[PATCH v7 5/8] RDMA/rxe: Make requester support atomic write on RC service

[PATCH v7 5/8] RDMA/rxe: Make requester support atomic write on RC service

[Xiao Yang]

Make requester process and send an atomic write request on RC service.

Signed-off-by: Xiao Yang <yangx.jy@fujitsu.com>
---
 drivers/infiniband/sw/rxe/rxe_req.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index 4d45f508392f..2713e9058922 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -258,6 +258,10 @@ static int next_opcode_rc(struct rxe_qp *qp, u32 opcode, int fits)
 		else
 			return fits ? IB_OPCODE_RC_SEND_ONLY_WITH_INVALIDATE :
 				IB_OPCODE_RC_SEND_FIRST;
+
+	case IB_WR_ATOMIC_WRITE:
+		return IB_OPCODE_RC_ATOMIC_WRITE;
+
 	case IB_WR_REG_MR:
 	case IB_WR_LOCAL_INV:
 		return opcode;
@@ -486,6 +490,11 @@ static int finish_packet(struct rxe_qp *qp, struct rxe_av *av,
 		}
 	}
 
+	if (pkt->mask & RXE_ATOMIC_WRITE_MASK) {
+		memcpy(payload_addr(pkt), wqe->dma.atomic_wr, payload);
+		wqe->dma.resid -= payload;
+	}
+
 	return 0;
 }
 
@@ -709,13 +718,15 @@ int rxe_requester(void *arg)
 	}
 
 	mask = rxe_opcode[opcode].mask;
-	if (unlikely(mask & RXE_READ_OR_ATOMIC_MASK)) {
+	if (unlikely(mask & (RXE_READ_OR_ATOMIC_MASK |
+			RXE_ATOMIC_WRITE_MASK))) {
 		if (check_init_depth(qp, wqe))
 			goto exit;
 	}
 
 	mtu = get_mtu(qp);
-	payload = (mask & RXE_WRITE_OR_SEND_MASK) ? wqe->dma.resid : 0;
+	payload = (mask & (RXE_WRITE_OR_SEND_MASK | RXE_ATOMIC_WRITE_MASK)) ?
+			wqe->dma.resid : 0;
 	if (payload > mtu) {
 		if (qp_type(qp) == IB_QPT_UD) {
 			/* C10-93.1.1: If the total sum of all the buffer lengths specified for a
-- 
2.34.1

[PATCH v7 6/8] RDMA/rxe: Make responder support atomic write on RC service

[Xiao Yang]

Make responder process an atomic write request and send a read response
on RC service.

Signed-off-by: Xiao Yang <yangx.jy@fujitsu.com>
---
 drivers/infiniband/sw/rxe/rxe_resp.c | 84 ++++++++++++++++++++++++++--
 1 file changed, 79 insertions(+), 5 deletions(-)

diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 6761bcd1d4d8..6ac544477f3f 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -22,6 +22,7 @@ enum resp_states {
 	RESPST_EXECUTE,
 	RESPST_READ_REPLY,
 	RESPST_ATOMIC_REPLY,
+	RESPST_ATOMIC_WRITE_REPLY,
 	RESPST_COMPLETE,
 	RESPST_ACKNOWLEDGE,
 	RESPST_CLEANUP,
@@ -57,6 +58,7 @@ static char *resp_state_name[] = {
 	[RESPST_EXECUTE]			= "EXECUTE",
 	[RESPST_READ_REPLY]			= "READ_REPLY",
 	[RESPST_ATOMIC_REPLY]			= "ATOMIC_REPLY",
+	[RESPST_ATOMIC_WRITE_REPLY]		= "ATOMIC_WRITE_REPLY",
 	[RESPST_COMPLETE]			= "COMPLETE",
 	[RESPST_ACKNOWLEDGE]			= "ACKNOWLEDGE",
 	[RESPST_CLEANUP]			= "CLEANUP",
@@ -263,7 +265,7 @@ static enum resp_states check_op_valid(struct rxe_qp *qp,
 	case IB_QPT_RC:
 		if (((pkt->mask & RXE_READ_MASK) &&
 		     !(qp->attr.qp_access_flags & IB_ACCESS_REMOTE_READ)) ||
-		    ((pkt->mask & RXE_WRITE_MASK) &&
+		    ((pkt->mask & (RXE_WRITE_MASK | RXE_ATOMIC_WRITE_MASK)) &&
 		     !(qp->attr.qp_access_flags & IB_ACCESS_REMOTE_WRITE)) ||
 		    ((pkt->mask & RXE_ATOMIC_MASK) &&
 		     !(qp->attr.qp_access_flags & IB_ACCESS_REMOTE_ATOMIC))) {
@@ -367,7 +369,7 @@ static enum resp_states check_resource(struct rxe_qp *qp,
 		}
 	}
 
