Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/gi…

…t/dledford/rdma

Pull rdma fixes from Doug Ledford:
 "Most are minor to important fixes.

  There is one performance enhancement that I took on the grounds that
  failing to check if other processes can run before running what's
  intended to be a background, idle-time task is a bug, even though the
  primary effect of the fix is to improve performance (and it was a very
  simple patch)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma:
  IB/mlx5: Postpone remove_keys under knowledge of coming preemption
  IB/mlx4: Use vmalloc for WR buffers when needed
  IB/mlx4: Use correct order of variables in log message
  iser-target: Remove explicit mlx4 work-around
  mlx4: Expose correct max_sge_rd limit
  IB/mad: Require CM send method for everything except ClassPortInfo
  IB/cma: Add a missing rcu_read_unlock()
  IB core: Fix ib_sg_to_pages()
  IB/srp: Fix srp_map_sg_fr()
  IB/srp: Fix indirect data buffer rkey endianness
  IB/srp: Initialize dma_length in srp_map_idb
  IB/srp: Fix possible send queue overflow
  IB/srp: Fix a memory leak
  IB/sa: Put netlink request into the request list before sending
  IB/iser: use sector_div instead of do_div
  IB/core: use RCU for uverbs id lookup
  IB/qib: Minor fixes to qib per SFF 8636
  IB/core: Fix user mode post wr corruption
  IB/qib: Fix qib_mr structure

drivers/infiniband/core/cma.c

@@ -1126,10 +1126,7 @@ static bool validate_ipv4_net_dev(struct net_device *net_dev,
 
 	rcu_read_lock();
 	err = fib_lookup(dev_net(net_dev), &fl4, &res, 0);
-	if (err)
-		return false;
-
-	ret = FIB_RES_DEV(res) == net_dev;
+	ret = err == 0 && FIB_RES_DEV(res) == net_dev;
 	rcu_read_unlock();
 
 	return ret;

drivers/infiniband/core/mad.c

@@ -1811,6 +1811,11 @@ static int validate_mad(const struct ib_mad_hdr *mad_hdr,
 		if (qp_num == 0)
 			valid = 1;
 	} else {
+		/* CM attributes other than ClassPortInfo only use Send method */
+		if ((mad_hdr->mgmt_class == IB_MGMT_CLASS_CM) &&
+		    (mad_hdr->attr_id != IB_MGMT_CLASSPORTINFO_ATTR_ID) &&
+		    (mad_hdr->method != IB_MGMT_METHOD_SEND))
+			goto out;
 		/* Filter GSI packets sent to QP0 */
 		if (qp_num != 0)
 			valid = 1;

drivers/infiniband/core/sa_query.c

@@ -512,7 +512,7 @@ static int ib_nl_get_path_rec_attrs_len(ib_sa_comp_mask comp_mask)
 	return len;
 }
 
-static int ib_nl_send_msg(struct ib_sa_query *query)
+static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask)
 {
 	struct sk_buff *skb = NULL;
 	struct nlmsghdr *nlh;
@@ -526,7 +526,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query)
 	if (len <= 0)
 		return -EMSGSIZE;
 
-	skb = nlmsg_new(len, GFP_KERNEL);
+	skb = nlmsg_new(len, gfp_mask);
 	if (!skb)
 		return -ENOMEM;
 
@@ -544,7 +544,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query)
 	/* Repair the nlmsg header length */
 	nlmsg_end(skb, nlh);
 
-	ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, GFP_KERNEL);
+	ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, gfp_mask);
 	if (!ret)
 		ret = len;
 	else
@@ -553,7 +553,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query)
 	return ret;
 }
 
-static int ib_nl_make_request(struct ib_sa_query *query)
+static int ib_nl_make_request(struct ib_sa_query *query, gfp_t gfp_mask)
 {
 	unsigned long flags;
 	unsigned long delay;
@@ -562,25 +562,27 @@ static int ib_nl_make_request(struct ib_sa_query *query)
 	INIT_LIST_HEAD(&query->list);
 	query->seq = (u32)atomic_inc_return(&ib_nl_sa_request_seq);
 
