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

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

From: Jon Maloy jon.maloy@ericsson.com

[ Upstream commit a7d5f107b4978e08eeab599ee7449af34d034053 ]

When the function tipc_accept_from_sock() fails to create an instance of struct tipc_subscriber it omits to free the already created instance of struct tipc_conn instance before it returns.

We fix that with this commit.

Reported-by: David S. Miller davem@davemloft.net 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/server.c | 1 + 1 file changed, 1 insertion(+)

--- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -313,6 +313,7 @@ static int tipc_accept_from_sock(struct newcon->usr_data = s->tipc_conn_new(newcon->conid); if (!newcon->usr_data) { sock_release(newsock); + conn_put(newcon); return -ENOMEM; }

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

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

From: Mike Maloney maloney@google.com

syzkaller found a race condition fanout_demux_rollover() while removing a packet socket from a fanout group.

po->rollover is read and operated on during packet_rcv_fanout(), via fanout_demux_rollover(), but the pointer is currently cleared before the synchronization in packet_release(). It is safer to delay the cleanup until after synchronize_net() has been called, ensuring all calls to packet_rcv_fanout() for this socket have finished.

To further simplify synchronization around the rollover structure, set po->rollover in fanout_add() only if there are no errors. This removes the need for rcu in the struct and in the call to packet_getsockopt(..., PACKET_ROLLOVER_STATS, ...).

Crashing stack trace: fanout_demux_rollover+0xb6/0x4d0 net/packet/af_packet.c:1392 packet_rcv_fanout+0x649/0x7c8 net/packet/af_packet.c:1487 dev_queue_xmit_nit+0x835/0xc10 net/core/dev.c:1953 xmit_one net/core/dev.c:2975 [inline] dev_hard_start_xmit+0x16b/0xac0 net/core/dev.c:2995 __dev_queue_xmit+0x17a4/0x2050 net/core/dev.c:3476 dev_queue_xmit+0x17/0x20 net/core/dev.c:3509 neigh_connected_output+0x489/0x720 net/core/neighbour.c:1379 neigh_output include/net/neighbour.h:482 [inline] ip6_finish_output2+0xad1/0x22a0 net/ipv6/ip6_output.c:120 ip6_finish_output+0x2f9/0x920 net/ipv6/ip6_output.c:146 NF_HOOK_COND include/linux/netfilter.h:239 [inline] ip6_output+0x1f4/0x850 net/ipv6/ip6_output.c:163 dst_output include/net/dst.h:459 [inline] NF_HOOK.constprop.35+0xff/0x630 include/linux/netfilter.h:250 mld_sendpack+0x6a8/0xcc0 net/ipv6/mcast.c:1660 mld_send_initial_cr.part.24+0x103/0x150 net/ipv6/mcast.c:2072 mld_send_initial_cr net/ipv6/mcast.c:2056 [inline] ipv6_mc_dad_complete+0x99/0x130 net/ipv6/mcast.c:2079 addrconf_dad_completed+0x595/0x970 net/ipv6/addrconf.c:4039 addrconf_dad_work+0xac9/0x1160 net/ipv6/addrconf.c:3971 process_one_work+0xbf0/0x1bc0 kernel/workqueue.c:2113 worker_thread+0x223/0x1990 kernel/workqueue.c:2247 kthread+0x35e/0x430 kernel/kthread.c:231 ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:432

Fixes: 0648ab70afe6 ("packet: rollover prepare: per-socket state") Fixes: 509c7a1ecc860 ("packet: avoid panic in packet_getsockopt()") Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: Mike Maloney maloney@google.com Reviewed-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/packet/af_packet.c | 32 ++++++++++---------------------- net/packet/internal.h | 1 - 2 files changed, 10 insertions(+), 23 deletions(-)

--- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1661,7 +1661,6 @@ static int fanout_add(struct sock *sk, u atomic_long_set(&rollover->num, 0); atomic_long_set(&rollover->num_huge, 0); atomic_long_set(&rollover->num_failed, 0); - po->rollover = rollover; }

match = NULL; @@ -1706,6 +1705,8 @@ static int fanout_add(struct sock *sk, u if (atomic_read(&match->sk_ref) < PACKET_FANOUT_MAX) { __dev_remove_pack(&po->prot_hook); po->fanout = match; + po->rollover = rollover; + rollover = NULL; atomic_inc(&match->sk_ref); __fanout_link(sk, po); err = 0; @@ -1719,10 +1720,7 @@ static int fanout_add(struct sock *sk, u }

out: - if (err && rollover) { - kfree_rcu(rollover, rcu); - po->rollover = NULL; - } + kfree(rollover); mutex_unlock(&fanout_mutex); return err; } @@ -1746,11 +1744,6 @@ static struct packet_fanout *fanout_rele list_del(&f->list); else f = NULL; - - if (po->rollover) { - kfree_rcu(po->rollover, rcu); - po->rollover = NULL; - } } mutex_unlock(&fanout_mutex);

