summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJann Horn <jannh@google.com>2019-07-16 17:20:45 +0200
committerIngo Molnar <mingo@kernel.org>2019-07-25 15:37:04 +0200
commit16d51a590a8ce3befb1308e0e7ab77f3b661af33 (patch)
treee147b1ad1061369a9fd8546aa18ef519474d2fc2
parent7b5cf701ea9c395c792e2a7e3b7caf4c68b87721 (diff)
sched/fair: Don't free p->numa_faults with concurrent readers
When going through execve(), zero out the NUMA fault statistics instead of freeing them. During execve, the task is reachable through procfs and the scheduler. A concurrent /proc/*/sched reader can read data from a freed ->numa_faults allocation (confirmed by KASAN) and write it back to userspace. I believe that it would also be possible for a use-after-free read to occur through a race between a NUMA fault and execve(): task_numa_fault() can lead to task_numa_compare(), which invokes task_weight() on the currently running task of a different CPU. Another way to fix this would be to make ->numa_faults RCU-managed or add extra locking, but it seems easier to wipe the NUMA fault statistics on execve. Signed-off-by: Jann Horn <jannh@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will@kernel.org> Fixes: 82727018b0d3 ("sched/numa: Call task_numa_free() from do_execve()") Link: https://lkml.kernel.org/r/20190716152047.14424-1-jannh@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
-rw-r--r--fs/exec.c2
-rw-r--r--include/linux/sched/numa_balancing.h4
-rw-r--r--kernel/fork.c2
-rw-r--r--kernel/sched/fair.c24
4 files changed, 24 insertions, 8 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/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..6adb0e0f5feb 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2353,13 +2353,23 @@ no_join:
return;
}
-void task_numa_free(struct task_struct *p)
+/*
+ * Get rid of NUMA staticstics associated with a task (either current or dead).
+ * If @final is set, the task is dead and has reached refcount zero, so we can
+ * safely free all relevant data structures. Otherwise, there might be
+ * concurrent reads from places like load balancing and procfs, and we should
+ * reset the data back to default state without freeing ->numa_faults.
+ */
+void task_numa_free(struct task_struct *p, bool final)
{
struct numa_group *grp = p->numa_group;
- void *numa_faults = p->numa_faults;
+ unsigned long *numa_faults = p->numa_faults;
unsigned long flags;
int i;
+ if (!numa_faults)
+ return;
+
if (grp) {
spin_lock_irqsave(&grp->lock, flags);
for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
@@ -2372,8 +2382,14 @@ void task_numa_free(struct task_struct *p)
put_numa_group(grp);
}
- p->numa_faults = NULL;
- kfree(numa_faults);
+ if (final) {
+ p->numa_faults = NULL;
+ kfree(numa_faults);
+ } else {
+ p->total_numa_faults = 0;
+ for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
+ numa_faults[i] = 0;
+ }
}
/*