Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband

Pull infiniband updates from Roland Dreier:
 "Main batch of InfiniBand/RDMA changes for 3.14:
   - Flow steering for InfiniBand UD traffic
   - IP-based addressing for IBoE aka RoCE
   - Pass SRP submaintainership from Dave to Bart
   - SRP transport fixes from Bart
   - Add the new Cisco usNIC low-level device driver
   - Various other fixes"

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (75 commits)
  IB/mlx5: Verify reserved fields are cleared
  IB/mlx5: Remove old field for create mkey mailbox
  IB/mlx5: Abort driver cleanup if teardown hca fails
  IB/mlx5: Allow creation of QPs with zero-length work queues
  mlx5_core: Fix PowerPC support
  mlx5_core: Improve debugfs readability
  IB/mlx5: Add support for resize CQ
  IB/mlx5: Implement modify CQ
  IB/mlx5: Make sure doorbell record is visible before doorbell
  mlx5_core: Use mlx5 core style warning
  IB/mlx5: Clear out struct before create QP command
  mlx5_core: Fix out arg size in access_register command
  RDMA/nes: Slight optimization of Ethernet address compare
  IB/qib: Fix QP check when looping back to/from QP1
  RDMA/cxgb4: Fix gcc warning on 32-bit arch
  IB/usnic: Remove unused includes of <linux/version.h>
  RDMA/amso1100: Add check if cache memory was allocated before freeing it
  IPoIB: Report operstate consistently when brought up without a link
  IB/core: Fix unused variable warning
  RDMA/cma: Handle global/non-linklocal IPv6 addresses in cma_check_linklocal()
  ...

6 files changed, 399 insertions, 65 deletions

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index b7262742974..b1705ce6eb8 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -73,14 +73,24 @@ static void *get_cqe(struct mlx5_ib_cq *cq, int n)
 	return get_cqe_from_buf(&cq->buf, n, cq->mcq.cqe_sz);
 }
 
+static u8 sw_ownership_bit(int n, int nent)
+{
+	return (n & nent) ? 1 : 0;
+}
+
 static void *get_sw_cqe(struct mlx5_ib_cq *cq, int n)
 {
 	void *cqe = get_cqe(cq, n & cq->ibcq.cqe);
 	struct mlx5_cqe64 *cqe64;
 
 	cqe64 = (cq->mcq.cqe_sz == 64) ? cqe : cqe + 64;
-	return ((cqe64->op_own & MLX5_CQE_OWNER_MASK) ^
-		!!(n & (cq->ibcq.cqe + 1))) ? NULL : cqe;
+
+	if (likely((cqe64->op_own) >> 4 != MLX5_CQE_INVALID) &&
+	    !((cqe64->op_own & MLX5_CQE_OWNER_MASK) ^ !!(n & (cq->ibcq.cqe + 1)))) {
+		return cqe;
+	} else {
+		return NULL;
+	}
 }
 
 static void *next_cqe_sw(struct mlx5_ib_cq *cq)
@@ -351,6 +361,11 @@ static void handle_atomics(struct mlx5_ib_qp *qp, struct mlx5_cqe64 *cqe64,
 	qp->sq.last_poll = tail;
 }
 
+static void free_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf)
+{
+	mlx5_buf_free(&dev->mdev, &buf->buf);
+}
+
 static int mlx5_poll_one(struct mlx5_ib_cq *cq,
 			 struct mlx5_ib_qp **cur_qp,
 			 struct ib_wc *wc)
@@ -366,6 +381,7 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq,
 	void *cqe;
 	int idx;
 
+repoll:
 	cqe = next_cqe_sw(cq);
 	if (!cqe)
 		return -EAGAIN;
@@ -379,7 +395,18 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq,
 	 */
 	rmb();
 
