Linux-RDMA Archive on lore.kernel.org
 help / color / Atom feed
From: Bob Pearson <rpearsonhpe@gmail.com>
To: jgg@nvidia.com, zyjzyj2000@gmail.com, linux-rdma@vger.kernel.org
Cc: Bob Pearson <rpearson@hpe.com>
Subject: [PATCH for-next v3 9/9] RDMA/rxe: Implement memory access through MWs
Date: Wed, 21 Apr 2021 00:20:16 -0500
Message-ID: <20210421052015.4546-10-rpearson@hpe.com> (raw)
In-Reply-To: <20210421052015.4546-1-rpearson@hpe.com>

Add code to implement memory access through memory windows.

Signed-off-by: Bob Pearson <rpearson@hpe.com>
---
v3:
  Adjusted patch for collisions with v3 of "RDMA/rxe: Implement
  invalidate MW operations" patch.
v2:
  Removed a copy of changes in ea4922518940 "Fix missing acks from responder"
  that was submitted separately.
---
 drivers/infiniband/sw/rxe/rxe_loc.h   |  1 +
 drivers/infiniband/sw/rxe/rxe_mw.c    | 23 +++++++++++
 drivers/infiniband/sw/rxe/rxe_resp.c  | 55 +++++++++++++++++++--------
 drivers/infiniband/sw/rxe/rxe_verbs.h | 11 ++++++
 4 files changed, 75 insertions(+), 15 deletions(-)

diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index bc0e484f8cde..076e1460577f 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -94,6 +94,7 @@ int rxe_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata);
 int rxe_dealloc_mw(struct ib_mw *ibmw);
 int rxe_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe);
 int rxe_invalidate_mw(struct rxe_qp *qp, u32 rkey);
+struct rxe_mw *lookup_mw(struct rxe_qp *qp, int access, u32 rkey);
 void rxe_mw_cleanup(struct rxe_pool_entry *arg);
 
 /* rxe_net.c */
diff --git a/drivers/infiniband/sw/rxe/rxe_mw.c b/drivers/infiniband/sw/rxe/rxe_mw.c
index 00490f232fde..6ed36845c693 100644
--- a/drivers/infiniband/sw/rxe/rxe_mw.c
+++ b/drivers/infiniband/sw/rxe/rxe_mw.c
@@ -312,6 +312,29 @@ int rxe_invalidate_mw(struct rxe_qp *qp, u32 rkey)
 	return ret;
 }
 
+struct rxe_mw *lookup_mw(struct rxe_qp *qp, int access, u32 rkey)
+{
+	struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
+	struct rxe_pd *pd = to_rpd(qp->ibqp.pd);
+	struct rxe_mw *mw;
+	int index = rkey >> 8;
+
+	mw = rxe_pool_get_index(&rxe->mw_pool, index);
+	if (!mw)
+		return NULL;
+
+	if (unlikely((mw_rkey(mw) != rkey) || mw_pd(mw) != pd ||
+		     (mw->ibmw.type == IB_MW_TYPE_2 && mw->qp != qp) ||
+		     (mw->length == 0) ||
+		     (access && !(access & mw->access)) ||
+		     mw->state != RXE_MW_STATE_VALID)) {
+		rxe_drop_ref(mw);
+		return NULL;
+	}
+
+	return mw;
+}
+
 void rxe_mw_cleanup(struct rxe_pool_entry *elem)
 {
 	struct rxe_mw *mw = container_of(elem, typeof(*mw), pelem);
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 759e9789cd4d..9c8cbfbc8820 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -394,6 +394,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 				   struct rxe_pkt_info *pkt)
 {
 	struct rxe_mr *mr = NULL;
+	struct rxe_mw *mw = NULL;
 	u64 va;
 	u32 rkey;
 	u32 resid;
@@ -405,6 +406,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 	if (pkt->mask & (RXE_READ_MASK | RXE_WRITE_MASK)) {
 		if (pkt->mask & RXE_RETH_MASK) {
 			qp->resp.va = reth_va(pkt);
+			qp->resp.offset = 0;
 			qp->resp.rkey = reth_rkey(pkt);
 			qp->resp.resid = reth_len(pkt);
 			qp->resp.length = reth_len(pkt);
@@ -413,6 +415,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 						     : IB_ACCESS_REMOTE_WRITE;
 	} else if (pkt->mask & RXE_ATOMIC_MASK) {
 		qp->resp.va = atmeth_va(pkt);
+		qp->resp.offset = 0;
 		qp->resp.rkey = atmeth_rkey(pkt);
 		qp->resp.resid = sizeof(u64);
 		access = IB_ACCESS_REMOTE_ATOMIC;
@@ -432,18 +435,36 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 	resid	= qp->resp.resid;
 	pktlen	= payload_size(pkt);
 
