4.19.4-stable review

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: "Michał Mirosław" <[email protected]>

[ Upstream commit e84b47941e15e6666afb8ee8b21d1c3fc1a013af ]

Don't request tag insertion when it isn't present in outgoing skb.

---
 drivers/net/ethernet/ibm/ibmvnic.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1545,7 +1545,7 @@ static int ibmvnic_xmit(struct sk_buff *
 	tx_crq.v1.sge_len = cpu_to_be32(skb->len);
 	tx_crq.v1.ioba = cpu_to_be64(data_dma_addr);
 
-	if (adapter->vlan_header_insertion) {
+	if (adapter->vlan_header_insertion && skb_vlan_tag_present(skb)) {
 		tx_crq.v1.flags2 |= IBMVNIC_TX_VLAN_INSERT;
 		tx_crq.v1.vlan_id = cpu_to_be16(skb->vlan_tci);
 	}

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit 0d5b9311baf27bb545f187f12ecfd558220c607d ]

Multiple cpus might attempt to insert a new fragment in rhashtable, if for example RPS is buggy, as reported by 배석진 in
https://patchwork.ozlabs.org/patch/994601/

We use rhashtable_lookup_get_insert_key() instead of rhashtable_insert_fast() to let cpus losing the race free their own inet_frag_queue and use the one that was inserted by another cpu.

---
 net/ipv4/inet_fragment.c |   29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

@@ -178,21 +178,22 @@ static struct inet_frag_queue *inet_frag
 }
 
 static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
-						void *arg)
+						void *arg,
+						struct inet_frag_queue **prev)
 {
 	struct inet_frags *f = nf->f;
 	struct inet_frag_queue *q;
-	int err;
 
 	q = inet_frag_alloc(nf, f, arg);
-	if (!q)
+	if (!q) {
+		*prev = ERR_PTR(-ENOMEM);
 		return NULL;
-
+	}
 	mod_timer(&q->timer, jiffies + nf->timeout);
 
-	err = rhashtable_insert_fast(&nf->rhashtable, &q->node,
-				     f->rhash_params);
-	if (err < 0) {
+	*prev = rhashtable_lookup_get_insert_key(&nf->rhashtable, &q->key,
+						 &q->node, f->rhash_params);
+	if (*prev) {
 		q->flags |= INET_FRAG_COMPLETE;
 		inet_frag_kill(q);
 		inet_frag_destroy(q);

@@ -204,22 +205,22 @@ static struct inet_frag_queue *inet_frag
 /* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
 struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
 {
-	struct inet_frag_queue *fq;
+	struct inet_frag_queue *fq = NULL, *prev;
 
 	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
 		return NULL;
 
 	rcu_read_lock();
 
-	fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
-	if (fq) {
+	prev = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
+	if (!prev)
+		fq = inet_frag_create(nf, key, &prev);
+	if (prev && !IS_ERR(prev)) {
+		fq = prev;
 		if (!refcount_inc_not_zero(&fq->refcnt))
 			fq = NULL;
-		rcu_read_unlock();
-		return fq;
 	}
 	rcu_read_unlock();
-
-	return inet_frag_create(nf, key);
+	return fq;
 }
 EXPORT_SYMBOL(inet_frag_find);

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Howells <[email protected]>

[ Upstream commit c7e86acfcee30794dc99a0759924bf7b9d43f1ca ]

If the network becomes (partially) unavailable, say by disabling IPv6, the background ACK transmission routine can get itself into a tizzy by proposing immediate ACK retransmission. Since we're in the call event processor, that happens immediately without returning to the workqueue manager.

The condition should clear after a while when either the network comes back or the call times out.

Fix this by:

(1) When re-proposing an ACK on failed Tx, don't schedule it immediately. This will allow a certain amount of time to elapse before we try again.

(2) Enforce a return to the workqueue manager after a certain number of iterations of the call processing loop.

(3) Add a backoff delay that increases the delay on deferred ACKs by a jiffy per failed transmission to a limit of HZ. The backoff delay is cleared on a successful return from kernel_sendmsg().

(4) Cancel calls immediately if the opening sendmsg fails. The layer above can arrange retransmission or rotate to another server.

---
 net/rxrpc/ar-internal.h |    1 +
 net/rxrpc/call_event.c  |   18 ++++++++++++++----
 net/rxrpc/output.c      |   35 +++++++++++++++++++++++++++++++----
 3 files changed, 46 insertions(+), 8 deletions(-)

@@ -611,6 +611,7 @@ struct rxrpc_call {
 						 * not hard-ACK'd packet follows this.
 						 */
 	rxrpc_seq_t		tx_top;		/* Highest Tx slot allocated. */
+	u16			tx_backoff;	/* Delay to insert due to Tx failure */
 
 	/* TCP-style slow-start congestion control [RFC5681].  Since the SMSS
 	 * is fixed, we keep these numbers in terms of segments (ie. DATA

@@ -123,6 +123,7 @@ static void __rxrpc_propose_ACK(struct r
 		else
 			ack_at = expiry;
 
+		ack_at += READ_ONCE(call->tx_backoff);
 		ack_at += now;
 		if (time_before(ack_at, call->ack_at)) {
 			WRITE_ONCE(call->ack_at, ack_at);

@@ -311,6 +312,7 @@ void rxrpc_process_call(struct work_stru
 		container_of(work, struct rxrpc_call, processor);
 	rxrpc_serial_t *send_ack;
 	unsigned long now, next, t;
+	unsigned int iterations = 0;
 
 	rxrpc_see_call(call);
 

@@ -319,6 +321,11 @@ void rxrpc_process_call(struct work_stru
 	       call->debug_id, rxrpc_call_states[call->state], call->events);
 
 recheck_state:
+	/* Limit the number of times we do this before returning to the manager */
+	iterations++;
+	if (iterations > 5)
+		goto requeue;
+
 	if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) {
 		rxrpc_send_abort_packet(call);
 		goto recheck_state;

@@ -447,13 +454,16 @@ recheck_state:
 	rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart);
 
 	/* other events may have been raised since we started checking */
-	if (call->events && call->state < RXRPC_CALL_COMPLETE) {
-		__rxrpc_queue_call(call);
-		goto out;
-	}
+	if (call->events && call->state < RXRPC_CALL_COMPLETE)
+		goto requeue;
 
 out_put:
 	rxrpc_put_call(call, rxrpc_call_put);
 out:
 	_leave("");
+	return;
+
+requeue:
+	__rxrpc_queue_call(call);
+	goto out;
 }

@@ -35,6 +35,21 @@ struct rxrpc_abort_buffer {
 static const char rxrpc_keepalive_string[] = "";
 
 /*
+ * Increase Tx backoff on transmission failure and clear it on success.
+ */
+static void rxrpc_tx_backoff(struct rxrpc_call *call, int ret)
+{
+	if (ret < 0) {
+		u16 tx_backoff = READ_ONCE(call->tx_backoff);
+
+		if (tx_backoff < HZ)
+			WRITE_ONCE(call->tx_backoff, tx_backoff + 1);
+	} else {
+		WRITE_ONCE(call->tx_backoff, 0);
+	}
+}
+
+/*
  * Arrange for a keepalive ping a certain time after we last transmitted.  This
  * lets the far side know we're still interested in this call and helps keep
  * the route through any intervening firewall open.

@@ -210,6 +225,7 @@ int rxrpc_send_ack_packet(struct rxrpc_c
 	else
 		trace_rxrpc_tx_packet(call->debug_id, &pkt->whdr,
 				      rxrpc_tx_point_call_ack);
+	rxrpc_tx_backoff(call, ret);
 
 	if (call->state < RXRPC_CALL_COMPLETE) {
 		if (ret < 0) {

@@ -218,7 +234,7 @@ int rxrpc_send_ack_packet(struct rxrpc_c
 			rxrpc_propose_ACK(call, pkt->ack.reason,
 					  ntohs(pkt->ack.maxSkew),
 					  ntohl(pkt->ack.serial),
-					  true, true,
+					  false, true,
 					  rxrpc_propose_ack_retry_tx);
 		} else {
 			spin_lock_bh(&call->lock);

@@ -300,7 +316,7 @@ int rxrpc_send_abort_packet(struct rxrpc
 	else
 		trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr,
 				      rxrpc_tx_point_call_abort);
-
+	rxrpc_tx_backoff(call, ret);
 
 	rxrpc_put_connection(conn);
 	return ret;

@@ -411,6 +427,7 @@ int rxrpc_send_data_packet(struct rxrpc_
 	else
 		trace_rxrpc_tx_packet(call->debug_id, &whdr,
 				      rxrpc_tx_point_call_data_nofrag);
+	rxrpc_tx_backoff(call, ret);
 	if (ret == -EMSGSIZE)
 		goto send_fragmentable;
 

@@ -445,9 +462,18 @@ done:
 			rxrpc_reduce_call_timer(call, expect_rx_by, nowj,
 						rxrpc_timer_set_for_normal);
 		}
-	}
 
-	rxrpc_set_keepalive(call);
+		rxrpc_set_keepalive(call);
+	} else {
+		/* Cancel the call if the initial transmission fails,
+		 * particularly if that's due to network routing issues that
+		 * aren't going away anytime soon.  The layer above can arrange
+		 * the retransmission.
+		 */
+		if (!test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags))
+			rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
+						  RX_USER_ABORT, ret);
+	}
 
 	_leave(" = %d [%u]", ret, call->peer->maxdata);
 	return ret;

@@ -506,6 +532,7 @@ send_fragmentable:
 	else
 		trace_rxrpc_tx_packet(call->debug_id, &whdr,
 				      rxrpc_tx_point_call_data_frag);
+	rxrpc_tx_backoff(call, ret);
 
 	up_write(&conn->params.local->defrag_sem);
 	goto done;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: 배석진 <[email protected]>

[ Upstream commit 62230715fd2453b3ba948c9d83cfb3ada9169169 ]

Only first fragment has the sport/dport information, not the following ones.

If we want consistent hash for all fragments, we need to ignore ports even for first fragment.

This bug is visible for IPv6 traffic, if incoming fragments do not have a flow label, since skb_get_hash() will give different results for first fragment and following ones.

It is also visible if any routing rule wants dissection and sport or dport.

See commit 5e5d6fed3741 ("ipv6: route: dissect flow in input path if fib rules need it") for details.

[edumazet] rewrote the changelog completely.

---
 net/core/flow_dissector.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1026,8 +1026,8 @@ ip_proto_again:
 		break;
 	}
 
-	if (dissector_uses_key(flow_dissector,
-			       FLOW_DISSECTOR_KEY_PORTS)) {
+	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS) &&
+	    !(key_control->flags & FLOW_DIS_IS_FRAGMENT)) {
 		key_ports = skb_flow_dissector_target(flow_dissector,
 						      FLOW_DISSECTOR_KEY_PORTS,
 						      target_container);

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sabrina Dubroca <[email protected]>

[ Upstream commit 16f7eb2b77b55da816c4e207f3f9440a8cafc00a ]

The various types of tunnels running over IPv4 can ask to set the DF bit to do PMTU discovery. However, PMTU discovery is subject to the threshold set by the net.ipv4.route.min_pmtu sysctl, and is also disabled on routes with "mtu lock". In those cases, we shouldn't set the DF bit.

This patch makes setting the DF bit conditional on the route's MTU locking state.

This issue seems to be older than git history.

---
 net/ipv4/ip_tunnel_core.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -80,7 +80,7 @@ void iptunnel_xmit(struct sock *sk, stru
 
 	iph->version	=	4;
 	iph->ihl	=	sizeof(struct iphdr) >> 2;
-	iph->frag_off	=	df;
+	iph->frag_off	=	ip_mtu_locked(&rt->dst) ? 0 : df;
 	iph->protocol	=	proto;
 	iph->tos	=	tos;
 	iph->daddr	=	dst;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xin Long <[email protected]>

[ Upstream commit 761f60261b4401aa368d71d431b4c218af0efcee ]

These is no need to hold dst before calling rt6_remove_exception_rt(). The call to dst_hold_safe() in ip6_link_failure() was for ip6_del_rt(), which has been removed in Commit 93531c674315 ("net/ipv6: separate handling of FIB entries from dst based routes"). Otherwise, it will cause a dst leak.

This patch is to simply remove the dst_hold_safe() call before calling rt6_remove_exception_rt() and also do the same in ip6_del_cached_rt(). It's safe, because the removal of the exception that holds its dst's refcnt is protected by rt6_exception_lock.

---
 net/ipv6/route.c |    7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

@@ -2263,8 +2263,7 @@ static void ip6_link_failure(struct sk_b
 	if (rt) {
 		rcu_read_lock();
 		if (rt->rt6i_flags & RTF_CACHE) {
-			if (dst_hold_safe(&rt->dst))
-				rt6_remove_exception_rt(rt);
+			rt6_remove_exception_rt(rt);
 		} else {
 			struct fib6_info *from;
 			struct fib6_node *fn;

@@ -3266,8 +3265,8 @@ static int ip6_del_cached_rt(struct rt6_
 	if (cfg->fc_flags & RTF_GATEWAY &&
 	    !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway))
 		goto out;
-	if (dst_hold_safe(&rt->dst))
-		rc = rt6_remove_exception_rt(rt);
+
+	rc = rt6_remove_exception_rt(rt);
 out:
 	return rc;
 }

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Ahern <[email protected]>

[ Upstream commit 7ddacfa564870cdd97275fd87decb6174abc6380 ]

Preethi reported that PMTU discovery for UDP/raw applications is not working in the presence of VRF when the socket is not bound to a device. The problem is that ip6_sk_update_pmtu does not consider the L3 domain of the skb device if the socket is not bound. Update the function to set oif to the L3 master device if relevant.

---
 net/ipv6/route.c |    7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

@@ -2391,10 +2391,13 @@ EXPORT_SYMBOL_GPL(ip6_update_pmtu);
 
 void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
 {
+	int oif = sk->sk_bound_dev_if;
 	struct dst_entry *dst;
 
-	ip6_update_pmtu(skb, sock_net(sk), mtu,
-			sk->sk_bound_dev_if, sk->sk_mark, sk->sk_uid);
+	if (!oif && skb->dev)
+		oif = l3mdev_master_ifindex(skb->dev);
+
+	ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark, sk->sk_uid);
 
 	dst = __sk_dst_get(sk);
 	if (!dst || !dst->obsolete ||

This is the start of the stable review cycle for the 4.19.4 release. There are 42 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Fri Nov 23 18:31:31 UTC 2018. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.19.4-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.19.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 4.19.4-rc1

Greg Kroah-Hartman <[email protected]>
Revert "x86/speculation: Enable cross-hyperthread spectre v2 STIBP mitigation"

Frieder Schrempf <[email protected]>
usbnet: smsc95xx: disable carrier check while suspending

David Howells <[email protected]>
rxrpc: Fix lockup due to no error backoff after ack transmit error

Stefan Wahren <[email protected]>
net: smsc95xx: Fix MTU range

Shalom Toledo <[email protected]>
mlxsw: spectrum: Fix IP2ME CPU policer configuration

Xin Long <[email protected]>
sctp: not increase stream's incnt before sending addstrm_in request

Martin Schiller <[email protected]>
net: phy: mdio-gpio: Fix working over slow can_sleep GPIOs

Xin Long <[email protected]>
sctp: fix strchange_flags name for Stream Change Event

Tristram Ha <[email protected]>
net: dsa: microchip: initialize mutex before use

Subash Abhinov Kasiviswanathan <[email protected]>
net: qualcomm: rmnet: Fix incorrect assignment of real_dev

Xin Long <[email protected]>
sctp: define SCTP_SS_DEFAULT for Stream schedulers

Holger Hoffstätte <[email protected]>
net: phy: realtek: fix RTL8201F sysfs name

Andrew Lunn <[email protected]>
net: dsa: mv88e6xxx: Fix clearing of stats counters

Denis Drozdov <[email protected]>
net/mlx5e: IPoIB, Reset QP after channels are closed

Raed Salem <[email protected]>
net/mlx5: IPSec, Fix the SA context hash key

Xin Long <[email protected]>
l2tp: fix a sock refcnt leak in l2tp_tunnel_register

Eric Dumazet <[email protected]>
inet: frags: better deal with smp races

Shay Agroskin <[email protected]>
net/mlx5e: Removed unnecessary warnings in FEC caps query

Valentine Fatiev <[email protected]>
net/mlx5e: Fix selftest for small MTUs

Or Gerlitz <[email protected]>
net/mlx5e: Always use the match level enum when parsing TC rule match

Xin Long <[email protected]>
Revert "sctp: remove sctp_transport_pmtu_check"

Moshe Shemesh <[email protected]>
net/mlx5e: RX, verify received packet size in Linear Striding RQ

Yuval Avnery <[email protected]>
net/mlx5e: Adjust to max number of channles when re-attaching

Or Gerlitz <[email protected]>
net/mlx5e: Claim TC hw offloads support only under a proper build config

Or Gerlitz <[email protected]>
net/mlx5e: Don't match on vlan non-existence if ethertype is wildcarded

Jon Maloy <[email protected]>
tipc: fix link re-establish failure

Jakub Kicinski <[email protected]>
net: sched: cls_flower: validate nested enc_opts_policy to avoid warning

Davide Caratti <[email protected]>
net/sched: act_pedit: fix memory leak when IDR allocation fails

Florian Fainelli <[email protected]>
net: systemport: Protect stop from timeout

Matthew Cover <[email protected]>
tuntap: fix multiqueue rx

Jon Maloy <[email protected]>
tipc: fix lockdep warning when reinitilaizing sockets

Jon Maloy <[email protected]>
tipc: don't assume linear buffer when reading ancillary data

Siva Reddy Kallam <[email protected]>
tg3: Add PHY reset for 5717/5719/5720 in change ring and flow control paths

Stephen Mallon <[email protected]>
tcp: Fix SOF_TIMESTAMPING_RX_HARDWARE to use the latest timestamp during TCP coalescing

Xin Long <[email protected]>
sctp: not allow to set asoc prsctp_enable by sockopt

Eric Dumazet <[email protected]>

    net-gro: reset skb->pkt_type in napi_reuse_skb()

Doug Berger <[email protected]>
net: bcmgenet: protect stop from timeout

David Ahern <[email protected]>
ipv6: Fix PMTU updates for UDP/raw sockets in presence of VRF

Xin Long <[email protected]>
ipv6: fix a dst leak when removing its exception

Sabrina Dubroca <[email protected]>
ip_tunnel: don't force DF when MTU is locked

Michał Mirosław <[email protected]>
ibmvnic: fix accelerated VLAN handling

배석진 <[email protected]>
flow_dissector: do not dissect l4 ports for fragments

-------------

Diffstat:

