Merge tag 'net-7.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/netstable

Pull networking fixes from Jakub Kicinski:
 "Including fixes from Bluetooth, IPSec and Netfilter.

  Current release - fix to a fix:

   - netfilter: ipset: remove need to allocate memory on delete operations

  Current release - regressions:

   - macb: drop CONFIG_OF #if block, fix build

  Previous releases - always broken:

   - stream of fixes for SCTP continues

   - inet: frags: strip GSO state from fragments before reassembly

   - virtio-net: ensure that TCP packets don't overflow gso_segs

   - tcp-ao: fix use-after-free of current_key on reconnect to another
     peer

   - page_pool: remove zone/policy GFP flags when allocating XArray
     entries

   - Bluetooth: L2CAP: reject accept queue add unless BT_LISTEN

   - tls: device: fix out-of-bounds write in tls_append_frag()

   - eth: bnxt:
      - ring the doorbell when SW USO exits early, avoid packets stuck
        in Tx
      - gate TPH enablement behind BNXT_SUPPORTS_QUEUE_API check, avoid
        users of older NICs seeing non-actionable warning messages

   - eth: qede: fix NULL pointer dereference in TPA fragment processing"

* tag 'net-7.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (216 commits)
  inet: frags: strip GSO state from fragments before reassembly
  net/sched: sch_htb: limit htb_classify inner-class filter hops
  selftests/net: packetdrill: add tcp_urg_ptr_retransmit
  tcp: fix corruption of urgent data on multi-segment retransmit
  usb: atm: usbatm: fix invalid ci_range initialization
  net: fec: only stop PTP if it was initialized
  slip: remove slip_hangup() to fix use-after-free in slip_receive_buf()
  net: bridge: mcast: fix use-after-free of a master VLAN's multicast context
  net/sched: bound qdisc_pkt_len to prevent qdisc soft lockup
  net: dsa: mxl862xx: enable assisted learning on CPU port
  net: stmmac: restore NET_IP_ALIGN in the RX DMA offset
  net: stmmac: drop gso_enabled_types and rely on netdev features
  net: stmmac: selftests: Don't test flow control for small rx fifos
  net: stmmac: selftests: Account for the UC filter list for filtering tests
  net: stmmac: dwxgmac: Account for the primary MAC address for UC filtering
  net: stmmac: dwmac4: Account for the primary MAC address for UC filtering
  net: stmmac: dwmac1000: Account for the primary MAC address for UC filtering
  net: stmmac: selftests: Check multiple MMC counters
  selftests: net: Fix slow configurations in big_tcp_tunnels.sh
  selftests: net: Lower threshold with csum offload off in big_tcp_tunnels.sh
  ...

6 files changed, 132 insertions, 46 deletions

diff --git a/net/smc/smc.h b/net/smc/smc.h
index 52145df83f6e..427b6d63b993 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -277,9 +277,9 @@ struct smc_connection {
 						 * 0 for SMC-R, 32 for SMC-D
 						 */
 	u64			peer_token;	/* SMC-D token of peer */
-	u8			killed : 1;	/* abnormal termination */
-	u8			freed : 1;	/* normal termination */
-	u8			out_of_sync : 1; /* out of sync with peer */
+	u8			killed;		/* abnormal termination */
+	u8			freed;		/* normal termination */
+	u8			out_of_sync;	/* out of sync with peer */
 };
 
 struct smc_sock {				/* smc sock container */
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 181647982490..04aedd957543 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1148,13 +1148,13 @@ again:
 		read_unlock_bh(&lgr->conns_lock);
 		/* pre-fetch buffer outside of send_lock, might sleep */
 		rc = smc_cdc_get_free_slot(conn, to_lnk, &wr_buf, NULL, &pend);
-		if (rc)
-			goto err_out;
-		/* avoid race with smcr_tx_sndbuf_nonempty() */
-		spin_lock_bh(&conn->send_lock);
-		smc_switch_link_and_count(conn, to_lnk);
-		rc = smc_switch_cursor(smc, pend, wr_buf);
-		spin_unlock_bh(&conn->send_lock);
+		if (!rc) {
+			/* avoid race with smcr_tx_sndbuf_nonempty() */
+			spin_lock_bh(&conn->send_lock);
+			smc_switch_link_and_count(conn, to_lnk);
+			rc = smc_switch_cursor(smc, pend, wr_buf);
+			spin_unlock_bh(&conn->send_lock);
+		}
 		sock_put(&smc->sk);
 		if (rc)
 			goto err_out;
diff --git a/net/smc/smc_inet.c b/net/smc/smc_inet.c
index a94084b4a498..520b666fdd8f 100644
--- a/net/smc/smc_inet.c
+++ b/net/smc/smc_inet.c
@@ -15,13 +15,16 @@
 
