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

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

From: "Michał Mirosław" mirq-linux@rere.qmqm.pl

[ Upstream commit e84b47941e15e6666afb8ee8b21d1c3fc1a013af ]

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

Signed-off-by: Michał Mirosław mirq-linux@rere.qmqm.pl Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/ibm/ibmvnic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -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: Xin Long lucien.xin@gmail.com

[ 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.

Fixes: 93531c674315 ("net/ipv6: separate handling of FIB entries from dst based routes") Fixes: 23fb93a4d3f1 ("net/ipv6: Cleanup exception and cache route handling") Reported-by: Li Shuang shuali@redhat.com Signed-off-by: Xin Long lucien.xin@gmail.com Reviewed-by: David Ahern dsahern@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/route.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)

--- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -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: Doug Berger opendmb@gmail.com

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 ]

Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file") Signed-off-by: Doug Berger opendmb@gmail.com Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-)

--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -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: Xin Long lucien.xin@gmail.com

[ 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.

Fixes: 28aa4c26fce2 ("sctp: add SCTP_PR_SUPPORTED on sctp sockopt") Reported-by: Ying Xu yinxu@redhat.com Signed-off-by: Xin Long lucien.xin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sctp/socket.c | 26 +++++--------------------- 1 file changed, 5 insertions(+), 21 deletions(-)

--- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -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: Siva Reddy Kallam siva.kallam@broadcom.com

[ 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.

Signed-off-by: Siva Reddy Kallam siva.kallam@broadcom.com Acked-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/tg3.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-)

--- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -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 donmalo99@gmail.com

[ 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.

Acked-by: Ying Xue ying.xue@windriver.com Signed-off-by: Jon Maloy jon.maloy@ericsson.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/tipc/discover.c | 19 ++++++++++--------- net/tipc/net.c | 45 +++++++++++++++++++++++++++++++++++++-------- net/tipc/net.h | 2 +- 3 files changed, 48 insertions(+), 18 deletions(-)

--- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -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); --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -104,6 +104,14 @@ * - A local spin_lock protecting the queue of subscriber events. */

+struct tipc_net_work { + struct work_struct work; + struct net *net; + u32 addr; +}; + +static void tipc_net_finalize(struct net *net, u32 addr); + int tipc_net_init(struct net *net, u8 *node_id, u32 addr) { if (tipc_own_id(net)) { @@ -119,17 +127,38 @@ int tipc_net_init(struct net *net, u8 *n return 0; }

-void tipc_net_finalize(struct net *net, u32 addr) +static void tipc_net_finalize(struct net *net, u32 addr) { struct tipc_net *tn = tipc_net(net);

- if (!cmpxchg(&tn->node_addr, 0, addr)) { - tipc_set_node_addr(net, addr); - tipc_named_reinit(net); - tipc_sk_reinit(net); - tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr, - TIPC_CLUSTER_SCOPE, 0, addr); - } + if (cmpxchg(&tn->node_addr, 0, addr)) + return; + tipc_set_node_addr(net, addr); + tipc_named_reinit(net); + tipc_sk_reinit(net); + tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr, + TIPC_CLUSTER_SCOPE, 0, addr); +} + +static void tipc_net_finalize_work(struct work_struct *work) +{ + struct tipc_net_work *fwork; + + fwork = container_of(work, struct tipc_net_work, work); + tipc_net_finalize(fwork->net, fwork->addr); + kfree(fwork); +} + +void tipc_sched_net_finalize(struct net *net, u32 addr) +{ + struct tipc_net_work *fwork = kzalloc(sizeof(*fwork), GFP_ATOMIC); + + if (!fwork) + return; + INIT_WORK(&fwork->work, tipc_net_finalize_work); + fwork->net = net; + fwork->addr = addr; + schedule_work(&fwork->work); }

void tipc_net_stop(struct net *net) --- a/net/tipc/net.h +++ b/net/tipc/net.h @@ -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: Florian Fainelli f.fainelli@gmail.com

[ 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.

Fixes: 40755a0fce17 ("net: systemport: add suspend and resume support") Fixes: 80105befdb4b ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver") Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bcmsysport.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-)

--- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -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: Jakub Kicinski jakub.kicinski@netronome.com

[ 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.

Fixes: 0a6e77784f49 ("net/sched: allow flower to match tunnel options") Signed-off-by: Jakub Kicinski jakub.kicinski@netronome.com Acked-by: Simon Horman simon.horman@netronome.com Acked-by: Jiri Pirko jiri@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/cls_flower.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-)

--- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -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]); }

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

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

From: Or Gerlitz ogerlitz@mellanox.com

[ 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.

