summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/cgroup.c8
-rw-r--r--kernel/exit.c10
-rw-r--r--kernel/fork.c33
-rw-r--r--kernel/hrtimer.c40
-rw-r--r--kernel/itimer.c169
-rw-r--r--kernel/kallsyms.c3
-rw-r--r--kernel/kmod.c13
-rw-r--r--kernel/kprobes.c2
-rw-r--r--kernel/lockdep.c3
-rw-r--r--kernel/lockdep_proc.c2
-rw-r--r--kernel/module.c5
-rw-r--r--kernel/panic.c2
-rw-r--r--kernel/pid.c15
-rw-r--r--kernel/posix-cpu-timers.c155
-rw-r--r--kernel/power/process.c1
-rw-r--r--kernel/power/snapshot.c2
-rw-r--r--kernel/printk.c27
-rw-r--r--kernel/resource.c23
-rw-r--r--kernel/sched.c22
-rw-r--r--kernel/smp.c29
-rw-r--r--kernel/sys.c14
-rw-r--r--kernel/sysctl.c14
-rw-r--r--kernel/timer.c32
-rw-r--r--kernel/trace/Kconfig2
-rw-r--r--kernel/trace/ftrace.c4
-rw-r--r--kernel/trace/trace.c4
-rw-r--r--kernel/trace/trace_hw_branches.c2
-rw-r--r--kernel/tracepoint.c2
28 files changed, 400 insertions, 238 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c7ece8f027f2..cd83d9933b6b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -596,7 +596,7 @@ void cgroup_unlock(void)
static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode);
static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
static int cgroup_populate_dir(struct cgroup *cgrp);
-static struct inode_operations cgroup_dir_inode_operations;
+static const struct inode_operations cgroup_dir_inode_operations;
static struct file_operations proc_cgroupstats_operations;
static struct backing_dev_info cgroup_backing_dev_info = {
@@ -961,7 +961,7 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
return ret;
}
-static struct super_operations cgroup_ops = {
+static const struct super_operations cgroup_ops = {
.statfs = simple_statfs,
.drop_inode = generic_delete_inode,
.show_options = cgroup_show_options,
@@ -1711,7 +1711,7 @@ static struct file_operations cgroup_file_operations = {
.release = cgroup_file_release,
};
-static struct inode_operations cgroup_dir_inode_operations = {
+static const struct inode_operations cgroup_dir_inode_operations = {
.lookup = simple_lookup,
.mkdir = cgroup_mkdir,
.rmdir = cgroup_rmdir,
@@ -2314,7 +2314,7 @@ static int cgroup_tasks_show(struct seq_file *s, void *v)
return seq_printf(s, "%d\n", *(int *)v);
}
-static struct seq_operations cgroup_tasks_seq_operations = {
+static const struct seq_operations cgroup_tasks_seq_operations = {
.start = cgroup_tasks_start,
.stop = cgroup_tasks_stop,
.next = cgroup_tasks_next,
diff --git a/kernel/exit.c b/kernel/exit.c
index e47ee8a06135..60d6fdcc9265 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -359,8 +359,10 @@ void __set_special_pids(struct pid *pid)
{
struct task_struct *curr = current->group_leader;
- if (task_session(curr) != pid)
+ if (task_session(curr) != pid) {
change_pid(curr, PIDTYPE_SID, pid);
+ proc_sid_connector(curr);
+ }
if (task_pgrp(curr) != pid)
change_pid(curr, PIDTYPE_PGID, pid);
@@ -945,6 +947,8 @@ NORET_TYPE void do_exit(long code)
if (group_dead) {
hrtimer_cancel(&tsk->signal->real_timer);
exit_itimers(tsk->signal);
+ if (tsk->mm)
+ setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
}
acct_collect(code, group_dead);
if (group_dead)
@@ -1208,6 +1212,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
if (likely(!traced) && likely(!task_detached(p))) {
struct signal_struct *psig;
struct signal_struct *sig;
+ unsigned long maxrss;
/*
* The resource counters for the group leader are in its
@@ -1256,6 +1261,9 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
psig->coublock +=
task_io_get_oublock(p) +
sig->oublock + sig->coublock;
+ maxrss = max(sig->maxrss, sig->cmaxrss);
+ if (psig->cmaxrss < maxrss)
+ psig->cmaxrss = maxrss;
task_io_accounting_add(&psig->ioac, &p->ioac);
task_io_accounting_add(&psig->ioac, &sig->ioac);
spin_unlock_irq(&p->real_parent->sighand->siglock);
diff --git a/kernel/fork.c b/kernel/fork.c
index 2cebfb23b0b8..51ad0b0b7266 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -49,6 +49,7 @@
#include <linux/ftrace.h>
#include <linux/profile.h>
#include <linux/rmap.h>
+#include <linux/ksm.h>
#include <linux/acct.h>
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
@@ -62,6 +63,7 @@
#include <linux/fs_struct.h>
#include <linux/magic.h>
#include <linux/perf_event.h>
+#include <linux/posix-timers.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -136,9 +138,17 @@ struct kmem_cache *vm_area_cachep;
/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
+static void account_kernel_stack(struct thread_info *ti, int account)
+{
+ struct zone *zone = page_zone(virt_to_page(ti));
+
+ mod_zone_page_state(zone, NR_KERNEL_STACK, account);
+}
+
void free_task(struct task_struct *tsk)
{
prop_local_destroy_single(&tsk->dirties);
+ account_kernel_stack(tsk->stack, -1);
free_thread_info(tsk->stack);
rt_mutex_debug_task_free(tsk);
ftrace_graph_exit_task(tsk);
@@ -253,6 +263,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
tsk->btrace_seq = 0;
#endif
tsk->splice_pipe = NULL;
+
+ account_kernel_stack(ti, 1);
+
return tsk;
out:
@@ -288,6 +301,9 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
rb_link = &mm->mm_rb.rb_node;
rb_parent = NULL;
pprev = &mm->mmap;
+ retval = ksm_fork(mm, oldmm);
+ if (retval)
+ goto out;
for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
struct file *file;
@@ -424,7 +440,8 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
atomic_set(&mm->mm_count, 1);
init_rwsem(&mm->mmap_sem);
INIT_LIST_HEAD(&mm->mmlist);
- mm->flags = (current->mm) ? current->mm->flags : default_dump_filter;
+ mm->flags = (current->mm) ?