 Makefile                                           |  4 +-
 arch/x86/kernel/cpu/bugs.c                         | 57 ++----------------
 drivers/net/dsa/microchip/ksz_common.c             | 10 ++--
 drivers/net/dsa/mv88e6xxx/global1.c                |  2 +
 drivers/net/ethernet/broadcom/bcmsysport.c         | 15 +++--
 drivers/net/ethernet/broadcom/genet/bcmgenet.c     | 13 +++--
 drivers/net/ethernet/broadcom/tg3.c                | 18 +++++-
 drivers/net/ethernet/ibm/ibmvnic.c                 |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/en/port.c  |  4 +-
 .../ethernet/mellanox/mlx5/core/en/port_buffer.c   |  4 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 37 ++++++++++--
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    |  6 ++
 .../net/ethernet/mellanox/mlx5/core/en_selftest.c  | 26 ++++-----
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c |  3 +
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h |  2 +
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    | 67 +++++++++++-----------
 .../net/ethernet/mellanox/mlx5/core/fpga/ipsec.c   | 10 +++-
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c  |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |  1 -
 drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c    |  6 +-
 drivers/net/phy/mdio-gpio.c                        | 10 ++--
 drivers/net/phy/realtek.c                          |  2 +-
 drivers/net/tun.c                                  |  6 +-
 drivers/net/usb/smsc95xx.c                         |  9 +++
 include/net/sctp/sctp.h                            | 12 ++++
 include/uapi/linux/sctp.h                          |  3 +
 kernel/cpu.c                                       | 11 +---
 net/core/dev.c                                     |  4 ++
 net/core/flow_dissector.c                          |  4 +-
 net/ipv4/inet_fragment.c                           | 29 +++++-----
 net/ipv4/ip_tunnel_core.c                          |  2 +-
 net/ipv4/tcp_input.c                               |  1 +
 net/ipv6/route.c                                   | 14 +++--
 net/l2tp/l2tp_core.c                               |  9 ++-
 net/rxrpc/ar-internal.h                            |  1 +
 net/rxrpc/call_event.c                             | 18 ++++--
 net/rxrpc/output.c                                 | 35 +++++++++--
 net/sched/act_pedit.c                              |  3 +-
 net/sched/cls_flower.c                             | 14 ++++-
 net/sctp/output.c                                  |  3 +
 net/sctp/outqueue.c                                |  2 +-
 net/sctp/socket.c                                  | 26 ++-------
 net/sctp/stream.c                                  |  1 -
 net/tipc/discover.c                                | 19 +++---
 net/tipc/link.c                                    | 11 ++--
 net/tipc/net.c                                     | 45 ++++++++++++---
 net/tipc/net.h                                     |  2 +-
 net/tipc/socket.c                                  | 15 +++--
 49 files changed, 356 insertions(+), 245 deletions(-)

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit 33d9a2c72f086cbf1087b2fd2d1a15aa9df14a7f ]

eth_type_trans() assumes initial value for skb->pkt_type is PACKET_HOST.

This is indeed the value right after a fresh skb allocation.

However, it is possible that GRO merged a packet with a different value (like PACKET_OTHERHOST in case macvlan is used), so we need to make sure napi->skb will have pkt_type set back to PACKET_HOST.

Otherwise, valid packets might be dropped by the stack because their pkt_type is not PACKET_HOST.

napi_reuse_skb() was added in commit 96e93eab2033 ("gro: Add internal interfaces for VLAN"), but this bug always has been there.

---
 net/core/dev.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -5630,6 +5630,10 @@ static void napi_reuse_skb(struct napi_s
 	skb->vlan_tci = 0;
 	skb->dev = napi->dev;
 	skb->skb_iif = 0;
+
+	/* eth_type_trans() assumes pkt_type is PACKET_HOST */
+	skb->pkt_type = PACKET_HOST;
+
 	skb->encapsulation = 0;
 	skb_shinfo(skb)->gso_type = 0;
 	skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jon Maloy <[email protected]>

[ Upstream commit 7ab412d33b4c7ff3e0148d3db25dd861edd1283d ]

When a link failure is detected locally, the link is reset, the flag link->in_session is set to false, and a RESET_MSG with the 'stopping' bit set is sent to the peer.

The purpose of this bit is to inform the peer that this endpoint just is going down, and that the peer should handle the reception of this particular RESET message as a local failure. This forces the peer to accept another RESET or ACTIVATE message from this endpoint before it can re-establish the link. This again is necessary to ensure that link session numbers are properly exchanged before the link comes up again.

If a failure is detected locally at the same time at the peer endpoint this will do the same, which is also a correct behavior.

However, when receiving such messages, the endpoints will not distinguish between 'stopping' RESETs and ordinary ones when it comes to updating session numbers. Both endpoints will copy the received session number and set their 'in_session' flags to true at the reception, while they are still expecting another RESET from the peer before they can go ahead and re-establish. This is contradictory, since, after applying the validation check referred to below, the 'in_session' flag will cause rejection of all such messages, and the link will never come up again.

We now fix this by not only handling received RESET/STOPPING messages as a local failure, but also by omitting to set a new session number and the 'in_session' flag in such cases.

---
 net/tipc/link.c |   11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

@@ -1594,14 +1594,17 @@ static int tipc_link_proto_rcv(struct ti
 		if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI))
 			l->priority = peers_prio;
 
-		/* ACTIVATE_MSG serves as PEER_RESET if link is already down */
-		if (msg_peer_stopping(hdr))
+		/* If peer is going down we want full re-establish cycle */
+		if (msg_peer_stopping(hdr)) {
 			rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
-		else if ((mtyp == RESET_MSG) || !link_is_up(l))
+			break;
+		}
+		/* ACTIVATE_MSG serves as PEER_RESET if link is already down */
+		if (mtyp == RESET_MSG || !link_is_up(l))
 			rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT);
 
 		/* ACTIVATE_MSG takes up link if it was already locally reset */
-		if ((mtyp == ACTIVATE_MSG) && (l->state == LINK_ESTABLISHING))
+		if (mtyp == ACTIVATE_MSG && l->state == LINK_ESTABLISHING)
 			rc = TIPC_LINK_UP_EVT;
 
 		l->peer_session = msg_session(hdr);

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Or Gerlitz <[email protected]>

[ Upstream commit d3a80bb5a3eac311ddf28387402593977574460d ]

For the "all" ethertype we should not care whether the packet has vlans. Besides being wrong, the way we did it caused FW error for rules such as:

tc filter add dev eth0 protocol all parent ffff: \
prio 1 flower skip_sw action drop

b/c the matching meta-data (outer headers bit in struct mlx5_flow_spec) wasn't set. Fix that by matching on vlan non-existence only if we were also told to match on the ethertype.

---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c |   63 ++++++++++++------------
 1 file changed, 32 insertions(+), 31 deletions(-)

@@ -1310,31 +1310,21 @@ static int __parse_cls_flower(struct mlx
 					 inner_headers);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		struct flow_dissector_key_eth_addrs *key =
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_dissector_key_basic *key =
 			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
+						  FLOW_DISSECTOR_KEY_BASIC,
 						  f->key);
-		struct flow_dissector_key_eth_addrs *mask =
+		struct flow_dissector_key_basic *mask =
 			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
+						  FLOW_DISSECTOR_KEY_BASIC,
 						  f->mask);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype,
+			 ntohs(mask->n_proto));
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
+			 ntohs(key->n_proto));
 
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
-					     dmac_47_16),
-				mask->dst);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
-					     dmac_47_16),
-				key->dst);
-
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
-					     smac_47_16),
-				mask->src);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
-					     smac_47_16),
-				key->src);
-
-		if (!is_zero_ether_addr(mask->src) || !is_zero_ether_addr(mask->dst))
+		if (mask->n_proto)
 			*match_level = MLX5_MATCH_L2;
 	}
 

@@ -1368,9 +1358,10 @@ static int __parse_cls_flower(struct mlx
 
 			*match_level = MLX5_MATCH_L2;
 		}
-	} else {
+	} else if (*match_level != MLX5_MATCH_NONE) {
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, svlan_tag, 1);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
+		*match_level = MLX5_MATCH_L2;
 	}
 
 	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CVLAN)) {

@@ -1408,21 +1399,31 @@ static int __parse_cls_flower(struct mlx
 		}
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_dissector_key_eth_addrs *key =
 			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
+						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
 						  f->key);
-		struct flow_dissector_key_basic *mask =
+		struct flow_dissector_key_eth_addrs *mask =
 			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
+						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
 						  f->mask);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype,
-			 ntohs(mask->n_proto));
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
-			 ntohs(key->n_proto));
 
-		if (mask->n_proto)
+		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
+					     dmac_47_16),
+				mask->dst);
+		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
+					     dmac_47_16),
+				key->dst);
+
+		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
+					     smac_47_16),
+				mask->src);
+		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
+					     smac_47_16),
+				key->src);
+
+		if (!is_zero_ether_addr(mask->src) || !is_zero_ether_addr(mask->dst))
 			*match_level = MLX5_MATCH_L2;
 	}
 

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Or Gerlitz <[email protected]>

[ Upstream commit 077ecd785d90c6cbba08d719faa4be8561aa0a1e ]

Currently, we are only supporting tc hw offloads when the eswitch support is compiled in, but we are not gating the adevertizment of the NETIF_F_HW_TC feature on this config being set.

Fix it, and while doing that, also avoid dealing with the feature on ethtool when the config is not set.

---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -3566,6 +3566,7 @@ static int set_feature_cvlan_filter(stru
 	return 0;
 }
 
+#ifdef CONFIG_MLX5_ESWITCH
 static int set_feature_tc_num_filters(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);

@@ -3578,6 +3579,7 @@ static int set_feature_tc_num_filters(st
 
 	return 0;
 }
+#endif
 
 static int set_feature_rx_all(struct net_device *netdev, bool enable)
 {

@@ -3676,7 +3678,9 @@ static int mlx5e_set_features(struct net
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_LRO, set_feature_lro);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_VLAN_CTAG_FILTER,
 				    set_feature_cvlan_filter);
+#ifdef CONFIG_MLX5_ESWITCH
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_TC, set_feature_tc_num_filters);
+#endif
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXALL, set_feature_rx_all);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXFCS, set_feature_rx_fcs);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_VLAN_CTAG_RX, set_feature_rx_vlan);

@@ -4685,7 +4689,9 @@ static void mlx5e_build_nic_netdev(struc
 	    FT_CAP(modify_root) &&
 	    FT_CAP(identified_miss_table_mode) &&
 	    FT_CAP(flow_table_modify)) {
+#ifdef CONFIG_MLX5_ESWITCH
 		netdev->hw_features      |= NETIF_F_HW_TC;
+#endif
 #ifdef CONFIG_MLX5_EN_ARFS
 		netdev->hw_features	 |= NETIF_F_NTUPLE;
 #endif

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yuval Avnery <[email protected]>

[ Upstream commit a1f240f1801721f76bee734c50df2d9529da86e0 ]

When core driver enters deattach/attach flow after pci reset, Number of logical CPUs may have changed.
As a result we need to update the cpu affiliated resource tables.
1. indirect rqt list
2. eq table

Reproduction (PowerPC):
echo 1000 > /sys/kernel/debug/powerpc/eeh_max_freezes
ppc64_cpu --smt=on
# Restart driver
modprobe -r ... ; modprobe ...
# Link up
ifconfig ...
# Only physical CPUs
ppc64_cpu --smt=off
# Inject PCI errors so PCI will reset - calling the pci error handler echo 0x8000000000000000 > /sys/kernel/debug/powerpc/<PCI BUS>/err_injct_inboundA

Call trace when trying to add non-existing rqs to an indirect rqt:

	mlx5e_redirect_rqt+0x84/0x260 [mlx5_core] (unreliable)
	mlx5e_redirect_rqts+0x188/0x190 [mlx5_core]
	mlx5e_activate_priv_channels+0x488/0x570 [mlx5_core]
	mlx5e_open_locked+0xbc/0x140 [mlx5_core]
	mlx5e_open+0x50/0x130 [mlx5_core]
	mlx5e_nic_enable+0x174/0x1b0 [mlx5_core]
	mlx5e_attach_netdev+0x154/0x290 [mlx5_core]
	mlx5e_attach+0x88/0xd0 [mlx5_core]
	mlx5_attach_device+0x168/0x1e0 [mlx5_core]
	mlx5_load_one+0x1140/0x1210 [mlx5_core]
	mlx5_pci_resume+0x6c/0xf0 [mlx5_core]

Create cq will fail when trying to use non-existing EQ.

---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |   27 +++++++++++++++++-----
 1 file changed, 22 insertions(+), 5 deletions(-)

@@ -1610,13 +1610,15 @@ static int mlx5e_alloc_cq_common(struct
 	int err;
 	u32 i;
 
+	err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn);
+	if (err)
+		return err;
+
 	err = mlx5_cqwq_create(mdev, &param->wq, param->cqc, &cq->wq,
 			       &cq->wq_ctrl);
 	if (err)
 		return err;
 
-	mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn);
-
 	mcq->cqe_sz     = 64;
 	mcq->set_ci_db  = cq->wq_ctrl.db.db;
 	mcq->arm_db     = cq->wq_ctrl.db.db + 1;

@@ -1674,6 +1676,10 @@ static int mlx5e_create_cq(struct mlx5e_
 	int eqn;
 	int err;
 
+	err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn, &irqn_not_used);
+	if (err)
+		return err;
+
 	inlen = MLX5_ST_SZ_BYTES(create_cq_in) +
 		sizeof(u64) * cq->wq_ctrl.buf.npages;
 	in = kvzalloc(inlen, GFP_KERNEL);

@@ -1687,8 +1693,6 @@ static int mlx5e_create_cq(struct mlx5e_
 	mlx5_fill_page_frag_array(&cq->wq_ctrl.buf,
 				  (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas));
 
-	mlx5_vector2eqn(mdev, param->eq_ix, &eqn, &irqn_not_used);
-
 	MLX5_SET(cqc,   cqc, cq_period_mode, param->cq_period_mode);
 	MLX5_SET(cqc,   cqc, c_eqn,         eqn);
 	MLX5_SET(cqc,   cqc, uar_page,      mdev->priv.uar->index);

@@ -1908,6 +1912,10 @@ static int mlx5e_open_channel(struct mlx
 	int err;
 	int eqn;
 
+	err = mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq);
+	if (err)
+		return err;
+
 	c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
 	if (!c)
 		return -ENOMEM;

@@ -1924,7 +1932,6 @@ static int mlx5e_open_channel(struct mlx
 	c->xdp      = !!params->xdp_prog;
 	c->stats    = &priv->channel_stats[ix].ch;
 
-	mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq);
 	c->irq_desc = irq_to_desc(irq);
 
 	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);

@@ -4964,11 +4971,21 @@ int mlx5e_attach_netdev(struct mlx5e_pri
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	const struct mlx5e_profile *profile;
+	int max_nch;
 	int err;
 
 	profile = priv->profile;
 	clear_bit(MLX5E_STATE_DESTROYING, &priv->state);
 
+	/* max number of channels may have changed */
+	max_nch = mlx5e_get_max_num_channels(priv->mdev);
+	if (priv->channels.params.num_channels > max_nch) {
+		mlx5_core_warn(priv->mdev, "MLX5E: Reducing number of channels to %d\n", max_nch);
+		priv->channels.params.num_channels = max_nch;
+		mlx5e_build_default_indir_rqt(priv->channels.params.indirection_rqt,
+					      MLX5E_INDIR_RQT_SIZE, max_nch);
+	}
+
 	err = profile->init_tx(priv);
 	if (err)
 		goto out;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Moshe Shemesh <[email protected]>

[ Upstream commit 0073c8f72736b423aade8a817587a5f3e4df4ad8 ]

In case of striding RQ, we use MPWRQ (Multi Packet WQE RQ), which means that WQE (RX descriptor) can be used for many packets and so the WQE is much bigger than MTU. In virtualization setups where the port mtu can be larger than the vf mtu, if received packet is bigger than MTU, it won't be dropped by HW on too small receive WQE. If we use linear SKB in striding RQ, since each stride has room for mtu size payload and skb info, an oversized packet can lead to crash for crossing allocated page boundary upon the call to build_skb. So driver needs to check packet size and drop it.

Introduce new SW rx counter, rx_oversize_pkts_sw_drop, which counts the number of packets dropped by the driver for being too large.

As a new field is added to the RQ struct, re-open the channels whenever this field is being used in datapath (i.e., in the case of linear Striding RQ).

---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |    1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |    4 +++-
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    |    6 ++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c |    3 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h |    2 ++
 5 files changed, 15 insertions(+), 1 deletion(-)

@@ -566,6 +566,7 @@ struct mlx5e_rq {
 
 	unsigned long          state;
 	int                    ix;
+	unsigned int           hw_mtu;
 
 	struct net_dim         dim; /* Dynamic Interrupt Moderation */
 

@@ -492,6 +492,7 @@ static int mlx5e_alloc_rq(struct mlx5e_c
 	rq->channel = c;
 	rq->ix      = c->ix;
 	rq->mdev    = mdev;
+	rq->hw_mtu  = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	rq->stats   = &c->priv->channel_stats[c->ix].rq;
 
 	rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;

@@ -3758,10 +3759,11 @@ int mlx5e_change_mtu(struct net_device *
 	}
 
 	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
+		bool is_linear = mlx5e_rx_mpwqe_is_linear_skb(priv->mdev, &new_channels.params);
 		u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params);
 		u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params);
 
-		reset = reset && (ppw_old != ppw_new);
+		reset = reset && (is_linear || (ppw_old != ppw_new));
 	}
 
 	if (!reset) {

@@ -1064,6 +1064,12 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct m
 	u32 frag_size;
 	bool consumed;
 
+	/* Check packet size. Note LRO doesn't use linear SKB */
+	if (unlikely(cqe_bcnt > rq->hw_mtu)) {
+		rq->stats->oversize_pkts_sw_drop++;
+		return NULL;
+	}
+
 	va             = page_address(di->page) + head_offset;
 	data           = va + rx_headroom;
 	frag_size      = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt32);

@@ -82,6 +82,7 @@ static const struct counter_desc sw_stat
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_cqes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_strides) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_oversize_pkts_sw_drop) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) },

@@ -158,6 +159,7 @@ void mlx5e_grp_sw_update_stats(struct ml
 		s->rx_wqe_err   += rq_stats->wqe_err;
 		s->rx_mpwqe_filler_cqes    += rq_stats->mpwqe_filler_cqes;
 		s->rx_mpwqe_filler_strides += rq_stats->mpwqe_filler_strides;
+		s->rx_oversize_pkts_sw_drop += rq_stats->oversize_pkts_sw_drop;
 		s->rx_buff_alloc_err += rq_stats->buff_alloc_err;
 		s->rx_cqe_compress_blks += rq_stats->cqe_compress_blks;
 		s->rx_cqe_compress_pkts += rq_stats->cqe_compress_pkts;

@@ -1148,6 +1150,7 @@ static const struct counter_desc rq_stat
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_cqes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_strides) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, oversize_pkts_sw_drop) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },

@@ -95,6 +95,7 @@ struct mlx5e_sw_stats {
 	u64 rx_wqe_err;
 	u64 rx_mpwqe_filler_cqes;
 	u64 rx_mpwqe_filler_strides;
+	u64 rx_oversize_pkts_sw_drop;
 	u64 rx_buff_alloc_err;
 	u64 rx_cqe_compress_blks;
 	u64 rx_cqe_compress_pkts;

@@ -190,6 +191,7 @@ struct mlx5e_rq_stats {
 	u64 wqe_err;
 	u64 mpwqe_filler_cqes;
 	u64 mpwqe_filler_strides;
+	u64 oversize_pkts_sw_drop;
 	u64 buff_alloc_err;
 	u64 cqe_compress_blks;
 	u64 cqe_compress_pkts;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xin Long <[email protected]>

[ Upstream commit 69fec325a64383667b8a35df5d48d6ce52fb2782 ]

This reverts commit 22d7be267eaa8114dcc28d66c1c347f667d7878a.