Fixes: cee26487620b ('net/mlx5e: Set vlan masks for all offloaded TC rules') Signed-off-by: Or Gerlitz ogerlitz@mellanox.com Reported-by: Slava Ovsiienko viacheslavo@mellanox.com Reviewed-by: Jianbo Liu jianbol@mellanox.com Reviewed-by: Roi Dayan roid@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 63 ++++++++++++------------ 1 file changed, 32 insertions(+), 31 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -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: Yuval Avnery yuvalav@mellanox.com

[ 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.

Fixes: 89d44f0a6c73 ("net/mlx5_core: Add pci error handlers to mlx5_core driver") Signed-off-by: Yuval Avnery yuvalav@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 27 +++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -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: Xin Long lucien.xin@gmail.com

[ 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.

Acked-by: Neil Horman nhorman@tuxdriver.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/sctp/sctp.h | 12 ++++++++++++ net/sctp/output.c | 3 +++ 2 files changed, 15 insertions(+)

--- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -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__ */ --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -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: Valentine Fatiev valentinef@mellanox.com

[ 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.

Fixes: d605d66 ("net/mlx5e: Add support for ethtool self diagnostics test") Signed-off-by: Valentine Fatiev valentinef@mellanox.com Reviewed-by: Eran Ben Elisha eranbe@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c | 26 ++++++------------ 1 file changed, 10 insertions(+), 16 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -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: Eric Dumazet edumazet@google.com

[ 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.

Fixes: 648700f76b03 ("inet: frags: use rhashtables for reassembly units") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: 배석진 soukjin.bae@samsung.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/inet_fragment.c | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-)

--- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -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: Raed Salem raeds@mellanox.com

[ 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.

Fixes: d6c4f0298cec ("net/mlx5: Refactor accel IPSec code") Signed-off-by: Raed Salem raeds@mellanox.com Reviewed-by: Aviad Yehezkel aviadye@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c @@ -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: Andrew Lunn andrew@lunn.ch

[ 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.

Reported-by: Chris Healy Chris.Healy@zii.aero Fixes: 40cff8fca9e3 ("net: dsa: mv88e6xxx: Fix stats histogram mode") Signed-off-by: Andrew Lunn andrew@lunn.ch Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/dsa/mv88e6xxx/global1.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -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: Xin Long lucien.xin@gmail.com

[ 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.

Fixes: 5bbbbe32a431 ("sctp: introduce stream scheduler foundations") Reported-by: Jianwen Ji jiji@redhat.com Signed-off-by: Xin Long lucien.xin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/uapi/linux/sctp.h | 1 + net/sctp/outqueue.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-)

--- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -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 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -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 Tristram.Ha@microchip.com

[ Upstream commit 284fb78ed7572117846f8e1d1d8e3dbfd16880c2 ]

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

Fixes: b987e98e50ab90e5 ("dsa: add DSA switch driver for Microchip KSZ9477") Signed-off-by: Tristram Ha Tristram.Ha@microchip.com Reviewed-by: Pavel Machek pavel@ucw.cz Reviewed-by: Andrew Lunn andrew@lunn.ch Reviewed-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/dsa/microchip/ksz_common.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

--- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -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: Martin Schiller ms@dev.tdt.de

[ 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.

Fixes: 7e5fbd1e0700 ("net: mdio-gpio: Convert to use gpiod functions where possible") Signed-off-by: Martin Schiller ms@dev.tdt.de Reviewed-by: Andrew Lunn andrew@lunn.ch Reviewed-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/phy/mdio-gpio.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

--- a/drivers/net/phy/mdio-gpio.c +++ b/drivers/net/phy/mdio-gpio.c @@ -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: Shalom Toledo shalomt@mellanox.com

[ 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.

Fixes: 9148e7cf73ce ("mlxsw: spectrum: Add policers for trap groups") Signed-off-by: Shalom Toledo shalomt@mellanox.com Signed-off-by: Ido Schimmel idosch@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 1 - 1 file changed, 1 deletion(-)

--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -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: David Howells dhowells@redhat.com

[ 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.

Fixes: 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code") Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/rxrpc/ar-internal.h | 1 + net/rxrpc/call_event.c | 18 ++++++++++++++---- net/rxrpc/output.c | 35 +++++++++++++++++++++++++++++++---- 3 files changed, 46 insertions(+), 8 deletions(-)

--- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -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 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -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; } --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -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: Greg Kroah-Hartman gregkh@linuxfoundation.org

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.

Reported-by: Jiri Kosina jkosina@suse.cz Cc: Thomas Gleixner tglx@linutronix.de Cc: Peter Zijlstra peterz@infradead.org Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: Andrea Arcangeli aarcange@redhat.com Cc: "WoodhouseDavid" dwmw@amazon.co.uk Cc: Andi Kleen ak@linux.intel.com Cc: Tim Chen tim.c.chen@linux.intel.com Cc: "SchauflerCasey" casey.schaufler@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/cpu/bugs.c | 57 ++++----------------------------------------- kernel/cpu.c | 11 -------- 2 files changed, 7 insertions(+), 61 deletions(-)

--- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -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]); --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -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)))