+ (current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
mm->core_state = NULL;
mm->nr_ptes = 0;
set_mm_counter(mm, file_rss, 0);
@@ -485,6 +502,7 @@ void mmput(struct mm_struct *mm)
if (atomic_dec_and_test(&mm->mm_users)) {
exit_aio(mm);
+ ksm_exit(mm);
exit_mmap(mm);
set_mm_exe_file(mm, NULL);
if (!list_empty(&mm->mmlist)) {
@@ -788,10 +806,10 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
thread_group_cputime_init(sig);
/* Expiration times and increments. */
- sig->it_virt_expires = cputime_zero;
- sig->it_virt_incr = cputime_zero;
- sig->it_prof_expires = cputime_zero;
- sig->it_prof_incr = cputime_zero;
+ sig->it[CPUCLOCK_PROF].expires = cputime_zero;
+ sig->it[CPUCLOCK_PROF].incr = cputime_zero;
+ sig->it[CPUCLOCK_VIRT].expires = cputime_zero;
+ sig->it[CPUCLOCK_VIRT].incr = cputime_zero;
/* Cached expiration times. */
sig->cputime_expires.prof_exp = cputime_zero;
@@ -849,6 +867,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
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;
+ sig->maxrss = sig->cmaxrss = 0;
task_io_accounting_init(&sig->ioac);
sig->sum_sched_runtime = 0;
taskstats_tgid_init(sig);
@@ -863,6 +882,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
tty_audit_fork(sig);
+ sig->oom_adj = current->signal->oom_adj;
+
return 0;
}
@@ -1075,6 +1096,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
p->bts = NULL;
+ p->stack_start = stack_start;
+
/* Perform scheduler related setup. Assign this task to a CPU. */
sched_fork(p, clone_flags);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index c03f221fee44..e5d98ce50f89 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -48,6 +48,8 @@
#include <asm/uaccess.h>
+#include <trace/events/timer.h>
+
/*
* The timer bases:
*
@@ -442,6 +444,26 @@ static inline void debug_hrtimer_activate(struct hrtimer *timer) { }
static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { }
#endif
+static inline void
+debug_init(struct hrtimer *timer, clockid_t clockid,
+ enum hrtimer_mode mode)
+{
+ debug_hrtimer_init(timer);
+ trace_hrtimer_init(timer, clockid, mode);
+}
+
+static inline void debug_activate(struct hrtimer *timer)
+{
+ debug_hrtimer_activate(timer);
+ trace_hrtimer_start(timer);
+}
+
+static inline void debug_deactivate(struct hrtimer *timer)
+{
+ debug_hrtimer_deactivate(timer);
+ trace_hrtimer_cancel(timer);
+}
+
/* High resolution timer related functions */
#ifdef CONFIG_HIGH_RES_TIMERS
@@ -798,7 +820,7 @@ static int enqueue_hrtimer(struct hrtimer *timer,
struct hrtimer *entry;
int leftmost = 1;
- debug_hrtimer_activate(timer);
+ debug_activate(timer);
/*
* Find the right place in the rbtree:
@@ -884,7 +906,7 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
* reprogramming happens in the interrupt handler. This is a
* rare case and less expensive than a smp call.
*/
- debug_hrtimer_deactivate(timer);
+ debug_deactivate(timer);
timer_stats_hrtimer_clear_start_info(timer);
reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE,
@@ -1117,7 +1139,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
enum hrtimer_mode mode)
{
- debug_hrtimer_init(timer);
+ debug_init(timer, clock_id, mode);
__hrtimer_init(timer, clock_id, mode);
}
EXPORT_SYMBOL_GPL(hrtimer_init);
@@ -1141,7 +1163,7 @@ int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
}
EXPORT_SYMBOL_GPL(hrtimer_get_res);
-static void __run_hrtimer(struct hrtimer *timer)
+static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
{
struct hrtimer_clock_base *base = timer->base;
struct hrtimer_cpu_base *cpu_base = base->cpu_base;
@@ -1150,7 +1172,7 @@ static void __run_hrtimer(struct hrtimer *timer)
WARN_ON(!irqs_disabled());
- debug_hrtimer_deactivate(timer);
+ debug_deactivate(timer);
__remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
timer_stats_account_hrtimer(timer);
fn = timer->function;
@@ -1161,7 +1183,9 @@ static void __run_hrtimer(struct hrtimer *timer)
* the timer base.
*/
spin_unlock(&cpu_base->lock);
+ trace_hrtimer_expire_entry(timer, now);
restart = fn(timer);
+ trace_hrtimer_expire_exit(timer);
spin_lock(&cpu_base->lock);
/*
@@ -1272,7 +1296,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
break;
}
- __run_hrtimer(timer);
+ __run_hrtimer(timer, &basenow);
}
base++;
}
@@ -1394,7 +1418,7 @@ void hrtimer_run_queues(void)
hrtimer_get_expires_tv64(timer))
break;
- __run_hrtimer(timer);
+ __run_hrtimer(timer, &base->softirq_time);
}
spin_unlock(&cpu_base->lock);
}
@@ -1571,7 +1595,7 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
while ((node = rb_first(&old_base->active))) {
timer = rb_entry(node, struct hrtimer, node);
BUG_ON(hrtimer_callback_running(timer));
- debug_hrtimer_deactivate(timer);
+ debug_deactivate(timer);
/*
