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

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

1 files changed, 205 insertions, 37 deletions

diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index ea4b21981b4b..5800a6b43d83 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -214,12 +214,11 @@ int smc_llc_send_confirm_link(struct smc_link *link, u8 mac[],
 	return rc;
 }
 
-/* send ADD LINK request or response */
-int smc_llc_send_add_link(struct smc_link *link, u8 mac[],
-			  union ib_gid *gid,
-			  enum smc_llc_reqresp reqresp)
+/* send LLC confirm rkey request */
+static int smc_llc_send_confirm_rkey(struct smc_link *link,
+				     struct smc_buf_desc *rmb_desc)
 {
-	struct smc_llc_msg_add_link *addllc;
+	struct smc_llc_msg_confirm_rkey *rkeyllc;
 	struct smc_wr_tx_pend_priv *pend;
 	struct smc_wr_buf *wr_buf;
 	int rc;
@@ -227,7 +226,25 @@ int smc_llc_send_add_link(struct smc_link *link, u8 mac[],
 	rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
 	if (rc)
 		return rc;
-	addllc = (struct smc_llc_msg_add_link *)wr_buf;
+	rkeyllc = (struct smc_llc_msg_confirm_rkey *)wr_buf;
+	memset(rkeyllc, 0, sizeof(*rkeyllc));
+	rkeyllc->hd.common.type = SMC_LLC_CONFIRM_RKEY;
+	rkeyllc->hd.length = sizeof(struct smc_llc_msg_confirm_rkey);
+	rkeyllc->rtoken[0].rmb_key =
+		htonl(rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+	rkeyllc->rtoken[0].rmb_vaddr = cpu_to_be64(
+		(u64)sg_dma_address(rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
+	/* send llc message */
+	rc = smc_wr_tx_send(link, pend);
+	return rc;
+}
+
+/* prepare an add link message */
+static void smc_llc_prep_add_link(struct smc_llc_msg_add_link *addllc,
+				  struct smc_link *link, u8 mac[],
+				  union ib_gid *gid,
+				  enum smc_llc_reqresp reqresp)
+{
 	memset(addllc, 0, sizeof(*addllc));
 	addllc->hd.common.type = SMC_LLC_ADD_LINK;
 	addllc->hd.length = sizeof(struct smc_llc_msg_add_link);
@@ -239,16 +256,14 @@ int smc_llc_send_add_link(struct smc_link *link, u8 mac[],
 	}
 	memcpy(addllc->sender_mac, mac, ETH_ALEN);
 	memcpy(addllc->sender_gid, gid, SMC_GID_SIZE);
-	/* send llc message */
-	rc = smc_wr_tx_send(link, pend);
-	return rc;
 }
 
-/* send DELETE LINK request or response */
-int smc_llc_send_delete_link(struct smc_link *link,
-			     enum smc_llc_reqresp reqresp)
+/* send ADD LINK request or response */
+int smc_llc_send_add_link(struct smc_link *link, u8 mac[],
+			  union ib_gid *gid,
+			  enum smc_llc_reqresp reqresp)
 {
-	struct smc_llc_msg_del_link *delllc;
+	struct smc_llc_msg_add_link *addllc;
 	struct smc_wr_tx_pend_priv *pend;
 	struct smc_wr_buf *wr_buf;
 	int rc;
@@ -256,7 +271,18 @@ int smc_llc_send_delete_link(struct smc_link *link,
 	rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
 	if (rc)
 		return rc;
-	delllc = (struct smc_llc_msg_del_link *)wr_buf;
+	addllc = (struct smc_llc_msg_add_link *)wr_buf;
+	smc_llc_prep_add_link(addllc, link, mac, gid, reqresp);
+	/* send llc message */
+	rc = smc_wr_tx_send(link, pend);
+	return rc;
+}
+
+/* prepare a delete link message */
+static void smc_llc_prep_delete_link(struct smc_llc_msg_del_link *delllc,
+				     struct smc_link *link,
+				     enum smc_llc_reqresp reqresp)
+{
 	memset(delllc, 0, sizeof(*delllc));
 	delllc->hd.common.type = SMC_LLC_DELETE_LINK;
 	delllc->hd.length = sizeof(struct smc_llc_msg_add_link);
@@ -266,14 +292,29 @@ int smc_llc_send_delete_link(struct smc_link *link,
 	delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ALL;
 	delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY;
 	delllc->link_num = link->link_id;
+}
+
+/* send DELETE LINK request or response */
+int smc_llc_send_delete_link(struct smc_link *link,
+			     enum smc_llc_reqresp reqresp)
+{
+	struct smc_llc_msg_del_link *delllc;
+	struct smc_wr_tx_pend_priv *pend;
+	struct smc_wr_buf *wr_buf;
+	int rc;
+
+	rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
+	if (rc)
+		return rc;
+	delllc = (struct smc_llc_msg_del_link *)wr_buf;
+	smc_llc_prep_delete_link(delllc, link, reqresp);
 	/* send llc message */
 	rc = smc_wr_tx_send(link, pend);
 	return rc;
 }
 
