Merge branch 'dynamic_sg' into rdma.git for-next

From Maor Gottlieb says:

====================
This series extends __sg_alloc_table_from_pages to allow chaining of new
pages to an already initialized SG table.

This allows for drivers to utilize the optimization of merging contiguous
pages without a need to pre allocate all the pages and hold them in a very
large temporary buffer prior to the call to SG table initialization.

The last patch changes the Infiniband core to use the new API. It removes
duplicate functionality from the code and benefits from the optimization
of allocating dynamic SG table from pages.

In huge pages system of 2MB page size, without this change, the SG table
would contain x512 SG entries.
====================

* branch 'dynamic_sg':
  RDMA/umem: Move to allocate SG table from pages
  lib/scatterlist: Add support in dynamic allocation of SG table from pages
  tools/testing/scatterlist: Show errors in human readable form
  tools/testing/scatterlist: Rejuvenate bit-rotten test

1 files changed, 29 insertions, 6 deletions

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 54b74fabf40c..2facbbd146ec 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3969,13 +3969,18 @@ static int separate_irq_context(struct task_struct *curr,
 static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			     enum lock_usage_bit new_bit)
 {
-	unsigned int new_mask = 1 << new_bit, ret = 1;
+	unsigned int old_mask, new_mask, ret = 1;
 
 	if (new_bit >= LOCK_USAGE_STATES) {
 		DEBUG_LOCKS_WARN_ON(1);
 		return 0;
 	}
 
+	if (new_bit == LOCK_USED && this->read)
+		new_bit = LOCK_USED_READ;
+
+	new_mask = 1 << new_bit;
+
 	/*
 	 * If already set then do not dirty the cacheline,
 	 * nor do any checks:
@@ -3988,13 +3993,22 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 	/*
 	 * Make sure we didn't race:
 	 */
-	if (unlikely(hlock_class(this)->usage_mask & new_mask)) {
-		graph_unlock();
-		return 1;
-	}
+	if (unlikely(hlock_class(this)->usage_mask & new_mask))
+		goto unlock;
 
+	old_mask = hlock_class(this)->usage_mask;
 	hlock_class(this)->usage_mask |= new_mask;
 
+	/*
+	 * Save one usage_traces[] entry and map both LOCK_USED and
+	 * LOCK_USED_READ onto the same entry.
+	 */
+	if (new_bit == LOCK_USED || new_bit == LOCK_USED_READ) {
+		if (old_mask & (LOCKF_USED | LOCKF_USED_READ))
+			goto unlock;
+		new_bit = LOCK_USED;
+	}
+
 	if (!(hlock_class(this)->usage_traces[new_bit] = save_trace()))
 		return 0;
 
@@ -4008,6 +4022,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			return 0;
 	}
 
+unlock:
 	graph_unlock();
 
 	/*
@@ -4942,12 +4957,20 @@ static void verify_lock_unused(struct lockdep_map *lock, struct held_lock *hlock
 {
 #ifdef CONFIG_PROVE_LOCKING
 	struct lock_class *class = look_up_lock_class(lock, subclass);
+	unsigned long mask = LOCKF_USED;
 
 	/* if it doesn't have a class (yet), it certainly hasn't been used yet */
 	if (!class)
 		return;
 
-	if (!(class->usage_mask & LOCK_USED))
+	/*
+	 * READ locks only conflict with USED, such that if we only ever use
+	 * READ locks, there is no deadlock possible -- RCU.
+	 */
+	if (!hlock->read)
+		mask |= LOCKF_USED_READ;
+
+	if (!(class->usage_mask & mask))
 		return;
 
 	hlock->class_idx = class - lock_classes;