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

Pull rdma updates from Jason Gunthorpe:
 "Aside from the usual things this has an arch update for
  __iowrite64_copy() used by the RDMA drivers.

  This API was intended to generate large 64 byte MemWr TLPs on PCI.
  These days most processors had done this by just repeating writel() in
  a loop. S390 and some new ARM64 designs require a special helper to
  get this to generate.

   - Small improvements and fixes for erdma, efa, hfi1, bnxt_re

   - Fix a UAF crash after module unload on leaking restrack entry

   - Continue adding full RDMA support in mana with support for EQs,
     GID's and CQs

   - Improvements to the mkey cache in mlx5

   - DSCP traffic class support in hns and several bug fixes

   - Cap the maximum number of MADs in the receive queue to avoid OOM

   - Another batch of rxe bug fixes from large scale testing

   - __iowrite64_copy() optimizations for write combining MMIO memory

   - Remove NULL checks before dev_put/hold()

   - EFA support for receive with immediate

   - Fix a recent memleaking regression in a cma error path"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (70 commits)
  RDMA/cma: Fix kmemleak in rdma_core observed during blktests nvme/rdma use siw
  RDMA/IPoIB: Fix format truncation compilation errors
  bnxt_re: avoid shift undefined behavior in bnxt_qplib_alloc_init_hwq
  RDMA/efa: Support QP with unsolicited write w/ imm. receive
  IB/hfi1: Remove generic .ndo_get_stats64
  IB/hfi1: Do not use custom stat allocator
  RDMA/hfi1: Use RMW accessors for changing LNKCTL2
  RDMA/mana_ib: implement uapi for creation of rnic cq
  RDMA/mana_ib: boundary check before installing cq callbacks
  RDMA/mana_ib: introduce a helper to remove cq callbacks
  RDMA/mana_ib: create and destroy RNIC cqs
  RDMA/mana_ib: create EQs for RNIC CQs
  RDMA/core: Remove NULL check before dev_{put, hold}
  RDMA/ipoib: Remove NULL check before dev_{put, hold}
  RDMA/mlx5: Remove NULL check before dev_{put, hold}
  RDMA/mlx5: Track DCT, DCI and REG_UMR QPs as diver_detail resources.
  RDMA/core: Add an option to display driver-specific QPs in the rdmatool
  RDMA/efa: Add shutdown notifier
  RDMA/mana_ib: Fix missing ret value
  IB/mlx5: Use __iowrite64_copy() for write combining stores
  ...

6 files changed, 60 insertions, 21 deletions

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index c2b557e64290..2366c46eebc8 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -264,8 +264,7 @@ static struct net_device *mlx5_ib_get_netdev(struct ib_device *device,
 	 */
 	read_lock(&ibdev->port[port_num - 1].roce.netdev_lock);
 	ndev = ibdev->port[port_num - 1].roce.netdev;
-	if (ndev)
-		dev_hold(ndev);
+	dev_hold(ndev);
 	read_unlock(&ibdev->port[port_num - 1].roce.netdev_lock);
 
 out:
diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index 96ffbbaf0a73..5a22be14d958 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -30,6 +30,7 @@
  * SOFTWARE.
  */
 
+#include <linux/io.h>
 #include <rdma/ib_umem_odp.h>
 #include "mlx5_ib.h"
 #include <linux/jiffies.h>
@@ -108,7 +109,6 @@ static int post_send_nop(struct mlx5_ib_dev *dev, struct ib_qp *ibqp, u64 wr_id,
 	__be32 mmio_wqe[16] = {};
 	unsigned long flags;
 	unsigned int idx;
-	int i;
 
 	if (unlikely(dev->mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR))
 		return -EIO;
@@ -148,10 +148,8 @@ static int post_send_nop(struct mlx5_ib_dev *dev, struct ib_qp *ibqp, u64 wr_id,
 	 * we hit doorbell
 	 */
 	wmb();
-	for (i = 0; i < 8; i++)
-		mlx5_write64(&mmio_wqe[i * 2],
-			     bf->bfreg->map + bf->offset + i * 8);
-	io_stop_wc();
+	__iowrite64_copy(bf->bfreg->map + bf->offset, mmio_wqe,
+			 sizeof(mmio_wqe) / 8);
 
 	bf->offset ^= bf->buf_size;
 
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index a8de35c07c9e..f255a12e26a0 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -643,9 +643,10 @@ struct mlx5_ib_mkey {
 	unsigned int ndescs;
 	struct wait_queue_head wait;
 	refcount_t usecount;
-	/* User Mkey must hold either a rb_key or a cache_ent. */
+	/* Cacheable user Mkey must hold either a rb_key or a cache_ent. */
 	struct mlx5r_cache_rb_key rb_key;
 	struct mlx5_cache_ent *cache_ent;
+	u8 cacheable : 1;
 };
 
 #define MLX5_IB_MTT_PRESENT (MLX5_IB_MTT_READ | MLX5_IB_MTT_WRITE)
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index a8ee2ca1f4a1..ecc111ed5d86 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1158,6 +1158,7 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd,
 		if (IS_ERR(mr))
 			return mr;
 		mr->mmkey.rb_key = rb_key;
+		mr->mmkey.cacheable = true;
 		return mr;
 	}
 