-	mr = lookup_mr(qp->pd, access, rkey, RXE_LOOKUP_REMOTE);
-	if (!mr) {
-		state = RESPST_ERR_RKEY_VIOLATION;
-		goto err;
-	}
+	if (rkey_is_mw(rkey)) {
+		mw = lookup_mw(qp, access, rkey);
+		if (!mw) {
+			pr_err("%s: no MW matches rkey %#x\n", __func__, rkey);
+			state = RESPST_ERR_RKEY_VIOLATION;
+			goto err;
+		}
 
-	if (unlikely(mr->state == RXE_MR_STATE_FREE)) {
-		state = RESPST_ERR_RKEY_VIOLATION;
-		goto err;
+		mr = mw->mr;
+		if (!mr) {
+			pr_err("%s: MW doesn't have an MR\n", __func__);
+			state = RESPST_ERR_RKEY_VIOLATION;
+			goto err;
+		}
+
+		if (mw->access & IB_ZERO_BASED)
+			qp->resp.offset = mw->addr;
+
+		rxe_drop_ref(mw);
+		rxe_add_ref(mr);
+	} else {
+		mr = lookup_mr(qp->pd, access, rkey, RXE_LOOKUP_REMOTE);
+		if (!mr) {
+			pr_err("%s: no MR matches rkey %#x\n", __func__, rkey);
+			state = RESPST_ERR_RKEY_VIOLATION;
+			goto err;
+		}
 	}
 
-	if (mr_check_range(mr, va, resid)) {
+	if (mr_check_range(mr, va + qp->resp.offset, resid)) {
 		state = RESPST_ERR_RKEY_VIOLATION;
 		goto err;
 	}
@@ -477,6 +498,9 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 err:
 	if (mr)
 		rxe_drop_ref(mr);
+	if (mw)
+		rxe_drop_ref(mw);
+
 	return state;
 }
 
@@ -501,8 +525,8 @@ static enum resp_states write_data_in(struct rxe_qp *qp,
 	int	err;
 	int data_len = payload_size(pkt);
 
-	err = rxe_mr_copy(qp->resp.mr, qp->resp.va, payload_addr(pkt), data_len,
-			  RXE_TO_MR_OBJ, NULL);
+	err = rxe_mr_copy(qp->resp.mr, qp->resp.va + qp->resp.offset,
+			  payload_addr(pkt), data_len, RXE_TO_MR_OBJ, NULL);
 	if (err) {
 		rc = RESPST_ERR_RKEY_VIOLATION;
 		goto out;
@@ -521,7 +545,6 @@ static DEFINE_SPINLOCK(atomic_ops_lock);
 static enum resp_states process_atomic(struct rxe_qp *qp,
 				       struct rxe_pkt_info *pkt)
 {
-	u64 iova = atmeth_va(pkt);
 	u64 *vaddr;
 	enum resp_states ret;
 	struct rxe_mr *mr = qp->resp.mr;
@@ -531,7 +554,7 @@ static enum resp_states process_atomic(struct rxe_qp *qp,
 		goto out;
 	}
 
