Merge rsync://rsync.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

8 files changed, 84 insertions, 47 deletions

diff --git a/drivers/infiniband/hw/mthca/mthca_allocator.c b/drivers/infiniband/hw/mthca/mthca_allocator.c
index 9ba3211cef7c..f930e55b58fc 100644
--- a/drivers/infiniband/hw/mthca/mthca_allocator.c
+++ b/drivers/infiniband/hw/mthca/mthca_allocator.c
@@ -41,9 +41,11 @@
 /* Trivial bitmap-based allocator */
 u32 mthca_alloc(struct mthca_alloc *alloc)
 {
+	unsigned long flags;
 	u32 obj;
 
-	spin_lock(&alloc->lock);
+	spin_lock_irqsave(&alloc->lock, flags);
+
 	obj = find_next_zero_bit(alloc->table, alloc->max, alloc->last);
 	if (obj >= alloc->max) {
 		alloc->top = (alloc->top + alloc->max) & alloc->mask;
@@ -56,19 +58,24 @@ u32 mthca_alloc(struct mthca_alloc *alloc)
 	} else
 		obj = -1;
 
-	spin_unlock(&alloc->lock);
+	spin_unlock_irqrestore(&alloc->lock, flags);
 
 	return obj;
 }
 
 void mthca_free(struct mthca_alloc *alloc, u32 obj)
 {
+	unsigned long flags;
+
 	obj &= alloc->max - 1;
-	spin_lock(&alloc->lock);
+
+	spin_lock_irqsave(&alloc->lock, flags);
+
 	clear_bit(obj, alloc->table);
 	alloc->last = min(alloc->last, obj);
 	alloc->top = (alloc->top + alloc->max) & alloc->mask;
-	spin_unlock(&alloc->lock);
+
+	spin_unlock_irqrestore(&alloc->lock, flags);
 }
 
 int mthca_alloc_init(struct mthca_alloc *alloc, u32 num, u32 mask,
@@ -108,14 +115,15 @@ void mthca_alloc_cleanup(struct mthca_alloc *alloc)
  * serialize access to the array.
  */
 
+#define MTHCA_ARRAY_MASK (PAGE_SIZE / sizeof (void *) - 1)
+
 void *mthca_array_get(struct mthca_array *array, int index)
 {
 	int p = (index * sizeof (void *)) >> PAGE_SHIFT;
 
-	if (array->page_list[p].page) {
-		int i = index & (PAGE_SIZE / sizeof (void *) - 1);
-		return array->page_list[p].page[i];
-	} else
+	if (array->page_list[p].page)
+		return array->page_list[p].page[index & MTHCA_ARRAY_MASK];
+	else
 		return NULL;
 }
 
@@ -130,8 +138,7 @@ int mthca_array_set(struct mthca_array *array, int index, void *value)
 	if (!array->page_list[p].page)
 		return -ENOMEM;
 
-	array->page_list[p].page[index & (PAGE_SIZE / sizeof (void *) - 1)] =
-		value;
+	array->page_list[p].page[index & MTHCA_ARRAY_MASK] = value;
 	++array->page_list[p].used;
 
 	return 0;
@@ -144,7 +151,8 @@ void mthca_array_clear(struct mthca_array *array, int index)
 	if (--array->page_list[p].used == 0) {
 		free_page((unsigned long) array->page_list[p].page);
 		array->page_list[p].page = NULL;
-	}
+	} else
+		array->page_list[p].page[index & MTHCA_ARRAY_MASK] = NULL;
 
 	if (array->page_list[p].used < 0)
 		pr_debug("Array %p index %d page %d with ref count %d < 0\n",
diff --git a/drivers/infiniband/hw/mthca/mthca_av.c b/drivers/infiniband/hw/mthca/mthca_av.c
index b12aa03be251..e215041b2db9 100644
--- a/drivers/infiniband/hw/mthca/mthca_av.c
+++ b/drivers/infiniband/hw/mthca/mthca_av.c
@@ -303,9 +303,10 @@ int mthca_ah_query(struct ib_ah *ibah, struct ib_ah_attr *attr)
 	memset(attr, 0, sizeof *attr);
 	attr->dlid          = be16_to_cpu(ah->av->dlid);
 	attr->sl            = be32_to_cpu(ah->av->sl_tclass_flowlabel) >> 28;
-	attr->static_rate   = ah->av->msg_sr & 0x7;
-	attr->src_path_bits = ah->av->g_slid & 0x7F;
 	attr->port_num      = be32_to_cpu(ah->av->port_pd) >> 24;
+	attr->static_rate   = mthca_rate_to_ib(dev, ah->av->msg_sr & 0x7,
+					       attr->port_num);
+	attr->src_path_bits = ah->av->g_slid & 0x7F;
 	attr->ah_flags      = mthca_ah_grh_present(ah) ? IB_AH_GRH : 0;
 