-	/* TBD: resize CQ */
+	opcode = cqe64->op_own >> 4;
+	if (unlikely(opcode == MLX5_CQE_RESIZE_CQ)) {
+		if (likely(cq->resize_buf)) {
+			free_cq_buf(dev, &cq->buf);
+			cq->buf = *cq->resize_buf;
+			kfree(cq->resize_buf);
+			cq->resize_buf = NULL;
+			goto repoll;
+		} else {
+			mlx5_ib_warn(dev, "unexpected resize cqe\n");
+		}
+	}
 
 	qpn = ntohl(cqe64->sop_drop_qpn) & 0xffffff;
 	if (!*cur_qp || (qpn != (*cur_qp)->ibqp.qp_num)) {
@@ -398,7 +425,6 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq,
 	}
 
 	wc->qp  = &(*cur_qp)->ibqp;
-	opcode = cqe64->op_own >> 4;
 	switch (opcode) {
 	case MLX5_CQE_REQ:
 		wq = &(*cur_qp)->sq;
@@ -503,15 +529,11 @@ static int alloc_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf,
 		return err;
 
 	buf->cqe_size = cqe_size;
+	buf->nent = nent;
 
 	return 0;
 }
 
-static void free_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf)
-{
-	mlx5_buf_free(&dev->mdev, &buf->buf);
-}
-
 static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 			  struct ib_ucontext *context, struct mlx5_ib_cq *cq,
 			  int entries, struct mlx5_create_cq_mbox_in **cqb,
@@ -576,16 +598,16 @@ static void destroy_cq_user(struct mlx5_ib_cq *cq, struct ib_ucontext *context)
 	ib_umem_release(cq->buf.umem);
 }
 
-static void init_cq_buf(struct mlx5_ib_cq *cq, int nent)
+static void init_cq_buf(struct mlx5_ib_cq *cq, struct mlx5_ib_cq_buf *buf)
 {
 	int i;
 	void *cqe;
 	struct mlx5_cqe64 *cqe64;
 
-	for (i = 0; i < nent; i++) {
-		cqe = get_cqe(cq, i);
-		cqe64 = (cq->buf.cqe_size == 64) ? cqe : cqe + 64;
-		cqe64->op_own = 0xf1;
+	for (i = 0; i < buf->nent; i++) {
+		cqe = get_cqe_from_buf(buf, i, buf->cqe_size);
+		cqe64 = buf->cqe_size == 64 ? cqe : cqe + 64;
+		cqe64->op_own = MLX5_CQE_INVALID << 4;
 	}
 }
 
@@ -610,7 +632,7 @@ static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
 	if (err)
 		goto err_db;
 
-	init_cq_buf(cq, entries);
+	init_cq_buf(cq, &cq->buf);
 
 	*inlen = sizeof(**cqb) + sizeof(*(*cqb)->pas) * cq->buf.buf.npages;
 	*cqb = mlx5_vzalloc(*inlen);
@@ -818,12 +840,266 @@ void mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq)
 
