp->cpu, rsp, rdp, rdp->passed_quiesc_completed);
}
#ifdef CONFIG_HOTPLUG_CPU
@@ -899,8 +947,8 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
{
unsigned long flags;
- long lastcomp;
unsigned long mask;
+ int need_report = 0;
struct rcu_data *rdp = rsp->rda[cpu];
struct rcu_node *rnp;
@@ -914,30 +962,32 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
spin_lock(&rnp->lock); /* irqs already disabled. */
rnp->qsmaskinit &= ~mask;
if (rnp->qsmaskinit != 0) {
- spin_unlock(&rnp->lock); /* irqs remain disabled. */
+ if (rnp != rdp->mynode)
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
break;
}
-
- /*
- * If there was a task blocking the current grace period,
- * and if all CPUs have checked in, we need to propagate
- * the quiescent state up the rcu_node hierarchy. But that
- * is inconvenient at the moment due to deadlock issues if
- * this should end the current grace period. So set the
- * offlined CPU's bit in ->qsmask in order to force the
- * next force_quiescent_state() invocation to clean up this
- * mess in a deadlock-free manner.
- */
- if (rcu_preempt_offline_tasks(rsp, rnp, rdp) && !rnp->qsmask)
- rnp->qsmask |= mask;
-
+ if (rnp == rdp->mynode)
+ need_report = rcu_preempt_offline_tasks(rsp, rnp, rdp);
+ else
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
mask = rnp->grpmask;
- spin_unlock(&rnp->lock); /* irqs remain disabled. */
rnp = rnp->parent;
} while (rnp != NULL);
- lastcomp = rsp->completed;
- spin_unlock_irqrestore(&rsp->onofflock, flags);
+ /*
+ * We still hold the leaf rcu_node structure lock here, and
+ * irqs are still disabled. The reason for this subterfuge is
+ * because invoking rcu_report_unblock_qs_rnp() with ->onofflock
+ * held leads to deadlock.
+ */
+ spin_unlock(&rsp->onofflock); /* irqs remain disabled. */
+ rnp = rdp->mynode;
+ if (need_report & RCU_OFL_TASKS_NORM_GP)
+ rcu_report_unblock_qs_rnp(rnp, flags);
+ else
+ spin_unlock_irqrestore(&rnp->lock, flags);
+ if (need_report & RCU_OFL_TASKS_EXP_GP)
+ rcu_report_exp_rnp(rsp, rnp);
rcu_adopt_orphan_cbs(rsp);
}
@@ -1109,7 +1159,7 @@ static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp,
rcu_for_each_leaf_node(rsp, rnp) {
mask = 0;
spin_lock_irqsave(&rnp->lock, flags);
- if (rsp->completed != lastcomp) {
+ if (rnp->completed != lastcomp) {
spin_unlock_irqrestore(&rnp->lock, flags);
return 1;
}
@@ -1123,10 +1173,10 @@ static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp,
if ((rnp->qsmask & bit) != 0 && f(rsp->rda[cpu]))
mask |= bit;
}
- if (mask != 0 && rsp->completed == lastcomp) {
+ if (mask != 0 && rnp->completed == lastcomp) {
- /* cpu_quiet_msk() releases rnp->lock. */
- cpu_quiet_msk(mask, rsp, rnp, flags);
+ /* rcu_report_qs_rnp() releases rnp->lock. */
+ rcu_report_qs_rnp(mask, rsp, rnp, flags);
continue;
}
spin_unlock_irqrestore(&rnp->lock, flags);
@@ -1144,6 +1194,7 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
long lastcomp;
struct rcu_node *rnp = rcu_get_root(rsp);
u8 signaled;
+ u8 forcenow;
if (!rcu_gp_in_progress(rsp))
return; /* No grace period in progress, nothing to force. */
@@ -1156,10 +1207,10 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
goto unlock_ret; /* no emergency and done recently. */
rsp->n_force_qs++;
spin_lock(&rnp->lock);
- lastcomp = rsp->completed;
+ lastcomp = rsp->gpnum - 1;
signaled = rsp->signaled;
rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
- if (lastcomp == rsp->gpnum) {
+ if(!rcu_gp_in_progress(rsp)) {
rsp->n_force_qs_ngp++;
spin_unlock(&rnp->lock);
goto unlock_ret; /* no GP in progress, time updated. */
@@ -1180,21 +1231,29 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
if (rcu_process_dyntick(rsp, lastcomp,
dyntick_save_progress_counter))
goto unlock_ret;
+ /* fall into next case. */
+
+ case RCU_SAVE_COMPLETED:
/* Update state, record completion counter. */
+ forcenow = 0;
spin_lock(&rnp->lock);
- if (lastcomp == rsp->completed &&
- rsp->signaled == RCU_SAVE_DYNTICK) {
+ if (lastcomp + 1 == rsp->gpnum &&
+ lastcomp == rsp->completed &&
+ rsp->signaled == signaled) {
rsp->signaled = RCU_FORCE_QS;
- dyntick_record_completed(rsp, lastcomp);
+ rsp->completed_fqs = lastcomp;
+ forcenow = signaled == RCU_SAVE_COMPLETED;
}
spin_unlock(&rnp->lock);
- break;
+ if (!forcenow)
+ break;
+ /* fall into next case. */
case RCU_FORCE_QS:
/* Check dyntick-idle state, send IPI to laggarts. */
- if (rcu_process_dyntick(rsp, dyntick_recall_completed(rsp),
+ if (rcu_process_dyntick(rsp, rsp->completed_fqs,
rcu_implicit_dynticks_qs))
goto unlock_ret;
@@ -1351,6 +1410,68 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
}
EXPORT_SYMBOL_GPL(call_rcu_bh);
+/**
+ * synchronize_sched - wait until an rcu-sched grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full rcu-sched
+ * grace period has elapsed, in other words after all currently executing
+ * rcu-sched read-side critical sections have completed. These read-side
+ * critical sections are delimited by rcu_read_lock_sched() and
+ * rcu_read_unlock_sched(), and may be nested. Note that preempt_disable(),
+ * local_irq_disable(), and so on may be used in place of
+ * rcu_read_lock_sched().
+ *
+ * This means that all preempt_disable code sequences, including NMI and
+ * hardware-interrupt handlers, in progress on entry will have completed
+ * before this primitive returns. However, this does not guarantee that
+ * softirq handlers will have completed, since in some kernels, these
+ * handlers can run in process context, and can block.
+ *
+ * This primitive provides the guarantees made by the (now removed)
+ * synchronize_kernel() API. In contrast, synchronize_rcu() only
+ * guarantees that rcu_read_lock() sections will have completed.
+ * In "classic RCU", these two guarantees happen to be one and
+ * the same, but can differ in realtime RCU implementations.
+ */
+void synchronize_sched(void)
+{
+ struct rcu_synchronize rcu;
+
+ if (rcu_blocking_is_gp())
+ return;
+
+ init_completion(&rcu.completion);
+ /* Will wake me after RCU finished. */
+ call_rcu_sched(&rcu.head, wakeme_after_rcu);
+ /* Wait for it. */
+ wait_for_completion(&rcu.completion);
+}
+EXPORT_SYMBOL_GPL(synchronize_sched);
+
+/**
+ * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full rcu_bh grace
+ * period has elapsed, in other words after all currently executing rcu_bh
+ * read-side critical sections have completed. RCU read-side critical
+ * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(),
+ * and may be nested.
+ */
+void synchronize_rcu_bh(void)
+{
+ struct rcu_synchronize rcu;
+
+ if (rcu_blocking_is_gp())
+ return;
+
+ init_completion(&rcu.completion);
+ /* Will wake me after RCU finished. */
+ call_rcu_bh(&rcu.head, wakeme_after_rcu);
+ /* Wait for it. */
+ wait_for_completion(&rcu.completion);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
+
/*
* Check to see if there is any immediate RCU-related work to be done
* by the current CPU, for the specified type of RCU, returning 1 if so.
@@ -1360,6 +1481,8 @@ EXPORT_SYMBOL_GPL(call_rcu_bh);
*/
static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
{
+ struct rcu_node *rnp = rdp->mynode;
+
rdp->n_rcu_pending++;
/* Check for CPU stalls, if enabled. */
@@ -1384,13 +1507,13 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
}
/* Has another RCU grace period completed? */
- if (ACCESS_ONCE(rsp->completed) != rdp->completed) { /* outside lock */
+ if (ACCESS_ONCE(rnp->completed) != rdp->completed) { /* outside lock */
rdp->n_rp_gp_completed++;
return 1;
}
/* Has a new RCU grace period started? */
- if (ACCESS_ONCE(rsp->gpnum) != rdp->gpnum) { /* outside lock */
+ if (ACCESS_ONCE(rnp->gpnum) != rdp->gpnum) { /* outside lock */
rdp->n_rp_gp_started++;
return 1;
}
@@ -1433,6 +1556,21 @@ int rcu_needs_cpu(int cpu)
rcu_preempt_needs_cpu(cpu);
}
+/*
+ * This function is invoked towards the end of the scheduler's initialization
+ * process. Before this is called, the idle task might contain
+ * RCU read-side critical sections (during which time, this idle
+ * task is booting the system). After this function is called, the
+ * idle tasks are prohibited from containing RCU read-side critical
+ * sections.
+ */
+void rcu_scheduler_starting(void)
+{
+ WARN_ON(num_online_cpus() != 1);
+ WARN_ON(nr_context_switches() > 0);
+ rcu_scheduler_active = 1;
+}
+
static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
static atomic_t rcu_barrier_cpu_count;
static DEFINE_MUTEX(rcu_barrier_mutex);
@@ -1544,21 +1682,16 @@ static void __cpuinit
rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
{
unsigned long flags;
- long lastcomp;
unsigned long mask;
struct rcu_data *rdp = rsp->rda[cpu];
struct rcu_node *rnp = rcu_get_root(rsp);
/* Set up local state, ensuring consistent view of global state. */
spin_lock_irqsave(&rnp->lock, flags);
- lastcomp = rsp->completed;
- rdp->completed = lastcomp;
- rdp->gpnum = lastcomp;
rdp->passed_quiesc = 0; /* We could be racing with new GP, */
rdp->qs_pending = 1; /* so set up to respond to current GP. */
rdp->beenonline = 1; /* We have now been online. */
rdp->preemptable = preemptable;
- rdp->passed_quiesc_completed = lastcomp - 1;
rdp->qlen_last_fqs_check = 0;
rdp->n_force_qs_snap = rsp->n_force_qs;
rdp->blimit = blimit;
@@ -1580,6 +1713,11 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
spin_lock(&rnp->lock); /* irqs already disabled. */
rnp->qsmaskinit |= mask;
mask = rnp->grpmask;
+ if (rnp == rdp->mynode) {
+ rdp->gpnum = rnp->completed; /* if GP in progress... */
+ rdp->completed = rnp->completed;
+ rdp->passed_quiesc_completed = rnp->completed - 1;
+ }
spin_unlock(&rnp->lock); /* irqs already disabled. */
rnp = rnp->parent;
} while (rnp != NULL && !(rnp->qsmaskinit & mask));
@@ -1597,8 +1735,8 @@ static void __cpuinit rcu_online_cpu(int cpu)
/*
* Handle CPU online/offline notification events.
*/
-int __cpuinit rcu_cpu_notify(struct notifier_block *self,
- unsigned long action, void *hcpu)
+static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *hcpu)
{
long cpu = (long)hcpu;
@@ -1685,8 +1823,8 @@ static void __init rcu_init_one(struct rcu_state *rsp)
cpustride *= rsp->levelspread[i];
rnp = rsp->level[i];
for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) {
- if (rnp != rcu_get_root(rsp))
- spin_lock_init(&rnp->lock);
+ spin_lock_init(&rnp->lock);
+ lockdep_set_class(&rnp->lock, &rcu_node_class[i]);
rnp->gpnum = 0;
rnp->qsmask = 0;
rnp->qsmaskinit = 0;
@@ -1707,9 +1845,10 @@ static void __init rcu_init_one(struct rcu_state *rsp)
rnp->level = i;
INIT_LIST_HEAD(&rnp->blocked_tasks[0]);
INIT_LIST_HEAD(&rnp->blocked_tasks[1]);
+ INIT_LIST_HEAD(&rnp->blocked_tasks[2]);
+ INIT_LIST_HEAD(&rnp->blocked_tasks[3]);
}
}
- spin_lock_init(&rcu_get_root(rsp)->lock);
}
/*
@@ -1735,16 +1874,30 @@ do { \
} \
} while (0)
-void __init __rcu_init(void)
+void __init rcu_init(void)
{
+ int i;
+
rcu_bootup_announce();
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+#if NUM_RCU_LVL_4 != 0
+ printk(KERN_INFO "Experimental four-level hierarchy is enabled.\n");
+#endif /* #if NUM_RCU_LVL_4 != 0 */
RCU_INIT_FLAVOR(&rcu_sched_state, rcu_sched_data);
RCU_INIT_FLAVOR(&rcu_bh_state, rcu_bh_data);
__rcu_init_preempt();
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+
+ /*
+ * We don't need protection against CPU-hotplug here because
+ * this is called early in boot, before either interrupts
+ * or the scheduler are operational.
+ */
+ cpu_notifier(rcu_cpu_notify, 0);
+ for_each_online_cpu(i)
+ rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)i);
}
#include "rcutree_plugin.h"
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 1899023b096..d2a0046f63b 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -34,10 +34,11 @@
* In practice, this has not been tested, so there is probably some
* bug somewhere.
*/
-#define MAX_RCU_LVLS 3
+#define MAX_RCU_LVLS 4
#define RCU_FANOUT (CONFIG_RCU_FANOUT)
#define RCU_FANOUT_SQ (RCU_FANOUT * RCU_FANOUT)
#define RCU_FANOUT_CUBE (RCU_FANOUT_SQ * RCU_FANOUT)
+#define RCU_FANOUT_FOURTH (RCU_FANOUT_CUBE * RCU_FANOUT)
#if NR_CPUS <= RCU_FANOUT
# define NUM_RCU_LVLS 1
@@ -45,23 +46,33 @@
# define NUM_RCU_LVL_1 (NR_CPUS)
# define NUM_RCU_LVL_2 0
# define NUM_RCU_LVL_3 0
+# define NUM_RCU_LVL_4 0
#elif NR_CPUS <= RCU_FANOUT_SQ
# define NUM_RCU_LVLS 2
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
# define NUM_RCU_LVL_2 (NR_CPUS)
# define NUM_RCU_LVL_3 0
+# define NUM_RCU_LVL_4 0
#elif NR_CPUS <= RCU_FANOUT_CUBE
# define NUM_RCU_LVLS 3
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
# define NUM_RCU_LVL_3 NR_CPUS
+# define NUM_RCU_LVL_4 0
+#elif NR_CPUS <= RCU_FANOUT_FOURTH
+# define NUM_RCU_LVLS 4
+# define NUM_RCU_LVL_0 1
+# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_CUBE)
+# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
+# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
+# define NUM_RCU_LVL_4 NR_CPUS
#else
# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
#endif /* #if (NR_CPUS) <= RCU_FANOUT */
-#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
+#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4)
#define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
/*
@@ -84,14 +95,21 @@ struct rcu_node {
long gpnum; /* Current grace period for this node. */
/* This will either be equal to or one */
/* behind the root rcu_node's gpnum. */
+ long completed; /* Last grace period completed for this node. */
+ /* This will either be equal to or one */
+ /* behind the root rcu_node's gpnum. */
unsigned long qsmask; /* CPUs or groups that need to switch in */
/* order for current grace period to proceed.*/
/* In leaf rcu_node, each bit corresponds to */
/* an rcu_data structure, otherwise, each */
/* bit corresponds to a child rcu_node */
/* structure. */
+ unsigned long expmask; /* Groups that have ->blocked_tasks[] */
+ /* elements that need to drain to allow the */
+ /* current expedited grace period to */
+ /* complete (only for TREE_PREEMPT_RCU). */
unsigned long qsmaskinit;
- /* Per-GP initialization for qsmask. */
+ /* Per-GP initial value for qsmask & expmask. */
unsigned long grpmask; /* Mask to apply to parent qsmask. */
/* Only one bit will be set in this mask. */
int grplo; /* lowest-numbered CPU or group here. */
@@ -99,7 +117,7 @@ struct rcu_node {
u8 grpnum; /* CPU/group number for next level up. */
u8 level; /* root is at level 0. */
struct rcu_node *parent;
- struct list_head blocked_tasks[2];
+ struct list_head blocked_tasks[4];
/* Tasks blocked in RCU read-side critsect. */
/* Grace period number (->gpnum) x blocked */
/* by tasks on the (x & 0x1) element of the */
@@ -114,6 +132,21 @@ struct rcu_node {
for ((rnp) = &(rsp)->node[0]; \
(rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++)
+/*
+ * Do a breadth-first scan of the non-leaf rcu_node structures for the
+ * specified rcu_state structure. Note that if there is a singleton
+ * rcu_node tree with but one rcu_node structure, this loop is a no-op.
