From: Karsten Graul <kgraul@linux.ibm.com>
Subject: net/smc: add SMC-D shutdown signal
Patch-mainline: v4.20-rc4
Git-commit: 0512f69e388c963dbe955d4bd9ae0f7d88d2dc54
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: add SMC-D shutdown signal
When a SMC-D link group is freed, a shutdown signal should be sent to
the peer to indicate that the link group is invalid. This patch adds the
shutdown signal to the SMC code.
Signed-off-by: Hans Wippel <hwippel@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/smc_core.c | 10 ++++++++--
net/smc/smc_core.h | 3 ++-
net/smc/smc_ism.c | 43 ++++++++++++++++++++++++++++++++-----------
net/smc/smc_ism.h | 1 +
4 files changed, 43 insertions(+), 14 deletions(-)
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -183,6 +183,8 @@ free:
if (!lgr->is_smcd && lnk->state != SMC_LNK_INACTIVE)
smc_llc_link_inactive(lnk);
+ if (lgr->is_smcd)
+ smc_ism_signal_shutdown(lgr);
smc_lgr_free(lgr);
}
}
@@ -484,7 +486,7 @@ void smc_port_terminate(struct smc_ib_de
}
/* Called when SMC-D device is terminated or peer is lost */
-void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid)
+void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, unsigned short vlan)
{
struct smc_link_group *lgr, *l;
LIST_HEAD(lgr_free_list);
@@ -494,7 +496,7 @@ void smc_smcd_terminate(struct smcd_dev
list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) {
if (lgr->is_smcd && lgr->smcd == dev &&
(!peer_gid || lgr->peer_gid == peer_gid) &&
- !list_empty(&lgr->list)) {
+ (vlan == VLAN_VID_MASK || lgr->vlan_id == vlan)) {
__smc_lgr_terminate(lgr);
list_move(&lgr->list, &lgr_free_list);
}
@@ -505,6 +507,8 @@ void smc_smcd_terminate(struct smcd_dev
list_for_each_entry_safe(lgr, l, &lgr_free_list, list) {
list_del_init(&lgr->list);
cancel_delayed_work_sync(&lgr->free_work);
+ if (!peer_gid && vlan == VLAN_VID_MASK) /* dev terminated? */
+ smc_ism_signal_shutdown(lgr);
smc_lgr_free(lgr);
}
}
@@ -1025,6 +1029,8 @@ void smc_core_exit(void)
smc_llc_link_inactive(lnk);
}
cancel_delayed_work_sync(&lgr->free_work);
+ if (lgr->is_smcd)
+ smc_ism_signal_shutdown(lgr);
smc_lgr_free(lgr); /* free link group */
}
}
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -246,7 +246,8 @@ void smc_lgr_free(struct smc_link_group
void smc_lgr_forget(struct smc_link_group *lgr);
void smc_lgr_terminate(struct smc_link_group *lgr);
void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport);
-void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid);
+void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid,
+ unsigned short vlan);
int smc_buf_create(struct smc_sock *smc, bool is_smcd);
int smc_uncompress_bufsize(u8 compressed);
int smc_rmb_rtoken_handling(struct smc_connection *conn,
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -187,22 +187,28 @@ struct smc_ism_event_work {
#define ISM_EVENT_REQUEST 0x0001
#define ISM_EVENT_RESPONSE 0x0002
#define ISM_EVENT_REQUEST_IR 0x00000001
+#define ISM_EVENT_CODE_SHUTDOWN 0x80
#define ISM_EVENT_CODE_TESTLINK 0x83
+union smcd_sw_event_info {
+ u64 info;
+ struct {
+ u8 uid[SMC_LGR_ID_SIZE];
+ unsigned short vlan_id;
+ u16 code;
+ };
+};
+
static void smcd_handle_sw_event(struct smc_ism_event_work *wrk)
{
- union {
- u64 info;
- struct {
- u32 uid;
- unsigned short vlanid;
- u16 code;
- };
- } ev_info;
+ union smcd_sw_event_info ev_info;
+ ev_info.info = wrk->event.info;
switch (wrk->event.code) {
+ case ISM_EVENT_CODE_SHUTDOWN: /* Peer shut down DMBs */
+ smc_smcd_terminate(wrk->smcd, wrk->event.tok, ev_info.vlan_id);
+ break;
case ISM_EVENT_CODE_TESTLINK: /* Activity timer */
- ev_info.info = wrk->event.info;
if (ev_info.code == ISM_EVENT_REQUEST) {
ev_info.code = ISM_EVENT_RESPONSE;
wrk->smcd->ops->signal_event(wrk->smcd,
@@ -215,6 +221,21 @@ static void smcd_handle_sw_event(struct
}
}
+int smc_ism_signal_shutdown(struct smc_link_group *lgr)
+{
+ int rc;
+ union smcd_sw_event_info ev_info;
+
+ memcpy(ev_info.uid, lgr->id, SMC_LGR_ID_SIZE);
+ ev_info.vlan_id = lgr->vlan_id;
+ ev_info.code = ISM_EVENT_REQUEST;
+ rc = lgr->smcd->ops->signal_event(lgr->smcd, lgr->peer_gid,
+ ISM_EVENT_REQUEST_IR,
+ ISM_EVENT_CODE_SHUTDOWN,
+ ev_info.info);
+ return rc;
+}
+
/* worker for SMC-D events */
static void smc_ism_event_work(struct work_struct *work)
{
@@ -223,7 +244,7 @@ static void smc_ism_event_work(struct wo
switch (wrk->event.type) {
case ISM_EVENT_GID: /* GID event, token is peer GID */
- smc_smcd_terminate(wrk->smcd, wrk->event.tok);
+ smc_smcd_terminate(wrk->smcd, wrk->event.tok, VLAN_VID_MASK);
break;
case ISM_EVENT_DMB:
break;
@@ -289,7 +310,7 @@ void smcd_unregister_dev(struct smcd_dev
spin_unlock(&smcd_dev_list.lock);
flush_workqueue(smcd->event_wq);
destroy_workqueue(smcd->event_wq);
- smc_smcd_terminate(smcd, 0);
+ smc_smcd_terminate(smcd, 0, VLAN_VID_MASK);
device_del(&smcd->dev);
}
--- a/net/smc/smc_ism.h
+++ b/net/smc/smc_ism.h
@@ -45,4 +45,5 @@ int smc_ism_register_dmb(struct smc_link
int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc);
int smc_ism_write(struct smcd_dev *dev, const struct smc_ism_position *pos,
void *data, size_t len);
+int smc_ism_signal_shutdown(struct smc_link_group *lgr);
#endif