The dst's mtu in transport can be updated by a non sctp place like in xfrm where the MTU information didn't get synced between asoc, transport and dst, so it is still needed to do the pmtu check in sctp_packet_config.

---
 include/net/sctp/sctp.h |   12 ++++++++++++
 net/sctp/output.c       |    3 +++
 2 files changed, 15 insertions(+)

@@ -608,4 +608,16 @@ static inline __u32 sctp_dst_mtu(const s
 				 SCTP_DEFAULT_MINSEGMENT));
 }
 
+static inline bool sctp_transport_pmtu_check(struct sctp_transport *t)
+{
+	__u32 pmtu = sctp_dst_mtu(t->dst);
+
+	if (t->pathmtu == pmtu)
+		return true;
+
+	t->pathmtu = pmtu;
+
+	return false;
+}
+
 #endif /* __net_sctp_h__ */

@@ -118,6 +118,9 @@ void sctp_packet_config(struct sctp_pack
 		sctp_transport_route(tp, NULL, sp);
 		if (asoc->param_flags & SPP_PMTUD_ENABLE)
 			sctp_assoc_sync_pmtu(asoc);
+	} else if (!sctp_transport_pmtu_check(tp)) {
+		if (asoc->param_flags & SPP_PMTUD_ENABLE)
+			sctp_assoc_sync_pmtu(asoc);
 	}
 
 	if (asoc->pmtu_pending) {

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Or Gerlitz <[email protected]>

[ Upstream commit 83621b7df6a646e550fd3d36db2e301cf9a5096b ]

We get the match level (none, l2, l3, l4) while going over the match dissectors of an offloaded tc rule. When doing this, the match level enum and the not min inline enum values should be used, fix that.

This worked accidentally b/c both enums have the same numerical values.

---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1450,10 +1450,10 @@ static int __parse_cls_flower(struct mlx
 
 			/* the HW doesn't need L3 inline to match on frag=no */
 			if (!(key->flags & FLOW_DIS_IS_FRAGMENT))
-				*match_level = MLX5_INLINE_MODE_L2;
+				*match_level = MLX5_MATCH_L2;
 	/* ***  L2 attributes parsing up to here *** */
 			else
-				*match_level = MLX5_INLINE_MODE_IP;
+				*match_level = MLX5_MATCH_L3;
 		}
 	}
 

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Valentine Fatiev <[email protected]>

[ Upstream commit 228c4cd04dfd0667eda182c91504b83c17d97584 ]

Loopback test had fixed packet size, which can be bigger than configured MTU. Shorten the loopback packet size to be bigger than minimal MTU allowed by the device. Text field removed from struct 'mlx5ehdr' as redundant to allow send small packets as minimal allowed MTU.

---
 drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c |   26 ++++++------------
 1 file changed, 10 insertions(+), 16 deletions(-)

@@ -98,18 +98,17 @@ static int mlx5e_test_link_speed(struct
 	return 1;
 }
 
-#ifdef CONFIG_INET
-/* loopback test */
-#define MLX5E_TEST_PKT_SIZE (MLX5E_RX_MAX_HEAD - NET_IP_ALIGN)
-static const char mlx5e_test_text[ETH_GSTRING_LEN] = "MLX5E SELF TEST";
-#define MLX5E_TEST_MAGIC 0x5AEED15C001ULL
-
 struct mlx5ehdr {
 	__be32 version;
 	__be64 magic;
-	char   text[ETH_GSTRING_LEN];
 };
 
+#ifdef CONFIG_INET
+/* loopback test */
+#define MLX5E_TEST_PKT_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) +\
+			     sizeof(struct udphdr) + sizeof(struct mlx5ehdr))
+#define MLX5E_TEST_MAGIC 0x5AEED15C001ULL
+
 static struct sk_buff *mlx5e_test_get_udp_skb(struct mlx5e_priv *priv)
 {
 	struct sk_buff *skb = NULL;

@@ -117,10 +116,7 @@ static struct sk_buff *mlx5e_test_get_ud
 	struct ethhdr *ethh;
 	struct udphdr *udph;
 	struct iphdr *iph;
-	int datalen, iplen;
-
-	datalen = MLX5E_TEST_PKT_SIZE -
-		  (sizeof(*ethh) + sizeof(*iph) + sizeof(*udph));
+	int    iplen;
 
 	skb = netdev_alloc_skb(priv->netdev, MLX5E_TEST_PKT_SIZE);
 	if (!skb) {

@@ -149,7 +145,7 @@ static struct sk_buff *mlx5e_test_get_ud
 	/* Fill UDP header */
 	udph->source = htons(9);
 	udph->dest = htons(9); /* Discard Protocol */
-	udph->len = htons(datalen + sizeof(struct udphdr));
+	udph->len = htons(sizeof(struct mlx5ehdr) + sizeof(struct udphdr));
 	udph->check = 0;
 
 	/* Fill IP header */

@@ -157,7 +153,8 @@ static struct sk_buff *mlx5e_test_get_ud
 	iph->ttl = 32;
 	iph->version = 4;
 	iph->protocol = IPPROTO_UDP;
-	iplen = sizeof(struct iphdr) + sizeof(struct udphdr) + datalen;
+	iplen = sizeof(struct iphdr) + sizeof(struct udphdr) +
+		sizeof(struct mlx5ehdr);
 	iph->tot_len = htons(iplen);
 	iph->frag_off = 0;
 	iph->saddr = 0;

@@ -170,9 +167,6 @@ static struct sk_buff *mlx5e_test_get_ud
 	mlxh = skb_put(skb, sizeof(*mlxh));
 	mlxh->version = 0;
 	mlxh->magic = cpu_to_be64(MLX5E_TEST_MAGIC);
-	strlcpy(mlxh->text, mlx5e_test_text, sizeof(mlxh->text));
-	datalen -= sizeof(*mlxh);
-	skb_put_zero(skb, datalen);
 
 	skb->csum = 0;
 	skb->ip_summed = CHECKSUM_PARTIAL;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shay Agroskin <[email protected]>

[ Upstream commit 64e283348458e2fd2fe41b60dfb6c30e88ee695f ]

Querying interface FEC caps with 'ethtool [int]' after link reset throws warning regading link speed.
This warning is not needed as there is already an indication in user space that the link is not up.

---
 drivers/net/ethernet/mellanox/mlx5/core/en/port.c        |    4 +---
 drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c |    4 +++-
 2 files changed, 4 insertions(+), 4 deletions(-)

@@ -88,10 +88,8 @@ int mlx5e_port_linkspeed(struct mlx5_cor
 
 	eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
 	*speed = mlx5e_port_ptys2speed(eth_proto_oper);
-	if (!(*speed)) {
-		mlx5_core_warn(mdev, "cannot get port speed\n");
+	if (!(*speed))
 		err = -EINVAL;
-	}
 
 	return err;
 }

@@ -130,8 +130,10 @@ static u32 calculate_xoff(struct mlx5e_p
 	int err;
 
 	err = mlx5e_port_linkspeed(priv->mdev, &speed);
-	if (err)
+	if (err) {
+		mlx5_core_warn(priv->mdev, "cannot get port speed\n");
 		return 0;
+	}
 
 	xoff = (301 + 216 * priv->dcbx.cable_len / 100) * speed / 1000 + 272 * mtu / 100;
 

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xin Long <[email protected]>

[ Upstream commit cc3ccf26f0649089b3a34a2781977755ea36e72c ]

As rfc7496#section4.5 says about SCTP_PR_SUPPORTED:

This socket option allows the enabling or disabling of the negotiation of PR-SCTP support for future associations. For existing associations, it allows one to query whether or not PR-SCTP support was negotiated on a particular association.

It means only sctp sock's prsctp_enable can be set.

Note that for the limitation of SCTP_{CURRENT|ALL}_ASSOC, we will add it when introducing SCTP_{FUTURE|CURRENT|ALL}_ASSOC for linux sctp in another patchset.

v1->v2:
- drop the params.assoc_id check as Neil suggested.

---
 net/sctp/socket.c |   26 +++++---------------------
 1 file changed, 5 insertions(+), 21 deletions(-)

@@ -3958,32 +3958,16 @@ static int sctp_setsockopt_pr_supported(
 					unsigned int optlen)
 {
 	struct sctp_assoc_value params;
-	struct sctp_association *asoc;
-	int retval = -EINVAL;
 
 	if (optlen != sizeof(params))
-		goto out;
+		return -EINVAL;
 
-	if (copy_from_user(&params, optval, optlen)) {
-		retval = -EFAULT;
-		goto out;
-	}
+	if (copy_from_user(&params, optval, optlen))
+		return -EFAULT;
 
-	asoc = sctp_id2assoc(sk, params.assoc_id);
-	if (asoc) {
-		asoc->prsctp_enable = !!params.assoc_value;
-	} else if (!params.assoc_id) {
-		struct sctp_sock *sp = sctp_sk(sk);
+	sctp_sk(sk)->ep->prsctp_enable = !!params.assoc_value;
 
-		sp->ep->prsctp_enable = !!params.assoc_value;
-	} else {
-		goto out;
-	}
-
-	retval = 0;
-
-out:
-	return retval;
+	return 0;
 }
 
 static int sctp_setsockopt_default_prinfo(struct sock *sk,

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xin Long <[email protected]>

[ Upstream commit f8504f4ca0a0e9f84546ef86e00b24d2ea9a0bd2 ]

This issue happens when trying to add an existent tunnel. It doesn't call sock_put() before returning -EEXIST to release the sock refcnt that was held by calling sock_hold() before the existence check.

This patch is to fix it by holding the sock after doing the existence check.

---
 net/l2tp/l2tp_core.c |    9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

@@ -1490,12 +1490,7 @@ int l2tp_tunnel_register(struct l2tp_tun
 			goto err_sock;
 	}
 
-	sk = sock->sk;
-
-	sock_hold(sk);
-	tunnel->sock = sk;
 	tunnel->l2tp_net = net;
-
 	pn = l2tp_pernet(net);
 
 	spin_lock_bh(&pn->l2tp_tunnel_list_lock);

@@ -1510,6 +1505,10 @@ int l2tp_tunnel_register(struct l2tp_tun
 	list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list);
 	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
 
+	sk = sock->sk;
+	sock_hold(sk);
+	tunnel->sock = sk;
+
 	if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
 		struct udp_tunnel_sock_cfg udp_cfg = {
 			.sk_user_data = tunnel,

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Raed Salem <[email protected]>

[ Upstream commit f2b18732ee9863ac036759baf616ffa03c252ed5 ]

The commit "net/mlx5: Refactor accel IPSec code" introduced a bug where asynchronous short time change in hash key value by create/release SA context might happen during an asynchronous hash resize operation this could cause a subsequent remove SA context operation to fail as the key value used during resize is not the same key value used when remove SA context operation is invoked.

This commit fixes the bug by defining the SA context hash key such that it includes only fields that never change during the lifetime of the SA context object.

---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c |   10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

@@ -83,8 +83,14 @@ struct mlx5_fpga_ipsec_rule {
 };
 
 static const struct rhashtable_params rhash_sa = {
-	.key_len = FIELD_SIZEOF(struct mlx5_fpga_ipsec_sa_ctx, hw_sa),
-	.key_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hw_sa),
+	/* Keep out "cmd" field from the key as it's
+	 * value is not constant during the lifetime
+	 * of the key object.
+	 */
+	.key_len = FIELD_SIZEOF(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) -
+		   FIELD_SIZEOF(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd),
+	.key_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) +
+		      FIELD_SIZEOF(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd),
 	.head_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hash),
 	.automatic_shrinking = true,
 	.min_size = 1,

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Denis Drozdov <[email protected]>

[ Upstream commit acf3766b36d8e59ecbc307894c6d05703ee48014 ]

The mlx5e channels should be closed before mlx5i_uninit_underlay_qp puts the QP into RST (reset) state during mlx5i_close. Currently QP state incorrectly set to RST before channels got deactivated and closed, since mlx5_post_send request expects QP in RTS (Ready To Send) state.

The fix is to keep QP in RTS state until mlx5e channels get closed and to reset QP afterwards.

Also this fix is simply correct in order to keep the open/close flow symmetric, i.e mlx5i_init_underlay_qp() is called first thing at open, the correct thing to do is to call mlx5i_uninit_underlay_qp() last thing at close, which is exactly what this patch is doing.

---
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -502,9 +502,9 @@ static int mlx5i_close(struct net_device
 
 	netif_carrier_off(epriv->netdev);
 	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn);
-	mlx5i_uninit_underlay_qp(epriv);
 	mlx5e_deactivate_priv_channels(epriv);
 	mlx5e_close_channels(&epriv->channels);
+	mlx5i_uninit_underlay_qp(epriv);
 unlock:
 	mutex_unlock(&epriv->state_lock);
 	return 0;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andrew Lunn <[email protected]>

[ Upstream commit a9049ff9214da68df1179a7d5e36b43479abc9b8 ]

The mv88e6161 would sometime fail to probe with a timeout waiting for the switch to complete an operation. This operation is supposed to clear the statistics counters. However, due to a read/modify/write, without the needed mask, the operation actually carried out was more random, with invalid parameters, resulting in the switch not responding. We need to preserve the histogram mode bits, so apply a mask to keep them.

---
 drivers/net/dsa/mv88e6xxx/global1.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -567,6 +567,8 @@ int mv88e6xxx_g1_stats_clear(struct mv88
 	if (err)
 		return err;
 
+	/* Keep the histogram mode bits */
+	val &= MV88E6XXX_G1_STATS_OP_HIST_RX_TX;
 	val |= MV88E6XXX_G1_STATS_OP_BUSY | MV88E6XXX_G1_STATS_OP_FLUSH_ALL;
 
 	err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_STATS_OP, val);

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Holger Hoffstätte <[email protected]>

[ Upstream commit 0432e833191ad4d17b7fc2364941f91dad51db1a ]

Since 4.19 the following error in sysfs has appeared when using the r8169 NIC driver:

$cd /sys/module/realtek/drivers
$ls -l
ls: cannot access 'mdio_bus:RTL8201F 10/100Mbps Ethernet': No such file or directory [..garbled dir entries follow..]

Apparently the forward slash in "10/100Mbps Ethernet" is interpreted as directory separator that leads nowhere, and was introduced in commit 513588dd44b ("net: phy: realtek: add RTL8201F phy-id and functions").

Fix this by removing the offending slash in the driver name.

Other drivers in net/phy seem to have the same problem, but I cannot test/verify them.

---
 drivers/net/phy/realtek.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -220,7 +220,7 @@ static struct phy_driver realtek_drvs[]
 		.flags          = PHY_HAS_INTERRUPT,
 	}, {
 		.phy_id		= 0x001cc816,
-		.name		= "RTL8201F 10/100Mbps Ethernet",
+		.name		= "RTL8201F Fast Ethernet",
 		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_BASIC_FEATURES,
 		.flags		= PHY_HAS_INTERRUPT,

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xin Long <[email protected]>

[ Upstream commit 12480e3b16982c4026de10dd8155823219cd6391 ]

According to rfc8260#section-4.3.2, SCTP_SS_DEFAULT is required to defined as SCTP_SS_FCFS or SCTP_SS_RR.

SCTP_SS_FCFS is used for SCTP_SS_DEFAULT's value in this patch.

---
 include/uapi/linux/sctp.h |    1 +
 net/sctp/outqueue.c       |    2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

@@ -1151,6 +1151,7 @@ struct sctp_add_streams {
 /* SCTP Stream schedulers */
 enum sctp_sched_type {
 	SCTP_SS_FCFS,
+	SCTP_SS_DEFAULT = SCTP_SS_FCFS,
 	SCTP_SS_PRIO,
 	SCTP_SS_RR,
 	SCTP_SS_MAX = SCTP_SS_RR

@@ -212,7 +212,7 @@ void sctp_outq_init(struct sctp_associat
 	INIT_LIST_HEAD(&q->retransmit);
 	INIT_LIST_HEAD(&q->sacked);
 	INIT_LIST_HEAD(&q->abandoned);
-	sctp_sched_set_sched(asoc, SCTP_SS_FCFS);
+	sctp_sched_set_sched(asoc, SCTP_SS_DEFAULT);
 }
 
 /* Free the outqueue structure and any related pending chunks.

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tristram Ha <[email protected]>

[ Upstream commit 284fb78ed7572117846f8e1d1d8e3dbfd16880c2 ]

Initialize mutex before use. Avoid kernel complaint when CONFIG_DEBUG_LOCK_ALLOC is enabled.