 	if (attr->ah_flags) {
diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c
index d0f7731802c9..deabc14b4ea4 100644
--- a/drivers/infiniband/hw/mthca/mthca_cmd.c
+++ b/drivers/infiniband/hw/mthca/mthca_cmd.c
@@ -778,11 +778,12 @@ int mthca_QUERY_FW(struct mthca_dev *dev, u8 *status)
 		((dev->fw_ver & 0xffff0000ull) >> 16) |
 		((dev->fw_ver & 0x0000ffffull) << 16);
 
+	MTHCA_GET(lg, outbox, QUERY_FW_MAX_CMD_OFFSET);
+	dev->cmd.max_cmds = 1 << lg;
+
 	mthca_dbg(dev, "FW version %012llx, max commands %d\n",
 		  (unsigned long long) dev->fw_ver, dev->cmd.max_cmds);
 
-	MTHCA_GET(lg, outbox, QUERY_FW_MAX_CMD_OFFSET);
-	dev->cmd.max_cmds = 1 << lg;
 	MTHCA_GET(dev->catas_err.addr, outbox, QUERY_FW_ERR_START_OFFSET);
 	MTHCA_GET(dev->catas_err.size, outbox, QUERY_FW_ERR_SIZE_OFFSET);
 
diff --git a/drivers/infiniband/hw/mthca/mthca_main.c b/drivers/infiniband/hw/mthca/mthca_main.c
index 557cde3a4563..7b82c1907f04 100644
--- a/drivers/infiniband/hw/mthca/mthca_main.c
+++ b/drivers/infiniband/hw/mthca/mthca_main.c
@@ -967,12 +967,12 @@ static struct {
 } mthca_hca_table[] = {
 	[TAVOR]        = { .latest_fw = MTHCA_FW_VER(3, 4, 0),
 			   .flags     = 0 },
-	[ARBEL_COMPAT] = { .latest_fw = MTHCA_FW_VER(4, 7, 400),
+	[ARBEL_COMPAT] = { .latest_fw = MTHCA_FW_VER(4, 7, 600),
 			   .flags     = MTHCA_FLAG_PCIE },
-	[ARBEL_NATIVE] = { .latest_fw = MTHCA_FW_VER(5, 1, 0),
+	[ARBEL_NATIVE] = { .latest_fw = MTHCA_FW_VER(5, 1, 400),
 			   .flags     = MTHCA_FLAG_MEMFREE |
 					MTHCA_FLAG_PCIE },
-	[SINAI]        = { .latest_fw = MTHCA_FW_VER(1, 0, 800),
+	[SINAI]        = { .latest_fw = MTHCA_FW_VER(1, 1, 0),
 			   .flags     = MTHCA_FLAG_MEMFREE |
 					MTHCA_FLAG_PCIE    |
 					MTHCA_FLAG_SINAI_OPT }
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index 230ae21db8fd..265b1d1c4a62 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -1287,11 +1287,7 @@ int mthca_register_device(struct mthca_dev *dev)
 		(1ull << IB_USER_VERBS_CMD_MODIFY_QP)		|
 		(1ull << IB_USER_VERBS_CMD_DESTROY_QP)		|
 		(1ull << IB_USER_VERBS_CMD_ATTACH_MCAST)	|
-		(1ull << IB_USER_VERBS_CMD_DETACH_MCAST)	|
-		(1ull << IB_USER_VERBS_CMD_CREATE_SRQ)		|
-		(1ull << IB_USER_VERBS_CMD_MODIFY_SRQ)		|
-		(1ull << IB_USER_VERBS_CMD_QUERY_SRQ)		|
-		(1ull << IB_USER_VERBS_CMD_DESTROY_SRQ);
+		(1ull << IB_USER_VERBS_CMD_DETACH_MCAST);
 	dev->ib_dev.node_type            = IB_NODE_CA;
 	dev->ib_dev.phys_port_cnt        = dev->limits.num_ports;
 	dev->ib_dev.dma_device           = &dev->pdev->dev;
@@ -1316,6 +1312,11 @@ int mthca_register_device(struct mthca_dev *dev)
 		dev->ib_dev.modify_srq           = mthca_modify_srq;
 		dev->ib_dev.query_srq            = mthca_query_srq;
 		dev->ib_dev.destroy_srq          = mthca_destroy_srq;
+		dev->ib_dev.uverbs_cmd_mask	|=
+			(1ull << IB_USER_VERBS_CMD_CREATE_SRQ)		|
+			(1ull << IB_USER_VERBS_CMD_MODIFY_SRQ)		|
+			(1ull << IB_USER_VERBS_CMD_QUERY_SRQ)		|
+			(1ull << IB_USER_VERBS_CMD_DESTROY_SRQ);
 
