[GIT PULL] scheduler fixes

From: Ingo Molnar
Date: Sat Feb 22 2014 - 14:20:22 EST


Linus,

Please pull the latest sched-urgent-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-for-linus

# HEAD: 995b9ea440862def83e8fcb1b498e68f93d4af59 sched/deadline: Remove useless dl_nr_total

Misc fixlets: a fair number of them resulting from the new
SCHED_DEADLINE code.

Sorry about the weekend pull request ... :-/

Thanks,

Ingo

------------------>
Boris Ostrovsky (1):
sched/deadline: Test for CPU's presence explicitly

Juri Lelli (3):
sched/deadline: Fix bad accounting of nr_running
sched/core: Fix sched_rt_global_validate
sched/core: Make dl_b->lock IRQ safe

Kirill Tkhai (1):
sched/deadline: Remove useless dl_nr_total

Peter Zijlstra (1):
sched: Add 'flags' argument to sched_{set,get}attr() syscalls

Rik van Riel (1):
sched,numa: add cond_resched to task_numa_work

Steven Rostedt (1):
sched/deadline: Fix overflow to handle period==0 and deadline!=0

Vegard Nossum (1):
sched: Fix information leak in sys_sched_getattr()


include/linux/syscalls.h | 6 ++++--
kernel/sched/core.c | 28 ++++++++++++++++------------
kernel/sched/cpudeadline.c | 6 +++---
kernel/sched/deadline.c | 10 +++-------
kernel/sched/fair.c | 2 ++
kernel/sched/sched.h | 1 -
6 files changed, 28 insertions(+), 25 deletions(-)

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 40ed9e9..a747a77 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -281,13 +281,15 @@ asmlinkage long sys_sched_setscheduler(pid_t pid, int policy,
asmlinkage long sys_sched_setparam(pid_t pid,
struct sched_param __user *param);
asmlinkage long sys_sched_setattr(pid_t pid,
- struct sched_attr __user *attr);
+ struct sched_attr __user *attr,
+ unsigned int flags);
asmlinkage long sys_sched_getscheduler(pid_t pid);
asmlinkage long sys_sched_getparam(pid_t pid,
struct sched_param __user *param);
asmlinkage long sys_sched_getattr(pid_t pid,
struct sched_attr __user *attr,
- unsigned int size);
+ unsigned int size,
+ unsigned int flags);
asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
unsigned long __user *user_mask_ptr);
asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b46131e..6edbef2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1952,7 +1952,7 @@ static int dl_overflow(struct task_struct *p, int policy,
{

struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
- u64 period = attr->sched_period;
+ u64 period = attr->sched_period ?: attr->sched_deadline;
u64 runtime = attr->sched_runtime;
u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
int cpus, err = -1;
@@ -3661,13 +3661,14 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
* @pid: the pid in question.
* @uattr: structure containing the extended parameters.
*/
-SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr)
+SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
+ unsigned int, flags)
{
struct sched_attr attr;
struct task_struct *p;
int retval;

- if (!uattr || pid < 0)
+ if (!uattr || pid < 0 || flags)
return -EINVAL;

if (sched_copy_attr(uattr, &attr))
@@ -3786,7 +3787,7 @@ static int sched_read_attr(struct sched_attr __user *uattr,
attr->size = usize;
}

- ret = copy_to_user(uattr, attr, usize);
+ ret = copy_to_user(uattr, attr, attr->size);
if (ret)
return -EFAULT;

@@ -3804,8 +3805,8 @@ err_size:
* @uattr: structure containing the extended parameters.
* @size: sizeof(attr) for fwd/bwd comp.
*/
-SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
- unsigned int, size)
+SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
+ unsigned int, size, unsigned int, flags)
{
struct sched_attr attr = {
.size = sizeof(struct sched_attr),
@@ -3814,7 +3815,7 @@ SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
int retval;

if (!uattr || pid < 0 || size > PAGE_SIZE ||
- size < SCHED_ATTR_SIZE_VER0)
+ size < SCHED_ATTR_SIZE_VER0 || flags)
return -EINVAL;

rcu_read_lock();
@@ -7422,6 +7423,7 @@ static int sched_dl_global_constraints(void)
u64 period = global_rt_period();
u64 new_bw = to_ratio(period, runtime);
int cpu, ret = 0;
+ unsigned long flags;

/*
* Here we want to check the bandwidth not being set to some
@@ -7435,10 +7437,10 @@ static int sched_dl_global_constraints(void)
for_each_possible_cpu(cpu) {
struct dl_bw *dl_b = dl_bw_of(cpu);

