Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Qian Cai <cai@gmx.us>
To:     akpm@linux-foundation.org, tglx@linutronix.de
Cc:     longman@redhat.com, yang.shi@linux.alibaba.com, arnd@arndb.de,
        linux-kernel@vger.kernel.org, Qian Cai <cai@gmx.us>
Subject: [PATCH] debugobjects: scale the static pool size
Date:   Tue, 20 Nov 2018 01:42:54 -0500
Message-Id: <20181120064254.1594-1-cai@gmx.us>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

The current value of the early boot static pool size is not big enough
for systems with large number of CPUs with timer or/and workqueue
objects selected. As the results, systems have 60+ CPUs with both timer
and workqueue objects enabled could trigger "ODEBUG: Out of memory.
ODEBUG disabled". Hence, fixed it by computing it according to
CONFIG_NR_CPUS and CONFIG_DEBUG_OBJECTS_* options.

Signed-off-by: Qian Cai <cai@gmx.us>
---
 lib/debugobjects.c | 53 +++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 52 insertions(+), 1 deletion(-)

diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 70935ed91125..372dc34206d5 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -23,7 +23,53 @@
 #define ODEBUG_HASH_BITS	14
 #define ODEBUG_HASH_SIZE	(1 << ODEBUG_HASH_BITS)
 
+/*
+ * Some debug objects are allocated during the early boot. Enabling some
+ * options like timers or workqueue objects may increase the size required
+ * significantly with large number of CPUs. For example,
+ *
+ * No. CPUs x 2 (worker pool) objects:
+ *
+ * start_kernel
+ *   workqueue_init_early
+ *     init_worker_pool
+ *       init_timer_key
+ *         debug_object_init
+ *
+ * No. CPUs objects (CONFIG_HIGH_RES_TIMERS):
+ *
+ * sched_init
+ *   hrtick_rq_init
+ *     hrtimer_init
+ *
+ * CONFIG_DEBUG_OBJECTS_WORK:
+ * No. CPUs x 6 (workqueue) objects:
+ *
+ * workqueue_init_early
+ *   alloc_workqueue
+ *     __alloc_workqueue_key
+ *       alloc_and_link_pwqs
+ *         init_pwq
+ *
+ * Also, plus No. CPUs objects:
+ *
+ * perf_event_init
+ *    __init_srcu_struct
+ *      init_srcu_struct_fields
+ *        init_srcu_struct_nodes
+ *          __init_work
+ *
+ * Increase the number a bit more in case the implmentatins are changed in
+ * the future.
+ */
+#if defined(CONFIG_NR_CPUS) && defined(CONFIG_DEBUG_OBJECTS_TIMERS) && \
+!defined(CONFIG_DEBUG_OBJECTS_WORK)
+#define ODEBUG_POOL_SIZE	(CONFIG_NR_CPUS * 10)
+#elif defined(CONFIG_NR_CPUS) && defined(CONFIG_DEBUG_OBJECTS_WORK)
+#define ODEBUG_POOL_SIZE	(CONFIG_NR_CPUS * 30)
+#else
 #define ODEBUG_POOL_SIZE	1024
+#endif /* CONFIG_NR_CPUS */
 #define ODEBUG_POOL_MIN_LEVEL	256
 
 #define ODEBUG_CHUNK_SHIFT	PAGE_SHIFT
@@ -58,8 +104,13 @@ static int			debug_objects_fixups __read_mostly;
 static int			debug_objects_warnings __read_mostly;
 static int			debug_objects_enabled __read_mostly
 				= CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT;
+/*
+ * This is only used after replaced static objects, so no need to scale it
+ * to use the early boot static pool size and it has already been scaled
+ * according to actual No. CPUs in the box within debug_objects_mem_init().
+ */
 static int			debug_objects_pool_size __read_mostly
-				= ODEBUG_POOL_SIZE;
+				= 1024;
 static int			debug_objects_pool_min_level __read_mostly
 				= ODEBUG_POOL_MIN_LEVEL;
 static struct debug_obj_descr	*descr_test  __read_mostly;
-- 
2.17.2 (Apple Git-113)