* Mark it as STATE_MIGRATE not INACTIVE otherwise the
diff --git a/kernel/itimer.c b/kernel/itimer.c
index 58762f7077ec..b03451ede528 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -12,6 +12,7 @@
#include <linux/time.h>
#include <linux/posix-timers.h>
#include <linux/hrtimer.h>
+#include <trace/events/timer.h>
#include <asm/uaccess.h>
@@ -41,10 +42,43 @@ static struct timeval itimer_get_remtime(struct hrtimer *timer)
return ktime_to_timeval(rem);
}
+static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
+ struct itimerval *const value)
+{
+ cputime_t cval, cinterval;
+ struct cpu_itimer *it = &tsk->signal->it[clock_id];
+
+ spin_lock_irq(&tsk->sighand->siglock);
+
+ cval = it->expires;
+ cinterval = it->incr;
+ if (!cputime_eq(cval, cputime_zero)) {
+ struct task_cputime cputime;
+ cputime_t t;
+
+ thread_group_cputimer(tsk, &cputime);
+ if (clock_id == CPUCLOCK_PROF)
+ t = cputime_add(cputime.utime, cputime.stime);
+ else
+ /* CPUCLOCK_VIRT */
+ t = cputime.utime;
+
+ if (cputime_le(cval, t))
+ /* about to fire */
+ cval = cputime_one_jiffy;
+ else
+ cval = cputime_sub(cval, t);
+ }
+
+ spin_unlock_irq(&tsk->sighand->siglock);
+
+ cputime_to_timeval(cval, &value->it_value);
+ cputime_to_timeval(cinterval, &value->it_interval);
+}
+
int do_getitimer(int which, struct itimerval *value)
{
struct task_struct *tsk = current;
- cputime_t cinterval, cval;
switch (which) {
case ITIMER_REAL:
@@ -55,44 +89,10 @@ int do_getitimer(int which, struct itimerval *value)
spin_unlock_irq(&tsk->sighand->siglock);
break;
case ITIMER_VIRTUAL:
- spin_lock_irq(&tsk->sighand->siglock);
- cval = tsk->signal->it_virt_expires;
- cinterval = tsk->signal->it_virt_incr;
- if (!cputime_eq(cval, cputime_zero)) {
- struct task_cputime cputime;
- cputime_t utime;
-
- thread_group_cputimer(tsk, &cputime);
- utime = cputime.utime;
- if (cputime_le(cval, utime)) { /* about to fire */
- cval = jiffies_to_cputime(1);
- } else {
- cval = cputime_sub(cval, utime);
- }
- }
- spin_unlock_irq(&tsk->sighand->siglock);
- cputime_to_timeval(cval, &value->it_value);
- cputime_to_timeval(cinterval, &value->it_interval);
+ get_cpu_itimer(tsk, CPUCLOCK_VIRT, value);
break;
case ITIMER_PROF:
- spin_lock_irq(&tsk->sighand->siglock);
- cval = tsk->signal->it_prof_expires;
- cinterval = tsk->signal->it_prof_incr;
- if (!cputime_eq(cval, cputime_zero)) {
- struct task_cputime times;
- cputime_t ptime;
-
- thread_group_cputimer(tsk, &times);
- ptime = cputime_add(times.utime, times.stime);
- if (cputime_le(cval, ptime)) { /* about to fire */
- cval = jiffies_to_cputime(1);
- } else {
- cval = cputime_sub(cval, ptime);
- }
- }
- spin_unlock_irq(&tsk->sighand->siglock);
- cputime_to_timeval(cval, &value->it_value);
- cputime_to_timeval(cinterval, &value->it_interval);
+ get_cpu_itimer(tsk, CPUCLOCK_PROF, value);
break;
default:
return(-EINVAL);
@@ -123,11 +123,62 @@ enum hrtimer_restart it_real_fn(struct hrtimer *timer)
struct signal_struct *sig =
container_of(timer, struct signal_struct, real_timer);
+ trace_itimer_expire(ITIMER_REAL, sig->leader_pid, 0);
kill_pid_info(SIGALRM, SEND_SIG_PRIV, sig->leader_pid);
return HRTIMER_NORESTART;
}
+static inline u32 cputime_sub_ns(cputime_t ct, s64 real_ns)
+{
+ struct timespec ts;
+ s64 cpu_ns;
+
+ cputime_to_timespec(ct, &ts);
+ cpu_ns = timespec_to_ns(&ts);
+
+ return (cpu_ns <= real_ns) ? 0 : cpu_ns - real_ns;
+}
+
+static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
+ const struct itimerval *const value,
+ struct itimerval *const ovalue)
+{
+ cputime_t cval, nval, cinterval, ninterval;
+ s64 ns_ninterval, ns_nval;
+ struct cpu_itimer *it = &tsk->signal->it[clock_id];
+
+ nval = timeval_to_cputime(&value->it_value);
+ ns_nval = timeval_to_ns(&value->it_value);
+ 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);
+
+ spin_lock_irq(&tsk->sighand->siglock);
+
+ cval = it->expires;
+ cinterval = it->incr;
+ if (!cputime_eq(cval, cputime_zero) ||
+ !cputime_eq(nval, cputime_zero)) {
+ if (cputime_gt(nval, cputime_zero))
+ nval = cputime_add(nval, cputime_one_jiffy);
+ set_process_cpu_timer(tsk, clock_id, &nval, &cval);
+ }
+ it->expires = nval;
+ it->incr = ninterval;
+ trace_itimer_state(clock_id == CPUCLOCK_VIRT ?
+ ITIMER_VIRTUAL : ITIMER_PROF, value, nval);
+
+ spin_unlock_irq(&tsk->sighand->siglock);
+
+ if (ovalue) {
+ cputime_to_timeval(cval, &ovalue->it_value);
+ cputime_to_timeval(cinterval, &ovalue->it_interval);
+ }
+}
+
/*
* Returns true if the timeval is in canonical form
*/
@@ -139,7 +190,6 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
struct task_struct *tsk = current;
struct hrtimer *timer;
ktime_t expires;
- cputime_t cval, cinterval, nval, ninterval;
/*
* Validate the timevals in value.