@@ -3039,6 +3032,7 @@ static int packet_release(struct socket synchronize_net();

if (f) { + kfree(po->rollover); fanout_release_data(f); kfree(f); } @@ -3853,7 +3847,6 @@ static int packet_getsockopt(struct sock void *data = &val; union tpacket_stats_u st; struct tpacket_rollover_stats rstats; - struct packet_rollover *rollover;

if (level != SOL_PACKET) return -ENOPROTOOPT; @@ -3932,18 +3925,13 @@ static int packet_getsockopt(struct sock 0); break; case PACKET_ROLLOVER_STATS: - rcu_read_lock(); - rollover = rcu_dereference(po->rollover); - if (rollover) { - rstats.tp_all = atomic_long_read(&rollover->num); - rstats.tp_huge = atomic_long_read(&rollover->num_huge); - rstats.tp_failed = atomic_long_read(&rollover->num_failed); - data = &rstats; - lv = sizeof(rstats); - } - rcu_read_unlock(); - if (!rollover) + if (!po->rollover) return -EINVAL; + rstats.tp_all = atomic_long_read(&po->rollover->num); + rstats.tp_huge = atomic_long_read(&po->rollover->num_huge); + rstats.tp_failed = atomic_long_read(&po->rollover->num_failed); + data = &rstats; + lv = sizeof(rstats); break; case PACKET_TX_HAS_OFF: val = po->tp_tx_has_off; --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -92,7 +92,6 @@ struct packet_fanout {

struct packet_rollover { int sock; - struct rcu_head rcu; atomic_long_t num; atomic_long_t num_huge; atomic_long_t num_failed;

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

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

From: Lars Persson lars.persson@axis.com

[ Upstream commit 45ab4b13e46325d00f4acdb365d406e941a15f81 ]

The mss variable tracks the last max segment size sent to the TSO engine. We do not update the hardware as long as we receive skb:s with the same value in gso_size.

During a network device down/up cycle (mapped to stmmac_release() and stmmac_open() callbacks) we issue a reset to the hardware and it forgets the setting for mss. However we did not zero out our mss variable so the next transmission of a gso packet happens with an undefined hardware setting.

This triggers a hang in the TSO engine and eventuelly the netdev watchdog will bark.

Fixes: f748be531d70 ("stmmac: support new GMAC4") Signed-off-by: Lars Persson larper@axis.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1795,6 +1795,7 @@ static int stmmac_open(struct net_device

priv->dma_buf_sz = STMMAC_ALIGN(buf_sz); priv->rx_copybreak = STMMAC_RX_COPYBREAK; + priv->mss = 0;

ret = alloc_dma_desc_resources(priv); if (ret < 0) {

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

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

From: Julian Wiedmann jwi@linux.vnet.ibm.com

[ Upstream commit 6d69b1f1eb7a2edf8a3547f361c61f2538e054bb ]

Using GSO with small MTUs currently results in a substantial throughput regression - which is caused by how qeth needs to map non-linear skbs into its IO buffer elements: compared to a linear skb, each GSO-segmented skb effectively consumes twice as many buffer elements (ie two instead of one) due to the additional header-only part. This causes the Output Queue to be congested with low-utilized IO buffers.

Fix this as follows: If the MSS is low enough so that a non-SG GSO segmentation produces order-0 skbs (currently ~3500 byte), opt out from NETIF_F_SG. This is where we anticipate the biggest savings, since an SG-enabled GSO segmentation produces skbs that always consume at least two buffer elements.

Larger MSS values continue to get a SG-enabled GSO segmentation, since 1) the relative overhead of the additional header-only buffer element becomes less noticeable, and 2) the linearization overhead increases.

With the throughput regression fixed, re-enable NETIF_F_SG by default to reap the significant CPU savings of GSO.

Fixes: 5722963a8e83 ("qeth: do not turn on SG per default") Reported-by: Nils Hoppmann niho@de.ibm.com Signed-off-by: Julian Wiedmann jwi@linux.vnet.ibm.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/s390/net/qeth_core.h | 3 +++ drivers/s390/net/qeth_core_main.c | 31 +++++++++++++++++++++++++++++++ drivers/s390/net/qeth_l2_main.c | 2 ++ drivers/s390/net/qeth_l3_main.c | 2 ++ 4 files changed, 38 insertions(+)

--- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -1004,6 +1004,9 @@ struct qeth_cmd_buffer *qeth_get_setassp int qeth_set_features(struct net_device *, netdev_features_t); int qeth_recover_features(struct net_device *); netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t); +netdev_features_t qeth_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features);

/* exports for OSN */ int qeth_osn_assist(struct net_device *, void *, int); --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -19,6 +19,11 @@ #include <linux/mii.h> #include <linux/kthread.h> #include <linux/slab.h> +#include <linux/if_vlan.h> +#include <linux/netdevice.h> +#include <linux/netdev_features.h> +#include <linux/skbuff.h> + #include <net/iucv/af_iucv.h> #include <net/dsfield.h>

