RDMA/rxe: Allow registering MRs for On-Demand Paging

Allow userspace to register an ODP-enabled MR, in which case the flag
IB_ACCESS_ON_DEMAND is passed to rxe_reg_user_mr(). However, there is no
RDMA operation enabled right now. They will be supported later in the
subsequent two patches.

rxe_odp_do_pagefault() is called to initialize an ODP-enabled MR. It syncs
process address space from the CPU page table to the driver page table
(dma_list/pfn_list in umem_odp) when called with RXE_PAGEFAULT_SNAPSHOT
flag. Additionally, It can be used to trigger page fault when pages being
accessed are not present or do not have proper read/write permissions, and
possibly to prefetch pages in the future.

Link: https://patch.msgid.link/r/20241220100936.2193541-4-matsuda-daisuke@fujitsu.com
Signed-off-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

drivers/infiniband/sw/rxe/rxe.c

@@ -92,6 +92,13 @@ static void rxe_init_device_param(struct rxe_dev *rxe)
 	dev_put(ndev);
 
 	rxe->max_ucontext			= RXE_MAX_UCONTEXT;
+
+	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
+		rxe->attr.kernel_cap_flags |= IBK_ON_DEMAND_PAGING;
+
+		/* IB_ODP_SUPPORT_IMPLICIT is not supported right now. */
+		rxe->attr.odp_caps.general_caps |= IB_ODP_SUPPORT;
+	}
 }
 
 /* initialize port attributes */

drivers/infiniband/sw/rxe/rxe_loc.h

@@ -184,4 +184,16 @@ static inline unsigned int wr_opcode_mask(int opcode, struct rxe_qp *qp)
 /* rxe_odp.c */
 extern const struct mmu_interval_notifier_ops rxe_mn_ops;
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+int rxe_odp_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length,
+			 u64 iova, int access_flags, struct rxe_mr *mr);
+#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
+static inline int
+rxe_odp_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length, u64 iova,
+		     int access_flags, struct rxe_mr *mr)
+{
+	return -EOPNOTSUPP;
+}
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
+
 #endif /* RXE_LOC_H */

drivers/infiniband/sw/rxe/rxe_mr.c

@@ -323,6 +323,9 @@ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr,
 		return err;
 	}
 
+	if (mr->umem->is_odp)
+		return -EOPNOTSUPP;
+	else
 		return rxe_mr_copy_xarray(mr, iova, addr, length, dir);
 }
 
@@ -532,6 +535,10 @@ int rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value)
 	struct page *page;
 	u64 *va;
 
+	/* ODP is not supported right now. WIP. */
+	if (mr->umem->is_odp)
+		return RESPST_ERR_UNSUPPORTED_OPCODE;
+
 	/* See IBA oA19-28 */
 	if (unlikely(mr->state != RXE_MR_STATE_VALID)) {
 		rxe_dbg_mr(mr, "mr not in valid state\n");