@@ -171,51 +221,14 @@ again:
} else
tsk->signal->it_real_incr.tv64 = 0;
+ trace_itimer_state(ITIMER_REAL, value, 0);
spin_unlock_irq(&tsk->sighand->siglock);
break;
case ITIMER_VIRTUAL:
- nval = timeval_to_cputime(&value->it_value);
- ninterval = timeval_to_cputime(&value->it_interval);
- spin_lock_irq(&tsk->sighand->siglock);
- cval = tsk->signal->it_virt_expires;
- cinterval = tsk->signal->it_virt_incr;
- if (!cputime_eq(cval, cputime_zero) ||
- !cputime_eq(nval, cputime_zero)) {
- if (cputime_gt(nval, cputime_zero))
- nval = cputime_add(nval,
- jiffies_to_cputime(1));
- set_process_cpu_timer(tsk, CPUCLOCK_VIRT,
- &nval, &cval);
- }
- tsk->signal->it_virt_expires = nval;
- tsk->signal->it_virt_incr = ninterval;
- spin_unlock_irq(&tsk->sighand->siglock);
- if (ovalue) {
- cputime_to_timeval(cval, &ovalue->it_value);
- cputime_to_timeval(cinterval, &ovalue->it_interval);
- }
+ set_cpu_itimer(tsk, CPUCLOCK_VIRT, value, ovalue);
break;
case ITIMER_PROF:
- nval = timeval_to_cputime(&value->it_value);
- ninterval = timeval_to_cputime(&value->it_interval);
- spin_lock_irq(&tsk->sighand->siglock);
- cval = tsk->signal->it_prof_expires;
- cinterval = tsk->signal->it_prof_incr;
- if (!cputime_eq(cval, cputime_zero) ||
- !cputime_eq(nval, cputime_zero)) {
- if (cputime_gt(nval, cputime_zero))
- nval = cputime_add(nval,
- jiffies_to_cputime(1));
- set_process_cpu_timer(tsk, CPUCLOCK_PROF,
- &nval, &cval);
- }
- tsk->signal->it_prof_expires = nval;
- tsk->signal->it_prof_incr = ninterval;
- spin_unlock_irq(&tsk->sighand->siglock);
- if (ovalue) {
- cputime_to_timeval(cval, &ovalue->it_value);
- cputime_to_timeval(cinterval, &ovalue->it_interval);
- }
+ set_cpu_itimer(tsk, CPUCLOCK_PROF, value, ovalue);
break;
default:
return -EINVAL;
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 3a29dbe7898e..8b6b8b697c68 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -59,7 +59,8 @@ static inline int is_kernel_inittext(unsigned long addr)
static inline int is_kernel_text(unsigned long addr)
{
- if (addr >= (unsigned long)_stext && addr <= (unsigned long)_etext)
+ if ((addr >= (unsigned long)_stext && addr <= (unsigned long)_etext) ||
+ arch_is_kernel_text(addr))
return 1;
return in_gate_area_no_task(addr);
}
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 9fcb53a11f87..689d20f39305 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -143,6 +143,7 @@ struct subprocess_info {
static int ____call_usermodehelper(void *data)
{
struct subprocess_info *sub_info = data;
+ enum umh_wait wait = sub_info->wait;
int retval;
BUG_ON(atomic_read(&sub_info->cred->usage) != 1);
@@ -184,10 +185,14 @@ static int ____call_usermodehelper(void *data)
*/
set_user_nice(current, 0);
+ if (wait == UMH_WAIT_EXEC)
+ complete(sub_info->complete);
+
retval = kernel_execve(sub_info->path, sub_info->argv, sub_info->envp);
/* Exec failed? */
- sub_info->retval = retval;
+ if (wait != UMH_WAIT_EXEC)
+ sub_info->retval = retval;
do_exit(0);
}
@@ -266,16 +271,14 @@ static void __call_usermodehelper(struct work_struct *work)
switch (wait) {
case UMH_NO_WAIT:
+ case UMH_WAIT_EXEC:
break;
case UMH_WAIT_PROC:
if (pid > 0)
break;
sub_info->retval = pid;
- /* FALLTHROUGH */
-
- case UMH_WAIT_EXEC:
- complete(sub_info->complete);
+ break;
}
}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ef177d653b2c..cfadc1291d0b 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1321,7 +1321,7 @@ static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v)
return 0;
}
-static struct seq_operations kprobes_seq_ops = {
+static const struct seq_operations kprobes_seq_ops = {
.start = kprobe_seq_start,
.next = kprobe_seq_next,
.stop = kprobe_seq_stop,
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index f74d2d7aa605..3815ac1d58b2 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -578,6 +578,9 @@ static int static_obj(void *obj)
if ((addr >= start) && (addr < end))
return 1;
+ if (arch_is_kernel_data(addr))
+ return 1;
+
#ifdef CONFIG_SMP
/*
* percpu var?
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index d4b3dbc79fdb..d4aba4f3584c 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -594,7 +594,7 @@ static int ls_show(struct seq_file *m, void *v)
return 0;
}
-static struct seq_operations lockstat_ops = {
+static const struct seq_operations lockstat_ops = {
.start = ls_start,
.next = ls_next,
.stop = ls_stop,
diff --git a/kernel/module.c b/kernel/module.c
index b6ee424245dd..e6bc4b28aa62 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -47,6 +47,7 @@
#include <linux/rculist.h>
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
#include <linux/license.h>
#include <asm/sections.h>
#include <linux/tracepoint.h>
@@ -1535,6 +1536,10 @@ static void free_module(struct module *mod)
/* Finally, free the core (containing the module structure) */
module_free(mod, mod->module_core);
+
+#ifdef CONFIG_MPU
+ update_protections(current->mm);
+#endif
}
void *__symbol_get(const char *symbol)
diff --git a/kernel/panic.c b/kernel/panic.c
index 512ab73b0ca3..bcdef26e3332 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -177,7 +177,7 @@ static const struct tnt tnts[] = {
* 'W' - Taint on warning.
* 'C' - modules from drivers/staging are loaded.
*
- * The string is overwritten by the next call to print_taint().
+ * The string is overwritten by the next call to print_tainted().
*/
const char *print_tainted(void)
{
diff --git a/kernel/pid.c b/kernel/pid.c
index 31310b5d3f50..d3f722d20f9c 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -40,7 +40,7 @@
#define pid_hashfn(nr, ns) \
hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift)
static struct hlist_head *pid_hash;
-static int pidhash_shift;
+static unsigned int pidhash_shift = 4;
struct pid init_struct_pid = INIT_STRUCT_PID;
int pid_max = PID_MAX_DEFAULT;
@@ -499,19 +499,12 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
void __init pidhash_init(void)
{
int i, pidhash_size;
- unsigned long megabytes = nr_kernel_pages >> (20 - PAGE_SHIFT);
- pidhash_shift = max(4, fls(megabytes * 4));
- pidhash_shift = min(12, pidhash_shift);
+ pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
+ HASH_EARLY | HASH_SMALL,
+ &pidhash_shift, NULL, 4096);
pidhash_size = 1 << pidhash_shift;
- printk("PID hash table entries: %d (order: %d, %Zd bytes)\n",
- pidhash_size, pidhash_shift,
- pidhash_size * sizeof(struct hlist_head));
-
- pid_hash = alloc_bootmem(pidhash_size * sizeof(*(pid_hash)));
- if (!pid_hash)
- panic("Could not alloc pidhash!\n");
for (i = 0; i < pidhash_size; i++)
INIT_HLIST_HEAD(&pid_hash[i]);
}
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index e33a21cb9407..5c9dc228747b 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -8,17 +8,18 @@
#include <linux/math64.h>
#include <asm/uaccess.h>
#include <linux/kernel_stat.h>
+#include <trace/events/timer.h>
/*
* Called after updating RLIMIT_CPU to set timer expiration if necessary.
