Add support for rw semaphore under PREEMPT_RT_FULL

The main complication from the RT patch set is that the RW semaphore
locks change such that read locks on an rwsem can be taken only by
a single thread.  All other threads are locked out. This single
thread can take a read lock multiple times though. The underlying
implementation changes to a mutex with an additional read_depth
count.

The implementation can be best understood by inspecting the RT
patch.  rwsem_rt.h and rt.c give the best insight into how RT
rwsem works. My implementation for rwsem_tryupgrade is basically
an inversion of rt_downgrade_write found in rt.c. Please see the
comments in the code.

Unfortunately, I have to drop SPLAT rwlock test4 completely as this
test tries to take multiple locks from different threads, which RT
rwsems do not support.  Otherwise SPLAT, zconfig.sh, zpios-sanity.sh
and zfs-tests.sh pass on my Debian-testing VM with the kernel
linux-image-4.8.0-1-rt-amd64.

Tested-by: kernelOfTruth <[email protected]>
Reviewed-by: Brian Behlendorf <[email protected]>
Signed-off-by: Clemens Fruhwirth <[email protected]>
Closes zfsonlinux/zfs#5491
Closes #589
Closes #308

1 files changed, 31 insertions, 1 deletions

diff --git a/module/spl/spl-rwlock.c b/module/spl/spl-rwlock.c
index 77f46f2d6..9e96c4f27 100644
--- a/module/spl/spl-rwlock.c
+++ b/module/spl/spl-rwlock.c
@@ -32,7 +32,37 @@
 
 #define DEBUG_SUBSYSTEM S_RWLOCK
 
-#if defined(CONFIG_RWSEM_GENERIC_SPINLOCK)
+#if defined(CONFIG_PREEMPT_RT_FULL)
+
+#include <linux/rtmutex.h>
+
+static int
+__rwsem_tryupgrade(struct rw_semaphore *rwsem)
+{
+	ASSERT(rt_mutex_owner(&rwsem->lock) == current);
+
+	/*
+	 * Under the realtime patch series, rwsem is implemented as a
+	 * single mutex held by readers and writers alike. However,
+	 * this implementation would prevent a thread from taking a
+	 * read lock twice, as the mutex would already be locked on
+	 * the second attempt. Therefore the implementation allows a
+	 * single thread to take a rwsem as read lock multiple times
+	 * tracking that nesting as read_depth counter.
+	 */
+	if (rwsem->read_depth <= 1) {
+		/*
+		 * In case, the current thread has not taken the lock
+		 * more than once as read lock, we can allow an
+		 * upgrade to a write lock. rwsem_rt.h implements
+		 * write locks as read_depth == 0.
+		 */
+		rwsem->read_depth = 0;
+		return (1);
+	}
+	return (0);
+}
+#elif defined(CONFIG_RWSEM_GENERIC_SPINLOCK)
 static int
 __rwsem_tryupgrade(struct rw_semaphore *rwsem)
 {