 #include "smc_inet.h"
 #include "smc.h"
+#include "smc_close.h"
 
 static int smc_inet_init_sock(struct sock *sk);
+static void smc_inet_destroy_sock(struct sock *sk);
 
 static struct proto smc_inet_prot = {
 	.name		= "INET_SMC",
 	.owner		= THIS_MODULE,
 	.init		= smc_inet_init_sock,
+	.destroy	= smc_inet_destroy_sock,
 	.hash		= smc_hash_sk,
 	.unhash		= smc_unhash_sk,
 	.release_cb	= smc_release_cb,
@@ -68,6 +71,7 @@ static struct proto smc_inet6_prot = {
 	.name		= "INET6_SMC",
 	.owner		= THIS_MODULE,
 	.init		= smc_inet_init_sock,
+	.destroy	= smc_inet_destroy_sock,
 	.hash		= smc_hash_sk,
 	.unhash		= smc_unhash_sk,
 	.release_cb	= smc_release_cb,
@@ -116,6 +120,18 @@ static int smc_inet_init_sock(struct sock *sk)
 	return smc_create_clcsk(net, sk, sk->sk_family);
 }
 
+static void smc_inet_destroy_sock(struct sock *sk)
+{
+	/* The sock is hashed and smc_diag dumps dereference smc->clcsock
+	 * without clcsock_release_lock, while sk_common_release() calls
+	 * .destroy before .unhash. Unhash first, as __smc_release() does,
+	 * so no dump can observe the clcsock being released; the second
+	 * unhash is a no-op.
+	 */
+	sk->sk_prot->unhash(sk);
+	smc_clcsock_release(smc_sk(sk));
+}
+
 int __init smc_inet_init(void)
 {
 	int rc;
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index aa6d83af55ed..c9ccd8480369 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -157,6 +157,7 @@ struct smc_llc_msg_confirm_rkey {	/* type 0x06 */
 };
 
 #define SMC_LLC_DEL_RKEY_MAX	8
+#define SMC_LLC_DEL_RKEY_V2_INLINE	9
 #define SMC_LLC_FLAG_RKEY_RETRY	0x10
 #define SMC_LLC_FLAG_RKEY_NEG	0x20
 
@@ -177,6 +178,15 @@ struct smc_llc_msg_delete_rkey_v2 {	/* type 0x29 */
 	__be32 rkey[];
 };
 
+/* the leading rkeys of a DELETE_RKEY_V2 fit into union smc_llc_msg */
+struct smc_llc_msg_delete_rkey_v2_inline {	/* type 0x29 */
+	struct smc_llc_hdr hd;
+	u8 num_rkeys;
+	u8 num_inval_rkeys;
+	u8 reserved[2];
+	__be32 rkey[SMC_LLC_DEL_RKEY_V2_INLINE];
+};
+
 union smc_llc_msg {
 	struct smc_llc_msg_confirm_link confirm_link;
 	struct smc_llc_msg_add_link add_link;
@@ -186,6 +196,7 @@ union smc_llc_msg {
 
 	struct smc_llc_msg_confirm_rkey confirm_rkey;
 	struct smc_llc_msg_delete_rkey delete_rkey;
+	struct smc_llc_msg_delete_rkey_v2_inline delete_rkey_v2;
 
 	struct smc_llc_msg_test_link test_link;
 	struct {
@@ -194,15 +205,25 @@ union smc_llc_msg {
 	} raw;
 };
 
+static_assert(SMC_LLC_DEL_RKEY_V2_INLINE ==
+	      (sizeof(union smc_llc_msg) -
+	       offsetof(struct smc_llc_msg_delete_rkey_v2, rkey)) /
+	      sizeof(__be32));
+static_assert(offsetof(struct smc_llc_msg_delete_rkey_v2_inline, rkey) ==
+	      offsetof(struct smc_llc_msg_delete_rkey_v2, rkey));
+
 #define SMC_LLC_FLAG_RESP		0x80
 
 struct smc_llc_qentry {
 	struct list_head list;
 	struct smc_link *link;
+	u16 body_len;
 	union smc_llc_msg msg;
+	u8 body[] __counted_by(body_len);
 };
 