*/
void update_rlimit_cpu(unsigned long rlim_new)
{
- cputime_t cputime;
+ cputime_t cputime = secs_to_cputime(rlim_new);
+ struct signal_struct *const sig = current->signal;
- cputime = secs_to_cputime(rlim_new);
- if (cputime_eq(current->signal->it_prof_expires, cputime_zero) ||
- cputime_gt(current->signal->it_prof_expires, cputime)) {
+ if (cputime_eq(sig->it[CPUCLOCK_PROF].expires, cputime_zero) ||
+ cputime_gt(sig->it[CPUCLOCK_PROF].expires, cputime)) {
spin_lock_irq(&current->sighand->siglock);
set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
spin_unlock_irq(&current->sighand->siglock);
@@ -542,6 +543,17 @@ static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
now);
}
+static inline int expires_gt(cputime_t expires, cputime_t new_exp)
+{
+ return cputime_eq(expires, cputime_zero) ||
+ cputime_gt(expires, new_exp);
+}
+
+static inline int expires_le(cputime_t expires, cputime_t new_exp)
+{
+ return !cputime_eq(expires, cputime_zero) &&
+ cputime_le(expires, new_exp);
+}
/*
* Insert the timer on the appropriate list before any timers that
* expire later. This must be called with the tasklist_lock held
@@ -586,34 +598,32 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
*/
if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
+ union cpu_time_count *exp = &nt->expires;
+
switch (CPUCLOCK_WHICH(timer->it_clock)) {
default:
BUG();
case CPUCLOCK_PROF:
- if (cputime_eq(p->cputime_expires.prof_exp,
- cputime_zero) ||
- cputime_gt(p->cputime_expires.prof_exp,
- nt->expires.cpu))
- p->cputime_expires.prof_exp =
- nt->expires.cpu;
+ if (expires_gt(p->cputime_expires.prof_exp,
+ exp->cpu))
+ p->cputime_expires.prof_exp = exp->cpu;
break;
case CPUCLOCK_VIRT:
- if (cputime_eq(p->cputime_expires.virt_exp,
- cputime_zero) ||
- cputime_gt(p->cputime_expires.virt_exp,
- nt->expires.cpu))
- p->cputime_expires.virt_exp =
- nt->expires.cpu;
+ if (expires_gt(p->cputime_expires.virt_exp,
+ exp->cpu))
+ p->cputime_expires.virt_exp = exp->cpu;
break;
case CPUCLOCK_SCHED:
if (p->cputime_expires.sched_exp == 0 ||
- p->cputime_expires.sched_exp >
- nt->expires.sched)
+ p->cputime_expires.sched_exp > exp->sched)
p->cputime_expires.sched_exp =
- nt->expires.sched;
+ exp->sched;
break;
}
} else {
+ struct signal_struct *const sig = p->signal;
+ union cpu_time_count *exp = &timer->it.cpu.expires;
+
/*
* For a process timer, set the cached expiration time.
*/
@@ -621,30 +631,23 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
default:
BUG();
case CPUCLOCK_VIRT:
- if (!cputime_eq(p->signal->it_virt_expires,
- cputime_zero) &&
- cputime_lt(p->signal->it_virt_expires,
- timer->it.cpu.expires.cpu))
+ if (expires_le(sig->it[CPUCLOCK_VIRT].expires,
+ exp->cpu))
break;
- p->signal->cputime_expires.virt_exp =
- timer->it.cpu.expires.cpu;
+ sig->cputime_expires.virt_exp = exp->cpu;
break;
case CPUCLOCK_PROF:
- if (!cputime_eq(p->signal->it_prof_expires,
- cputime_zero) &&
- cputime_lt(p->signal->it_prof_expires,
- timer->it.cpu.expires.cpu))
+ if (expires_le(sig->it[CPUCLOCK_PROF].expires,
+ exp->cpu))
break;
- i = p->signal->rlim[RLIMIT_CPU].rlim_cur;
+ i = sig->rlim[RLIMIT_CPU].rlim_cur;
if (i != RLIM_INFINITY &&
- i <= cputime_to_secs(timer->it.cpu.expires.cpu))
+ i <= cputime_to_secs(exp->cpu))
break;
- p->signal->cputime_expires.prof_exp =
- timer->it.cpu.expires.cpu;
+ sig->cputime_expires.prof_exp = exp->cpu;
break;
case CPUCLOCK_SCHED:
- p->signal->cputime_expires.sched_exp =
- timer->it.cpu.expires.sched;
+ sig->cputime_expires.sched_exp = exp->sched;
break;
}
}
@@ -1071,6 +1074,40 @@ static void stop_process_timers(struct task_struct *tsk)
spin_unlock_irqrestore(&cputimer->lock, flags);
}
+static u32 onecputick;
+
+static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
+ cputime_t *expires, cputime_t cur_time, int signo)
+{
+ if (cputime_eq(it->expires, cputime_zero))
+ return;
+
+ if (cputime_ge(cur_time, it->expires)) {
+ if (!cputime_eq(it->incr, cputime_zero)) {
+ it->expires = cputime_add(it->expires, it->incr);
+ it->error += it->incr_error;
+ if (it->error >= onecputick) {
+ it->expires = cputime_sub(it->expires,
+ cputime_one_jiffy);
+ it->error -= onecputick;
+ }
+ } else {
+ it->expires = cputime_zero;
+ }
+
+ trace_itimer_expire(signo == SIGPROF ?
+ ITIMER_PROF : ITIMER_VIRTUAL,
+ tsk->signal->leader_pid, cur_time);
+ __group_send_sig_info(signo, SEND_SIG_PRIV, tsk);
+ }
+
+ if (!cputime_eq(it->expires, cputime_zero) &&
+ (cputime_eq(*expires, cputime_zero) ||
+ cputime_lt(it->expires, *expires))) {
+ *expires = it->expires;
+ }
+}
+
/*
* Check for any per-thread CPU timers that have fired and move them
* off the tsk->*_timers list onto the firing list. Per-thread timers
@@ -1090,10 +1127,10 @@ static void check_process_timers(struct task_struct *tsk,
* Don't sample the current process CPU clocks if there are no timers.
*/
if (list_empty(&timers[CPUCLOCK_PROF]) &&
- cputime_eq(sig->it_prof_expires, cputime_zero) &&
+ cputime_eq(sig->it[CPUCLOCK_PROF].expires, cputime_zero) &&
sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY &&
list_empty(&timers[CPUCLOCK_VIRT]) &&
- cputime_eq(sig->it_virt_expires, cputime_zero) &&
+ cputime_eq(sig->it[CPUCLOCK_VIRT].expires, cputime_zero) &&
list_empty(&timers[CPUCLOCK_SCHED])) {
stop_process_timers(tsk);
return;
@@ -1153,38 +1190,11 @@ static void check_process_timers(struct task_struct *tsk,
/*
* Check for the special case process timers.
