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
up to: cb361d8cdef6: sched/fair: Use RCU accessors consistently for
->numa_group
Two fixes for the fair scheduling class:
- Prevent freeing memory which is accessible by concurrent readers
- Make the RCU annotations for numa groups consistent
Thanks,
tglx
-->
Jann Horn (2):
sched/fair: Don't free p->numa_faults with concurrent readers
sched/fair: Use RCU accessors consistently for ->numa_group
fs/exec.c| 2 +-
include/linux/sched.h| 10 ++-
include/linux/sched/numa_balancing.h | 4 +-
kernel/fork.c| 2 +-
kernel/sched/fair.c | 144 ---
5 files changed, 114 insertions(+), 48 deletions(-)
diff --git a/fs/exec.c b/fs/exec.c
index c71cbfe6826a..f7f6a140856a 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1828,7 +1828,7 @@ static int __do_execve_file(int fd, struct filename
*filename,
membarrier_execve(current);
rseq_execve(current);
acct_update_integrals(current);
- task_numa_free(current);
+ task_numa_free(current, false);
free_bprm(bprm);
kfree(pathbuf);
if (filename)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8dc1811487f5..9f51932bd543 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1092,7 +1092,15 @@ struct task_struct {
u64 last_sum_exec_runtime;
struct callback_headnuma_work;
- struct numa_group *numa_group;
+ /*
+* This pointer is only modified for current in syscall and
+* pagefault context (and for tasks being destroyed), so it can be read
+* from any of the following contexts:
+* - RCU read-side critical section
+* - current->numa_group from everywhere
+* - task's runqueue locked, task not running
+*/
+ struct numa_group __rcu *numa_group;
/*
* numa_faults is an array split into four regions:
diff --git a/include/linux/sched/numa_balancing.h
b/include/linux/sched/numa_balancing.h
index e7dd04a84ba8..3988762efe15 100644
--- a/include/linux/sched/numa_balancing.h
+++ b/include/linux/sched/numa_balancing.h
@@ -19,7 +19,7 @@
extern void task_numa_fault(int last_node, int node, int pages, int flags);
extern pid_t task_numa_group_id(struct task_struct *p);
extern void set_numabalancing_state(bool enabled);
-extern void task_numa_free(struct task_struct *p);
+extern void task_numa_free(struct task_struct *p, bool final);
extern bool should_numa_migrate_memory(struct task_struct *p, struct page
*page,
int src_nid, int dst_cpu);
#else
@@ -34,7 +34,7 @@ static inline pid_t task_numa_group_id(struct task_struct *p)
static inline void set_numabalancing_state(bool enabled)
{
}
-static inline void task_numa_free(struct task_struct *p)
+static inline void task_numa_free(struct task_struct *p, bool final)
{
}
static inline bool should_numa_migrate_memory(struct task_struct *p,
diff --git a/kernel/fork.c b/kernel/fork.c
index d8ae0f1b4148..2852d0e76ea3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -726,7 +726,7 @@ void __put_task_struct(struct task_struct *tsk)
WARN_ON(tsk == current);
cgroup_free(tsk);
- task_numa_free(tsk);
+ task_numa_free(tsk, true);
security_task_free(tsk);
exit_creds(tsk);
delayacct_tsk_free(tsk);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 036be95a87e9..bc9cfeaac8bd 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1086,6 +1086,21 @@ struct numa_group {
unsigned long faults[0];
};
+/*
+ * For functions that can be called in multiple contexts that permit reading
+ * ->numa_group (see struct task_struct for locking rules).
+ */
+static struct numa_group *deref_task_numa_group(struct task_struct *p)
+{
+ return rcu_dereference_check(p->numa_group, p == current ||
+ (lockdep_is_held(_rq(p)->lock) && !READ_ONCE(p->on_cpu)));
+}
+
+static struct numa_group *deref_curr_numa_group(struct task_struct *p)
+{
+ return rcu_dereference_protected(p->numa_group, p == current);
+}
+
static inline unsigned long group_faults_priv(struct numa_group *ng);
static inline unsigned long group_faults_shared(struct numa_group *ng);
@@ -1129,10 +1144,12 @@ static unsigned int task_scan_start(struct task_struct
*p)
{
unsigned long smin = task_scan_min(p);
unsigned long period = smin;
+ struct numa_group *ng;
/* Scale the maximum scan period with the amount of shared memory. */
- if (p->numa_group) {
- struct numa_group *ng = p->numa_group;
+ rcu_read_lock();
+ ng =