@@ -6240,6 +6245,32 @@ netdev_features_t qeth_fix_features(stru } EXPORT_SYMBOL_GPL(qeth_fix_features);

+netdev_features_t qeth_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + /* GSO segmentation builds skbs with + * a (small) linear part for the headers, and + * page frags for the data. + * Compared to a linear skb, the header-only part consumes an + * additional buffer element. This reduces buffer utilization, and + * hurts throughput. So compress small segments into one element. + */ + if (netif_needs_gso(skb, features)) { + /* match skb_segment(): */ + unsigned int doffset = skb->data - skb_mac_header(skb); + unsigned int hsize = skb_shinfo(skb)->gso_size; + unsigned int hroom = skb_headroom(skb); + + /* linearize only if resulting skb allocations are order-0: */ + if (SKB_DATA_ALIGN(hroom + doffset + hsize) <= SKB_MAX_HEAD(0)) + features &= ~NETIF_F_SG; + } + + return vlan_features_check(skb, features); +} +EXPORT_SYMBOL_GPL(qeth_features_check); + static int __init qeth_core_init(void) { int rc; --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -1084,6 +1084,7 @@ static const struct net_device_ops qeth_ .ndo_stop = qeth_l2_stop, .ndo_get_stats = qeth_get_stats, .ndo_start_xmit = qeth_l2_hard_start_xmit, + .ndo_features_check = qeth_features_check, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = qeth_l2_set_rx_mode, .ndo_do_ioctl = qeth_l2_do_ioctl, @@ -1128,6 +1129,7 @@ static int qeth_l2_setup_netdev(struct q if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) { card->dev->hw_features = NETIF_F_SG; card->dev->vlan_features = NETIF_F_SG; + card->dev->features |= NETIF_F_SG; /* OSA 3S and earlier has no RX/TX support */ if (qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM)) { card->dev->hw_features |= NETIF_F_IP_CSUM; --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -3066,6 +3066,7 @@ static const struct net_device_ops qeth_ .ndo_stop = qeth_l3_stop, .ndo_get_stats = qeth_get_stats, .ndo_start_xmit = qeth_l3_hard_start_xmit, + .ndo_features_check = qeth_features_check, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = qeth_l3_set_multicast_list, .ndo_do_ioctl = qeth_l3_do_ioctl, @@ -3122,6 +3123,7 @@ static int qeth_l3_setup_netdev(struct q card->dev->vlan_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_TSO; + card->dev->features |= NETIF_F_SG; } } } else if (card->info.type == QETH_CARD_TYPE_IQD) {

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

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

From: Tommi Rantala tommi.t.rantala@nokia.com

[ Upstream commit c7799c067c2ae33e348508c8afec354f3257ff25 ]

Remove the second tipc_rcv() call in tipc_udp_recv(). We have just checked that the bearer is not up, and calling tipc_rcv() with a bearer that is not up leads to a TIPC div-by-zero crash in tipc_node_calculate_timer(). The crash is rare in practice, but can happen like this:

We're enabling a bearer, but it's not yet up and fully initialized. At the same time we receive a discovery packet, and in tipc_udp_recv() we end up calling tipc_rcv() with the not-yet-initialized bearer, causing later the div-by-zero crash in tipc_node_calculate_timer().

Jon Maloy explains the impact of removing the second tipc_rcv() call: "link setup in the worst case will be delayed until the next arriving discovery messages, 1 sec later, and this is an acceptable delay."

As the tipc_rcv() call is removed, just leave the function via the rcu_out label, so that we will kfree_skb().

