futex: add requeue_pi functionality

PI Futexes and their underlying rt_mutex cannot be left ownerless if
there are pending waiters as this will break the PI boosting logic, so
the standard requeue commands aren't sufficient.  The new commands
properly manage pi futex ownership by ensuring a futex with waiters
has an owner at all times.  This will allow glibc to properly handle
pi mutexes with pthread_condvars.

The approach taken here is to create two new futex op codes:

FUTEX_WAIT_REQUEUE_PI:
Tasks will use this op code to wait on a futex (such as a non-pi waitqueue)
and wake after they have been requeued to a pi futex.  Prior to returning to
userspace, they will acquire this pi futex (and the underlying rt_mutex).

futex_wait_requeue_pi() is the result of a high speed collision between
futex_wait() and futex_lock_pi() (with the first part of futex_lock_pi() being
done by futex_proxy_trylock_atomic() on behalf of the top_waiter).

FUTEX_REQUEUE_PI (and FUTEX_CMP_REQUEUE_PI):
This call must be used to wake tasks waiting with FUTEX_WAIT_REQUEUE_PI,
regardless of how many tasks the caller intends to wake or requeue.
pthread_cond_broadcast() should call this with nr_wake=1 and
nr_requeue=INT_MAX.  pthread_cond_signal() should call this with nr_wake=1 and
nr_requeue=0.  The reason being we need both callers to get the benefit of the
futex_proxy_trylock_atomic() routine.  futex_requeue() also enqueues the
top_waiter on the rt_mutex via rt_mutex_start_proxy_lock().

Signed-off-by: Darren Hart <dvhltc@us.ibm.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

2 files changed, 10 insertions, 1 deletions

diff --git a/include/linux/futex.h b/include/linux/futex.h
index 3bf5bb5a34f..b05519ca9e5 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -23,6 +23,9 @@ union ktime;
 #define FUTEX_TRYLOCK_PI	8
 #define FUTEX_WAIT_BITSET	9
 #define FUTEX_WAKE_BITSET	10
+#define FUTEX_WAIT_REQUEUE_PI	11
+#define FUTEX_REQUEUE_PI	12
+#define FUTEX_CMP_REQUEUE_PI	13
 
 #define FUTEX_PRIVATE_FLAG	128
 #define FUTEX_CLOCK_REALTIME	256
@@ -38,6 +41,11 @@ union ktime;
 #define FUTEX_TRYLOCK_PI_PRIVATE (FUTEX_TRYLOCK_PI | FUTEX_PRIVATE_FLAG)
 #define FUTEX_WAIT_BITSET_PRIVATE	(FUTEX_WAIT_BITS | FUTEX_PRIVATE_FLAG)
 #define FUTEX_WAKE_BITSET_PRIVATE	(FUTEX_WAKE_BITS | FUTEX_PRIVATE_FLAG)
+#define FUTEX_WAIT_REQUEUE_PI_PRIVATE	(FUTEX_WAIT_REQUEUE_PI | \
+					 FUTEX_PRIVATE_FLAG)
+#define FUTEX_REQUEUE_PI_PRIVATE	(FUTEX_REQUEUE_PI | FUTEX_PRIVATE_FLAG)
+#define FUTEX_CMP_REQUEUE_PI_PRIVATE	(FUTEX_CMP_REQUEUE_PI | \
+					 FUTEX_PRIVATE_FLAG)
 
 /*
  * Support for robust futexes: the kernel cleans up held futexes at
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index e6b820f8b56..a8cc4e13434 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -21,13 +21,14 @@ struct restart_block {
 		struct {
 			unsigned long arg0, arg1, arg2, arg3;
 		};
-		/* For futex_wait */
+		/* For futex_wait and futex_wait_requeue_pi */
 		struct {
 			u32 *uaddr;
 			u32 val;
 			u32 flags;
 			u32 bitset;
 			u64 time;
+			u32 *uaddr2;
 		} futex;
 		/* For nanosleep */
 		struct {