1 files changed, 137 insertions, 78 deletions

diff --git a/drivers/infiniband/hw/qib/qib_keys.c b/drivers/infiniband/hw/qib/qib_keys.c
index 4b80eb153d5..3b9afccaaad 100644
--- a/drivers/infiniband/hw/qib/qib_keys.c
+++ b/drivers/infiniband/hw/qib/qib_keys.c
@@ -35,21 +35,41 @@
 
 /**
  * qib_alloc_lkey - allocate an lkey
- * @rkt: lkey table in which to allocate the lkey
  * @mr: memory region that this lkey protects
+ * @dma_region: 0->normal key, 1->restricted DMA key
+ *
+ * Returns 0 if successful, otherwise returns -errno.
+ *
+ * Increments mr reference count as required.
+ *
+ * Sets the lkey field mr for non-dma regions.
  *
- * Returns 1 if successful, otherwise returns 0.
  */
 
-int qib_alloc_lkey(struct qib_lkey_table *rkt, struct qib_mregion *mr)
+int qib_alloc_lkey(struct qib_mregion *mr, int dma_region)
 {
 	unsigned long flags;
 	u32 r;
 	u32 n;
-	int ret;
+	int ret = 0;
+	struct qib_ibdev *dev = to_idev(mr->pd->device);
+	struct qib_lkey_table *rkt = &dev->lk_table;
 
 	spin_lock_irqsave(&rkt->lock, flags);
 
+	/* special case for dma_mr lkey == 0 */
+	if (dma_region) {
+		struct qib_mregion *tmr;
+
+		tmr = rcu_access_pointer(dev->dma_mr);
+		if (!tmr) {
+			qib_get_mr(mr);
+			rcu_assign_pointer(dev->dma_mr, mr);
+			mr->lkey_published = 1;
+		}
+		goto success;
+	}
+
 	/* Find the next available LKEY */
 	r = rkt->next;
 	n = r;
@@ -57,11 +77,8 @@ int qib_alloc_lkey(struct qib_lkey_table *rkt, struct qib_mregion *mr)
 		if (rkt->table[r] == NULL)
 			break;
 		r = (r + 1) & (rkt->max - 1);
-		if (r == n) {
-			spin_unlock_irqrestore(&rkt->lock, flags);
-			ret = 0;
+		if (r == n)
 			goto bail;
-		}
 	}
 	rkt->next = (r + 1) & (rkt->max - 1);
 	/*
@@ -76,57 +93,58 @@ int qib_alloc_lkey(struct qib_lkey_table *rkt, struct qib_mregion *mr)
 		mr->lkey |= 1 << 8;
 		rkt->gen++;
 	}
-	rkt->table[r] = mr;
+	qib_get_mr(mr);
+	rcu_assign_pointer(rkt->table[r], mr);
+	mr->lkey_published = 1;
+success:
 	spin_unlock_irqrestore(&rkt->lock, flags);
-
-	ret = 1;
-
-bail:
+out:
 	return ret;
+bail:
+	spin_unlock_irqrestore(&rkt->lock, flags);
+	ret = -ENOMEM;
+	goto out;
 }
 
 /**
  * qib_free_lkey - free an lkey
- * @rkt: table from which to free the lkey
- * @lkey: lkey id to free
+ * @mr: mr to free from tables
  */
-int qib_free_lkey(struct qib_ibdev *dev, struct qib_mregion *mr)
+void qib_free_lkey(struct qib_mregion *mr)
 {
 	unsigned long flags;
 	u32 lkey = mr->lkey;
 	u32 r;
-	int ret;
+	struct qib_ibdev *dev = to_idev(mr->pd->device);
+	struct qib_lkey_table *rkt = &dev->lk_table;
 
-	spin_lock_irqsave(&dev->lk_table.lock, flags);
-	if (lkey == 0) {
-		if (dev->dma_mr && dev->dma_mr == mr) {
-			ret = atomic_read(&dev->dma_mr->refcount);
-			if (!ret)
-				dev->dma_mr = NULL;
-		} else
-			ret = 0;
-	} else {
+	spin_lock_irqsave(&rkt->lock, flags);
+	if (!mr->lkey_published)
+		goto out;
+	if (lkey == 0)
+		rcu_assign_pointer(dev->dma_mr, NULL);
+	else {
 		r = lkey >> (32 - ib_qib_lkey_table_size);
-		ret = atomic_read(&dev->lk_table.table[r]->refcount);
-		if (!ret)
-			dev->lk_table.table[r] = NULL;
+		rcu_assign_pointer(rkt->table[r], NULL);
 	}
-	spin_unlock_irqrestore(&dev->lk_table.lock, flags);
-
-	if (ret)
-		ret = -EBUSY;
-	return ret;
+	qib_put_mr(mr);
+	mr->lkey_published = 0;
+out:
+	spin_unlock_irqrestore(&rkt->lock, flags);
 }
 
