summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/cgroup.c17
-rw-r--r--kernel/sched/core.c68
-rw-r--r--kernel/sched/fair.c42
-rw-r--r--kernel/sched/rt.c51
-rw-r--r--kernel/sys.c60
-rw-r--r--kernel/time/tick-sched.c1
6 files changed, 162 insertions, 77 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 0f3527d6184a..72fcd3069a90 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -896,10 +896,13 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
mutex_unlock(&cgroup_mutex);
/*
- * Drop the active superblock reference that we took when we
- * created the cgroup
+ * We want to drop the active superblock reference from the
+ * cgroup creation after all the dentry refs are gone -
+ * kill_sb gets mighty unhappy otherwise. Mark
+ * dentry->d_fsdata with cgroup_diput() to tell
+ * cgroup_d_release() to call deactivate_super().
*/
- deactivate_super(cgrp->root->sb);
+ dentry->d_fsdata = cgroup_diput;
/*
* if we're getting rid of the cgroup, refcount should ensure
@@ -925,6 +928,13 @@ static int cgroup_delete(const struct dentry *d)
return 1;
}
+static void cgroup_d_release(struct dentry *dentry)
+{
+ /* did cgroup_diput() tell me to deactivate super? */
+ if (dentry->d_fsdata == cgroup_diput)
+ deactivate_super(dentry->d_sb);
+}
+
static void remove_dir(struct dentry *d)
{
struct dentry *parent = dget(d->d_parent);
@@ -1532,6 +1542,7 @@ static int cgroup_get_rootdir(struct super_block *sb)
static const struct dentry_operations cgroup_dops = {
.d_iput = cgroup_diput,
.d_delete = cgroup_delete,
+ .d_release = cgroup_d_release,
};
struct inode *inode =
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 39eb6011bc38..c46958e26121 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -142,9 +142,8 @@ const_debug unsigned int sysctl_sched_features =
#define SCHED_FEAT(name, enabled) \
#name ,
-static __read_mostly char *sched_feat_names[] = {
+static const char * const sched_feat_names[] = {
#include "features.h"
- NULL
};
#undef SCHED_FEAT
@@ -2517,25 +2516,32 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
sched_avg_update(this_rq);
}
+#ifdef CONFIG_NO_HZ
+/*
+ * There is no sane way to deal with nohz on smp when using jiffies because the
+ * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
+ * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
+ *
+ * Therefore we cannot use the delta approach from the regular tick since that
+ * would seriously skew the load calculation. However we'll make do for those
+ * updates happening while idle (nohz_idle_balance) or coming out of idle
+ * (tick_nohz_idle_exit).
+ *
+ * This means we might still be one tick off for nohz periods.
+ */
+
/*
* Called from nohz_idle_balance() to update the load ratings before doing the
* idle balance.
*/
void update_idle_cpu_load(struct rq *this_rq)
{
- unsigned long curr_jiffies = jiffies;
+ unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
unsigned long load = this_rq->load.weight;
unsigned long pending_updates;
/*
- * Bloody broken means of dealing with nohz, but better than nothing..
- * jiffies is updated by one cpu, another cpu can drift wrt the jiffy
- * update and see 0 difference the one time and 2 the next, even though
- * we ticked at roughtly the same rate.
- *
- * Hence we only use this from nohz_idle_balance() and skip this
- * nonsense when called from the scheduler_tick() since that's
- * guaranteed a stable rate.
+ * bail if there's load or we're actually up-to-date.
*/
if (load || curr_jiffies == this_rq->last_load_update_tick)
return;
@@ -2547,12 +2553,38 @@ void update_idle_cpu_load(struct rq *this_rq)
}
/*
+ * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
+ */
+void update_cpu_load_nohz(void)
+{
+ struct rq *this_rq = this_rq();
+ unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
+ unsigned long pending_updates;
+
+ if (curr_jiffies == this_rq->last_load_update_tick)
+ return;
+
+ raw_spin_lock(&this_rq->lock);
+ pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+ if (pending_updates) {
+ this_rq->last_load_update_tick = curr_jiffies;
+ /*
+ * We were idle, this means load 0, the current load might be
+ * !0 due to remote wakeups and the sort.
+ */
+ __update_cpu_load(this_rq, 0, pending_updates);
+ }
+ raw_spin_unlock(&this_rq->lock);
+}
+#endif /* CONFIG_NO_HZ */
+
+/*
* Called from scheduler_tick()
*/
static void update_cpu_load_active(struct rq *this_rq)
{
/*
- * See the mess in update_idle_cpu_load().
+ * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
*/
this_rq->last_load_update_tick = jiffies;
__update_cpu_load(this_rq, this_rq->load.weight, 1);
@@ -4982,7 +5014,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
p->sched_class->set_cpus_allowed(p, new_mask);
cpumask_copy(&p->cpus_allowed, new_mask);
- p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
+ p->nr_cpus_allowed = cpumask_weight(new_mask);
}
/*
@@ -5997,11 +6029,14 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
cpumask_or(covered, covered, sg_span);
- sg->sgp = *per_cpu_ptr(sdd->sgp, cpumask_first(sg_span));
+ sg->sgp = *per_cpu_ptr(sdd->sgp, i);
atomic_inc(&sg->sgp->ref);
- if (cpumask_test_cpu(cpu, sg_span))
+ if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
+ cpumask_first(sg_span) == cpu) {
+ WARN_ON_ONCE(!cpumask_test_cpu(cpu, sg_span));
groups = sg;
+ }
if (!first)
first = sg;
@@ -6403,7 +6438,7 @@ static void sched_init_numa(void)
return;
for (j = 0; j < nr_node_ids; j++) {
- struct cpumask *mask = kzalloc_node(cpumask_size(), GFP_KERNEL, j);
+ struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
if (!mask)
return;
@@ -6691,7 +6726,6 @@ static int init_sched_domains(const struct cpumask *cpu_map)
if (!doms_cur)
doms_cur = &fallback_doms;
cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
- dattr_cur = NULL;
err = build_sched_domains(doms_cur[0], NULL);
register_sched_domain_sysctl();
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 940e6d17cf96..b2a2d236f27b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2703,7 +2703,7 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
int want_sd = 1;
int sync = wake_flags & WF_SYNC;
- if (p->rt.nr_cpus_allowed == 1)
+ if (p->nr_cpus_allowed == 1)
return prev_cpu;
if (sd_flag & SD_BALANCE_WAKE) {
@@ -3503,15 +3503,22 @@ unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
unsigned long scale_rt_power(int cpu)
{
struct rq *rq = cpu_rq(cpu);
- u64 total, available;
+ u64 total, available, age_stamp, avg;
- total = sched_avg_period() + (rq->clock - rq->age_stamp);
+ /*
+ * Since we're reading these variables without serialization make sure
+ * we read them once before doing sanity checks on them.
+ */
+ age_stamp = ACCESS_ONCE(rq->age_stamp);
+ avg = ACCESS_ONCE(rq->rt_avg);
+
+ total = sched_avg_period() + (rq->clock - age_stamp);
- if (unlikely(total < rq->rt_avg)) {
+ if (unlikely(total < avg)) {
/* Ensures that power won't end up being negative */
available = 0;
} else {
- available = total - rq->rt_avg;
+ available = total - avg;
}
if (unlikely((s64)total < SCHED_POWER_SCALE))
@@ -3574,11 +3581,26 @@ void update_group_power(struct sched_domain *sd, int cpu)
power = 0;
- group = child->groups;
- do {
- power += group->sgp->power;
- group = group->next;
- } while (group != child->groups);
+ if (child->flags & SD_OVERLAP) {
+ /*
+ * SD_OVERLAP domains cannot assume that child groups
+ * span the current group.
+ */
+
+ for_each_cpu(cpu, sched_group_cpus(sdg))
+ power += power_of(cpu);
+ } else {
+ /*
+ * !SD_OVERLAP domains can assume that child groups
+ * span the current group.