 int mlx5_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period)
 {
-	return -ENOSYS;
+	struct mlx5_modify_cq_mbox_in *in;
+	struct mlx5_ib_dev *dev = to_mdev(cq->device);
+	struct mlx5_ib_cq *mcq = to_mcq(cq);
+	int err;
+	u32 fsel;
+
+	if (!(dev->mdev.caps.flags & MLX5_DEV_CAP_FLAG_CQ_MODER))
+		return -ENOSYS;
+
+	in = kzalloc(sizeof(*in), GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	in->cqn = cpu_to_be32(mcq->mcq.cqn);
+	fsel = (MLX5_CQ_MODIFY_PERIOD | MLX5_CQ_MODIFY_COUNT);
+	in->ctx.cq_period = cpu_to_be16(cq_period);
+	in->ctx.cq_max_count = cpu_to_be16(cq_count);
+	in->field_select = cpu_to_be32(fsel);
+	err = mlx5_core_modify_cq(&dev->mdev, &mcq->mcq, in, sizeof(*in));
+	kfree(in);
+
+	if (err)
+		mlx5_ib_warn(dev, "modify cq 0x%x failed\n", mcq->mcq.cqn);
+
+	return err;
+}
+
+static int resize_user(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
+		       int entries, struct ib_udata *udata, int *npas,
+		       int *page_shift, int *cqe_size)
+{
+	struct mlx5_ib_resize_cq ucmd;
+	struct ib_umem *umem;
+	int err;
+	int npages;
+	struct ib_ucontext *context = cq->buf.umem->context;
+
+	err = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd));
+	if (err)
+		return err;
+
+	if (ucmd.reserved0 || ucmd.reserved1)
+		return -EINVAL;
+
+	umem = ib_umem_get(context, ucmd.buf_addr, entries * ucmd.cqe_size,
+			   IB_ACCESS_LOCAL_WRITE, 1);
+	if (IS_ERR(umem)) {
+		err = PTR_ERR(umem);
+		return err;
+	}
+
+	mlx5_ib_cont_pages(umem, ucmd.buf_addr, &npages, page_shift,
+			   npas, NULL);
+
+	cq->resize_umem = umem;
+	*cqe_size = ucmd.cqe_size;
+
+	return 0;
+}
+
+static void un_resize_user(struct mlx5_ib_cq *cq)
+{
+	ib_umem_release(cq->resize_umem);
+}
+
+static int resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
+			 int entries, int cqe_size)
+{
+	int err;
+
+	cq->resize_buf = kzalloc(sizeof(*cq->resize_buf), GFP_KERNEL);
+	if (!cq->resize_buf)
+		return -ENOMEM;
+
+	err = alloc_cq_buf(dev, cq->resize_buf, entries, cqe_size);
+	if (err)
+		goto ex;
+
+	init_cq_buf(cq, cq->resize_buf);
+
+	return 0;
+
+ex:
+	kfree(cq->resize_buf);
+	return err;
+}
+
+static void un_resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq)
+{
+	free_cq_buf(dev, cq->resize_buf);
+	cq->resize_buf = NULL;
+}
+
+static int copy_resize_cqes(struct mlx5_ib_cq *cq)
+{
+	struct mlx5_ib_dev *dev = to_mdev(cq->ibcq.device);
+	struct mlx5_cqe64 *scqe64;
+	struct mlx5_cqe64 *dcqe64;
+	void *start_cqe;
+	void *scqe;
+	void *dcqe;
+	int ssize;
+	int dsize;
+	int i;
+	u8 sw_own;
+
+	ssize = cq->buf.cqe_size;
+	dsize = cq->resize_buf->cqe_size;
+	if (ssize != dsize) {
+		mlx5_ib_warn(dev, "resize from different cqe size is not supported\n");
+		return -EINVAL;
+	}
+
+	i = cq->mcq.cons_index;
+	scqe = get_sw_cqe(cq, i);
+	scqe64 = ssize == 64 ? scqe : scqe + 64;
+	start_cqe = scqe;
+	if (!scqe) {
+		mlx5_ib_warn(dev, "expected cqe in sw ownership\n");
+		return -EINVAL;
+	}
+
+	while ((scqe64->op_own >> 4) != MLX5_CQE_RESIZE_CQ) {
+		dcqe = get_cqe_from_buf(cq->resize_buf,
+					(i + 1) & (cq->resize_buf->nent),
+					dsize);
+		dcqe64 = dsize == 64 ? dcqe : dcqe + 64;
+		sw_own = sw_ownership_bit(i + 1, cq->resize_buf->nent);
+		memcpy(dcqe, scqe, dsize);
+		dcqe64->op_own = (dcqe64->op_own & ~MLX5_CQE_OWNER_MASK) | sw_own;
+
+		++i;
+		scqe = get_sw_cqe(cq, i);
+		scqe64 = ssize == 64 ? scqe : scqe + 64;
+		if (!scqe) {
+			mlx5_ib_warn(dev, "expected cqe in sw ownership\n");
+			return -EINVAL;
+		}
+
+		if (scqe == start_cqe) {
+			pr_warn("resize CQ failed to get resize CQE, CQN 0x%x\n",
+				cq->mcq.cqn);
+			return -ENOMEM;
+		}
+	}
+	++cq->mcq.cons_index;
+	return 0;
 }
 