-/* send LLC test link request or response */
-int smc_llc_send_test_link(struct smc_link *link, u8 user_data[16],
-			   enum smc_llc_reqresp reqresp)
+/* send LLC test link request */
+static int smc_llc_send_test_link(struct smc_link *link, u8 user_data[16])
 {
 	struct smc_llc_msg_test_link *testllc;
 	struct smc_wr_tx_pend_priv *pend;
@@ -287,28 +328,52 @@ int smc_llc_send_test_link(struct smc_link *link, u8 user_data[16],
 	memset(testllc, 0, sizeof(*testllc));
 	testllc->hd.common.type = SMC_LLC_TEST_LINK;
 	testllc->hd.length = sizeof(struct smc_llc_msg_test_link);
-	if (reqresp == SMC_LLC_RESP)
-		testllc->hd.flags |= SMC_LLC_FLAG_RESP;
 	memcpy(testllc->user_data, user_data, sizeof(testllc->user_data));
 	/* send llc message */
 	rc = smc_wr_tx_send(link, pend);
 	return rc;
 }
 
-/* send a prepared message */
-static int smc_llc_send_message(struct smc_link *link, void *llcbuf, int llclen)
+struct smc_llc_send_work {
+	struct work_struct work;
+	struct smc_link *link;
+	int llclen;
+	union smc_llc_msg llcbuf;
+};
+
+/* worker that sends a prepared message */
+static void smc_llc_send_message_work(struct work_struct *work)
 {
+	struct smc_llc_send_work *llcwrk = container_of(work,
+						struct smc_llc_send_work, work);
 	struct smc_wr_tx_pend_priv *pend;
 	struct smc_wr_buf *wr_buf;
 	int rc;
 
-	rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
+	if (llcwrk->link->state == SMC_LNK_INACTIVE)
+		goto out;
+	rc = smc_llc_add_pending_send(llcwrk->link, &wr_buf, &pend);
 	if (rc)
-		return rc;
-	memcpy(wr_buf, llcbuf, llclen);
-	/* send llc message */
-	rc = smc_wr_tx_send(link, pend);
-	return rc;
+		goto out;
+	memcpy(wr_buf, &llcwrk->llcbuf, llcwrk->llclen);
+	smc_wr_tx_send(llcwrk->link, pend);
+out:
+	kfree(llcwrk);
+}
+
+/* copy llcbuf and schedule an llc send on link */
+static int smc_llc_send_message(struct smc_link *link, void *llcbuf, int llclen)
+{
+	struct smc_llc_send_work *wrk = kmalloc(sizeof(*wrk), GFP_ATOMIC);
+
+	if (!wrk)
+		return -ENOMEM;
+	INIT_WORK(&wrk->work, smc_llc_send_message_work);
+	wrk->link = link;
+	wrk->llclen = llclen;
+	memcpy(&wrk->llcbuf, llcbuf, llclen);
+	queue_work(link->llc_wq, &wrk->work);
+	return 0;
 }
 