+ */
+#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
+ for ((rnp) = &(rsp)->node[0]; \
+ (rnp) < (rsp)->level[NUM_RCU_LVLS - 1]; (rnp)++)
+
+/*
+ * Scan the leaves of the rcu_node hierarchy for the specified rcu_state
+ * structure. Note that if there is a singleton rcu_node tree with but
+ * one rcu_node structure, this loop -will- visit the rcu_node structure.
+ * It is still a leaf node, even if it is also the root node.
+ */
#define rcu_for_each_leaf_node(rsp, rnp) \
for ((rnp) = (rsp)->level[NUM_RCU_LVLS - 1]; \
(rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++)
@@ -204,11 +237,12 @@ struct rcu_data {
#define RCU_GP_IDLE 0 /* No grace period in progress. */
#define RCU_GP_INIT 1 /* Grace period being initialized. */
#define RCU_SAVE_DYNTICK 2 /* Need to scan dyntick state. */
-#define RCU_FORCE_QS 3 /* Need to force quiescent state. */
+#define RCU_SAVE_COMPLETED 3 /* Need to save rsp->completed. */
+#define RCU_FORCE_QS 4 /* Need to force quiescent state. */
#ifdef CONFIG_NO_HZ
#define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK
#else /* #ifdef CONFIG_NO_HZ */
-#define RCU_SIGNAL_INIT RCU_FORCE_QS
+#define RCU_SIGNAL_INIT RCU_SAVE_COMPLETED
#endif /* #else #ifdef CONFIG_NO_HZ */
#define RCU_JIFFIES_TILL_FORCE_QS 3 /* for rsp->jiffies_force_qs */
@@ -246,7 +280,7 @@ struct rcu_state {
long gpnum; /* Current gp number. */
long completed; /* # of last completed gp. */
- /* End of fields guarded by root rcu_node's lock. */
+ /* End of fields guarded by root rcu_node's lock. */
spinlock_t onofflock; /* exclude on/offline and */
/* starting new GP. Also */
@@ -260,6 +294,8 @@ struct rcu_state {
long orphan_qlen; /* Number of orphaned cbs. */
spinlock_t fqslock; /* Only one task forcing */
/* quiescent states. */
+ long completed_fqs; /* Value of completed @ snap. */
+ /* Protected by fqslock. */
unsigned long jiffies_force_qs; /* Time at which to invoke */
/* force_quiescent_state(). */
unsigned long n_force_qs; /* Number of calls to */
@@ -274,11 +310,15 @@ struct rcu_state {
unsigned long jiffies_stall; /* Time at which to check */
/* for CPU stalls. */
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-#ifdef CONFIG_NO_HZ
- long dynticks_completed; /* Value of completed @ snap. */
-#endif /* #ifdef CONFIG_NO_HZ */
};
+/* Return values for rcu_preempt_offline_tasks(). */
+
+#define RCU_OFL_TASKS_NORM_GP 0x1 /* Tasks blocking normal */
+ /* GP were moved to root. */
+#define RCU_OFL_TASKS_EXP_GP 0x2 /* Tasks blocking expedited */
+ /* GP were moved to root. */
+
#ifdef RCU_TREE_NONCORE
/*
@@ -298,10 +338,14 @@ DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
#else /* #ifdef RCU_TREE_NONCORE */
/* Forward declarations for rcutree_plugin.h */
-static inline void rcu_bootup_announce(void);
+static void rcu_bootup_announce(void);
long rcu_batches_completed(void);
static void rcu_preempt_note_context_switch(int cpu);
static int rcu_preempted_readers(struct rcu_node *rnp);
+#ifdef CONFIG_HOTPLUG_CPU
+static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
+ unsigned long flags);
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
static void rcu_print_task_stall(struct rcu_node *rnp);
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
@@ -315,6 +359,9 @@ static void rcu_preempt_offline_cpu(int cpu);
static void rcu_preempt_check_callbacks(int cpu);
static void rcu_preempt_process_callbacks(void);
void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU)
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp);
+#endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */
static int rcu_preempt_pending(int cpu);
static int rcu_preempt_needs_cpu(int cpu);
static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index ef2a58c2b9d..37fbccdf41d 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -24,16 +24,19 @@
* Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
+#include <linux/delay.h>
#ifdef CONFIG_TREE_PREEMPT_RCU
struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);
+static int rcu_preempted_readers_exp(struct rcu_node *rnp);
+
/*
* Tell them what RCU they are running.
*/
-static inline void rcu_bootup_announce(void)
+static void __init rcu_bootup_announce(void)
{
printk(KERN_INFO
"Experimental preemptable hierarchical RCU implementation.\n");
@@ -67,7 +70,7 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed);
static void rcu_preempt_qs(int cpu)
{
struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
- rdp->passed_quiesc_completed = rdp->completed;
+ rdp->passed_quiesc_completed = rdp->gpnum - 1;
barrier();
rdp->passed_quiesc = 1;
}
@@ -157,14 +160,58 @@ EXPORT_SYMBOL_GPL(__rcu_read_lock);
*/
static int rcu_preempted_readers(struct rcu_node *rnp)
{
- return !list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]);
+ int phase = rnp->gpnum & 0x1;
+
+ return !list_empty(&rnp->blocked_tasks[phase]) ||
+ !list_empty(&rnp->blocked_tasks[phase + 2]);
+}
+
+/*
+ * Record a quiescent state for all tasks that were previously queued
+ * on the specified rcu_node structure and that were blocking the current
+ * RCU grace period. The caller must hold the specified rnp->lock with
+ * irqs disabled, and this lock is released upon return, but irqs remain
+ * disabled.
+ */
+static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
+ __releases(rnp->lock)
+{
+ unsigned long mask;
+ struct rcu_node *rnp_p;
+
+ if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) {
+ spin_unlock_irqrestore(&rnp->lock, flags);
+ return; /* Still need more quiescent states! */
+ }
+
+ rnp_p = rnp->parent;
+ if (rnp_p == NULL) {
+ /*
+ * Either there is only one rcu_node in the tree,
+ * or tasks were kicked up to root rcu_node due to
+ * CPUs going offline.
+ */
+ rcu_report_qs_rsp(&rcu_preempt_state, flags);
+ return;
+ }
+
+ /* Report up the rest of the hierarchy. */
+ mask = rnp->grpmask;
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
+ spin_lock(&rnp_p->lock); /* irqs already disabled. */
+ rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
}
+/*
+ * Handle special cases during rcu_read_unlock(), such as needing to
+ * notify RCU core processing or task having blocked during the RCU
+ * read-side critical section.
+ */
static void rcu_read_unlock_special(struct task_struct *t)
{
int empty;
+ int empty_exp;
unsigned long flags;
- unsigned long mask;
struct rcu_node *rnp;
int special;
@@ -207,36 +254,30 @@ static void rcu_read_unlock_special(struct task_struct *t)
spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
empty = !rcu_preempted_readers(rnp);
+ empty_exp = !rcu_preempted_readers_exp(rnp);
+ smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
list_del_init(&t->rcu_node_entry);
t->rcu_blocked_node = NULL;
/*
* If this was the last task on the current list, and if
* we aren't waiting on any CPUs, report the quiescent state.
- * Note that both cpu_quiet_msk_finish() and cpu_quiet_msk()
- * drop rnp->lock and restore irq.
+ * Note that rcu_report_unblock_qs_rnp() releases rnp->lock.
*/
- if (!empty && rnp->qsmask == 0 &&
- !rcu_preempted_readers(rnp)) {
- struct rcu_node *rnp_p;
-
- if (rnp->parent == NULL) {
- /* Only one rcu_node in the tree. */
- cpu_quiet_msk_finish(&rcu_preempt_state, flags);
- return;
- }
- /* Report up the rest of the hierarchy. */
- mask = rnp->grpmask;
+ if (empty)
spin_unlock_irqrestore(&rnp->lock, flags);
- rnp_p = rnp->parent;
- spin_lock_irqsave(&rnp_p->lock, flags);
- WARN_ON_ONCE(rnp->qsmask);
- cpu_quiet_msk(mask, &rcu_preempt_state, rnp_p, flags);
- return;
- }
- spin_unlock(&rnp->lock);
+ else
+ rcu_report_unblock_qs_rnp(rnp, flags);
+
+ /*
+ * If this was the last task on the expedited lists,
+ * then we need to report up the rcu_node hierarchy.
+ */
+ if (!empty_exp && !rcu_preempted_readers_exp(rnp))
+ rcu_report_exp_rnp(&rcu_preempt_state, rnp);
+ } else {
+ local_irq_restore(flags);
}
- local_irq_restore(flags);
}
/*
@@ -303,6 +344,8 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
* rcu_node. The reason for not just moving them to the immediate
* parent is to remove the need for rcu_read_unlock_special() to
* make more than two attempts to acquire the target rcu_node's lock.
+ * Returns true if there were tasks blocking the current RCU grace
+ * period.
*
* Returns 1 if there was previously a task blocking the current grace
* period on the specified rcu_node structure.
@@ -316,7 +359,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
int i;
struct list_head *lp;
struct list_head *lp_root;
- int retval = rcu_preempted_readers(rnp);
+ int retval = 0;
struct rcu_node *rnp_root = rcu_get_root(rsp);
struct task_struct *tp;
@@ -326,7 +369,9 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
}
WARN_ON_ONCE(rnp != rdp->mynode &&
(!list_empty(&rnp->blocked_tasks[0]) ||
- !list_empty(&rnp->blocked_tasks[1])));
+ !list_empty(&rnp->blocked_tasks[1]) ||
+ !list_empty(&rnp->blocked_tasks[2]) ||
+ !list_empty(&rnp->blocked_tasks[3])));
/*
* Move tasks up to root rcu_node. Rely on the fact that the
@@ -334,7 +379,11 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
* rcu_nodes in terms of gp_num value. This fact allows us to
* move the blocked_tasks[] array directly, element by element.
*/
- for (i = 0; i < 2; i++) {
+ if (rcu_preempted_readers(rnp))
+ retval |= RCU_OFL_TASKS_NORM_GP;
+ if (rcu_preempted_readers_exp(rnp))
+ retval |= RCU_OFL_TASKS_EXP_GP;
+ for (i = 0; i < 4; i++) {
lp = &rnp->blocked_tasks[i];
lp_root = &rnp_root->blocked_tasks[i];
while (!list_empty(lp)) {
@@ -346,7 +395,6 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
spin_unlock(&rnp_root->lock); /* irqs remain disabled */
}
}
-
return retval;
}
@@ -398,14 +446,183 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
}
EXPORT_SYMBOL_GPL(call_rcu);
+/**
+ * synchronize_rcu - wait until a grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full grace
+ * period has elapsed, in other words after all currently executing RCU
+ * read-side critical sections have completed. RCU read-side critical
+ * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
+ * and may be nested.
+ */
+void synchronize_rcu(void)
+{
+ struct rcu_synchronize rcu;
+
+ if (!rcu_scheduler_active)
+ return;
+
+ init_completion(&rcu.completion);
+ /* Will wake me after RCU finished. */
+ call_rcu(&rcu.head, wakeme_after_rcu);
+ /* Wait for it. */
+ wait_for_completion(&rcu.completion);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu);
+
+static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq);
+static long sync_rcu_preempt_exp_count;
+static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex);
+
/*
- * Wait for an rcu-preempt grace period. We are supposed to expedite the
- * grace period, but this is the crude slow compatability hack, so just
- * invoke synchronize_rcu().
+ * Return non-zero if there are any tasks in RCU read-side critical
+ * sections blocking the current preemptible-RCU expedited grace period.
+ * If there is no preemptible-RCU expedited grace period currently in
+ * progress, returns zero unconditionally.
+ */
+static int rcu_preempted_readers_exp(struct rcu_node *rnp)
+{
+ return !list_empty(&rnp->blocked_tasks[2]) ||
+ !list_empty(&rnp->blocked_tasks[3]);
+}
+
+/*
+ * return non-zero if there is no RCU expedited grace period in progress
+ * for the specified rcu_node structure, in other words, if all CPUs and
+ * tasks covered by the specified rcu_node structure have done their bit
+ * for the current expedited grace period. Works only for preemptible
+ * RCU -- other RCU implementation use other means.
+ *
+ * Caller must hold sync_rcu_preempt_exp_mutex.
+ */
+static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
+{
+ return !rcu_preempted_readers_exp(rnp) &&
+ ACCESS_ONCE(rnp->expmask) == 0;
+}
+
+/*
+ * Report the exit from RCU read-side critical section for the last task
+ * that queued itself during or before the current expedited preemptible-RCU
+ * grace period. This event is reported either to the rcu_node structure on
+ * which the task was queued or to one of that rcu_node structure's ancestors,
+ * recursively up the tree. (Calm down, calm down, we do the recursion
+ * iteratively!)
+ *
+ * Caller must hold sync_rcu_preempt_exp_mutex.
+ */
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
+{
+ unsigned long flags;
+ unsigned long mask;
+
+ spin_lock_irqsave(&rnp->lock, flags);
+ for (;;) {
+ if (!sync_rcu_preempt_exp_done(rnp))
+ break;
+ if (rnp->parent == NULL) {
+ wake_up(&sync_rcu_preempt_exp_wq);
+ break;
+ }
+ mask = rnp->grpmask;
+ spin_unlock(&rnp->lock); /* irqs remain disabled */
+ rnp = rnp->parent;
+ spin_lock(&rnp->lock); /* irqs already disabled */
+ rnp->expmask &= ~mask;
+ }
+ spin_unlock_irqrestore(&rnp->lock, flags);
+}
+
+/*
+ * Snapshot the tasks blocking the newly started preemptible-RCU expedited
+ * grace period for the specified rcu_node structure. If there are no such
+ * tasks, report it up the rcu_node hierarchy.
+ *
+ * Caller must hold sync_rcu_preempt_exp_mutex and rsp->onofflock.
+ */
+static void
+sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
+{
+ int must_wait;
+
+ spin_lock(&rnp->lock); /* irqs already disabled */
+ list_splice_init(&rnp->blocked_tasks[0], &rnp->blocked_tasks[2]);
+ list_splice_init(&rnp->blocked_tasks[1], &rnp->blocked_tasks[3]);
+ must_wait = rcu_preempted_readers_exp(rnp);
+ spin_unlock(&rnp->lock); /* irqs remain disabled */
+ if (!must_wait)
+ rcu_report_exp_rnp(rsp, rnp);
+}
+
+/*
+ * Wait for an rcu-preempt grace period, but expedite it. The basic idea
+ * is to invoke synchronize_sched_expedited() to push all the tasks to
+ * the ->blocked_tasks[] lists, move all entries from the first set of
+ * ->blocked_tasks[] lists to the second set, and finally wait for this
+ * second set to drain.