*/
- if (!cputime_eq(sig->it_prof_expires, cputime_zero)) {
- if (cputime_ge(ptime, sig->it_prof_expires)) {
- /* ITIMER_PROF fires and reloads. */
- sig->it_prof_expires = sig->it_prof_incr;
- if (!cputime_eq(sig->it_prof_expires, cputime_zero)) {
- sig->it_prof_expires = cputime_add(
- sig->it_prof_expires, ptime);
- }
- __group_send_sig_info(SIGPROF, SEND_SIG_PRIV, tsk);
- }
- if (!cputime_eq(sig->it_prof_expires, cputime_zero) &&
- (cputime_eq(prof_expires, cputime_zero) ||
- cputime_lt(sig->it_prof_expires, prof_expires))) {
- prof_expires = sig->it_prof_expires;
- }
- }
- if (!cputime_eq(sig->it_virt_expires, cputime_zero)) {
- if (cputime_ge(utime, sig->it_virt_expires)) {
- /* ITIMER_VIRTUAL fires and reloads. */
- sig->it_virt_expires = sig->it_virt_incr;
- if (!cputime_eq(sig->it_virt_expires, cputime_zero)) {
- sig->it_virt_expires = cputime_add(
- sig->it_virt_expires, utime);
- }
- __group_send_sig_info(SIGVTALRM, SEND_SIG_PRIV, tsk);
- }
- if (!cputime_eq(sig->it_virt_expires, cputime_zero) &&
- (cputime_eq(virt_expires, cputime_zero) ||
- cputime_lt(sig->it_virt_expires, virt_expires))) {
- virt_expires = sig->it_virt_expires;
- }
- }
+ check_cpu_itimer(tsk, &sig->it[CPUCLOCK_PROF], &prof_expires, ptime,
+ SIGPROF);
+ check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime,
+ SIGVTALRM);
+
if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
unsigned long psecs = cputime_to_secs(ptime);
cputime_t x;
@@ -1457,7 +1467,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
if (!cputime_eq(*oldval, cputime_zero)) {
if (cputime_le(*oldval, now.cpu)) {
/* Just about to fire. */
- *oldval = jiffies_to_cputime(1);
+ *oldval = cputime_one_jiffy;
} else {
*oldval = cputime_sub(*oldval, now.cpu);
}
@@ -1703,10 +1713,15 @@ static __init int init_posix_cpu_timers(void)
.nsleep = thread_cpu_nsleep,
.nsleep_restart = thread_cpu_nsleep_restart,
};
+ struct timespec ts;
register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
register_posix_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
+ cputime_to_timespec(cputime_one_jiffy, &ts);
+ onecputick = ts.tv_nsec;
+ WARN_ON(ts.tv_sec != 0);
+
return 0;
}
__initcall(init_posix_cpu_timers);
diff --git a/kernel/power/process.c b/kernel/power/process.c
index da2072d73811..cc2e55373b68 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -9,6 +9,7 @@
#undef DEBUG
#include <linux/interrupt.h>
+#include <linux/oom.h>
#include <linux/suspend.h>
#include <linux/module.h>
#include <linux/syscalls.h>
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 97955b0e44f4..36cb168e4330 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -619,7 +619,7 @@ __register_nosave_region(unsigned long start_pfn, unsigned long end_pfn,
BUG_ON(!region);
} else
/* This allocation cannot fail */
- region = alloc_bootmem_low(sizeof(struct nosave_region));
+ region = alloc_bootmem(sizeof(struct nosave_region));
region->start_pfn = start_pfn;
region->end_pfn = end_pfn;
list_add_tail(&region->list, &nosave_regions);
diff --git a/kernel/printk.c b/kernel/printk.c
index 602033acd6c7..f38b07f78a4e 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -206,12 +206,11 @@ __setup("log_buf_len=", log_buf_len_setup);
#ifdef CONFIG_BOOT_PRINTK_DELAY
static unsigned int boot_delay; /* msecs delay after each printk during bootup */
-static unsigned long long printk_delay_msec; /* per msec, based on boot_delay */
+static unsigned long long loops_per_msec; /* based on boot_delay */
static int __init boot_delay_setup(char *str)
{
unsigned long lpj;
- unsigned long long loops_per_msec;
lpj = preset_lpj ? preset_lpj : 1000000; /* some guess */
loops_per_msec = (unsigned long long)lpj / 1000 * HZ;
@@ -220,10 +219,9 @@ static int __init boot_delay_setup(char *str)
if (boot_delay > 10 * 1000)
boot_delay = 0;
- printk_delay_msec = loops_per_msec;
- printk(KERN_DEBUG "boot_delay: %u, preset_lpj: %ld, lpj: %lu, "
- "HZ: %d, printk_delay_msec: %llu\n",
- boot_delay, preset_lpj, lpj, HZ, printk_delay_msec);
+ pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, "
+ "HZ: %d, loops_per_msec: %llu\n",
+ boot_delay, preset_lpj, lpj, HZ, loops_per_msec);
return 1;
}
__setup("boot_delay=", boot_delay_setup);
@@ -236,7 +234,7 @@ static void boot_delay_msec(void)
if (boot_delay == 0 || system_state != SYSTEM_BOOTING)
return;
- k = (unsigned long long)printk_delay_msec * boot_delay;
+ k = (unsigned long long)loops_per_msec * boot_delay;
timeout = jiffies + msecs_to_jiffies(boot_delay);
while (k) {
@@ -655,6 +653,20 @@ static int recursion_bug;
static int new_text_line = 1;
static char printk_buf[1024];
+int printk_delay_msec __read_mostly;
+
+static inline void printk_delay(void)
+{
+ if (unlikely(printk_delay_msec)) {
+ int m = printk_delay_msec;
+
+ while (m--) {
+ mdelay(1);
+ touch_nmi_watchdog();
+ }
+ }
+}
+
asmlinkage int vprintk(const char *fmt, va_list args)
{
int printed_len = 0;
@@ -664,6 +676,7 @@ asmlinkage int vprintk(const char *fmt, va_list args)
char *p;
boot_delay_msec();
+ printk_delay();
preempt_disable();
/* This stops the holder of console_sem just where we want him */
diff --git a/kernel/resource.c b/kernel/resource.c
index 78b087221c15..fb11a58b9594 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -223,13 +223,13 @@ int release_resource(struct resource *old)
EXPORT_SYMBOL(release_resource);
-#if defined(CONFIG_MEMORY_HOTPLUG) && !defined(CONFIG_ARCH_HAS_WALK_MEMORY)
+#if !defined(CONFIG_ARCH_HAS_WALK_MEMORY)
/*
* Finds the lowest memory reosurce exists within [res->start.res->end)
- * the caller must specify res->start, res->end, res->flags.