-	if (pkt->mask & RXE_READ_OR_ATOMIC_MASK) {
+	if (pkt->mask & (RXE_READ_OR_ATOMIC_MASK | RXE_ATOMIC_WRITE_MASK)) {
 		/* it is the requesters job to not send
 		 * too many read/atomic ops, we just
 		 * recycle the responder resource queue
@@ -438,7 +440,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 	enum resp_states state;
 	int access;
 
-	if (pkt->mask & RXE_READ_OR_WRITE_MASK) {
+	if (pkt->mask & (RXE_READ_OR_WRITE_MASK | RXE_ATOMIC_WRITE_MASK)) {
 		if (pkt->mask & RXE_RETH_MASK) {
 			qp->resp.va = reth_va(pkt);
 			qp->resp.offset = 0;
@@ -504,7 +506,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 		goto err;
 	}
 
-	if (pkt->mask & RXE_WRITE_MASK)	 {
+	if (pkt->mask & (RXE_WRITE_MASK | RXE_ATOMIC_WRITE_MASK)) {
 		if (resid > mtu) {
 			if (pktlen != mtu || bth_pad(pkt)) {
 				state = RESPST_ERR_LENGTH;
@@ -604,6 +606,7 @@ static struct resp_res *rxe_prepare_res(struct rxe_qp *qp,
 		res->state = rdatm_res_state_new;
 		break;
 	case RXE_ATOMIC_MASK:
+	case RXE_ATOMIC_WRITE_MASK:
 		res->first_psn = pkt->psn;
 		res->last_psn = pkt->psn;
 		res->cur_psn = pkt->psn;
@@ -673,6 +676,55 @@ static enum resp_states atomic_reply(struct rxe_qp *qp,
 	return ret;
 }
 
+static enum resp_states atomic_write_reply(struct rxe_qp *qp,
+						struct rxe_pkt_info *pkt)
+{
+	u64 src, *dst;
+	struct resp_res *res = qp->resp.res;
+	struct rxe_mr *mr = qp->resp.mr;
+	int payload = payload_size(pkt);
+
+	if (!res) {
+		res = rxe_prepare_res(qp, pkt, RXE_ATOMIC_WRITE_MASK);
+		qp->resp.res = res;
+	}
+
+	if (!res->replay) {
+#ifdef CONFIG_64BIT
+		if (mr->state != RXE_MR_STATE_VALID)
+			return RESPST_ERR_RKEY_VIOLATION;
+
+		memcpy(&src, payload_addr(pkt), payload);
+
+		dst = iova_to_vaddr(mr, qp->resp.va + qp->resp.offset, payload);
+		/* check vaddr is 8 bytes aligned. */
+		if (!dst || (uintptr_t)dst & 7)
+			return RESPST_ERR_MISALIGNED_ATOMIC;
+
+		/* Do atomic write after all prior operations have completed */
+		smp_store_release(dst, src);
+
+		/* decrease resp.resid to zero */
+		qp->resp.resid -= sizeof(payload);
+
+		qp->resp.msn++;
+
+		/* next expected psn, read handles this separately */
+		qp->resp.psn = (pkt->psn + 1) & BTH_PSN_MASK;
+		qp->resp.ack_psn = qp->resp.psn;
+
+		qp->resp.opcode = pkt->opcode;
+		qp->resp.status = IB_WC_SUCCESS;
+
+		return RESPST_ACKNOWLEDGE;
+#else
+		return RESPST_ERR_UNSUPPORTED_OPCODE;
+#endif /* CONFIG_64BIT */
+	}
+
+	return RESPST_ACKNOWLEDGE;
+}
+
 static struct sk_buff *prepare_ack_packet(struct rxe_qp *qp,
 					  struct rxe_pkt_info *ack,
 					  int opcode,
@@ -912,6 +964,8 @@ static enum resp_states execute(struct rxe_qp *qp, struct rxe_pkt_info *pkt)
 		return RESPST_READ_REPLY;
 	} else if (pkt->mask & RXE_ATOMIC_MASK) {
 		return RESPST_ATOMIC_REPLY;
+	} else if (pkt->mask & RXE_ATOMIC_WRITE_MASK) {
+		return RESPST_ATOMIC_WRITE_REPLY;
 	} else {
 		/* Unreachable */
 		WARN_ON_ONCE(1);
@@ -1085,6 +1139,19 @@ static int send_atomic_ack(struct rxe_qp *qp, u8 syndrome, u32 psn)
 	return ret;
 }
 