 /**
  * qib_lkey_ok - check IB SGE for validity and initialize
  * @rkt: table containing lkey to check SGE against
+ * @pd: protection domain
  * @isge: outgoing internal SGE
  * @sge: SGE to check
  * @acc: access flags
  *
  * Return 1 if valid and successful, otherwise returns 0.
  *
+ * increments the reference count upon success
+ *
  * Check the IB SGE for validity and initialize our internal version
  * of it.
  */
@@ -136,23 +154,25 @@ int qib_lkey_ok(struct qib_lkey_table *rkt, struct qib_pd *pd,
 	struct qib_mregion *mr;
 	unsigned n, m;
 	size_t off;
-	int ret = 0;
-	unsigned long flags;
 
 	/*
 	 * We use LKEY == zero for kernel virtual addresses
 	 * (see qib_get_dma_mr and qib_dma.c).
 	 */
-	spin_lock_irqsave(&rkt->lock, flags);
+	rcu_read_lock();
 	if (sge->lkey == 0) {
 		struct qib_ibdev *dev = to_idev(pd->ibpd.device);
 
 		if (pd->user)
 			goto bail;
-		if (!dev->dma_mr)
+		mr = rcu_dereference(dev->dma_mr);
+		if (!mr)
+			goto bail;
+		if (unlikely(!atomic_inc_not_zero(&mr->refcount)))
 			goto bail;
-		atomic_inc(&dev->dma_mr->refcount);
-		isge->mr = dev->dma_mr;
+		rcu_read_unlock();
+
+		isge->mr = mr;
 		isge->vaddr = (void *) sge->addr;
 		isge->length = sge->length;
 		isge->sge_length = sge->length;
@@ -160,9 +180,9 @@ int qib_lkey_ok(struct qib_lkey_table *rkt, struct qib_pd *pd,
 		isge->n = 0;
 		goto ok;
 	}
-	mr = rkt->table[(sge->lkey >> (32 - ib_qib_lkey_table_size))];
-	if (unlikely(mr == NULL || mr->lkey != sge->lkey ||
-		     mr->pd != &pd->ibpd))
+	mr = rcu_dereference(
+		rkt->table[(sge->lkey >> (32 - ib_qib_lkey_table_size))]);
+	if (unlikely(!mr || mr->lkey != sge->lkey || mr->pd != &pd->ibpd))
 		goto bail;
 
 	off = sge->addr - mr->user_base;
@@ -170,19 +190,35 @@ int qib_lkey_ok(struct qib_lkey_table *rkt, struct qib_pd *pd,
 		     off + sge->length > mr->length ||
 		     (mr->access_flags & acc) != acc))
 		goto bail;
+	if (unlikely(!atomic_inc_not_zero(&mr->refcount)))
+		goto bail;
+	rcu_read_unlock();
 
 	off += mr->offset;
-	m = 0;
-	n = 0;
-	while (off >= mr->map[m]->segs[n].length) {
-		off -= mr->map[m]->segs[n].length;
-		n++;
-		if (n >= QIB_SEGSZ) {
-			m++;
-			n = 0;
+	if (mr->page_shift) {
+		/*
+		page sizes are uniform power of 2 so no loop is necessary
+		entries_spanned_by_off is the number of times the loop below
+		would have executed.
+		*/
+		size_t entries_spanned_by_off;
+
+		entries_spanned_by_off = off >> mr->page_shift;
+		off -= (entries_spanned_by_off << mr->page_shift);
+		m = entries_spanned_by_off/QIB_SEGSZ;
+		n = entries_spanned_by_off%QIB_SEGSZ;
+	} else {
+		m = 0;
+		n = 0;
+		while (off >= mr->map[m]->segs[n].length) {
+			off -= mr->map[m]->segs[n].length;
+			n++;
+			if (n >= QIB_SEGSZ) {
+				m++;
+				n = 0;
+			}
 		}
 	}
-	atomic_inc(&mr->refcount);
 	isge->mr = mr;
 	isge->vaddr = mr->map[m]->segs[n].vaddr + off;
 	isge->length = mr->map[m]->segs[n].length - off;
@@ -190,22 +226,24 @@ int qib_lkey_ok(struct qib_lkey_table *rkt, struct qib_pd *pd,
 	isge->m = m;
 	isge->n = n;
 ok:
-	ret = 1;
+	return 1;
 bail:
-	spin_unlock_irqrestore(&rkt->lock, flags);
-	return ret;
+	rcu_read_unlock();
+	return 0;
 }
 