-static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc);
+static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc,
+			    u32 byte_len);
 
 struct smc_llc_qentry *smc_llc_flow_qentry_clr(struct smc_llc_flow *flow)
 {
@@ -320,6 +341,7 @@ again:
 void smc_llc_flow_stop(struct smc_link_group *lgr, struct smc_llc_flow *flow)
 {
 	spin_lock_bh(&lgr->llc_flow_lock);
+	smc_llc_flow_qentry_del(flow);
 	memset(flow, 0, sizeof(*flow));
 	flow->type = SMC_LLC_FLOW_NONE;
 	spin_unlock_bh(&lgr->llc_flow_lock);
@@ -998,15 +1020,20 @@ static int smc_llc_cli_conf_link(struct smc_link *link,
 
 static void smc_llc_save_add_link_rkeys(struct smc_link *link,
 					struct smc_link *link_new,
-					u8 *llc_msg)
+					struct smc_llc_qentry *qentry)
 {
+	const u32 rt_off = offsetof(struct smc_llc_msg_add_link_v2_ext, rt);
 	struct smc_llc_msg_add_link_v2_ext *ext;
 	struct smc_link_group *lgr = link->lgr;
 	int max, i;
 
-	ext = (struct smc_llc_msg_add_link_v2_ext *)(llc_msg +
-						     SMC_WR_TX_SIZE);
+	/* the rkey count itself is only there if enough bytes arrived */
+	if (qentry->body_len < rt_off)
+		return;
+	ext = (struct smc_llc_msg_add_link_v2_ext *)qentry->body;
 	max = min_t(u8, ext->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2);
+	max = min_t(u32, max, (qentry->body_len - rt_off) /
+			      sizeof(ext->rt[0]));
 	down_write(&lgr->rmbs_lock);
 	for (i = 0; i < max; i++) {
 		smc_rtoken_set(lgr, link->link_idx, link_new->link_idx,
@@ -1099,9 +1126,7 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry)
 	if (rc)
 		goto out_clear_lnk;
 	if (lgr->smc_version == SMC_V2) {
-		u8 *llc_msg = smc_link_shared_v2_rxbuf(link) ?
-			(u8 *)lgr->wr_rx_buf_v2 : (u8 *)llc;
-		smc_llc_save_add_link_rkeys(link, lnk_new, llc_msg);
+		smc_llc_save_add_link_rkeys(link, lnk_new, qentry);
 	} else {
 		rc = smc_llc_cli_rkey_exchange(link, lnk_new);
 		if (rc) {
@@ -1481,7 +1506,7 @@ int smc_llc_srv_add_link(struct smc_link *link,
 	}
 	add_llc = &qentry->msg.add_link;
 	if (add_llc->hd.flags & SMC_LLC_FLAG_ADD_LNK_REJ) {
-		smc_llc_flow_qentry_del(&lgr->llc_flow_lcl);
+		smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl);
 		rc = -ENOLINK;
 		goto out_err;
 	}
@@ -1492,7 +1517,8 @@ int smc_llc_srv_add_link(struct smc_link *link,
 		lgr_new_t = SMC_LGR_ASYMMETRIC_PEER;
 	}
 	smc_llc_save_add_link_info(link_new, add_llc);
-	smc_llc_flow_qentry_del(&lgr->llc_flow_lcl);
+	/* add_llc still points into qentry, so only detach it here */
+	smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl);
 