*/
void synchronize_rcu_expedited(void)
{
- synchronize_rcu();
+ unsigned long flags;
+ struct rcu_node *rnp;
+ struct rcu_state *rsp = &rcu_preempt_state;
+ long snap;
+ int trycount = 0;
+
+ smp_mb(); /* Caller's modifications seen first by other CPUs. */
+ snap = ACCESS_ONCE(sync_rcu_preempt_exp_count) + 1;
+ smp_mb(); /* Above access cannot bleed into critical section. */
+
+ /*
+ * Acquire lock, falling back to synchronize_rcu() if too many
+ * lock-acquisition failures. Of course, if someone does the
+ * expedited grace period for us, just leave.
+ */
+ while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) {
+ if (trycount++ < 10)
+ udelay(trycount * num_online_cpus());
+ else {
+ synchronize_rcu();
+ return;
+ }
+ if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0)
+ goto mb_ret; /* Others did our work for us. */
+ }
+ if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0)
+ goto unlock_mb_ret; /* Others did our work for us. */
+
+ /* force all RCU readers onto blocked_tasks[]. */
+ synchronize_sched_expedited();
+
+ spin_lock_irqsave(&rsp->onofflock, flags);
+
+ /* Initialize ->expmask for all non-leaf rcu_node structures. */
+ rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
+ spin_lock(&rnp->lock); /* irqs already disabled. */
+ rnp->expmask = rnp->qsmaskinit;
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
+ }
+
+ /* Snapshot current state of ->blocked_tasks[] lists. */
+ rcu_for_each_leaf_node(rsp, rnp)
+ sync_rcu_preempt_exp_init(rsp, rnp);
+ if (NUM_RCU_NODES > 1)
+ sync_rcu_preempt_exp_init(rsp, rcu_get_root(rsp));
+
+ spin_unlock_irqrestore(&rsp->onofflock, flags);
+
+ /* Wait for snapshotted ->blocked_tasks[] lists to drain. */
+ rnp = rcu_get_root(rsp);
+ wait_event(sync_rcu_preempt_exp_wq,
+ sync_rcu_preempt_exp_done(rnp));
+
+ /* Clean up and exit. */
+ smp_mb(); /* ensure expedited GP seen before counter increment. */
+ ACCESS_ONCE(sync_rcu_preempt_exp_count)++;
+unlock_mb_ret:
+ mutex_unlock(&sync_rcu_preempt_exp_mutex);
+mb_ret:
+ smp_mb(); /* ensure subsequent action seen after grace period. */
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
@@ -481,7 +698,7 @@ void exit_rcu(void)
/*
* Tell them what RCU they are running.
*/
-static inline void rcu_bootup_announce(void)
+static void __init rcu_bootup_announce(void)
{
printk(KERN_INFO "Hierarchical RCU implementation.\n");
}
@@ -512,6 +729,16 @@ static int rcu_preempted_readers(struct rcu_node *rnp)
return 0;
}
+#ifdef CONFIG_HOTPLUG_CPU
+
+/* Because preemptible RCU does not exist, no quieting of tasks. */
+static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
+{
+ spin_unlock_irqrestore(&rnp->lock, flags);
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
/*
@@ -594,6 +821,20 @@ void synchronize_rcu_expedited(void)
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Because preemptable RCU does not exist, there is never any need to
+ * report on tasks preempted in RCU read-side critical sections during
+ * expedited RCU grace periods.
+ */
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
+{
+ return;
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
/*
* Because preemptable RCU does not exist, it never has any work to do.
*/
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index 4b31c779e62..9d2c88423b3 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -155,12 +155,15 @@ static const struct file_operations rcudata_csv_fops = {
static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
{
+ long gpnum;
int level = 0;
+ int phase;
struct rcu_node *rnp;
+ gpnum = rsp->gpnum;
seq_printf(m, "c=%ld g=%ld s=%d jfq=%ld j=%x "
"nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld\n",
- rsp->completed, rsp->gpnum, rsp->signaled,
+ rsp->completed, gpnum, rsp->signaled,
(long)(rsp->jiffies_force_qs - jiffies),
(int)(jiffies & 0xffff),
rsp->n_force_qs, rsp->n_force_qs_ngp,
@@ -171,8 +174,13 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
seq_puts(m, "\n");
level = rnp->level;
}
- seq_printf(m, "%lx/%lx %d:%d ^%d ",
+ phase = gpnum & 0x1;
+ seq_printf(m, "%lx/%lx %c%c>%c%c %d:%d ^%d ",
rnp->qsmask, rnp->qsmaskinit,
+ "T."[list_empty(&rnp->blocked_tasks[phase])],
+ "E."[list_empty(&rnp->blocked_tasks[phase + 2])],
+ "T."[list_empty(&rnp->blocked_tasks[!phase])],
+ "E."[list_empty(&rnp->blocked_tasks[!phase + 2])],
rnp->grplo, rnp->grphi, rnp->grpnum);
}
seq_puts(m, "\n");
diff --git a/kernel/resource.c b/kernel/resource.c
index fb11a58b959..dc15686b7a7 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -308,35 +308,37 @@ static int find_resource(struct resource *root, struct resource *new,
void *alignf_data)
{
struct resource *this = root->child;
+ resource_size_t start, end;
- new->start = root->start;
+ start = root->start;
/*
* Skip past an allocated resource that starts at 0, since the assignment
* of this->start - 1 to new->end below would cause an underflow.
*/
if (this && this->start == 0) {
- new->start = this->end + 1;
+ start = this->end + 1;
this = this->sibling;
}
for(;;) {
if (this)
- new->end = this->start - 1;
+ end = this->start - 1;
else
- new->end = root->end;
- if (new->start < min)
- new->start = min;
- if (new->end > max)
- new->end = max;
- new->start = ALIGN(new->start, align);
+ end = root->end;
+ if (start < min)
+ start = min;
+ if (end > max)
+ end = max;
+ start = ALIGN(start, align);
if (alignf)
alignf(alignf_data, new, size, align);
- if (new->start < new->end && new->end - new->start >= size - 1) {
- new->end = new->start + size - 1;
+ if (start < end && end - start >= size - 1) {
+ new->start = start;
+ new->end = start + size - 1;
return 0;
}
if (!this)
break;
- new->start = this->end + 1;
+ start = this->end + 1;
this = this->sibling;
}
return -EBUSY;
diff --git a/kernel/sched.c b/kernel/sched.c
index 3c11ae0a948..e7f2cfa6a25 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.
@@ -5481,7 +5527,7 @@ need_resched_nonpreemptible:
}
EXPORT_SYMBOL(schedule);
-#ifdef CONFIG_SMP
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
/*
* Look out! "owner" is an entirely speculative pointer
* access and not reliable.
@@ -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();
@@ -10901,6 +10978,7 @@ void synchronize_sched_expedited(void)
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)
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index efb84409bc4..6988cf08f70 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 37087a7fac2..f61837ad336 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 a4d790cddb1..5c5fef37841 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 93e72e5feae..6b982f2cf52 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -22,6 +22,7 @@
#include <linux/ptrace.h>
#include <linux/signal.h>
#include <linux/signalfd.h>
+#include <linux/ratelimit.h>
#include <linux/tracehook.h>
#include <linux/capability.h>
#include <linux/freezer.h>
@@ -42,6 +43,8 @@
static struct kmem_cache *sigqueue_cachep;
+int print_fatal_signals __read_mostly;
+
static void __user *sig_handler(struct task_struct *t, int sig)
{
return t->sighand->action[sig - 1].sa.sa_handler;
@@ -160,7 +163,7 @@ int next_signal(struct sigpending *pending, sigset_t *mask)
{
unsigned long i, *s, *m, x;
int sig = 0;
-
+
s = pending->signal.sig;
m = mask->sig;
switch (_NSIG_WORDS) {
@@ -185,17 +188,31 @@ int next_signal(struct sigpending *pending, sigset_t *mask)
sig = ffz(~x) + 1;
break;
}
-
+
return sig;
}
+static inline void print_dropped_signal(int sig)
+{
+ static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10);
+
+ if (!print_fatal_signals)
+ return;
+
+ if (!__ratelimit(&ratelimit_state))
+ return;
+
+ printk(KERN_INFO "%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n",
+ current->comm, current->pid, sig);
+}
+
/*
* allocate a new signal queue record
* - this may be called without locks if and only if t == current, otherwise an
* appopriate lock must be held to stop the target task from exiting
*/
-static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
- int override_rlimit)
+static struct sigqueue *
+__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit)
{
struct sigqueue *q = NULL;
struct user_struct *user;
@@ -208,10 +225,15 @@ static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
*/
user = get_uid(__task_cred(t)->user);
atomic_inc(&user->sigpending);
+
if (override_rlimit ||
atomic_read(&user->sigpending) <=
- t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur)
+ t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur) {
q = kmem_cache_alloc(sigqueue_cachep, flags);
+ } else {
+ print_dropped_signal(sig);
+ }
+
if (unlikely(q == NULL)) {
atomic_dec(&user->sigpending);
free_uid(user);
@@ -870,7 +892,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
else
override_rlimit = 0;
- q = __sigqueue_alloc(t, GFP_ATOMIC | __GFP_NOTRACK_FALSE_POSITIVE,
+ q = __sigqueue_alloc(sig, t, GFP_ATOMIC | __GFP_NOTRACK_FALSE_POSITIVE,
override_rlimit);
if (q) {
list_add_tail(&q->list, &pending->list);
@@ -935,8 +957,6 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
return __send_signal(sig, info, t, group, from_ancestor_ns);
}
-int print_fatal_signals;
-
static void print_fatal_signal(struct pt_regs *regs, int signr)
{
printk("%s/%d: potentially unexpected fatal signal %d.\n",
@@ -1303,19 +1323,19 @@ EXPORT_SYMBOL(kill_pid);
* These functions support sending signals using preallocated sigqueue
* structures. This is needed "because realtime applications cannot
* afford to lose notifications of asynchronous events, like timer
- * expirations or I/O completions". In the case of Posix Timers
+ * expirations or I/O completions". In the case of Posix Timers
* we allocate the sigqueue structure from the timer_create. If this
* allocation fails we are able to report the failure to the application
* with an EAGAIN error.
*/
-
struct sigqueue *sigqueue_alloc(void)
{
- struct sigqueue *q;
+ struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0);
- if ((q = __sigqueue_alloc(current, GFP_KERNEL, 0)))
+ if (q)
q->flags |= SIGQUEUE_PREALLOC;
- return(q);
+
+ return q;
}
void sigqueue_free(struct sigqueue *q)
diff --git a/kernel/slow-work-debugfs.c b/kernel/slow-work-debugfs.c
new file mode 100644
index 00000000000..e45c4364529
--- /dev/null
+++ b/kernel/slow-work-debugfs.c
@@ -0,0 +1,227 @@
+/* Slow work debugging
+ *
+ * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/slow-work.h>
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/seq_file.h>
+#include "slow-work.h"
+
+#define ITERATOR_SHIFT (BITS_PER_LONG - 4)
+#define ITERATOR_SELECTOR (0xfUL << ITERATOR_SHIFT)
+#define ITERATOR_COUNTER (~ITERATOR_SELECTOR)
+
+void slow_work_new_thread_desc(struct slow_work *work, struct seq_file *m)
+{
+ seq_puts(m, "Slow-work: New thread");
+}
+
+/*
+ * Render the time mark field on a work item into a 5-char time with units plus
+ * a space
+ */
+static void slow_work_print_mark(struct seq_file *m, struct slow_work *work)
+{
+ struct timespec now, diff;
+
+ now = CURRENT_TIME;
+ diff = timespec_sub(now, work->mark);
+
+ if (diff.tv_sec < 0)
+ seq_puts(m, " -ve ");
+ else if (diff.tv_sec == 0 && diff.tv_nsec < 1000)
+ seq_printf(m, "%3luns ", diff.tv_nsec);
+ else if (diff.tv_sec == 0 && diff.tv_nsec < 1000000)
+ seq_printf(m, "%3luus ", diff.tv_nsec / 1000);
+ else if (diff.tv_sec == 0 && diff.tv_nsec < 1000000000)
+ seq_printf(m, "%3lums ", diff.tv_nsec / 1000000);
+ else if (diff.tv_sec <= 1)
+ seq_puts(m, " 1s ");
+ else if (diff.tv_sec < 60)
+ seq_printf(m, "%4lus ", diff.tv_sec);
+ else if (diff.tv_sec < 60 * 60)
+ seq_printf(m, "%4lum ", diff.tv_sec / 60);
+ else if (diff.tv_sec < 60 * 60 * 24)
+ seq_printf(m, "%4luh ", diff.tv_sec / 3600);
+ else
+ seq_puts(m, "exces ");
+}
+
+/*
+ * Describe a slow work item for debugfs
+ */
+static int slow_work_runqueue_show(struct seq_file *m, void *v)
+{
+ struct slow_work *work;
+ struct list_head *p = v;
+ unsigned long id;
+
+ switch ((unsigned long) v) {
+ case 1:
+ seq_puts(m, "THR PID ITEM ADDR FL MARK DESC\n");
+ return 0;
+ case 2:
+ seq_puts(m, "=== ===== ================ == ===== ==========\n");
+ return 0;
+
+ case 3 ... 3 + SLOW_WORK_THREAD_LIMIT - 1:
+ id = (unsigned long) v - 3;
+
+ read_lock(&slow_work_execs_lock);
+ work = slow_work_execs[id];
+ if (work) {
+ smp_read_barrier_depends();
+
+ seq_printf(m, "%3lu %5d %16p %2lx ",
+ id, slow_work_pids[id], work, work->flags);
+ slow_work_print_mark(m, work);
+
+ if (work->ops->desc)
+ work->ops->desc(work, m);
+ seq_putc(m, '\n');
+ }
+ read_unlock(&slow_work_execs_lock);
+ return 0;
+
+ default:
+ work = list_entry(p, struct slow_work, link);
+ seq_printf(m, "%3s - %16p %2lx ",
+ work->flags & SLOW_WORK_VERY_SLOW ? "vsq" : "sq",
+ work, work->flags);
+ slow_work_print_mark(m, work);
+
+ if (work->ops->desc)
+ work->ops->desc(work, m);
+ seq_putc(m, '\n');
+ return 0;
+ }
+}
+
+/*
+ * map the iterator to a work item
+ */
+static void *slow_work_runqueue_index(struct seq_file *m, loff_t *_pos)
+{
+ struct list_head *p;
+ unsigned long count, id;
+
+ switch (*_pos >> ITERATOR_SHIFT) {
+ case 0x0:
+ if (*_pos == 0)
+ *_pos = 1;
+ if (*_pos < 3)
+ return (void *)(unsigned long) *_pos;
+ if (*_pos < 3 + SLOW_WORK_THREAD_LIMIT)
+ for (id = *_pos - 3;
+ id < SLOW_WORK_THREAD_LIMIT;
+ id++, (*_pos)++)
+ if (slow_work_execs[id])
+ return (void *)(unsigned long) *_pos;
+ *_pos = 0x1UL << ITERATOR_SHIFT;
+
+ case 0x1:
+ count = *_pos & ITERATOR_COUNTER;
+ list_for_each(p, &slow_work_queue) {
+ if (count == 0)
+ return p;
+ count--;
+ }
+ *_pos = 0x2UL << ITERATOR_SHIFT;
+
+ case 0x2:
+ count = *_pos & ITERATOR_COUNTER;
+ list_for_each(p, &vslow_work_queue) {
+ if (count == 0)
+ return p;
+ count--;
+ }
+ *_pos = 0x3UL << ITERATOR_SHIFT;
+
+ default:
+ return NULL;
+ }
+}
+
+/*
+ * set up the iterator to start reading from the first line
+ */
+static void *slow_work_runqueue_start(struct seq_file *m, loff_t *_pos)
+{
+ spin_lock_irq(&slow_work_queue_lock);
+ return slow_work_runqueue_index(m, _pos);
+}
+
+/*
+ * move to the next line
+ */
+static void *slow_work_runqueue_next(struct seq_file *m, void *v, loff_t *_pos)
+{
+ struct list_head *p = v;
+ unsigned long selector = *_pos >> ITERATOR_SHIFT;
+
+ (*_pos)++;
+ switch (selector) {
+ case 0x0:
+ return slow_work_runqueue_index(m, _pos);
+
+ case 0x1:
+ if (*_pos >> ITERATOR_SHIFT == 0x1) {
+ p = p->next;
+ if (p != &slow_work_queue)
+ return p;
+ }
+ *_pos = 0x2UL << ITERATOR_SHIFT;
+ p = &vslow_work_queue;
+
+ case 0x2:
+ if (*_pos >> ITERATOR_SHIFT == 0x2) {
+ p = p->next;
+ if (p != &vslow_work_queue)
+ return p;
+ }
+ *_pos = 0x3UL << ITERATOR_SHIFT;
+
+ default:
+ return NULL;
+ }
+}
+
+/*
+ * clean up after reading
+ */
+static void slow_work_runqueue_stop(struct seq_file *m, void *v)
+{
+ spin_unlock_irq(&slow_work_queue_lock);
+}
+
+static const struct seq_operations slow_work_runqueue_ops = {
+ .start = slow_work_runqueue_start,
+ .stop = slow_work_runqueue_stop,
+ .next = slow_work_runqueue_next,
+ .show = slow_work_runqueue_show,
+};
+
+/*
+ * open "/sys/kernel/debug/slow_work/runqueue" to list queue contents
+ */
+static int slow_work_runqueue_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &slow_work_runqueue_ops);
+}
+
+const struct file_operations slow_work_runqueue_fops = {
+ .owner = THIS_MODULE,
+ .open = slow_work_runqueue_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
diff --git a/kernel/slow-work.c b/kernel/slow-work.c
index 0d31135efbf..7494bbf5a27 100644
--- a/kernel/slow-work.c
+++ b/kernel/slow-work.c
@@ -16,11 +16,8 @@
#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);
@@ -46,13 +43,12 @@ static unsigned vslow_work_proportion = 50; /* % of threads that may process
#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),
@@ -62,7 +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),
@@ -72,16 +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
@@ -98,6 +92,56 @@ 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
* as the number of threads bears no relation to the number of CPUs.
