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

Pull networking fixes from David Miller:

 1) Fix deadlock in bpf_send_signal() from Yonghong Song.

 2) Fix off by one in kTLS offload of mlx5, from Tariq Toukan.

 3) Add missing locking in iwlwifi mvm code, from Avraham Stern.

 4) Fix MSG_WAITALL handling in rxrpc, from David Howells.

 5) Need to hold RTNL mutex in tcindex_partial_destroy_work(), from Cong
    Wang.

 6) Fix producer race condition in AF_PACKET, from Willem de Bruijn.

 7) cls_route removes the wrong filter during change operations, from
    Cong Wang.

 8) Reject unrecognized request flags in ethtool netlink code, from
    Michal Kubecek.

 9) Need to keep MAC in reset until PHY is up in bcmgenet driver, from
    Doug Berger.

10) Don't leak ct zone template in act_ct during replace, from Paul
    Blakey.

11) Fix flushing of offloaded netfilter flowtable flows, also from Paul
    Blakey.

12) Fix throughput drop during tx backpressure in cxgb4, from Rahul
    Lakkireddy.

13) Don't let a non-NULL skb->dev leave the TCP stack, from Eric
    Dumazet.

14) TCP_QUEUE_SEQ socket option has to update tp->copied_seq as well,
    also from Eric Dumazet.

15) Restrict macsec to ethernet devices, from Willem de Bruijn.

16) Fix reference leak in some ethtool *_SET handlers, from Michal
    Kubecek.

17) Fix accidental disabling of MSI for some r8169 chips, from Heiner
    Kallweit.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (138 commits)
  net: Fix CONFIG_NET_CLS_ACT=n and CONFIG_NFT_FWD_NETDEV={y, m} build
  net: ena: Add PCI shutdown handler to allow safe kexec
  selftests/net/forwarding: define libs as TEST_PROGS_EXTENDED
  selftests/net: add missing tests to Makefile
  r8169: re-enable MSI on RTL8168c
  net: phy: mdio-bcm-unimac: Fix clock handling
  cxgb4/ptp: pass the sign of offset delta in FW CMD
  net: dsa: tag_8021q: replace dsa_8021q_remove_header with __skb_vlan_pop
  net: cbs: Fix software cbs to consider packet sending time
  net/mlx5e: Do not recover from a non-fatal syndrome
  net/mlx5e: Fix ICOSQ recovery flow with Striding RQ
  net/mlx5e: Fix missing reset of SW metadata in Striding RQ reset
  net/mlx5e: Enhance ICOSQ WQE info fields
  net/mlx5_core: Set IB capability mask1 to fix ib_srpt connection failure
  selftests: netfilter: add nfqueue test case
  netfilter: nft_fwd_netdev: allow to redirect to ifb via ingress
  netfilter: nft_fwd_netdev: validate family and chain type
  netfilter: nft_set_rbtree: Detect partial overlaps on insertion
  netfilter: nft_set_rbtree: Introduce and use nft_rbtree_interval_start()
  netfilter: nft_set_pipapo: Separate partial and complete overlap cases on insertion
  ...

1 files changed, 56 insertions, 19 deletions

diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 813fd6888142..0fcf157aa09f 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -18,6 +18,21 @@
 #include "ar-internal.h"
 
 /*
+ * Return true if there's sufficient Tx queue space.
+ */
+static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win)
+{
+	unsigned int win_size =
+		min_t(unsigned int, call->tx_winsize,
+		      call->cong_cwnd + call->cong_extra);
+	rxrpc_seq_t tx_win = READ_ONCE(call->tx_hard_ack);
+
+	if (_tx_win)
+		*_tx_win = tx_win;
+	return call->tx_top - tx_win < win_size;
+}
+
+/*
  * Wait for space to appear in the Tx queue or a signal to occur.
  */
 static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
@@ -26,9 +41,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
 {
 	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);
-		if (call->tx_top - call->tx_hard_ack <
-		    min_t(unsigned int, call->tx_winsize,
-			  call->cong_cwnd + call->cong_extra))
+		if (rxrpc_check_tx_space(call, NULL))
 			return 0;
 
 		if (call->state >= RXRPC_CALL_COMPLETE)
@@ -49,7 +62,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
  * Wait for space to appear in the Tx queue uninterruptibly, but with
  * a timeout of 2*RTT if no progress was made and a signal occurred.
  */
-static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
+static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx,
 					    struct rxrpc_call *call)
 {
 	rxrpc_seq_t tx_start, tx_win;
@@ -58,8 +71,8 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
 
 	rtt = READ_ONCE(call->peer->rtt);
 	rtt2 = nsecs_to_jiffies64(rtt) * 2;
-	if (rtt2 < 1)
-		rtt2 = 1;
+	if (rtt2 < 2)
+		rtt2 = 2;
 
 	timeout = rtt2;
 	tx_start = READ_ONCE(call->tx_hard_ack);
@@ -68,16 +81,13 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
 		set_current_state(TASK_UNINTERRUPTIBLE);
 
 		tx_win = READ_ONCE(call->tx_hard_ack);
-		if (call->tx_top - tx_win <
-		    min_t(unsigned int, call->tx_winsize,
-			  call->cong_cwnd + call->cong_extra))
+		if (rxrpc_check_tx_space(call, &tx_win))
 			return 0;
 
 		if (call->state >= RXRPC_CALL_COMPLETE)
 			return call->error;
 
-		if (test_bit(RXRPC_CALL_IS_INTR, &call->flags) &&
-		    timeout == 0 &&
+		if (timeout == 0 &&
 		    tx_win == tx_start && signal_pending(current))
 			return -EINTR;
 
@@ -92,6 +102,26 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
 }
 
 /*
+ * Wait for space to appear in the Tx queue uninterruptibly.
+ */
+static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
+					    struct rxrpc_call *call,
+					    long *timeo)
+{
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (rxrpc_check_tx_space(call, NULL))
+			return 0;
+
+		if (call->state >= RXRPC_CALL_COMPLETE)
+			return call->error;
+
+		trace_rxrpc_transmit(call, rxrpc_transmit_wait);
+		*timeo = schedule_timeout(*timeo);
+	}
+}
+
+/*
  * wait for space to appear in the transmit/ACK window
  * - caller holds the socket locked
  */
@@ -108,10 +138,19 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx,
 
 	add_wait_queue(&call->waitq, &myself);
 
-	if (waitall)
-		ret = rxrpc_wait_for_tx_window_nonintr(rx, call);
-	else
-		ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo);
+	switch (call->interruptibility) {
+	case RXRPC_INTERRUPTIBLE:
+		if (waitall)
+			ret = rxrpc_wait_for_tx_window_waitall(rx, call);
+		else
+			ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo);
+		break;
+	case RXRPC_PREINTERRUPTIBLE:
+	case RXRPC_UNINTERRUPTIBLE:
+	default:
+		ret = rxrpc_wait_for_tx_window_nonintr(rx, call, timeo);
+		break;
+	}
 
 	remove_wait_queue(&call->waitq, &myself);
 	set_current_state(TASK_RUNNING);
@@ -302,9 +341,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 
 			_debug("alloc");
 
-			if (call->tx_top - call->tx_hard_ack >=
-			    min_t(unsigned int, call->tx_winsize,
-				  call->cong_cwnd + call->cong_extra)) {
+			if (!rxrpc_check_tx_space(call, NULL)) {
 				ret = -EAGAIN;
 				if (msg->msg_flags & MSG_DONTWAIT)
 					goto maybe_error;
@@ -619,7 +656,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 		.call.tx_total_len	= -1,
 		.call.user_call_ID	= 0,
 		.call.nr_timeouts	= 0,
-		.call.intr		= true,
+		.call.interruptibility	= RXRPC_INTERRUPTIBLE,
 		.abort_code		= 0,
 		.command		= RXRPC_CMD_SEND_DATA,
 		.exclusive		= false,