 /********************************* receive ***********************************/
@@ -359,17 +424,18 @@ static void smc_llc_rx_add_link(struct smc_link *link,
 		}
 
 		if (lgr->role == SMC_SERV) {
-			smc_llc_send_add_link(link,
+			smc_llc_prep_add_link(llc, link,
 					link->smcibdev->mac[link->ibport - 1],
 					&link->smcibdev->gid[link->ibport - 1],
 					SMC_LLC_REQ);
 
 		} else {
-			smc_llc_send_add_link(link,
+			smc_llc_prep_add_link(llc, link,
 					link->smcibdev->mac[link->ibport - 1],
 					&link->smcibdev->gid[link->ibport - 1],
 					SMC_LLC_RESP);
 		}
+		smc_llc_send_message(link, llc, sizeof(*llc));
 	}
 }
 
@@ -385,9 +451,11 @@ static void smc_llc_rx_delete_link(struct smc_link *link,
 	} else {
 		if (lgr->role == SMC_SERV) {
 			smc_lgr_forget(lgr);
-			smc_llc_send_delete_link(link, SMC_LLC_REQ);
+			smc_llc_prep_delete_link(llc, link, SMC_LLC_REQ);
+			smc_llc_send_message(link, llc, sizeof(*llc));
 		} else {
-			smc_llc_send_delete_link(link, SMC_LLC_RESP);
+			smc_llc_prep_delete_link(llc, link, SMC_LLC_RESP);
+			smc_llc_send_message(link, llc, sizeof(*llc));
 			smc_lgr_terminate(lgr);
 		}
 	}
@@ -397,9 +465,11 @@ static void smc_llc_rx_test_link(struct smc_link *link,
 				 struct smc_llc_msg_test_link *llc)
 {
 	if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
-		/* unused as long as we don't send this type of msg */
+		if (link->state == SMC_LNK_ACTIVE)
+			complete(&link->llc_testlink_resp);
 	} else {
-		smc_llc_send_test_link(link, llc->user_data, SMC_LLC_RESP);
+		llc->hd.flags |= SMC_LLC_FLAG_RESP;
+		smc_llc_send_message(link, llc, sizeof(*llc));
 	}
 }
 
@@ -412,7 +482,9 @@ static void smc_llc_rx_confirm_rkey(struct smc_link *link,
 	lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
 
 	if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
-		/* unused as long as we don't send this type of msg */
+		link->llc_confirm_rkey_rc = llc->hd.flags &
+					    SMC_LLC_FLAG_RKEY_NEG;
+		complete(&link->llc_confirm_rkey);
 	} else {
 		rc = smc_rtoken_add(lgr,
 				    llc->rtoken[0].rmb_vaddr,
@@ -423,7 +495,7 @@ static void smc_llc_rx_confirm_rkey(struct smc_link *link,
 		llc->hd.flags |= SMC_LLC_FLAG_RESP;
 		if (rc < 0)
 			llc->hd.flags |= SMC_LLC_FLAG_RKEY_NEG;
-		smc_llc_send_message(link, (void *)llc, sizeof(*llc));
+		smc_llc_send_message(link, llc, sizeof(*llc));
 	}
 }
 
@@ -435,7 +507,7 @@ static void smc_llc_rx_confirm_rkey_cont(struct smc_link *link,
 	} else {
 		/* ignore rtokens for other links, we have only one link */
 		llc->hd.flags |= SMC_LLC_FLAG_RESP;
-		smc_llc_send_message(link, (void *)llc, sizeof(*llc));
+		smc_llc_send_message(link, llc, sizeof(*llc));
 	}
 }
 
@@ -463,7 +535,7 @@ static void smc_llc_rx_delete_rkey(struct smc_link *link,
 		}
 
 		llc->hd.flags |= SMC_LLC_FLAG_RESP;
-		smc_llc_send_message(link, (void *)llc, sizeof(*llc));
+		smc_llc_send_message(link, llc, sizeof(*llc));
 	}
 }
 
@@ -476,6 +548,8 @@ static void smc_llc_rx_handler(struct ib_wc *wc, void *buf)
 		return; /* short message */
 	if (llc->raw.hdr.length != sizeof(*llc))
 		return; /* invalid message */
+	if (link->state == SMC_LNK_INACTIVE)
+		return; /* link not active, drop msg */
 
 	switch (llc->raw.hdr.common.type) {
 	case SMC_LLC_TEST_LINK:
@@ -502,6 +576,100 @@ static void smc_llc_rx_handler(struct ib_wc *wc, void *buf)
 	}
 }
 