+	/* Put the request on the list first.*/
 	spin_lock_irqsave(&ib_nl_request_lock, flags);
-	ret = ib_nl_send_msg(query);
-	if (ret <= 0) {
-		ret = -EIO;
-		goto request_out;
-	} else {
-		ret = 0;
-	}
-
 	delay = msecs_to_jiffies(sa_local_svc_timeout_ms);
 	query->timeout = delay + jiffies;
 	list_add_tail(&query->list, &ib_nl_request_list);
 	/* Start the timeout if this is the only request */
 	if (ib_nl_request_list.next == &query->list)
 		queue_delayed_work(ib_nl_wq, &ib_nl_timed_work, delay);
-
-request_out:
 	spin_unlock_irqrestore(&ib_nl_request_lock, flags);
 
+	ret = ib_nl_send_msg(query, gfp_mask);
+	if (ret <= 0) {
+		ret = -EIO;
+		/* Remove the request */
+		spin_lock_irqsave(&ib_nl_request_lock, flags);
+		list_del(&query->list);
+		spin_unlock_irqrestore(&ib_nl_request_lock, flags);
+	} else {
+		ret = 0;
+	}
+
 	return ret;
 }
 
@@ -1108,7 +1110,7 @@ static int send_mad(struct ib_sa_query *query, int timeout_ms, gfp_t gfp_mask)
 
 	if (query->flags & IB_SA_ENABLE_LOCAL_SERVICE) {
 		if (!ibnl_chk_listeners(RDMA_NL_GROUP_LS)) {
-			if (!ib_nl_make_request(query))
+			if (!ib_nl_make_request(query, gfp_mask))
 				return id;
 		}
 		ib_sa_disable_local_svc(query);

drivers/infiniband/core/uverbs_cmd.c

@@ -62,9 +62,11 @@ static struct uverbs_lock_class rule_lock_class = { .name = "RULE-uobj" };
  * The ib_uobject locking scheme is as follows:
  *
  * - ib_uverbs_idr_lock protects the uverbs idrs themselves, so it
- *   needs to be held during all idr operations.  When an object is
+ *   needs to be held during all idr write operations.  When an object is
  *   looked up, a reference must be taken on the object's kref before
- *   dropping this lock.
+ *   dropping this lock.  For read operations, the rcu_read_lock()
+ *   and rcu_write_lock() but similarly the kref reference is grabbed
+ *   before the rcu_read_unlock().
  *
  * - Each object also has an rwsem.  This rwsem must be held for
  *   reading while an operation that uses the object is performed.
@@ -96,7 +98,7 @@ static void init_uobj(struct ib_uobject *uobj, u64 user_handle,
 
 static void release_uobj(struct kref *kref)
 {
-	kfree(container_of(kref, struct ib_uobject, ref));
+	kfree_rcu(container_of(kref, struct ib_uobject, ref), rcu);
 }
 
 static void put_uobj(struct ib_uobject *uobj)
@@ -145,15 +147,15 @@ static struct ib_uobject *__idr_get_uobj(struct idr *idr, int id,
 {
 	struct ib_uobject *uobj;
 
-	spin_lock(&ib_uverbs_idr_lock);
+	rcu_read_lock();
 	uobj = idr_find(idr, id);
 	if (uobj) {
 		if (uobj->context == context)
 			kref_get(&uobj->ref);
 		else
 			uobj = NULL;
 	}
-	spin_unlock(&ib_uverbs_idr_lock);
+	rcu_read_unlock();
 
 	return uobj;
 }
@@ -2446,6 +2448,7 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file,
 	int                             i, sg_ind;
 	int				is_ud;
 	ssize_t                         ret = -EINVAL;
+	size_t                          next_size;
 
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
@@ -2490,7 +2493,8 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file,
 				goto out_put;
 			}
 
-			ud = alloc_wr(sizeof(*ud), user_wr->num_sge);
+			next_size = sizeof(*ud);
+			ud = alloc_wr(next_size, user_wr->num_sge);
 			if (!ud) {
 				ret = -ENOMEM;
 				goto out_put;
@@ -2511,7 +2515,8 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file,
 			   user_wr->opcode == IB_WR_RDMA_READ) {
 			struct ib_rdma_wr *rdma;
 
-			rdma = alloc_wr(sizeof(*rdma), user_wr->num_sge);
+			next_size = sizeof(*rdma);
+			rdma = alloc_wr(next_size, user_wr->num_sge);
 			if (!rdma) {
 				ret = -ENOMEM;
 				goto out_put;
@@ -2525,7 +2530,8 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file,
 			   user_wr->opcode == IB_WR_ATOMIC_FETCH_AND_ADD) {
 			struct ib_atomic_wr *atomic;
 