---
 drivers/net/dsa/microchip/ksz_common.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

@@ -1117,11 +1117,6 @@ static int ksz_switch_init(struct ksz_de
 {
 	int i;
 
-	mutex_init(&dev->reg_mutex);
-	mutex_init(&dev->stats_mutex);
-	mutex_init(&dev->alu_mutex);
-	mutex_init(&dev->vlan_mutex);
-
 	dev->ds->ops = &ksz_switch_ops;
 
 	for (i = 0; i < ARRAY_SIZE(ksz_switch_chips); i++) {

@@ -1206,6 +1201,11 @@ int ksz_switch_register(struct ksz_devic
 	if (dev->pdata)
 		dev->chip_id = dev->pdata->chip_id;
 
+	mutex_init(&dev->reg_mutex);
+	mutex_init(&dev->stats_mutex);
+	mutex_init(&dev->alu_mutex);
+	mutex_init(&dev->vlan_mutex);
+
 	if (ksz_switch_detect(dev))
 		return -EINVAL;
 

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xin Long <[email protected]>

[ Upstream commit fd82d61ba142f0b83463e47064bf5460aac57b6e ]

As defined in rfc6525#section-6.1.3, SCTP_STREAM_CHANGE_DENIED and SCTP_STREAM_CHANGE_FAILED should be used instead of SCTP_ASSOC_CHANGE_DENIED and SCTP_ASSOC_CHANGE_FAILED.

To keep the compatibility, fix it by adding two macros.

---
 include/uapi/linux/sctp.h |    2 ++
 1 file changed, 2 insertions(+)

@@ -568,6 +568,8 @@ struct sctp_assoc_reset_event {
 
 #define SCTP_ASSOC_CHANGE_DENIED	0x0004
 #define SCTP_ASSOC_CHANGE_FAILED	0x0008
+#define SCTP_STREAM_CHANGE_DENIED	SCTP_ASSOC_CHANGE_DENIED
+#define SCTP_STREAM_CHANGE_FAILED	SCTP_ASSOC_CHANGE_FAILED
 struct sctp_stream_change_event {
 	__u16 strchange_type;
 	__u16 strchange_flags;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Stephen Mallon <[email protected]>

[ Upstream commit cadf9df27e7cf40e390e060a1c71bb86ecde798b ]

During tcp coalescing ensure that the skb hardware timestamp refers to the highest sequence number data.
Previously only the software timestamp was updated during coalescing.

---
 net/ipv4/tcp_input.c |    1 +
 1 file changed, 1 insertion(+)

@@ -4371,6 +4371,7 @@ static bool tcp_try_coalesce(struct sock
 	if (TCP_SKB_CB(from)->has_rxtstamp) {
 		TCP_SKB_CB(to)->has_rxtstamp = true;
 		to->tstamp = from->tstamp;
+		skb_hwtstamps(to)->hwtstamp = skb_hwtstamps(from)->hwtstamp;
 	}
 
 	return true;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Martin Schiller <[email protected]>

[ Upstream commit df5a8ec64eed7fe45b556cfff503acd6429ab817 ]

Up until commit 7e5fbd1e0700 ("net: mdio-gpio: Convert to use gpiod functions where possible"), the _cansleep variants of the gpio_ API was used. After that commit and the change to gpiod_ API, the _cansleep() was dropped. This then results in WARN_ON() when used with GPIO devices which do sleep. Add back the _cansleep() to avoid this.

---
 drivers/net/phy/mdio-gpio.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

@@ -63,7 +63,7 @@ static void mdio_dir(struct mdiobb_ctrl
 		 * assume the pin serves as pull-up. If direction is
 		 * output, the default value is high.
 		 */
-		gpiod_set_value(bitbang->mdo, 1);
+		gpiod_set_value_cansleep(bitbang->mdo, 1);
 		return;
 	}
 

@@ -78,7 +78,7 @@ static int mdio_get(struct mdiobb_ctrl *
 	struct mdio_gpio_info *bitbang =
 		container_of(ctrl, struct mdio_gpio_info, ctrl);
 
-	return gpiod_get_value(bitbang->mdio);
+	return gpiod_get_value_cansleep(bitbang->mdio);
 }
 
 static void mdio_set(struct mdiobb_ctrl *ctrl, int what)

@@ -87,9 +87,9 @@ static void mdio_set(struct mdiobb_ctrl
 		container_of(ctrl, struct mdio_gpio_info, ctrl);
 
 	if (bitbang->mdo)
-		gpiod_set_value(bitbang->mdo, what);
+		gpiod_set_value_cansleep(bitbang->mdo, what);
 	else
-		gpiod_set_value(bitbang->mdio, what);
+		gpiod_set_value_cansleep(bitbang->mdio, what);
 }
 
 static void mdc_set(struct mdiobb_ctrl *ctrl, int what)

@@ -97,7 +97,7 @@ static void mdc_set(struct mdiobb_ctrl *
 	struct mdio_gpio_info *bitbang =
 		container_of(ctrl, struct mdio_gpio_info, ctrl);
 
-	gpiod_set_value(bitbang->mdc, what);
+	gpiod_set_value_cansleep(bitbang->mdc, what);
 }
 
 static const struct mdiobb_ops mdio_gpio_ops = {

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xin Long <[email protected]>

[ Upstream commit e1e46479847e66f78f79d8c24d5169a5954b3fc2 ]

Different from processing the addstrm_out request, The receiver handles an addstrm_in request by sending back an addstrm_out request to the sender who will increase its stream's in and incnt later.

Now stream->incnt has been increased since it sent out the addstrm_in request in sctp_send_add_streams(), with the wrong stream->incnt will even cause crash when copying stream info from the old stream's in to the new one's in sctp_process_strreset_addstrm_out().

This patch is to fix it by simply removing the stream->incnt change from sctp_send_add_streams().

---
 net/sctp/stream.c |    1 -
 1 file changed, 1 deletion(-)

@@ -535,7 +535,6 @@ int sctp_send_add_streams(struct sctp_as
 		goto out;
 	}
 
-	stream->incnt = incnt;
 	stream->outcnt = outcnt;
 
 	asoc->strreset_outstanding = !!out + !!in;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shalom Toledo <[email protected]>

[ Upstream commit 96801552f846460fe9ac10f1b189602992f004e1 ]

The CPU policer used to police packets being trapped via a local route (IP2ME) was incorrectly configured to police based on bytes per second instead of packets per second.

Change the policer to police based on packets per second and avoid packet loss under certain circumstances.

---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c |    1 -
 1 file changed, 1 deletion(-)

@@ -3519,7 +3519,6 @@ static int mlxsw_sp_cpu_policers_set(str
 			burst_size = 7;
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME:
-			is_bytes = true;
 			rate = 4 * 1024;
 			burst_size = 4;
 			break;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Stefan Wahren <[email protected]>

[ Upstream commit 85b18b0237ce9986a81a1b9534b5e2ee116f5504 ]

The commit f77f0aee4da4 ("net: use core MTU range checking in USB NIC drivers") introduce a common MTU handling for usbnet. But it's missing the necessary changes for smsc95xx. So set the MTU range accordingly.

This patch has been tested on a Raspberry Pi 3.

---
 drivers/net/usb/smsc95xx.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -1321,6 +1321,8 @@ static int smsc95xx_bind(struct usbnet *
 	dev->net->ethtool_ops = &smsc95xx_ethtool_ops;
 	dev->net->flags |= IFF_MULTICAST;
 	dev->net->hard_header_len += SMSC95XX_TX_OVERHEAD_CSUM;
+	dev->net->min_mtu = ETH_MIN_MTU;
+	dev->net->max_mtu = ETH_DATA_LEN;
 	dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len;
 
 	pdata->dev = dev;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Frieder Schrempf <[email protected]>

[ Upstream commit 7b900ead6cc66b2ee873cb042dfba169aa68b56c ]

We need to make sure, that the carrier check polling is disabled while suspending. Otherwise we can end up with usbnet_read_cmd() being issued when only usbnet_read_cmd_nopm() is allowed. If this happens, read operations lock up.

---
 drivers/net/usb/smsc95xx.c |    7 +++++++
 1 file changed, 7 insertions(+)

@@ -1600,6 +1600,8 @@ static int smsc95xx_suspend(struct usb_i
 		return ret;
 	}
 
+	cancel_delayed_work_sync(&pdata->carrier_check);
+
 	if (pdata->suspend_flags) {
 		netdev_warn(dev->net, "error during last resume\n");
 		pdata->suspend_flags = 0;

@@ -1842,6 +1844,11 @@ done:
 	 */
 	if (ret && PMSG_IS_AUTO(message))
 		usbnet_resume(intf);
+
+	if (ret)
+		schedule_delayed_work(&pdata->carrier_check,
+				      CARRIER_CHECK_DELAY);
+
 	return ret;
 }
 

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Greg Kroah-Hartman <[email protected]>

This reverts commit 233b9d7df0e114c7e7c3674559fb0fc41ada3e8f which is commit 53c613fe6349994f023245519265999eed75957f upstream.

It's not ready for the stable trees as there are major slowdowns involved with this patch.

---
 arch/x86/kernel/cpu/bugs.c |   57 ++++-----------------------------------------
 kernel/cpu.c               |   11 --------
 2 files changed, 7 insertions(+), 61 deletions(-)

@@ -35,10 +35,12 @@ static void __init spectre_v2_select_mit
 static void __init ssb_select_mitigation(void);
 static void __init l1tf_select_mitigation(void);
 
-/* The base value of the SPEC_CTRL MSR that always has to be preserved. */
-u64 x86_spec_ctrl_base;
+/*
+ * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any
+ * writes to SPEC_CTRL contain whatever reserved bits have been set.
+ */
+u64 __ro_after_init x86_spec_ctrl_base;
 EXPORT_SYMBOL_GPL(x86_spec_ctrl_base);
-static DEFINE_MUTEX(spec_ctrl_mutex);
 
 /*
  * The vendor and possibly platform specific bits which can be modified in

@@ -323,46 +325,6 @@ static enum spectre_v2_mitigation_cmd __
 	return cmd;
 }
 
-static bool stibp_needed(void)
-{
-	if (spectre_v2_enabled == SPECTRE_V2_NONE)
-		return false;
-
-	if (!boot_cpu_has(X86_FEATURE_STIBP))
-		return false;
-
-	return true;
-}
-
-static void update_stibp_msr(void *info)
-{
-	wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
-}
-
-void arch_smt_update(void)
-{
-	u64 mask;
-
-	if (!stibp_needed())
-		return;
-
-	mutex_lock(&spec_ctrl_mutex);
-	mask = x86_spec_ctrl_base;
-	if (cpu_smt_control == CPU_SMT_ENABLED)
-		mask |= SPEC_CTRL_STIBP;
-	else
-		mask &= ~SPEC_CTRL_STIBP;
-
-	if (mask != x86_spec_ctrl_base) {
-		pr_info("Spectre v2 cross-process SMT mitigation: %s STIBP\n",
-				cpu_smt_control == CPU_SMT_ENABLED ?
-				"Enabling" : "Disabling");
-		x86_spec_ctrl_base = mask;
-		on_each_cpu(update_stibp_msr, NULL, 1);
-	}
-	mutex_unlock(&spec_ctrl_mutex);
-}
-
 static void __init spectre_v2_select_mitigation(void)
 {
 	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();

@@ -462,9 +424,6 @@ specv2_set_mode:
 		setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
 		pr_info("Enabling Restricted Speculation for firmware calls\n");
 	}
-
-	/* Enable STIBP if appropriate */
-	arch_smt_update();
 }
 
 #undef pr_fmt

@@ -855,8 +814,6 @@ static ssize_t l1tf_show_state(char *buf
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {
-	int ret;
-
 	if (!boot_cpu_has_bug(bug))
 		return sprintf(buf, "Not affected\n");
 

@@ -874,12 +831,10 @@ static ssize_t cpu_show_common(struct de
 		return sprintf(buf, "Mitigation: __user pointer sanitization\n");
 
 	case X86_BUG_SPECTRE_V2:
-		ret = sprintf(buf, "%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+		return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
 			       boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
 			       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
-			       (x86_spec_ctrl_base & SPEC_CTRL_STIBP) ? ", STIBP" : "",
 			       spectre_v2_module_string());
-		return ret;
 
 	case X86_BUG_SPEC_STORE_BYPASS:
 		return sprintf(buf, "%s\n", ssb_strings[ssb_mode]);

@@ -2026,12 +2026,6 @@ static void cpuhp_online_cpu_device(unsi
 	kobject_uevent(&dev->kobj, KOBJ_ONLINE);
 }
 
-/*
- * Architectures that need SMT-specific errata handling during SMT hotplug
- * should override this.
- */
-void __weak arch_smt_update(void) { };
-
 static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
 {
 	int cpu, ret = 0;

@@ -2058,10 +2052,8 @@ static int cpuhp_smt_disable(enum cpuhp_
 		 */
 		cpuhp_offline_cpu_device(cpu);
 	}
-	if (!ret) {
+	if (!ret)
 		cpu_smt_control = ctrlval;
-		arch_smt_update();
-	}
 	cpu_maps_update_done();
 	return ret;
 }

@@ -2072,7 +2064,6 @@ static int cpuhp_smt_enable(void)
 
 	cpu_maps_update_begin();
 	cpu_smt_control = CPU_SMT_ENABLED;
-	arch_smt_update();
 	for_each_present_cpu(cpu) {
 		/* Skip online CPUs and CPUs on offline nodes */
 		if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Siva Reddy Kallam <[email protected]>

[ Upstream commit 59663e42199c93d1d7314d1446f6782fc4b1eb81 ]

This patch has the fix to avoid PHY lockup with 5717/5719/5720 in change ring and flow control paths. This patch solves the RX hang while doing continuous ring or flow control parameters with heavy traffic from peer.

---
 drivers/net/ethernet/broadcom/tg3.c |   18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

@@ -12426,6 +12426,7 @@ static int tg3_set_ringparam(struct net_
 {
 	struct tg3 *tp = netdev_priv(dev);
 	int i, irq_sync = 0, err = 0;
+	bool reset_phy = false;
 
 	if ((ering->rx_pending > tp->rx_std_ring_mask) ||
 	    (ering->rx_jumbo_pending > tp->rx_jmb_ring_mask) ||

@@ -12457,7 +12458,13 @@ static int tg3_set_ringparam(struct net_
 
 	if (netif_running(dev)) {
 		tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
-		err = tg3_restart_hw(tp, false);
+		/* Reset PHY to avoid PHY lock up */
+		if (tg3_asic_rev(tp) == ASIC_REV_5717 ||
+		    tg3_asic_rev(tp) == ASIC_REV_5719 ||
+		    tg3_asic_rev(tp) == ASIC_REV_5720)
+			reset_phy = true;
+
+		err = tg3_restart_hw(tp, reset_phy);
 		if (!err)
 			tg3_netif_start(tp);
 	}

@@ -12491,6 +12498,7 @@ static int tg3_set_pauseparam(struct net
 {
 	struct tg3 *tp = netdev_priv(dev);
 	int err = 0;
+	bool reset_phy = false;
 
 	if (tp->link_config.autoneg == AUTONEG_ENABLE)
 		tg3_warn_mgmt_link_flap(tp);

@@ -12581,7 +12589,13 @@ static int tg3_set_pauseparam(struct net
 
 		if (netif_running(dev)) {
 			tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
-			err = tg3_restart_hw(tp, false);
+			/* Reset PHY to avoid PHY lock up */
+			if (tg3_asic_rev(tp) == ASIC_REV_5717 ||
+			    tg3_asic_rev(tp) == ASIC_REV_5719 ||
+			    tg3_asic_rev(tp) == ASIC_REV_5720)
+				reset_phy = true;
+
+			err = tg3_restart_hw(tp, reset_phy);
 			if (!err)
 				tg3_netif_start(tp);
 		}

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jon Maloy <[email protected]>

[ Upstream commit 1c1274a56999fbdf9cf84e332b28448bb2d55221 ]

The code for reading ancillary data from a received buffer is assuming the buffer is linear. To make this assumption true we have to linearize the buffer before message data is read.

---
 net/tipc/socket.c |   15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

@@ -1548,16 +1548,17 @@ static void tipc_sk_set_orig_addr(struct
 /**
  * tipc_sk_anc_data_recv - optionally capture ancillary data for received message
  * @m: descriptor for message info
- * @msg: received message header
+ * @skb: received message buffer
  * @tsk: TIPC port associated with message
  *
  * Note: Ancillary data is not captured if not requested by receiver.
  *
  * Returns 0 if successful, otherwise errno
  */
-static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
+static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb,
 				 struct tipc_sock *tsk)
 {
+	struct tipc_msg *msg;
 	u32 anc_data[3];
 	u32 err;
 	u32 dest_type;

@@ -1566,6 +1567,7 @@ static int tipc_sk_anc_data_recv(struct
 
 	if (likely(m->msg_controllen == 0))
 		return 0;
+	msg = buf_msg(skb);
 
 	/* Optionally capture errored message object(s) */
 	err = msg ? msg_errcode(msg) : 0;

@@ -1576,6 +1578,9 @@ static int tipc_sk_anc_data_recv(struct
 		if (res)
 			return res;
 		if (anc_data[1]) {
+			if (skb_linearize(skb))
+				return -ENOMEM;
+			msg = buf_msg(skb);
 			res = put_cmsg(m, SOL_TIPC, TIPC_RETDATA, anc_data[1],
 				       msg_data(msg));
 			if (res)

@@ -1737,9 +1742,10 @@ static int tipc_recvmsg(struct socket *s
 
 	/* Collect msg meta data, including error code and rejected data */
 	tipc_sk_set_orig_addr(m, skb);
-	rc = tipc_sk_anc_data_recv(m, hdr, tsk);
+	rc = tipc_sk_anc_data_recv(m, skb, tsk);
 	if (unlikely(rc))
 		goto exit;
+	hdr = buf_msg(skb);
 
 	/* Capture data if non-error msg, otherwise just set return value */
 	if (likely(!err)) {

@@ -1849,9 +1855,10 @@ static int tipc_recvstream(struct socket
 		/* Collect msg meta data, incl. error code and rejected data */
 		if (!copied) {
 			tipc_sk_set_orig_addr(m, skb);
-			rc = tipc_sk_anc_data_recv(m, hdr, tsk);
+			rc = tipc_sk_anc_data_recv(m, skb, tsk);
 			if (rc)
 				break;
+			hdr = buf_msg(skb);
 		}
 
 		/* Copy data if msg ok, otherwise return error/partial data */

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jon Maloy <[email protected]>

[ Upstream commit adba75be0d23cca92a028749d92c60c8909bbdb3 ]

We get the following warning:

