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

Pull rdma fixes from Jason Gunthorpe:
 "One core bug fix and a few driver ones

   - FRWR memory registration for hfi1/qib didn't work with with some
     iovas causing a NFSoRDMA failure regression due to a fix in the NFS
     side

   - A command flow error in mlx5 allowed user space to send a corrupt
     command (and also smash the kernel stack we've since learned)

   - Fix a regression and some bugs with device hot unplug that was
     discovered while reviewing Andrea's patches

   - hns has a failure if the user asks for certain QP configurations"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  RDMA/hns: Bugfix for mapping user db
  RDMA/ucontext: Fix regression with disassociate
  RDMA/mlx5: Use rdma_user_map_io for mapping BAR pages
  RDMA/mlx5: Do not allow the user to write to the clock page
  IB/mlx5: Fix scatter to CQE in DCT QP creation
  IB/rdmavt: Fix frwr memory registration

drivers/infiniband/core/uverbs.h

@@ -160,6 +160,7 @@ struct ib_uverbs_file {
 
 	struct mutex umap_lock;
 	struct list_head umaps;
+	struct page *disassociate_page;
 
 	struct idr		idr;
 	/* spinlock protects write access to idr */

drivers/infiniband/core/uverbs_main.c

@@ -208,6 +208,9 @@ void ib_uverbs_release_file(struct kref *ref)
 		kref_put(&file->async_file->ref,
 			 ib_uverbs_release_async_event_file);
 	put_device(&file->device->dev);
+
+	if (file->disassociate_page)
+		__free_pages(file->disassociate_page, 0);
 	kfree(file);
 }
 
@@ -877,9 +880,50 @@ static void rdma_umap_close(struct vm_area_struct *vma)
 	kfree(priv);
 }
 
+/*
+ * Once the zap_vma_ptes has been called touches to the VMA will come here and
+ * we return a dummy writable zero page for all the pfns.
+ */
+static vm_fault_t rdma_umap_fault(struct vm_fault *vmf)
+{
+	struct ib_uverbs_file *ufile = vmf->vma->vm_file->private_data;
+	struct rdma_umap_priv *priv = vmf->vma->vm_private_data;
+	vm_fault_t ret = 0;
+
+	if (!priv)
+		return VM_FAULT_SIGBUS;
+
+	/* Read only pages can just use the system zero page. */
+	if (!(vmf->vma->vm_flags & (VM_WRITE | VM_MAYWRITE))) {
+		vmf->page = ZERO_PAGE(vmf->vm_start);
+		get_page(vmf->page);
+		return 0;
+	}
+
+	mutex_lock(&ufile->umap_lock);
+	if (!ufile->disassociate_page)
+		ufile->disassociate_page =
+			alloc_pages(vmf->gfp_mask | __GFP_ZERO, 0);
+
+	if (ufile->disassociate_page) {
+		/*
+		 * This VMA is forced to always be shared so this doesn't have
+		 * to worry about COW.
+		 */
+		vmf->page = ufile->disassociate_page;
+		get_page(vmf->page);
+	} else {
+		ret = VM_FAULT_SIGBUS;
+	}
+	mutex_unlock(&ufile->umap_lock);
+
+	return ret;
+}
+
 static const struct vm_operations_struct rdma_umap_ops = {
 	.open = rdma_umap_open,
 	.close = rdma_umap_close,
+	.fault = rdma_umap_fault,
 };
 
 static struct rdma_umap_priv *rdma_user_mmap_pre(struct ib_ucontext *ucontext,
@@ -889,6 +933,9 @@ static struct rdma_umap_priv *rdma_user_mmap_pre(struct ib_ucontext *ucontext,
 	struct ib_uverbs_file *ufile = ucontext->ufile;
 	struct rdma_umap_priv *priv;
 
+	if (!(vma->vm_flags & VM_SHARED))
+		return ERR_PTR(-EINVAL);
+
 	if (vma->vm_end - vma->vm_start != size)
 		return ERR_PTR(-EINVAL);
 
@@ -992,7 +1039,7 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile)
 		 * at a time to get the lock ordering right. Typically there
 		 * will only be one mm, so no big deal.
 		 */
-		down_write(&mm->mmap_sem);
+		down_read(&mm->mmap_sem);
 		if (!mmget_still_valid(mm))
 			goto skip_mm;
 		mutex_lock(&ufile->umap_lock);
@@ -1006,11 +1053,10 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile)
 
 			zap_vma_ptes(vma, vma->vm_start,
 				     vma->vm_end - vma->vm_start);
-			vma->vm_flags &= ~(VM_SHARED | VM_MAYSHARE);
 		}
 		mutex_unlock(&ufile->umap_lock);
 	skip_mm:
-		up_write(&mm->mmap_sem);
+		up_read(&mm->mmap_sem);
 		mmput(mm);
 	}
 }

drivers/infiniband/hw/hns/hns_roce_qp.c

@@ -533,7 +533,7 @@ static int hns_roce_set_kernel_sq_size(struct hns_roce_dev *hr_dev,
 
 static int hns_roce_qp_has_sq(struct ib_qp_init_attr *attr)
 {
-	if (attr->qp_type == IB_QPT_XRC_TGT)
+	if (attr->qp_type == IB_QPT_XRC_TGT || !attr->cap.max_send_wr)
 		return 0;
 
 	return 1;

