8 files changed, 88 insertions, 35 deletions

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index c2b557e642..43660c831b 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:
@@ -3760,10 +3759,10 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 	spin_lock_init(&dev->dm.lock);
 	dev->dm.dev = mdev;
 	return 0;
-err:
-	mlx5r_macsec_dealloc_gids(dev);
 err_mp:
 	mlx5_ib_cleanup_multiport_master(dev);
+err:
+	mlx5r_macsec_dealloc_gids(dev);
 	return err;
 }
 
diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index 96ffbbaf0a..5a22be14d9 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 a8de35c07c..f9abdca349 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -115,6 +115,19 @@ unsigned long __mlx5_umem_find_best_quantized_pgoff(
 		__mlx5_bit_sz(typ, page_offset_fld), 0, scale,                 \
 		page_offset_quantized)
 
+static inline unsigned long
+mlx5_umem_dmabuf_find_best_pgsz(struct ib_umem_dmabuf *umem_dmabuf)
+{
+	/*
+	 * mkeys used for dmabuf are fixed at PAGE_SIZE because we must be able
+	 * to hold any sgl after a move operation. Ideally the mkc page size
+	 * could be changed at runtime to be optimal, but right now the driver
+	 * cannot do that.
+	 */
+	return ib_umem_find_best_pgsz(&umem_dmabuf->umem, PAGE_SIZE,
+				      umem_dmabuf->umem.iova);
+}
+
 enum {
 	MLX5_IB_MMAP_OFFSET_START = 9,
 	MLX5_IB_MMAP_OFFSET_END = 255,
@@ -643,9 +656,10 @@ 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 a8ee2ca1f4..d3c1f63791 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -246,6 +246,7 @@ static void set_cache_mkc(struct mlx5_cache_ent *ent, void *mkc)
 	MLX5_SET(mkc, mkc, access_mode_1_0, ent->rb_key.access_mode & 0x3);
 	MLX5_SET(mkc, mkc, access_mode_4_2,
 		(ent->rb_key.access_mode >> 2) & 0x7);
+	MLX5_SET(mkc, mkc, ma_translation_mode, !!ent->rb_key.ats);
 
 	MLX5_SET(mkc, mkc, translations_octword_size,
 		 get_mkc_octo_size(ent->rb_key.access_mode,
@@ -641,10 +642,8 @@ static int mlx5_cache_ent_insert(struct mlx5_mkey_cache *cache,
 			new = &((*new)->rb_left);
 		if (cmp < 0)
 			new = &((*new)->rb_right);
-		if (cmp == 0) {
-			mutex_unlock(&cache->rb_lock);
+		if (cmp == 0)
 			return -EEXIST;
-		}
 	}
 
 	/* Add new node and rebalance tree. */
@@ -719,6 +718,8 @@ static struct mlx5_ib_mr *_mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev,
 	}
 	mr->mmkey.cache_ent = ent;
 	mr->mmkey.type = MLX5_MKEY_MR;
+	mr->mmkey.rb_key = ent->rb_key;
+	mr->mmkey.cacheable = true;
 	init_waitqueue_head(&mr->mmkey.wait);
 	return mr;
 }
@@ -1158,6 +1159,7 @@ 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;
 	}
 
@@ -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/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 4a04cbc5b7..a524181f34 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -705,10 +705,8 @@ static int pagefault_dmabuf_mr(struct mlx5_ib_mr *mr, size_t bcnt,
 		return err;
 	}
 
-	page_size = mlx5_umem_find_best_pgsz(&umem_dmabuf->umem, mkc,
-					     log_page_size, 0,
-					     umem_dmabuf->umem.iova);
-	if (unlikely(page_size < PAGE_SIZE)) {
+	page_size = mlx5_umem_dmabuf_find_best_pgsz(umem_dmabuf);
+	if (!page_size) {
 		ib_umem_dmabuf_unmap_pages(umem_dmabuf);
 		err = -EINVAL;
 	} else {
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 8115ab1071..e2164f8136 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 4ac429e720..affcf8fe94 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,
 };
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index a056ea835d..84be0c3d56 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -199,17 +199,20 @@ int mlx5_ib_create_srq(struct ib_srq *ib_srq,
 	int err;
 	struct mlx5_srq_attr in = {};
 	__u32 max_srq_wqes = 1 << MLX5_CAP_GEN(dev->mdev, log_max_srq_sz);
+	__u32 max_sge_sz =  MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq) /
+			    sizeof(struct mlx5_wqe_data_seg);
 
 	if (init_attr->srq_type != IB_SRQT_BASIC &&
 	    init_attr->srq_type != IB_SRQT_XRC &&
 	    init_attr->srq_type != IB_SRQT_TM)
 		return -EOPNOTSUPP;
 
-	/* Sanity check SRQ size before proceeding */
-	if (init_attr->attr.max_wr >= max_srq_wqes) {
-		mlx5_ib_dbg(dev, "max_wr %d, cap %d\n",
-			    init_attr->attr.max_wr,
-			    max_srq_wqes);
+	/* Sanity check SRQ and sge size before proceeding */
+	if (init_attr->attr.max_wr >= max_srq_wqes ||
+	    init_attr->attr.max_sge > max_sge_sz) {
+		mlx5_ib_dbg(dev, "max_wr %d,wr_cap %d,max_sge %d, sge_cap:%d\n",
+			    init_attr->attr.max_wr, max_srq_wqes,
+			    init_attr->attr.max_sge, max_sge_sz);
 		return -EINVAL;
 	}