 int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 {
-	return -ENOSYS;
+	struct mlx5_ib_dev *dev = to_mdev(ibcq->device);
+	struct mlx5_ib_cq *cq = to_mcq(ibcq);
+	struct mlx5_modify_cq_mbox_in *in;
+	int err;
+	int npas;
+	int page_shift;
+	int inlen;
+	int uninitialized_var(cqe_size);
+	unsigned long flags;
+
+	if (!(dev->mdev.caps.flags & MLX5_DEV_CAP_FLAG_RESIZE_CQ)) {
+		pr_info("Firmware does not support resize CQ\n");
+		return -ENOSYS;
+	}
+
+	if (entries < 1)
+		return -EINVAL;
+
+	entries = roundup_pow_of_two(entries + 1);
+	if (entries > dev->mdev.caps.max_cqes + 1)
+		return -EINVAL;
+
+	if (entries == ibcq->cqe + 1)
+		return 0;
+
+	mutex_lock(&cq->resize_mutex);
+	if (udata) {
+		err = resize_user(dev, cq, entries, udata, &npas, &page_shift,
+				  &cqe_size);
+	} else {
+		cqe_size = 64;
+		err = resize_kernel(dev, cq, entries, cqe_size);
+		if (!err) {
+			npas = cq->resize_buf->buf.npages;
+			page_shift = cq->resize_buf->buf.page_shift;
+		}
+	}
+
+	if (err)
+		goto ex;
+
+	inlen = sizeof(*in) + npas * sizeof(in->pas[0]);
+	in = mlx5_vzalloc(inlen);
+	if (!in) {
+		err = -ENOMEM;
+		goto ex_resize;
+	}
+
+	if (udata)
+		mlx5_ib_populate_pas(dev, cq->resize_umem, page_shift,
+				     in->pas, 0);
+	else
+		mlx5_fill_page_array(&cq->resize_buf->buf, in->pas);
+
+	in->field_select = cpu_to_be32(MLX5_MODIFY_CQ_MASK_LOG_SIZE  |
+				       MLX5_MODIFY_CQ_MASK_PG_OFFSET |
+				       MLX5_MODIFY_CQ_MASK_PG_SIZE);
+	in->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT;
+	in->ctx.cqe_sz_flags = cqe_sz_to_mlx_sz(cqe_size) << 5;
+	in->ctx.page_offset = 0;
+	in->ctx.log_sz_usr_page = cpu_to_be32(ilog2(entries) << 24);
+	in->hdr.opmod = cpu_to_be16(MLX5_CQ_OPMOD_RESIZE);
+	in->cqn = cpu_to_be32(cq->mcq.cqn);
+
+	err = mlx5_core_modify_cq(&dev->mdev, &cq->mcq, in, inlen);
+	if (err)
+		goto ex_alloc;
+
+	if (udata) {
+		cq->ibcq.cqe = entries - 1;
+		ib_umem_release(cq->buf.umem);
+		cq->buf.umem = cq->resize_umem;
+		cq->resize_umem = NULL;
+	} else {
+		struct mlx5_ib_cq_buf tbuf;
+		int resized = 0;
+
+		spin_lock_irqsave(&cq->lock, flags);
+		if (cq->resize_buf) {
+			err = copy_resize_cqes(cq);
+			if (!err) {
+				tbuf = cq->buf;
+				cq->buf = *cq->resize_buf;
+				kfree(cq->resize_buf);
+				cq->resize_buf = NULL;
+				resized = 1;
+			}
+		}
+		cq->ibcq.cqe = entries - 1;
+		spin_unlock_irqrestore(&cq->lock, flags);
+		if (resized)
+			free_cq_buf(dev, &tbuf);
+	}
+	mutex_unlock(&cq->resize_mutex);
+
+	mlx5_vfree(in);
+	return 0;
+
+ex_alloc:
+	mlx5_vfree(in);
+
+ex_resize:
+	if (udata)
+		un_resize_user(cq);
+	else
+		un_resize_kernel(dev, cq);
+ex:
+	mutex_unlock(&cq->resize_mutex);
+	return err;
 }
 
 int mlx5_ib_get_cqe_size(struct mlx5_ib_dev *dev, struct ib_cq *ibcq)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 30653410962..9660d093f8c 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -541,6 +541,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	struct mlx5_ib_ucontext *context;
 	struct mlx5_uuar_info *uuari;
 	struct mlx5_uar *uars;
+	int gross_uuars;
 	int num_uars;
 	int uuarn;
 	int err;
@@ -559,11 +560,13 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	if (req.total_num_uuars == 0)
 		return ERR_PTR(-EINVAL);
 
