summaryrefslogtreecommitdiff
path: root/kernel/sched
diff options
context:
space:
mode:
authorElena Reshetova <elena.reshetova@intel.com>2019-01-18 14:27:28 +0200
committerIngo Molnar <mingo@kernel.org>2019-02-04 08:53:54 +0100
commitc45a77952427b678aa9205e1b0ee3bcf33339a2e (patch)
treedac91a1d9af9d651c1f991153263068c314131c2 /kernel/sched
parent60d4de3ff7f775509deba94b3db3c1abe55bf7a5 (diff)
sched/fair: Convert numa_group.refcount to refcount_t
atomic_t variables are currently used to implement reference counters with the following properties: - counter is initialized to 1 using atomic_set() - a resource is freed upon counter reaching zero - once counter reaches zero, its further increments aren't allowed - counter schema uses basic atomic operations (set, inc, inc_not_zero, dec_and_test, etc.) Such atomic variables should be converted to a newly provided refcount_t type and API that prevents accidental counter overflows and underflows. This is important since overflows and underflows can lead to use-after-free situation and be exploitable. The variable numa_group.refcount is used as pure reference counter. Convert it to refcount_t and fix up the operations. ** Important note for maintainers: Some functions from refcount_t API defined in lib/refcount.c have different memory ordering guarantees than their atomic counterparts. The full comparison can be seen in https://lkml.org/lkml/2017/11/15/57 and it is hopefully soon in state to be merged to the documentation tree. Normally the differences should not matter since refcount_t provides enough guarantees to satisfy the refcounting use cases, but in some rare cases it might matter. Please double check that you don't have some undocumented memory guarantees for this variable usage. For the numa_group.refcount it might make a difference in following places: - get_numa_group(): increment in refcount_inc_not_zero() only guarantees control dependency on success vs. fully ordered atomic counterpart - put_numa_group(): decrement in refcount_dec_and_test() only provides RELEASE ordering and control dependency on success vs. fully ordered atomic counterpart Suggested-by: Kees Cook <keescook@chromium.org> Signed-off-by: Elena Reshetova <elena.reshetova@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: David Windsor <dwindsor@gmail.com> Reviewed-by: Hans Liljestrand <ishkamiel@gmail.com> Reviewed-by: Andrea Parri <andrea.parri@amarulasolutions.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: akpm@linux-foundation.org Cc: viro@zeniv.linux.org.uk Link: https://lkml.kernel.org/r/1547814450-18902-4-git-send-email-elena.reshetova@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/fair.c12
1 files changed, 6 insertions, 6 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e2ff4b69dcf6..5b2b919c7929 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1035,7 +1035,7 @@ unsigned int sysctl_numa_balancing_scan_size = 256;
unsigned int sysctl_numa_balancing_scan_delay = 1000;
struct numa_group {
- atomic_t refcount;
+ refcount_t refcount;
spinlock_t lock; /* nr_tasks, tasks */
int nr_tasks;
@@ -1104,7 +1104,7 @@ static unsigned int task_scan_start(struct task_struct *p)
unsigned long shared = group_faults_shared(ng);
unsigned long private = group_faults_priv(ng);
- period *= atomic_read(&ng->refcount);
+ period *= refcount_read(&ng->refcount);
period *= shared + 1;
period /= private + shared + 1;
}
@@ -1127,7 +1127,7 @@ static unsigned int task_scan_max(struct task_struct *p)
unsigned long private = group_faults_priv(ng);
unsigned long period = smax;
- period *= atomic_read(&ng->refcount);
+ period *= refcount_read(&ng->refcount);
period *= shared + 1;
period /= private + shared + 1;
@@ -2203,12 +2203,12 @@ static void task_numa_placement(struct task_struct *p)
static inline int get_numa_group(struct numa_group *grp)
{
- return atomic_inc_not_zero(&grp->refcount);
+ return refcount_inc_not_zero(&grp->refcount);
}
static inline void put_numa_group(struct numa_group *grp)
{
- if (atomic_dec_and_test(&grp->refcount))
+ if (refcount_dec_and_test(&grp->refcount))
kfree_rcu(grp, rcu);
}
@@ -2229,7 +2229,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
if (!grp)
return;
- atomic_set(&grp->refcount, 1);
+ refcount_set(&grp->refcount, 1);
grp->active_nodes = 1;
grp->max_faults_cpu = 0;
spin_lock_init(&grp->lock);