+ */
+
+ group = child->groups;
+ do {
+ power += group->sgp->power;
+ group = group->next;
+ } while (group != child->groups);
+ }
sdg->sgp->power = power;
}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index c5565c3c515f..2a4e8dffbd6b 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -274,13 +274,16 @@ static void update_rt_migration(struct rt_rq *rt_rq)
static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
+ struct task_struct *p;
+
if (!rt_entity_is_task(rt_se))
return;
+ p = rt_task_of(rt_se);
rt_rq = &rq_of_rt_rq(rt_rq)->rt;
rt_rq->rt_nr_total++;
- if (rt_se->nr_cpus_allowed > 1)
+ if (p->nr_cpus_allowed > 1)
rt_rq->rt_nr_migratory++;
update_rt_migration(rt_rq);
@@ -288,13 +291,16 @@ static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
+ struct task_struct *p;
+
if (!rt_entity_is_task(rt_se))
return;
+ p = rt_task_of(rt_se);
rt_rq = &rq_of_rt_rq(rt_rq)->rt;
rt_rq->rt_nr_total--;
- if (rt_se->nr_cpus_allowed > 1)
+ if (p->nr_cpus_allowed > 1)
rt_rq->rt_nr_migratory--;
update_rt_migration(rt_rq);
@@ -1161,7 +1167,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);
- if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
+ if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
enqueue_pushable_task(rq, p);
inc_nr_running(rq);
@@ -1225,7 +1231,7 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
cpu = task_cpu(p);
- if (p->rt.nr_cpus_allowed == 1)
+ if (p->nr_cpus_allowed == 1)
goto out;
/* For anything but wake ups, just return the task_cpu */
@@ -1260,9 +1266,9 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
* will have to sort it out.
*/
if (curr && unlikely(rt_task(curr)) &&
- (curr->rt.nr_cpus_allowed < 2 ||
+ (curr->nr_cpus_allowed < 2 ||
curr->prio <= p->prio) &&
- (p->rt.nr_cpus_allowed > 1)) {
+ (p->nr_cpus_allowed > 1)) {
int target = find_lowest_rq(p);
if (target != -1)
@@ -1276,10 +1282,10 @@ out:
static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
{
- if (rq->curr->rt.nr_cpus_allowed == 1)
+ if (rq->curr->nr_cpus_allowed == 1)
return;
- if (p->rt.nr_cpus_allowed != 1
+ if (p->nr_cpus_allowed != 1
&& cpupri_find(&rq->rd->cpupri, p, NULL))
return;
@@ -1395,7 +1401,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
* The previous task needs to be made eligible for pushing
* if it is still active
*/
- if (on_rt_rq(&p->rt) && p->rt.nr_cpus_allowed > 1)
+ if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
enqueue_pushable_task(rq, p);
}
@@ -1408,7 +1414,7 @@ static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
{
if (!task_running(rq, p) &&
(cpu < 0 || cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) &&
- (p->rt.nr_cpus_allowed > 1))
+ (p->nr_cpus_allowed > 1))
return 1;
return 0;
}
@@ -1464,7 +1470,7 @@ static int find_lowest_rq(struct task_struct *task)
if (unlikely(!lowest_mask))
return -1;
- if (task->rt.nr_cpus_allowed == 1)
+ if (task->nr_cpus_allowed == 1)
return -1; /* No other targets possible */
if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
@@ -1586,7 +1592,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq)
BUG_ON(rq->cpu != task_cpu(p));
BUG_ON(task_current(rq, p));
- BUG_ON(p->rt.nr_cpus_allowed <= 1);
+ BUG_ON(p->nr_cpus_allowed <= 1);
BUG_ON(!p->on_rq);
BUG_ON(!rt_task(p));
@@ -1793,9 +1799,9 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
if (!task_running(rq, p) &&
!test_tsk_need_resched(rq->curr) &&
has_pushable_tasks(rq) &&
- p->rt.nr_cpus_allowed > 1 &&
+ p->nr_cpus_allowed > 1 &&
rt_task(rq->curr) &&
- (rq->curr->rt.nr_cpus_allowed < 2 ||
+ (rq->curr->nr_cpus_allowed < 2 ||
rq->curr->prio <= p->prio))
push_rt_tasks(rq);
}
@@ -1817,7 +1823,7 @@ static void set_cpus_allowed_rt(struct task_struct *p,
* Only update if the process changes its state from whether it
* can migrate or not.
