[PATCH v2 2/2] ras: close the race condition with timer

[Cong Wang]

cec_timer_fn() is a timer callback which reads ce_arr.array[]
and updates its decay values. Elements could be added to or
removed from this global array in parallel, although the array
itself will not grow or shrink. del_lru_elem_unlocked() uses
FULL_COUNT() as a key to find a right element to remove,
which could be affected by the parallel timer.

Fix this by converting the timer to a delayed work as suggested
by Borislav, to avoid using spinlock.

Fixes: 011d82611172 ("RAS: Add a Corrected Errors Collector")
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Cong Wang <xiyou.wangcong@xxxxxxxxx>
---
 drivers/ras/cec.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c
index a4ff54e50673..5c2040a7389d 100644
--- a/drivers/ras/cec.c
+++ b/drivers/ras/cec.c
@@ -2,6 +2,7 @@
 #include <linux/mm.h>
 #include <linux/gfp.h>
 #include <linux/kernel.h>
+#include <linux/workqueue.h>
 
 #include <asm/mce.h>
 
@@ -131,7 +132,7 @@ static unsigned int count_threshold = COUNT_MASK;
 #define CEC_TIMER_DEFAULT_INTERVAL	24 * 60 * 60	/* 24 hrs */
 #define CEC_TIMER_MIN_INTERVAL		 1 * 60 * 60	/* 1h */
 #define CEC_TIMER_MAX_INTERVAL	   30 *	24 * 60 * 60	/* one month */
-static struct timer_list cec_timer;
+static struct delayed_work cec_work;
 static u64 timer_interval = CEC_TIMER_DEFAULT_INTERVAL;
 
 /*
@@ -160,20 +161,21 @@ static void do_spring_cleaning(struct ce_array *ca)
 /*
  * @interval in seconds
  */
-static void cec_mod_timer(struct timer_list *t, unsigned long interval)
+static void cec_mod_work(unsigned long interval)
 {
 	unsigned long iv;
 
-	iv = interval * HZ + jiffies;
-
-	mod_timer(t, round_jiffies(iv));
+	iv = interval * HZ;
+	mod_delayed_work(system_wq, &cec_work, round_jiffies(iv));
 }
 
-static void cec_timer_fn(struct timer_list *unused)
+static void cec_work_fn(struct work_struct *work)
 {
+	mutex_lock(&ce_mutex);
 	do_spring_cleaning(&ce_arr);
+	mutex_unlock(&ce_mutex);
 
-	cec_mod_timer(&cec_timer, timer_interval);
+	cec_mod_work(timer_interval);
 }
 
 /*
@@ -383,7 +385,7 @@ static int decay_interval_set(void *data, u64 val)
 
 	timer_interval = val;
 
-	cec_mod_timer(&cec_timer, timer_interval);
+	cec_mod_work(timer_interval);
 	return 0;
 }
 DEFINE_DEBUGFS_ATTRIBUTE(decay_interval_ops, u64_get, decay_interval_set, "%lld\n");
@@ -509,8 +511,8 @@ void __init cec_init(void)
 	if (create_debugfs_nodes())
 		return;
 
-	timer_setup(&cec_timer, cec_timer_fn, 0);
-	cec_mod_timer(&cec_timer, CEC_TIMER_DEFAULT_INTERVAL);
+	INIT_DELAYED_WORK(&cec_work, cec_work_fn);
+	schedule_delayed_work(&cec_work, CEC_TIMER_DEFAULT_INTERVAL);
 
 	pr_info("Correctable Errors collector initialized.\n");
 }
-- 
2.20.1