lockdep: Reintroduce generation count to make BFS faster

We still can apply DaveM's generation count optimization to
BFS, based on the following idea:

 - before doing each BFS, increase the global generation id
   by 1

 - if one node in the graph has been visited, mark it as
   visited by storing the current global generation id into
   the node's dep_gen_id field

 - so we can decide if one node has been visited already, by
   comparing the node's dep_gen_id with the global generation id.

By applying DaveM's generation count optimization to current
implementation of BFS, we gain the following advantages:

 - we save MAX_LOCKDEP_ENTRIES/8 bytes memory;

 - we remove the bitmap_zero(bfs_accessed, MAX_LOCKDEP_ENTRIES);
   in each BFS, which is very time-consuming since
   MAX_LOCKDEP_ENTRIES may be very large.(16384UL)

Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: "David S. Miller" <davem@davemloft.net>
LKML-Reference: <1248274089-6358-1-git-send-email-tom.leiming@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

2 files changed, 7 insertions, 5 deletions

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 47d42eff6124..9ccf0e286b2a 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -58,6 +58,7 @@ struct lock_class {
 
         struct lockdep_subclass_key     *key;
         unsigned int                    subclass;
+        unsigned int                    dep_gen_id;
 
         /*
          * IRQ/softirq usage tracking bits:
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 0bb246e21cd7..2b443b5090a1 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -861,14 +861,15 @@ struct circular_queue {
 };
 
 static struct circular_queue lock_cq;
-static unsigned long bfs_accessed[BITS_TO_LONGS(MAX_LOCKDEP_ENTRIES)];
 
 unsigned int max_bfs_queue_depth;
 
+static unsigned int lockdep_dependency_gen_id;
+
 static inline void __cq_init(struct circular_queue *cq)
 {
         cq->front = cq->rear = 0;
-        bitmap_zero(bfs_accessed, MAX_LOCKDEP_ENTRIES);
+        lockdep_dependency_gen_id++;
 }
 
 static inline int __cq_empty(struct circular_queue *cq)
@@ -914,7 +915,7 @@ static inline void mark_lock_accessed(struct lock_list *lock,
         nr = lock - list_entries;
         WARN_ON(nr >= nr_list_entries);
         lock->parent = parent;
-        set_bit(nr, bfs_accessed);
+        lock->class->dep_gen_id = lockdep_dependency_gen_id;
 }
 
 static inline unsigned long lock_accessed(struct lock_list *lock)
@@ -923,7 +924,7 @@ static inline unsigned long lock_accessed(struct lock_list *lock)
 
         nr = lock - list_entries;
         WARN_ON(nr >= nr_list_entries);
-        return test_bit(nr, bfs_accessed);
+        return lock->class->dep_gen_id == lockdep_dependency_gen_id;
 }
 
 static inline struct lock_list *get_lock_parent(struct lock_list *child)
@@ -3604,7 +3605,7 @@ void __init lockdep_info(void)
                 sizeof(struct lock_chain) * MAX_LOCKDEP_CHAINS +
                 sizeof(struct list_head) * CHAINHASH_SIZE) / 1024
 #ifdef CONFIG_PROVE_LOCKING
-                + sizeof(struct circular_queue) + sizeof(bfs_accessed)
+                + sizeof(struct circular_queue)
 #endif
                 );