[   47.926140] 32-bit node address hash set to 2010a0a
[   47.927202]
[   47.927433] ================================
[   47.928050] WARNING: inconsistent lock state
[   47.928661] 4.19.0+ #37 Tainted: G            E
[   47.929346] --------------------------------
[   47.929954] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
[   47.930116] swapper/3/0 [HC0[0]:SC1[3]:HE1:SE0] takes:
[   47.930116] 00000000af8bc31e (&(&ht->lock)->rlock){+.?.}, at: rhashtable_walk_enter+0x36/0xb0
[   47.930116] {SOFTIRQ-ON-W} state was registered at:
[   47.930116]   _raw_spin_lock+0x29/0x60
[   47.930116]   rht_deferred_worker+0x556/0x810
[   47.930116]   process_one_work+0x1f5/0x540
[   47.930116]   worker_thread+0x64/0x3e0
[   47.930116]   kthread+0x112/0x150
[   47.930116]   ret_from_fork+0x3a/0x50
[   47.930116] irq event stamp: 14044
[   47.930116] hardirqs last  enabled at (14044): [<ffffffff9a07fbba>] __local_bh_enable_ip+0x7a/0xf0
[   47.938117] hardirqs last disabled at (14043): [<ffffffff9a07fb81>] __local_bh_enable_ip+0x41/0xf0
[   47.938117] softirqs last  enabled at (14028): [<ffffffff9a0803ee>] irq_enter+0x5e/0x60
[   47.938117] softirqs last disabled at (14029): [<ffffffff9a0804a5>] irq_exit+0xb5/0xc0
[   47.938117]
[   47.938117] other info that might help us debug this:
[   47.938117]  Possible unsafe locking scenario:
[   47.938117]
[   47.938117]        CPU0
[   47.938117]        ----
[   47.938117]   lock(&(&ht->lock)->rlock);
[   47.938117]   <Interrupt>
[   47.938117]     lock(&(&ht->lock)->rlock);
[   47.938117]
[   47.938117]  *** DEADLOCK ***
[   47.938117]
[   47.938117] 2 locks held by swapper/3/0:
[   47.938117]  #0: 0000000062c64f90 ((&d->timer)){+.-.}, at: call_timer_fn+0x5/0x280
[   47.938117]  #1: 00000000ee39619c (&(&d->lock)->rlock){+.-.}, at: tipc_disc_timeout+0xc8/0x540 [tipc]
[   47.938117]
[   47.938117] stack backtrace:
[   47.938117] CPU: 3 PID: 0 Comm: swapper/3 Tainted: G            E     4.19.0+ #37
[   47.938117] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[   47.938117] Call Trace:
[   47.938117]  <IRQ>
[   47.938117]  dump_stack+0x5e/0x8b
[   47.938117]  print_usage_bug+0x1ed/0x1ff
[   47.938117]  mark_lock+0x5b5/0x630
[   47.938117]  __lock_acquire+0x4c0/0x18f0
[   47.938117]  ? lock_acquire+0xa6/0x180
[   47.938117]  lock_acquire+0xa6/0x180
[   47.938117]  ? rhashtable_walk_enter+0x36/0xb0
[   47.938117]  _raw_spin_lock+0x29/0x60
[   47.938117]  ? rhashtable_walk_enter+0x36/0xb0
[   47.938117]  rhashtable_walk_enter+0x36/0xb0
[   47.938117]  tipc_sk_reinit+0xb0/0x410 [tipc]
[   47.938117]  ? mark_held_locks+0x6f/0x90
[   47.938117]  ? __local_bh_enable_ip+0x7a/0xf0
[   47.938117]  ? lockdep_hardirqs_on+0x20/0x1a0
[   47.938117]  tipc_net_finalize+0xbf/0x180 [tipc]
[   47.938117]  tipc_disc_timeout+0x509/0x540 [tipc]
[   47.938117]  ? call_timer_fn+0x5/0x280
[   47.938117]  ? tipc_disc_msg_xmit.isra.19+0xa0/0xa0 [tipc]
[   47.938117]  ? tipc_disc_msg_xmit.isra.19+0xa0/0xa0 [tipc]
[   47.938117]  call_timer_fn+0xa1/0x280
[   47.938117]  ? tipc_disc_msg_xmit.isra.19+0xa0/0xa0 [tipc]
[   47.938117]  run_timer_softirq+0x1f2/0x4d0
[   47.938117]  __do_softirq+0xfc/0x413
[   47.938117]  irq_exit+0xb5/0xc0
[   47.938117]  smp_apic_timer_interrupt+0xac/0x210
[   47.938117]  apic_timer_interrupt+0xf/0x20
[   47.938117]  </IRQ>
[   47.938117] RIP: 0010:default_idle+0x1c/0x140
[   47.938117] Code: 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 41 54 55 53 65 8b 2d d8 2b 74 65 0f 1f 44 00 00 e8 c6 2c 8b ff fb f4 <65> 8b 2d c5 2b 74 65 0f 1f 44 00 00 5b 5d 41 5c c3 65 8b 05 b4 2b
[   47.938117] RSP: 0018:ffffaf6ac0207ec8 EFLAGS: 00000206 ORIG_RAX: ffffffffffffff13
[   47.938117] RAX: ffff8f5b3735e200 RBX: 0000000000000003 RCX: 0000000000000001
[   47.938117] RDX: 0000000000000001 RSI: 0000000000000001 RDI: ffff8f5b3735e200
[   47.938117] RBP: 0000000000000003 R08: 0000000000000001 R09: 0000000000000000
[   47.938117] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
[   47.938117] R13: 0000000000000000 R14: ffff8f5b3735e200 R15: ffff8f5b3735e200
[   47.938117]  ? default_idle+0x1a/0x140
[   47.938117]  do_idle+0x1bc/0x280
[   47.938117]  cpu_startup_entry+0x19/0x20
[   47.938117]  start_secondary+0x187/0x1c0
[   47.938117]  secondary_startup_64+0xa4/0xb0

The reason seems to be that tipc_net_finalize()->tipc_sk_reinit() is calling the function rhashtable_walk_enter() within a timer interrupt. We fix this by executing tipc_net_finalize() in work queue context.

---
 net/tipc/discover.c |   19 ++++++++++---------
 net/tipc/net.c      |   45 +++++++++++++++++++++++++++++++++++++--------
 net/tipc/net.h      |    2 +-
 3 files changed, 48 insertions(+), 18 deletions(-)

@@ -166,7 +166,8 @@ static bool tipc_disc_addr_trial_msg(str
 
 	/* Apply trial address if we just left trial period */
 	if (!trial && !self) {
-		tipc_net_finalize(net, tn->trial_addr);
+		tipc_sched_net_finalize(net, tn->trial_addr);
+		msg_set_prevnode(buf_msg(d->skb), tn->trial_addr);
 		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
 	}
 

@@ -300,14 +301,12 @@ static void tipc_disc_timeout(struct tim
 		goto exit;
 	}
 
-	/* Trial period over ? */
-	if (!time_before(jiffies, tn->addr_trial_end)) {
-		/* Did we just leave it ? */
-		if (!tipc_own_addr(net))
-			tipc_net_finalize(net, tn->trial_addr);
-
-		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
-		msg_set_prevnode(buf_msg(d->skb), tipc_own_addr(net));
+	/* Did we just leave trial period ? */
+	if (!time_before(jiffies, tn->addr_trial_end) && !tipc_own_addr(net)) {
+		mod_timer(&d->timer, jiffies + TIPC_DISC_INIT);
+		spin_unlock_bh(&d->lock);
+		tipc_sched_net_finalize(net, tn->trial_addr);
+		return;
 	}
 
 	/* Adjust timeout interval according to discovery phase */

@@ -319,6 +318,8 @@ static void tipc_disc_timeout(struct tim
 			d->timer_intv = TIPC_DISC_SLOW;
 		else if (!d->num_nodes && d->timer_intv > TIPC_DISC_FAST)
 			d->timer_intv = TIPC_DISC_FAST;
+		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
+		msg_set_prevnode(buf_msg(d->skb), tn->trial_addr);
 	}
 
 	mod_timer(&d->timer, jiffies + d->timer_intv);

@@ -42,7 +42,7 @@
 extern const struct nla_policy tipc_nl_net_policy[];
 
 int tipc_net_init(struct net *net, u8 *node_id, u32 addr);
-void tipc_net_finalize(struct net *net, u32 addr);
+void tipc_sched_net_finalize(struct net *net, u32 addr);
 void tipc_net_stop(struct net *net);
 int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb);
 int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info);

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Matthew Cover <[email protected]>

[ Upstream commit 8ebebcba559a1bfbaec7bbda64feb9870b9c58da ]

When writing packets to a descriptor associated with a combined queue, the packets should end up on that queue.

Before this change all packets written to any descriptor associated with a tap interface end up on rx-0, even when the descriptor is associated with a different queue.

The rx traffic can be generated by either of the following.
1. a simple tap program which spins up multiple queues and writes packets to each of the file descriptors
2. tx from a qemu vm with a tap multiqueue netdev

The queue for rx traffic can be observed by either of the following (done on the hypervisor in the qemu case).
1. a simple netmap program which opens and reads from per-queue descriptors
2. configuring RPS and doing per-cpu captures with rxtxcpu

Alternatively, if you printk() the return value of skb_get_rx_queue() just before each instance of netif_receive_skb() in tun.c, you will get 65535 for every skb.

Calling skb_record_rx_queue() to set the rx queue to the queue_index fixes the association between descriptor and rx queue.

---
 drivers/net/tun.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

@@ -1527,6 +1527,7 @@ static void tun_rx_batched(struct tun_st
 
 	if (!rx_batched || (!more && skb_queue_empty(queue))) {
 		local_bh_disable();
+		skb_record_rx_queue(skb, tfile->queue_index);
 		netif_receive_skb(skb);
 		local_bh_enable();
 		return;

@@ -1546,8 +1547,11 @@ static void tun_rx_batched(struct tun_st
 		struct sk_buff *nskb;
 
 		local_bh_disable();
-		while ((nskb = __skb_dequeue(&process_queue)))
+		while ((nskb = __skb_dequeue(&process_queue))) {
+			skb_record_rx_queue(nskb, tfile->queue_index);
 			netif_receive_skb(nskb);
+		}
+		skb_record_rx_queue(skb, tfile->queue_index);
 		netif_receive_skb(skb);
 		local_bh_enable();
 	}

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Florian Fainelli <[email protected]>

[ Upstream commit 7cb6a2a2c72c1ed8f42fb01f1a661281b568dead ]

A timing hazard exists when the network interface is stopped that allows a watchdog timeout to be processed by a separate core in parallel. This creates the potential for the timeout handler to wake the queues while the driver is shutting down, or access registers after their clocks have been removed.

The more common case is that the watchdog timeout will produce a warning message which doesn't lead to a crash. The chances of this are greatly increased by the fact that bcm_sysport_netif_stop stops the transmit queues which can easily precipitate a watchdog time- out because of stale trans_start data in the queues.

This commit corrects the behavior by ensuring that the watchdog timeout is disabled before enterring bcm_sysport_netif_stop. There are currently only two users of the bcm_sysport_netif_stop function:
close and suspend.

The close case already handles the issue by exiting the RUNNING state before invoking the driver close service.

The suspend case now performs the netif_device_detach to exit the PRESENT state before the call to bcm_sysport_netif_stop rather than after it.

These behaviors prevent any future scheduling of the driver timeout service during the window. The netif_tx_stop_all_queues function in bcm_sysport_netif_stop is replaced with netif_tx_disable to ensure synchronization with any transmit or timeout threads that may already be executing on other cores.

For symmetry, the netif_device_attach call upon resume is moved to after the call to bcm_sysport_netif_start. Since it wakes the transmit queues it is not necessary to invoke netif_tx_start_all_queues from bcm_sysport_netif_start so it is moved into the driver open service.

---
 drivers/net/ethernet/broadcom/bcmsysport.c |   15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

@@ -1897,9 +1897,6 @@ static void bcm_sysport_netif_start(stru
 		intrl2_1_mask_clear(priv, 0xffffffff);
 	else
 		intrl2_0_mask_clear(priv, INTRL2_0_TDMA_MBDONE_MASK);
-
-	/* Last call before we start the real business */
-	netif_tx_start_all_queues(dev);
 }
 
 static void rbuf_init(struct bcm_sysport_priv *priv)

@@ -2045,6 +2042,8 @@ static int bcm_sysport_open(struct net_d
 
 	bcm_sysport_netif_start(dev);
 
+	netif_tx_start_all_queues(dev);
+
 	return 0;
 
 out_clear_rx_int:

@@ -2068,7 +2067,7 @@ static void bcm_sysport_netif_stop(struc
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 
 	/* stop all software from updating hardware */
-	netif_tx_stop_all_queues(dev);
+	netif_tx_disable(dev);
 	napi_disable(&priv->napi);
 	cancel_work_sync(&priv->dim.dim.work);
 	phy_stop(dev->phydev);

@@ -2654,12 +2653,12 @@ static int __maybe_unused bcm_sysport_su
 	if (!netif_running(dev))
 		return 0;
 
+	netif_device_detach(dev);
+
 	bcm_sysport_netif_stop(dev);
 
 	phy_suspend(dev->phydev);
 
-	netif_device_detach(dev);
-
 	/* Disable UniMAC RX */
 	umac_enable_set(priv, CMD_RX_EN, 0);
 

@@ -2743,8 +2742,6 @@ static int __maybe_unused bcm_sysport_re
 		goto out_free_rx_ring;
 	}
 
-	netif_device_attach(dev);
-
 	/* RX pipe enable */
 	topctrl_writel(priv, 0, RX_FLUSH_CNTL);
 

@@ -2789,6 +2786,8 @@ static int __maybe_unused bcm_sysport_re
 
 	bcm_sysport_netif_start(dev);
 
+	netif_device_attach(dev);
+
 	return 0;
 
 out_free_rx_ring:

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Davide Caratti <[email protected]>

[ Upstream commit 19ab69107d3ecfb7cd3e38ad262a881be40c01a3 ]

tcf_idr_check_alloc() can return a negative value, on allocation failures (-ENOMEM) or IDR exhaustion (-ENOSPC): don't leak keys_ex in these cases.

---
 net/sched/act_pedit.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -201,7 +201,8 @@ static int tcf_pedit_init(struct net *ne
 			goto out_release;
 		}
 	} else {
-		return err;
+		ret = err;
+		goto out_free;
 	}
 
 	p = to_pedit(*a);

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Doug Berger <[email protected]>

A timing hazard exists when the network interface is stopped that allows a watchdog timeout to be processed by a separate core in parallel. This creates the potential for the timeout handler to wake the queues while the driver is shutting down, or access registers after their clocks have been removed.

The more common case is that the watchdog timeout will produce a warning message which doesn't lead to a crash. The chances of this are greatly increased by the fact that bcmgenet_netif_stop stops the transmit queues which can easily precipitate a watchdog time- out because of stale trans_start data in the queues.

This commit corrects the behavior by ensuring that the watchdog timeout is disabled before enterring bcmgenet_netif_stop. There are currently only two users of the bcmgenet_netif_stop function:
close and suspend.

The close case already handles the issue by exiting the RUNNING state before invoking the driver close service.

The suspend case now performs the netif_device_detach to exit the PRESENT state before the call to bcmgenet_netif_stop rather than after it.

These behaviors prevent any future scheduling of the driver timeout service during the window. The netif_tx_stop_all_queues function in bcmgenet_netif_stop is replaced with netif_tx_disable to ensure synchronization with any transmit or timeout threads that may already be executing on other cores.

For symmetry, the netif_device_attach call upon resume is moved to after the call to bcmgenet_netif_start. Since it wakes the transmit queues it is not necessary to invoke netif_tx_start_all_queues from bcmgenet_netif_start so it is moved into the driver open service.

[ Upstream commit 09e805d2570a3a94f13dd9c9ad2bcab23da76e09 ]

---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c |   13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

@@ -2855,7 +2855,6 @@ static void bcmgenet_netif_start(struct
 
 	umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, true);
 
-	netif_tx_start_all_queues(dev);
 	bcmgenet_enable_tx_napi(priv);
 
 	/* Monitor link interrupts now */

@@ -2937,6 +2936,8 @@ static int bcmgenet_open(struct net_devi
 
 	bcmgenet_netif_start(dev);
 
+	netif_tx_start_all_queues(dev);
+
 	return 0;
 
 err_irq1:

@@ -2958,7 +2959,7 @@ static void bcmgenet_netif_stop(struct n
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 
 	bcmgenet_disable_tx_napi(priv);
-	netif_tx_stop_all_queues(dev);
+	netif_tx_disable(dev);
 
 	/* Disable MAC receive */
 	umac_enable_set(priv, CMD_RX_EN, false);

@@ -3620,13 +3621,13 @@ static int bcmgenet_suspend(struct devic
 	if (!netif_running(dev))
 		return 0;
 
+	netif_device_detach(dev);
+
 	bcmgenet_netif_stop(dev);
 
 	if (!device_may_wakeup(d))
 		phy_suspend(dev->phydev);
 
-	netif_device_detach(dev);
-
 	/* Prepare the device for Wake-on-LAN and switch to the slow clock */
 	if (device_may_wakeup(d) && priv->wolopts) {
 		ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC);

@@ -3700,8 +3701,6 @@ static int bcmgenet_resume(struct device
 	/* Always enable ring 16 - descriptor ring */
 	bcmgenet_enable_dma(priv, dma_ctrl);
 
-	netif_device_attach(dev);
-
 	if (!device_may_wakeup(d))
 		phy_resume(dev->phydev);
 

@@ -3710,6 +3709,8 @@ static int bcmgenet_resume(struct device
 
 	bcmgenet_netif_start(dev);
 
+	netif_device_attach(dev);
+
 	return 0;
 
 out_clk_disable:

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Subash Abhinov Kasiviswanathan <[email protected]>

[ Upstream commit d02854dc1999ed3e7fd79ec700c64ac23ac0c458 ]

A null dereference was observed when a sysctl was being set from userspace and rmnet was stuck trying to complete some actions in the NETDEV_REGISTER callback. This is because the real_dev is set only after the device registration handler completes.