drivers/infiniband/sw/rxe/rxe_odp.c

@@ -36,3 +36,89 @@ static bool rxe_ib_invalidate_range(struct mmu_interval_notifier *mni,
 const struct mmu_interval_notifier_ops rxe_mn_ops = {
 	.invalidate = rxe_ib_invalidate_range,
 };
+
+#define RXE_PAGEFAULT_RDONLY BIT(1)
+#define RXE_PAGEFAULT_SNAPSHOT BIT(2)
+static int rxe_odp_do_pagefault_and_lock(struct rxe_mr *mr, u64 user_va, int bcnt, u32 flags)
+{
+	struct ib_umem_odp *umem_odp = to_ib_umem_odp(mr->umem);
+	bool fault = !(flags & RXE_PAGEFAULT_SNAPSHOT);
+	u64 access_mask;
+	int np;
+
+	access_mask = ODP_READ_ALLOWED_BIT;
+	if (umem_odp->umem.writable && !(flags & RXE_PAGEFAULT_RDONLY))
+		access_mask |= ODP_WRITE_ALLOWED_BIT;
+
+	/*
+	 * ib_umem_odp_map_dma_and_lock() locks umem_mutex on success.
+	 * Callers must release the lock later to let invalidation handler
+	 * do its work again.
+	 */
+	np = ib_umem_odp_map_dma_and_lock(umem_odp, user_va, bcnt,
+					  access_mask, fault);
+	return np;
+}
+
+static int rxe_odp_init_pages(struct rxe_mr *mr)
+{
+	struct ib_umem_odp *umem_odp = to_ib_umem_odp(mr->umem);
+	int ret;
+
+	ret = rxe_odp_do_pagefault_and_lock(mr, mr->umem->address,
+					    mr->umem->length,
+					    RXE_PAGEFAULT_SNAPSHOT);
+
+	if (ret >= 0)
+		mutex_unlock(&umem_odp->umem_mutex);
+
+	return ret >= 0 ? 0 : ret;
+}
+
+int rxe_odp_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length,
+			 u64 iova, int access_flags, struct rxe_mr *mr)
+{
+	struct ib_umem_odp *umem_odp;
+	int err;
+
+	if (!IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING))
+		return -EOPNOTSUPP;
+
+	rxe_mr_init(access_flags, mr);
+
+	if (!start && length == U64_MAX) {
+		if (iova != 0)
+			return -EINVAL;
+		if (!(rxe->attr.odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT))
+			return -EINVAL;
+
+		/* Never reach here, for implicit ODP is not implemented. */
+	}
+
+	umem_odp = ib_umem_odp_get(&rxe->ib_dev, start, length, access_flags,
+				   &rxe_mn_ops);
+	if (IS_ERR(umem_odp)) {
+		rxe_dbg_mr(mr, "Unable to create umem_odp err = %d\n",
+			   (int)PTR_ERR(umem_odp));
+		return PTR_ERR(umem_odp);
+	}
+
+	umem_odp->private = mr;
+
+	mr->umem = &umem_odp->umem;
+	mr->access = access_flags;
+	mr->ibmr.length = length;
+	mr->ibmr.iova = iova;
+	mr->page_offset = ib_umem_offset(&umem_odp->umem);
+
+	err = rxe_odp_init_pages(mr);
+	if (err) {
+		ib_umem_odp_release(umem_odp);
+		return err;
+	}
+
+	mr->state = RXE_MR_STATE_VALID;
+	mr->ibmr.type = IB_MR_TYPE_USER;
+
+	return err;
+}

drivers/infiniband/sw/rxe/rxe_resp.c

@@ -649,6 +649,10 @@ static enum resp_states process_flush(struct rxe_qp *qp,
 	struct rxe_mr *mr = qp->resp.mr;
 	struct resp_res *res = qp->resp.res;
 
+	/* ODP is not supported right now. WIP. */
+	if (mr->umem->is_odp)
+		return RESPST_ERR_UNSUPPORTED_OPCODE;
+
 	/* oA19-14, oA19-15 */
 	if (res && res->replay)
 		return RESPST_ACKNOWLEDGE;
@@ -702,6 +706,9 @@ static enum resp_states atomic_reply(struct rxe_qp *qp,
 	if (!res->replay) {
 		u64 iova = qp->resp.va + qp->resp.offset;
 
+		if (mr->umem->is_odp)
+			err = RESPST_ERR_UNSUPPORTED_OPCODE;
+		else
 			err = rxe_mr_do_atomic_op(mr, iova, pkt->opcode,
 						  atmeth_comp(pkt),
 						  atmeth_swap_add(pkt),

drivers/infiniband/sw/rxe/rxe_verbs.c

@@ -1298,6 +1298,9 @@ static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd, u64 start,
 	mr->ibmr.pd = ibpd;
 	mr->ibmr.device = ibpd->device;
 
+	if (access & IB_ACCESS_ON_DEMAND)
+		err = rxe_odp_mr_init_user(rxe, start, length, iova, access, mr);
+	else
 		err = rxe_mr_init_user(rxe, start, length, access, mr);
 	if (err) {
 		rxe_dbg_mr(mr, "reg_user_mr failed, err = %d\n", err);