@@ -105,9 +149,18 @@ static struct slow_work slow_work_new_thread; /* new thread starter */
* 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
@@ -126,6 +179,20 @@ static DECLARE_COMPLETION(slow_work_last_thread_exited);
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.
@@ -149,7 +216,7 @@ static unsigned slow_work_calc_vsmax(void)
* 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;
@@ -186,6 +253,13 @@ static bool slow_work_execute(void)
} 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)
@@ -194,12 +268,19 @@ static bool slow_work_execute(void)
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
@@ -219,7 +300,10 @@ static bool slow_work_execute(void)
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:
@@ -227,15 +311,61 @@ 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
*
@@ -260,16 +390,22 @@ auto_requeue:
* 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
@@ -280,8 +416,19 @@ int slow_work_enqueue(struct slow_work *work)
* 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
*
@@ -299,25 +446,221 @@ int slow_work_enqueue(struct slow_work *work)
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
*/
@@ -368,13 +711,23 @@ static inline bool slow_work_available(int vsmax)
*/
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);
@@ -395,7 +748,7 @@ static int slow_work_thread(void *_data)
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) &&
@@ -412,6 +765,11 @@ static int slow_work_thread(void *_data)
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;
@@ -427,21 +785,6 @@ static void slow_work_cull_timeout(unsigned long data)
}
/*
- * 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 void slow_work_new_thread_execute(struct slow_work *work)
@@ -475,9 +818,11 @@ static void slow_work_new_thread_execute(struct slow_work *work)
}
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
};
/*
@@ -546,12 +891,13 @@ static int slow_work_max_threads_sysctl(struct ctl_table *table, int write,
/**
* 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;
@@ -598,14 +944,81 @@ error:
}
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);
@@ -639,6 +1052,16 @@ static int __init init_slow_work(void)
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;
}
diff --git a/kernel/slow-work.h b/kernel/slow-work.h
new file mode 100644
index 00000000000..321f3c59d73
--- /dev/null
+++ b/kernel/slow-work.h
@@ -0,0 +1,72 @@
+/* Slow work private definitions
+ *
+ * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#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 */
+
+#define SLOW_WORK_THREAD_LIMIT 255 /* abs maximum number of slow-work threads */
+
+/*
+ * slow-work.c
+ */
+#ifdef CONFIG_SLOW_WORK_DEBUG
+extern struct slow_work *slow_work_execs[];
+extern pid_t slow_work_pids[];
+extern rwlock_t slow_work_execs_lock;
+#endif
+
+extern struct list_head slow_work_queue;
+extern struct list_head vslow_work_queue;
+extern spinlock_t slow_work_queue_lock;
+
+/*
+ * slow-work-debugfs.c
+ */
+#ifdef CONFIG_SLOW_WORK_DEBUG
+extern const struct file_operations slow_work_runqueue_fops;
+
+extern void slow_work_new_thread_desc(struct slow_work *, struct seq_file *);
+#endif
+
+/*
+ * Helper functions
+ */
+static inline void slow_work_set_thread_pid(int id, pid_t pid)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+ slow_work_pids[id] = pid;
+#endif
+}
+
+static inline void slow_work_mark_time(struct slow_work *work)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+ work->mark = CURRENT_TIME;
+#endif
+}
+
+static inline void slow_work_begin_exec(int id, struct slow_work *work)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+ slow_work_execs[id] = work;
+#endif
+}
+
+static inline void slow_work_end_exec(int id, struct slow_work *work)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+ write_lock(&slow_work_execs_lock);
+ slow_work_execs[id] = NULL;
+ write_unlock(&slow_work_execs_lock);
+#endif
+}
diff --git a/kernel/smp.c b/kernel/smp.c
index c9d1c7835c2..a8c76069cf5 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -265,9 +265,7 @@ static DEFINE_PER_CPU(struct call_single_data, csd_data);
* @info: An arbitrary pointer to pass to the function.
* @wait: If true, wait until function has completed on other CPUs.
*
- * Returns 0 on success, else a negative status code. Note that @wait
- * will be implicitly turned on in case of allocation failures, since
- * we fall back to on-stack allocation.
+ * Returns 0 on success, else a negative status code.
*/
int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
int wait)
@@ -321,6 +319,51 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
}
EXPORT_SYMBOL(smp_call_function_single);
+/*
+ * smp_call_function_any - Run a function on any of the given cpus
+ * @mask: The mask of cpus it can run on.
+ * @func: The function to run. This must be fast and non-blocking.
+ * @info: An arbitrary pointer to pass to the function.
+ * @wait: If true, wait until function has completed.
+ *
+ * Returns 0 on success, else a negative status code (if no cpus were online).
+ * Note that @wait will be implicitly turned on in case of allocation failures,
+ * since we fall back to on-stack allocation.
+ *
+ * Selection preference:
+ * 1) current cpu if in @mask
+ * 2) any cpu of current node if in @mask
+ * 3) any other online cpu in @mask
+ */
+int smp_call_function_any(const struct cpumask *mask,
+ void (*func)(void *info), void *info, int wait)
+{
+ unsigned int cpu;
+ const struct cpumask *nodemask;
+ int ret;
+
+ /* Try for same CPU (cheapest) */
+ cpu = get_cpu();
+ if (cpumask_test_cpu(cpu, mask))
+ goto call;
+
+ /* Try for same node. */
+ nodemask = cpumask_of_node(cpu);
+ for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids;
+ cpu = cpumask_next_and(cpu, nodemask, mask)) {
+ if (cpu_online(cpu))
+ goto call;
+ }
+
+ /* Any online will do: smp_call_function_single handles nr_cpu_ids. */
+ cpu = cpumask_any_and(mask, cpu_online_mask);
+call:
+ ret = smp_call_function_single(cpu, func, info, wait);
+ put_cpu();
+ return ret;
+}
+EXPORT_SYMBOL_GPL(smp_call_function_any);
+
/**
* __smp_call_function_single(): Run a function on another CPU
* @cpu: The CPU to run on.
@@ -355,9 +398,7 @@ void __smp_call_function_single(int cpu, struct call_single_data *data,
* @wait: If true, wait (atomically) until function has completed
* on other CPUs.
*
- * If @wait is true, then returns once @func has returned. Note that @wait
- * will be implicitly turned on in case of allocation failures, since
- * we fall back to on-stack allocation.
+ * If @wait is true, then returns once @func has returned.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler. Preemption
@@ -443,8 +484,7 @@ EXPORT_SYMBOL(smp_call_function_many);
* Returns 0.
*
* If @wait is true, then returns once @func has returned; otherwise
- * it returns just before the target cpu calls @func. In case of allocation
- * failure, @wait will be implicitly turned on.
+ * it returns just before the target cpu calls @func.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler.
diff --git a/kernel/softirq.c b/kernel/softirq.c
index f8749e5216e..21939d9e830 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -302,9 +302,9 @@ void irq_exit(void)
if (!in_interrupt() && local_softirq_pending())
invoke_softirq();
+ rcu_irq_exit();
#ifdef CONFIG_NO_HZ
/* Make sure that timer wheel updates are propagated */
- rcu_irq_exit();
if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched())
tick_nohz_stop_sched_tick(0);
#endif
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index 5ddab730cb2..41e042219ff 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -21,145 +21,28 @@
#include <linux/debug_locks.h>
#include <linux/module.h>
-#ifndef _spin_trylock
-int __lockfunc _spin_trylock(spinlock_t *lock)
-{
- return __spin_trylock(lock);
-}
-EXPORT_SYMBOL(_spin_trylock);
-#endif
-
-#ifndef _read_trylock
-int __lockfunc _read_trylock(rwlock_t *lock)
-{
- return __read_trylock(lock);
-}
-EXPORT_SYMBOL(_read_trylock);
-#endif
-
-#ifndef _write_trylock
-int __lockfunc _write_trylock(rwlock_t *lock)
-{
- return __write_trylock(lock);
-}
-EXPORT_SYMBOL(_write_trylock);
-#endif
-
/*
* If lockdep is enabled then we use the non-preemption spin-ops
* even on CONFIG_PREEMPT, because lockdep assumes that interrupts are
* not re-enabled during lock-acquire (which the preempt-spin-ops do):
*/
#if !defined(CONFIG_GENERIC_LOCKBREAK) || defined(CONFIG_DEBUG_LOCK_ALLOC)
-
-#ifndef _read_lock
-void __lockfunc _read_lock(rwlock_t *lock)
-{
- __read_lock(lock);
-}
-EXPORT_SYMBOL(_read_lock);
-#endif
-
-#ifndef _spin_lock_irqsave
-unsigned long __lockfunc _spin_lock_irqsave(spinlock_t *lock)
-{
- return __spin_lock_irqsave(lock);
-}
-EXPORT_SYMBOL(_spin_lock_irqsave);
-#endif
-
-#ifndef _spin_lock_irq
-void __lockfunc _spin_lock_irq(spinlock_t *lock)
-{
- __spin_lock_irq(lock);
-}
-EXPORT_SYMBOL(_spin_lock_irq);
-#endif
-
-#ifndef _spin_lock_bh
-void __lockfunc _spin_lock_bh(spinlock_t *lock)
-{
- __spin_lock_bh(lock);
-}
-EXPORT_SYMBOL(_spin_lock_bh);
-#endif
-
-#ifndef _read_lock_irqsave
-unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock)
-{
- return __read_lock_irqsave(lock);
-}
-EXPORT_SYMBOL(_read_lock_irqsave);
-#endif
-
-#ifndef _read_lock_irq
-void __lockfunc _read_lock_irq(rwlock_t *lock)
-{
- __read_lock_irq(lock);
-}
-EXPORT_SYMBOL(_read_lock_irq);
-#endif
-
-#ifndef _read_lock_bh
-void __lockfunc _read_lock_bh(rwlock_t *lock)
-{
- __read_lock_bh(lock);
-}
-EXPORT_SYMBOL(_read_lock_bh);
-#endif
-
-#ifndef _write_lock_irqsave
-unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock)
-{
- return __write_lock_irqsave(lock);
-}
-EXPORT_SYMBOL(_write_lock_irqsave);
-#endif
-
-#ifndef _write_lock_irq
-void __lockfunc _write_lock_irq(rwlock_t *lock)
-{
- __write_lock_irq(lock);
-}
-EXPORT_SYMBOL(_write_lock_irq);
-#endif
-
-#ifndef _write_lock_bh
-void __lockfunc _write_lock_bh(rwlock_t *lock)
-{
- __write_lock_bh(lock);
-}
-EXPORT_SYMBOL(_write_lock_bh);
-#endif
-
-#ifndef _spin_lock
-void __lockfunc _spin_lock(spinlock_t *lock)
-{
- __spin_lock(lock);
-}
-EXPORT_SYMBOL(_spin_lock);
-#endif
-
-#ifndef _write_lock
-void __lockfunc _write_lock(rwlock_t *lock)
-{
- __write_lock(lock);
-}
-EXPORT_SYMBOL(_write_lock);
-#endif
-
-#else /* CONFIG_PREEMPT: */
-
/*
+ * The __lock_function inlines are taken from
+ * include/linux/spinlock_api_smp.h
+ */
+#else
+/*
+ * We build the __lock_function inlines here. They are too large for
+ * inlining all over the place, but here is only one user per function
+ * which embedds them into the calling _lock_function below.
+ *
* This could be a long-held lock. We both prepare to spin for a long
* time (making _this_ CPU preemptable if possible), and we also signal
* towards that other CPU that it should break the lock ASAP.
- *
- * (We do this in a function because inlining it would be excessive.)