[ 12.590450] Own node address <1.1.1>, network identity 1 [ 12.668088] divide error: 0000 [#1] SMP [ 12.676952] CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.14.2-dirty #1 [ 12.679225] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-2.fc27 04/01/2014 [ 12.682095] task: ffff8c2a761edb80 task.stack: ffffa41cc0cac000 [ 12.684087] RIP: 0010:tipc_node_calculate_timer.isra.12+0x45/0x60 [tipc] [ 12.686486] RSP: 0018:ffff8c2a7fc838a0 EFLAGS: 00010246 [ 12.688451] RAX: 0000000000000000 RBX: ffff8c2a5b382600 RCX: 0000000000000000 [ 12.691197] RDX: 0000000000000000 RSI: ffff8c2a5b382600 RDI: ffff8c2a5b382600 [ 12.693945] RBP: ffff8c2a7fc838b0 R08: 0000000000000001 R09: 0000000000000001 [ 12.696632] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8c2a5d8949d8 [ 12.699491] R13: ffffffff95ede400 R14: 0000000000000000 R15: ffff8c2a5d894800 [ 12.702338] FS: 0000000000000000(0000) GS:ffff8c2a7fc80000(0000) knlGS:0000000000000000 [ 12.705099] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 12.706776] CR2: 0000000001bb9440 CR3: 00000000bd009001 CR4: 00000000003606e0 [ 12.708847] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 12.711016] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 12.712627] Call Trace: [ 12.713390] <IRQ> [ 12.714011] tipc_node_check_dest+0x2e8/0x350 [tipc] [ 12.715286] tipc_disc_rcv+0x14d/0x1d0 [tipc] [ 12.716370] tipc_rcv+0x8b0/0xd40 [tipc] [ 12.717396] ? minmax_running_min+0x2f/0x60 [ 12.718248] ? dst_alloc+0x4c/0xa0 [ 12.718964] ? tcp_ack+0xaf1/0x10b0 [ 12.719658] ? tipc_udp_is_known_peer+0xa0/0xa0 [tipc] [ 12.720634] tipc_udp_recv+0x71/0x1d0 [tipc] [ 12.721459] ? dst_alloc+0x4c/0xa0 [ 12.722130] udp_queue_rcv_skb+0x264/0x490 [ 12.722924] __udp4_lib_rcv+0x21e/0x990 [ 12.723670] ? ip_route_input_rcu+0x2dd/0xbf0 [ 12.724442] ? tcp_v4_rcv+0x958/0xa40 [ 12.725039] udp_rcv+0x1a/0x20 [ 12.725587] ip_local_deliver_finish+0x97/0x1d0 [ 12.726323] ip_local_deliver+0xaf/0xc0 [ 12.726959] ? ip_route_input_noref+0x19/0x20 [ 12.727689] ip_rcv_finish+0xdd/0x3b0 [ 12.728307] ip_rcv+0x2ac/0x360 [ 12.728839] __netif_receive_skb_core+0x6fb/0xa90 [ 12.729580] ? udp4_gro_receive+0x1a7/0x2c0 [ 12.730274] __netif_receive_skb+0x1d/0x60 [ 12.730953] ? __netif_receive_skb+0x1d/0x60 [ 12.731637] netif_receive_skb_internal+0x37/0xd0 [ 12.732371] napi_gro_receive+0xc7/0xf0 [ 12.732920] receive_buf+0x3c3/0xd40 [ 12.733441] virtnet_poll+0xb1/0x250 [ 12.733944] net_rx_action+0x23e/0x370 [ 12.734476] __do_softirq+0xc5/0x2f8 [ 12.734922] irq_exit+0xfa/0x100 [ 12.735315] do_IRQ+0x4f/0xd0 [ 12.735680] common_interrupt+0xa2/0xa2 [ 12.736126] </IRQ> [ 12.736416] RIP: 0010:native_safe_halt+0x6/0x10 [ 12.736925] RSP: 0018:ffffa41cc0cafe90 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff4d [ 12.737756] RAX: 0000000000000000 RBX: ffff8c2a761edb80 RCX: 0000000000000000 [ 12.738504] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 [ 12.739258] RBP: ffffa41cc0cafe90 R08: 0000014b5b9795e5 R09: ffffa41cc12c7e88 [ 12.740118] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000002 [ 12.740964] R13: ffff8c2a761edb80 R14: 0000000000000000 R15: 0000000000000000 [ 12.741831] default_idle+0x2a/0x100 [ 12.742323] arch_cpu_idle+0xf/0x20 [ 12.742796] default_idle_call+0x28/0x40 [ 12.743312] do_idle+0x179/0x1f0 [ 12.743761] cpu_startup_entry+0x1d/0x20 [ 12.744291] start_secondary+0x112/0x120 [ 12.744816] secondary_startup_64+0xa5/0xa5 [ 12.745367] Code: b9 f4 01 00 00 48 89 c2 48 c1 ea 02 48 3d d3 07 00 00 48 0f 47 d1 49 8b 0c 24 48 39 d1 76 07 49 89 14 24 48 89 d1 31 d2 48 89 df <48> f7 f1 89 c6 e8 81 6e ff ff 5b 41 5c 5d c3 66 90 66 2e 0f 1f [ 12.747527] RIP: tipc_node_calculate_timer.isra.12+0x45/0x60 [tipc] RSP: ffff8c2a7fc838a0 [ 12.748555] ---[ end trace 1399ab83390650fd ]--- [ 12.749296] Kernel panic - not syncing: Fatal exception in interrupt [ 12.750123] Kernel Offset: 0x13200000 from 0xffffffff82000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 12.751215] Rebooting in 60 seconds..