sysctl call stack -

<6> Unable to handle kernel NULL pointer dereference at

    virtual address 00000108
<2> pc : rmnet_vnd_get_iflink+0x1c/0x28
<2> lr : dev_get_iflink+0x2c/0x40
<2>  rmnet_vnd_get_iflink+0x1c/0x28
<2>  inet6_fill_ifinfo+0x15c/0x234
<2>  inet6_ifinfo_notify+0x68/0xd4
<2>  ndisc_ifinfo_sysctl_change+0x1b8/0x234
<2>  proc_sys_call_handler+0xac/0x100
<2>  proc_sys_write+0x3c/0x4c
<2>  __vfs_write+0x54/0x14c
<2>  vfs_write+0xcc/0x188
<2>  SyS_write+0x60/0xc0
<2>  el0_svc_naked+0x34/0x38

device register call stack -

<2>  notifier_call_chain+0x84/0xbc
<2>  raw_notifier_call_chain+0x38/0x48
<2>  call_netdevice_notifiers_info+0x40/0x70
<2>  call_netdevice_notifiers+0x38/0x60
<2>  register_netdevice+0x29c/0x3d8
<2>  rmnet_vnd_newlink+0x68/0xe8
<2>  rmnet_newlink+0xa0/0x160
<2>  rtnl_newlink+0x57c/0x6c8
<2>  rtnetlink_rcv_msg+0x1dc/0x328
<2>  netlink_rcv_skb+0xac/0x118
<2>  rtnetlink_rcv+0x24/0x30
<2>  netlink_unicast+0x158/0x1f0
<2>  netlink_sendmsg+0x32c/0x338
<2>  sock_sendmsg+0x44/0x60
<2>  SyS_sendto+0x150/0x1ac
<2>  el0_svc_naked+0x34/0x38

---
 drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -234,7 +234,7 @@ int rmnet_vnd_newlink(u8 id, struct net_
 		      struct net_device *real_dev,
 		      struct rmnet_endpoint *ep)
 {
-	struct rmnet_priv *priv;
+	struct rmnet_priv *priv = netdev_priv(rmnet_dev);
 	int rc;
 
 	if (ep->egress_dev)

@@ -247,6 +247,8 @@ int rmnet_vnd_newlink(u8 id, struct net_
 	rmnet_dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 	rmnet_dev->hw_features |= NETIF_F_SG;
 
+	priv->real_dev = real_dev;
+
 	rc = register_netdevice(rmnet_dev);
 	if (!rc) {
 		ep->egress_dev = rmnet_dev;

@@ -255,9 +257,7 @@ int rmnet_vnd_newlink(u8 id, struct net_
 
 		rmnet_dev->rtnl_link_ops = &rmnet_link_ops;
 
-		priv = netdev_priv(rmnet_dev);
 		priv->mux_id = id;
-		priv->real_dev = real_dev;
 
 		netdev_dbg(rmnet_dev, "rmnet dev created\n");
 	}

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jakub Kicinski <[email protected]>

[ Upstream commit 63c82997f5c0f3e1b914af43d82f712a86bc5f3a ]

TCA_FLOWER_KEY_ENC_OPTS and TCA_FLOWER_KEY_ENC_OPTS_MASK can only currently contain further nested attributes, which are parsed by hand, so the policy is never actually used resulting in a W=1 build warning:

net/sched/cls_flower.c:492:1: warning: ‘enc_opts_policy’ defined but not used [-Wunused-const-variable=]
enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = {

Add the validation anyway to avoid potential bugs when other attributes are added and to make the attribute structure slightly more clear. Validation will also set extact to point to bad attribute on error.

---
 net/sched/cls_flower.c |   14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

@@ -709,11 +709,23 @@ static int fl_set_enc_opt(struct nlattr
 			  struct netlink_ext_ack *extack)
 {
 	const struct nlattr *nla_enc_key, *nla_opt_key, *nla_opt_msk = NULL;
-	int option_len, key_depth, msk_depth = 0;
+	int err, option_len, key_depth, msk_depth = 0;
+
+	err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS],
+				  TCA_FLOWER_KEY_ENC_OPTS_MAX,
+				  enc_opts_policy, extack);
+	if (err)
+		return err;
 
 	nla_enc_key = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS]);
 
 	if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) {
+		err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK],
+					  TCA_FLOWER_KEY_ENC_OPTS_MAX,
+					  enc_opts_policy, extack);
+		if (err)
+			return err;
+
 		nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
 		msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
 	}

Built and booted on the Lenovo IdeaPad 330-15ARR, no dmesg regressions.

Harsh Shandilya
PRJKT Development LLC

Wonderful, thanks for testing and letting me know.

greg k-h

Build results:

	total: 135 pass: 135 fail: 0
Qemu test results:
	total: 291 pass: 291 fail: 0

Details are available at https://kerneltests.org/builders/.

Guenter

Doesn't compile for me on OpenSuSE 15.0 (gcc 7.3.1):

CALL scripts/checksyscalls.sh
DESCEND objtool
CHK include/generated/compile.h
CC [M] drivers/gpu/drm/i915/i915_gem_gtt.o
drivers/gpu/drm/i915/i915_gem_gtt.c: In function ‘gen6_dump_ppgtt’:
drivers/gpu/drm/i915/i915_gem_gtt.c:1771:41: error: format ‘%llx’ expects argument of type ‘long long unsigned int’, but argument 5 has type ‘long unsigned int’ [-Werror=format=]

    seq_printf(m, "\t\t(%03d, %04d) %08llx: ",
                                    ~~~~~^
                                    %08lx

cc1: all warnings being treated as errors
make[4]: *** [scripts/Makefile.build:306:
drivers/gpu/drm/i915/i915_gem_gtt.o] Error 1
make[3]: *** [scripts/Makefile.build:546: drivers/gpu/drm/i915] Error 2 make[2]: *** [scripts/Makefile.build:546: drivers/gpu/drm] Error 2 make[1]: *** [scripts/Makefile.build:546: drivers/gpu] Error 2
make: *** [Makefile:1052: drivers] Error 2

4.19.3 is broken for me, too. 4.19.2 is works.
4.20-rc tree works.

Config attached.

Thomas

#
# Automatically generated file; DO NOT EDIT.
# Linux/x86 4.19.4-rc1 Kernel Configuration
#

#
# Compiler: gcc (SUSE Linux) 7.3.1 20180323 [gcc-7-branch revision 258812] #
CONFIG_CC_IS_GCC=y
CONFIG_GCC_VERSION=70301
CONFIG_CLANG_VERSION=0
CONFIG_IRQ_WORK=y
CONFIG_BUILDTIME_EXTABLE_SORT=y
CONFIG_THREAD_INFO_IN_TASK=y

#
# General setup
#
CONFIG_INIT_ENV_ARG_LIMIT=32
# CONFIG_COMPILE_TEST is not set
CONFIG_LOCALVERSION="-cx"
# CONFIG_LOCALVERSION_AUTO is not set
CONFIG_BUILD_SALT=""
CONFIG_HAVE_KERNEL_GZIP=y
CONFIG_HAVE_KERNEL_BZIP2=y
CONFIG_HAVE_KERNEL_LZMA=y
CONFIG_HAVE_KERNEL_XZ=y
CONFIG_HAVE_KERNEL_LZO=y
CONFIG_HAVE_KERNEL_LZ4=y
# CONFIG_KERNEL_GZIP is not set
# CONFIG_KERNEL_BZIP2 is not set
# CONFIG_KERNEL_LZMA is not set
CONFIG_KERNEL_XZ=y
# CONFIG_KERNEL_LZO is not set
# CONFIG_KERNEL_LZ4 is not set
CONFIG_DEFAULT_HOSTNAME="(none)"
CONFIG_SWAP=y
CONFIG_SYSVIPC=y
CONFIG_SYSVIPC_SYSCTL=y
CONFIG_POSIX_MQUEUE=y
CONFIG_POSIX_MQUEUE_SYSCTL=y
CONFIG_CROSS_MEMORY_ATTACH=y
CONFIG_USELIB=y
CONFIG_AUDIT=y
CONFIG_HAVE_ARCH_AUDITSYSCALL=y
CONFIG_AUDITSYSCALL=y
CONFIG_AUDIT_WATCH=y
CONFIG_AUDIT_TREE=y

#
# IRQ subsystem
#
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_GENERIC_IRQ_SHOW=y
CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK=y
CONFIG_GENERIC_PENDING_IRQ=y
CONFIG_GENERIC_IRQ_MIGRATION=y
CONFIG_GENERIC_IRQ_CHIP=y
CONFIG_IRQ_DOMAIN=y
CONFIG_IRQ_SIM=y
CONFIG_IRQ_DOMAIN_HIERARCHY=y
CONFIG_GENERIC_MSI_IRQ=y
CONFIG_GENERIC_MSI_IRQ_DOMAIN=y
CONFIG_GENERIC_IRQ_MATRIX_ALLOCATOR=y
CONFIG_GENERIC_IRQ_RESERVATION_MODE=y
CONFIG_IRQ_FORCED_THREADING=y
CONFIG_SPARSE_IRQ=y
# CONFIG_GENERIC_IRQ_DEBUGFS is not set
CONFIG_CLOCKSOURCE_WATCHDOG=y
CONFIG_ARCH_CLOCKSOURCE_DATA=y
CONFIG_CLOCKSOURCE_VALIDATE_LAST_CYCLE=y
CONFIG_GENERIC_TIME_VSYSCALL=y
CONFIG_GENERIC_CLOCKEVENTS=y
CONFIG_GENERIC_CLOCKEVENTS_BROADCAST=y
CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST=y
CONFIG_GENERIC_CMOS_UPDATE=y

#
# Timers subsystem
#
CONFIG_TICK_ONESHOT=y
CONFIG_NO_HZ_COMMON=y
# CONFIG_HZ_PERIODIC is not set
CONFIG_NO_HZ_IDLE=y
# CONFIG_NO_HZ_FULL is not set
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
# CONFIG_PREEMPT_NONE is not set
CONFIG_PREEMPT_VOLUNTARY=y
# CONFIG_PREEMPT is not set

#
# CPU/Task time and stats accounting
#
CONFIG_TICK_CPU_ACCOUNTING=y
# CONFIG_VIRT_CPU_ACCOUNTING_GEN is not set
# CONFIG_IRQ_TIME_ACCOUNTING is not set
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
CONFIG_TASKSTATS=y
CONFIG_TASK_DELAY_ACCT=y
CONFIG_TASK_XACCT=y
CONFIG_TASK_IO_ACCOUNTING=y
CONFIG_CPU_ISOLATION=y

#
# RCU Subsystem
#
CONFIG_TREE_RCU=y
# CONFIG_RCU_EXPERT is not set
CONFIG_SRCU=y
CONFIG_TREE_SRCU=y
CONFIG_TASKS_RCU=y
CONFIG_RCU_STALL_COMMON=y
CONFIG_RCU_NEED_SEGCBLIST=y
CONFIG_BUILD_BIN2C=y
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_LOG_BUF_SHIFT=18
CONFIG_LOG_CPU_MAX_BUF_SHIFT=15
CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT=13
CONFIG_HAVE_UNSTABLE_SCHED_CLOCK=y
CONFIG_ARCH_SUPPORTS_NUMA_BALANCING=y
CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH=y
CONFIG_ARCH_SUPPORTS_INT128=y
CONFIG_NUMA_BALANCING=y
CONFIG_NUMA_BALANCING_DEFAULT_ENABLED=y
CONFIG_CGROUPS=y
CONFIG_PAGE_COUNTER=y
CONFIG_MEMCG=y
CONFIG_MEMCG_SWAP=y
# CONFIG_MEMCG_SWAP_ENABLED is not set
CONFIG_MEMCG_KMEM=y
CONFIG_BLK_CGROUP=y
# CONFIG_DEBUG_BLK_CGROUP is not set
CONFIG_CGROUP_WRITEBACK=y
CONFIG_CGROUP_SCHED=y
CONFIG_FAIR_GROUP_SCHED=y
CONFIG_CFS_BANDWIDTH=y
# CONFIG_RT_GROUP_SCHED is not set
CONFIG_CGROUP_PIDS=y
# CONFIG_CGROUP_RDMA is not set
CONFIG_CGROUP_FREEZER=y
CONFIG_CGROUP_HUGETLB=y
CONFIG_CPUSETS=y
CONFIG_PROC_PID_CPUSET=y
CONFIG_CGROUP_DEVICE=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_CGROUP_PERF=y
# CONFIG_CGROUP_BPF is not set
# CONFIG_CGROUP_DEBUG is not set
CONFIG_SOCK_CGROUP_DATA=y
CONFIG_NAMESPACES=y
CONFIG_UTS_NS=y
CONFIG_IPC_NS=y
CONFIG_USER_NS=y
CONFIG_PID_NS=y
CONFIG_NET_NS=y
CONFIG_CHECKPOINT_RESTORE=y
# CONFIG_SCHED_AUTOGROUP is not set
# CONFIG_SYSFS_DEPRECATED is not set
CONFIG_RELAY=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_INITRAMFS_SOURCE=""
CONFIG_RD_GZIP=y
CONFIG_RD_BZIP2=y
CONFIG_RD_LZMA=y
CONFIG_RD_XZ=y
CONFIG_RD_LZO=y
CONFIG_RD_LZ4=y
CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y
# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
CONFIG_SYSCTL=y
CONFIG_ANON_INODES=y
CONFIG_HAVE_UID16=y
CONFIG_SYSCTL_EXCEPTION_TRACE=y
CONFIG_HAVE_PCSPKR_PLATFORM=y
CONFIG_BPF=y
CONFIG_EXPERT=y
CONFIG_UID16=y
CONFIG_MULTIUSER=y
CONFIG_SGETMASK_SYSCALL=y
CONFIG_SYSFS_SYSCALL=y
# CONFIG_SYSCTL_SYSCALL is not set
CONFIG_FHANDLE=y
CONFIG_POSIX_TIMERS=y
CONFIG_PRINTK=y
CONFIG_PRINTK_NMI=y
CONFIG_BUG=y
CONFIG_ELF_CORE=y
CONFIG_PCSPKR_PLATFORM=y
CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
CONFIG_FUTEX_PI=y
CONFIG_EPOLL=y
CONFIG_SIGNALFD=y
CONFIG_TIMERFD=y
CONFIG_EVENTFD=y
CONFIG_SHMEM=y
CONFIG_AIO=y
CONFIG_ADVISE_SYSCALLS=y
CONFIG_MEMBARRIER=y
CONFIG_KALLSYMS=y
CONFIG_KALLSYMS_ALL=y
CONFIG_KALLSYMS_ABSOLUTE_PERCPU=y
CONFIG_KALLSYMS_BASE_RELATIVE=y
CONFIG_BPF_SYSCALL=y
# CONFIG_BPF_JIT_ALWAYS_ON is not set
CONFIG_USERFAULTFD=y
CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE=y
CONFIG_RSEQ=y
# CONFIG_DEBUG_RSEQ is not set
# CONFIG_EMBEDDED is not set
CONFIG_HAVE_PERF_EVENTS=y
# CONFIG_PC104 is not set

#
# Kernel Performance Events And Counters
#
CONFIG_PERF_EVENTS=y
# CONFIG_DEBUG_PERF_USE_VMALLOC is not set CONFIG_VM_EVENT_COUNTERS=y
# CONFIG_COMPAT_BRK is not set
CONFIG_SLAB=y
# CONFIG_SLUB is not set
# CONFIG_SLOB is not set CONFIG_SLAB_MERGE_DEFAULT=y CONFIG_SLAB_FREELIST_RANDOM=y
CONFIG_PROFILING=y
CONFIG_64BIT=y
CONFIG_X86_64=y
CONFIG_X86=y
CONFIG_INSTRUCTION_DECODER=y CONFIG_OUTPUT_FORMAT="elf64-x86-64" CONFIG_ARCH_DEFCONFIG="arch/x86/configs/x86_64_defconfig" CONFIG_LOCKDEP_SUPPORT=y CONFIG_STACKTRACE_SUPPORT=y
CONFIG_MMU=y
CONFIG_ARCH_MMAP_RND_BITS_MIN=28 CONFIG_ARCH_MMAP_RND_BITS_MAX=32 CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN=8 CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX=16 CONFIG_GENERIC_ISA_DMA=y
CONFIG_GENERIC_BUG=y CONFIG_GENERIC_BUG_RELATIVE_POINTERS=y CONFIG_GENERIC_HWEIGHT=y CONFIG_ARCH_MAY_HAVE_PC_FDC=y CONFIG_RWSEM_XCHGADD_ALGORITHM=y CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_ARCH_HAS_CPU_RELAX=y CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y CONFIG_ARCH_HAS_FILTER_PGPROT=y CONFIG_HAVE_SETUP_PER_CPU_AREA=y CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK=y CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK=y CONFIG_ARCH_HIBERNATION_POSSIBLE=y CONFIG_ARCH_SUSPEND_POSSIBLE=y CONFIG_ARCH_WANT_HUGE_PMD_SHARE=y CONFIG_ARCH_WANT_GENERAL_HUGETLB=y CONFIG_ZONE_DMA32=y
CONFIG_AUDIT_ARCH=y CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y CONFIG_HAVE_INTEL_TXT=y
CONFIG_X86_64_SMP=y CONFIG_ARCH_SUPPORTS_UPROBES=y CONFIG_FIX_EARLYCON_MEM=y CONFIG_PGTABLE_LEVELS=4 CONFIG_CC_HAS_SANE_STACKPROTECTOR=y

