From a1fd3e24d8a484b3265a6d485202afe093c058f3 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 17 Dec 2012 16:01:32 -0800 Subject: percpu_rw_semaphore: reimplement to not block the readers unnecessarily Currently the writer does msleep() plus synchronize_sched() 3 times to acquire/release the semaphore, and during this time the readers are blocked completely. Even if the "write" section was not actually started or if it was already finished. With this patch down_write/up_write does synchronize_sched() twice and down_read/up_read are still possible during this time, just they use the slow path. percpu_down_write() first forces the readers to use rw_semaphore and increment the "slow" counter to take the lock for reading, then it takes that rw_semaphore for writing and blocks the readers. Also. With this patch the code relies on the documented behaviour of synchronize_sched(), it doesn't try to pair synchronize_sched() with barrier. Signed-off-by: Oleg Nesterov Reviewed-by: Paul E. McKenney Cc: Linus Torvalds Cc: Mikulas Patocka Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Srikar Dronamraju Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib/Makefile') diff --git a/lib/Makefile b/lib/Makefile index e2152fa7ff4..e959c20efb2 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -9,7 +9,7 @@ endif lib-y := ctype.o string.o vsprintf.o cmdline.o \ rbtree.o radix-tree.o dump_stack.o timerqueue.o\ - idr.o int_sqrt.o extable.o \ + idr.o int_sqrt.o extable.o percpu-rwsem.o \ sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \ proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ -- cgit v1.2.3-70-g09d2