From: Karsten Graul <kgraul@linux.ibm.com>
Subject: net/smc: use queue pair number when matching link group
Patch-mainline: v4.20-rc4
Git-commit: ee05ff7af26509f39360534a5225ee714416cdfd
References: FATE#325698, LTC#167867, bsc#1113481

Description:  net/smc: bugfix and compatibility patches
Symptom:      Random hangs in smc processing:
                user space application hangs in socket send() or recv() call or
                does never get a notification from a select() call.
              Missing compatibility to other platforms:
                confirm rkey and delete rkey processing is required by the
                design, but delete rkey processing is missing. This leads to
                protocol failures when communicating with other platforms like
                zOS. The SMC-D shutdown signal support is missing, so there is
                no detection if the remote peer closed the link group.
              Broken administration of available WR send payload buffers due to
              a use-after-free condition.
Problem:      Misbehaviour regarding the user space api can lead to hang
              situations. SMC is not fully compatible to some other platforms
              due to missing rkey processing and SMC-D shutdown signal support.
Solution:     Fixed protocoll deficiencies by implementing the required rkey
              processing. For SMC-D, the cursors are now handled atomically to
              handle parallel modifications. The SMC-D shutdown signal is now
              processed when received and sent to the remote peer if needed.
              Prereq patches are included.
Reproduction: Run SMC on a loaded system against zOS as peer system.

Upstream-Description:

              net/smc: use queue pair number when matching link group

              When searching for an existing link group the queue pair number is also
              to be taken into consideration. When the SMC server sends a new number
              in a CLC packet (keeping all other values equal) then a new link group
              is to be created on the SMC client side.

              Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
              Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
              Signed-off-by: David S. Miller <davem@davemloft.net>


Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Acked-by: Petr Tesarik <ptesarik@suse.com>
---
 net/smc/af_smc.c   |    9 +++++----
 net/smc/smc_core.c |   10 ++++++----
 net/smc/smc_core.h |    2 +-
 3 files changed, 12 insertions(+), 9 deletions(-)

--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -549,7 +549,8 @@ static int smc_connect_rdma(struct smc_s
 
 	mutex_lock(&smc_create_lgr_pending);
 	local_contact = smc_conn_create(smc, false, aclc->hdr.flag, ibdev,
-					ibport, &aclc->lcl, NULL, 0);
+					ibport, ntoh24(aclc->qpn), &aclc->lcl,
+					NULL, 0);
 	if (local_contact < 0) {
 		if (local_contact == -ENOMEM)
 			reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
@@ -620,7 +621,7 @@ static int smc_connect_ism(struct smc_so
 	int rc = 0;
 
 	mutex_lock(&smc_create_lgr_pending);
-	local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0,
+	local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0, 0,
 					NULL, ismdev, aclc->gid);
 	if (local_contact < 0)
 		return smc_connect_abort(smc, SMC_CLC_DECL_MEM, 0);
@@ -1085,7 +1086,7 @@ static int smc_listen_rdma_init(struct s
 				int *local_contact)
 {
 	/* allocate connection / link group */
-	*local_contact = smc_conn_create(new_smc, false, 0, ibdev, ibport,
+	*local_contact = smc_conn_create(new_smc, false, 0, ibdev, ibport, 0,
 					 &pclc->lcl, NULL, 0);
 	if (*local_contact < 0) {
 		if (*local_contact == -ENOMEM)
@@ -1109,7 +1110,7 @@ static int smc_listen_ism_init(struct sm
 	struct smc_clc_msg_smcd *pclc_smcd;
 
 	pclc_smcd = smc_get_clc_msg_smcd(pclc);
-	*local_contact = smc_conn_create(new_smc, true, 0, NULL, 0, NULL,
+	*local_contact = smc_conn_create(new_smc, true, 0, NULL, 0, 0, NULL,
 					 ismdev, pclc_smcd->gid);
 	if (*local_contact < 0) {
 		if (*local_contact == -ENOMEM)
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -558,7 +558,7 @@ out:
 
 static bool smcr_lgr_match(struct smc_link_group *lgr,
 			   struct smc_clc_msg_local *lcl,
-			   enum smc_lgr_role role)
+			   enum smc_lgr_role role, u32 clcqpn)
 {
 	return !memcmp(lgr->peer_systemid, lcl->id_for_peer,
 		       SMC_SYSTEMID_LEN) &&
@@ -566,7 +566,9 @@ static bool smcr_lgr_match(struct smc_li
 			SMC_GID_SIZE) &&
 		!memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_mac, lcl->mac,
 			sizeof(lcl->mac)) &&
-		lgr->role == role;
+		lgr->role == role &&
+		(lgr->role == SMC_SERV ||
+		 lgr->lnk[SMC_SINGLE_LINK].peer_qpn == clcqpn);
 }
 
 static bool smcd_lgr_match(struct smc_link_group *lgr,
@@ -577,7 +579,7 @@ static bool smcd_lgr_match(struct smc_li
 
 /* create a new SMC connection (and a new link group if necessary) */
 int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
-		    struct smc_ib_device *smcibdev, u8 ibport,
+		    struct smc_ib_device *smcibdev, u8 ibport, u32 clcqpn,
 		    struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
 		    u64 peer_gid)
 {
@@ -602,7 +604,7 @@ int smc_conn_create(struct smc_sock *smc
 	list_for_each_entry(lgr, &smc_lgr_list.list, list) {
 		write_lock_bh(&lgr->conns_lock);
 		if ((is_smcd ? smcd_lgr_match(lgr, smcd, peer_gid) :
-		     smcr_lgr_match(lgr, lcl, role)) &&
+		     smcr_lgr_match(lgr, lcl, role, clcqpn)) &&
 		    !lgr->sync_err &&
 		    lgr->vlan_id == vlan_id &&
 		    (role == SMC_CLNT ||
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -261,7 +261,7 @@ int smc_vlan_by_tcpsk(struct socket *clc
 
 void smc_conn_free(struct smc_connection *conn);
 int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
-		    struct smc_ib_device *smcibdev, u8 ibport,
+		    struct smc_ib_device *smcibdev, u8 ibport, u32 clcqpn,
 		    struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
 		    u64 peer_gid);
 void smcd_conn_free(struct smc_connection *conn);