 	rc = smc_ib_ready_link(link_new);
 	if (rc)
@@ -1501,9 +1527,7 @@ int smc_llc_srv_add_link(struct smc_link *link,
 	if (rc)
 		goto out_err;
 	if (lgr->smc_version == SMC_V2) {
-		u8 *llc_msg = smc_link_shared_v2_rxbuf(link) ?
-			(u8 *)lgr->wr_rx_buf_v2 : (u8 *)add_llc;
-		smc_llc_save_add_link_rkeys(link, link_new, llc_msg);
+		smc_llc_save_add_link_rkeys(link, link_new, qentry);
 	} else {
 		rc = smc_llc_srv_rkey_exchange(link, link_new);
 		if (rc)
@@ -1512,14 +1536,14 @@ int smc_llc_srv_add_link(struct smc_link *link,
 	rc = smc_llc_srv_conf_link(link, link_new, lgr_new_t);
 	if (rc)
 		goto out_err;
-	kfree(ini);
-	return 0;
+	goto out;
 out_err:
 	if (link_new) {
 		link_new->state = SMC_LNK_INACTIVE;
 		smcr_link_clear(link_new, false);
 	}
 out:
+	kfree(qentry);
 	kfree(ini);
 	if (send_req_add_link_resp)
 		smc_llc_send_req_add_link_response(req_qentry);
@@ -1552,7 +1576,8 @@ void smc_llc_add_link_local(struct smc_link *link)
 	add_llc.hd.common.llc_type = SMC_LLC_ADD_LINK;
 	smc_llc_init_msg_hdr(&add_llc.hd, link->lgr, sizeof(add_llc));
 	/* no dev and port needed */
-	smc_llc_enqueue(link, (union smc_llc_msg *)&add_llc);
+	smc_llc_enqueue(link, (union smc_llc_msg *)&add_llc,
+			sizeof(union smc_llc_msg));
 }
 
 /* worker to process an add link message */
@@ -1588,7 +1613,8 @@ void smc_llc_srv_delete_link_local(struct smc_link *link, u8 del_link_id)
 	del_llc.link_num = del_link_id;
 	del_llc.reason = htonl(SMC_LLC_DEL_LOST_PATH);
 	del_llc.hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY;
-	smc_llc_enqueue(link, (union smc_llc_msg *)&del_llc);
+	smc_llc_enqueue(link, (union smc_llc_msg *)&del_llc,
+			sizeof(union smc_llc_msg));
 }
 
 static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr)
@@ -1810,19 +1836,28 @@ static void smc_llc_rmt_delete_rkey(struct smc_link_group *lgr)
 	link = qentry->link;
 
 	if (lgr->smc_version == SMC_V2) {
-		struct smc_llc_msg_delete_rkey_v2 *llcv2;
+		struct smc_llc_msg_delete_rkey_v2_inline *llcv2;
 
-		if (smc_link_shared_v2_rxbuf(link)) {
-			memcpy(lgr->wr_rx_buf_v2, llc, sizeof(*llc));
-			llcv2 = (struct smc_llc_msg_delete_rkey_v2 *)lgr->wr_rx_buf_v2;
-		} else {
-			llcv2 = (struct smc_llc_msg_delete_rkey_v2 *)llc;
-		}
+		/* The leading SMC_LLC_DEL_RKEY_V2_INLINE rkeys are declared in
+		 * the message itself, any further ones were received into
+		 * qentry->body.
+		 */
+		llcv2 = &qentry->msg.delete_rkey_v2;
 		llcv2->num_inval_rkeys = 0;
 
 		max = min_t(u8, llcv2->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2);
+		max = min_t(u32, max, SMC_LLC_DEL_RKEY_V2_INLINE +
+				      qentry->body_len / sizeof(__be32));
 		for (i = 0; i < max; i++) {
-			if (smc_rtoken_delete(link, llcv2->rkey[i]))
+			__be32 rkey;
+
+			if (i < SMC_LLC_DEL_RKEY_V2_INLINE)
+				rkey = llcv2->rkey[i];
+			else
+				memcpy(&rkey, qentry->body +
+					      (i - SMC_LLC_DEL_RKEY_V2_INLINE) *
+					      sizeof(rkey), sizeof(rkey));
+			if (smc_rtoken_delete(link, rkey))
 				llcv2->num_inval_rkeys++;
 		}
 		memset(&llc->rkey[0], 0, sizeof(llc->rkey));
@@ -1911,6 +1946,8 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry)
 			if (lgr->llc_flow_lcl.type ==
 					SMC_LLC_FLOW_REQ_ADD_LINK) {
 				/* server started add_link processing */
+				/* free any qentry stashed in REQ_ADD_LINK state */
+				smc_llc_flow_qentry_del(&lgr->llc_flow_lcl);
 				lgr->llc_flow_lcl.type = SMC_LLC_FLOW_ADD_LINK;
 				smc_llc_flow_qentry_set(&lgr->llc_flow_lcl,
 							qentry);
@@ -2064,18 +2101,52 @@ assign:
 	wake_up(&link->lgr->llc_msg_waiter);
 }
 