Fixes: c9b64d492b1f ("tipc: add replicast peer discovery") Signed-off-by: Tommi Rantala tommi.t.rantala@nokia.com Cc: 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/udp_media.c | 4 ---- 1 file changed, 4 deletions(-)

--- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -371,10 +371,6 @@ static int tipc_udp_recv(struct sock *sk goto rcu_out; }

- tipc_rcv(sock_net(sk), skb, b); - rcu_read_unlock(); - return 0; - rcu_out: rcu_read_unlock(); out:

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

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

From: Masamitsu Yamazaki m-yamazaki@ah.jp.nec.com

commit 4f7f5551a760eb0124267be65763008169db7087 upstream.

System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources.

cleanup_one_si() contains the following processing.

/* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean);

/* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); }

si_state changes as following in the while loop calling poll(to_clean).

SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL

As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES.

=> poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer

As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes.

For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release.

[exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> ---

To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion.

Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu m-yamazaki@ah.jp.nec.com [Adjusted for recent changes in the driver.] [Some fairly major changes went into the IPMI driver in 4.15, so this required a backport as the code had changed and moved to a different file. The 4.14 version of this patch moved some code under an if statement causing it to not apply to 4.7-4.13.] Signed-off-by: Corey Minyard cminyard@mvista.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/char/ipmi/ipmi_si_intf.c | 44 ++++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 21 deletions(-)

--- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -241,6 +241,9 @@ struct smi_info { /* The timer for this si. */ struct timer_list si_timer;

+ /* This flag is set, if the timer can be set */ + bool timer_can_start; + /* This flag is set, if the timer is running (timer_pending() isn't enough) */ bool timer_running;

@@ -416,6 +419,8 @@ out:

static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val) { + if (!smi_info->timer_can_start) + return; smi_info->last_timeout_jiffies = jiffies; mod_timer(&smi_info->si_timer, new_val); smi_info->timer_running = true; @@ -435,21 +440,18 @@ static void start_new_msg(struct smi_inf smi_info->handlers->start_transaction(smi_info->si_sm, msg, size); }

-static void start_check_enables(struct smi_info *smi_info, bool start_timer) +static void start_check_enables(struct smi_info *smi_info) { unsigned char msg[2];

msg[0] = (IPMI_NETFN_APP_REQUEST << 2); msg[1] = IPMI_GET_BMC_GLOBAL_ENABLES_CMD;

- if (start_timer) - start_new_msg(smi_info, msg, 2); - else - smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2); + start_new_msg(smi_info, msg, 2); smi_info->si_state = SI_CHECKING_ENABLES; }

-static void start_clear_flags(struct smi_info *smi_info, bool start_timer) +static void start_clear_flags(struct smi_info *smi_info) { unsigned char msg[3];

@@ -458,10 +460,7 @@ static void start_clear_flags(struct smi msg[1] = IPMI_CLEAR_MSG_FLAGS_CMD; msg[2] = WDT_PRE_TIMEOUT_INT;

- if (start_timer) - start_new_msg(smi_info, msg, 3); - else - smi_info->handlers->start_transaction(smi_info->si_sm, msg, 3); + start_new_msg(smi_info, msg, 3); smi_info->si_state = SI_CLEARING_FLAGS; }

@@ -496,11 +495,11 @@ static void start_getting_events(struct * Note that we cannot just use disable_irq(), since the interrupt may * be shared. */ -static inline bool disable_si_irq(struct smi_info *smi_info, bool start_timer) +static inline bool disable_si_irq(struct smi_info *smi_info) { if ((smi_info->irq) && (!smi_info->interrupt_disabled)) { smi_info->interrupt_disabled = true; - start_check_enables(smi_info, start_timer); + start_check_enables(smi_info); return true; } return false; @@ -510,7 +509,7 @@ static inline bool enable_si_irq(struct { if ((smi_info->irq) && (smi_info->interrupt_disabled)) { smi_info->interrupt_disabled = false; - start_check_enables(smi_info, true); + start_check_enables(smi_info); return true; } return false; @@ -528,7 +527,7 @@ static struct ipmi_smi_msg *alloc_msg_ha

msg = ipmi_alloc_smi_msg(); if (!msg) { - if (!disable_si_irq(smi_info, true)) + if (!disable_si_irq(smi_info)) smi_info->si_state = SI_NORMAL; } else if (enable_si_irq(smi_info)) { ipmi_free_smi_msg(msg); @@ -544,7 +543,7 @@ retry: /* Watchdog pre-timeout */ smi_inc_stat(smi_info, watchdog_pretimeouts);

- start_clear_flags(smi_info, true); + start_clear_flags(smi_info); smi_info->msg_flags &= ~WDT_PRE_TIMEOUT_INT; if (smi_info->intf) ipmi_smi_watchdog_pretimeout(smi_info->intf); @@ -927,7 +926,7 @@ restart: * disable and messages disabled. */ if (smi_info->supports_event_msg_buff || smi_info->irq) { - start_check_enables(smi_info, true); + start_check_enables(smi_info); } else { smi_info->curr_msg = alloc_msg_handle_irq(smi_info); if (!smi_info->curr_msg) @@ -1234,6 +1233,7 @@ static int smi_start_processing(void