+static int send_read_response_ack(struct rxe_qp *qp, u8 syndrome, u32 psn)
+{
+	int ret = send_common_ack(qp, syndrome, psn,
+			IB_OPCODE_RC_RDMA_READ_RESPONSE_ONLY,
+			"RDMA READ response of length zero ACK");
+
+	/* have to clear this since it is used to trigger
+	 * long read replies
+	 */
+	qp->resp.res = NULL;
+	return ret;
+}
+
 static enum resp_states acknowledge(struct rxe_qp *qp,
 				    struct rxe_pkt_info *pkt)
 {
@@ -1095,6 +1162,8 @@ static enum resp_states acknowledge(struct rxe_qp *qp,
 		send_ack(qp, qp->resp.aeth_syndrome, pkt->psn);
 	else if (pkt->mask & RXE_ATOMIC_MASK)
 		send_atomic_ack(qp, AETH_ACK_UNLIMITED, pkt->psn);
+	else if (pkt->mask & RXE_ATOMIC_WRITE_MASK)
+		send_read_response_ack(qp, AETH_ACK_UNLIMITED, pkt->psn);
 	else if (bth_ack(pkt))
 		send_ack(qp, AETH_ACK_UNLIMITED, pkt->psn);
 
@@ -1206,7 +1275,9 @@ static enum resp_states duplicate_request(struct rxe_qp *qp,
 			res->replay = 1;
 			res->cur_psn = pkt->psn;
 			qp->resp.res = res;
-			rc = RESPST_ATOMIC_REPLY;
+			rc = pkt->mask & RXE_ATOMIC_MASK ?
+					RESPST_ATOMIC_REPLY :
+					RESPST_ATOMIC_WRITE_REPLY;
 			goto out;
 		}
 
@@ -1343,6 +1414,9 @@ int rxe_responder(void *arg)
 		case RESPST_ATOMIC_REPLY:
 			state = atomic_reply(qp, pkt);
 			break;
+		case RESPST_ATOMIC_WRITE_REPLY:
+			state = atomic_write_reply(qp, pkt);
+			break;
 		case RESPST_ACKNOWLEDGE:
 			state = acknowledge(qp, pkt);
 			break;
-- 
2.34.1

[PATCH v7 7/8] RDMA/rxe: Implement atomic write completion

[Xiao Yang]

Generate an atomic write completion when the atomic write request
has been finished.

Signed-off-by: Xiao Yang <yangx.jy@fujitsu.com>
---
 drivers/infiniband/sw/rxe/rxe_comp.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
index 4dca4f8bbb5a..1c525325e271 100644
--- a/drivers/infiniband/sw/rxe/rxe_comp.c
+++ b/drivers/infiniband/sw/rxe/rxe_comp.c
@@ -104,6 +104,7 @@ static enum ib_wc_opcode wr_to_wc_opcode(enum ib_wr_opcode opcode)
 	case IB_WR_LOCAL_INV:			return IB_WC_LOCAL_INV;
 	case IB_WR_REG_MR:			return IB_WC_REG_MR;
 	case IB_WR_BIND_MW:			return IB_WC_BIND_MW;
+	case IB_WR_ATOMIC_WRITE:		return IB_WC_ATOMIC_WRITE;
 
 	default:
 		return 0xff;
@@ -269,6 +270,9 @@ static inline enum comp_state check_ack(struct rxe_qp *qp,
 		if ((syn & AETH_TYPE_MASK) != AETH_ACK)
 			return COMPST_ERROR;
 
+		if (wqe->wr.opcode == IB_WR_ATOMIC_WRITE)
+			return COMPST_WRITE_SEND;
+
 		fallthrough;
 		/* (IB_OPCODE_RC_RDMA_READ_RESPONSE_MIDDLE doesn't have an AETH)
 		 */
-- 
2.34.1

[PATCH v7 8/8] RDMA/rxe: Enable atomic write capability for rxe device

[Xiao Yang]

The capability shows that rxe device supports atomic write operation.