-	req.total_num_uuars = ALIGN(req.total_num_uuars, MLX5_BF_REGS_PER_PAGE);
+	req.total_num_uuars = ALIGN(req.total_num_uuars,
+				    MLX5_NON_FP_BF_REGS_PER_PAGE);
 	if (req.num_low_latency_uuars > req.total_num_uuars - 1)
 		return ERR_PTR(-EINVAL);
 
-	num_uars = req.total_num_uuars / MLX5_BF_REGS_PER_PAGE;
+	num_uars = req.total_num_uuars / MLX5_NON_FP_BF_REGS_PER_PAGE;
+	gross_uuars = num_uars * MLX5_BF_REGS_PER_PAGE;
 	resp.qp_tab_size      = 1 << dev->mdev.caps.log_max_qp;
 	resp.bf_reg_size      = dev->mdev.caps.bf_reg_size;
 	resp.cache_line_size  = L1_CACHE_BYTES;
@@ -585,7 +588,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 		goto out_ctx;
 	}
 
-	uuari->bitmap = kcalloc(BITS_TO_LONGS(req.total_num_uuars),
+	uuari->bitmap = kcalloc(BITS_TO_LONGS(gross_uuars),
 				sizeof(*uuari->bitmap),
 				GFP_KERNEL);
 	if (!uuari->bitmap) {
@@ -595,13 +598,13 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	/*
 	 * clear all fast path uuars
 	 */
-	for (i = 0; i < req.total_num_uuars; i++) {
+	for (i = 0; i < gross_uuars; i++) {
 		uuarn = i & 3;
 		if (uuarn == 2 || uuarn == 3)
 			set_bit(i, uuari->bitmap);
 	}
 
-	uuari->count = kcalloc(req.total_num_uuars, sizeof(*uuari->count), GFP_KERNEL);
+	uuari->count = kcalloc(gross_uuars, sizeof(*uuari->count), GFP_KERNEL);
 	if (!uuari->count) {
 		err = -ENOMEM;
 		goto out_bitmap;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 4c134d93d4f..389e3196577 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -195,6 +195,7 @@ struct mlx5_ib_cq_buf {
 	struct mlx5_buf		buf;
 	struct ib_umem		*umem;
 	int			cqe_size;
+	int			nent;
 };
 
 enum mlx5_ib_qp_flags {
@@ -220,7 +221,7 @@ struct mlx5_ib_cq {
 	/* protect resize cq
 	 */
 	struct mutex		resize_mutex;
-	struct mlx5_ib_cq_resize *resize_buf;
+	struct mlx5_ib_cq_buf  *resize_buf;
 	struct ib_umem	       *resize_umem;
 	int			cqe_size;
 };
@@ -264,7 +265,6 @@ struct mlx5_ib_mr {
 	enum ib_wc_status	status;
 	struct mlx5_ib_dev     *dev;
 	struct mlx5_create_mkey_mbox_out out;
-	unsigned long		start;
 };
 
 struct mlx5_ib_fast_reg_page_list {
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 039c3e40fcb..7c95ca1f0c2 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -146,7 +146,6 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num)
 		spin_lock_irq(&ent->lock);
 		ent->pending++;
 		spin_unlock_irq(&ent->lock);
-		mr->start = jiffies;
 		err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in,
 					    sizeof(*in), reg_mr_callback,
 					    mr, &mr->out);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 7c6b4ba49be..ae37fb9bf26 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -340,14 +340,57 @@ static int qp_has_rq(struct ib_qp_init_attr *attr)
 	return 1;
 }
 