 		if (mthca_is_memfree(dev))
 			dev->ib_dev.post_srq_recv = mthca_arbel_post_srq_recv;
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.h b/drivers/infiniband/hw/mthca/mthca_provider.h
index 8de2887ba15c..9a5bece3fa5c 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.h
+++ b/drivers/infiniband/hw/mthca/mthca_provider.h
@@ -136,8 +136,8 @@ struct mthca_ah {
  * We have one global lock that protects dev->cq/qp_table.  Each
  * struct mthca_cq/qp also has its own lock.  An individual qp lock
  * may be taken inside of an individual cq lock.  Both cqs attached to
- * a qp may be locked, with the send cq locked first.  No other
- * nesting should be done.
+ * a qp may be locked, with the cq with the lower cqn locked first.
+ * No other nesting should be done.
  *
  * Each struct mthca_cq/qp also has an ref count, protected by the
  * corresponding table lock.  The pointer from the cq/qp_table to the
diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c
index 490fc783bb0c..2e8f6f36e0a5 100644
--- a/drivers/infiniband/hw/mthca/mthca_qp.c
+++ b/drivers/infiniband/hw/mthca/mthca_qp.c
@@ -99,6 +99,10 @@ enum {
 	MTHCA_QP_BIT_RSC = 1 <<  3
 };
 
+enum {
+	MTHCA_SEND_DOORBELL_FENCE = 1 << 5
+};
+
 struct mthca_qp_path {
 	__be32 port_pkey;
 	u8     rnr_retry;
@@ -222,9 +226,8 @@ static void *get_send_wqe(struct mthca_qp *qp, int n)
 			 (PAGE_SIZE - 1));
 }
 
-static void mthca_wq_init(struct mthca_wq *wq)
+static void mthca_wq_reset(struct mthca_wq *wq)
 {
-	/* mthca_alloc_qp_common() initializes the locks */
 	wq->next_ind  = 0;
 	wq->last_comp = wq->max - 1;
 	wq->head      = 0;
@@ -845,10 +848,10 @@ int mthca_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask)
 			mthca_cq_clean(dev, to_mcq(qp->ibqp.recv_cq), qp->qpn,
 				       qp->ibqp.srq ? to_msrq(qp->ibqp.srq) : NULL);
 
-		mthca_wq_init(&qp->sq);
+		mthca_wq_reset(&qp->sq);
 		qp->sq.last = get_send_wqe(qp, qp->sq.max - 1);
 
-		mthca_wq_init(&qp->rq);
+		mthca_wq_reset(&qp->rq);
 		qp->rq.last = get_recv_wqe(qp, qp->rq.max - 1);
 
 		if (mthca_is_memfree(dev)) {
@@ -1112,9 +1115,9 @@ static int mthca_alloc_qp_common(struct mthca_dev *dev,
 	qp->atomic_rd_en = 0;
 	qp->resp_depth   = 0;
 	qp->sq_policy    = send_policy;
-	mthca_wq_init(&qp->sq);
-	mthca_wq_init(&qp->rq);
-	/* these are initialized separately so lockdep can tell them apart */
+	mthca_wq_reset(&qp->sq);
+	mthca_wq_reset(&qp->rq);
+
 	spin_lock_init(&qp->sq.lock);
 	spin_lock_init(&qp->rq.lock);
 