#
# Processor type and features
#
CONFIG_ZONE_DMA=y
CONFIG_SMP=y
CONFIG_X86_FEATURE_NAMES=y CONFIG_X86_X2APIC=y
CONFIG_X86_MPPARSE=y
# CONFIG_GOLDFISH is not set CONFIG_RETPOLINE=y
# CONFIG_INTEL_RDT is not set CONFIG_X86_EXTENDED_PLATFORM=y
# CONFIG_X86_NUMACHIP is not set
# CONFIG_X86_VSMP is not set
# CONFIG_X86_UV is not set
# CONFIG_X86_GOLDFISH is not set
# CONFIG_X86_INTEL_MID is not set CONFIG_X86_INTEL_LPSS=y CONFIG_X86_AMD_PLATFORM_DEVICE=y CONFIG_IOSF_MBI=y
# CONFIG_IOSF_MBI_DEBUG is not set CONFIG_X86_SUPPORTS_MEMORY_FAILURE=y CONFIG_SCHED_OMIT_FRAME_POINTER=y CONFIG_HYPERVISOR_GUEST=y
CONFIG_PARAVIRT=y
# CONFIG_PARAVIRT_DEBUG is not set
# CONFIG_PARAVIRT_SPINLOCKS is not set CONFIG_XEN=y
CONFIG_XEN_PV=y
CONFIG_XEN_PV_SMP=y
CONFIG_XEN_DOM0=y
CONFIG_XEN_PVHVM=y
CONFIG_XEN_PVHVM_SMP=y
CONFIG_XEN_512GB=y
CONFIG_XEN_SAVE_RESTORE=y
# CONFIG_XEN_DEBUG_FS is not set CONFIG_XEN_PVH=y
CONFIG_KVM_GUEST=y
# CONFIG_KVM_DEBUG_FS is not set
# CONFIG_PARAVIRT_TIME_ACCOUNTING is not set CONFIG_PARAVIRT_CLOCK=y
# CONFIG_JAILHOUSE_GUEST is not set CONFIG_NO_BOOTMEM=y
# CONFIG_MK8 is not set
# CONFIG_MPSC is not set
# CONFIG_MCORE2 is not set
# CONFIG_MATOM is not set CONFIG_GENERIC_CPU=y CONFIG_X86_INTERNODE_CACHE_SHIFT=6 CONFIG_X86_L1_CACHE_SHIFT=6
CONFIG_X86_TSC=y
CONFIG_X86_CMPXCHG64=y
CONFIG_X86_CMOV=y CONFIG_X86_MINIMUM_CPU_FAMILY=64 CONFIG_X86_DEBUGCTLMSR=y
# CONFIG_PROCESSOR_SELECT is not set CONFIG_CPU_SUP_INTEL=y
CONFIG_CPU_SUP_AMD=y CONFIG_CPU_SUP_CENTAUR=y
CONFIG_HPET_TIMER=y CONFIG_HPET_EMULATE_RTC=y
CONFIG_DMI=y
CONFIG_GART_IOMMU=y
CONFIG_CALGARY_IOMMU=y
# CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT is not set # CONFIG_MAXSMP is not set CONFIG_NR_CPUS_RANGE_BEGIN=2 CONFIG_NR_CPUS_RANGE_END=512 CONFIG_NR_CPUS_DEFAULT=64
CONFIG_NR_CPUS=512
CONFIG_SCHED_SMT=y
CONFIG_SCHED_MC=y
CONFIG_SCHED_MC_PRIO=y CONFIG_X86_LOCAL_APIC=y
CONFIG_X86_IO_APIC=y CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y CONFIG_X86_MCE=y
# CONFIG_X86_MCELOG_LEGACY is not set CONFIG_X86_MCE_INTEL=y
CONFIG_X86_MCE_AMD=y CONFIG_X86_MCE_THRESHOLD=y CONFIG_X86_MCE_INJECT=m CONFIG_X86_THERMAL_VECTOR=y

#
# Performance monitoring
#
CONFIG_PERF_EVENTS_INTEL_UNCORE=y
CONFIG_PERF_EVENTS_INTEL_RAPL=y
CONFIG_PERF_EVENTS_INTEL_CSTATE=y
CONFIG_PERF_EVENTS_AMD_POWER=m
CONFIG_X86_16BIT=y
CONFIG_X86_ESPFIX64=y
CONFIG_X86_VSYSCALL_EMULATION=y
# CONFIG_I8K is not set
CONFIG_MICROCODE=y
CONFIG_MICROCODE_INTEL=y
CONFIG_MICROCODE_AMD=y
CONFIG_MICROCODE_OLD_INTERFACE=y
CONFIG_X86_MSR=m
CONFIG_X86_CPUID=m
# CONFIG_X86_5LEVEL is not set
CONFIG_X86_DIRECT_GBPAGES=y
CONFIG_ARCH_HAS_MEM_ENCRYPT=y
# CONFIG_AMD_MEM_ENCRYPT is not set
CONFIG_NUMA=y
CONFIG_AMD_NUMA=y
CONFIG_X86_64_ACPI_NUMA=y
CONFIG_NODES_SPAN_OTHER_NODES=y
CONFIG_NUMA_EMU=y
CONFIG_NODES_SHIFT=9
CONFIG_ARCH_SPARSEMEM_ENABLE=y
CONFIG_ARCH_SPARSEMEM_DEFAULT=y
CONFIG_ARCH_SELECT_MEMORY_MODEL=y
CONFIG_ARCH_MEMORY_PROBE=y
CONFIG_ARCH_PROC_KCORE_TEXT=y
CONFIG_ILLEGAL_POINTER_VALUE=0xdead000000000000
CONFIG_X86_PMEM_LEGACY_DEVICE=y
CONFIG_X86_PMEM_LEGACY=m
CONFIG_X86_CHECK_BIOS_CORRUPTION=y
CONFIG_X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK=y
CONFIG_X86_RESERVE_LOW=64
CONFIG_MTRR=y
CONFIG_MTRR_SANITIZER=y
CONFIG_MTRR_SANITIZER_ENABLE_DEFAULT=0
CONFIG_MTRR_SANITIZER_SPARE_REG_NR_DEFAULT=1
CONFIG_X86_PAT=y
CONFIG_ARCH_USES_PG_UNCACHED=y
CONFIG_ARCH_RANDOM=y
CONFIG_X86_SMAP=y
CONFIG_X86_INTEL_UMIP=y
CONFIG_X86_INTEL_MPX=y
CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS=y
CONFIG_EFI=y
CONFIG_EFI_STUB=y
CONFIG_EFI_MIXED=y
CONFIG_SECCOMP=y
# CONFIG_HZ_100 is not set
CONFIG_HZ_250=y
# CONFIG_HZ_300 is not set
# CONFIG_HZ_1000 is not set
CONFIG_HZ=250
CONFIG_SCHED_HRTICK=y
CONFIG_KEXEC=y
CONFIG_KEXEC_FILE=y
CONFIG_ARCH_HAS_KEXEC_PURGATORY=y
# CONFIG_KEXEC_VERIFY_SIG is not set
CONFIG_CRASH_DUMP=y
# CONFIG_KEXEC_JUMP is not set
CONFIG_PHYSICAL_START=0x200000
CONFIG_RELOCATABLE=y
CONFIG_RANDOMIZE_BASE=y
CONFIG_X86_NEED_RELOCS=y
CONFIG_PHYSICAL_ALIGN=0x1000000
CONFIG_DYNAMIC_MEMORY_LAYOUT=y
CONFIG_RANDOMIZE_MEMORY=y
CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING=0xa
CONFIG_HOTPLUG_CPU=y
# CONFIG_BOOTPARAM_HOTPLUG_CPU0 is not set
# CONFIG_DEBUG_HOTPLUG_CPU0 is not set
# CONFIG_COMPAT_VDSO is not set
CONFIG_LEGACY_VSYSCALL_EMULATE=y
# CONFIG_LEGACY_VSYSCALL_NONE is not set
# CONFIG_CMDLINE_BOOL is not set
CONFIG_MODIFY_LDT_SYSCALL=y
CONFIG_HAVE_LIVEPATCH=y
CONFIG_ARCH_HAS_ADD_PAGES=y
CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE=y
CONFIG_USE_PERCPU_NUMA_NODE_ID=y
CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK=y
CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION=y
CONFIG_ARCH_ENABLE_THP_MIGRATION=y

#
# Power management and ACPI options
#
CONFIG_ARCH_HIBERNATION_HEADER=y
CONFIG_SUSPEND=y
CONFIG_SUSPEND_FREEZER=y
# CONFIG_SUSPEND_SKIP_SYNC is not set
CONFIG_HIBERNATE_CALLBACKS=y
CONFIG_HIBERNATION=y
CONFIG_PM_STD_PARTITION=""
CONFIG_PM_SLEEP=y
CONFIG_PM_SLEEP_SMP=y
CONFIG_PM_AUTOSLEEP=y
CONFIG_PM_WAKELOCKS=y
CONFIG_PM_WAKELOCKS_LIMIT=100
CONFIG_PM_WAKELOCKS_GC=y
CONFIG_PM=y
# CONFIG_PM_DEBUG is not set
CONFIG_PM_CLK=y
CONFIG_PM_GENERIC_DOMAINS=y
# CONFIG_WQ_POWER_EFFICIENT_DEFAULT is not set
CONFIG_PM_GENERIC_DOMAINS_SLEEP=y
CONFIG_ARCH_SUPPORTS_ACPI=y
CONFIG_ACPI=y
CONFIG_ACPI_LEGACY_TABLES_LOOKUP=y
CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC=y
CONFIG_ACPI_SYSTEM_POWER_STATES_SUPPORT=y
# CONFIG_ACPI_DEBUGGER is not set
CONFIG_ACPI_SPCR_TABLE=y
CONFIG_ACPI_LPIT=y
CONFIG_ACPI_SLEEP=y
CONFIG_ACPI_PROCFS_POWER=y
CONFIG_ACPI_REV_OVERRIDE_POSSIBLE=y
CONFIG_ACPI_EC_DEBUGFS=m
CONFIG_ACPI_AC=m
CONFIG_ACPI_BATTERY=m
CONFIG_ACPI_BUTTON=m
CONFIG_ACPI_VIDEO=m
CONFIG_ACPI_FAN=m
# CONFIG_ACPI_TAD is not set
CONFIG_ACPI_DOCK=y
CONFIG_ACPI_CPU_FREQ_PSS=y
CONFIG_ACPI_PROCESSOR_CSTATE=y
CONFIG_ACPI_PROCESSOR_IDLE=y
CONFIG_ACPI_CPPC_LIB=y
CONFIG_ACPI_PROCESSOR=y
CONFIG_ACPI_IPMI=m
CONFIG_ACPI_HOTPLUG_CPU=y
CONFIG_ACPI_PROCESSOR_AGGREGATOR=m
CONFIG_ACPI_THERMAL=m
CONFIG_ACPI_NUMA=y
CONFIG_ACPI_CUSTOM_DSDT_FILE=""
CONFIG_ARCH_HAS_ACPI_TABLE_UPGRADE=y
CONFIG_ACPI_TABLE_UPGRADE=y
# CONFIG_ACPI_DEBUG is not set
CONFIG_ACPI_PCI_SLOT=y
CONFIG_ACPI_CONTAINER=y
CONFIG_ACPI_HOTPLUG_MEMORY=y
CONFIG_ACPI_HOTPLUG_IOAPIC=y
CONFIG_ACPI_SBS=m
CONFIG_ACPI_HED=y
# CONFIG_ACPI_CUSTOM_METHOD is not set
CONFIG_ACPI_BGRT=y
# CONFIG_ACPI_REDUCED_HARDWARE_ONLY is not set
CONFIG_ACPI_NFIT=m
CONFIG_HAVE_ACPI_APEI=y
CONFIG_HAVE_ACPI_APEI_NMI=y
CONFIG_ACPI_APEI=y
CONFIG_ACPI_APEI_GHES=y
CONFIG_ACPI_APEI_PCIEAER=y
CONFIG_ACPI_APEI_MEMORY_FAILURE=y
CONFIG_ACPI_APEI_EINJ=m
CONFIG_ACPI_APEI_ERST_DEBUG=m
CONFIG_DPTF_POWER=m
CONFIG_ACPI_WATCHDOG=y
# CONFIG_ACPI_EXTLOG is not set
# CONFIG_PMIC_OPREGION is not set
CONFIG_ACPI_CONFIGFS=m
CONFIG_X86_PM_TIMER=y
# CONFIG_SFI is not set

#
# CPU Frequency scaling
#
CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_GOV_ATTR_SET=y CONFIG_CPU_FREQ_GOV_COMMON=y
# CONFIG_CPU_FREQ_STAT is not set CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
# CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set # CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set # CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND is not set # CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set # CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL is not set CONFIG_CPU_FREQ_GOV_PERFORMANCE=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m CONFIG_CPU_FREQ_GOV_USERSPACE=m CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y

#
# CPU frequency scaling drivers
#
CONFIG_X86_INTEL_PSTATE=y
CONFIG_X86_PCC_CPUFREQ=m
CONFIG_X86_ACPI_CPUFREQ=m
CONFIG_X86_ACPI_CPUFREQ_CPB=y
CONFIG_X86_POWERNOW_K8=m
CONFIG_X86_AMD_FREQ_SENSITIVITY=m
# CONFIG_X86_SPEEDSTEP_CENTRINO is not set
# CONFIG_X86_P4_CLOCKMOD is not set

#

# shared options
#

#
# CPU Idle
#
CONFIG_CPU_IDLE=y
CONFIG_CPU_IDLE_GOV_LADDER=y
CONFIG_CPU_IDLE_GOV_MENU=y
CONFIG_INTEL_IDLE=y

#
# Bus options (PCI etc.)
#
CONFIG_PCI=y
CONFIG_PCI_DIRECT=y
CONFIG_PCI_MMCONFIG=y
CONFIG_PCI_XEN=y
CONFIG_PCI_DOMAINS=y
CONFIG_MMCONF_FAM10H=y
# CONFIG_PCI_CNB20LE_QUIRK is not set
CONFIG_PCIEPORTBUS=y
CONFIG_HOTPLUG_PCI_PCIE=y
CONFIG_PCIEAER=y
CONFIG_PCIEAER_INJECT=m
# CONFIG_PCIE_ECRC is not set
CONFIG_PCIEASPM=y
# CONFIG_PCIEASPM_DEBUG is not set
CONFIG_PCIEASPM_DEFAULT=y
# CONFIG_PCIEASPM_POWERSAVE is not set
# CONFIG_PCIEASPM_POWER_SUPERSAVE is not set
# CONFIG_PCIEASPM_PERFORMANCE is not set
CONFIG_PCIE_PME=y
CONFIG_PCIE_DPC=y
CONFIG_PCIE_PTM=y
CONFIG_PCI_MSI=y
CONFIG_PCI_MSI_IRQ_DOMAIN=y
CONFIG_PCI_QUIRKS=y
# CONFIG_PCI_DEBUG is not set
# CONFIG_PCI_REALLOC_ENABLE_AUTO is not set
CONFIG_PCI_STUB=y
# CONFIG_PCI_PF_STUB is not set
CONFIG_XEN_PCIDEV_FRONTEND=m
CONFIG_PCI_ATS=y
CONFIG_PCI_LOCKLESS_CONFIG=y
CONFIG_PCI_IOV=y
CONFIG_PCI_PRI=y
CONFIG_PCI_PASID=y
CONFIG_PCI_LABEL=y
CONFIG_PCI_HYPERV=m
CONFIG_HOTPLUG_PCI=y
CONFIG_HOTPLUG_PCI_ACPI=y
CONFIG_HOTPLUG_PCI_ACPI_IBM=m
CONFIG_HOTPLUG_PCI_CPCI=y
CONFIG_HOTPLUG_PCI_CPCI_ZT5550=m
CONFIG_HOTPLUG_PCI_CPCI_GENERIC=m
# CONFIG_HOTPLUG_PCI_SHPC is not set

#
# PCI controller drivers
#

#
# Cadence PCIe controllers support
#
CONFIG_VMD=m

#
# DesignWare PCI Core Support
#
# CONFIG_PCIE_DW_PLAT_HOST is not set

#
# PCI Endpoint
#
# CONFIG_PCI_ENDPOINT is not set

#
# PCI switch controller drivers
#
# CONFIG_PCI_SW_SWITCHTEC is not set
# CONFIG_ISA_BUS is not set
CONFIG_ISA_DMA_API=y
CONFIG_AMD_NB=y
CONFIG_PCCARD=m
CONFIG_PCMCIA=m
CONFIG_PCMCIA_LOAD_CIS=y
CONFIG_CARDBUS=y

#
# PC-card bridges
#
CONFIG_YENTA=m
CONFIG_YENTA_O2=y
CONFIG_YENTA_RICOH=y
CONFIG_YENTA_TI=y
CONFIG_YENTA_ENE_TUNE=y
CONFIG_YENTA_TOSHIBA=y
CONFIG_PD6729=m
CONFIG_I82092=m
CONFIG_PCCARD_NONSTATIC=y
# CONFIG_RAPIDIO is not set
# CONFIG_X86_SYSFB is not set

#
# Binary Emulations
#
CONFIG_IA32_EMULATION=y
CONFIG_IA32_AOUT=m
# CONFIG_X86_X32 is not set
CONFIG_COMPAT_32=y
CONFIG_COMPAT=y
CONFIG_COMPAT_FOR_U64_ALIGNMENT=y
CONFIG_SYSVIPC_COMPAT=y
CONFIG_X86_DEV_DMA_OPS=y
CONFIG_HAVE_GENERIC_GUP=y

#
# Firmware Drivers
#
CONFIG_EDD=m
# CONFIG_EDD_OFF is not set
CONFIG_FIRMWARE_MEMMAP=y
CONFIG_DELL_RBU=m
CONFIG_DCDBAS=m
CONFIG_DMIID=y
CONFIG_DMI_SYSFS=m
CONFIG_DMI_SCAN_MACHINE_NON_EFI_FALLBACK=y
CONFIG_ISCSI_IBFT_FIND=y
CONFIG_ISCSI_IBFT=m
CONFIG_FW_CFG_SYSFS=m
CONFIG_FW_CFG_SYSFS_CMDLINE=y
# CONFIG_GOOGLE_FIRMWARE is not set

#
# EFI (Extensible Firmware Interface) Support #
CONFIG_EFI_VARS=y
CONFIG_EFI_ESRT=y
CONFIG_EFI_VARS_PSTORE=y
# CONFIG_EFI_VARS_PSTORE_DEFAULT_DISABLE is not set CONFIG_EFI_RUNTIME_MAP=y
# CONFIG_EFI_FAKE_MEMMAP is not set CONFIG_EFI_RUNTIME_WRAPPERS=y CONFIG_EFI_BOOTLOADER_CONTROL=m CONFIG_EFI_CAPSULE_LOADER=m
# CONFIG_EFI_TEST is not set CONFIG_APPLE_PROPERTIES=y
# CONFIG_RESET_ATTACK_MITIGATION is not set CONFIG_UEFI_CPER=y
CONFIG_UEFI_CPER_X86=y CONFIG_EFI_DEV_PATH_PARSER=y

#
# Tegra firmware driver
#
CONFIG_HAVE_KVM=y
CONFIG_HAVE_KVM_IRQCHIP=y
CONFIG_HAVE_KVM_IRQFD=y
CONFIG_HAVE_KVM_IRQ_ROUTING=y
CONFIG_HAVE_KVM_EVENTFD=y
CONFIG_KVM_MMIO=y
CONFIG_KVM_ASYNC_PF=y
CONFIG_HAVE_KVM_MSI=y
CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT=y
CONFIG_KVM_VFIO=y
CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT=y
CONFIG_KVM_COMPAT=y
CONFIG_HAVE_KVM_IRQ_BYPASS=y
CONFIG_VIRTUALIZATION=y
CONFIG_KVM=m
CONFIG_KVM_INTEL=m
CONFIG_KVM_AMD=m
CONFIG_VHOST_NET=m
CONFIG_VHOST_SCSI=m
CONFIG_VHOST_VSOCK=m
CONFIG_VHOST=m
# CONFIG_VHOST_CROSS_ENDIAN_LEGACY is not set