-			atomic = alloc_wr(sizeof(*atomic), user_wr->num_sge);
+			next_size = sizeof(*atomic);
+			atomic = alloc_wr(next_size, user_wr->num_sge);
 			if (!atomic) {
 				ret = -ENOMEM;
 				goto out_put;
@@ -2540,7 +2546,8 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file,
 		} else if (user_wr->opcode == IB_WR_SEND ||
 			   user_wr->opcode == IB_WR_SEND_WITH_IMM ||
 			   user_wr->opcode == IB_WR_SEND_WITH_INV) {
-			next = alloc_wr(sizeof(*next), user_wr->num_sge);
+			next_size = sizeof(*next);
+			next = alloc_wr(next_size, user_wr->num_sge);
 			if (!next) {
 				ret = -ENOMEM;
 				goto out_put;
@@ -2572,7 +2579,7 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file,
 
 		if (next->num_sge) {
 			next->sg_list = (void *) next +
-				ALIGN(sizeof *next, sizeof (struct ib_sge));
+				ALIGN(next_size, sizeof(struct ib_sge));
 			if (copy_from_user(next->sg_list,
 					   buf + sizeof cmd +
 					   cmd.wr_count * cmd.wqe_size +

drivers/infiniband/core/verbs.c

@@ -1516,7 +1516,7 @@ EXPORT_SYMBOL(ib_map_mr_sg);
  * @sg_nents:      number of entries in sg
  * @set_page:      driver page assignment function pointer
  *
- * Core service helper for drivers to covert the largest
+ * Core service helper for drivers to convert the largest
  * prefix of given sg list to a page vector. The sg list
  * prefix converted is the prefix that meet the requirements
  * of ib_map_mr_sg.
@@ -1533,7 +1533,7 @@ int ib_sg_to_pages(struct ib_mr *mr,
 	u64 last_end_dma_addr = 0, last_page_addr = 0;
 	unsigned int last_page_off = 0;
 	u64 page_mask = ~((u64)mr->page_size - 1);
-	int i;
+	int i, ret;
 
 	mr->iova = sg_dma_address(&sgl[0]);
 	mr->length = 0;
@@ -1544,27 +1544,29 @@ int ib_sg_to_pages(struct ib_mr *mr,
 		u64 end_dma_addr = dma_addr + dma_len;
 		u64 page_addr = dma_addr & page_mask;
 
-		if (i && page_addr != dma_addr) {
-			if (last_end_dma_addr != dma_addr) {
-				/* gap */
-				goto done;
-
-			} else if (last_page_off + dma_len <= mr->page_size) {
-				/* chunk this fragment with the last */
-				mr->length += dma_len;
-				last_end_dma_addr += dma_len;
-				last_page_off += dma_len;
-				continue;
-			} else {
-				/* map starting from the next page */
-				page_addr = last_page_addr + mr->page_size;
-				dma_len -= mr->page_size - last_page_off;
-			}
+		/*
+		 * For the second and later elements, check whether either the
+		 * end of element i-1 or the start of element i is not aligned
+		 * on a page boundary.
+		 */
+		if (i && (last_page_off != 0 || page_addr != dma_addr)) {
+			/* Stop mapping if there is a gap. */
+			if (last_end_dma_addr != dma_addr)
+				break;
+
+			/*
+			 * Coalesce this element with the last. If it is small
+			 * enough just update mr->length. Otherwise start
+			 * mapping from the next page.
+			 */
+			goto next_page;
 		}
 
 		do {
-			if (unlikely(set_page(mr, page_addr)))
-				goto done;
+			ret = set_page(mr, page_addr);
+			if (unlikely(ret < 0))
+				return i ? : ret;
+next_page:
 			page_addr += mr->page_size;
 		} while (page_addr < end_dma_addr);
 
@@ -1574,7 +1576,6 @@ int ib_sg_to_pages(struct ib_mr *mr,
 		last_page_off = end_dma_addr & ~page_mask;
 	}
 
-done:
 	return i;
 }
 EXPORT_SYMBOL(ib_sg_to_pages);

drivers/infiniband/hw/mlx4/main.c

@@ -456,7 +456,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->max_qp_wr	   = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE;
 	props->max_sge		   = min(dev->dev->caps.max_sq_sg,
 					 dev->dev->caps.max_rq_sg);
-	props->max_sge_rd = props->max_sge;
+	props->max_sge_rd	   = MLX4_MAX_SGE_RD;
 	props->max_cq		   = dev->dev->quotas.cq;
 	props->max_cqe		   = dev->dev->caps.max_cqes;
 	props->max_mr		   = dev->dev->quotas.mpt;

drivers/infiniband/hw/mlx4/qp.c

@@ -34,6 +34,7 @@
 #include <linux/log2.h>
 #include <linux/slab.h>
 #include <linux/netdevice.h>
+#include <linux/vmalloc.h>
 