+ * the caller must specify res->start, res->end, res->flags and "name".
* If found, returns 0, res is overwritten, if not found, returns -1.
*/
-static int find_next_system_ram(struct resource *res)
+static int find_next_system_ram(struct resource *res, char *name)
{
resource_size_t start, end;
struct resource *p;
@@ -245,6 +245,8 @@ static int find_next_system_ram(struct resource *res)
/* system ram is just marked as IORESOURCE_MEM */
if (p->flags != res->flags)
continue;
+ if (name && strcmp(p->name, name))
+ continue;
if (p->start > end) {
p = NULL;
break;
@@ -262,19 +264,26 @@ static int find_next_system_ram(struct resource *res)
res->end = p->end;
return 0;
}
-int
-walk_memory_resource(unsigned long start_pfn, unsigned long nr_pages, void *arg,
- int (*func)(unsigned long, unsigned long, void *))
+
+/*
+ * This function calls callback against all memory range of "System RAM"
+ * which are marked as IORESOURCE_MEM and IORESOUCE_BUSY.
+ * Now, this function is only for "System RAM".
+ */
+int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
+ void *arg, int (*func)(unsigned long, unsigned long, void *))
{
struct resource res;
unsigned long pfn, len;
u64 orig_end;
int ret = -1;
+
res.start = (u64) start_pfn << PAGE_SHIFT;
res.end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1;
res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
orig_end = res.end;
- while ((res.start < res.end) && (find_next_system_ram(&res) >= 0)) {
+ while ((res.start < res.end) &&
+ (find_next_system_ram(&res, "System RAM") >= 0)) {
pfn = (unsigned long)(res.start >> PAGE_SHIFT);
len = (unsigned long)((res.end + 1 - res.start) >> PAGE_SHIFT);
ret = (*func)(pfn, len, arg);
diff --git a/kernel/sched.c b/kernel/sched.c
index 91843ba7f237..2f76e06bea58 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2904,6 +2904,19 @@ unsigned long nr_iowait(void)
return sum;
}
+unsigned long nr_iowait_cpu(void)
+{
+ struct rq *this = this_rq();
+ return atomic_read(&this->nr_iowait);
+}
+
+unsigned long this_cpu_load(void)
+{
+ struct rq *this = this_rq();
+ return this->cpu_load[0];
+}
+
+
/* Variables and functions for calc_load */
static atomic_long_t calc_load_tasks;
static unsigned long calc_load_update;
@@ -5079,17 +5092,16 @@ void account_idle_time(cputime_t cputime)
*/
void account_process_tick(struct task_struct *p, int user_tick)
{
- cputime_t one_jiffy = jiffies_to_cputime(1);
- cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy);
+ cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
struct rq *rq = this_rq();
if (user_tick)
- account_user_time(p, one_jiffy, one_jiffy_scaled);
+ account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
- account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
+ account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
one_jiffy_scaled);
else
- account_idle_time(one_jiffy);
+ account_idle_time(cputime_one_jiffy);
}
/*
diff --git a/kernel/smp.c b/kernel/smp.c
index 8e218500ab14..fd47a256a24e 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -29,8 +29,7 @@ enum {
struct call_function_data {
struct call_single_data csd;
- spinlock_t lock;
- unsigned int refs;
+ atomic_t refs;
cpumask_var_t cpumask;
};
@@ -39,9 +38,7 @@ struct call_single_queue {
spinlock_t lock;
};
-static DEFINE_PER_CPU(struct call_function_data, cfd_data) = {
- .lock = __SPIN_LOCK_UNLOCKED(cfd_data.lock),
-};
+static DEFINE_PER_CPU(struct call_function_data, cfd_data);
static int
hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
@@ -196,25 +193,18 @@ void generic_smp_call_function_interrupt(void)
list_for_each_entry_rcu(data, &call_function.queue, csd.list) {
int refs;
- spin_lock(&data->lock);
- if (!cpumask_test_cpu(cpu, data->cpumask)) {
- spin_unlock(&data->lock);
+ if (!cpumask_test_and_clear_cpu(cpu, data->cpumask))
continue;
- }
- cpumask_clear_cpu(cpu, data->cpumask);
- spin_unlock(&data->lock);
data->csd.func(data->csd.info);
- spin_lock(&data->lock);
- WARN_ON(data->refs == 0);
- refs = --data->refs;
+ refs = atomic_dec_return(&data->refs);
+ WARN_ON(refs < 0);
if (!refs) {
spin_lock(&call_function.lock);
list_del_rcu(&data->csd.list);
spin_unlock(&call_function.lock);
}
- spin_unlock(&data->lock);
if (refs)
continue;
@@ -419,23 +409,20 @@ void smp_call_function_many(const struct cpumask *mask,
data = &__get_cpu_var(cfd_data);
csd_lock(&data->csd);
- spin_lock_irqsave(&data->lock, flags);
data->csd.func = func;
data->csd.info = info;
cpumask_and(data->cpumask, mask, cpu_online_mask);
cpumask_clear_cpu(this_cpu, data->cpumask);
- data->refs = cpumask_weight(data->cpumask);
+ atomic_set(&data->refs, cpumask_weight(data->cpumask));
- spin_lock(&call_function.lock);
+ spin_lock_irqsave(&call_function.lock, flags);
/*
* Place entry at the _HEAD_ of the list, so that any cpu still
* observing the entry in generic_smp_call_function_interrupt()
* will not miss any other list entries:
*/
list_add_rcu(&data->csd.list, &call_function.queue);
- spin_unlock(&call_function.lock);
-
- spin_unlock_irqrestore(&data->lock, flags);
+ spin_unlock_irqrestore(&call_function.lock, flags);
/*
* Make the list addition visible before sending the ipi.