@@ -1260,6 +1263,32 @@ int mthca_alloc_qp(struct mthca_dev *dev,
 	return 0;
 }
 
+static void mthca_lock_cqs(struct mthca_cq *send_cq, struct mthca_cq *recv_cq)
+{
+	if (send_cq == recv_cq)
+		spin_lock_irq(&send_cq->lock);
+	else if (send_cq->cqn < recv_cq->cqn) {
+		spin_lock_irq(&send_cq->lock);
+		spin_lock_nested(&recv_cq->lock, SINGLE_DEPTH_NESTING);
+	} else {
+		spin_lock_irq(&recv_cq->lock);
+		spin_lock_nested(&send_cq->lock, SINGLE_DEPTH_NESTING);
+	}
+}
+
+static void mthca_unlock_cqs(struct mthca_cq *send_cq, struct mthca_cq *recv_cq)
+{
+	if (send_cq == recv_cq)
+		spin_unlock_irq(&send_cq->lock);
+	else if (send_cq->cqn < recv_cq->cqn) {
+		spin_unlock(&recv_cq->lock);
+		spin_unlock_irq(&send_cq->lock);
+	} else {
+		spin_unlock(&send_cq->lock);
+		spin_unlock_irq(&recv_cq->lock);
+	}
+}
+
 int mthca_alloc_sqp(struct mthca_dev *dev,
 		    struct mthca_pd *pd,
 		    struct mthca_cq *send_cq,
@@ -1312,17 +1341,13 @@ int mthca_alloc_sqp(struct mthca_dev *dev,
 	 * Lock CQs here, so that CQ polling code can do QP lookup
 	 * without taking a lock.
 	 */
-	spin_lock_irq(&send_cq->lock);
-	if (send_cq != recv_cq)
-		spin_lock(&recv_cq->lock);
+	mthca_lock_cqs(send_cq, recv_cq);
 
 	spin_lock(&dev->qp_table.lock);
 	mthca_array_clear(&dev->qp_table.qp, mqpn);
 	spin_unlock(&dev->qp_table.lock);
 
-	if (send_cq != recv_cq)
-		spin_unlock(&recv_cq->lock);
-	spin_unlock_irq(&send_cq->lock);
+	mthca_unlock_cqs(send_cq, recv_cq);
 
  err_out:
 	dma_free_coherent(&dev->pdev->dev, sqp->header_buf_size,
@@ -1356,9 +1381,7 @@ void mthca_free_qp(struct mthca_dev *dev,
 	 * Lock CQs here, so that CQ polling code can do QP lookup
 	 * without taking a lock.
 	 */
-	spin_lock_irq(&send_cq->lock);
-	if (send_cq != recv_cq)
-		spin_lock(&recv_cq->lock);
+	mthca_lock_cqs(send_cq, recv_cq);
 
 	spin_lock(&dev->qp_table.lock);
 	mthca_array_clear(&dev->qp_table.qp,
@@ -1366,9 +1389,7 @@ void mthca_free_qp(struct mthca_dev *dev,
 	--qp->refcount;
 	spin_unlock(&dev->qp_table.lock);
 
-	if (send_cq != recv_cq)
-		spin_unlock(&recv_cq->lock);
-	spin_unlock_irq(&send_cq->lock);
+	mthca_unlock_cqs(send_cq, recv_cq);
 
 	wait_event(qp->wait, !get_qp_refcount(dev, qp));
 
@@ -1503,7 +1524,7 @@ int mthca_tavor_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 	int i;
 	int size;
 	int size0 = 0;
-	u32 f0 = 0;
+	u32 f0;
 	int ind;
 	u8 op0 = 0;
 
@@ -1687,6 +1708,8 @@ int mthca_tavor_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		if (!size0) {
 			size0 = size;
 			op0   = mthca_opcode[wr->opcode];
+			f0    = wr->send_flags & IB_SEND_FENCE ?
+				MTHCA_SEND_DOORBELL_FENCE : 0;
 		}
 
 		++ind;
@@ -1844,7 +1867,7 @@ int mthca_arbel_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 	int i;
 	int size;
 	int size0 = 0;
-	u32 f0 = 0;
+	u32 f0;
 	int ind;
 	u8 op0 = 0;
 
@@ -2052,6 +2075,8 @@ int mthca_arbel_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		if (!size0) {
 			size0 = size;
 			op0   = mthca_opcode[wr->opcode];
+			f0    = wr->send_flags & IB_SEND_FENCE ?
+				MTHCA_SEND_DOORBELL_FENCE : 0;
 		}
 
 		++ind;
diff --git a/drivers/infiniband/hw/mthca/mthca_srq.c b/drivers/infiniband/hw/mthca/mthca_srq.c
index fab417c5cf43..b60a9d79ae54 100644
--- a/drivers/infiniband/hw/mthca/mthca_srq.c
+++ b/drivers/infiniband/hw/mthca/mthca_srq.c
@@ -370,7 +370,8 @@ int mthca_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
 		return -EINVAL;
 
 	if (attr_mask & IB_SRQ_LIMIT) {
-		if (attr->srq_limit > srq->max)
+		u32 max_wr = mthca_is_memfree(dev) ? srq->max - 1 : srq->max;
+		if (attr->srq_limit > max_wr)
 			return -EINVAL;
 
 		mutex_lock(&srq->mutex);