AUDIT: Stop waiting for backlog after audit_panic() happens

We force a rate-limit on auditable events by making them wait for space 
on the backlog queue. However, if auditd really is AWOL then this could 
potentially bring the entire system to a halt, depending on the audit 
rules in effect.

Firstly, make sure the wait time is honoured correctly -- it's the 
maximum time the process should wait, rather than the time to wait 
_each_ time round the loop. We were getting re-woken _each_ time a 
packet was dequeued, and the timeout was being restarted each time.

Secondly, reset the wait time after audit_panic() is called. In general 
this will be reset to zero, to allow progress to be made. If the system
is configured to _actually_ panic on audit_panic() then that will 
already have happened; otherwise we know that audit records are being 
lost anyway. 

These two tunables can't be exposed via AUDIT_GET and AUDIT_SET because 
those aren't particularly well-designed. It probably should have been 
done by sysctls or sysfs anyway -- one for a later patch.

Signed-off-by: David Woodhouse <dwmw2@infradead.org>

1 files changed, 10 insertions, 5 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index 2617d0552400..b683f2b5e866 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -79,6 +79,8 @@ static int	audit_rate_limit;
 
 /* Number of outstanding audit_buffers allowed. */
 static int      audit_backlog_limit = 64;
+static int      audit_backlog_wait_time = 60 * HZ;
+static int      audit_backlog_wait_overflow = 0;
 
 /* The identity of the user shutting down the audit system. */
 uid_t           audit_sig_uid = -1;
@@ -655,6 +657,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, int gfp_mask,
         struct timespec         t;
         unsigned int            serial;
         int reserve;
+        unsigned long timeout_start = jiffies;
 
         if (!audit_initialized)
                 return NULL;
@@ -667,8 +670,9 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, int gfp_mask,
 
         while (audit_backlog_limit
                && skb_queue_len(&audit_skb_queue) > audit_backlog_limit + reserve) {
-                if (gfp_mask & __GFP_WAIT) {
-                        int ret = 1;
+                if (gfp_mask & __GFP_WAIT && audit_backlog_wait_time
+                    && time_before(jiffies, timeout_start + audit_backlog_wait_time)) {
+
                         /* Wait for auditd to drain the queue a little */
                         DECLARE_WAITQUEUE(wait, current);
                         set_current_state(TASK_INTERRUPTIBLE);
@@ -676,12 +680,11 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, int gfp_mask,
 
                         if (audit_backlog_limit &&
                             skb_queue_len(&audit_skb_queue) > audit_backlog_limit)
-                                ret = schedule_timeout(HZ * 60);
+                                schedule_timeout(timeout_start + audit_backlog_wait_time - jiffies);
 
                         __set_current_state(TASK_RUNNING);
                         remove_wait_queue(&audit_backlog_wait, &wait);
-                        if (ret)
-                                continue;
+                        continue;
                 }
                 if (audit_rate_check())
                         printk(KERN_WARNING
@@ -690,6 +693,8 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, int gfp_mask,
                                skb_queue_len(&audit_skb_queue),
                                audit_backlog_limit);
                 audit_log_lost("backlog limit exceeded");
+                audit_backlog_wait_time = audit_backlog_wait_overflow;
+                wake_up(&audit_backlog_wait);
                 return NULL;
         }