Signed-off-by: Xiao Yang <yangx.jy@fujitsu.com>
---
 drivers/infiniband/sw/rxe/rxe_param.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/infiniband/sw/rxe/rxe_param.h b/drivers/infiniband/sw/rxe/rxe_param.h
index 86c7a8bf3cbb..bbc88cd71d95 100644
--- a/drivers/infiniband/sw/rxe/rxe_param.h
+++ b/drivers/infiniband/sw/rxe/rxe_param.h
@@ -51,7 +51,12 @@ enum rxe_device_param {
 					| IB_DEVICE_SRQ_RESIZE
 					| IB_DEVICE_MEM_MGT_EXTENSIONS
 					| IB_DEVICE_MEM_WINDOW
+#ifdef CONFIG_64BIT
+					| IB_DEVICE_MEM_WINDOW_TYPE_2B
+					| IB_DEVICE_ATOMIC_WRITE,
+#else
 					| IB_DEVICE_MEM_WINDOW_TYPE_2B,
+#endif /* CONFIG_64BIT */
 	RXE_MAX_SGE			= 32,
 	RXE_MAX_WQE_SIZE		= sizeof(struct rxe_send_wqe) +
 					  sizeof(struct ib_sge) * RXE_MAX_SGE,
-- 
2.34.1

Re: [PATCH v7 6/8] RDMA/rxe: Make responder support atomic write on RC service

[Guenter Roeck]

On Thu, Dec 01, 2022 at 02:39:26PM +0000, Xiao Yang wrote:
> Make responder process an atomic write request and send a read response
> on RC service.
> 
> Signed-off-by: Xiao Yang <yangx.jy@fujitsu.com>
> ---

On all 32-bit builds with CONFIG_WERROR enabled:

Error log:
drivers/infiniband/sw/rxe/rxe_resp.c: In function 'atomic_write_reply':
drivers/infiniband/sw/rxe/rxe_resp.c:794:13: error: unused variable 'payload' [-Werror=unused-variable]
  794 |         int payload = payload_size(pkt);
      |             ^~~~~~~
drivers/infiniband/sw/rxe/rxe_resp.c:793:24: error: unused variable 'mr' [-Werror=unused-variable]
  793 |         struct rxe_mr *mr = qp->resp.mr;
      |                        ^~
drivers/infiniband/sw/rxe/rxe_resp.c:791:19: error: unused variable 'dst' [-Werror=unused-variable]
  791 |         u64 src, *dst;
      |                   ^~~
drivers/infiniband/sw/rxe/rxe_resp.c:791:13: error: unused variable 'src' [-Werror=unused-variable]
  791 |         u64 src, *dst;

Guenter

Re: [PATCH v7 6/8] RDMA/rxe: Make responder support atomic write on RC service

[Jason Gunthorpe]

On Thu, Dec 15, 2022 at 07:19:24AM -0800, Guenter Roeck wrote:
> On Thu, Dec 01, 2022 at 02:39:26PM +0000, Xiao Yang wrote:
> > Make responder process an atomic write request and send a read response
> > on RC service.
> > 
> > Signed-off-by: Xiao Yang <yangx.jy@fujitsu.com>
> > ---
> 
> On all 32-bit builds with CONFIG_WERROR enabled:

Why are we only just seeing this now? It has been in linux-next for
long enough?

From 7e708569f7bb5dba6df8342bc2402deda4e2414e Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 15 Dec 2022 11:29:25 -0400
Subject: [PATCH] RDMA/rxe: Fix compile warnings on 32-bit

Move the conditional code into a function, with two varients so it is
harder to make these kinds of mistakes.

 drivers/infiniband/sw/rxe/rxe_resp.c: In function 'atomic_write_reply':
 drivers/infiniband/sw/rxe/rxe_resp.c:794:13: error: unused variable 'payload' [-Werror=unused-variable]
   794 |         int payload = payload_size(pkt);
       |             ^~~~~~~
 drivers/infiniband/sw/rxe/rxe_resp.c:793:24: error: unused variable 'mr' [-Werror=unused-variable]
   793 |         struct rxe_mr *mr = qp->resp.mr;
       |                        ^~
 drivers/infiniband/sw/rxe/rxe_resp.c:791:19: error: unused variable 'dst' [-Werror=unused-variable]
   791 |         u64 src, *dst;
       |                   ^~~
 drivers/infiniband/sw/rxe/rxe_resp.c:791:13: error: unused variable 'src' [-Werror=unused-variable]
   791 |         u64 src, *dst;