#
# General architecture-dependent options
#
CONFIG_CRASH_CORE=y
CONFIG_KEXEC_CORE=y
CONFIG_HOTPLUG_SMT=y
CONFIG_OPROFILE=m
# CONFIG_OPROFILE_EVENT_MULTIPLEX is not set
CONFIG_HAVE_OPROFILE=y
CONFIG_OPROFILE_NMI_TIMER=y
CONFIG_KPROBES=y
CONFIG_JUMP_LABEL=y
# CONFIG_STATIC_KEYS_SELFTEST is not set
CONFIG_OPTPROBES=y
CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y
CONFIG_ARCH_USE_BUILTIN_BSWAP=y
CONFIG_KRETPROBES=y
CONFIG_USER_RETURN_NOTIFIER=y
CONFIG_HAVE_IOREMAP_PROT=y
CONFIG_HAVE_KPROBES=y
CONFIG_HAVE_KRETPROBES=y
CONFIG_HAVE_OPTPROBES=y
CONFIG_HAVE_KPROBES_ON_FTRACE=y
CONFIG_HAVE_FUNCTION_ERROR_INJECTION=y
CONFIG_HAVE_NMI=y
CONFIG_HAVE_ARCH_TRACEHOOK=y
CONFIG_HAVE_DMA_CONTIGUOUS=y
CONFIG_GENERIC_SMP_IDLE_THREAD=y
CONFIG_ARCH_HAS_FORTIFY_SOURCE=y
CONFIG_ARCH_HAS_SET_MEMORY=y
CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST=y
CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT=y
CONFIG_HAVE_REGS_AND_STACK_ACCESS_API=y
CONFIG_HAVE_RSEQ=y
CONFIG_HAVE_CLK=y
CONFIG_HAVE_HW_BREAKPOINT=y
CONFIG_HAVE_MIXED_BREAKPOINTS_REGS=y
CONFIG_HAVE_USER_RETURN_NOTIFIER=y
CONFIG_HAVE_PERF_EVENTS_NMI=y
CONFIG_HAVE_HARDLOCKUP_DETECTOR_PERF=y
CONFIG_HAVE_PERF_REGS=y
CONFIG_HAVE_PERF_USER_STACK_DUMP=y
CONFIG_HAVE_ARCH_JUMP_LABEL=y
CONFIG_HAVE_RCU_TABLE_FREE=y
CONFIG_HAVE_RCU_TABLE_INVALIDATE=y
CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG=y
CONFIG_HAVE_CMPXCHG_LOCAL=y
CONFIG_HAVE_CMPXCHG_DOUBLE=y
CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION=y
CONFIG_ARCH_WANT_OLD_COMPAT_IPC=y
CONFIG_HAVE_ARCH_SECCOMP_FILTER=y
CONFIG_SECCOMP_FILTER=y
CONFIG_HAVE_STACKPROTECTOR=y
CONFIG_CC_HAS_STACKPROTECTOR_NONE=y
CONFIG_STACKPROTECTOR=y
CONFIG_STACKPROTECTOR_STRONG=y
CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES=y
CONFIG_HAVE_CONTEXT_TRACKING=y
CONFIG_HAVE_VIRT_CPU_ACCOUNTING_GEN=y
CONFIG_HAVE_IRQ_TIME_ACCOUNTING=y
CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE=y
CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD=y
CONFIG_HAVE_ARCH_HUGE_VMAP=y
CONFIG_HAVE_ARCH_SOFT_DIRTY=y
CONFIG_HAVE_MOD_ARCH_SPECIFIC=y
CONFIG_MODULES_USE_ELF_RELA=y
CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK=y
CONFIG_ARCH_HAS_ELF_RANDOMIZE=y
CONFIG_HAVE_ARCH_MMAP_RND_BITS=y
CONFIG_HAVE_EXIT_THREAD=y
CONFIG_ARCH_MMAP_RND_BITS=28
CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS=y
CONFIG_ARCH_MMAP_RND_COMPAT_BITS=8
CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES=y
CONFIG_HAVE_COPY_THREAD_TLS=y
CONFIG_HAVE_STACK_VALIDATION=y
CONFIG_HAVE_RELIABLE_STACKTRACE=y
CONFIG_OLD_SIGSUSPEND3=y
CONFIG_COMPAT_OLD_SIGACTION=y
CONFIG_COMPAT_32BIT_TIME=y
CONFIG_HAVE_ARCH_VMAP_STACK=y
CONFIG_VMAP_STACK=y
CONFIG_ARCH_HAS_STRICT_KERNEL_RWX=y
CONFIG_STRICT_KERNEL_RWX=y
CONFIG_ARCH_HAS_STRICT_MODULE_RWX=y
CONFIG_STRICT_MODULE_RWX=y
CONFIG_ARCH_HAS_REFCOUNT=y
# CONFIG_REFCOUNT_FULL is not set
CONFIG_HAVE_ARCH_PREL32_RELOCATIONS=y

#
# GCOV-based kernel profiling
#
# CONFIG_GCOV_KERNEL is not set
CONFIG_ARCH_HAS_GCOV_PROFILE_ALL=y
CONFIG_PLUGIN_HOSTCC=""
CONFIG_HAVE_GCC_PLUGINS=y
CONFIG_RT_MUTEXES=y
CONFIG_BASE_SMALL=0
CONFIG_MODULES=y
CONFIG_MODULE_FORCE_LOAD=y
CONFIG_MODULE_UNLOAD=y
# CONFIG_MODULE_FORCE_UNLOAD is not set
CONFIG_MODVERSIONS=y
CONFIG_MODULE_SRCVERSION_ALL=y
# CONFIG_MODULE_SIG is not set
# CONFIG_MODULE_COMPRESS is not set
CONFIG_MODULES_TREE_LOOKUP=y
CONFIG_BLOCK=y
CONFIG_BLK_SCSI_REQUEST=y
CONFIG_BLK_DEV_BSG=y
CONFIG_BLK_DEV_BSGLIB=y
CONFIG_BLK_DEV_INTEGRITY=y
# CONFIG_BLK_DEV_ZONED is not set
CONFIG_BLK_DEV_THROTTLING=y
# CONFIG_BLK_DEV_THROTTLING_LOW is not set
# CONFIG_BLK_CMDLINE_PARSER is not set
# CONFIG_BLK_WBT is not set
# CONFIG_BLK_CGROUP_IOLATENCY is not set
CONFIG_BLK_DEBUG_FS=y
# CONFIG_BLK_SED_OPAL is not set

#
# Partition Types
#
CONFIG_PARTITION_ADVANCED=y
# CONFIG_ACORN_PARTITION is not set
# CONFIG_AIX_PARTITION is not set
# CONFIG_OSF_PARTITION is not set
# CONFIG_AMIGA_PARTITION is not set
# CONFIG_ATARI_PARTITION is not set
# CONFIG_MAC_PARTITION is not set
CONFIG_MSDOS_PARTITION=y
# CONFIG_BSD_DISKLABEL is not set
# CONFIG_MINIX_SUBPARTITION is not set
# CONFIG_SOLARIS_X86_PARTITION is not set
# CONFIG_UNIXWARE_DISKLABEL is not set
# CONFIG_LDM_PARTITION is not set
# CONFIG_SGI_PARTITION is not set
# CONFIG_ULTRIX_PARTITION is not set
# CONFIG_SUN_PARTITION is not set
# CONFIG_KARMA_PARTITION is not set
CONFIG_EFI_PARTITION=y
# CONFIG_SYSV68_PARTITION is not set
# CONFIG_CMDLINE_PARTITION is not set
CONFIG_BLOCK_COMPAT=y
CONFIG_BLK_MQ_PCI=y
CONFIG_BLK_MQ_VIRTIO=y
CONFIG_BLK_MQ_RDMA=y

#
# IO Schedulers
#
CONFIG_IOSCHED_NOOP=y
CONFIG_IOSCHED_DEADLINE=y
CONFIG_IOSCHED_CFQ=m
CONFIG_CFQ_GROUP_IOSCHED=y
CONFIG_DEFAULT_DEADLINE=y
# CONFIG_DEFAULT_NOOP is not set
CONFIG_DEFAULT_IOSCHED="deadline"
CONFIG_MQ_IOSCHED_DEADLINE=y
CONFIG_MQ_IOSCHED_KYBER=y
# CONFIG_IOSCHED_BFQ is not set
CONFIG_PREEMPT_NOTIFIERS=y
CONFIG_PADATA=y
CONFIG_ASN1=m
CONFIG_INLINE_SPIN_UNLOCK_IRQ=y
CONFIG_INLINE_READ_UNLOCK=y
CONFIG_INLINE_READ_UNLOCK_IRQ=y
CONFIG_INLINE_WRITE_UNLOCK=y
CONFIG_INLINE_WRITE_UNLOCK_IRQ=y
CONFIG_ARCH_SUPPORTS_ATOMIC_RMW=y
CONFIG_MUTEX_SPIN_ON_OWNER=y
CONFIG_RWSEM_SPIN_ON_OWNER=y
CONFIG_LOCK_SPIN_ON_OWNER=y
CONFIG_ARCH_USE_QUEUED_SPINLOCKS=y
CONFIG_QUEUED_SPINLOCKS=y
CONFIG_ARCH_USE_QUEUED_RWLOCKS=y
CONFIG_QUEUED_RWLOCKS=y
CONFIG_ARCH_HAS_SYNC_CORE_BEFORE_USERMODE=y
CONFIG_ARCH_HAS_SYSCALL_WRAPPER=y
CONFIG_FREEZER=y

#
# Executable file formats
#
CONFIG_BINFMT_ELF=y
CONFIG_COMPAT_BINFMT_ELF=y
CONFIG_ELFCORE=y
CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS=y
CONFIG_BINFMT_SCRIPT=y
CONFIG_BINFMT_MISC=m
CONFIG_COREDUMP=y

#
# Memory Management options
#
CONFIG_SELECT_MEMORY_MODEL=y
CONFIG_SPARSEMEM_MANUAL=y
CONFIG_SPARSEMEM=y
CONFIG_NEED_MULTIPLE_NODES=y
CONFIG_HAVE_MEMORY_PRESENT=y
CONFIG_SPARSEMEM_EXTREME=y
CONFIG_SPARSEMEM_VMEMMAP_ENABLE=y
CONFIG_SPARSEMEM_VMEMMAP=y
CONFIG_HAVE_MEMBLOCK=y
CONFIG_HAVE_MEMBLOCK_NODE_MAP=y
CONFIG_ARCH_DISCARD_MEMBLOCK=y
CONFIG_MEMORY_ISOLATION=y
CONFIG_HAVE_BOOTMEM_INFO_NODE=y
CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTPLUG_SPARSE=y
# CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE is not set
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_SPLIT_PTLOCK_CPUS=4
CONFIG_MEMORY_BALLOON=y
CONFIG_BALLOON_COMPACTION=y
CONFIG_COMPACTION=y
CONFIG_MIGRATION=y
CONFIG_PHYS_ADDR_T_64BIT=y
CONFIG_BOUNCE=y
CONFIG_VIRT_TO_BUS=y
CONFIG_MMU_NOTIFIER=y
CONFIG_KSM=y
CONFIG_DEFAULT_MMAP_MIN_ADDR=65536
CONFIG_ARCH_SUPPORTS_MEMORY_FAILURE=y
CONFIG_MEMORY_FAILURE=y
CONFIG_HWPOISON_INJECT=m
CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS=y
# CONFIG_TRANSPARENT_HUGEPAGE_MADVISE is not set
CONFIG_ARCH_WANTS_THP_SWAP=y
CONFIG_THP_SWAP=y
CONFIG_TRANSPARENT_HUGE_PAGECACHE=y
CONFIG_CLEANCACHE=y
CONFIG_FRONTSWAP=y
# CONFIG_CMA is not set
CONFIG_MEM_SOFT_DIRTY=y
CONFIG_ZSWAP=y
CONFIG_ZPOOL=y
CONFIG_ZBUD=y
CONFIG_Z3FOLD=m
CONFIG_ZSMALLOC=y
# CONFIG_PGTABLE_MAPPING is not set
# CONFIG_ZSMALLOC_STAT is not set
CONFIG_GENERIC_EARLY_IOREMAP=y
CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
# CONFIG_IDLE_PAGE_TRACKING is not set
CONFIG_ARCH_HAS_ZONE_DEVICE=y
CONFIG_ZONE_DEVICE=y
CONFIG_ARCH_HAS_HMM=y
CONFIG_DEV_PAGEMAP_OPS=y
# CONFIG_HMM_MIRROR is not set
# CONFIG_DEVICE_PRIVATE is not set
# CONFIG_DEVICE_PUBLIC is not set
CONFIG_ARCH_USES_HIGH_VMA_FLAGS=y
CONFIG_ARCH_HAS_PKEYS=y
# CONFIG_PERCPU_STATS is not set
# CONFIG_GUP_BENCHMARK is not set
CONFIG_ARCH_HAS_PTE_SPECIAL=y
CONFIG_NET=y
CONFIG_NET_INGRESS=y
CONFIG_NET_EGRESS=y

#
# Networking options
#
CONFIG_PACKET=m
CONFIG_PACKET_DIAG=m
CONFIG_UNIX=y
CONFIG_UNIX_DIAG=m
# CONFIG_TLS is not set
CONFIG_XFRM=y
CONFIG_XFRM_ALGO=m
CONFIG_XFRM_USER=m
# CONFIG_XFRM_INTERFACE is not set
CONFIG_XFRM_SUB_POLICY=y
CONFIG_XFRM_MIGRATE=y
CONFIG_XFRM_STATISTICS=y
CONFIG_XFRM_IPCOMP=m
CONFIG_NET_KEY=m
CONFIG_NET_KEY_MIGRATE=y
# CONFIG_SMC is not set
# CONFIG_XDP_SOCKETS is not set
CONFIG_INET=y
CONFIG_IP_MULTICAST=y
CONFIG_IP_ADVANCED_ROUTER=y
# CONFIG_IP_FIB_TRIE_STATS is not set
CONFIG_IP_MULTIPLE_TABLES=y
CONFIG_IP_ROUTE_MULTIPATH=y
CONFIG_IP_ROUTE_VERBOSE=y
CONFIG_IP_ROUTE_CLASSID=y
# CONFIG_IP_PNP is not set
CONFIG_NET_IPIP=m
CONFIG_NET_IPGRE_DEMUX=m
CONFIG_NET_IP_TUNNEL=m
CONFIG_NET_IPGRE=m
CONFIG_NET_IPGRE_BROADCAST=y
CONFIG_IP_MROUTE_COMMON=y
CONFIG_IP_MROUTE=y
CONFIG_IP_MROUTE_MULTIPLE_TABLES=y
CONFIG_IP_PIMSM_V1=y
CONFIG_IP_PIMSM_V2=y
CONFIG_SYN_COOKIES=y
CONFIG_NET_IPVTI=m
CONFIG_NET_UDP_TUNNEL=m
CONFIG_NET_FOU=m
CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
# CONFIG_INET_ESP_OFFLOAD is not set
CONFIG_INET_IPCOMP=m
CONFIG_INET_XFRM_TUNNEL=m
CONFIG_INET_TUNNEL=m
CONFIG_INET_XFRM_MODE_TRANSPORT=m
CONFIG_INET_XFRM_MODE_TUNNEL=m
CONFIG_INET_XFRM_MODE_BEET=m
CONFIG_INET_DIAG=m
CONFIG_INET_TCP_DIAG=m
CONFIG_INET_UDP_DIAG=m
# CONFIG_INET_RAW_DIAG is not set
CONFIG_INET_DIAG_DESTROY=y
CONFIG_TCP_CONG_ADVANCED=y
CONFIG_TCP_CONG_BIC=m
CONFIG_TCP_CONG_CUBIC=y
CONFIG_TCP_CONG_WESTWOOD=m
CONFIG_TCP_CONG_HTCP=m
CONFIG_TCP_CONG_HSTCP=m
CONFIG_TCP_CONG_HYBLA=m
CONFIG_TCP_CONG_VEGAS=m
CONFIG_TCP_CONG_NV=m
CONFIG_TCP_CONG_SCALABLE=m
CONFIG_TCP_CONG_LP=m
CONFIG_TCP_CONG_VENO=m
CONFIG_TCP_CONG_YEAH=m
CONFIG_TCP_CONG_ILLINOIS=m
CONFIG_TCP_CONG_DCTCP=m
CONFIG_TCP_CONG_CDG=m
CONFIG_TCP_CONG_BBR=m
CONFIG_DEFAULT_CUBIC=y
# CONFIG_DEFAULT_RENO is not set
CONFIG_DEFAULT_TCP_CONG="cubic"
# CONFIG_TCP_MD5SIG is not set
CONFIG_IPV6=m
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_IPV6_ROUTE_INFO=y
CONFIG_IPV6_OPTIMISTIC_DAD=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
# CONFIG_INET6_ESP_OFFLOAD is not set
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_MIP6=m
CONFIG_IPV6_ILA=m
CONFIG_INET6_XFRM_TUNNEL=m
CONFIG_INET6_TUNNEL=m
CONFIG_INET6_XFRM_MODE_TRANSPORT=m
CONFIG_INET6_XFRM_MODE_TUNNEL=m
CONFIG_INET6_XFRM_MODE_BEET=m
CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_SIT=m
CONFIG_IPV6_SIT_6RD=y
CONFIG_IPV6_NDISC_NODETYPE=y
CONFIG_IPV6_TUNNEL=m
CONFIG_IPV6_GRE=m
CONFIG_IPV6_FOU=m
CONFIG_IPV6_FOU_TUNNEL=m
CONFIG_IPV6_MULTIPLE_TABLES=y
CONFIG_IPV6_SUBTREES=y
CONFIG_IPV6_MROUTE=y
CONFIG_IPV6_MROUTE_MULTIPLE_TABLES=y
CONFIG_IPV6_PIMSM_V2=y
# CONFIG_IPV6_SEG6_LWTUNNEL is not set
# CONFIG_IPV6_SEG6_HMAC is not set
CONFIG_NETLABEL=y
CONFIG_NETWORK_SECMARK=y
CONFIG_NET_PTP_CLASSIFY=y
# CONFIG_NETWORK_PHY_TIMESTAMPING is not set
CONFIG_NETFILTER=y
CONFIG_NETFILTER_ADVANCED=y
# CONFIG_BRIDGE_NETFILTER is not set