| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20190802132302.13537-38-sashal@kernel.org>
Date: Fri, 2 Aug 2019 09:22:58 -0400
From: Sasha Levin <sashal@...nel.org>
To: linux-kernel@...r.kernel.org, stable@...r.kernel.org
Cc: Jann Horn <jannh@...gle.com>,
Peter Zijlstra <peterz@...radead.org>,
Linus Torvalds <torvalds@...ux-foundation.org>,
Petr Mladek <pmladek@...e.com>,
Sergey Senozhatsky <sergey.senozhatsky@...il.com>,
Thomas Gleixner <tglx@...utronix.de>,
Will Deacon <will@...nel.org>, Ingo Molnar <mingo@...nel.org>,
Sasha Levin <sashal@...nel.org>, linux-fsdevel@...r.kernel.org
Subject: [PATCH AUTOSEL 4.19 38/42] sched/fair: Don't free p->numa_faults with concurrent readers
From: Jann Horn <jannh@...gle.com>
[ Upstream commit 16d51a590a8ce3befb1308e0e7ab77f3b661af33 ]
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@...gle.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Petr Mladek <pmladek@...e.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky@...il.com>
Cc: Thomas Gleixner <tglx@...utronix.de>
Cc: Will Deacon <will@...nel.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@...nel.org>
Signed-off-by: Sasha Levin <sashal@...nel.org>
---
fs/exec.c | 2 +-
include/linux/sched/numa_balancing.h | 4 ++--
kernel/fork.c | 2 +-
kernel/sched/fair.c | 24 ++++++++++++++++++++----
4 files changed, 24 insertions(+), 8 deletions(-)
diff --git a/fs/exec.c b/fs/exec.c
index 433b1257694ab..561ea64829ece 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1826,7 +1826,7 @@ 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 e7dd04a84ba89..3988762efe15c 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 69874db3fba83..e76ce81c9c757 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -679,7 +679,7 @@ 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 4a433608ba74a..34b998678b97d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2345,13 +2345,23 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
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++)
@@ -2364,8 +2374,14 @@ 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;
+ }
}
/*
--
2.20.1
Powered by blists - more mailing lists