Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:

 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz
    Augusto von Dentz.

 2) Add GSO partial support to igc, from Sasha Neftin.

 3) Several cleanups and improvements to r8169 from Heiner Kallweit.

 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a
    device self-test. From Andrew Lunn.

 5) Start moving away from custom driver versions, use the globally
    defined kernel version instead, from Leon Romanovsky.

 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin.

 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet.

 8) Add sriov and vf support to hinic, from Luo bin.

 9) Support Media Redundancy Protocol (MRP) in the bridging code, from
    Horatiu Vultur.

10) Support netmap in the nft_nat code, from Pablo Neira Ayuso.

11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina
    Dubroca. Also add ipv6 support for espintcp.

12) Lots of ReST conversions of the networking documentation, from Mauro
    Carvalho Chehab.

13) Support configuration of ethtool rxnfc flows in bcmgenet driver,
    from Doug Berger.

14) Allow to dump cgroup id and filter by it in inet_diag code, from
    Dmitry Yakunin.

15) Add infrastructure to export netlink attribute policies to
    userspace, from Johannes Berg.

16) Several optimizations to sch_fq scheduler, from Eric Dumazet.

17) Fallback to the default qdisc if qdisc init fails because otherwise
    a packet scheduler init failure will make a device inoperative. From
    Jesper Dangaard Brouer.

18) Several RISCV bpf jit optimizations, from Luke Nelson.

19) Correct the return type of the ->ndo_start_xmit() method in several
    drivers, it's netdev_tx_t but many drivers were using
    'int'. From Yunjian Wang.

20) Add an ethtool interface for PHY master/slave config, from Oleksij
    Rempel.

21) Add BPF iterators, from Yonghang Song.

22) Add cable test infrastructure, including ethool interfaces, from
    Andrew Lunn. Marvell PHY driver is the first to support this
    facility.

23) Remove zero-length arrays all over, from Gustavo A. R. Silva.

24) Calculate and maintain an explicit frame size in XDP, from Jesper
    Dangaard Brouer.

25) Add CAP_BPF, from Alexei Starovoitov.

26) Support terse dumps in the packet scheduler, from Vlad Buslov.

27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei.

28) Add devm_register_netdev(), from Bartosz Golaszewski.

29) Minimize qdisc resets, from Cong Wang.

30) Get rid of kernel_getsockopt and kernel_setsockopt in order to
    eliminate set_fs/get_fs calls. From Christoph Hellwig.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits)
  selftests: net: ip_defrag: ignore EPERM
  net_failover: fixed rollback in net_failover_open()
  Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv"
  Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv"
  vmxnet3: allow rx flow hash ops only when rss is enabled
  hinic: add set_channels ethtool_ops support
  selftests/bpf: Add a default $(CXX) value
  tools/bpf: Don't use $(COMPILE.c)
  bpf, selftests: Use bpf_probe_read_kernel
  s390/bpf: Use bcr 0,%0 as tail call nop filler
  s390/bpf: Maintain 8-byte stack alignment
  selftests/bpf: Fix verifier test
  selftests/bpf: Fix sample_cnt shared between two threads
  bpf, selftests: Adapt cls_redirect to call csum_level helper
  bpf: Add csum_level helper for fixing up csum levels
  bpf: Fix up bpf_skb_adjust_room helper's skb csum setting
  sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()
  crypto/chtls: IPv6 support for inline TLS
  Crypto/chcr: Fixes a coccinile check error
  Crypto/chcr: Fixes compilations warnings
  ...

1 files changed, 49 insertions, 13 deletions

diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 337ee52ad3d3..7239ba9b99dc 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -44,6 +44,7 @@ struct smc_wr_tx_pend {	/* control data for a pending send request */
 	struct smc_link		*link;
 	u32			idx;
 	struct smc_wr_tx_pend_priv priv;
+	u8			compl_requested;
 };
 
 /******************************** send queue *********************************/
@@ -61,7 +62,7 @@ static inline bool smc_wr_is_tx_pend(struct smc_link *link)
 }
 