*/
-
#define BUILD_LOCK_OPS(op, locktype) \
-void __lockfunc _##op##_lock(locktype##_t *lock) \
+void __lockfunc __##op##_lock(locktype##_t *lock) \
{ \
for (;;) { \
preempt_disable(); \
@@ -175,9 +58,7 @@ void __lockfunc _##op##_lock(locktype##_t *lock) \
(lock)->break_lock = 0; \
} \
\
-EXPORT_SYMBOL(_##op##_lock); \
- \
-unsigned long __lockfunc _##op##_lock_irqsave(locktype##_t *lock) \
+unsigned long __lockfunc __##op##_lock_irqsave(locktype##_t *lock) \
{ \
unsigned long flags; \
\
@@ -198,16 +79,12 @@ unsigned long __lockfunc _##op##_lock_irqsave(locktype##_t *lock) \
return flags; \
} \
\
-EXPORT_SYMBOL(_##op##_lock_irqsave); \
- \
-void __lockfunc _##op##_lock_irq(locktype##_t *lock) \
+void __lockfunc __##op##_lock_irq(locktype##_t *lock) \
{ \
_##op##_lock_irqsave(lock); \
} \
\
-EXPORT_SYMBOL(_##op##_lock_irq); \
- \
-void __lockfunc _##op##_lock_bh(locktype##_t *lock) \
+void __lockfunc __##op##_lock_bh(locktype##_t *lock) \
{ \
unsigned long flags; \
\
@@ -220,23 +97,21 @@ void __lockfunc _##op##_lock_bh(locktype##_t *lock) \
local_bh_disable(); \
local_irq_restore(flags); \
} \
- \
-EXPORT_SYMBOL(_##op##_lock_bh)
/*
* Build preemption-friendly versions of the following
* lock-spinning functions:
*
- * _[spin|read|write]_lock()
- * _[spin|read|write]_lock_irq()
- * _[spin|read|write]_lock_irqsave()
- * _[spin|read|write]_lock_bh()
+ * __[spin|read|write]_lock()
+ * __[spin|read|write]_lock_irq()
+ * __[spin|read|write]_lock_irqsave()
+ * __[spin|read|write]_lock_bh()
*/
BUILD_LOCK_OPS(spin, spinlock);
BUILD_LOCK_OPS(read, rwlock);
BUILD_LOCK_OPS(write, rwlock);
-#endif /* CONFIG_PREEMPT */
+#endif
#ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -248,7 +123,8 @@ void __lockfunc _spin_lock_nested(spinlock_t *lock, int subclass)
}
EXPORT_SYMBOL(_spin_lock_nested);
-unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclass)
+unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock,
+ int subclass)
{
unsigned long flags;
@@ -272,7 +148,127 @@ EXPORT_SYMBOL(_spin_lock_nest_lock);
#endif
-#ifndef _spin_unlock
+#ifndef CONFIG_INLINE_SPIN_TRYLOCK
+int __lockfunc _spin_trylock(spinlock_t *lock)
+{
+ return __spin_trylock(lock);
+}
+EXPORT_SYMBOL(_spin_trylock);
+#endif
+
+#ifndef CONFIG_INLINE_READ_TRYLOCK
+int __lockfunc _read_trylock(rwlock_t *lock)
+{
+ return __read_trylock(lock);
+}
+EXPORT_SYMBOL(_read_trylock);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_TRYLOCK
+int __lockfunc _write_trylock(rwlock_t *lock)
+{
+ return __write_trylock(lock);
+}
+EXPORT_SYMBOL(_write_trylock);
+#endif
+
+#ifndef CONFIG_INLINE_READ_LOCK
+void __lockfunc _read_lock(rwlock_t *lock)
+{
+ __read_lock(lock);
+}
+EXPORT_SYMBOL(_read_lock);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_LOCK_IRQSAVE
+unsigned long __lockfunc _spin_lock_irqsave(spinlock_t *lock)
+{
+ return __spin_lock_irqsave(lock);
+}
+EXPORT_SYMBOL(_spin_lock_irqsave);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_LOCK_IRQ
+void __lockfunc _spin_lock_irq(spinlock_t *lock)
+{
+ __spin_lock_irq(lock);
+}
+EXPORT_SYMBOL(_spin_lock_irq);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_LOCK_BH
+void __lockfunc _spin_lock_bh(spinlock_t *lock)
+{
+ __spin_lock_bh(lock);
+}
+EXPORT_SYMBOL(_spin_lock_bh);
+#endif
+
+#ifndef CONFIG_INLINE_READ_LOCK_IRQSAVE
+unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock)
+{
+ return __read_lock_irqsave(lock);
+}
+EXPORT_SYMBOL(_read_lock_irqsave);
+#endif
+
+#ifndef CONFIG_INLINE_READ_LOCK_IRQ
+void __lockfunc _read_lock_irq(rwlock_t *lock)
+{
+ __read_lock_irq(lock);
+}
+EXPORT_SYMBOL(_read_lock_irq);
+#endif
+
+#ifndef CONFIG_INLINE_READ_LOCK_BH
+void __lockfunc _read_lock_bh(rwlock_t *lock)
+{
+ __read_lock_bh(lock);
+}
+EXPORT_SYMBOL(_read_lock_bh);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_LOCK_IRQSAVE
+unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock)
+{
+ return __write_lock_irqsave(lock);
+}
+EXPORT_SYMBOL(_write_lock_irqsave);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_LOCK_IRQ
+void __lockfunc _write_lock_irq(rwlock_t *lock)
+{
+ __write_lock_irq(lock);
+}
+EXPORT_SYMBOL(_write_lock_irq);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_LOCK_BH
+void __lockfunc _write_lock_bh(rwlock_t *lock)
+{
+ __write_lock_bh(lock);
+}
+EXPORT_SYMBOL(_write_lock_bh);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_LOCK
+void __lockfunc _spin_lock(spinlock_t *lock)
+{
+ __spin_lock(lock);
+}
+EXPORT_SYMBOL(_spin_lock);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_LOCK
+void __lockfunc _write_lock(rwlock_t *lock)
+{
+ __write_lock(lock);
+}
+EXPORT_SYMBOL(_write_lock);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_UNLOCK
void __lockfunc _spin_unlock(spinlock_t *lock)
{
__spin_unlock(lock);
@@ -280,7 +276,7 @@ void __lockfunc _spin_unlock(spinlock_t *lock)
EXPORT_SYMBOL(_spin_unlock);
#endif
-#ifndef _write_unlock
+#ifndef CONFIG_INLINE_WRITE_UNLOCK
void __lockfunc _write_unlock(rwlock_t *lock)
{
__write_unlock(lock);
@@ -288,7 +284,7 @@ void __lockfunc _write_unlock(rwlock_t *lock)
EXPORT_SYMBOL(_write_unlock);
#endif
-#ifndef _read_unlock
+#ifndef CONFIG_INLINE_READ_UNLOCK
void __lockfunc _read_unlock(rwlock_t *lock)
{
__read_unlock(lock);
@@ -296,7 +292,7 @@ void __lockfunc _read_unlock(rwlock_t *lock)
EXPORT_SYMBOL(_read_unlock);
#endif
-#ifndef _spin_unlock_irqrestore
+#ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE
void __lockfunc _spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags)
{
__spin_unlock_irqrestore(lock, flags);
@@ -304,7 +300,7 @@ void __lockfunc _spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags)
EXPORT_SYMBOL(_spin_unlock_irqrestore);
#endif
-#ifndef _spin_unlock_irq
+#ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQ
void __lockfunc _spin_unlock_irq(spinlock_t *lock)
{
__spin_unlock_irq(lock);
@@ -312,7 +308,7 @@ void __lockfunc _spin_unlock_irq(spinlock_t *lock)
EXPORT_SYMBOL(_spin_unlock_irq);
#endif
-#ifndef _spin_unlock_bh
+#ifndef CONFIG_INLINE_SPIN_UNLOCK_BH
void __lockfunc _spin_unlock_bh(spinlock_t *lock)
{
__spin_unlock_bh(lock);
@@ -320,7 +316,7 @@ void __lockfunc _spin_unlock_bh(spinlock_t *lock)
EXPORT_SYMBOL(_spin_unlock_bh);
#endif
-#ifndef _read_unlock_irqrestore
+#ifndef CONFIG_INLINE_READ_UNLOCK_IRQRESTORE
void __lockfunc _read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
{
__read_unlock_irqrestore(lock, flags);
@@ -328,7 +324,7 @@ void __lockfunc _read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
EXPORT_SYMBOL(_read_unlock_irqrestore);
#endif
-#ifndef _read_unlock_irq
+#ifndef CONFIG_INLINE_READ_UNLOCK_IRQ
void __lockfunc _read_unlock_irq(rwlock_t *lock)
{
__read_unlock_irq(lock);
@@ -336,7 +332,7 @@ void __lockfunc _read_unlock_irq(rwlock_t *lock)
EXPORT_SYMBOL(_read_unlock_irq);
#endif
-#ifndef _read_unlock_bh
+#ifndef CONFIG_INLINE_READ_UNLOCK_BH
void __lockfunc _read_unlock_bh(rwlock_t *lock)
{
__read_unlock_bh(lock);
@@ -344,7 +340,7 @@ void __lockfunc _read_unlock_bh(rwlock_t *lock)
EXPORT_SYMBOL(_read_unlock_bh);
#endif
-#ifndef _write_unlock_irqrestore
+#ifndef CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE
void __lockfunc _write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
{
__write_unlock_irqrestore(lock, flags);
@@ -352,7 +348,7 @@ void __lockfunc _write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
EXPORT_SYMBOL(_write_unlock_irqrestore);
#endif
-#ifndef _write_unlock_irq
+#ifndef CONFIG_INLINE_WRITE_UNLOCK_IRQ
void __lockfunc _write_unlock_irq(rwlock_t *lock)
{
__write_unlock_irq(lock);
@@ -360,7 +356,7 @@ void __lockfunc _write_unlock_irq(rwlock_t *lock)
EXPORT_SYMBOL(_write_unlock_irq);
#endif
-#ifndef _write_unlock_bh
+#ifndef CONFIG_INLINE_WRITE_UNLOCK_BH
void __lockfunc _write_unlock_bh(rwlock_t *lock)
{
__write_unlock_bh(lock);
@@ -368,7 +364,7 @@ void __lockfunc _write_unlock_bh(rwlock_t *lock)
EXPORT_SYMBOL(_write_unlock_bh);
#endif
-#ifndef _spin_trylock_bh
+#ifndef CONFIG_INLINE_SPIN_TRYLOCK_BH
int __lockfunc _spin_trylock_bh(spinlock_t *lock)
{
return __spin_trylock_bh(lock);
diff --git a/kernel/srcu.c b/kernel/srcu.c
index b0aeeaf22ce..818d7d9aa03 100644
--- a/kernel/srcu.c
+++ b/kernel/srcu.c
@@ -49,6 +49,7 @@ int init_srcu_struct(struct srcu_struct *sp)
sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array);
return (sp->per_cpu_ref ? 0 : -ENOMEM);
}
+EXPORT_SYMBOL_GPL(init_srcu_struct);
/*
* srcu_readers_active_idx -- returns approximate number of readers
@@ -97,6 +98,7 @@ void cleanup_srcu_struct(struct srcu_struct *sp)
free_percpu(sp->per_cpu_ref);
sp->per_cpu_ref = NULL;
}
+EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
/**
* srcu_read_lock - register a new reader for an SRCU-protected structure.
@@ -118,6 +120,7 @@ int srcu_read_lock(struct srcu_struct *sp)
preempt_enable();
return idx;
}
+EXPORT_SYMBOL_GPL(srcu_read_lock);
/**
* srcu_read_unlock - unregister a old reader from an SRCU-protected structure.
@@ -136,22 +139,12 @@ void srcu_read_unlock(struct srcu_struct *sp, int idx)
per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]--;
preempt_enable();
}
+EXPORT_SYMBOL_GPL(srcu_read_unlock);
-/**
- * synchronize_srcu - wait for prior SRCU read-side critical-section completion
- * @sp: srcu_struct with which to synchronize.
- *
- * Flip the completed counter, and wait for the old count to drain to zero.
- * As with classic RCU, the updater must use some separate means of
- * synchronizing concurrent updates. Can block; must be called from
- * process context.
- *
- * Note that it is illegal to call synchornize_srcu() from the corresponding
- * SRCU read-side critical section; doing so will result in deadlock.
- * However, it is perfectly legal to call synchronize_srcu() on one
- * srcu_struct from some other srcu_struct's read-side critical section.
+/*
+ * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
*/
-void synchronize_srcu(struct srcu_struct *sp)
+void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
{
int idx;
@@ -173,7 +166,7 @@ void synchronize_srcu(struct srcu_struct *sp)
return;
}
- synchronize_sched(); /* Force memory barrier on all CPUs. */
+ sync_func(); /* Force memory barrier on all CPUs. */
/*
* The preceding synchronize_sched() ensures that any CPU that
@@ -190,7 +183,7 @@ void synchronize_srcu(struct srcu_struct *sp)
idx = sp->completed & 0x1;
sp->completed++;
- synchronize_sched(); /* Force memory barrier on all CPUs. */
+ sync_func(); /* Force memory barrier on all CPUs. */
/*
* At this point, because of the preceding synchronize_sched(),
@@ -203,7 +196,7 @@ void synchronize_srcu(struct srcu_struct *sp)
while (srcu_readers_active_idx(sp, idx))
schedule_timeout_interruptible(1);
- synchronize_sched(); /* Force memory barrier on all CPUs. */
+ sync_func(); /* Force memory barrier on all CPUs. */
/*
* The preceding synchronize_sched() forces all srcu_read_unlock()
@@ -237,6 +230,47 @@ void synchronize_srcu(struct srcu_struct *sp)
}
/**
+ * synchronize_srcu - wait for prior SRCU read-side critical-section completion
+ * @sp: srcu_struct with which to synchronize.
+ *
+ * Flip the completed counter, and wait for the old count to drain to zero.
+ * As with classic RCU, the updater must use some separate means of
+ * synchronizing concurrent updates. Can block; must be called from
+ * process context.
+ *
+ * Note that it is illegal to call synchronize_srcu() from the corresponding
+ * SRCU read-side critical section; doing so will result in deadlock.
+ * However, it is perfectly legal to call synchronize_srcu() on one
+ * srcu_struct from some other srcu_struct's read-side critical section.
+ */
+void synchronize_srcu(struct srcu_struct *sp)
+{
+ __synchronize_srcu(sp, synchronize_sched);
+}
+EXPORT_SYMBOL_GPL(synchronize_srcu);
+
+/**
+ * synchronize_srcu_expedited - like synchronize_srcu, but less patient
+ * @sp: srcu_struct with which to synchronize.
+ *
+ * Flip the completed counter, and wait for the old count to drain to zero.
+ * As with classic RCU, the updater must use some separate means of
+ * synchronizing concurrent updates. Can block; must be called from
+ * process context.
+ *
+ * Note that it is illegal to call synchronize_srcu_expedited()
+ * from the corresponding SRCU read-side critical section; doing so
+ * will result in deadlock. However, it is perfectly legal to call
+ * synchronize_srcu_expedited() on one srcu_struct from some other
+ * srcu_struct's read-side critical section.
+ */
+void synchronize_srcu_expedited(struct srcu_struct *sp)
+{
+ __synchronize_srcu(sp, synchronize_sched_expedited);
+}
+EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
+
+/**
* srcu_batches_completed - return batches completed.
* @sp: srcu_struct on which to report batch completion.