 #include <rdma/ib_cache.h>
 #include <rdma/ib_pack.h>
@@ -795,8 +796,14 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 		if (err)
 			goto err_mtt;
 
-		qp->sq.wrid  = kmalloc(qp->sq.wqe_cnt * sizeof (u64), gfp);
-		qp->rq.wrid  = kmalloc(qp->rq.wqe_cnt * sizeof (u64), gfp);
+		qp->sq.wrid = kmalloc(qp->sq.wqe_cnt * sizeof(u64), gfp);
+		if (!qp->sq.wrid)
+			qp->sq.wrid = __vmalloc(qp->sq.wqe_cnt * sizeof(u64),
+						gfp, PAGE_KERNEL);
+		qp->rq.wrid = kmalloc(qp->rq.wqe_cnt * sizeof(u64), gfp);
+		if (!qp->rq.wrid)
+			qp->rq.wrid = __vmalloc(qp->rq.wqe_cnt * sizeof(u64),
+						gfp, PAGE_KERNEL);
 		if (!qp->sq.wrid || !qp->rq.wrid) {
 			err = -ENOMEM;
 			goto err_wrid;
@@ -886,8 +893,8 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 		if (qp_has_rq(init_attr))
 			mlx4_ib_db_unmap_user(to_mucontext(pd->uobject->context), &qp->db);
 	} else {
-		kfree(qp->sq.wrid);
-		kfree(qp->rq.wrid);
+		kvfree(qp->sq.wrid);
+		kvfree(qp->rq.wrid);
 	}
 
 err_mtt:
@@ -1062,8 +1069,8 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
 					      &qp->db);
 		ib_umem_release(qp->umem);
 	} else {
-		kfree(qp->sq.wrid);
-		kfree(qp->rq.wrid);
+		kvfree(qp->sq.wrid);
+		kvfree(qp->rq.wrid);
 		if (qp->mlx4_ib_qp_type & (MLX4_IB_QPT_PROXY_SMI_OWNER |
 		    MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI))
 			free_proxy_bufs(&dev->ib_dev, qp);

drivers/infiniband/hw/mlx4/srq.c

@@ -34,6 +34,7 @@
 #include <linux/mlx4/qp.h>
 #include <linux/mlx4/srq.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 
 #include "mlx4_ib.h"
 #include "user.h"
@@ -172,8 +173,12 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd,
 
 		srq->wrid = kmalloc(srq->msrq.max * sizeof (u64), GFP_KERNEL);
 		if (!srq->wrid) {
-			err = -ENOMEM;
-			goto err_mtt;
+			srq->wrid = __vmalloc(srq->msrq.max * sizeof(u64),
+					      GFP_KERNEL, PAGE_KERNEL);
+			if (!srq->wrid) {
+				err = -ENOMEM;
+				goto err_mtt;
+			}
 		}
 	}
 
@@ -204,7 +209,7 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd,
 	if (pd->uobject)
 		mlx4_ib_db_unmap_user(to_mucontext(pd->uobject->context), &srq->db);
 	else
-		kfree(srq->wrid);
+		kvfree(srq->wrid);
 
 err_mtt:
 	mlx4_mtt_cleanup(dev->dev, &srq->mtt);

drivers/infiniband/hw/mlx5/mr.c

@@ -381,7 +381,19 @@ static void __cache_work_func(struct mlx5_cache_ent *ent)
 			}
 		}
 	} else if (ent->cur > 2 * ent->limit) {
-		if (!someone_adding(cache) &&
+		/*
+		 * The remove_keys() logic is performed as garbage collection
+		 * task. Such task is intended to be run when no other active
+		 * processes are running.
+		 *
+		 * The need_resched() will return TRUE if there are user tasks
+		 * to be activated in near future.
+		 *
+		 * In such case, we don't execute remove_keys() and postpone
+		 * the garbage collection work to try to run in next cycle,
+		 * in order to free CPU resources to other tasks.
+		 */
+		if (!need_resched() && !someone_adding(cache) &&
 		    time_after(jiffies, cache->last_add + 300 * HZ)) {
 			remove_keys(dev, i, 1);
 			if (ent->cur > ent->limit)