+/***************************** worker, utils *********************************/
+
+static void smc_llc_testlink_work(struct work_struct *work)
+{
+	struct smc_link *link = container_of(to_delayed_work(work),
+					     struct smc_link, llc_testlink_wrk);
+	unsigned long next_interval;
+	struct smc_link_group *lgr;
+	unsigned long expire_time;
+	u8 user_data[16] = { 0 };
+	int rc;
+
+	lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
+	if (link->state != SMC_LNK_ACTIVE)
+		return;		/* don't reschedule worker */
+	expire_time = link->wr_rx_tstamp + link->llc_testlink_time;
+	if (time_is_after_jiffies(expire_time)) {
+		next_interval = expire_time - jiffies;
+		goto out;
+	}
+	reinit_completion(&link->llc_testlink_resp);
+	smc_llc_send_test_link(link, user_data);
+	/* receive TEST LINK response over RoCE fabric */
+	rc = wait_for_completion_interruptible_timeout(&link->llc_testlink_resp,
+						       SMC_LLC_WAIT_TIME);
+	if (rc <= 0) {
+		smc_lgr_terminate(lgr);
+		return;
+	}
+	next_interval = link->llc_testlink_time;
+out:
+	queue_delayed_work(link->llc_wq, &link->llc_testlink_wrk,
+			   next_interval);
+}
+
+int smc_llc_link_init(struct smc_link *link)
+{
+	struct smc_link_group *lgr = container_of(link, struct smc_link_group,
+						  lnk[SMC_SINGLE_LINK]);
+	link->llc_wq = alloc_ordered_workqueue("llc_wq-%x:%x)", WQ_MEM_RECLAIM,
+					       *((u32 *)lgr->id),
+					       link->link_id);
+	if (!link->llc_wq)
+		return -ENOMEM;
+	init_completion(&link->llc_confirm);
+	init_completion(&link->llc_confirm_resp);
+	init_completion(&link->llc_add);
+	init_completion(&link->llc_add_resp);
+	init_completion(&link->llc_confirm_rkey);
+	init_completion(&link->llc_testlink_resp);
+	INIT_DELAYED_WORK(&link->llc_testlink_wrk, smc_llc_testlink_work);
+	return 0;
+}
+
+void smc_llc_link_active(struct smc_link *link, int testlink_time)
+{
+	link->state = SMC_LNK_ACTIVE;
+	if (testlink_time) {
+		link->llc_testlink_time = testlink_time * HZ;
+		queue_delayed_work(link->llc_wq, &link->llc_testlink_wrk,
+				   link->llc_testlink_time);
+	}
+}
+
+/* called in tasklet context */
+void smc_llc_link_inactive(struct smc_link *link)
+{
+	link->state = SMC_LNK_INACTIVE;
+	cancel_delayed_work(&link->llc_testlink_wrk);
+}
+
+/* called in worker context */
+void smc_llc_link_clear(struct smc_link *link)
+{
+	flush_workqueue(link->llc_wq);
+	destroy_workqueue(link->llc_wq);
+}
+
+/* register a new rtoken at the remote peer */
+int smc_llc_do_confirm_rkey(struct smc_link *link,
+			    struct smc_buf_desc *rmb_desc)
+{
+	int rc;
+
+	reinit_completion(&link->llc_confirm_rkey);
+	smc_llc_send_confirm_rkey(link, rmb_desc);
+	/* receive CONFIRM RKEY response from server over RoCE fabric */
+	rc = wait_for_completion_interruptible_timeout(&link->llc_confirm_rkey,
+						       SMC_LLC_WAIT_TIME);
+	if (rc <= 0 || link->llc_confirm_rkey_rc)
+		return -EFAULT;
+	return 0;
+}
+
 /***************************** init, exit, misc ******************************/
 
 static struct smc_wr_rx_handler smc_llc_rx_handlers[] = {