*
@@ -248,10 +282,4 @@ long srcu_batches_completed(struct srcu_struct *sp)
{
return sp->completed;
}
-
-EXPORT_SYMBOL_GPL(init_srcu_struct);
-EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
-EXPORT_SYMBOL_GPL(srcu_read_lock);
-EXPORT_SYMBOL_GPL(srcu_read_unlock);
-EXPORT_SYMBOL_GPL(synchronize_srcu);
EXPORT_SYMBOL_GPL(srcu_batches_completed);
diff --git a/kernel/sys.c b/kernel/sys.c
index ce17760d9c5..585d6cd1004 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -8,7 +8,6 @@
#include <linux/mm.h>
#include <linux/utsname.h>
#include <linux/mman.h>
-#include <linux/smp_lock.h>
#include <linux/notifier.h>
#include <linux/reboot.h>
#include <linux/prctl.h>
@@ -349,6 +348,9 @@ void kernel_power_off(void)
machine_power_off();
}
EXPORT_SYMBOL_GPL(kernel_power_off);
+
+static DEFINE_MUTEX(reboot_mutex);
+
/*
* Reboot system call: for obvious reasons only root may call it,
* and even root needs to set up some magic numbers in the registers
@@ -381,7 +383,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
cmd = LINUX_REBOOT_CMD_HALT;
- lock_kernel();
+ mutex_lock(&reboot_mutex);
switch (cmd) {
case LINUX_REBOOT_CMD_RESTART:
kernel_restart(NULL);
@@ -397,20 +399,18 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
case LINUX_REBOOT_CMD_HALT:
kernel_halt();
- unlock_kernel();
do_exit(0);
panic("cannot halt");
case LINUX_REBOOT_CMD_POWER_OFF:
kernel_power_off();
- unlock_kernel();
do_exit(0);
break;
case LINUX_REBOOT_CMD_RESTART2:
if (strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1) < 0) {
- unlock_kernel();
- return -EFAULT;
+ ret = -EFAULT;
+ break;
}
buffer[sizeof(buffer) - 1] = '\0';
@@ -433,7 +433,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
ret = -EINVAL;
break;
}
- unlock_kernel();
+ mutex_unlock(&reboot_mutex);
return ret;
}
@@ -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 e06d0b8d195..695384f12a7 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -48,8 +48,10 @@ cond_syscall(sys_shutdown);
cond_syscall(sys_sendmsg);
cond_syscall(compat_sys_sendmsg);
cond_syscall(sys_recvmsg);
+cond_syscall(sys_recvmmsg);
cond_syscall(compat_sys_recvmsg);
cond_syscall(compat_sys_recvfrom);
+cond_syscall(compat_sys_recvmmsg);
cond_syscall(sys_socketcall);
cond_syscall(sys_futex);
cond_syscall(compat_sys_futex);
@@ -139,7 +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 0d949c51741..9327a26765c 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>
@@ -36,6 +35,7 @@
#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>
@@ -60,7 +60,6 @@
#include <asm/io.h>
#endif
-static int deprecated_sysctl_warning(struct __sysctl_args *args);
#if defined(CONFIG_SYSCTL)
@@ -158,6 +157,8 @@ extern int no_unaligned_warning;
extern int unaligned_dump_stack;
#endif
+extern struct ratelimit_state printk_ratelimit_state;
+
#ifdef CONFIG_RT_MUTEXES
extern int max_lock_depth;
#endif
@@ -207,31 +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,
@@ -240,7 +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
@@ -252,192 +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
@@ -446,181 +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
@@ -629,215 +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)
@@ -846,123 +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,
@@ -970,17 +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,
@@ -988,146 +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,
},
{
@@ -1135,31 +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,
},
@@ -1169,255 +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,
},
@@ -1427,116 +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
@@ -1545,19 +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,
@@ -1572,19 +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,
@@ -1594,13 +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),
@@ -1608,11 +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);
@@ -1766,122 +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.
@@ -1917,7 +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);
@@ -1949,11 +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)
@@ -1998,9 +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
*
@@ -2015,8 +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
@@ -2029,19 +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
@@ -2068,13 +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.
@@ -2091,7 +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;
@@ -2953,286 +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 :-)
@@ -3247,9 +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 00000000000..b75dbf40f57
--- /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 b6e7aaea460..04cdcf72c82 100644
--- a/kernel/sysctl_check.c
+++ b/kernel/sysctl_check.c
@@ -5,1239 +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" },
- {}
-};
-
-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)
{
@@ -1261,47 +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)
{
@@ -1315,26 +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,
@@ -1352,7 +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;
@@ -1361,10 +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--;
@@ -1392,38 +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)
{
@@ -1434,37 +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");
@@ -1477,21 +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) ||
@@ -1513,14 +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");
@@ -1531,7 +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 2e2e469a7fe..c6324d96009 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -136,7 +136,6 @@ static inline void warp_clock(void)
write_seqlock_irq(&xtime_lock);
wall_to_monotonic.tv_sec -= sys_tz.tz_minuteswest * 60;
xtime.tv_sec += sys_tz.tz_minuteswest * 60;
- update_xtime_cache(0);
write_sequnlock_irq(&xtime_lock);
clock_was_set();
}
@@ -662,6 +661,36 @@ 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/time/clockevents.c b/kernel/time/clockevents.c
index 620b58abdc3..20a8920029e 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -20,6 +20,8 @@
#include <linux/sysdev.h>
#include <linux/tick.h>
+#include "tick-internal.h"
+
/* The registered clock event devices */
static LIST_HEAD(clockevent_devices);
static LIST_HEAD(clockevents_released);
@@ -37,10 +39,9 @@ static DEFINE_SPINLOCK(clockevents_lock);
*
* Math helper, returns latch value converted to nanoseconds (bound checked)
*/
-unsigned long clockevent_delta2ns(unsigned long latch,
- struct clock_event_device *evt)
+u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
{
- u64 clc = ((u64) latch << evt->shift);
+ u64 clc = (u64) latch << evt->shift;
if (unlikely(!evt->mult)) {
evt->mult = 1;
@@ -50,10 +51,10 @@ unsigned long clockevent_delta2ns(unsigned long latch,
do_div(clc, evt->mult);
if (clc < 1000)
clc = 1000;
- if (clc > LONG_MAX)
- clc = LONG_MAX;
+ if (clc > KTIME_MAX)
+ clc = KTIME_MAX;
- return (unsigned long) clc;
+ return clc;
}
EXPORT_SYMBOL_GPL(clockevent_delta2ns);
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 5e18c6ab2c6..e85c23404d3 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -39,7 +39,7 @@ void timecounter_init(struct timecounter *tc,
tc->cycle_last = cc->read(cc);
tc->nsec = start_tstamp;
}
-EXPORT_SYMBOL(timecounter_init);
+EXPORT_SYMBOL_GPL(timecounter_init);
/**
* timecounter_read_delta - get nanoseconds since last call of this function
@@ -83,7 +83,7 @@ u64 timecounter_read(struct timecounter *tc)
return nsec;
}
-EXPORT_SYMBOL(timecounter_read);
+EXPORT_SYMBOL_GPL(timecounter_read);
u64 timecounter_cyc2time(struct timecounter *tc,
cycle_t cycle_tstamp)
@@ -105,7 +105,60 @@ u64 timecounter_cyc2time(struct timecounter *tc,
return nsec;
}
-EXPORT_SYMBOL(timecounter_cyc2time);
+EXPORT_SYMBOL_GPL(timecounter_cyc2time);
+
+/**
+ * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks
+ * @mult: pointer to mult variable
+ * @shift: pointer to shift variable
+ * @from: frequency to convert from
+ * @to: frequency to convert to
+ * @minsec: guaranteed runtime conversion range in seconds
+ *
+ * The function evaluates the shift/mult pair for the scaled math
+ * operations of clocksources and clockevents.
+ *
+ * @to and @from are frequency values in HZ. For clock sources @to is
+ * NSEC_PER_SEC == 1GHz and @from is the counter frequency. For clock
+ * event @to is the counter frequency and @from is NSEC_PER_SEC.
+ *
+ * The @minsec conversion range argument controls the time frame in
+ * seconds which must be covered by the runtime conversion with the
+ * calculated mult and shift factors. This guarantees that no 64bit
+ * overflow happens when the input value of the conversion is
+ * multiplied with the calculated mult factor. Larger ranges may
+ * reduce the conversion accuracy by chosing smaller mult and shift
+ * factors.
+ */
+void
+clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec)
+{
+ u64 tmp;
+ u32 sft, sftacc= 32;
+
+ /*
+ * Calculate the shift factor which is limiting the conversion
+ * range:
+ */
+ tmp = ((u64)minsec * from) >> 32;
+ while (tmp) {
+ tmp >>=1;
+ sftacc--;
+ }
+
+ /*
+ * Find the conversion shift/mult pair which has the best
+ * accuracy and fits the maxsec conversion range:
+ */
+ for (sft = 32; sft > 0; sft--) {
+ tmp = (u64) to << sft;
+ do_div(tmp, from);
+ if ((tmp >> sftacc) == 0)
+ break;
+ }
+ *mult = tmp;
+ *shift = sft;
+}
/*[Clocksource internal variables]---------
* curr_clocksource:
@@ -413,6 +466,47 @@ void clocksource_touch_watchdog(void)
clocksource_resume_watchdog();
}
+/**
+ * clocksource_max_deferment - Returns max time the clocksource can be deferred
+ * @cs: Pointer to clocksource
+ *
+ */
+static u64 clocksource_max_deferment(struct clocksource *cs)
+{
+ u64 max_nsecs, max_cycles;
+
+ /*
+ * Calculate the maximum number of cycles that we can pass to the
+ * cyc2ns function without overflowing a 64-bit signed result. The
+ * maximum number of cycles is equal to ULLONG_MAX/cs->mult which
+ * is equivalent to the below.
+ * max_cycles < (2^63)/cs->mult
+ * max_cycles < 2^(log2((2^63)/cs->mult))
+ * max_cycles < 2^(log2(2^63) - log2(cs->mult))
+ * max_cycles < 2^(63 - log2(cs->mult))
+ * max_cycles < 1 << (63 - log2(cs->mult))
+ * Please note that we add 1 to the result of the log2 to account for
+ * any rounding errors, ensure the above inequality is satisfied and
+ * no overflow will occur.
+ */
+ max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1));
+
+ /*
+ * The actual maximum number of cycles we can defer the clocksource is
+ * determined by the minimum of max_cycles and cs->mask.
+ */
+ max_cycles = min_t(u64, max_cycles, (u64) cs->mask);
+ max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift);
+
+ /*
+ * To ensure that the clocksource does not wrap whilst we are idle,
+ * limit the time the clocksource can be deferred by 12.5%. Please
+ * note a margin of 12.5% is used because this can be computed with
+ * a shift, versus say 10% which would require division.
+ */
+ return max_nsecs - (max_nsecs >> 5);
+}
+
#ifdef CONFIG_GENERIC_TIME
/**
@@ -511,6 +605,9 @@ static void clocksource_enqueue(struct clocksource *cs)
*/
int clocksource_register(struct clocksource *cs)
{
+ /* calculate max idle time permitted for this clocksource */
+ cs->max_idle_ns = clocksource_max_deferment(cs);
+
mutex_lock(&clocksource_mutex);
clocksource_enqueue(cs);
clocksource_select();
@@ -580,7 +677,7 @@ sysfs_show_current_clocksources(struct sys_device *dev,
* @count: length of buffer
*
* Takes input from sysfs interface for manually overriding the default
- * clocksource selction.
+ * clocksource selection.
*/
static ssize_t sysfs_override_clocksource(struct sys_device *dev,
struct sysdev_attribute *attr,
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index a96c0e2b89c..0a8a213016f 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -50,9 +50,9 @@ int tick_dev_program_event(struct clock_event_device *dev, ktime_t expires,
dev->min_delta_ns += dev->min_delta_ns >> 1;
printk(KERN_WARNING
- "CE: %s increasing min_delta_ns to %lu nsec\n",
+ "CE: %s increasing min_delta_ns to %llu nsec\n",
dev->name ? dev->name : "?",
- dev->min_delta_ns << 1);
+ (unsigned long long) dev->min_delta_ns << 1);
i = 0;
}
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 89aed5933ed..f992762d7f5 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -134,18 +134,13 @@ __setup("nohz=", setup_tick_nohz);
* value. We do this unconditionally on any cpu, as we don't know whether the
* cpu, which has the update task assigned is in a long sleep.
*/
-static void tick_nohz_update_jiffies(void)
+static void tick_nohz_update_jiffies(ktime_t now)
{
int cpu = smp_processor_id();
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
unsigned long flags;
- ktime_t now;
-
- if (!ts->tick_stopped)
- return;
cpumask_clear_cpu(cpu, nohz_cpu_mask);
- now = ktime_get();
ts->idle_waketime = now;
local_irq_save(flags);
@@ -155,20 +150,17 @@ static void tick_nohz_update_jiffies(void)
touch_softlockup_watchdog();
}
-static void tick_nohz_stop_idle(int cpu)
+static void tick_nohz_stop_idle(int cpu, ktime_t now)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ ktime_t delta;
- if (ts->idle_active) {
- ktime_t now, delta;
- now = ktime_get();
- delta = ktime_sub(now, ts->idle_entrytime);
- ts->idle_lastupdate = now;
- ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
- ts->idle_active = 0;
+ delta = ktime_sub(now, ts->idle_entrytime);
+ ts->idle_lastupdate = now;
+ ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+ ts->idle_active = 0;
- sched_clock_idle_wakeup_event(0);
- }
+ sched_clock_idle_wakeup_event(0);
}
static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
@@ -216,6 +208,7 @@ void tick_nohz_stop_sched_tick(int inidle)
struct tick_sched *ts;
ktime_t last_update, expires, now;
struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+ u64 time_delta;
int cpu;
local_irq_save(flags);
@@ -263,7 +256,7 @@ void tick_nohz_stop_sched_tick(int inidle)
if (ratelimit < 10) {
printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
- local_softirq_pending());
+ (unsigned int) local_softirq_pending());
ratelimit++;
}
goto end;
@@ -275,14 +268,18 @@ void tick_nohz_stop_sched_tick(int inidle)
seq = read_seqbegin(&xtime_lock);
last_update = last_jiffies_update;
last_jiffies = jiffies;
+ time_delta = timekeeping_max_deferment();
} while (read_seqretry(&xtime_lock, seq));
- /* Get the next timer wheel timer */
- next_jiffies = get_next_timer_interrupt(last_jiffies);
- delta_jiffies = next_jiffies - last_jiffies;
-
- if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu))
+ if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) ||
+ arch_needs_cpu(cpu)) {
+ next_jiffies = last_jiffies + 1;
delta_jiffies = 1;
+ } else {
+ /* Get the next timer wheel timer */
+ next_jiffies = get_next_timer_interrupt(last_jiffies);
+ delta_jiffies = next_jiffies - last_jiffies;
+ }
/*
* Do not stop the tick, if we are only one off
* or if the cpu is required for rcu
@@ -294,22 +291,51 @@ void tick_nohz_stop_sched_tick(int inidle)
if ((long)delta_jiffies >= 1) {
/*
- * calculate the expiry time for the next timer wheel
- * timer
- */
- expires = ktime_add_ns(last_update, tick_period.tv64 *
- delta_jiffies);
-
- /*
* If this cpu is the one which updates jiffies, then
* give up the assignment and let it be taken by the
* cpu which runs the tick timer next, which might be
* this cpu as well. If we don't drop this here the
* jiffies might be stale and do_timer() never
- * invoked.
+ * invoked. Keep track of the fact that it was the one
+ * which had the do_timer() duty last. If this cpu is
+ * the one which had the do_timer() duty last, we
+ * limit the sleep time to the timekeeping
+ * max_deferement value which we retrieved
+ * above. Otherwise we can sleep as long as we want.
*/
- if (cpu == tick_do_timer_cpu)
+ if (cpu == tick_do_timer_cpu) {
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+ ts->do_timer_last = 1;
+ } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
+ time_delta = KTIME_MAX;
+ ts->do_timer_last = 0;
+ } else if (!ts->do_timer_last) {
+ time_delta = KTIME_MAX;
+ }
+
+ /*
+ * calculate the expiry time for the next timer wheel
+ * timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals
+ * that there is no timer pending or at least extremely
+ * far into the future (12 days for HZ=1000). In this
+ * case we set the expiry to the end of time.
+ */
+ if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) {
+ /*
+ * Calculate the time delta for the next timer event.
+ * If the time delta exceeds the maximum time delta
+ * permitted by the current clocksource then adjust
+ * the time delta accordingly to ensure the
+ * clocksource does not wrap.
+ */
+ time_delta = min_t(u64, time_delta,
+ tick_period.tv64 * delta_jiffies);
+ }
+
+ if (time_delta < KTIME_MAX)
+ expires = ktime_add_ns(last_update, time_delta);
+ else
+ expires.tv64 = KTIME_MAX;
if (delta_jiffies > 1)
cpumask_set_cpu(cpu, nohz_cpu_mask);
@@ -342,22 +368,19 @@ void tick_nohz_stop_sched_tick(int inidle)
ts->idle_sleeps++;
+ /* Mark expires */
+ ts->idle_expires = expires;
+
/*
- * delta_jiffies >= NEXT_TIMER_MAX_DELTA signals that
- * there is no timer pending or at least extremly far
- * into the future (12 days for HZ=1000). In this case
- * we simply stop the tick timer:
+ * If the expiration time == KTIME_MAX, then
+ * in this case we simply stop the tick timer.
*/
- if (unlikely(delta_jiffies >= NEXT_TIMER_MAX_DELTA)) {
- ts->idle_expires.tv64 = KTIME_MAX;
+ if (unlikely(expires.tv64 == KTIME_MAX)) {
if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
hrtimer_cancel(&ts->sched_timer);
goto out;
}
- /* Mark expiries */
- ts->idle_expires = expires;
-
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
hrtimer_start(&ts->sched_timer, expires,
HRTIMER_MODE_ABS_PINNED);
@@ -436,7 +459,11 @@ void tick_nohz_restart_sched_tick(void)
ktime_t now;
local_irq_disable();
- tick_nohz_stop_idle(cpu);
+ if (ts->idle_active || (ts->inidle && ts->tick_stopped))
+ now = ktime_get();
+
+ if (ts->idle_active)
+ tick_nohz_stop_idle(cpu, now);
if (!ts->inidle || !ts->tick_stopped) {
ts->inidle = 0;
@@ -450,7 +477,6 @@ void tick_nohz_restart_sched_tick(void)
/* Update jiffies first */
select_nohz_load_balancer(0);
- now = ktime_get();
tick_do_update_jiffies64(now);
cpumask_clear_cpu(cpu, nohz_cpu_mask);
@@ -584,22 +610,18 @@ static void tick_nohz_switch_to_nohz(void)
* timer and do not touch the other magic bits which need to be done
* when idle is left.
*/
-static void tick_nohz_kick_tick(int cpu)
+static void tick_nohz_kick_tick(int cpu, ktime_t now)
{
#if 0
/* Switch back to 2.6.27 behaviour */
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
- ktime_t delta, now;
-
- if (!ts->tick_stopped)
- return;
+ ktime_t delta;
/*
* Do not touch the tick device, when the next expiry is either
* already reached or less/equal than the tick period.
*/
- now = ktime_get();
delta = ktime_sub(hrtimer_get_expires(&ts->sched_timer), now);
if (delta.tv64 <= tick_period.tv64)
return;
@@ -608,9 +630,26 @@ static void tick_nohz_kick_tick(int cpu)
#endif
}
+static inline void tick_check_nohz(int cpu)
+{
+ struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ ktime_t now;
+
+ if (!ts->idle_active && !ts->tick_stopped)
+ return;
+ now = ktime_get();
+ if (ts->idle_active)
+ tick_nohz_stop_idle(cpu, now);
+ if (ts->tick_stopped) {
+ tick_nohz_update_jiffies(now);
+ tick_nohz_kick_tick(cpu, now);
+ }
+}
+
#else
static inline void tick_nohz_switch_to_nohz(void) { }
+static inline void tick_check_nohz(int cpu) { }
#endif /* NO_HZ */
@@ -620,11 +659,7 @@ static inline void tick_nohz_switch_to_nohz(void) { }
void tick_check_idle(int cpu)
{
tick_check_oneshot_broadcast(cpu);
-#ifdef CONFIG_NO_HZ
- tick_nohz_stop_idle(cpu);
- tick_nohz_update_jiffies();
- tick_nohz_kick_tick(cpu);
-#endif
+ tick_check_nohz(cpu);
}
/*
diff --git a/kernel/time/timecompare.c b/kernel/time/timecompare.c
index 71e7f1a1915..96ff643a5a5 100644
--- a/kernel/time/timecompare.c
+++ b/kernel/time/timecompare.c
@@ -40,7 +40,7 @@ ktime_t timecompare_transform(struct timecompare *sync,
return ns_to_ktime(nsec);
}
-EXPORT_SYMBOL(timecompare_transform);
+EXPORT_SYMBOL_GPL(timecompare_transform);
int timecompare_offset(struct timecompare *sync,
s64 *offset,
@@ -131,7 +131,7 @@ int timecompare_offset(struct timecompare *sync,
return used;
}
-EXPORT_SYMBOL(timecompare_offset);
+EXPORT_SYMBOL_GPL(timecompare_offset);
void __timecompare_update(struct timecompare *sync,
u64 source_tstamp)
@@ -188,4 +188,4 @@ void __timecompare_update(struct timecompare *sync,
}
}
}
-EXPORT_SYMBOL(__timecompare_update);
+EXPORT_SYMBOL_GPL(__timecompare_update);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index c3a4e2907ea..af4135f0582 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -165,19 +165,12 @@ struct timespec raw_time;
/* flag for if timekeeping is suspended */
int __read_mostly timekeeping_suspended;
-static struct timespec xtime_cache __attribute__ ((aligned (16)));
-void update_xtime_cache(u64 nsec)
-{
- xtime_cache = xtime;
- timespec_add_ns(&xtime_cache, nsec);
-}
-
/* must hold xtime_lock */
void timekeeping_leap_insert(int leapsecond)
{
xtime.tv_sec += leapsecond;
wall_to_monotonic.tv_sec -= leapsecond;
- update_vsyscall(&xtime, timekeeper.clock);
+ update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
}
#ifdef CONFIG_GENERIC_TIME
@@ -332,12 +325,10 @@ int do_settimeofday(struct timespec *tv)
xtime = *tv;
- update_xtime_cache(0);
-
timekeeper.ntp_error = 0;
ntp_clear();
- update_vsyscall(&xtime, timekeeper.clock);
+ update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -488,6 +479,17 @@ int timekeeping_valid_for_hres(void)
}
/**
+ * timekeeping_max_deferment - Returns max time the clocksource can be deferred
+ *
+ * Caller must observe xtime_lock via read_seqbegin/read_seqretry to
+ * ensure that the clocksource does not change!
+ */
+u64 timekeeping_max_deferment(void)
+{
+ return timekeeper.clock->max_idle_ns;
+}
+
+/**
* read_persistent_clock - Return time from the persistent clock.
*
* Weak dummy function for arches that do not yet support it.
@@ -548,7 +550,6 @@ void __init timekeeping_init(void)
}
set_normalized_timespec(&wall_to_monotonic,
-boot.tv_sec, -boot.tv_nsec);
- update_xtime_cache(0);
total_sleep_time.tv_sec = 0;
total_sleep_time.tv_nsec = 0;
write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -582,7 +583,6 @@ static int timekeeping_resume(struct sys_device *dev)
wall_to_monotonic = timespec_sub(wall_to_monotonic, ts);
total_sleep_time = timespec_add_safe(total_sleep_time, ts);
}
- update_xtime_cache(0);
/* re-base the last cycle value */
timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
timekeeper.ntp_error = 0;
@@ -723,6 +723,49 @@ static void timekeeping_adjust(s64 offset)
}
/**
+ * logarithmic_accumulation - shifted accumulation of cycles
+ *
+ * This functions accumulates a shifted interval of cycles into
+ * into a shifted interval nanoseconds. Allows for O(log) accumulation
+ * loop.
+ *
+ * Returns the unconsumed cycles.
+ */
+static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
+{
+ u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
+
+ /* If the offset is smaller then a shifted interval, do nothing */
+ if (offset < timekeeper.cycle_interval<<shift)
+ return offset;
+
+ /* Accumulate one shifted interval */
+ offset -= timekeeper.cycle_interval << shift;
+ timekeeper.clock->cycle_last += timekeeper.cycle_interval << shift;
+
+ timekeeper.xtime_nsec += timekeeper.xtime_interval << shift;
+ while (timekeeper.xtime_nsec >= nsecps) {
+ timekeeper.xtime_nsec -= nsecps;
+ xtime.tv_sec++;
+ second_overflow();
+ }
+
+ /* Accumulate into raw time */
+ raw_time.tv_nsec += timekeeper.raw_interval << shift;;
+ while (raw_time.tv_nsec >= NSEC_PER_SEC) {
+ raw_time.tv_nsec -= NSEC_PER_SEC;
+ raw_time.tv_sec++;
+ }
+
+ /* Accumulate error between NTP and clock interval */
+ timekeeper.ntp_error += tick_length << shift;
+ timekeeper.ntp_error -= timekeeper.xtime_interval <<
+ (timekeeper.ntp_error_shift + shift);
+
+ return offset;
+}
+
+/**
* update_wall_time - Uses the current clocksource to increment the wall time
*
* Called from the timer interrupt, must hold a write on xtime_lock.
@@ -731,7 +774,7 @@ void update_wall_time(void)
{
struct clocksource *clock;
cycle_t offset;
- u64 nsecs;
+ int shift = 0, maxshift;
/* Make sure we're fully resumed: */
if (unlikely(timekeeping_suspended))
@@ -745,33 +788,22 @@ void update_wall_time(void)
#endif
timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift;
- /* normally this loop will run just once, however in the
- * case of lost or late ticks, it will accumulate correctly.
+ /*
+ * With NO_HZ we may have to accumulate many cycle_intervals
+ * (think "ticks") worth of time at once. To do this efficiently,
+ * we calculate the largest doubling multiple of cycle_intervals
+ * that is smaller then the offset. We then accumulate that
+ * chunk in one go, and then try to consume the next smaller
+ * doubled multiple.
*/
+ shift = ilog2(offset) - ilog2(timekeeper.cycle_interval);
+ shift = max(0, shift);
+ /* Bound shift to one less then what overflows tick_length */
+ maxshift = (8*sizeof(tick_length) - (ilog2(tick_length)+1)) - 1;
+ shift = min(shift, maxshift);
while (offset >= timekeeper.cycle_interval) {
- u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
-
- /* accumulate one interval */
- offset -= timekeeper.cycle_interval;
- clock->cycle_last += timekeeper.cycle_interval;
-
- timekeeper.xtime_nsec += timekeeper.xtime_interval;
- if (timekeeper.xtime_nsec >= nsecps) {
- timekeeper.xtime_nsec -= nsecps;
- xtime.tv_sec++;
- second_overflow();
- }
-
- raw_time.tv_nsec += timekeeper.raw_interval;
- if (raw_time.tv_nsec >= NSEC_PER_SEC) {
- raw_time.tv_nsec -= NSEC_PER_SEC;
- raw_time.tv_sec++;
- }
-
- /* accumulate error between NTP and clock interval */
- timekeeper.ntp_error += tick_length;
- timekeeper.ntp_error -= timekeeper.xtime_interval <<
- timekeeper.ntp_error_shift;
+ offset = logarithmic_accumulation(offset, shift);
+ shift--;
}
/* correct the clock when NTP error is too big */
@@ -807,11 +839,8 @@ void update_wall_time(void)
timekeeper.ntp_error += timekeeper.xtime_nsec <<
timekeeper.ntp_error_shift;
- nsecs = clocksource_cyc2ns(offset, timekeeper.mult, timekeeper.shift);
- update_xtime_cache(nsecs);
-
/* check to see if there is a new clocksource to use */
- update_vsyscall(&xtime, timekeeper.clock);
+ update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
}
/**
@@ -846,13 +875,13 @@ void monotonic_to_bootbased(struct timespec *ts)
unsigned long get_seconds(void)
{
- return xtime_cache.tv_sec;
+ return xtime.tv_sec;
}
EXPORT_SYMBOL(get_seconds);
struct timespec __current_kernel_time(void)
{
- return xtime_cache;
+ return xtime;
}
struct timespec current_kernel_time(void)
@@ -862,8 +891,7 @@ struct timespec current_kernel_time(void)
do {
seq = read_seqbegin(&xtime_lock);
-
- now = xtime_cache;
+ now = xtime;
} while (read_seqretry(&xtime_lock, seq));
return now;
@@ -877,8 +905,7 @@ struct timespec get_monotonic_coarse(void)
do {
seq = read_seqbegin(&xtime_lock);
-
- now = xtime_cache;
+ now = xtime;
mono = wall_to_monotonic;
} while (read_seqretry(&xtime_lock, seq));
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 1b5b7aa2fdf..665c76edbf1 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -204,10 +204,12 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
return;
}
SEQ_printf(m, "%s\n", dev->name);
- SEQ_printf(m, " max_delta_ns: %lu\n", dev->max_delta_ns);
- SEQ_printf(m, " min_delta_ns: %lu\n", dev->min_delta_ns);
- SEQ_printf(m, " mult: %lu\n", dev->mult);
- SEQ_printf(m, " shift: %d\n", dev->shift);
+ SEQ_printf(m, " max_delta_ns: %llu\n",
+ (unsigned long long) dev->max_delta_ns);
+ SEQ_printf(m, " min_delta_ns: %llu\n",
+ (unsigned long long) dev->min_delta_ns);
+ SEQ_printf(m, " mult: %u\n", dev->mult);
+ SEQ_printf(m, " shift: %u\n", dev->shift);
SEQ_printf(m, " mode: %d\n", dev->mode);
SEQ_printf(m, " next_event: %Ld nsecs\n",
(unsigned long long) ktime_to_ns(dev->next_event));
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 7cb6f192259..e51a1bcb7be 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2274,7 +2274,6 @@ void ftrace_set_notrace(unsigned char *buf, int len, int reset)
#define FTRACE_FILTER_SIZE COMMAND_LINE_SIZE
static char ftrace_notrace_buf[FTRACE_FILTER_SIZE] __initdata;
static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata;
-static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
static int __init set_ftrace_notrace(char *str)
{
@@ -2291,6 +2290,7 @@ static int __init set_ftrace_filter(char *str)
__setup("ftrace_filter=", set_ftrace_filter);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
static int __init set_graph_function(char *str)
{
strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
@@ -2985,7 +2985,7 @@ static ssize_t
ftrace_pid_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- char buf[64];
+ char buf[64], *tmp;
long val;
int ret;
@@ -3001,11 +3001,11 @@ ftrace_pid_write(struct file *filp, const char __user *ubuf,
* Allow "echo > set_ftrace_pid" or "echo -n '' > set_ftrace_pid"
* to clean the filter quietly.
*/
- strstrip(buf);
- if (strlen(buf) == 0)
+ tmp = strstrip(buf);
+ if (strlen(tmp) == 0)
return 1;
- ret = strict_strtol(buf, 10, &val);
+ ret = strict_strtol(tmp, 10, &val);
if (ret < 0)
return ret;
@@ -3391,4 +3391,3 @@ void ftrace_graph_stop(void)
ftrace_stop();
}
#endif
-
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index db223fe8887..a1ca4956ab5 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1790,9 +1790,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
static struct ring_buffer_event *
rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
unsigned long length, unsigned long tail,
- struct buffer_page *commit_page,
struct buffer_page *tail_page, u64 *ts)
{
+ struct buffer_page *commit_page = cpu_buffer->commit_page;
struct ring_buffer *buffer = cpu_buffer->buffer;
struct buffer_page *next_page;
int ret;
@@ -1895,13 +1895,10 @@ static struct ring_buffer_event *
__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
unsigned type, unsigned long length, u64 *ts)
{
- struct buffer_page *tail_page, *commit_page;
+ struct buffer_page *tail_page;
struct ring_buffer_event *event;
unsigned long tail, write;
- commit_page = cpu_buffer->commit_page;
- /* we just need to protect against interrupts */
- barrier();
tail_page = cpu_buffer->tail_page;
write = local_add_return(length, &tail_page->write);
@@ -1912,7 +1909,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
/* See if we shot pass the end of this buffer page */
if (write > BUF_PAGE_SIZE)
return rb_move_tail(cpu_buffer, length, tail,
- commit_page, tail_page, ts);
+ tail_page, ts);
/* We reserved something on the buffer */
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 573d3cc762c..b2477caf09c 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -35,6 +35,28 @@ static int disable_reader;
module_param(disable_reader, uint, 0644);
MODULE_PARM_DESC(disable_reader, "only run producer");
+static int write_iteration = 50;
+module_param(write_iteration, uint, 0644);
+MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings");
+
+static int producer_nice = 19;
+static int consumer_nice = 19;
+
+static int producer_fifo = -1;
+static int consumer_fifo = -1;
+
+module_param(producer_nice, uint, 0644);
+MODULE_PARM_DESC(producer_nice, "nice prio for producer");
+
+module_param(consumer_nice, uint, 0644);
+MODULE_PARM_DESC(consumer_nice, "nice prio for consumer");
+
+module_param(producer_fifo, uint, 0644);
+MODULE_PARM_DESC(producer_fifo, "fifo prio for producer");
+
+module_param(consumer_fifo, uint, 0644);
+MODULE_PARM_DESC(consumer_fifo, "fifo prio for consumer");
+
static int read_events;
static int kill_test;
@@ -208,15 +230,18 @@ static void ring_buffer_producer(void)
do {
struct ring_buffer_event *event;
int *entry;
-
- event = ring_buffer_lock_reserve(buffer, 10);
- if (!event) {
- missed++;
- } else {
- hit++;
- entry = ring_buffer_event_data(event);
- *entry = smp_processor_id();
- ring_buffer_unlock_commit(buffer, event);
+ int i;
+
+ for (i = 0; i < write_iteration; i++) {
+ event = ring_buffer_lock_reserve(buffer, 10);
+ if (!event) {
+ missed++;
+ } else {
+ hit++;
+ entry = ring_buffer_event_data(event);
+ *entry = smp_processor_id();
+ ring_buffer_unlock_commit(buffer, event);
+ }
}
do_gettimeofday(&end_tv);
@@ -263,6 +288,27 @@ static void ring_buffer_producer(void)
if (kill_test)
trace_printk("ERROR!\n");
+
+ if (!disable_reader) {
+ if (consumer_fifo < 0)
+ trace_printk("Running Consumer at nice: %d\n",
+ consumer_nice);
+ else
+ trace_printk("Running Consumer at SCHED_FIFO %d\n",
+ consumer_fifo);
+ }
+ if (producer_fifo < 0)
+ trace_printk("Running Producer at nice: %d\n",
+ producer_nice);
+ else
+ trace_printk("Running Producer at SCHED_FIFO %d\n",
+ producer_fifo);
+
+ /* Let the user know that the test is running at low priority */
+ if (producer_fifo < 0 && consumer_fifo < 0 &&
+ producer_nice == 19 && consumer_nice == 19)
+ trace_printk("WARNING!!! This test is running at lowest priority.\n");
+
trace_printk("Time: %lld (usecs)\n", time);
trace_printk("Overruns: %lld\n", overruns);
if (disable_reader)
@@ -392,6 +438,27 @@ static int __init ring_buffer_benchmark_init(void)
if (IS_ERR(producer))
goto out_kill;
+ /*
+ * Run them as low-prio background tasks by default:
+ */
+ if (!disable_reader) {
+ if (consumer_fifo >= 0) {
+ struct sched_param param = {
+ .sched_priority = consumer_fifo
+ };
+ sched_setscheduler(consumer, SCHED_FIFO, &param);
+ } else
+ set_user_nice(consumer, consumer_nice);
+ }
+
+ if (producer_fifo >= 0) {
+ struct sched_param param = {
+ .sched_priority = consumer_fifo
+ };
+ sched_setscheduler(producer, SCHED_FIFO, &param);
+ } else
+ set_user_nice(producer, producer_nice);
+
return 0;
out_kill:
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 9d3067a62d4..874f2893cff 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1361,10 +1361,11 @@ int trace_array_vprintk(struct trace_array *tr,
pause_graph_tracing();
raw_local_irq_save(irq_flags);
__raw_spin_lock(&trace_buf_lock);
- len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args);
-
- len = min(len, TRACE_BUF_SIZE-1);
- trace_buf[len] = 0;
+ if (args == NULL) {
+ strncpy(trace_buf, fmt, TRACE_BUF_SIZE);
+ len = strlen(trace_buf);
+ } else
+ len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args);
size = sizeof(*entry) + len + 1;
buffer = tr->buffer;
@@ -1373,10 +1374,10 @@ int trace_array_vprintk(struct trace_array *tr,
if (!event)
goto out_unlock;
entry = ring_buffer_event_data(event);
- entry->ip = ip;
+ entry->ip = ip;
memcpy(&entry->buf, trace_buf, len);
- entry->buf[len] = 0;
+ entry->buf[len] = '\0';
if (!filter_check_discard(call, entry, buffer, event))
ring_buffer_unlock_commit(buffer, event);
@@ -3319,22 +3320,11 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
return cnt;
}
-static int mark_printk(const char *fmt, ...)
-{
- int ret;
- va_list args;
- va_start(args, fmt);
- ret = trace_vprintk(0, fmt, args);
- va_end(args);
- return ret;
-}
-
static ssize_t
tracing_mark_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *fpos)
{
char *buf;
- char *end;
if (tracing_disabled)
return -EINVAL;
@@ -3342,7 +3332,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
if (cnt > TRACE_BUF_SIZE)
cnt = TRACE_BUF_SIZE;
- buf = kmalloc(cnt + 1, GFP_KERNEL);
+ buf = kmalloc(cnt + 2, GFP_KERNEL);
if (buf == NULL)
return -ENOMEM;
@@ -3350,14 +3340,13 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
kfree(buf);
return -EFAULT;
}
+ if (buf[cnt-1] != '\n') {
+ buf[cnt] = '\n';
+ buf[cnt+1] = '\0';
+ } else
+ buf[cnt] = '\0';
- /* Cut from the first nil or newline. */
- buf[cnt] = '\0';
- end = strchr(buf, '\n');
- if (end)
- *end = '\0';
-
- cnt = mark_printk("%s\n", buf);
+ cnt = trace_vprintk(0, buf, NULL);
kfree(buf);
*fpos += cnt;
@@ -3730,7 +3719,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
s = kmalloc(sizeof(*s), GFP_KERNEL);
if (!s)
- return ENOMEM;
+ return -ENOMEM;
trace_seq_init(s);
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 20c5f92e28a..878c03f386b 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -20,6 +20,8 @@
#include <linux/ktime.h>
#include <linux/trace_clock.h>
+#include "trace.h"
+
/*
* trace_clock_local(): the simplest and least coherent tracing clock.
*
@@ -28,17 +30,17 @@
*/
u64 notrace trace_clock_local(void)
{
- unsigned long flags;
u64 clock;
+ int resched;
/*
* sched_clock() is an architecture implemented, fast, scalable,
* lockless clock. It is not guaranteed to be coherent across
* CPUs, nor across CPU idle events.
*/
- raw_local_irq_save(flags);
+ resched = ftrace_preempt_disable();
clock = sched_clock();
- raw_local_irq_restore(flags);
+ ftrace_preempt_enable(resched);
return clock;
}
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 934d81fb4ca..dff8c84ddf1 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -48,11 +48,11 @@
struct ____ftrace_##name { \
tstruct \
}; \
-static void __used ____ftrace_check_##name(void) \
+static void __always_unused ____ftrace_check_##name(void) \
{ \
struct ____ftrace_##name *__entry = NULL; \
\
- /* force cmpile-time check on F_printk() */ \
+ /* force compile-time check on F_printk() */ \
printk(print); \
}
diff --git a/kernel/user-return-notifier.c b/kernel/user-return-notifier.c
new file mode 100644
index 00000000000..eb27fd3430a
--- /dev/null
+++ b/kernel/user-return-notifier.c
@@ -0,0 +1,44 @@
+
+#include <linux/user-return-notifier.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+
+static DEFINE_PER_CPU(struct hlist_head, return_notifier_list);
+
+/*
+ * Request a notification when the current cpu returns to userspace. Must be
+ * called in atomic context. The notifier will also be called in atomic
+ * context.
+ */
+void user_return_notifier_register(struct user_return_notifier *urn)
+{
+ set_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY);
+ hlist_add_head(&urn->link, &__get_cpu_var(return_notifier_list));
+}
+EXPORT_SYMBOL_GPL(user_return_notifier_register);
+
+/*
+ * Removes a registered user return notifier. Must be called from atomic
+ * context, and from the same cpu registration occured in.
+ */
+void user_return_notifier_unregister(struct user_return_notifier *urn)
+{
+ hlist_del(&urn->link);
+ if (hlist_empty(&__get_cpu_var(return_notifier_list)))
+ clear_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY);
+}
+EXPORT_SYMBOL_GPL(user_return_notifier_unregister);
+
+/* Calls registered user return notifiers */
+void fire_user_return_notifiers(void)
+{
+ struct user_return_notifier *urn;
+ struct hlist_node *tmp1, *tmp2;
+ struct hlist_head *head;
+
+ head = &get_cpu_var(return_notifier_list);
+ hlist_for_each_entry_safe(urn, tmp1, tmp2, head, link)
+ urn->on_user_return(urn);
+ put_cpu_var(return_notifier_list);
+}
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 69eae358a72..a2cd77e70d4 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,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 12328147132..dee48658805 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -68,6 +68,116 @@ struct workqueue_struct {
#endif
};
+#ifdef CONFIG_DEBUG_OBJECTS_WORK
+
+static struct debug_obj_descr work_debug_descr;
+
+/*
+ * fixup_init is called when:
+ * - an active object is initialized
+ */
+static int work_fixup_init(void *addr, enum debug_obj_state state)
+{
+ struct work_struct *work = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_ACTIVE:
+ cancel_work_sync(work);
+ debug_object_init(work, &work_debug_descr);
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+/*
+ * fixup_activate is called when:
+ * - an active object is activated
+ * - an unknown object is activated (might be a statically initialized object)
+ */
+static int work_fixup_activate(void *addr, enum debug_obj_state state)
+{
+ struct work_struct *work = addr;
+
+ switch (state) {
+
+ case ODEBUG_STATE_NOTAVAILABLE:
+ /*
+ * This is not really a fixup. The work struct was
+ * statically initialized. We just make sure that it
+ * is tracked in the object tracker.
+ */
+ if (test_bit(WORK_STRUCT_STATIC, work_data_bits(work))) {
+ debug_object_init(work, &work_debug_descr);
+ debug_object_activate(work, &work_debug_descr);
+ return 0;
+ }
+ WARN_ON_ONCE(1);
+ return 0;
+
+ case ODEBUG_STATE_ACTIVE:
+ WARN_ON(1);
+
+ default:
+ return 0;
+ }
+}
+
+/*
+ * fixup_free is called when:
+ * - an active object is freed
+ */
+static int work_fixup_free(void *addr, enum debug_obj_state state)
+{
+ struct work_struct *work = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_ACTIVE:
+ cancel_work_sync(work);
+ debug_object_free(work, &work_debug_descr);
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+static struct debug_obj_descr work_debug_descr = {
+ .name = "work_struct",
+ .fixup_init = work_fixup_init,
+ .fixup_activate = work_fixup_activate,
+ .fixup_free = work_fixup_free,
+};
+
+static inline void debug_work_activate(struct work_struct *work)
+{
+ debug_object_activate(work, &work_debug_descr);
+}
+
+static inline void debug_work_deactivate(struct work_struct *work)
+{
+ debug_object_deactivate(work, &work_debug_descr);
+}
+
+void __init_work(struct work_struct *work, int onstack)
+{
+ if (onstack)
+ debug_object_init_on_stack(work, &work_debug_descr);
+ else
+ debug_object_init(work, &work_debug_descr);
+}
+EXPORT_SYMBOL_GPL(__init_work);
+
+void destroy_work_on_stack(struct work_struct *work)
+{
+ debug_object_free(work, &work_debug_descr);
+}
+EXPORT_SYMBOL_GPL(destroy_work_on_stack);
+
+#else
+static inline void debug_work_activate(struct work_struct *work) { }
+static inline void debug_work_deactivate(struct work_struct *work) { }
+#endif
+
/* Serializes the accesses to the list of workqueues. */
static DEFINE_SPINLOCK(workqueue_lock);
static LIST_HEAD(workqueues);
@@ -145,6 +255,7 @@ static void __queue_work(struct cpu_workqueue_struct *cwq,
{
unsigned long flags;
+ debug_work_activate(work);
spin_lock_irqsave(&cwq->lock, flags);
insert_work(cwq, work, &cwq->worklist);
spin_unlock_irqrestore(&cwq->lock, flags);
@@ -280,6 +391,7 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq)
struct lockdep_map lockdep_map = work->lockdep_map;
#endif
trace_workqueue_execution(cwq->thread, work);
+ debug_work_deactivate(work);
cwq->current_work = work;
list_del_init(cwq->worklist.next);
spin_unlock_irq(&cwq->lock);
@@ -350,11 +462,18 @@ static void wq_barrier_func(struct work_struct *work)
static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
struct wq_barrier *barr, struct list_head *head)
{
- INIT_WORK(&barr->work, wq_barrier_func);
+ /*
+ * debugobject calls are safe here even with cwq->lock locked
+ * as we know for sure that this will not trigger any of the
+ * checks and call back into the fixup functions where we
+ * might deadlock.
+ */
+ INIT_WORK_ON_STACK(&barr->work, wq_barrier_func);
__set_bit(WORK_STRUCT_PENDING, work_data_bits(&barr->work));
init_completion(&barr->done);
+ debug_work_activate(&barr->work);
insert_work(cwq, &barr->work, head);
}
@@ -372,8 +491,10 @@ static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
}
spin_unlock_irq(&cwq->lock);
- if (active)
+ if (active) {
wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
+ }
return active;
}
@@ -451,6 +572,7 @@ out:
return 0;
wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
return 1;
}
EXPORT_SYMBOL_GPL(flush_work);
@@ -485,6 +607,7 @@ static int try_to_grab_pending(struct work_struct *work)
*/
smp_rmb();
if (cwq == get_wq_data(work)) {
+ debug_work_deactivate(work);
list_del_init(&work->entry);
ret = 1;
}
@@ -507,8 +630,10 @@ static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq,
}
spin_unlock_irq(&cwq->lock);
- if (unlikely(running))
+ if (unlikely(running)) {
wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
+ }
}
static void wait_on_work(struct work_struct *work)
@@ -692,31 +817,29 @@ int schedule_on_each_cpu(work_func_t func)
if (!works)
return -ENOMEM;
+ get_online_cpus();
+
/*
- * when running in keventd don't schedule a work item on itself.
- * Can just call directly because the work queue is already bound.
- * This also is faster.
- * Make this a generic parameter for other workqueues?
+ * When running in keventd don't schedule a work item on
+ * itself. Can just call directly because the work queue is
+ * already bound. This also is faster.
*/
- if (current_is_keventd()) {
+ if (current_is_keventd())
orig = raw_smp_processor_id();
- INIT_WORK(per_cpu_ptr(works, orig), func);
- func(per_cpu_ptr(works, orig));
- }
- get_online_cpus();
for_each_online_cpu(cpu) {
struct work_struct *work = per_cpu_ptr(works, cpu);
- if (cpu == orig)
- continue;
INIT_WORK(work, func);
- schedule_work_on(cpu, work);
- }
- for_each_online_cpu(cpu) {
if (cpu != orig)
- flush_work(per_cpu_ptr(works, cpu));
+ schedule_work_on(cpu, work);
}
+ if (orig >= 0)
+ func(per_cpu_ptr(works, orig));
+
+ for_each_online_cpu(cpu)
+ flush_work(per_cpu_ptr(works, cpu));
+
put_online_cpus();
free_percpu(works);
return 0;