+static int first_med_uuar(void)
+{
+	return 1;
+}
+
+static int next_uuar(int n)
+{
+	n++;
+
+	while (((n % 4) & 2))
+		n++;
+
+	return n;
+}
+
+static int num_med_uuar(struct mlx5_uuar_info *uuari)
+{
+	int n;
+
+	n = uuari->num_uars * MLX5_NON_FP_BF_REGS_PER_PAGE -
+		uuari->num_low_latency_uuars - 1;
+
+	return n >= 0 ? n : 0;
+}
+
+static int max_uuari(struct mlx5_uuar_info *uuari)
+{
+	return uuari->num_uars * 4;
+}
+
+static int first_hi_uuar(struct mlx5_uuar_info *uuari)
+{
+	int med;
+	int i;
+	int t;
+
+	med = num_med_uuar(uuari);
+	for (t = 0, i = first_med_uuar();; i = next_uuar(i)) {
+		t++;
+		if (t == med)
+			return next_uuar(i);
+	}
+
+	return 0;
+}
+
 static int alloc_high_class_uuar(struct mlx5_uuar_info *uuari)
 {
-	int nuuars = uuari->num_uars * MLX5_BF_REGS_PER_PAGE;
-	int start_uuar;
 	int i;
 
-	start_uuar = nuuars - uuari->num_low_latency_uuars;
-	for (i = start_uuar; i < nuuars; i++) {
+	for (i = first_hi_uuar(uuari); i < max_uuari(uuari); i = next_uuar(i)) {
 		if (!test_bit(i, uuari->bitmap)) {
 			set_bit(i, uuari->bitmap);
 			uuari->count[i]++;
@@ -360,19 +403,10 @@ static int alloc_high_class_uuar(struct mlx5_uuar_info *uuari)
 
 static int alloc_med_class_uuar(struct mlx5_uuar_info *uuari)
 {
-	int nuuars = uuari->num_uars * MLX5_BF_REGS_PER_PAGE;
-	int minidx = 1;
-	int uuarn;
-	int end;
+	int minidx = first_med_uuar();
 	int i;
 
-	end = nuuars - uuari->num_low_latency_uuars;
-
-	for (i = 1; i < end; i++) {
-		uuarn = i & 3;
-		if (uuarn == 2 || uuarn == 3)
-			continue;
-
+	for (i = first_med_uuar(); i < first_hi_uuar(uuari); i = next_uuar(i)) {
 		if (uuari->count[i] < uuari->count[minidx])
 			minidx = i;
 	}
@@ -489,12 +523,12 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 {
 	struct mlx5_ib_ucontext *context;
 	struct mlx5_ib_create_qp ucmd;
-	int page_shift;
+	int page_shift = 0;
 	int uar_index;
 	int npages;
-	u32 offset;
+	u32 offset = 0;
 	int uuarn;
-	int ncont;
+	int ncont = 0;
 	int err;
 
 	err = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd));
@@ -510,11 +544,16 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_HIGH);
 	if (uuarn < 0) {
 		mlx5_ib_dbg(dev, "failed to allocate low latency UUAR\n");
-		mlx5_ib_dbg(dev, "reverting to high latency\n");
-		uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_LOW);
+		mlx5_ib_dbg(dev, "reverting to medium latency\n");
+		uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_MEDIUM);
 		if (uuarn < 0) {
-			mlx5_ib_dbg(dev, "uuar allocation failed\n");
-			return uuarn;
+			mlx5_ib_dbg(dev, "failed to allocate medium latency UUAR\n");
+			mlx5_ib_dbg(dev, "reverting to high latency\n");
+			uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_LOW);
+			if (uuarn < 0) {
+				mlx5_ib_warn(dev, "uuar allocation failed\n");
+				return uuarn;
+			}
 		}
 	}
 
@@ -525,23 +564,29 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	if (err)
 		goto err_uuar;
 
-	qp->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr,
-			       qp->buf_size, 0, 0);
-	if (IS_ERR(qp->umem)) {
-		mlx5_ib_dbg(dev, "umem_get failed\n");
-		err = PTR_ERR(qp->umem);
-		goto err_uuar;
+	if (ucmd.buf_addr && qp->buf_size) {
+		qp->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr,
+				       qp->buf_size, 0, 0);
+		if (IS_ERR(qp->umem)) {
+			mlx5_ib_dbg(dev, "umem_get failed\n");
+			err = PTR_ERR(qp->umem);
+			goto err_uuar;
+		}
+	} else {
+		qp->umem = NULL;
 	}
 