/* Set up the timer that drives the interface. */ setup_timer(&new_smi->si_timer, smi_timeout, (long)new_smi); + new_smi->timer_can_start = true; smi_mod_timer(new_smi, jiffies + SI_TIMEOUT_JIFFIES);

/* Try to claim any interrupts. */ @@ -3448,10 +3448,12 @@ static void check_for_broken_irqs(struct check_set_rcv_irq(smi_info); }

-static inline void wait_for_timer_and_thread(struct smi_info *smi_info) +static inline void stop_timer_and_thread(struct smi_info *smi_info) { if (smi_info->thread != NULL) kthread_stop(smi_info->thread); + + smi_info->timer_can_start = false; if (smi_info->timer_running) del_timer_sync(&smi_info->si_timer); } @@ -3593,7 +3595,7 @@ static int try_smi_init(struct smi_info * Start clearing the flags before we enable interrupts or the * timer to avoid racing with the timer. */ - start_clear_flags(new_smi, false); + start_clear_flags(new_smi);

/* * IRQ is defined to be set when non-zero. req_events will @@ -3671,7 +3673,7 @@ static int try_smi_init(struct smi_info return 0;

out_err_stop_timer: - wait_for_timer_and_thread(new_smi); + stop_timer_and_thread(new_smi);

out_err: new_smi->interrupt_disabled = true; @@ -3865,7 +3867,7 @@ static void cleanup_one_si(struct smi_in */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); - wait_for_timer_and_thread(to_clean); + stop_timer_and_thread(to_clean);

/* * Timeouts are stopped, now make sure the interrupts are off @@ -3876,7 +3878,7 @@ static void cleanup_one_si(struct smi_in poll(to_clean); schedule_timeout_uninterruptible(1); } - disable_si_irq(to_clean, false); + disable_si_irq(to_clean); while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1);

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

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

From: Vincent Pelletier plr.vincent@gmail.com

commit 30bf90ccdec1da9c8198b161ecbff39ce4e5a9ba upstream.

Found using DEBUG_ATOMIC_SLEEP while submitting an AIO read operation:

[ 100.853642] BUG: sleeping function called from invalid context at mm/slab.h:421 [ 100.861148] in_atomic(): 1, irqs_disabled(): 1, pid: 1880, name: python [ 100.867954] 2 locks held by python/1880: [ 100.867961] #0: (&epfile->mutex){....}, at: [<f8188627>] ffs_mutex_lock+0x27/0x30 [usb_f_fs] [ 100.868020] #1: (&(&ffs->eps_lock)->rlock){....}, at: [<f818ad4b>] ffs_epfile_io.isra.17+0x24b/0x590 [usb_f_fs] [ 100.868076] CPU: 1 PID: 1880 Comm: python Not tainted 4.14.0-edison+ #118 [ 100.868085] Hardware name: Intel Corporation Merrifield/BODEGA BAY, BIOS 542 2015.01.21:18.19.48 [ 100.868093] Call Trace: [ 100.868122] dump_stack+0x47/0x62 [ 100.868156] ___might_sleep+0xfd/0x110 [ 100.868182] __might_sleep+0x68/0x70 [ 100.868217] kmem_cache_alloc_trace+0x4b/0x200 [ 100.868248] ? dwc3_gadget_ep_alloc_request+0x24/0xe0 [dwc3] [ 100.868302] dwc3_gadget_ep_alloc_request+0x24/0xe0 [dwc3] [ 100.868343] usb_ep_alloc_request+0x16/0xc0 [udc_core] [ 100.868386] ffs_epfile_io.isra.17+0x444/0x590 [usb_f_fs] [ 100.868424] ? _raw_spin_unlock_irqrestore+0x27/0x40 [ 100.868457] ? kiocb_set_cancel_fn+0x57/0x60 [ 100.868477] ? ffs_ep0_poll+0xc0/0xc0 [usb_f_fs] [ 100.868512] ffs_epfile_read_iter+0xfe/0x157 [usb_f_fs] [ 100.868551] ? security_file_permission+0x9c/0xd0 [ 100.868587] ? rw_verify_area+0xac/0x120 [ 100.868633] aio_read+0x9d/0x100 [ 100.868692] ? __fget+0xa2/0xd0 [ 100.868727] ? __might_sleep+0x68/0x70 [ 100.868763] SyS_io_submit+0x471/0x680 [ 100.868878] do_int80_syscall_32+0x4e/0xd0 [ 100.868921] entry_INT80_32+0x2a/0x2a [ 100.868932] EIP: 0xb7fbb676 [ 100.868941] EFLAGS: 00000292 CPU: 1 [ 100.868951] EAX: ffffffda EBX: b7aa2000 ECX: 00000002 EDX: b7af8368 [ 100.868961] ESI: b7fbb660 EDI: b7aab000 EBP: bfb6c658 ESP: bfb6c638 [ 100.868973] DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b