*/
- if ((p->rt.nr_cpus_allowed > 1) == (weight > 1))
+ if ((p->nr_cpus_allowed > 1) == (weight > 1))
return;
rq = task_rq(p);
@@ -1979,6 +1985,8 @@ static void watchdog(struct rq *rq, struct task_struct *p)
static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
{
+ struct sched_rt_entity *rt_se = &p->rt;
+
update_curr_rt(rq);
watchdog(rq, p);
@@ -1996,12 +2004,15 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
p->rt.time_slice = RR_TIMESLICE;
/*
- * Requeue to the end of queue if we are not the only element
- * on the queue:
+ * Requeue to the end of queue if we (and all of our ancestors) are the
+ * only element on the queue
*/
- if (p->rt.run_list.prev != p->rt.run_list.next) {
- requeue_task_rt(rq, p, 0);
- set_tsk_need_resched(p);
+ for_each_sched_rt_entity(rt_se) {
+ if (rt_se->run_list.prev != rt_se->run_list.next) {
+ requeue_task_rt(rq, p, 0);
+ set_tsk_need_resched(p);
+ return;
+ }
}
}
diff --git a/kernel/sys.c b/kernel/sys.c
index 9ff89cb9657a..f0ec44dcd415 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1786,27 +1786,13 @@ SYSCALL_DEFINE1(umask, int, mask)
}
#ifdef CONFIG_CHECKPOINT_RESTORE
-static bool vma_flags_mismatch(struct vm_area_struct *vma,
- unsigned long required,
- unsigned long banned)
-{
- return (vma->vm_flags & required) != required ||
- (vma->vm_flags & banned);
-}
-
static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
{
+ struct vm_area_struct *vma;
struct file *exe_file;
struct dentry *dentry;
int err;
- /*
- * Setting new mm::exe_file is only allowed when no VM_EXECUTABLE vma's
- * remain. So perform a quick test first.
- */
- if (mm->num_exe_file_vmas)
- return -EBUSY;
-
exe_file = fget(fd);
if (!exe_file)
return -EBADF;
@@ -1827,17 +1813,30 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
if (err)
goto exit;
+ down_write(&mm->mmap_sem);
+
+ /*
+ * Forbid mm->exe_file change if there are mapped other files.
+ */
+ err = -EBUSY;
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (vma->vm_file && !path_equal(&vma->vm_file->f_path,
+ &exe_file->f_path))
+ goto exit_unlock;
+ }
+
/*
* The symlink can be changed only once, just to disallow arbitrary
* transitions malicious software might bring in. This means one
* could make a snapshot over all processes running and monitor
* /proc/pid/exe changes to notice unusual activity if needed.
*/
- down_write(&mm->mmap_sem);
- if (likely(!mm->exe_file))
- set_mm_exe_file(mm, exe_file);
- else
- err = -EBUSY;
+ err = -EPERM;
+ if (test_and_set_bit(MMF_EXE_FILE_CHANGED, &mm->flags))
+ goto exit_unlock;
+
+ set_mm_exe_file(mm, exe_file);
+exit_unlock:
up_write(&mm->mmap_sem);
exit:
@@ -1862,7 +1861,7 @@ static int prctl_set_mm(int opt, unsigned long addr,
if (opt == PR_SET_MM_EXE_FILE)
return prctl_set_mm_exe_file(mm, (unsigned int)addr);
- if (addr >= TASK_SIZE)
+ if (addr >= TASK_SIZE || addr < mmap_min_addr)
return -EINVAL;
error = -EINVAL;
@@ -1924,12 +1923,6 @@ static int prctl_set_mm(int opt, unsigned long addr,
error = -EFAULT;
goto out;
}
-#ifdef CONFIG_STACK_GROWSUP
- if (vma_flags_mismatch(vma, VM_READ | VM_WRITE | VM_GROWSUP, 0))
-#else
- if (vma_flags_mismatch(vma, VM_READ | VM_WRITE | VM_GROWSDOWN, 0))
-#endif
- goto out;
if (opt == PR_SET_MM_START_STACK)
mm->start_stack = addr;
else if (opt == PR_SET_MM_ARG_START)
@@ -1981,12 +1974,22 @@ out:
up_read(&mm->mmap_sem);
return error;
}
+
+static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
+{
+ return put_user(me->clear_child_tid, tid_addr);
+}
+
#else /* CONFIG_CHECKPOINT_RESTORE */
static int prctl_set_mm(int opt, unsigned long addr,
unsigned long arg4, unsigned long arg5)
{
return -EINVAL;
}
+static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
+{
+ return -EINVAL;
+}
#endif
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
@@ -2124,6 +2127,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
else
return -EINVAL;
break;
+ case PR_GET_TID_ADDRESS:
+ error = prctl_get_tid_address(me, (int __user **)arg2);
+ break;
default:
return -EINVAL;
}
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index efd386667536..da70c6db496c 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -576,6 +576,7 @@ void tick_nohz_idle_exit(void)
/* Update jiffies first */
select_nohz_load_balancer(0);
tick_do_update_jiffies64(now);
+ update_cpu_load_nohz();
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
/*
generated by cgit v1.2.3 (git 2.0.4) at 2024-11-20 05:40:26 +0000