Fixes: 034e285f8b99 ("RDMA/rxe: Make responder support atomic write on RC service")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/sw/rxe/rxe_resp.c | 72 +++++++++++++++-------------
 1 file changed, 40 insertions(+), 32 deletions(-)

diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 7a60c7709da045..c74972244f08f5 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -785,53 +785,61 @@ static enum resp_states atomic_reply(struct rxe_qp *qp,
 	return ret;
 }
 
-static enum resp_states atomic_write_reply(struct rxe_qp *qp,
-						struct rxe_pkt_info *pkt)
+#ifdef CONFIG_64BIT
+static enum resp_states do_atomic_write(struct rxe_qp *qp,
+					struct rxe_pkt_info *pkt)
 {
-	u64 src, *dst;
-	struct resp_res *res = qp->resp.res;
 	struct rxe_mr *mr = qp->resp.mr;
 	int payload = payload_size(pkt);
+	u64 src, *dst;
 
-	if (!res) {
-		res = rxe_prepare_res(qp, pkt, RXE_ATOMIC_WRITE_MASK);
-		qp->resp.res = res;
-	}
-
-	if (!res->replay) {
-#ifdef CONFIG_64BIT
-		if (mr->state != RXE_MR_STATE_VALID)
-			return RESPST_ERR_RKEY_VIOLATION;
-
-		memcpy(&src, payload_addr(pkt), payload);
+	if (mr->state != RXE_MR_STATE_VALID)
+		return RESPST_ERR_RKEY_VIOLATION;
 
-		dst = iova_to_vaddr(mr, qp->resp.va + qp->resp.offset, payload);
-		/* check vaddr is 8 bytes aligned. */
-		if (!dst || (uintptr_t)dst & 7)
-			return RESPST_ERR_MISALIGNED_ATOMIC;
+	memcpy(&src, payload_addr(pkt), payload);
 
-		/* Do atomic write after all prior operations have completed */
-		smp_store_release(dst, src);
+	dst = iova_to_vaddr(mr, qp->resp.va + qp->resp.offset, payload);
+	/* check vaddr is 8 bytes aligned. */
+	if (!dst || (uintptr_t)dst & 7)
+		return RESPST_ERR_MISALIGNED_ATOMIC;
 
-		/* decrease resp.resid to zero */
-		qp->resp.resid -= sizeof(payload);
+	/* Do atomic write after all prior operations have completed */
+	smp_store_release(dst, src);
 
-		qp->resp.msn++;
+	/* decrease resp.resid to zero */
+	qp->resp.resid -= sizeof(payload);
 
-		/* next expected psn, read handles this separately */
-		qp->resp.psn = (pkt->psn + 1) & BTH_PSN_MASK;
-		qp->resp.ack_psn = qp->resp.psn;
+	qp->resp.msn++;
 
-		qp->resp.opcode = pkt->opcode;
-		qp->resp.status = IB_WC_SUCCESS;
+	/* next expected psn, read handles this separately */
+	qp->resp.psn = (pkt->psn + 1) & BTH_PSN_MASK;
+	qp->resp.ack_psn = qp->resp.psn;
 
-		return RESPST_ACKNOWLEDGE;
+	qp->resp.opcode = pkt->opcode;
+	qp->resp.status = IB_WC_SUCCESS;
+	return RESPST_ACKNOWLEDGE;
+}
 #else
-		return RESPST_ERR_UNSUPPORTED_OPCODE;
+static enum resp_states do_atomic_write(struct rxe_qp *qp,
+					struct rxe_pkt_info *pkt)
+{
+	return RESPST_ERR_UNSUPPORTED_OPCODE;
+}
 #endif /* CONFIG_64BIT */
+
+static enum resp_states atomic_write_reply(struct rxe_qp *qp,
+					   struct rxe_pkt_info *pkt)
+{
+	struct resp_res *res = qp->resp.res;
+
+	if (!res) {
+		res = rxe_prepare_res(qp, pkt, RXE_ATOMIC_WRITE_MASK);
+		qp->resp.res = res;
 	}
 
-	return RESPST_ACKNOWLEDGE;
+	if (res->replay)
+		return RESPST_ACKNOWLEDGE;
+	return do_atomic_write(qp, pkt);
 }
 
 static struct sk_buff *prepare_ack_packet(struct rxe_qp *qp,
-- 
2.38.2