Signed-off-by: Vincent Pelletier plr.vincent@gmail.com Signed-off-by: Felipe Balbi felipe.balbi@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/gadget/function/f_fs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1015,7 +1015,7 @@ static ssize_t ffs_epfile_io(struct file else ret = ep->status; goto error_mutex; - } else if (!(req = usb_ep_alloc_request(ep->ep, GFP_KERNEL))) { + } else if (!(req = usb_ep_alloc_request(ep->ep, GFP_ATOMIC))) { ret = -ENOMEM; } else { req->buf = data;

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

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

From: Marc Zyngier marc.zyngier@arm.com

commit 64afe6e9eb4841f35317da4393de21a047a883b3 upstream.

The current pending table parsing code assumes that we keep the previous read of the pending bits, but keep that variable in the current block, making sure it is discarded on each loop.

We end-up using whatever is on the stack. Who knows, it might just be the right thing...

Fixes: 33d3bc9556a7d ("KVM: arm64: vgic-its: Read initial LPI pending table") Cc: stable@vger.kernel.org # 4.8 Reported-by: AKASHI Takahiro takahiro.akashi@linaro.org Reviewed-by: Christoffer Dall christoffer.dall@linaro.org Signed-off-by: Marc Zyngier marc.zyngier@arm.com Signed-off-by: Christoffer Dall christoffer.dall@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- virt/kvm/arm/vgic/vgic-its.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -322,6 +322,7 @@ static int its_sync_lpi_pending_table(st int ret = 0; u32 *intids; int nr_irqs, i; + u8 pendmask;

nr_irqs = vgic_copy_lpi_list(vcpu->kvm, &intids); if (nr_irqs < 0) @@ -329,7 +330,6 @@ static int its_sync_lpi_pending_table(st

for (i = 0; i < nr_irqs; i++) { int byte_offset, bit_nr; - u8 pendmask;

byte_offset = intids[i] / BITS_PER_BYTE; bit_nr = intids[i] % BITS_PER_BYTE;

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

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

From: Masahiro Yamada yamada.masahiro@socionext.com

[ Upstream commit 433dc2ebe7d17dd21cba7ad5c362d37323592236 ]

Some $(call cc-option,...) are invoked very early, even before KBUILD_CFLAGS, etc. are initialized.

The returned string from $(call cc-option,...) depends on KBUILD_CPPFLAGS, KBUILD_CFLAGS, and GCC_PLUGINS_CFLAGS.

Since they are exported, they are not empty when the top Makefile is recursively invoked.

The recursion occurs in several places. For example, the top Makefile invokes itself for silentoldconfig. "make tinyconfig", "make rpm-pkg" are the cases, too.

In those cases, the second call of cc-option from the same line runs a different shell command due to non-pristine KBUILD_CFLAGS.

To get the same result all the time, KBUILD_* and GCC_PLUGINS_CFLAGS must be initialized before any call of cc-option. This avoids garbage data in the .cache.mk file.

Move all calls of cc-option below the config targets because target compiler flags are unnecessary for Kconfig.

Signed-off-by: Masahiro Yamada yamada.masahiro@socionext.com Reviewed-by: Douglas Anderson dianders@chromium.org Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Makefile | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-)

--- a/Makefile +++ b/Makefile @@ -370,9 +370,6 @@ LDFLAGS_MODULE = CFLAGS_KERNEL = AFLAGS_KERNEL = LDFLAGS_vmlinux = -CFLAGS_GCOV := -fprofile-arcs -ftest-coverage -fno-tree-loop-im $(call cc-disable-warning,maybe-uninitialized,) -CFLAGS_KCOV := $(call cc-option,-fsanitize-coverage=trace-pc,) -

# Use USERINCLUDE when you must reference the UAPI directories only. USERINCLUDE := \ @@ -393,21 +390,19 @@ LINUXINCLUDE := \

LINUXINCLUDE += $(filter-out $(LINUXINCLUDE),$(USERINCLUDE))

-KBUILD_CPPFLAGS := -D__KERNEL__ - +KBUILD_AFLAGS := -D__ASSEMBLY__ KBUILD_CFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -fno-common \ -Werror-implicit-function-declaration \ -Wno-format-security \ - -std=gnu89 $(call cc-option,-fno-PIE) - - + -std=gnu89 +KBUILD_CPPFLAGS := -D__KERNEL__ KBUILD_AFLAGS_KERNEL := KBUILD_CFLAGS_KERNEL := -KBUILD_AFLAGS := -D__ASSEMBLY__ $(call cc-option,-fno-PIE) KBUILD_AFLAGS_MODULE := -DMODULE KBUILD_CFLAGS_MODULE := -DMODULE KBUILD_LDFLAGS_MODULE := -T $(srctree)/scripts/module-common.lds +GCC_PLUGINS_CFLAGS :=