-	mlx5_ib_cont_pages(qp->umem, ucmd.buf_addr, &npages, &page_shift,
-			   &ncont, NULL);
-	err = mlx5_ib_get_buf_offset(ucmd.buf_addr, page_shift, &offset);
-	if (err) {
-		mlx5_ib_warn(dev, "bad offset\n");
-		goto err_umem;
+	if (qp->umem) {
+		mlx5_ib_cont_pages(qp->umem, ucmd.buf_addr, &npages, &page_shift,
+				   &ncont, NULL);
+		err = mlx5_ib_get_buf_offset(ucmd.buf_addr, page_shift, &offset);
+		if (err) {
+			mlx5_ib_warn(dev, "bad offset\n");
+			goto err_umem;
+		}
+		mlx5_ib_dbg(dev, "addr 0x%llx, size %d, npages %d, page_shift %d, ncont %d, offset %d\n",
+			    ucmd.buf_addr, qp->buf_size, npages, page_shift, ncont, offset);
 	}
-	mlx5_ib_dbg(dev, "addr 0x%llx, size %d, npages %d, page_shift %d, ncont %d, offset %d\n",
-		    ucmd.buf_addr, qp->buf_size, npages, page_shift, ncont, offset);
 
 	*inlen = sizeof(**in) + sizeof(*(*in)->pas) * ncont;
 	*in = mlx5_vzalloc(*inlen);
@@ -549,7 +594,8 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 		err = -ENOMEM;
 		goto err_umem;
 	}
-	mlx5_ib_populate_pas(dev, qp->umem, page_shift, (*in)->pas, 0);
+	if (qp->umem)
+		mlx5_ib_populate_pas(dev, qp->umem, page_shift, (*in)->pas, 0);
 	(*in)->ctx.log_pg_sz_remote_qpn =
 		cpu_to_be32((page_shift - MLX5_ADAPTER_PAGE_SHIFT) << 24);
 	(*in)->ctx.params2 = cpu_to_be32(offset << 6);
@@ -580,7 +626,8 @@ err_free:
 	mlx5_vfree(*in);
 
 err_umem:
-	ib_umem_release(qp->umem);
+	if (qp->umem)
+		ib_umem_release(qp->umem);
 
 err_uuar:
 	free_uuar(&context->uuari, uuarn);
@@ -593,7 +640,8 @@ static void destroy_qp_user(struct ib_pd *pd, struct mlx5_ib_qp *qp)
 
 	context = to_mucontext(pd->uobject->context);
 	mlx5_ib_db_unmap_user(context, &qp->db);
-	ib_umem_release(qp->umem);
+	if (qp->umem)
+		ib_umem_release(qp->umem);
 	free_uuar(&context->uuari, qp->uuarn);
 }
 
@@ -1616,7 +1664,8 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
 
 	if (ibqp->qp_type != MLX5_IB_QPT_REG_UMR &&
-	    !ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask))
+	    !ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask,
+				IB_LINK_LAYER_UNSPECIFIED))
 		goto out;
 
 	if ((attr_mask & IB_QP_PORT) &&
@@ -2212,6 +2261,10 @@ out:
 
 		qp->db.db[MLX5_SND_DBR] = cpu_to_be32(qp->sq.cur_post);
 
+		/* Make sure doorbell record is visible to the HCA before
+		 * we hit doorbell */
+		wmb();
+
 		if (bf->need_lock)
 			spin_lock(&bf->lock);
 
diff --git a/drivers/infiniband/hw/mlx5/user.h b/drivers/infiniband/hw/mlx5/user.h
index a886de3e593..32a2a5dfc52 100644
--- a/drivers/infiniband/hw/mlx5/user.h
+++ b/drivers/infiniband/hw/mlx5/user.h
@@ -93,6 +93,9 @@ struct mlx5_ib_create_cq_resp {
 
 struct mlx5_ib_resize_cq {
 	__u64	buf_addr;
+	__u16	cqe_size;
+	__u16	reserved0;
+	__u32	reserved1;
 };
 
 struct mlx5_ib_create_srq {