@@ -1168,6 +1169,7 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd,
 	mr->ibmr.pd = pd;
 	mr->umem = umem;
 	mr->page_shift = order_base_2(page_size);
+	mr->mmkey.cacheable = true;
 	set_mr_fields(dev, mr, umem->length, access_flags, iova);
 
 	return mr;
@@ -1570,7 +1572,8 @@ static bool can_use_umr_rereg_access(struct mlx5_ib_dev *dev,
 	unsigned int diffs = current_access_flags ^ target_access_flags;
 
 	if (diffs & ~(IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE |
-		      IB_ACCESS_REMOTE_READ | IB_ACCESS_RELAXED_ORDERING))
+		      IB_ACCESS_REMOTE_READ | IB_ACCESS_RELAXED_ORDERING |
+		      IB_ACCESS_REMOTE_ATOMIC))
 		return false;
 	return mlx5r_umr_can_reconfig(dev, current_access_flags,
 				      target_access_flags);
@@ -1835,6 +1838,23 @@ end:
 	return ret;
 }
 
+static int mlx5_revoke_mr(struct mlx5_ib_mr *mr)
+{
+	struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
+	struct mlx5_cache_ent *ent = mr->mmkey.cache_ent;
+
+	if (mr->mmkey.cacheable && !mlx5r_umr_revoke_mr(mr) && !cache_ent_find_and_store(dev, mr))
+		return 0;
+
+	if (ent) {
+		spin_lock_irq(&ent->mkeys_queue.lock);
+		ent->in_use--;
+		mr->mmkey.cache_ent = NULL;
+		spin_unlock_irq(&ent->mkeys_queue.lock);
+	}
+	return destroy_mkey(dev, mr);
+}
+
 int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
 {
 	struct mlx5_ib_mr *mr = to_mmr(ibmr);
@@ -1880,16 +1900,9 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
 	}
 
 	/* Stop DMA */
-	if (mr->umem && mlx5r_umr_can_load_pas(dev, mr->umem->length))
-		if (mlx5r_umr_revoke_mr(mr) ||
-		    cache_ent_find_and_store(dev, mr))
-			mr->mmkey.cache_ent = NULL;
-
-	if (!mr->mmkey.cache_ent) {
-		rc = destroy_mkey(to_mdev(mr->ibmr.device), mr);
-		if (rc)
-			return rc;
-	}
+	rc = mlx5_revoke_mr(mr);
+	if (rc)
+		return rc;
 
 	if (mr->umem) {
 		bool is_odp = is_odp_mr(mr);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 8115ab107149..e2164f813607 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3097,7 +3097,6 @@ static int create_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	switch (qp->type) {
 	case MLX5_IB_QPT_DCT:
 		err = create_dct(dev, pd, qp, params);
-		rdma_restrack_no_track(&qp->ibqp.res);
 		break;
 	case MLX5_IB_QPT_DCI:
 		err = create_dci(dev, pd, qp, params);
@@ -3109,9 +3108,9 @@ static int create_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 		err = mlx5_ib_create_gsi(pd, qp, params->attr);
 		break;
 	case MLX5_IB_QPT_HW_GSI:
-	case MLX5_IB_QPT_REG_UMR:
 		rdma_restrack_no_track(&qp->ibqp.res);
 		fallthrough;
+	case MLX5_IB_QPT_REG_UMR:
 	default:
 		if (params->udata)
 			err = create_user_qp(dev, pd, qp, params);
diff --git a/drivers/infiniband/hw/mlx5/restrack.c b/drivers/infiniband/hw/mlx5/restrack.c
index 4ac429e72004..affcf8fe943c 100644
--- a/drivers/infiniband/hw/mlx5/restrack.c
+++ b/drivers/infiniband/hw/mlx5/restrack.c
@@ -156,6 +156,34 @@ static int fill_res_cq_entry_raw(struct sk_buff *msg, struct ib_cq *ibcq)
 	return fill_res_raw(msg, dev, MLX5_SGMT_TYPE_PRM_QUERY_CQ, cq->mcq.cqn);
 }
 
+static int fill_res_qp_entry(struct sk_buff *msg, struct ib_qp *ibqp)
+{
+	struct mlx5_ib_qp *qp = to_mqp(ibqp);
+	int ret;
+
+	if (qp->type < IB_QPT_DRIVER)
+		return 0;
+
+	switch (qp->type) {
+	case MLX5_IB_QPT_REG_UMR:
+		ret = nla_put_string(msg, RDMA_NLDEV_ATTR_RES_SUBTYPE,
+				     "REG_UMR");
+		break;
+	case MLX5_IB_QPT_DCT:
+		ret = nla_put_string(msg, RDMA_NLDEV_ATTR_RES_SUBTYPE, "DCT");
+		break;
+	case MLX5_IB_QPT_DCI:
+		ret = nla_put_string(msg, RDMA_NLDEV_ATTR_RES_SUBTYPE, "DCI");
+		break;
+	default:
+		return 0;
+	}
+	if (ret)
+		return ret;
+
+	return nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_TYPE, IB_QPT_DRIVER);
+}
+
 static int fill_res_qp_entry_raw(struct sk_buff *msg, struct ib_qp *ibqp)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
@@ -168,6 +196,7 @@ static const struct ib_device_ops restrack_ops = {
 	.fill_res_cq_entry_raw = fill_res_cq_entry_raw,
 	.fill_res_mr_entry = fill_res_mr_entry,
 	.fill_res_mr_entry_raw = fill_res_mr_entry_raw,
+	.fill_res_qp_entry = fill_res_qp_entry,
 	.fill_res_qp_entry_raw = fill_res_qp_entry_raw,
 	.fill_stat_mr_entry = fill_stat_mr_entry,
 };