linux-imx
Public
Source
committed c437c3a405f1
+
====================1
2
Percpu rw semaphores2
-
--------------------3
+
====================3
4
4
5
Percpu rw semaphores is a new read-write semaphore design that is5
6
optimized for locking for reading.6
7
7
8
The problem with traditional read-write semaphores is that when multiple8
9
cores take the lock for reading, the cache line containing the semaphore9
10
is bouncing between L1 caches of the cores, causing performance10
11
degradation.11
12
12
13
Locking for reading is very fast, it uses RCU and it avoids any atomic