 /**
  * qib_rkey_ok - check the IB virtual address, length, and RKEY
- * @dev: infiniband device
- * @ss: SGE state
+ * @qp: qp for validation
+ * @sge: SGE state
  * @len: length of data
  * @vaddr: virtual address to place data
  * @rkey: rkey to check
  * @acc: access flags
  *
  * Return 1 if successful, otherwise 0.
+ *
+ * increments the reference count upon success
  */
 int qib_rkey_ok(struct qib_qp *qp, struct qib_sge *sge,
 		u32 len, u64 vaddr, u32 rkey, int acc)
@@ -214,24 +252,26 @@ int qib_rkey_ok(struct qib_qp *qp, struct qib_sge *sge,
 	struct qib_mregion *mr;
 	unsigned n, m;
 	size_t off;
-	int ret = 0;
-	unsigned long flags;
 
 	/*
 	 * We use RKEY == zero for kernel virtual addresses
 	 * (see qib_get_dma_mr and qib_dma.c).
 	 */
-	spin_lock_irqsave(&rkt->lock, flags);
+	rcu_read_lock();
 	if (rkey == 0) {
 		struct qib_pd *pd = to_ipd(qp->ibqp.pd);
 		struct qib_ibdev *dev = to_idev(pd->ibpd.device);
 
 		if (pd->user)
 			goto bail;
-		if (!dev->dma_mr)
+		mr = rcu_dereference(dev->dma_mr);
+		if (!mr)
+			goto bail;
+		if (unlikely(!atomic_inc_not_zero(&mr->refcount)))
 			goto bail;
-		atomic_inc(&dev->dma_mr->refcount);
-		sge->mr = dev->dma_mr;
+		rcu_read_unlock();
+
+		sge->mr = mr;
 		sge->vaddr = (void *) vaddr;
 		sge->length = len;
 		sge->sge_length = len;
@@ -240,27 +280,44 @@ int qib_rkey_ok(struct qib_qp *qp, struct qib_sge *sge,
 		goto ok;
 	}
 
-	mr = rkt->table[(rkey >> (32 - ib_qib_lkey_table_size))];
-	if (unlikely(mr == NULL || mr->lkey != rkey || qp->ibqp.pd != mr->pd))
+	mr = rcu_dereference(
+		rkt->table[(rkey >> (32 - ib_qib_lkey_table_size))]);
+	if (unlikely(!mr || mr->lkey != rkey || qp->ibqp.pd != mr->pd))
 		goto bail;
 
 	off = vaddr - mr->iova;
 	if (unlikely(vaddr < mr->iova || off + len > mr->length ||
 		     (mr->access_flags & acc) == 0))
 		goto bail;
+	if (unlikely(!atomic_inc_not_zero(&mr->refcount)))
+		goto bail;
+	rcu_read_unlock();
 
 	off += mr->offset;
-	m = 0;
-	n = 0;
-	while (off >= mr->map[m]->segs[n].length) {
-		off -= mr->map[m]->segs[n].length;
-		n++;
-		if (n >= QIB_SEGSZ) {
-			m++;
-			n = 0;
+	if (mr->page_shift) {
+		/*
+		page sizes are uniform power of 2 so no loop is necessary
+		entries_spanned_by_off is the number of times the loop below
+		would have executed.
+		*/
+		size_t entries_spanned_by_off;
+
+		entries_spanned_by_off = off >> mr->page_shift;
+		off -= (entries_spanned_by_off << mr->page_shift);
+		m = entries_spanned_by_off/QIB_SEGSZ;
+		n = entries_spanned_by_off%QIB_SEGSZ;
+	} else {
+		m = 0;
+		n = 0;
+		while (off >= mr->map[m]->segs[n].length) {
+			off -= mr->map[m]->segs[n].length;
+			n++;
+			if (n >= QIB_SEGSZ) {
+				m++;
+				n = 0;
+			}
 		}
 	}
-	atomic_inc(&mr->refcount);
 	sge->mr = mr;
 	sge->vaddr = mr->map[m]->segs[n].vaddr + off;
 	sge->length = mr->map[m]->segs[n].length - off;
@@ -268,10 +325,10 @@ int qib_rkey_ok(struct qib_qp *qp, struct qib_sge *sge,
 	sge->m = m;
 	sge->n = n;
 ok:
-	ret = 1;
+	return 1;
 bail:
-	spin_unlock_irqrestore(&rkt->lock, flags);
-	return ret;
+	rcu_read_unlock();
+	return 0;
 }
 
 /*
@@ -293,7 +350,9 @@ int qib_fast_reg_mr(struct qib_qp *qp, struct ib_send_wr *wr)
 	if (pd->user || rkey == 0)
 		goto bail;
 
-	mr = rkt->table[(rkey >> (32 - ib_qib_lkey_table_size))];
+	mr = rcu_dereference_protected(
+		rkt->table[(rkey >> (32 - ib_qib_lkey_table_size))],
+		lockdep_is_held(&rkt->lock));
 	if (unlikely(mr == NULL || qp->ibqp.pd != mr->pd))
 		goto bail;