- raw_spin_lock(&dl_b->lock);
+ raw_spin_lock_irqsave(&dl_b->lock, flags);
if (new_bw < dl_b->total_bw)
ret = -EBUSY;
- raw_spin_unlock(&dl_b->lock);
+ raw_spin_unlock_irqrestore(&dl_b->lock, flags);

if (ret)
break;
@@ -7451,6 +7453,7 @@ static void sched_dl_do_global(void)
{
u64 new_bw = -1;
int cpu;
+ unsigned long flags;

def_dl_bandwidth.dl_period = global_rt_period();
def_dl_bandwidth.dl_runtime = global_rt_runtime();
@@ -7464,9 +7467,9 @@ static void sched_dl_do_global(void)
for_each_possible_cpu(cpu) {
struct dl_bw *dl_b = dl_bw_of(cpu);

- raw_spin_lock(&dl_b->lock);
+ raw_spin_lock_irqsave(&dl_b->lock, flags);
dl_b->bw = new_bw;
- raw_spin_unlock(&dl_b->lock);
+ raw_spin_unlock_irqrestore(&dl_b->lock, flags);
}
}

@@ -7475,7 +7478,8 @@ static int sched_rt_global_validate(void)
if (sysctl_sched_rt_period <= 0)
return -EINVAL;

- if (sysctl_sched_rt_runtime > sysctl_sched_rt_period)
+ if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
+ (sysctl_sched_rt_runtime > sysctl_sched_rt_period))
return -EINVAL;

return 0;
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 045fc74..5b8838b 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -70,7 +70,7 @@ static void cpudl_heapify(struct cpudl *cp, int idx)

static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
{
- WARN_ON(idx > num_present_cpus() || idx == IDX_INVALID);
+ WARN_ON(!cpu_present(idx) || idx == IDX_INVALID);

if (dl_time_before(new_dl, cp->elements[idx].dl)) {
cp->elements[idx].dl = new_dl;
@@ -117,7 +117,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
}

out:
- WARN_ON(best_cpu > num_present_cpus() && best_cpu != -1);
+ WARN_ON(!cpu_present(best_cpu) && best_cpu != -1);

return best_cpu;
}
@@ -137,7 +137,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
int old_idx, new_cpu;
unsigned long flags;

- WARN_ON(cpu > num_present_cpus());
+ WARN_ON(!cpu_present(cpu));

raw_spin_lock_irqsave(&cp->lock, flags);
old_idx = cp->cpu_to_idx[cpu];
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 0dd5e09..15cbc17 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -121,7 +121,7 @@ static inline void dl_clear_overload(struct rq *rq)

static void update_dl_migration(struct dl_rq *dl_rq)
{
- if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_total > 1) {
+ if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) {
if (!dl_rq->overloaded) {
dl_set_overload(rq_of_dl_rq(dl_rq));
dl_rq->overloaded = 1;
@@ -137,7 +137,6 @@ static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
struct task_struct *p = dl_task_of(dl_se);
dl_rq = &rq_of_dl_rq(dl_rq)->dl;

- dl_rq->dl_nr_total++;
if (p->nr_cpus_allowed > 1)
dl_rq->dl_nr_migratory++;

@@ -149,7 +148,6 @@ static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
struct task_struct *p = dl_task_of(dl_se);
dl_rq = &rq_of_dl_rq(dl_rq)->dl;

- dl_rq->dl_nr_total--;
if (p->nr_cpus_allowed > 1)
dl_rq->dl_nr_migratory--;

@@ -717,6 +715,7 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)

WARN_ON(!dl_prio(prio));
dl_rq->dl_nr_running++;
+ inc_nr_running(rq_of_dl_rq(dl_rq));

inc_dl_deadline(dl_rq, deadline);
inc_dl_migration(dl_se, dl_rq);
@@ -730,6 +729,7 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
WARN_ON(!dl_prio(prio));
WARN_ON(!dl_rq->dl_nr_running);
dl_rq->dl_nr_running--;
+ dec_nr_running(rq_of_dl_rq(dl_rq));

dec_dl_deadline(dl_rq, dl_se->deadline);
dec_dl_migration(dl_se, dl_rq);
@@ -836,8 +836,6 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)

if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
enqueue_pushable_dl_task(rq, p);
-
- inc_nr_running(rq);
}

static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
@@ -850,8 +848,6 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
{
update_curr_dl(rq);
__dequeue_task_dl(rq, p, flags);
-
- dec_nr_running(rq);
}

/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 966cc2b..7815709 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1757,6 +1757,8 @@ void task_numa_work(struct callback_head *work)
start = end;
if (pages <= 0)
goto out;
+
+ cond_resched();
} while (end != vma->vm_end);
}

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c2119fd..f964add 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -462,7 +462,6 @@ struct dl_rq {
} earliest_dl;

unsigned long dl_nr_migratory;
- unsigned long dl_nr_total;
int overloaded;

/*
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/