# Read KERNELRELEASE from include/config/kernel.release (if it exists) KERNELRELEASE = $(shell cat include/config/kernel.release 2> /dev/null) @@ -420,7 +415,7 @@ export MAKE AWK GENKSYMS INSTALLKERNEL P export HOSTCXX HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS

export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS LDFLAGS -export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE CFLAGS_GCOV CFLAGS_KCOV CFLAGS_KASAN CFLAGS_UBSAN +export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE CFLAGS_KASAN CFLAGS_UBSAN export KBUILD_AFLAGS AFLAGS_KERNEL AFLAGS_MODULE export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL @@ -620,6 +615,12 @@ endif # Defaults to vmlinux, but the arch makefile usually adds further targets all: vmlinux

+KBUILD_CFLAGS += $(call cc-option,-fno-PIE) +KBUILD_AFLAGS += $(call cc-option,-fno-PIE) +CFLAGS_GCOV := -fprofile-arcs -ftest-coverage -fno-tree-loop-im $(call cc-disable-warning,maybe-uninitialized,) +CFLAGS_KCOV := $(call cc-option,-fsanitize-coverage=trace-pc,) +export CFLAGS_GCOV CFLAGS_KCOV + # The arch Makefile can set ARCH_{CPP,A,C}FLAGS to override the default # values of the respective KBUILD_* variables ARCH_CPPFLAGS :=

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

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

From: Paul Moore paul@paul-moore.com

[ Upstream commit 173743dd99a49c956b124a74c8aacb0384739a4c ]

Prior to this patch we enabled audit in audit_init(), which is too late for PID 1 as the standard initcalls are run after the PID 1 task is forked. This means that we never allocate an audit_context (see audit_alloc()) for PID 1 and therefore miss a lot of audit events generated by PID 1.

This patch enables audit as early as possible to help ensure that when PID 1 is forked it can allocate an audit_context if required.

Reviewed-by: Richard Guy Briggs rgb@redhat.com Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/audit.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

--- a/kernel/audit.c +++ b/kernel/audit.c @@ -79,13 +79,13 @@ static int audit_initialized; #define AUDIT_OFF 0 #define AUDIT_ON 1 #define AUDIT_LOCKED 2 -u32 audit_enabled; -u32 audit_ever_enabled; +u32 audit_enabled = AUDIT_OFF; +u32 audit_ever_enabled = !!AUDIT_OFF;

EXPORT_SYMBOL_GPL(audit_enabled);

/* Default state when kernel boots without any parameters. */ -static u32 audit_default; +static u32 audit_default = AUDIT_OFF;

/* If auditing cannot proceed, audit_failure selects what happens. */ static u32 audit_failure = AUDIT_FAIL_PRINTK; @@ -1199,8 +1199,6 @@ static int __init audit_init(void) skb_queue_head_init(&audit_skb_queue); skb_queue_head_init(&audit_skb_hold_queue); audit_initialized = AUDIT_INITIALIZED; - audit_enabled = audit_default; - audit_ever_enabled |= !!audit_default;

audit_log(NULL, GFP_KERNEL, AUDIT_KERNEL, "initialized");

@@ -1217,6 +1215,8 @@ static int __init audit_enable(char *str audit_default = !!simple_strtol(str, NULL, 0); if (!audit_default) audit_initialized = AUDIT_DISABLED; + audit_enabled = audit_default; + audit_ever_enabled = !!audit_enabled;

pr_info("%s\n", audit_default ? "enabled (after initialization)" : "disabled (until reboot)");

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

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

From: Leon Romanovsky leon@kernel.org

[ Upstream commit 7d7d065a5eec7e218174d5c64a9f53f99ffdb119 ]

Chelsio cxgb4 HW is big-endian, hence there is need to properly annotate r2 and stag fields as __be32 and not __u32 to fix the following sparse warnings.

drivers/infiniband/hw/cxgb4/qp.c:614:16: warning: incorrect type in assignment (different base types) expected unsigned int [unsigned] [usertype] r2 got restricted __be32 [usertype] <noident> drivers/infiniband/hw/cxgb4/qp.c:615:18: warning: incorrect type in assignment (different base types) expected unsigned int [unsigned] [usertype] stag got restricted __be32 [usertype] <noident>

Cc: Steve Wise swise@opengridcomputing.com Signed-off-by: Leon Romanovsky leon@kernel.org Reviewed-by: Steve Wise swise@opengridcomputing.com Signed-off-by: Doug Ledford dledford@redhat.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/infiniband/hw/cxgb4/t4fw_ri_api.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h +++ b/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h @@ -675,8 +675,8 @@ struct fw_ri_fr_nsmr_tpte_wr { __u16 wrid; __u8 r1[3]; __u8 len16; - __u32 r2; - __u32 stag; + __be32 r2; + __be32 stag; struct fw_ri_tpte tpte; __u64 pbl[2]; };