-static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc)
+/* the longest tail either reader of qentry->body can use */
+static u32 smc_llc_max_body_len(union smc_llc_msg *llc)
+{
+	switch (llc->raw.hdr.common.llc_type) {
+	case SMC_LLC_ADD_LINK:
+		return offsetof(struct smc_llc_msg_add_link_v2_ext, rt) +
+		       SMC_LLC_RKEYS_PER_MSG_V2 *
+		       sizeof(struct smc_llc_msg_add_link_cont_rt);
+	case SMC_LLC_DELETE_RKEY:
+		return (SMC_LLC_RKEYS_PER_MSG_V2 -
+			SMC_LLC_DEL_RKEY_V2_INLINE) * sizeof(__be32);
+	default:
+		return 0;
+	}
+}
+
+static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc,
+			    u32 byte_len)
 {
 	struct smc_link_group *lgr = link->lgr;
 	struct smc_llc_qentry *qentry;
 	unsigned long flags;
+	u16 body_len = 0;
+
+	/* V2 messages can be longer than the inline union smc_llc_msg. Carry
+	 * the remainder in the qentry itself, so that its lifetime and its
+	 * length match the message the peer actually sent.
+	 */
+	if (lgr->smc_version == SMC_V2 && byte_len > SMC_WR_TX_SIZE)
+		body_len = min_t(u32, byte_len, SMC_WR_BUF_V2_SIZE) -
+			   SMC_WR_TX_SIZE;
+	body_len = min_t(u32, body_len, smc_llc_max_body_len(llc));
 
-	qentry = kmalloc_obj(*qentry, GFP_ATOMIC);
+	qentry = kmalloc_flex(*qentry, body, body_len, GFP_ATOMIC);
 	if (!qentry)
 		return;
+	qentry->body_len = body_len;
 	qentry->link = link;
 	INIT_LIST_HEAD(&qentry->list);
 	memcpy(&qentry->msg, llc, sizeof(union smc_llc_msg));
+	if (body_len) {
+		u8 *src = smc_link_shared_v2_rxbuf(link) ?
+			(u8 *)lgr->wr_rx_buf_v2 : (u8 *)llc;
+
+		memcpy(qentry->body, src + SMC_WR_TX_SIZE, body_len);
+	}
 
 	/* process responses immediately */
 	if ((llc->raw.hdr.flags & SMC_LLC_FLAG_RESP) &&
@@ -2107,7 +2178,7 @@ static void smc_llc_rx_handler(struct ib_wc *wc, void *buf)
 			return; /* invalid message */
 	}
 
-	smc_llc_enqueue(link, llc);
+	smc_llc_enqueue(link, llc, wc->byte_len);
 }
 
 /***************************** worker, utils *********************************/
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index 5c9e4d8b57de..197fddc6271f 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -115,16 +115,15 @@ static void smc_rx_pipe_buf_release(struct pipe_inode_info *pipe,
 				    struct pipe_buffer *buf)
 {
 	struct smc_spd_priv *priv = (struct smc_spd_priv *)buf->private;
+	struct smc_connection *conn = &priv->smc->conn;
 	struct smc_sock *smc = priv->smc;
-	struct smc_connection *conn;
 	struct sock *sk = &smc->sk;
 
-	if (sk->sk_state == SMC_CLOSED ||
-	    sk->sk_state == SMC_PEERFINCLOSEWAIT ||
-	    sk->sk_state == SMC_APPFINCLOSEWAIT)
-		goto out;
-	conn = &smc->conn;
 	lock_sock(sk);
+	if (conn->freed) {
+		release_sock(sk);
+		goto out;
+	}
 	smc_rx_update_cons(smc, priv->len);
 	release_sock(sk);
 	if (atomic_sub_and_test(priv->len, &conn->splice_pending))
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 59c92b46945c..97ba46893b17 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -602,9 +602,9 @@ static void smc_wr_init_sge(struct smc_link *lnk)
 
 	/* With SMC-Rv2 there can be messages larger than SMC_WR_TX_SIZE.
 	 * Each ib_recv_wr gets 2 sges, the second one is a spillover buffer
-	 * and the same buffer for all sges. When a larger message arrived then
-	 * the content of the first small sge is copied to the beginning of
-	 * the larger spillover buffer, allowing easy data mapping.
+	 * and the same buffer for all sges. The spillover sge starts at
+	 * SMC_WR_TX_SIZE, so the leading bytes of that buffer are never
+	 * written.
 	 */
 	for (i = 0; i < lnk->wr_rx_cnt; i++) {
 		int x = i * lnk->wr_rx_sge_cnt;