-	vaddr = iova_to_vaddr(mr, iova, sizeof(u64));
+	vaddr = iova_to_vaddr(mr, qp->resp.va + qp->resp.offset, sizeof(u64));
 
 	/* check vaddr is 8 bytes aligned. */
 	if (!vaddr || (uintptr_t)vaddr & 7) {
@@ -655,8 +678,10 @@ static enum resp_states read_reply(struct rxe_qp *qp,
 		res->type		= RXE_READ_MASK;
 		res->replay		= 0;
 
-		res->read.va		= qp->resp.va;
-		res->read.va_org	= qp->resp.va;
+		res->read.va		= qp->resp.va +
+					  qp->resp.offset;
+		res->read.va_org	= qp->resp.va +
+					  qp->resp.offset;
 
 		res->first_psn		= req_pkt->psn;
 
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index 74fcd871757d..f426bf30f86a 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -183,6 +183,7 @@ struct rxe_resp_info {
 
 	/* RDMA read / atomic only */
 	u64			va;
+	u64			offset;
 	struct rxe_mr		*mr;
 	u32			resid;
 	u32			rkey;
@@ -480,6 +481,16 @@ static inline u32 mr_rkey(struct rxe_mr *mr)
 	return mr->ibmr.rkey;
 }
 
+static inline struct rxe_pd *mw_pd(struct rxe_mw *mw)
+{
+	return to_rpd(mw->ibmw.pd);
+}
+
+static inline u32 mw_rkey(struct rxe_mw *mw)
+{
+	return mw->ibmw.rkey;
+}
+
 int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name);
 
 void rxe_mc_cleanup(struct rxe_pool_entry *arg);
-- 
2.27.0


      parent reply index

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-21  5:20 [PATCH for-next v3 0/9] RDMA/rxe: Implement memory windows Bob Pearson
2021-04-21  5:20 ` [PATCH for-next v3 1/9] RDMA/rxe: Add bind MW fields to rxe_send_wr Bob Pearson
2021-04-21  5:20 ` [PATCH for-next v3 2/9] RDMA/rxe: Return errors for add index and key Bob Pearson
2021-04-21  5:20 ` [PATCH for-next v3 3/9] RDMA/rxe: Enable MW object pool Bob Pearson
2021-04-21  5:20 ` [PATCH for-next v3 4/9] RDMA/rxe: Add ib_alloc_mw and ib_dealloc_mw verbs Bob Pearson
2021-04-21  5:54   ` Zhu Yanjun
2021-04-21  6:20     ` Leon Romanovsky
2021-04-21  6:26       ` Zhu Yanjun
2021-04-21  5:20 ` [PATCH for-next v3 5/9] RDMA/rxe: Replace WR_REG_MASK by WR_LOCAL_OP_MASK Bob Pearson
2021-04-21  5:20 ` [PATCH for-next v3 6/9] RDMA/rxe: Move local ops to subroutine Bob Pearson
2021-04-21  5:20 ` [PATCH for-next v3 7/9] RDMA/rxe: Add support for bind MW work requests Bob Pearson
2021-04-21  9:36   ` Zhu Yanjun
2021-04-21 15:21     ` Robert Pearson
2021-04-22  5:33     ` Bob Pearson
2021-04-21  5:20 ` [PATCH for-next v3 8/9] RDMA/rxe: Implement invalidate MW operations Bob Pearson
2021-04-21  5:20 ` Bob Pearson [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210421052015.4546-10-rpearson@hpe.com \
    --to=rpearsonhpe@gmail.com \
    --cc=jgg@nvidia.com \
    --cc=linux-rdma@vger.kernel.org \
    --cc=rpearson@hpe.com \
    --cc=zyjzyj2000@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-RDMA Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-rdma/0 linux-rdma/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-rdma linux-rdma/ https://lore.kernel.org/linux-rdma \
		linux-rdma@vger.kernel.org
	public-inbox-index linux-rdma

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-rdma


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git