diff --git a/kernel/sys.c b/kernel/sys.c
index ea5c3bcac881..ebcb15611728 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1338,6 +1338,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
unsigned long flags;
cputime_t utime, stime;
struct task_cputime cputime;
+ unsigned long maxrss = 0;
memset((char *) r, 0, sizeof *r);
utime = stime = cputime_zero;
@@ -1346,6 +1347,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
utime = task_utime(current);
stime = task_stime(current);
accumulate_thread_rusage(p, r);
+ maxrss = p->signal->maxrss;
goto out;
}
@@ -1363,6 +1365,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
r->ru_majflt = p->signal->cmaj_flt;
r->ru_inblock = p->signal->cinblock;
r->ru_oublock = p->signal->coublock;
+ maxrss = p->signal->cmaxrss;
if (who == RUSAGE_CHILDREN)
break;
@@ -1377,6 +1380,8 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
r->ru_majflt += p->signal->maj_flt;
r->ru_inblock += p->signal->inblock;
r->ru_oublock += p->signal->oublock;
+ if (maxrss < p->signal->maxrss)
+ maxrss = p->signal->maxrss;
t = p;
do {
accumulate_thread_rusage(t, r);
@@ -1392,6 +1397,15 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
out:
cputime_to_timeval(utime, &r->ru_utime);
cputime_to_timeval(stime, &r->ru_stime);
+
+ if (who != RUSAGE_CHILDREN) {
+ struct mm_struct *mm = get_task_mm(p);
+ if (mm) {
+ setmax_mm_hiwater_rss(&maxrss, mm);
+ mmput(mm);
+ }
+ }
+ r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */
}
int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 6ba49c7cb128..0dfaa47d7cb6 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -106,6 +106,9 @@ static int __maybe_unused one = 1;
static int __maybe_unused two = 2;
static unsigned long one_ul = 1;
static int one_hundred = 100;
+#ifdef CONFIG_PRINTK
+static int ten_thousand = 10000;
+#endif
/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
@@ -722,6 +725,17 @@ static struct ctl_table kern_table[] = {
.mode = 0644,
.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,
+ .extra1 = &zero,
+ .extra2 = &ten_thousand,
+ },
#endif
{
.ctl_name = KERN_NGROUPS_MAX,
diff --git a/kernel/timer.c b/kernel/timer.c
index 811e5c391456..5db5a8d26811 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -46,6 +46,9 @@
#include <asm/timex.h>
#include <asm/io.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/timer.h>
+
u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
EXPORT_SYMBOL(jiffies_64);
@@ -521,6 +524,25 @@ static inline void debug_timer_activate(struct timer_list *timer) { }
static inline void debug_timer_deactivate(struct timer_list *timer) { }
#endif
+static inline void debug_init(struct timer_list *timer)
+{
+ debug_timer_init(timer);
+ trace_timer_init(timer);
+}
+
+static inline void
+debug_activate(struct timer_list *timer, unsigned long expires)
+{
+ debug_timer_activate(timer);
+ trace_timer_start(timer, expires);
+}
+
+static inline void debug_deactivate(struct timer_list *timer)
+{
+ debug_timer_deactivate(timer);
+ trace_timer_cancel(timer);
+}
+
static void __init_timer(struct timer_list *timer,
const char *name,
struct lock_class_key *key)
@@ -549,7 +571,7 @@ void init_timer_key(struct timer_list *timer,
const char *name,
struct lock_class_key *key)
{
- debug_timer_init(timer);
+ debug_init(timer);
__init_timer(timer, name, key);
}
EXPORT_SYMBOL(init_timer_key);
@@ -568,7 +590,7 @@ static inline void detach_timer(struct timer_list *timer,
{
struct list_head *entry = &timer->entry;
- debug_timer_deactivate(timer);
+ debug_deactivate(timer);
__list_del(entry->prev, entry->next);
if (clear_pending)
@@ -632,7 +654,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires,
goto out_unlock;
}
- debug_timer_activate(timer);
+ debug_activate(timer, expires);
new_base = __get_cpu_var(tvec_bases);
@@ -787,7 +809,7 @@ void add_timer_on(struct timer_list *timer, int cpu)
BUG_ON(timer_pending(timer) || !timer->function);
spin_lock_irqsave(&base->lock, flags);
timer_set_base(timer, base);
- debug_timer_activate(timer);
+ debug_activate(timer, timer->expires);
if (time_before(timer->expires, base->next_timer) &&
!tbase_get_deferrable(timer->base))
base->next_timer = timer->expires;
@@ -1000,7 +1022,9 @@ static inline void __run_timers(struct tvec_base *base)
*/
lock_map_acquire(&lockdep_map);
+ trace_timer_expire_entry(timer);
fn(data);
+ trace_timer_expire_exit(timer);
lock_map_release(&lockdep_map);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e71634604400..b416512ad17f 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -83,7 +83,7 @@ config RING_BUFFER_ALLOW_SWAP
# This allows those options to appear when no other tracer is selected. But the
# options do not appear when something else selects it. We need the two options
# GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the
-# hidding of the automatic options options.
+# hidding of the automatic options.
config TRACING
bool
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index c71e91bf7372..23df7771c937 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1520,7 +1520,7 @@ static int t_show(struct seq_file *m, void *v)
return 0;
}
-static struct seq_operations show_ftrace_seq_ops = {
+static const struct seq_operations show_ftrace_seq_ops = {
.start = t_start,
.next = t_next,
.stop = t_stop,
@@ -2459,7 +2459,7 @@ static int g_show(struct seq_file *m, void *v)
return 0;
}
-static struct seq_operations ftrace_graph_seq_ops = {
+static const struct seq_operations ftrace_graph_seq_ops = {
.start = g_start,
.next = g_next,
.stop = g_stop,
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a35925d222ba..6c0f6a8a22eb 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1949,7 +1949,7 @@ static int s_show(struct seq_file *m, void *v)
return 0;
}
-static struct seq_operations tracer_seq_ops = {
+static const struct seq_operations tracer_seq_ops = {
.start = s_start,
.next = s_next,
.stop = s_stop,
@@ -2163,7 +2163,7 @@ static int t_show(struct seq_file *m, void *v)
return 0;
}
-static struct seq_operations show_traces_seq_ops = {
+static const struct seq_operations show_traces_seq_ops = {
.start = t_start,
.next = t_next,
.stop = t_stop,
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
index ca7d7c4d0c2a..23b63859130e 100644
--- a/kernel/trace/trace_hw_branches.c
+++ b/kernel/trace/trace_hw_branches.c
@@ -155,7 +155,7 @@ static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
seq_print_ip_sym(seq, it->from, symflags) &&
trace_seq_printf(seq, "\n"))
return TRACE_TYPE_HANDLED;
- return TRACE_TYPE_PARTIAL_LINE;;
+ return TRACE_TYPE_PARTIAL_LINE;
}
return TRACE_TYPE_UNHANDLED;
}
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 9489a0a9b1be..cc89be5bc0f8 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -48,7 +48,7 @@ static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE];
/*
* Note about RCU :
- * It is used to to delay the free of multiple probes array until a quiescent
+ * It is used to delay the free of multiple probes array until a quiescent
* state is reached.
* Tracepoint entries modifications are protected by the tracepoints_mutex.
*/
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-09 06:40:32 +0100