drivers/infiniband/hw/mlx5/main.c

@@ -1119,6 +1119,8 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		if (MLX5_CAP_GEN(mdev, qp_packet_based))
 			resp.flags |=
 				MLX5_IB_QUERY_DEV_RESP_PACKET_BASED_CREDIT_MODE;
+
+		resp.flags |= MLX5_IB_QUERY_DEV_RESP_FLAGS_SCAT2CQE_DCT;
 	}
 
 	if (field_avail(typeof(resp), sw_parsing_caps,
@@ -2066,6 +2068,7 @@ static int mlx5_ib_mmap_clock_info_page(struct mlx5_ib_dev *dev,
 
 	if (vma->vm_flags & VM_WRITE)
 		return -EPERM;
+	vma->vm_flags &= ~VM_MAYWRITE;
 
 	if (!dev->mdev->clock_info_page)
 		return -EOPNOTSUPP;
@@ -2231,19 +2234,18 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm
 
 		if (vma->vm_flags & VM_WRITE)
 			return -EPERM;
+		vma->vm_flags &= ~VM_MAYWRITE;
 
 		/* Don't expose to user-space information it shouldn't have */
 		if (PAGE_SIZE > 4096)
 			return -EOPNOTSUPP;
 
-		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 		pfn = (dev->mdev->iseg_base +
 		       offsetof(struct mlx5_init_seg, internal_timer_h)) >>
 			PAGE_SHIFT;
-		if (io_remap_pfn_range(vma, vma->vm_start, pfn,
-				       PAGE_SIZE, vma->vm_page_prot))
-			return -EAGAIN;
-		break;
+		return rdma_user_mmap_io(&context->ibucontext, vma, pfn,
+					 PAGE_SIZE,
+					 pgprot_noncached(vma->vm_page_prot));
 	case MLX5_IB_MMAP_CLOCK_INFO:
 		return mlx5_ib_mmap_clock_info_page(dev, vma, context);
 

drivers/infiniband/hw/mlx5/qp.c

@@ -1818,13 +1818,16 @@ static void configure_responder_scat_cqe(struct ib_qp_init_attr *init_attr,
 
 	rcqe_sz = mlx5_ib_get_cqe_size(init_attr->recv_cq);
 
-	if (rcqe_sz == 128) {
-		MLX5_SET(qpc, qpc, cs_res, MLX5_RES_SCAT_DATA64_CQE);
+	if (init_attr->qp_type == MLX5_IB_QPT_DCT) {
+		if (rcqe_sz == 128)
+			MLX5_SET(dctc, qpc, cs_res, MLX5_RES_SCAT_DATA64_CQE);
+
 		return;
 	}
 
-	if (init_attr->qp_type != MLX5_IB_QPT_DCT)
-		MLX5_SET(qpc, qpc, cs_res, MLX5_RES_SCAT_DATA32_CQE);
+	MLX5_SET(qpc, qpc, cs_res,
+		 rcqe_sz == 128 ? MLX5_RES_SCAT_DATA64_CQE :
+				  MLX5_RES_SCAT_DATA32_CQE);
 }
 
 static void configure_requester_scat_cqe(struct mlx5_ib_dev *dev,

drivers/infiniband/sw/rdmavt/mr.c

@@ -608,11 +608,6 @@ static int rvt_set_page(struct ib_mr *ibmr, u64 addr)
 	if (unlikely(mapped_segs == mr->mr.max_segs))
 		return -ENOMEM;
 
-	if (mr->mr.length == 0) {
-		mr->mr.user_base = addr;
-		mr->mr.iova = addr;
-	}
-
 	m = mapped_segs / RVT_SEGSZ;
 	n = mapped_segs % RVT_SEGSZ;
 	mr->mr.map[m]->segs[n].vaddr = (void *)addr;
@@ -630,17 +625,24 @@ static int rvt_set_page(struct ib_mr *ibmr, u64 addr)
  * @sg_nents: number of entries in sg
  * @sg_offset: offset in bytes into sg
  *
+ * Overwrite rvt_mr length with mr length calculated by ib_sg_to_pages.
+ *
  * Return: number of sg elements mapped to the memory region
  */
 int rvt_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg,
 		  int sg_nents, unsigned int *sg_offset)
 {
 	struct rvt_mr *mr = to_imr(ibmr);
+	int ret;
 
 	mr->mr.length = 0;
 	mr->mr.page_shift = PAGE_SHIFT;
-	return ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset,
-			      rvt_set_page);
+	ret = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, rvt_set_page);
+	mr->mr.user_base = ibmr->iova;
+	mr->mr.iova = ibmr->iova;
+	mr->mr.offset = ibmr->iova - (u64)mr->mr.map[0]->segs[0].vaddr;
+	mr->mr.length = (size_t)ibmr->length;
+	return ret;
 }
 
 /**
@@ -671,6 +673,7 @@ int rvt_fast_reg_mr(struct rvt_qp *qp, struct ib_mr *ibmr, u32 key,
 	ibmr->rkey = key;
 	mr->mr.lkey = key;
 	mr->mr.access_flags = access;
+	mr->mr.iova = ibmr->iova;
 	atomic_set(&mr->mr.lkey_invalid, 0);
 
 	return 0;

include/uapi/rdma/mlx5-abi.h

@@ -238,6 +238,7 @@ enum mlx5_ib_query_dev_resp_flags {
 	MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_COMP = 1 << 0,
 	MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_PAD  = 1 << 1,
 	MLX5_IB_QUERY_DEV_RESP_PACKET_BASED_CREDIT_MODE = 1 << 2,
+	MLX5_IB_QUERY_DEV_RESP_FLAGS_SCAT2CQE_DCT = 1 << 3,
 };
 
 enum mlx5_ib_tunnel_offloads {