 /* wait till all pending tx work requests on the given link are completed */
-static inline int smc_wr_tx_wait_no_pending_sends(struct smc_link *link)
+int smc_wr_tx_wait_no_pending_sends(struct smc_link *link)
 {
 	if (wait_event_timeout(link->wr_tx_wait, !smc_wr_is_tx_pend(link),
 			       SMC_WR_TX_WAIT_PENDING_TIME))
@@ -103,6 +104,8 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
 	if (pnd_snd_idx == link->wr_tx_cnt)
 		return;
 	link->wr_tx_pends[pnd_snd_idx].wc_status = wc->status;
+	if (link->wr_tx_pends[pnd_snd_idx].compl_requested)
+		complete(&link->wr_tx_compl[pnd_snd_idx]);
 	memcpy(&pnd_snd, &link->wr_tx_pends[pnd_snd_idx], sizeof(pnd_snd));
 	/* clear the full struct smc_wr_tx_pend including .priv */
 	memset(&link->wr_tx_pends[pnd_snd_idx], 0,
@@ -120,8 +123,8 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
 			       sizeof(link->wr_tx_bufs[i]));
 			clear_bit(i, link->wr_tx_mask);
 		}
-		/* terminate connections of this link group abnormally */
-		smc_lgr_terminate_sched(smc_get_lgr(link));
+		/* terminate link */
+		smcr_link_down_cond_sched(link);
 	}
 	if (pnd_snd.handler)
 		pnd_snd.handler(&pnd_snd.priv, link, wc->status);
@@ -207,13 +210,13 @@ int smc_wr_tx_get_free_slot(struct smc_link *link,
 	} else {
 		rc = wait_event_interruptible_timeout(
 			link->wr_tx_wait,
-			link->state == SMC_LNK_INACTIVE ||
+			!smc_link_usable(link) ||
 			lgr->terminating ||
 			(smc_wr_tx_get_free_slot_index(link, &idx) != -EBUSY),
 			SMC_WR_TX_WAIT_FREE_SLOT_TIME);
 		if (!rc) {
-			/* timeout - terminate connections */
-			smc_lgr_terminate_sched(lgr);
+			/* timeout - terminate link */
+			smcr_link_down_cond_sched(link);
 			return -EPIPE;
 		}
 		if (idx == link->wr_tx_cnt)
@@ -270,11 +273,38 @@ int smc_wr_tx_send(struct smc_link *link, struct smc_wr_tx_pend_priv *priv)
 	rc = ib_post_send(link->roce_qp, &link->wr_tx_ibs[pend->idx], NULL);
 	if (rc) {
 		smc_wr_tx_put_slot(link, priv);
-		smc_lgr_terminate_sched(smc_get_lgr(link));
+		smcr_link_down_cond_sched(link);
 	}
 	return rc;
 }
 
+/* Send prepared WR slot via ib_post_send and wait for send completion
+ * notification.
+ * @priv: pointer to smc_wr_tx_pend_priv identifying prepared message buffer
+ */
+int smc_wr_tx_send_wait(struct smc_link *link, struct smc_wr_tx_pend_priv *priv,
+			unsigned long timeout)
+{
+	struct smc_wr_tx_pend *pend;
+	int rc;
+
+	pend = container_of(priv, struct smc_wr_tx_pend, priv);
+	pend->compl_requested = 1;
+	init_completion(&link->wr_tx_compl[pend->idx]);
+
+	rc = smc_wr_tx_send(link, priv);
+	if (rc)
+		return rc;
+	/* wait for completion by smc_wr_tx_process_cqe() */
+	rc = wait_for_completion_interruptible_timeout(
+					&link->wr_tx_compl[pend->idx], timeout);
+	if (rc <= 0)
+		rc = -ENODATA;
+	if (rc > 0)
+		rc = 0;
+	return rc;
+}
+
 /* Register a memory region and wait for result. */
 int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr)
 {
@@ -294,8 +324,8 @@ int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr)
 					      (link->wr_reg_state != POSTED),
 					      SMC_WR_REG_MR_WAIT_TIME);
 	if (!rc) {
-		/* timeout - terminate connections */
-		smc_lgr_terminate_sched(smc_get_lgr(link));
+		/* timeout - terminate link */
+		smcr_link_down_cond_sched(link);
 		return -EPIPE;
 	}
 	if (rc == -ERESTARTSYS)
@@ -393,10 +423,7 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num)
 			case IB_WC_RETRY_EXC_ERR:
 			case IB_WC_RNR_RETRY_EXC_ERR:
 			case IB_WC_WR_FLUSH_ERR:
-				/* terminate connections of this link group
-				 * abnormally
-				 */
-				smc_lgr_terminate_sched(smc_get_lgr(link));
+				smcr_link_down_cond_sched(link);
 				break;
 			default:
 				smc_wr_rx_post(link); /* refill WR RX */
@@ -558,6 +585,8 @@ void smc_wr_free_link(struct smc_link *lnk)
 
 void smc_wr_free_link_mem(struct smc_link *lnk)
 {
+	kfree(lnk->wr_tx_compl);
+	lnk->wr_tx_compl = NULL;
 	kfree(lnk->wr_tx_pends);
 	lnk->wr_tx_pends = NULL;
 	kfree(lnk->wr_tx_mask);
@@ -628,8 +657,15 @@ int smc_wr_alloc_link_mem(struct smc_link *link)
 				    GFP_KERNEL);
 	if (!link->wr_tx_pends)
 		goto no_mem_wr_tx_mask;
+	link->wr_tx_compl = kcalloc(SMC_WR_BUF_CNT,
+				    sizeof(link->wr_tx_compl[0]),
+				    GFP_KERNEL);
+	if (!link->wr_tx_compl)
+		goto no_mem_wr_tx_pends;
 	return 0;
 
+no_mem_wr_tx_pends:
+	kfree(link->wr_tx_pends);
 no_mem_wr_tx_mask:
 	kfree(link->wr_tx_mask);
 no_mem_wr_rx_sges: