From: David S. Miller davem@davemloft.net

commit 7b566f70e1bf65b189b66eb3de6f431c30f7dff2 upstream.

This reverts:

ef1b5bf506b1 ("net: phy: Fix not to call phy_resume() if PHY is not attached") 8c85f4b81296 ("net: phy: micrel: add toggling phy reset if PHY is not attached")

Andrew Lunn informs me that there are alternative efforts underway to fix this more properly.

Signed-off-by: David S. Miller davem@davemloft.net [just take the ef1b5bf506b1 revert - gregkh] Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/net/phy/phy_device.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)

--- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -76,7 +76,7 @@ static LIST_HEAD(phy_fixup_list); static DEFINE_MUTEX(phy_fixup_lock);

#ifdef CONFIG_PM -static bool mdio_bus_phy_may_suspend(struct phy_device *phydev, bool suspend) +static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) { struct device_driver *drv = phydev->mdio.dev.driver; struct phy_driver *phydrv = to_phy_driver(drv); @@ -88,11 +88,10 @@ static bool mdio_bus_phy_may_suspend(str /* PHY not attached? May suspend if the PHY has not already been * suspended as part of a prior call to phy_disconnect() -> * phy_detach() -> phy_suspend() because the parent netdev might be the - * MDIO bus driver and clock gated at this point. Also may resume if - * PHY is not attached. + * MDIO bus driver and clock gated at this point. */ if (!netdev) - return suspend ? !phydev->suspended : phydev->suspended; + return !phydev->suspended;

/* Don't suspend PHY if the attached netdev parent may wakeup. * The parent may point to a PCI device, as in tg3 driver. @@ -122,7 +121,7 @@ static int mdio_bus_phy_suspend(struct d if (phydev->attached_dev && phydev->adjust_link) phy_stop_machine(phydev);

- if (!mdio_bus_phy_may_suspend(phydev, true)) + if (!mdio_bus_phy_may_suspend(phydev)) return 0;

return phy_suspend(phydev); @@ -133,7 +132,7 @@ static int mdio_bus_phy_resume(struct de struct phy_device *phydev = to_phy_device(dev); int ret;

- if (!mdio_bus_phy_may_suspend(phydev, false)) + if (!mdio_bus_phy_may_suspend(phydev)) goto no_resume;

ret = phy_resume(phydev);

From: Dmitry Yakunin zeil@yandex-team.ru

[ Upstream commit 018d26fcd12a75fb9b5fe233762aa3f2f0854b88 ]

In our production environment we have faced with problem that updating classid in cgroup with heavy tasks cause long freeze of the file tables in this tasks. By heavy tasks we understand tasks with many threads and opened sockets (e.g. balancers). This freeze leads to an increase number of client timeouts.

This patch implements following logic to fix this issue: аfter iterating 1000 file descriptors file table lock will be released thus providing a time gap for socket creation/deletion.

Now update is non atomic and socket may be skipped using calls:

dup2(oldfd, newfd); close(oldfd);

But this case is not typical. Moreover before this patch skip is possible too by hiding socket fd in unix socket buffer.

New sockets will be allocated with updated classid because cgroup state is updated before start of the file descriptors iteration.

So in common cases this patch has no side effects.

Signed-off-by: Dmitry Yakunin zeil@yandex-team.ru Reviewed-by: Konstantin Khlebnikov khlebnikov@yandex-team.ru Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/netclassid_cgroup.c | 47 +++++++++++++++++++++++++++++++++---------- 1 file changed, 37 insertions(+), 10 deletions(-)

--- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -57,30 +57,60 @@ static void cgrp_css_free(struct cgroup_ kfree(css_cls_state(css)); }

+/* + * To avoid freezing of sockets creation for tasks with big number of threads + * and opened sockets lets release file_lock every 1000 iterated descriptors. + * New sockets will already have been created with new classid. + */ + +struct update_classid_context { + u32 classid; + unsigned int batch; +}; + +#define UPDATE_CLASSID_BATCH 1000 + static int update_classid_sock(const void *v, struct file *file, unsigned n) { int err; + struct update_classid_context *ctx = (void *)v; struct socket *sock = sock_from_file(file, &err);

if (sock) { spin_lock(&cgroup_sk_update_lock); - sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, - (unsigned long)v); + sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, ctx->classid); spin_unlock(&cgroup_sk_update_lock); } + if (--ctx->batch == 0) { + ctx->batch = UPDATE_CLASSID_BATCH; + return n + 1; + } return 0; }

+static void update_classid_task(struct task_struct *p, u32 classid) +{ + struct update_classid_context ctx = { + .classid = classid, + .batch = UPDATE_CLASSID_BATCH + }; + unsigned int fd = 0; + + do { + task_lock(p); + fd = iterate_fd(p->files, fd, update_classid_sock, &ctx); + task_unlock(p); + cond_resched(); + } while (fd); +} + static void cgrp_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct task_struct *p;

cgroup_taskset_for_each(p, css, tset) { - task_lock(p); - iterate_fd(p->files, 0, update_classid_sock, - (void *)(unsigned long)css_cls_state(css)->classid); - task_unlock(p); + update_classid_task(p, css_cls_state(css)->classid); } }

@@ -102,10 +132,7 @@ static int write_classid(struct cgroup_s

css_task_iter_start(css, 0, &it); while ((p = css_task_iter_next(&it))) { - task_lock(p); - iterate_fd(p->files, 0, update_classid_sock, - (void *)(unsigned long)cs->classid); - task_unlock(p); + update_classid_task(p, cs->classid); cond_resched(); } css_task_iter_end(&it);

From: Hangbin Liu liuhangbin@gmail.com

[ Upstream commit 60380488e4e0b95e9e82aa68aa9705baa86de84c ]

Rafał found an issue that for non-Ethernet interface, if we down and up frequently, the memory will be consumed slowly.

The reason is we add allnodes/allrouters addressed in multicast list in ipv6_add_dev(). When link down, we call ipv6_mc_down(), store all multicast addresses via mld_add_delrec(). But when link up, we don't call ipv6_mc_up() for non-Ethernet interface to remove the addresses. This makes idev->mc_tomb getting bigger and bigger. The call stack looks like:

addrconf_notify(NETDEV_REGISTER) ipv6_add_dev ipv6_dev_mc_inc(ff01::1) ipv6_dev_mc_inc(ff02::1) ipv6_dev_mc_inc(ff02::2)

addrconf_notify(NETDEV_UP) addrconf_dev_config /* Alas, we support only Ethernet autoconfiguration. */ return;

addrconf_notify(NETDEV_DOWN) addrconf_ifdown ipv6_mc_down igmp6_group_dropped(ff02::2) mld_add_delrec(ff02::2) igmp6_group_dropped(ff02::1) igmp6_group_dropped(ff01::1)

After investigating, I can't found a rule to disable multicast on non-Ethernet interface. In RFC2460, the link could be Ethernet, PPP, ATM, tunnels, etc. In IPv4, it doesn't check the dev type when calls ip_mc_up() in inetdev_event(). Even for IPv6, we don't check the dev type and call ipv6_add_dev(), ipv6_dev_mc_inc() after register device.

So I think it's OK to fix this memory consumer by calling ipv6_mc_up() for non-Ethernet interface.

v2: Also check IFF_MULTICAST flag to make sure the interface supports multicast

Reported-by: Rafał Miłecki zajec5@gmail.com Tested-by: Rafał Miłecki zajec5@gmail.com Fixes: 74235a25c673 ("[IPV6] addrconf: Fix IPv6 on tuntap tunnels") Fixes: 1666d49e1d41 ("mld: do not remove mld souce list info when set link down") Signed-off-by: Hangbin Liu liuhangbin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/addrconf.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3223,6 +3223,10 @@ static void addrconf_dev_config(struct n (dev->type != ARPHRD_TUNNEL) && (dev->type != ARPHRD_NONE)) { /* Alas, we support only Ethernet autoconfiguration. */ + idev = __in6_dev_get(dev); + if (!IS_ERR_OR_NULL(idev) && dev->flags & IFF_UP && + dev->flags & IFF_MULTICAST) + ipv6_mc_up(idev); return; }

From: Eric Dumazet edumazet@google.com

[ Upstream commit afe207d80a61e4d6e7cfa0611a4af46d0ba95628 ]

Commit e18b353f102e ("ipvlan: add cond_resched_rcu() while processing muticast backlog") added a cond_resched_rcu() in a loop using rcu protection to iterate over slaves.

This is breaking rcu rules, so lets instead use cond_resched() at a point we can reschedule

Fixes: e18b353f102e ("ipvlan: add cond_resched_rcu() while processing muticast backlog") Signed-off-by: Eric Dumazet edumazet@google.com Cc: Mahesh Bandewar maheshb@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ipvlan/ipvlan_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -240,7 +240,6 @@ void ipvlan_process_multicast(struct wor } ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true); local_bh_enable(); - cond_resched_rcu(); } rcu_read_unlock();

@@ -257,6 +256,7 @@ void ipvlan_process_multicast(struct wor } if (dev) dev_put(dev); + cond_resched(); } }

From: Dmitry Bogdanov dbogdanov@marvell.com

[ Upstream commit 6fc498bc82929ee23aa2f35a828c6178dfd3f823 ]

SCI should be updated, because it contains MAC in its first 6 octets.

Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Signed-off-by: Dmitry Bogdanov dbogdanov@marvell.com Signed-off-by: Mark Starovoytov mstarovoitov@marvell.com Signed-off-by: Igor Russkikh irusskikh@marvell.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/macsec.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)

--- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2871,6 +2871,11 @@ static void macsec_dev_set_rx_mode(struc dev_uc_sync(real_dev, dev); }

+static sci_t dev_to_sci(struct net_device *dev, __be16 port) +{ + return make_sci(dev->dev_addr, port); +} + static int macsec_set_mac_address(struct net_device *dev, void *p) { struct macsec_dev *macsec = macsec_priv(dev); @@ -2892,6 +2897,7 @@ static int macsec_set_mac_address(struct

out: ether_addr_copy(dev->dev_addr, addr->sa_data); + macsec->secy.sci = dev_to_sci(dev, MACSEC_PORT_ES); return 0; }

@@ -3159,11 +3165,6 @@ static bool sci_exists(struct net_device return false; }

-static sci_t dev_to_sci(struct net_device *dev, __be16 port) -{ - return make_sci(dev->dev_addr, port); -} - static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len) { struct macsec_dev *macsec = macsec_priv(dev);

From: Willem de Bruijn willemb@google.com

[ Upstream commit 46e4c421a053c36bf7a33dda2272481bcaf3eed3 ]

In one error case, tpacket_rcv drops packets after incrementing the ring producer index.

If this happens, it does not update tp_status to TP_STATUS_USER and thus the reader is stalled for an iteration of the ring, causing out of order arrival.

The only such error path is when virtio_net_hdr_from_skb fails due to encountering an unknown GSO type.

Signed-off-by: Willem de Bruijn willemb@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 | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-)

--- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2299,6 +2299,13 @@ static int tpacket_rcv(struct sk_buff *s TP_STATUS_KERNEL, (macoff+snaplen)); if (!h.raw) goto drop_n_account; + + if (do_vnet && + virtio_net_hdr_from_skb(skb, h.raw + macoff - + sizeof(struct virtio_net_hdr), + vio_le(), true, 0)) + goto drop_n_account; + if (po->tp_version <= TPACKET_V2) { packet_increment_rx_head(po, &po->rx_ring); /* @@ -2311,12 +2318,6 @@ static int tpacket_rcv(struct sk_buff *s status |= TP_STATUS_LOSING; }

- if (do_vnet && - virtio_net_hdr_from_skb(skb, h.raw + macoff - - sizeof(struct virtio_net_hdr), - vio_le(), true, 0)) - goto drop_n_account; - po->stats.stats1.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY;

From: Edward Cree ecree@solarflare.com

[ Upstream commit 4b1bd9db078f7d5332c8601a2f5bd43cf0458fd4 ]

It's a resource, not a parameter, so we can't copy it into the new channel's TX queues, otherwise aliasing will lead to resource- management bugs if the channel is subsequently torn down without being initialised.

Before the Fixes:-tagged commit there was a similar bug with tsoh_page, but I'm not sure it's worth doing another fix for such old kernels.

Fixes: e9117e5099ea ("sfc: Firmware-Assisted TSO version 2") Suggested-by: Derek Shute Derek.Shute@stratus.com Signed-off-by: Edward Cree ecree@solarflare.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/sfc/efx.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -505,6 +505,7 @@ efx_copy_channel(const struct efx_channe if (tx_queue->channel) tx_queue->channel = channel; tx_queue->buffer = NULL; + tx_queue->cb_page = NULL; memset(&tx_queue->txd, 0, sizeof(tx_queue->txd)); }

From: Shakeel Butt shakeelb@google.com

[ Upstream commit e876ecc67db80dfdb8e237f71e5b43bb88ae549c ]

We are testing network memory accounting in our setup and noticed inconsistent network memory usage and often unrelated cgroups network usage correlates with testing workload. On further inspection, it seems like mem_cgroup_sk_alloc() and cgroup_sk_alloc() are broken in irq context specially for cgroup v1.

mem_cgroup_sk_alloc() and cgroup_sk_alloc() can be called in irq context and kind of assumes that this can only happen from sk_clone_lock() and the source sock object has already associated cgroup. However in cgroup v1, where network memory accounting is opt-in, the source sock can be unassociated with any cgroup and the new cloned sock can get associated with unrelated interrupted cgroup.

Cgroup v2 can also suffer if the source sock object was created by process in the root cgroup or if sk_alloc() is called in irq context. The fix is to just do nothing in interrupt.

WARNING: Please note that about half of the TCP sockets are allocated from the IRQ context, so, memory used by such sockets will not be accouted by the memcg.

The stack trace of mem_cgroup_sk_alloc() from IRQ-context:

CPU: 70 PID: 12720 Comm: ssh Tainted: 5.6.0-smp-DEV #1 Hardware name: ... Call Trace: <IRQ> dump_stack+0x57/0x75 mem_cgroup_sk_alloc+0xe9/0xf0 sk_clone_lock+0x2a7/0x420 inet_csk_clone_lock+0x1b/0x110 tcp_create_openreq_child+0x23/0x3b0 tcp_v6_syn_recv_sock+0x88/0x730 tcp_check_req+0x429/0x560 tcp_v6_rcv+0x72d/0xa40 ip6_protocol_deliver_rcu+0xc9/0x400 ip6_input+0x44/0xd0 ? ip6_protocol_deliver_rcu+0x400/0x400 ip6_rcv_finish+0x71/0x80 ipv6_rcv+0x5b/0xe0 ? ip6_sublist_rcv+0x2e0/0x2e0 process_backlog+0x108/0x1e0 net_rx_action+0x26b/0x460 __do_softirq+0x104/0x2a6 do_softirq_own_stack+0x2a/0x40 </IRQ> do_softirq.part.19+0x40/0x50 __local_bh_enable_ip+0x51/0x60 ip6_finish_output2+0x23d/0x520 ? ip6table_mangle_hook+0x55/0x160 __ip6_finish_output+0xa1/0x100 ip6_finish_output+0x30/0xd0 ip6_output+0x73/0x120 ? __ip6_finish_output+0x100/0x100 ip6_xmit+0x2e3/0x600 ? ipv6_anycast_cleanup+0x50/0x50 ? inet6_csk_route_socket+0x136/0x1e0 ? skb_free_head+0x1e/0x30 inet6_csk_xmit+0x95/0xf0 __tcp_transmit_skb+0x5b4/0xb20 __tcp_send_ack.part.60+0xa3/0x110 tcp_send_ack+0x1d/0x20 tcp_rcv_state_process+0xe64/0xe80 ? tcp_v6_connect+0x5d1/0x5f0 tcp_v6_do_rcv+0x1b1/0x3f0 ? tcp_v6_do_rcv+0x1b1/0x3f0 __release_sock+0x7f/0xd0 release_sock+0x30/0xa0 __inet_stream_connect+0x1c3/0x3b0 ? prepare_to_wait+0xb0/0xb0 inet_stream_connect+0x3b/0x60 __sys_connect+0x101/0x120 ? __sys_getsockopt+0x11b/0x140 __x64_sys_connect+0x1a/0x20 do_syscall_64+0x51/0x200 entry_SYSCALL_64_after_hwframe+0x44/0xa9

The stack trace of mem_cgroup_sk_alloc() from IRQ-context: Fixes: 2d7580738345 ("mm: memcontrol: consolidate cgroup socket tracking") Fixes: d979a39d7242 ("cgroup: duplicate cgroup reference when cloning sockets") Signed-off-by: Shakeel Butt shakeelb@google.com Reviewed-by: Roman Gushchin guro@fb.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/cgroup/cgroup.c | 4 ++++ mm/memcontrol.c | 4 ++++ 2 files changed, 8 insertions(+)

--- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5799,6 +5799,10 @@ void cgroup_sk_alloc(struct sock_cgroup_ return; }

+ /* Don't associate the sock with unrelated interrupted task's cgroup. */ + if (in_interrupt()) + return; + rcu_read_lock();

while (true) { --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5881,6 +5881,10 @@ void mem_cgroup_sk_alloc(struct sock *sk return; }

+ /* Do not associate the sock with unrelated interrupted task's memcg. */ + if (in_interrupt()) + return; + rcu_read_lock(); memcg = mem_cgroup_from_task(current); if (memcg == root_mem_cgroup)

From: Eric Dumazet edumazet@google.com

commit 06669ea346e476a5339033d77ef175566a40efbb upstream.

Locking newsk while still holding the listener lock triggered a lockdep splat [1]

We can simply move the memcg code after we release the listener lock, as this can also help if multiple threads are sharing a common listener.

Also fix a typo while reading socket sk_rmem_alloc.

[1] WARNING: possible recursive locking detected 5.6.0-rc3-syzkaller #0 Not tainted -------------------------------------------- syz-executor598/9524 is trying to acquire lock: ffff88808b5b8b90 (sk_lock-AF_INET6){+.+.}, at: lock_sock include/net/sock.h:1541 [inline] ffff88808b5b8b90 (sk_lock-AF_INET6){+.+.}, at: inet_csk_accept+0x69f/0xd30 net/ipv4/inet_connection_sock.c:492

but task is already holding lock: ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: lock_sock include/net/sock.h:1541 [inline] ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: inet_csk_accept+0x8d/0xd30 net/ipv4/inet_connection_sock.c:445

other info that might help us debug this: Possible unsafe locking scenario:

CPU0 ---- lock(sk_lock-AF_INET6); lock(sk_lock-AF_INET6);

*** DEADLOCK ***

May be due to missing lock nesting notation

1 lock held by syz-executor598/9524: #0: ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: lock_sock include/net/sock.h:1541 [inline] #0: ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: inet_csk_accept+0x8d/0xd30 net/ipv4/inet_connection_sock.c:445

stack backtrace: CPU: 0 PID: 9524 Comm: syz-executor598 Not tainted 5.6.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x188/0x20d lib/dump_stack.c:118 print_deadlock_bug kernel/locking/lockdep.c:2370 [inline] check_deadlock kernel/locking/lockdep.c:2411 [inline] validate_chain kernel/locking/lockdep.c:2954 [inline] __lock_acquire.cold+0x114/0x288 kernel/locking/lockdep.c:3954 lock_acquire+0x197/0x420 kernel/locking/lockdep.c:4484 lock_sock_nested+0xc5/0x110 net/core/sock.c:2947 lock_sock include/net/sock.h:1541 [inline] inet_csk_accept+0x69f/0xd30 net/ipv4/inet_connection_sock.c:492 inet_accept+0xe9/0x7c0 net/ipv4/af_inet.c:734 __sys_accept4_file+0x3ac/0x5b0 net/socket.c:1758 __sys_accept4+0x53/0x90 net/socket.c:1809 __do_sys_accept4 net/socket.c:1821 [inline] __se_sys_accept4 net/socket.c:1818 [inline] __x64_sys_accept4+0x93/0xf0 net/socket.c:1818 do_syscall_64+0xf6/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4445c9 Code: e8 0c 0d 03 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffc35b37608 EFLAGS: 00000246 ORIG_RAX: 0000000000000120 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00000000004445c9 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003 RBP: 0000000000000000 R08: 0000000000306777 R09: 0000000000306777 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00000000004053d0 R14: 0000000000000000 R15: 0000000000000000

Fixes: d752a4986532 ("net: memcg: late association of sock to memcg") Signed-off-by: Eric Dumazet edumazet@google.com Cc: Shakeel Butt shakeelb@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/inet_connection_sock.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)

--- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -476,27 +476,27 @@ struct sock *inet_csk_accept(struct sock spin_unlock_bh(&queue->fastopenq.lock); }

- if (mem_cgroup_sockets_enabled) { +out: + release_sock(sk); + if (newsk && mem_cgroup_sockets_enabled) { int amt;

/* atomically get the memory usage, set and charge the - * sk->sk_memcg. + * newsk->sk_memcg. */ lock_sock(newsk);

- /* The sk has not been accepted yet, no need to look at - * sk->sk_wmem_queued. + /* The socket has not been accepted yet, no need to look at + * newsk->sk_wmem_queued. */ amt = sk_mem_pages(newsk->sk_forward_alloc + - atomic_read(&sk->sk_rmem_alloc)); + atomic_read(&newsk->sk_rmem_alloc)); mem_cgroup_sk_alloc(newsk); if (newsk->sk_memcg && amt) mem_cgroup_charge_skmem(newsk->sk_memcg, amt);

release_sock(newsk); } -out: - release_sock(sk); if (req) reqsk_put(req); return newsk;

From: Jakub Kicinski kuba@kernel.org

[ Upstream commit 9322cd7c4af2ccc7fe7c5f01adb53f4f77949e92 ]

Add missing attribute validation for several u8 types.

Fixes: 2c21d11518b6 ("net: add NL802154 interface for configuration of 802.15.4 devices") Signed-off-by: Jakub Kicinski kuba@kernel.org Acked-by: Stefan Schmidt stefan@datenfreihafen.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ieee802154/nl_policy.c | 5 +++++ 1 file changed, 5 insertions(+)

--- a/net/ieee802154/nl_policy.c +++ b/net/ieee802154/nl_policy.c @@ -30,6 +30,11 @@ const struct nla_policy ieee802154_polic [IEEE802154_ATTR_HW_ADDR] = { .type = NLA_HW_ADDR, }, [IEEE802154_ATTR_PAN_ID] = { .type = NLA_U16, }, [IEEE802154_ATTR_CHANNEL] = { .type = NLA_U8, }, + [IEEE802154_ATTR_BCN_ORD] = { .type = NLA_U8, }, + [IEEE802154_ATTR_SF_ORD] = { .type = NLA_U8, }, + [IEEE802154_ATTR_PAN_COORD] = { .type = NLA_U8, }, + [IEEE802154_ATTR_BAT_EXT] = { .type = NLA_U8, }, + [IEEE802154_ATTR_COORD_REALIGN] = { .type = NLA_U8, }, [IEEE802154_ATTR_PAGE] = { .type = NLA_U8, }, [IEEE802154_ATTR_COORD_SHORT_ADDR] = { .type = NLA_U16, }, [IEEE802154_ATTR_COORD_HW_ADDR] = { .type = NLA_HW_ADDR, },

From: Jakub Kicinski kuba@kernel.org

[ Upstream commit ab02ad660586b94f5d08912a3952b939cf4c4430 ]

Add missing attribute validation for IFLA_CAN_TERMINATION to the netlink policy.

Fixes: 12a6075cabc0 ("can: dev: add CAN interface termination API") Signed-off-by: Jakub Kicinski kuba@kernel.org Acked-by: Oliver Hartkopp socketcan@hartkopp.net Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/can/dev.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -867,6 +867,7 @@ static const struct nla_policy can_polic = { .len = sizeof(struct can_bittiming) }, [IFLA_CAN_DATA_BITTIMING_CONST] = { .len = sizeof(struct can_bittiming_const) }, + [IFLA_CAN_TERMINATION] = { .type = NLA_U16 }, };

static int can_validate(struct nlattr *tb[], struct nlattr *data[],

From: Jakub Kicinski kuba@kernel.org

[ Upstream commit 7e6dc03eeb023e18427a373522f1d247b916a641 ]

Add missing attribute validation for TCA_FQ_ORPHAN_MASK to the netlink policy.

Fixes: 06eb395fa985 ("pkt_sched: fq: better control of DDOS traffic") Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/sch_fq.c | 1 + 1 file changed, 1 insertion(+)

--- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -695,6 +695,7 @@ static const struct nla_policy fq_policy [TCA_FQ_FLOW_MAX_RATE] = { .type = NLA_U32 }, [TCA_FQ_BUCKETS_LOG] = { .type = NLA_U32 }, [TCA_FQ_FLOW_REFILL_DELAY] = { .type = NLA_U32 }, + [TCA_FQ_ORPHAN_MASK] = { .type = NLA_U32 }, [TCA_FQ_LOW_RATE_THRESHOLD] = { .type = NLA_U32 }, };

From: Jakub Kicinski kuba@kernel.org

[ Upstream commit 669fcd7795900cd1880237cbbb57a7db66cb9ac8 ]

Add missing attribute validation for TEAM_ATTR_OPTION_ARRAY_INDEX to the netlink policy.

Fixes: b13033262d24 ("team: introduce array options") Signed-off-by: Jakub Kicinski kuba@kernel.org Reviewed-by: Jiri Pirko jiri@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/team/team.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2208,6 +2208,7 @@ team_nl_option_policy[TEAM_ATTR_OPTION_M [TEAM_ATTR_OPTION_TYPE] = { .type = NLA_U8 }, [TEAM_ATTR_OPTION_DATA] = { .type = NLA_BINARY }, [TEAM_ATTR_OPTION_PORT_IFINDEX] = { .type = NLA_U32 }, + [TEAM_ATTR_OPTION_ARRAY_INDEX] = { .type = NLA_U32 }, };

static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info)

From: Jakub Kicinski kuba@kernel.org

[ Upstream commit 6ba3da446551f2150fadbf8c7788edcb977683d3 ]

Add missing attribute validation for vendor subcommand attributes to the netlink policy.

Fixes: 9e58095f9660 ("NFC: netlink: Implement vendor command support") Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/nfc/netlink.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -57,6 +57,8 @@ static const struct nla_policy nfc_genl_ .len = NFC_FIRMWARE_NAME_MAXSIZE }, [NFC_ATTR_SE_INDEX] = { .type = NLA_U32 }, [NFC_ATTR_SE_APDU] = { .type = NLA_BINARY }, + [NFC_ATTR_VENDOR_ID] = { .type = NLA_U32 }, + [NFC_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 }, [NFC_ATTR_VENDOR_DATA] = { .type = NLA_BINARY },

};

From: Eric Dumazet edumazet@google.com

commit b7469e83d2add567e4e0b063963db185f3167cea upstream.

Similar to commit 38f88c454042 ("bonding/alb: properly access headers in bond_alb_xmit()"), we need to make sure arp header was pulled in skb->head before blindly accessing it in rlb_arp_xmit().

Remove arp_pkt() private helper, since it is more readable/obvious to have the following construct back to back :

if (!pskb_network_may_pull(skb, sizeof(*arp))) return NULL; arp = (struct arp_pkt *)skb_network_header(skb);

syzbot reported :

BUG: KMSAN: uninit-value in bond_slave_has_mac_rx include/net/bonding.h:704 [inline] BUG: KMSAN: uninit-value in rlb_arp_xmit drivers/net/bonding/bond_alb.c:662 [inline] BUG: KMSAN: uninit-value in bond_alb_xmit+0x575/0x25e0 drivers/net/bonding/bond_alb.c:1477 CPU: 0 PID: 12743 Comm: syz-executor.4 Not tainted 5.6.0-rc2-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1c9/0x220 lib/dump_stack.c:118 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215 bond_slave_has_mac_rx include/net/bonding.h:704 [inline] rlb_arp_xmit drivers/net/bonding/bond_alb.c:662 [inline] bond_alb_xmit+0x575/0x25e0 drivers/net/bonding/bond_alb.c:1477 __bond_start_xmit drivers/net/bonding/bond_main.c:4257 [inline] bond_start_xmit+0x85d/0x2f70 drivers/net/bonding/bond_main.c:4282 __netdev_start_xmit include/linux/netdevice.h:4524 [inline] netdev_start_xmit include/linux/netdevice.h:4538 [inline] xmit_one net/core/dev.c:3470 [inline] dev_hard_start_xmit+0x531/0xab0 net/core/dev.c:3486 __dev_queue_xmit+0x37de/0x4220 net/core/dev.c:4063 dev_queue_xmit+0x4b/0x60 net/core/dev.c:4096 packet_snd net/packet/af_packet.c:2967 [inline] packet_sendmsg+0x8347/0x93b0 net/packet/af_packet.c:2992 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg net/socket.c:672 [inline] __sys_sendto+0xc1b/0xc50 net/socket.c:1998 __do_sys_sendto net/socket.c:2010 [inline] __se_sys_sendto+0x107/0x130 net/socket.c:2006 __x64_sys_sendto+0x6e/0x90 net/socket.c:2006 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x45c479 Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fc77ffbbc78 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00007fc77ffbc6d4 RCX: 000000000045c479 RDX: 000000000000000e RSI: 00000000200004c0 RDI: 0000000000000003 RBP: 000000000076bf20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff R13: 0000000000000a04 R14: 00000000004cc7b0 R15: 000000000076bf2c

Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline] kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82 slab_alloc_node mm/slub.c:2793 [inline] __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4401 __kmalloc_reserve net/core/skbuff.c:142 [inline] __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:210 alloc_skb include/linux/skbuff.h:1051 [inline] alloc_skb_with_frags+0x18c/0xa70 net/core/skbuff.c:5766 sock_alloc_send_pskb+0xada/0xc60 net/core/sock.c:2242 packet_alloc_skb net/packet/af_packet.c:2815 [inline] packet_snd net/packet/af_packet.c:2910 [inline] packet_sendmsg+0x66a0/0x93b0 net/packet/af_packet.c:2992 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg net/socket.c:672 [inline] __sys_sendto+0xc1b/0xc50 net/socket.c:1998 __do_sys_sendto net/socket.c:2010 [inline] __se_sys_sendto+0x107/0x130 net/socket.c:2006 __x64_sys_sendto+0x6e/0x90 net/socket.c:2006 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Cc: Jay Vosburgh j.vosburgh@gmail.com Cc: Veaceslav Falico vfalico@gmail.com Cc: Andy Gospodarek andy@greyhouse.net Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/bonding/bond_alb.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-)

--- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -71,11 +71,6 @@ struct arp_pkt { }; #pragma pack()

-static inline struct arp_pkt *arp_pkt(const struct sk_buff *skb) -{ - return (struct arp_pkt *)skb_network_header(skb); -} - /* Forward declaration */ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[], bool strict_match); @@ -574,10 +569,11 @@ static void rlb_req_update_subnet_client spin_unlock(&bond->mode_lock); }

-static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bond) +static struct slave *rlb_choose_channel(struct sk_buff *skb, + struct bonding *bond, + const struct arp_pkt *arp) { struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); - struct arp_pkt *arp = arp_pkt(skb); struct slave *assigned_slave, *curr_active_slave; struct rlb_client_info *client_info; u32 hash_index = 0; @@ -674,8 +670,12 @@ static struct slave *rlb_choose_channel( */ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) { - struct arp_pkt *arp = arp_pkt(skb); struct slave *tx_slave = NULL; + struct arp_pkt *arp; + + if (!pskb_network_may_pull(skb, sizeof(*arp))) + return NULL; + arp = (struct arp_pkt *)skb_network_header(skb);

/* Don't modify or load balance ARPs that do not originate locally * (e.g.,arrive via a bridge). @@ -685,7 +685,7 @@ static struct slave *rlb_arp_xmit(struct

if (arp->op_code == htons(ARPOP_REPLY)) { /* the arp must be sent on the selected rx channel */ - tx_slave = rlb_choose_channel(skb, bond); + tx_slave = rlb_choose_channel(skb, bond, arp); if (tx_slave) bond_hw_addr_copy(arp->mac_src, tx_slave->dev->dev_addr, tx_slave->dev->addr_len); @@ -696,7 +696,7 @@ static struct slave *rlb_arp_xmit(struct * When the arp reply is received the entry will be updated * with the correct unicast address of the client. */ - rlb_choose_channel(skb, bond); + rlb_choose_channel(skb, bond, arp);

/* The ARP reply packets must be delayed so that * they can cancel out the influence of the ARP request.

From: Jakub Kicinski kuba@kernel.org

[ Upstream commit ab14961d10d02d20767612c78ce148f6eb85bd58 ]

fec_enet_set_coalesce() validates the previously set params and if they are within range proceeds to apply the new ones. The new ones, however, are not validated. This seems backwards, probably a copy-paste error?

Compile tested only.

Fixes: d851b47b22fc ("net: fec: add interrupt coalescence feature support") Signed-off-by: Jakub Kicinski kuba@kernel.org Acked-by: Fugang Duan fugang.duan@nxp.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/freescale/fec_main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2478,15 +2478,15 @@ fec_enet_set_coalesce(struct net_device return -EINVAL; }

- cycle = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr); + cycle = fec_enet_us_to_itr_clock(ndev, ec->rx_coalesce_usecs); if (cycle > 0xFFFF) { pr_err("Rx coalesced usec exceed hardware limitation\n"); return -EINVAL; }

- cycle = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr); + cycle = fec_enet_us_to_itr_clock(ndev, ec->tx_coalesce_usecs); if (cycle > 0xFFFF) { - pr_err("Rx coalesced usec exceed hardware limitation\n"); + pr_err("Tx coalesced usec exceed hardware limitation\n"); return -EINVAL; }

From: Dmitry Yakunin zeil@yandex-team.ru

[ Upstream commit 83f73c5bb7b9a9135173f0ba2b1aa00c06664ff9 ]

In commit 1ec17dbd90f8 ("inet_diag: fix reporting cgroup classid and fallback to priority") croup classid reporting was fixed. But this works only for TCP sockets because for other socket types icsk parameter can be NULL and classid code path is skipped. This change moves classid handling to inet_diag_msg_attrs_fill() function.

Also inet_diag_msg_attrs_size() helper was added and addends in nlmsg_new() were reordered to save order from inet_sk_diag_fill().

Fixes: 1ec17dbd90f8 ("inet_diag: fix reporting cgroup classid and fallback to priority") Signed-off-by: Dmitry Yakunin zeil@yandex-team.ru Reviewed-by: Konstantin Khlebnikov khlebnikov@yandex-team.ru Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/inet_diag.h | 18 ++++++++++++------ net/ipv4/inet_diag.c | 44 ++++++++++++++++++++------------------------ net/ipv4/raw_diag.c | 5 +++-- net/ipv4/udp_diag.c | 5 +++-- net/sctp/sctp_diag.c | 8 ++------ 5 files changed, 40 insertions(+), 40 deletions(-)

--- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -2,15 +2,10 @@ #ifndef _INET_DIAG_H_ #define _INET_DIAG_H_ 1

+#include <net/netlink.h> #include <uapi/linux/inet_diag.h>

-struct net; -struct sock; struct inet_hashinfo; -struct nlattr; -struct nlmsghdr; -struct sk_buff; -struct netlink_callback;

struct inet_diag_handler { void (*dump)(struct sk_buff *skb, @@ -62,6 +57,17 @@ int inet_diag_bc_sk(const struct nlattr

void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk);

+static inline size_t inet_diag_msg_attrs_size(void) +{ + return nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + + nla_total_size(1) /* INET_DIAG_TOS */ +#if IS_ENABLED(CONFIG_IPV6) + + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(1) /* INET_DIAG_SKV6ONLY */ +#endif + + nla_total_size(4) /* INET_DIAG_MARK */ + + nla_total_size(4); /* INET_DIAG_CLASS_ID */ +} int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_msg *r, int ext, struct user_namespace *user_ns, bool net_admin); --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -105,13 +105,9 @@ static size_t inet_sk_attr_size(struct s aux = handler->idiag_get_aux_size(sk, net_admin);

return nla_total_size(sizeof(struct tcp_info)) - + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ - + nla_total_size(1) /* INET_DIAG_TOS */ - + nla_total_size(1) /* INET_DIAG_TCLASS */ - + nla_total_size(4) /* INET_DIAG_MARK */ - + nla_total_size(4) /* INET_DIAG_CLASS_ID */ - + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) + nla_total_size(TCP_CA_NAME_MAX) + nla_total_size(sizeof(struct tcpvegas_info)) @@ -152,6 +148,24 @@ int inet_diag_msg_attrs_fill(struct sock if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark)) goto errout;

+ if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || + ext & (1 << (INET_DIAG_TCLASS - 1))) { + u32 classid = 0; + +#ifdef CONFIG_SOCK_CGROUP_DATA + classid = sock_cgroup_classid(&sk->sk_cgrp_data); +#endif + /* Fallback to socket priority if class id isn't set. + * Classful qdiscs use it as direct reference to class. + * For cgroup2 classid is always zero. + */ + if (!classid) + classid = sk->sk_priority; + + if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) + goto errout; + } + r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = sock_i_ino(sk);

@@ -289,24 +303,6 @@ int inet_sk_diag_fill(struct sock *sk, s goto errout; }

- if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || - ext & (1 << (INET_DIAG_TCLASS - 1))) { - u32 classid = 0; - -#ifdef CONFIG_SOCK_CGROUP_DATA - classid = sock_cgroup_classid(&sk->sk_cgrp_data); -#endif - /* Fallback to socket priority if class id isn't set. - * Classful qdiscs use it as direct reference to class. - * For cgroup2 classid is always zero. - */ - if (!classid) - classid = sk->sk_priority; - - if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) - goto errout; - } - out: nlmsg_end(skb, nlh); return 0; --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -99,8 +99,9 @@ static int raw_diag_dump_one(struct sk_b if (IS_ERR(sk)) return PTR_ERR(sk);

- rep = nlmsg_new(sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + 64, + rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64, GFP_KERNEL); if (!rep) { sock_put(sk); --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -67,8 +67,9 @@ static int udp_dump_one(struct udp_table goto out;

err = -ENOMEM; - rep = nlmsg_new(sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + 64, + rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64, GFP_KERNEL); if (!rep) goto out; --- a/net/sctp/sctp_diag.c +++ b/net/sctp/sctp_diag.c @@ -221,15 +221,11 @@ static size_t inet_assoc_attr_size(struc addrcnt++;

return nla_total_size(sizeof(struct sctp_info)) - + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ - + nla_total_size(1) /* INET_DIAG_TOS */ - + nla_total_size(1) /* INET_DIAG_TCLASS */ - + nla_total_size(4) /* INET_DIAG_MARK */ - + nla_total_size(4) /* INET_DIAG_CLASS_ID */ + nla_total_size(addrlen * asoc->peer.transport_count) + nla_total_size(addrlen * addrcnt) - + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64; }

From: Paolo Abeni pabeni@redhat.com

commit cccc200fcaf04cff4342036a72e51d6adf6c98c1 upstream.

Currently, if IPv6 is enabled on top of an ipvlan device in l3 mode, the following warning message:

Dropped {multi|broad}cast of type= [86dd]

is emitted every time that a RS is generated and dmseg is soon filled with irrelevant messages. Replace pr_warn with pr_debug, to preserve debuggability, without scaring the sysadmin.

Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/net/ipvlan/ipvlan_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -451,8 +451,8 @@ static int ipvlan_process_outbound(struc

/* In this mode we dont care about multicast and broadcast traffic */ if (is_multicast_ether_addr(ethh->h_dest)) { - pr_warn_ratelimited("Dropped {multi|broad}cast of type= [%x]\n", - ntohs(skb->protocol)); + pr_debug_ratelimited("Dropped {multi|broad}cast of type=[%x]\n", + ntohs(skb->protocol)); kfree_skb(skb); goto out; }

From: Vasily Averin vvs@virtuozzo.com

commit 2d4ecb030dcc90fb725ecbfc82ce5d6c37906e0e upstream.

If seq_file .next fuction does not change position index, read after some lseek can generate unexpected output:

1) dd bs=1 skip output of each 2nd elements $ dd if=/sys/fs/cgroup/cgroup.procs bs=8 count=1 2 3 4 5 1+0 records in 1+0 records out 8 bytes copied, 0,000267297 s, 29,9 kB/s [test@localhost ~]$ dd if=/sys/fs/cgroup/cgroup.procs bs=1 count=8 2 4 <<< NB! 3 was skipped 6 <<< ... and 5 too 8 <<< ... and 7 8+0 records in 8+0 records out 8 bytes copied, 5,2123e-05 s, 153 kB/s

This happen because __cgroup_procs_start() makes an extra extra cgroup_procs_next() call

2) read after lseek beyond end of file generates whole last line. 3) read after lseek into middle of last line generates expected rest of last line and unexpected whole line once again.

Additionally patch removes an extra position index changes in __cgroup_procs_start()

Cc: stable@vger.kernel.org https://bugzilla.kernel.org/show_bug.cgi?id=206283 Signed-off-by: Vasily Averin vvs@virtuozzo.com Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/cgroup/cgroup.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

--- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4249,6 +4249,9 @@ static void *cgroup_procs_next(struct se struct kernfs_open_file *of = s->private; struct css_task_iter *it = of->priv;

+ if (pos) + (*pos)++; + return css_task_iter_next(it); }

@@ -4264,7 +4267,7 @@ static void *__cgroup_procs_start(struct * from position 0, so we can simply keep iterating on !0 *pos. */ if (!it) { - if (WARN_ON_ONCE((*pos)++)) + if (WARN_ON_ONCE((*pos))) return ERR_PTR(-EINVAL);

it = kzalloc(sizeof(*it), GFP_KERNEL); @@ -4272,10 +4275,11 @@ static void *__cgroup_procs_start(struct return ERR_PTR(-ENOMEM); of->priv = it; css_task_iter_start(&cgrp->self, iter_flags, it); - } else if (!(*pos)++) { + } else if (!(*pos)) { css_task_iter_end(it); css_task_iter_start(&cgrp->self, iter_flags, it); - } + } else + return it->cur_task;

return cgroup_procs_next(s, NULL, NULL); }

From: Dan Moulding dmoulding@me.com

commit a9149d243f259ad8f02b1e23dfe8ba06128f15e1 upstream.

The logic for checking required NVM sections was recently fixed in commit b3f20e098293 ("iwlwifi: mvm: fix NVM check for 3168 devices"). However, with that fixed the else is now taken for 3168 devices and within the else clause there is a mandatory check for the PHY_SKU section. This causes the parsing to fail for 3168 devices.

The PHY_SKU section is really only mandatory for the IWL_NVM_EXT layout (the phy_sku parameter of iwl_parse_nvm_data is only used when the NVM type is IWL_NVM_EXT). So this changes the PHY_SKU section check so that it's only mandatory for IWL_NVM_EXT.

Fixes: b3f20e098293 ("iwlwifi: mvm: fix NVM check for 3168 devices") Signed-off-by: Dan Moulding dmoulding@me.com Signed-off-by: Kalle Valo kvalo@codeaurora.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/net/wireless/intel/iwlwifi/mvm/nvm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c @@ -326,7 +326,8 @@ iwl_parse_nvm_sections(struct iwl_mvm *m }

/* PHY_SKU section is mandatory in B0 */ - if (!mvm->nvm_sections[NVM_SECTION_TYPE_PHY_SKU].data) { + if (mvm->trans->cfg->nvm_type == IWL_NVM_EXT && + !mvm->nvm_sections[NVM_SECTION_TYPE_PHY_SKU].data) { IWL_ERR(mvm, "Can't parse phy_sku in B0, empty sections\n"); return NULL;

From: Hans de Goede hdegoede@redhat.com

commit 81ee85d0462410de8eeeec1b9761941fd6ed8c7b upstream.

Quoting from the comment describing the WARN functions in include/asm-generic/bug.h:

* WARN(), WARN_ON(), WARN_ON_ONCE, and so on can be used to report * significant kernel issues that need prompt attention if they should ever * appear at runtime. * * Do not use these macros when checking for invalid external inputs

The (buggy) firmware tables which the dmar code was calling WARN_TAINT for really are invalid external inputs. They are not under the kernel's control and the issues in them cannot be fixed by a kernel update. So logging a backtrace, which invites bug reports to be filed about this, is not helpful.

Fixes: 556ab45f9a77 ("ioat2: catch and recover from broken vtd configurations v6") Signed-off-by: Hans de Goede hdegoede@redhat.com Acked-by: Lu Baolu baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20200309182510.373875-1-hdegoede@redhat.com BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=701847 Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/iommu/intel-iommu.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

--- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -3984,10 +3984,11 @@ static void quirk_ioat_snb_local_iommu(s

/* we know that the this iommu should be at offset 0xa000 from vtbar */ drhd = dmar_find_matched_drhd_unit(pdev); - if (WARN_TAINT_ONCE(!drhd || drhd->reg_base_addr - vtbar != 0xa000, - TAINT_FIRMWARE_WORKAROUND, - "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n")) + if (!drhd || drhd->reg_base_addr - vtbar != 0xa000) { + pr_warn_once(FW_BUG "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n"); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); pdev->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO; + } } DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB, quirk_ioat_snb_local_iommu);

From: Colin Ian King colin.king@canonical.com

commit d785476c608c621b345dd9396e8b21e90375cb0e upstream.

Variable grph_obj_type is being assigned twice, one of these is redundant so remove it.

Addresses-Coverity: ("Evaluation order violation") Signed-off-by: Colin Ian King colin.king@canonical.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: nobuhiro1.iwamatsu@toshiba.co.jp Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -363,8 +363,7 @@ bool amdgpu_atombios_get_connector_info_ router.ddc_valid = false; router.cd_valid = false; for (j = 0; j < ((le16_to_cpu(path->usSize) - 8) / 2); j++) { - uint8_t grph_obj_type= - grph_obj_type = + uint8_t grph_obj_type = (le16_to_cpu(path->usGraphicObjIds[j]) & OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;

From: Al Viro viro@zeniv.linux.org.uk

commit d9a9f4849fe0c9d560851ab22a85a666cddfdd24 upstream.

several iterations of ->atomic_open() calling conventions ago, we used to need fput() if ->atomic_open() failed at some point after successful finish_open(). Now (since 2016) it's not needed - struct file carries enough state to make fput() work regardless of the point in struct file lifecycle and discarding it on failure exits in open() got unified. Unfortunately, I'd missed the fact that we had an instance of ->atomic_open() (cifs one) that used to need that fput(), as well as the stale comment in finish_open() demanding such late failure handling. Trivially fixed...

Fixes: fe9ec8291fca "do_last(): take fput() on error after opening to out:" Cc: stable@kernel.org # v4.7+ Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- Documentation/filesystems/porting | 7 +++++++ fs/cifs/dir.c | 1 - fs/open.c | 3 --- 3 files changed, 7 insertions(+), 4 deletions(-)

--- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -606,3 +606,10 @@ in your dentry operations instead. dentry separately, and it now has request_mask and query_flags arguments to specify the fields and sync type requested by statx. Filesystems not supporting any statx-specific features may ignore the new arguments. +-- +[mandatory] + + [should've been added in 2016] stale comment in finish_open() + nonwithstanding, failure exits in ->atomic_open() instances should + *NOT* fput() the file, no matter what. Everything is handled by the + caller. --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -562,7 +562,6 @@ cifs_atomic_open(struct inode *inode, st if (server->ops->close) server->ops->close(xid, tcon, &fid); cifs_del_pending_open(&open); - fput(file); rc = -ENOMEM; }

--- a/fs/open.c +++ b/fs/open.c @@ -824,9 +824,6 @@ cleanup_file: * the return value of d_splice_alias(), then the caller needs to perform dput() * on it after finish_open(). * - * On successful return @file is a fully instantiated open file. After this, if - * an error occurs in ->atomic_open(), it needs to clean up with fput(). - * * Returns zero on success or -errno if the open failed. */ int finish_open(struct file *file, struct dentry *dentry,

From: Vitaly Kuznetsov vkuznets@redhat.com

commit 342993f96ab24d5864ab1216f46c0b199c2baf8e upstream.

After commit 07721feee46b ("KVM: nVMX: Don't emulate instructions in guest mode") Hyper-V guests on KVM stopped booting with:

kvm_nested_vmexit: rip fffff802987d6169 reason EPT_VIOLATION info1 181 info2 0 int_info 0 int_info_err 0 kvm_page_fault: address febd0000 error_code 181 kvm_emulate_insn: 0:fffff802987d6169: f3 a5 kvm_emulate_insn: 0:fffff802987d6169: f3 a5 FAIL kvm_inj_exception: #UD (0x0)

"f3 a5" is a "rep movsw" instruction, which should not be intercepted at all. Commit c44b4c6ab80e ("KVM: emulate: clean up initializations in init_decode_cache") reduced the number of fields cleared by init_decode_cache() claiming that they are being cleared elsewhere, 'intercept', however, is left uncleared if the instruction does not have any of the "slow path" flags (NotImpl, Stack, Op3264, Sse, Mmx, CheckPerm, NearBranch, No16 and of course Intercept itself).

Fixes: c44b4c6ab80e ("KVM: emulate: clean up initializations in init_decode_cache") Fixes: 07721feee46b ("KVM: nVMX: Don't emulate instructions in guest mode") Cc: stable@vger.kernel.org Suggested-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Vitaly Kuznetsov vkuznets@redhat.com Reviewed-by: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kvm/emulate.c | 1 + 1 file changed, 1 insertion(+)

--- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -5062,6 +5062,7 @@ int x86_decode_insn(struct x86_emulate_c ctxt->fetch.ptr = ctxt->fetch.data; ctxt->fetch.end = ctxt->fetch.data + insn_len; ctxt->opcode_len = 1; + ctxt->intercept = x86_intercept_none; if (insn_len > 0) memcpy(ctxt->fetch.data, insn, insn_len); else {

From: Vladis Dronov vdronov@redhat.com

commit 286d3250c9d6437340203fb64938bea344729a0e upstream.

There is a race and a buffer overflow corrupting a kernel memory while reading an EFI variable with a size more than 1024 bytes via the older sysfs method. This happens because accessing struct efi_variable in efivar_{attr,size,data}_read() and friends is not protected from a concurrent access leading to a kernel memory corruption and, at best, to a crash. The race scenario is the following:

CPU0: CPU1: efivar_attr_read() var->DataSize = 1024; efivar_entry_get(... &var->DataSize) down_interruptible(&efivars_lock) efivar_attr_read() // same EFI var var->DataSize = 1024; efivar_entry_get(... &var->DataSize) down_interruptible(&efivars_lock) virt_efi_get_variable() // returns EFI_BUFFER_TOO_SMALL but // var->DataSize is set to a real // var size more than 1024 bytes up(&efivars_lock) virt_efi_get_variable() // called with var->DataSize set // to a real var size, returns // successfully and overwrites // a 1024-bytes kernel buffer up(&efivars_lock)

This can be reproduced by concurrent reading of an EFI variable which size is more than 1024 bytes:

ts# for cpu in $(seq 0 $(nproc --ignore=1)); do ( taskset -c $cpu \ cat /sys/firmware/efi/vars/KEKDefault*/size & ) ; done

Fix this by using a local variable for a var's data buffer size so it does not get overwritten.

Fixes: e14ab23dde12b80d ("efivars: efivar_entry API") Reported-by: Bob Sanders bob.sanders@hpe.com and the LTP testsuite Signed-off-by: Vladis Dronov vdronov@redhat.com Signed-off-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Ingo Molnar mingo@kernel.org Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20200305084041.24053-2-vdronov@redhat.com Link: https://lore.kernel.org/r/20200308080859.21568-24-ardb@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/firmware/efi/efivars.c | 29 ++++++++++++++++++++--------- 1 file changed, 20 insertions(+), 9 deletions(-)

--- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -139,13 +139,16 @@ static ssize_t efivar_attr_read(struct efivar_entry *entry, char *buf) { struct efi_variable *var = &entry->var; + unsigned long size = sizeof(var->Data); char *str = buf; + int ret;

if (!entry || !buf) return -EINVAL;

- var->DataSize = 1024; - if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data)) + ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data); + var->DataSize = size; + if (ret) return -EIO;

if (var->Attributes & EFI_VARIABLE_NON_VOLATILE) @@ -172,13 +175,16 @@ static ssize_t efivar_size_read(struct efivar_entry *entry, char *buf) { struct efi_variable *var = &entry->var; + unsigned long size = sizeof(var->Data); char *str = buf; + int ret;

if (!entry || !buf) return -EINVAL;

- var->DataSize = 1024; - if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data)) + ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data); + var->DataSize = size; + if (ret) return -EIO;

str += sprintf(str, "0x%lx\n", var->DataSize); @@ -189,12 +195,15 @@ static ssize_t efivar_data_read(struct efivar_entry *entry, char *buf) { struct efi_variable *var = &entry->var; + unsigned long size = sizeof(var->Data); + int ret;

if (!entry || !buf) return -EINVAL;

- var->DataSize = 1024; - if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data)) + ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data); + var->DataSize = size; + if (ret) return -EIO;

memcpy(buf, var->Data, var->DataSize); @@ -314,14 +323,16 @@ efivar_show_raw(struct efivar_entry *ent { struct efi_variable *var = &entry->var; struct compat_efi_variable *compat; + unsigned long datasize = sizeof(var->Data); size_t size; + int ret;

if (!entry || !buf) return 0;

- var->DataSize = 1024; - if (efivar_entry_get(entry, &entry->var.Attributes, - &entry->var.DataSize, entry->var.Data)) + ret = efivar_entry_get(entry, &var->Attributes, &datasize, var->Data); + var->DataSize = datasize; + if (ret) return -EIO;

if (is_compat()) {

From: Marc Zyngier maz@kernel.org

commit 65ac74f1de3334852fb7d9b1b430fa5a06524276 upstream.

The way cookie_init_hw_msi_region() allocates the iommu_dma_msi_page structures doesn't match the way iommu_put_dma_cookie() frees them.

The former performs a single allocation of all the required structures, while the latter tries to free them one at a time. It doesn't quite work for the main use case (the GICv3 ITS where the range is 64kB) when the base granule size is 4kB.

This leads to a nice slab corruption on teardown, which is easily observable by simply creating a VF on a SRIOV-capable device, and tearing it down immediately (no need to even make use of it). Fortunately, this only affects systems where the ITS isn't translated by the SMMU, which are both rare and non-standard.

Fix it by allocating iommu_dma_msi_page structures one at a time.

Fixes: 7c1b058c8b5a3 ("iommu/dma: Handle IOMMU API reserved regions") Signed-off-by: Marc Zyngier maz@kernel.org Reviewed-by: Eric Auger eric.auger@redhat.com Cc: Robin Murphy robin.murphy@arm.com Cc: Joerg Roedel jroedel@suse.de Cc: Will Deacon will@kernel.org Cc: stable@vger.kernel.org Reviewed-by: Robin Murphy robin.murphy@arm.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/iommu/dma-iommu.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)

--- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -208,15 +208,15 @@ static int cookie_init_hw_msi_region(str start -= iova_offset(iovad, start); num_pages = iova_align(iovad, end - start) >> iova_shift(iovad);

- msi_page = kcalloc(num_pages, sizeof(*msi_page), GFP_KERNEL); - if (!msi_page) - return -ENOMEM; - for (i = 0; i < num_pages; i++) { - msi_page[i].phys = start; - msi_page[i].iova = start; - INIT_LIST_HEAD(&msi_page[i].list); - list_add(&msi_page[i].list, &cookie->msi_page_list); + msi_page = kmalloc(sizeof(*msi_page), GFP_KERNEL); + if (!msi_page) + return -ENOMEM; + + msi_page->phys = start; + msi_page->iova = start; + INIT_LIST_HEAD(&msi_page->list); + list_add(&msi_page->list, &cookie->msi_page_list); start += iovad->granule; }

From: Yonghyun Hwang yonghyun@google.com

commit 77a1bce84bba01f3f143d77127b72e872b573795 upstream.

intel_iommu_iova_to_phys() has a bug when it translates an IOVA for a huge page onto its corresponding physical address. This commit fixes the bug by accomodating the level of page entry for the IOVA and adds IOVA's lower address to the physical address.

Cc: stable@vger.kernel.org Acked-by: Lu Baolu baolu.lu@linux.intel.com Reviewed-by: Moritz Fischer mdf@kernel.org Signed-off-by: Yonghyun Hwang yonghyun@google.com Fixes: 3871794642579 ("VT-d: Changes to support KVM") Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/iommu/intel-iommu.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5124,8 +5124,10 @@ static phys_addr_t intel_iommu_iova_to_p u64 phys = 0;

pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level); - if (pte) - phys = dma_pte_addr(pte); + if (pte && dma_pte_present(pte)) + phys = dma_pte_addr(pte) + + (iova & (BIT_MASK(level_to_offset_bits(level) + + VTD_PAGE_SHIFT) - 1));

return phys; }

From: Charles Keepax ckeepax@opensource.cirrus.com

commit aafd56fc79041bf36f97712d4b35208cbe07db90 upstream.

kref_init starts with the reference count at 1, which will be balanced by the pinctrl_put in pinctrl_unregister. The additional kref_get in pinctrl_claim_hogs will increase this count to 2 and cause the hogs to not get freed when pinctrl_unregister is called.

Fixes: 6118714275f0 ("pinctrl: core: Fix pinctrl_register_and_init() with pinctrl_enable()") Signed-off-by: Charles Keepax ckeepax@opensource.cirrus.com Link: https://lore.kernel.org/r/20200228154142.13860-1-ckeepax@opensource.cirrus.c... Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/pinctrl/core.c | 1 - 1 file changed, 1 deletion(-)

--- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -2031,7 +2031,6 @@ static int pinctrl_claim_hogs(struct pin return PTR_ERR(pctldev->p); }

- kref_get(&pctldev->p->users); pctldev->hog_default = pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_DEFAULT); if (IS_ERR(pctldev->hog_default)) {

From: Jakub Kicinski kuba@kernel.org

commit 056e9375e1f3c4bf2fd49b70258c7daf788ecd9d upstream.

Add missing attribute validation for beacon report scanning to the netlink policy.

Fixes: 1d76250bd34a ("nl80211: support beacon report scanning") Signed-off-by: Jakub Kicinski kuba@kernel.org Link: https://lore.kernel.org/r/20200303051058.4089398-3-kuba@kernel.org Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/wireless/nl80211.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -347,6 +347,8 @@ static const struct nla_policy nl80211_p [NL80211_ATTR_KEY_DEFAULT_TYPES] = { .type = NLA_NESTED }, [NL80211_ATTR_WOWLAN_TRIGGERS] = { .type = NLA_NESTED }, [NL80211_ATTR_STA_PLINK_STATE] = { .type = NLA_U8 }, + [NL80211_ATTR_MEASUREMENT_DURATION] = { .type = NLA_U16 }, + [NL80211_ATTR_MEASUREMENT_DURATION_MANDATORY] = { .type = NLA_FLAG }, [NL80211_ATTR_SCHED_SCAN_INTERVAL] = { .type = NLA_U32 }, [NL80211_ATTR_REKEY_DATA] = { .type = NLA_NESTED }, [NL80211_ATTR_SCAN_SUPP_RATES] = { .type = NLA_NESTED },

From: Jakub Kicinski kuba@kernel.org

commit c049b3450072b8e3998053490e025839fecfef31 upstream.

Add missing attribute validation for cthelper to the netlink policy.

Fixes: 12f7a505331e ("netfilter: add user-space connection tracking helper infrastructure") Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/netfilter/nfnetlink_cthelper.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -733,6 +733,8 @@ static const struct nla_policy nfnl_cthe [NFCTH_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN-1 }, [NFCTH_QUEUE_NUM] = { .type = NLA_U32, }, + [NFCTH_PRIV_DATA_LEN] = { .type = NLA_U32, }, + [NFCTH_STATUS] = { .type = NLA_U32, }, };

static const struct nfnl_callback nfnl_cthelper_cb[NFNL_MSG_CTHELPER_MAX] = {

From: Zhenzhong Duan zhenzhong.duan@gmail.com

commit b0bb0c22c4db623f2e7b1a471596fbf1c22c6dc5 upstream.

When base address in RHSA structure doesn't match base address in each DRHD structure, the base address in last DRHD is printed out.

This doesn't make sense when there are multiple DRHD units, fix it by printing the buggy RHSA's base address.

Signed-off-by: Lu Baolu baolu.lu@linux.intel.com Signed-off-by: Zhenzhong Duan zhenzhong.duan@gmail.com Fixes: fd0c8894893cb ("intel-iommu: Set a more specific taint flag for invalid BIOS DMAR tables") Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/iommu/dmar.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -486,7 +486,7 @@ static int dmar_parse_one_rhsa(struct ac pr_warn(FW_BUG "Your BIOS is broken; RHSA refers to non-existent DMAR unit at %llx\n" "BIOS vendor: %s; Ver: %s; Product Version: %s\n", - drhd->reg_base_addr, + rhsa->base_address, dmi_get_system_info(DMI_BIOS_VENDOR), dmi_get_system_info(DMI_BIOS_VERSION), dmi_get_system_info(DMI_PRODUCT_VERSION));

From: Wolfram Sang wsa+renesas@sang-engineering.com

commit 8daee952b4389729358665fb91949460641659d4 upstream.

i2c_verify_client() can fail, so we need to put the device when that happens.

Fixes: 525e6fabeae2 ("i2c / ACPI: add support for ACPI reconfigure notifications") Reported-by: Geert Uytterhoeven geert+renesas@glider.be Signed-off-by: Wolfram Sang wsa+renesas@sang-engineering.com Reviewed-by: Geert Uytterhoeven geert+renesas@glider.be Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Acked-by: Mika Westerberg mika.westerberg@linux.intel.com Signed-off-by: Wolfram Sang wsa@the-dreams.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/i2c/i2c-core-acpi.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

--- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -352,10 +352,18 @@ static struct i2c_adapter *i2c_acpi_find static struct i2c_client *i2c_acpi_find_client_by_adev(struct acpi_device *adev) { struct device *dev; + struct i2c_client *client;

dev = bus_find_device(&i2c_bus_type, NULL, adev, i2c_acpi_find_match_device); - return dev ? i2c_verify_client(dev) : NULL; + if (!dev) + return NULL; + + client = i2c_verify_client(dev); + if (!client) + put_device(dev); + + return client; }

static int i2c_acpi_notify(struct notifier_block *nb, unsigned long value,

From: Karsten Graul kgraul@linux.ibm.com

commit a2f2ef4a54c0d97aa6a8386f4ff23f36ebb488cf upstream.

In smc_ib_remove_dev() check if the provided ib device was actually initialized for SMC before.

Reported-by: syzbot+84484ccebdd4e5451d91@syzkaller.appspotmail.com Fixes: a4cf0443c414 ("smc: introduce SMC as an IB-client") Signed-off-by: Karsten Graul kgraul@linux.ibm.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/smc/smc_ib.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -513,6 +513,8 @@ static void smc_ib_remove_dev(struct ib_ struct smc_ib_device *smcibdev;

smcibdev = ib_get_client_data(ibdev, &smc_ib_client); + if (!smcibdev || smcibdev->ibdev != ibdev) + return; ib_set_client_data(ibdev, &smc_ib_client, NULL); spin_lock(&smc_ib_devices.lock); list_del_init(&smcibdev->list); /* remove from smc_ib_devices */

From: Sven Eckelmann sven.eckelmann@openmesh.com

commit 6a4bc44b012cbc29c9d824be2c7ab9eac8ee6b6f upstream.

The neighbor compare API implementation for B.A.T.M.A.N. V checks whether the neigh_ifinfo for this neighbor on a specific interface exists. A warning is printed when it isn't found.

But it is not called inside a lock which would prevent that this information is lost right before batadv_neigh_ifinfo_get. It must therefore be expected that batadv_v_neigh_(cmp|is_sob) might not be able to get the requested neigh_ifinfo.

A WARN_ON for such a situation seems not to be appropriate because this will only flood the kernel logs. The warnings must therefore be removed.

Signed-off-by: Sven Eckelmann sven.eckelmann@openmesh.com Signed-off-by: Simon Wunderlich sw@simonwunderlich.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/batman-adv/bat_v.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)

--- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -19,7 +19,6 @@ #include "main.h"

#include <linux/atomic.h> -#include <linux/bug.h> #include <linux/cache.h> #include <linux/errno.h> #include <linux/if_ether.h> @@ -623,11 +622,11 @@ static int batadv_v_neigh_cmp(struct bat int ret = 0;

ifinfo1 = batadv_neigh_ifinfo_get(neigh1, if_outgoing1); - if (WARN_ON(!ifinfo1)) + if (!ifinfo1) goto err_ifinfo1;

ifinfo2 = batadv_neigh_ifinfo_get(neigh2, if_outgoing2); - if (WARN_ON(!ifinfo2)) + if (!ifinfo2) goto err_ifinfo2;

ret = ifinfo1->bat_v.throughput - ifinfo2->bat_v.throughput; @@ -649,11 +648,11 @@ static bool batadv_v_neigh_is_sob(struct bool ret = false;

ifinfo1 = batadv_neigh_ifinfo_get(neigh1, if_outgoing1); - if (WARN_ON(!ifinfo1)) + if (!ifinfo1) goto err_ifinfo1;

ifinfo2 = batadv_neigh_ifinfo_get(neigh2, if_outgoing2); - if (WARN_ON(!ifinfo2)) + if (!ifinfo2) goto err_ifinfo2;

threshold = ifinfo1->bat_v.throughput / 4;

From: Sven Eckelmann sven.eckelmann@openmesh.com

commit 198a62ddffa4a4ffaeb741f642b7b52f2d91ae9b upstream.

The batadv_v_gw_is_eligible function already assumes that orig_node is not NULL. But batadv_gw_node_get may have failed to find the originator. It must therefore be checked whether the batadv_gw_node_get failed and not whether orig_node is NULL to detect this error.

Fixes: 50164d8f500f ("batman-adv: B.A.T.M.A.N. V - implement GW selection logic") Signed-off-by: Sven Eckelmann sven.eckelmann@openmesh.com Acked-by: Antonio Quartulli a@unstable.cc Signed-off-by: Simon Wunderlich sw@simonwunderlich.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/batman-adv/bat_v.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -814,7 +814,7 @@ static bool batadv_v_gw_is_eligible(stru }

orig_gw = batadv_gw_node_get(bat_priv, orig_node); - if (!orig_node) + if (!orig_gw) goto out;

if (batadv_v_gw_throughput_get(orig_gw, &orig_throughput) < 0)

From: Sven Eckelmann sven@narfation.org

commit f22e08932c2960f29b5e828e745c9f3fb7c1bb86 upstream.

batman-adv uses internal indices for each enabled and active interface. It is currently used by the B.A.T.M.A.N. IV algorithm to identifify the correct position in the ogm_cnt bitmaps.

The type for the number of enabled interfaces (which defines the next interface index) was set to char. This type can be (depending on the architecture) either signed (limiting batman-adv to 127 active slave interfaces) or unsigned (limiting batman-adv to 255 active slave interfaces).

This limit was not correctly checked when an interface was enabled and thus an overflow happened. This was only catched on systems with the signed char type when the B.A.T.M.A.N. IV code tried to resize its counter arrays with a negative size.

The if_num interface index was only a s16 and therefore significantly smaller than the ifindex (int) used by the code net code.

Both &batadv_hard_iface->if_num and &batadv_priv->num_ifaces must be (unsigned) int to support the same number of slave interfaces as the net core code. And the interface activation code must check the number of active slave interfaces to avoid integer overflows.

Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol") Signed-off-by: Sven Eckelmann sven@narfation.org Signed-off-by: Simon Wunderlich sw@simonwunderlich.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/batman-adv/bat_iv_ogm.c | 24 ++++++++++++++---------- net/batman-adv/hard-interface.c | 9 +++++++-- net/batman-adv/originator.c | 4 ++-- net/batman-adv/originator.h | 4 ++-- net/batman-adv/types.h | 11 ++++++----- 5 files changed, 31 insertions(+), 21 deletions(-)

--- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -149,7 +149,7 @@ static void batadv_iv_ogm_orig_free(stru * Return: 0 on success, a negative error code otherwise. */ static int batadv_iv_ogm_orig_add_if(struct batadv_orig_node *orig_node, - int max_if_num) + unsigned int max_if_num) { void *data_ptr; size_t old_size; @@ -193,7 +193,8 @@ unlock: */ static void batadv_iv_ogm_drop_bcast_own_entry(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num) + unsigned int max_if_num, + unsigned int del_if_num) { size_t chunk_size; size_t if_offset; @@ -231,7 +232,8 @@ batadv_iv_ogm_drop_bcast_own_entry(struc */ static void batadv_iv_ogm_drop_bcast_own_sum_entry(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num) + unsigned int max_if_num, + unsigned int del_if_num) { size_t if_offset; void *data_ptr; @@ -268,7 +270,8 @@ batadv_iv_ogm_drop_bcast_own_sum_entry(s * Return: 0 on success, a negative error code otherwise. */ static int batadv_iv_ogm_orig_del_if(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num) + unsigned int max_if_num, + unsigned int del_if_num) { spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock);

@@ -302,7 +305,8 @@ static struct batadv_orig_node * batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr) { struct batadv_orig_node *orig_node; - int size, hash_added; + int hash_added; + size_t size;

orig_node = batadv_orig_hash_find(bat_priv, addr); if (orig_node) @@ -890,7 +894,7 @@ batadv_iv_ogm_slide_own_bcast_window(str u32 i; size_t word_index; u8 *w; - int if_num; + unsigned int if_num;

for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -1020,7 +1024,7 @@ batadv_iv_ogm_orig_update(struct batadv_ struct batadv_neigh_node *tmp_neigh_node = NULL; struct batadv_neigh_node *router = NULL; struct batadv_orig_node *orig_node_tmp; - int if_num; + unsigned int if_num; u8 sum_orig, sum_neigh; u8 *neigh_addr; u8 tq_avg; @@ -1179,7 +1183,7 @@ static bool batadv_iv_ogm_calc_tq(struct u8 total_count; u8 orig_eq_count, neigh_rq_count, neigh_rq_inv, tq_own; unsigned int neigh_rq_inv_cube, neigh_rq_max_cube; - int if_num; + unsigned int if_num; unsigned int tq_asym_penalty, inv_asym_penalty; unsigned int combined_tq; unsigned int tq_iface_penalty; @@ -1698,9 +1702,9 @@ static void batadv_iv_ogm_process(const

if (is_my_orig) { unsigned long *word; - int offset; + size_t offset; s32 bit_pos; - s16 if_num; + unsigned int if_num; u8 *weight;

orig_neigh_node = batadv_iv_ogm_orig_get(bat_priv, --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -738,6 +738,11 @@ int batadv_hardif_enable_interface(struc hard_iface->soft_iface = soft_iface; bat_priv = netdev_priv(hard_iface->soft_iface);

+ if (bat_priv->num_ifaces >= UINT_MAX) { + ret = -ENOSPC; + goto err_dev; + } + ret = netdev_master_upper_dev_link(hard_iface->net_dev, soft_iface, NULL, NULL); if (ret) @@ -845,7 +850,7 @@ void batadv_hardif_disable_interface(str batadv_hardif_recalc_extra_skbroom(hard_iface->soft_iface);

/* nobody uses this interface anymore */ - if (!bat_priv->num_ifaces) { + if (bat_priv->num_ifaces == 0) { batadv_gw_check_client_stop(bat_priv);

if (autodel == BATADV_IF_CLEANUP_AUTO) @@ -881,7 +886,7 @@ batadv_hardif_add_interface(struct net_d if (ret) goto free_if;

- hard_iface->if_num = -1; + hard_iface->if_num = 0; hard_iface->net_dev = net_dev; hard_iface->soft_iface = NULL; hard_iface->if_status = BATADV_IF_NOT_IN_USE; --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1500,7 +1500,7 @@ int batadv_orig_dump(struct sk_buff *msg }

int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, - int max_if_num) + unsigned int max_if_num) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_algo_ops *bao = bat_priv->algo_ops; @@ -1535,7 +1535,7 @@ err: }

int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, - int max_if_num) + unsigned int max_if_num) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hashtable *hash = bat_priv->orig_hash; --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -78,9 +78,9 @@ int batadv_orig_seq_print_text(struct se int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb); int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset); int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, - int max_if_num); + unsigned int max_if_num); int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, - int max_if_num); + unsigned int max_if_num); struct batadv_orig_node_vlan * batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, unsigned short vid); --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -155,7 +155,7 @@ enum batadv_hard_iface_wifi_flags { */ struct batadv_hard_iface { struct list_head list; - s16 if_num; + unsigned int if_num; char if_status; u8 num_bcasts; u32 wifi_flags; @@ -1081,7 +1081,7 @@ struct batadv_priv { atomic_t bcast_seqno; atomic_t bcast_queue_left; atomic_t batman_queue_left; - char num_ifaces; + unsigned int num_ifaces; struct kobject *mesh_obj; struct dentry *debug_dir; struct hlist_head forw_bat_list; @@ -1479,9 +1479,10 @@ struct batadv_algo_neigh_ops { */ struct batadv_algo_orig_ops { void (*free)(struct batadv_orig_node *orig_node); - int (*add_if)(struct batadv_orig_node *orig_node, int max_if_num); - int (*del_if)(struct batadv_orig_node *orig_node, int max_if_num, - int del_if_num); + int (*add_if)(struct batadv_orig_node *orig_node, + unsigned int max_if_num); + int (*del_if)(struct batadv_orig_node *orig_node, + unsigned int max_if_num, unsigned int del_if_num); #ifdef CONFIG_BATMAN_ADV_DEBUGFS void (*print)(struct batadv_priv *priv, struct seq_file *seq, struct batadv_hard_iface *hard_iface);

From: Sven Eckelmann sven@narfation.org

commit 8ba0f9bd3bdea1058c2b2676bec7905724418e40 upstream.

The functions batadv_tt_prepare_tvlv_local_data and batadv_tt_prepare_tvlv_global_data are responsible for preparing a buffer which can be used to store the TVLV container for TT and add the VLAN information to it.

This will be done in three phases:

1. count the number of VLANs and their entries 2. allocate the buffer using the counters from the previous step and limits from the caller (parameter tt_len) 3. insert the VLAN information to the buffer

The step 1 and 3 operate on a list which contains the VLANs. The access to these lists must be protected with an appropriate lock or otherwise they might operate on on different entries. This could for example happen when another context is adding VLAN entries to this list.

This could lead to a buffer overflow in these functions when enough entries were added between step 1 and 3 to the VLAN lists that the buffer room for the entries (*tt_change) is smaller then the now required extra buffer for new VLAN entries.

Fixes: 7ea7b4a14275 ("batman-adv: make the TT CRC logic VLAN specific") Signed-off-by: Sven Eckelmann sven@narfation.org Acked-by: Antonio Quartulli a@unstable.cc Signed-off-by: Simon Wunderlich sw@simonwunderlich.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/batman-adv/translation-table.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -872,7 +872,7 @@ batadv_tt_prepare_tvlv_global_data(struc struct batadv_orig_node_vlan *vlan; u8 *tt_change_ptr;

- rcu_read_lock(); + spin_lock_bh(&orig_node->vlan_list_lock); hlist_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) { num_vlan++; num_entries += atomic_read(&vlan->tt.num_entries); @@ -910,7 +910,7 @@ batadv_tt_prepare_tvlv_global_data(struc *tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr;

out: - rcu_read_unlock(); + spin_unlock_bh(&orig_node->vlan_list_lock); return tvlv_len; }

@@ -946,7 +946,7 @@ batadv_tt_prepare_tvlv_local_data(struct u8 *tt_change_ptr; int change_offset;

- rcu_read_lock(); + spin_lock_bh(&bat_priv->softif_vlan_list_lock); hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) { num_vlan++; num_entries += atomic_read(&vlan->tt.num_entries); @@ -984,7 +984,7 @@ batadv_tt_prepare_tvlv_local_data(struct *tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr;

out: - rcu_read_unlock(); + spin_unlock_bh(&bat_priv->softif_vlan_list_lock); return tvlv_len; }

From: Marek Lindner mareklindner@neomailbox.ch

commit 16116dac23396e73c01eeee97b102e4833a4b205 upstream.

A translation table TVLV changset sent with an OGM consists of a number of headers (one per VLAN) plus the changeset itself (addition and/or deletion of entries).

The per-VLAN headers are used by OGM recipients for consistency checks. Said consistency check might determine that a full translation table request is needed to restore consistency. If the TT sender adds per-VLAN headers of empty VLANs into the OGM, recipients are led to believe to have reached an inconsistent state and thus request a full table update. The full table does not contain empty VLANs (due to missing entries) the cycle restarts when the next OGM is issued.

Consequently, when the translation table TVLV headers are composed, empty VLANs are to be excluded.

Fixes: 21a57f6e7a3b ("batman-adv: make the TT CRC logic VLAN specific") Signed-off-by: Marek Lindner mareklindner@neomailbox.ch Signed-off-by: Sven Eckelmann sven@narfation.org Signed-off-by: Simon Wunderlich sw@simonwunderlich.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/batman-adv/translation-table.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-)

--- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -941,15 +941,20 @@ batadv_tt_prepare_tvlv_local_data(struct struct batadv_tvlv_tt_vlan_data *tt_vlan; struct batadv_softif_vlan *vlan; u16 num_vlan = 0; - u16 num_entries = 0; + u16 vlan_entries = 0; + u16 total_entries = 0; u16 tvlv_len; u8 *tt_change_ptr; int change_offset;

spin_lock_bh(&bat_priv->softif_vlan_list_lock); hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) { + vlan_entries = atomic_read(&vlan->tt.num_entries); + if (vlan_entries < 1) + continue; + num_vlan++; - num_entries += atomic_read(&vlan->tt.num_entries); + total_entries += vlan_entries; }

change_offset = sizeof(**tt_data); @@ -957,7 +962,7 @@ batadv_tt_prepare_tvlv_local_data(struct

/* if tt_len is negative, allocate the space needed by the full table */ if (*tt_len < 0) - *tt_len = batadv_tt_len(num_entries); + *tt_len = batadv_tt_len(total_entries);

tvlv_len = *tt_len; tvlv_len += change_offset; @@ -974,6 +979,10 @@ batadv_tt_prepare_tvlv_local_data(struct

tt_vlan = (struct batadv_tvlv_tt_vlan_data *)(*tt_data + 1); hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) { + vlan_entries = atomic_read(&vlan->tt.num_entries); + if (vlan_entries < 1) + continue; + tt_vlan->vid = htons(vlan->vid); tt_vlan->crc = htonl(vlan->tt.crc);

From: Sven Eckelmann sven@narfation.org

commit 6da7be7d24b2921f8215473ba7552796dff05fe1 upstream.

batman-adv is creating special debugfs directories in the init net_namespace for each created soft-interface (batadv net_device). But it is possible to rename a net_device to a completely different name then the original one.

It can therefore happen that a user registers a new batadv net_device with the name "bat0". batman-adv is then also adding a new directory under $debugfs/batman-adv/ with the name "wlan0".

The user then decides to rename this device to "bat1" and registers a different batadv device with the name "bat0". batman-adv will then try to create a directory with the name "bat0" under $debugfs/batman-adv/ again. But there already exists one with this name under this path and thus this fails. batman-adv will detect a problem and rollback the registering of this device.

batman-adv must therefore take care of renaming the debugfs directories for soft-interfaces whenever it detects such a net_device rename.

Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol") Signed-off-by: Sven Eckelmann sven@narfation.org Signed-off-by: Simon Wunderlich sw@simonwunderlich.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/batman-adv/debugfs.c | 24 ++++++++++++++++++++++++ net/batman-adv/debugfs.h | 5 +++++ net/batman-adv/hard-interface.c | 34 ++++++++++++++++++++++++++++------ 3 files changed, 57 insertions(+), 6 deletions(-)

--- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -421,6 +421,30 @@ out: return -ENOMEM; }

+/** + * batadv_debugfs_rename_meshif() - Fix debugfs path for renamed softif + * @dev: net_device which was renamed + */ +void batadv_debugfs_rename_meshif(struct net_device *dev) +{ + struct batadv_priv *bat_priv = netdev_priv(dev); + const char *name = dev->name; + struct dentry *dir; + struct dentry *d; + + dir = bat_priv->debug_dir; + if (!dir) + return; + + d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name); + if (!d) + pr_err("Can't rename debugfs dir to %s\n", name); +} + +/** + * batadv_debugfs_del_meshif() - Remove interface dependent debugfs entries + * @dev: netdev struct of the soft interface + */ void batadv_debugfs_del_meshif(struct net_device *dev) { struct batadv_priv *bat_priv = netdev_priv(dev); --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -29,6 +29,7 @@ struct net_device; void batadv_debugfs_init(void); void batadv_debugfs_destroy(void); int batadv_debugfs_add_meshif(struct net_device *dev); +void batadv_debugfs_rename_meshif(struct net_device *dev); void batadv_debugfs_del_meshif(struct net_device *dev); int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface); void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface); @@ -49,6 +50,10 @@ static inline int batadv_debugfs_add_mes return 0; }

+static inline void batadv_debugfs_rename_meshif(struct net_device *dev) +{ +} + static inline void batadv_debugfs_del_meshif(struct net_device *dev) { } --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -955,6 +955,32 @@ void batadv_hardif_remove_interfaces(voi rtnl_unlock(); }

+/** + * batadv_hard_if_event_softif() - Handle events for soft interfaces + * @event: NETDEV_* event to handle + * @net_dev: net_device which generated an event + * + * Return: NOTIFY_* result + */ +static int batadv_hard_if_event_softif(unsigned long event, + struct net_device *net_dev) +{ + struct batadv_priv *bat_priv; + + switch (event) { + case NETDEV_REGISTER: + batadv_sysfs_add_meshif(net_dev); + bat_priv = netdev_priv(net_dev); + batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS); + break; + case NETDEV_CHANGENAME: + batadv_debugfs_rename_meshif(net_dev); + break; + } + + return NOTIFY_DONE; +} + static int batadv_hard_if_event(struct notifier_block *this, unsigned long event, void *ptr) { @@ -963,12 +989,8 @@ static int batadv_hard_if_event(struct n struct batadv_hard_iface *primary_if = NULL; struct batadv_priv *bat_priv;

- if (batadv_softif_is_valid(net_dev) && event == NETDEV_REGISTER) { - batadv_sysfs_add_meshif(net_dev); - bat_priv = netdev_priv(net_dev); - batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS); - return NOTIFY_DONE; - } + if (batadv_softif_is_valid(net_dev)) + return batadv_hard_if_event_softif(event, net_dev);

hard_iface = batadv_hardif_get_by_netdev(net_dev); if (!hard_iface && (event == NETDEV_REGISTER ||

From: Sven Eckelmann sven@narfation.org

commit a8d23cbbf6c9f515ed678204ad2962be7c336344 upstream.

A B.A.T.M.A.N. V virtual interface has an OGM2 packet buffer which is initialized using data from the netdevice notifier and other rtnetlink related hooks. It is sent regularly via various slave interfaces of the batadv virtual interface and in this process also modified (realloced) to integrate additional state information via TVLV containers.

It must be avoided that the worker item is executed without a common lock with the netdevice notifier/rtnetlink helpers. Otherwise it can either happen that half modified data is sent out or the functions modifying the OGM2 buffer try to access already freed memory regions.

Fixes: 0da0035942d4 ("batman-adv: OGMv2 - add basic infrastructure") Signed-off-by: Sven Eckelmann sven@narfation.org Signed-off-by: Simon Wunderlich sw@simonwunderlich.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/batman-adv/bat_v_ogm.c | 42 ++++++++++++++++++++++++++++++++++-------- net/batman-adv/types.h | 3 +++ 2 files changed, 37 insertions(+), 8 deletions(-)

--- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -28,6 +28,8 @@ #include <linux/kernel.h> #include <linux/kref.h> #include <linux/list.h> +#include <linux/lockdep.h> +#include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/random.h> #include <linux/rculist.h> @@ -127,14 +129,12 @@ static void batadv_v_ogm_send_to_if(stru }

/** - * batadv_v_ogm_send - periodic worker broadcasting the own OGM - * @work: work queue item + * batadv_v_ogm_send_softif() - periodic worker broadcasting the own OGM + * @bat_priv: the bat priv with all the soft interface information */ -static void batadv_v_ogm_send(struct work_struct *work) +static void batadv_v_ogm_send_softif(struct batadv_priv *bat_priv) { struct batadv_hard_iface *hard_iface; - struct batadv_priv_bat_v *bat_v; - struct batadv_priv *bat_priv; struct batadv_ogm2_packet *ogm_packet; struct sk_buff *skb, *skb_tmp; unsigned char *ogm_buff; @@ -142,8 +142,7 @@ static void batadv_v_ogm_send(struct wor u16 tvlv_len = 0; int ret;

- bat_v = container_of(work, struct batadv_priv_bat_v, ogm_wq.work); - bat_priv = container_of(bat_v, struct batadv_priv, bat_v); + lockdep_assert_held(&bat_priv->bat_v.ogm_buff_mutex);

if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) goto out; @@ -235,6 +234,23 @@ out: }

/** + * batadv_v_ogm_send() - periodic worker broadcasting the own OGM + * @work: work queue item + */ +static void batadv_v_ogm_send(struct work_struct *work) +{ + struct batadv_priv_bat_v *bat_v; + struct batadv_priv *bat_priv; + + bat_v = container_of(work, struct batadv_priv_bat_v, ogm_wq.work); + bat_priv = container_of(bat_v, struct batadv_priv, bat_v); + + mutex_lock(&bat_priv->bat_v.ogm_buff_mutex); + batadv_v_ogm_send_softif(bat_priv); + mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex); +} + +/** * batadv_v_ogm_iface_enable - prepare an interface for B.A.T.M.A.N. V * @hard_iface: the interface to prepare * @@ -260,11 +276,15 @@ void batadv_v_ogm_primary_iface_set(stru struct batadv_priv *bat_priv = netdev_priv(primary_iface->soft_iface); struct batadv_ogm2_packet *ogm_packet;

+ mutex_lock(&bat_priv->bat_v.ogm_buff_mutex); if (!bat_priv->bat_v.ogm_buff) - return; + goto unlock;

ogm_packet = (struct batadv_ogm2_packet *)bat_priv->bat_v.ogm_buff; ether_addr_copy(ogm_packet->orig, primary_iface->net_dev->dev_addr); + +unlock: + mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex); }

/** @@ -886,6 +906,8 @@ int batadv_v_ogm_init(struct batadv_priv atomic_set(&bat_priv->bat_v.ogm_seqno, random_seqno); INIT_DELAYED_WORK(&bat_priv->bat_v.ogm_wq, batadv_v_ogm_send);

+ mutex_init(&bat_priv->bat_v.ogm_buff_mutex); + return 0; }

@@ -897,7 +919,11 @@ void batadv_v_ogm_free(struct batadv_pri { cancel_delayed_work_sync(&bat_priv->bat_v.ogm_wq);

+ mutex_lock(&bat_priv->bat_v.ogm_buff_mutex); + kfree(bat_priv->bat_v.ogm_buff); bat_priv->bat_v.ogm_buff = NULL; bat_priv->bat_v.ogm_buff_len = 0; + + mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex); } --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -27,6 +27,7 @@ #include <linux/compiler.h> #include <linux/if_ether.h> #include <linux/kref.h> +#include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/sched.h> /* for linux/wait.h */ @@ -989,12 +990,14 @@ struct batadv_softif_vlan { * @ogm_buff: buffer holding the OGM packet * @ogm_buff_len: length of the OGM packet buffer * @ogm_seqno: OGM sequence number - used to identify each OGM + * @ogm_buff_mutex: lock protecting ogm_buff and ogm_buff_len * @ogm_wq: workqueue used to schedule OGM transmissions */ struct batadv_priv_bat_v { unsigned char *ogm_buff; int ogm_buff_len; atomic_t ogm_seqno; + struct mutex ogm_buff_mutex; struct delayed_work ogm_wq; };

From: Sven Eckelmann sven@narfation.org

commit 8e8ce08198de193e3d21d42e96945216e3d9ac7f upstream.

A transmission scheduling for an interface which is currently dropped by batadv_iv_ogm_iface_disable could still be in progress. The B.A.T.M.A.N. V is simply cancelling the workqueue item in an synchronous way but this is not possible with B.A.T.M.A.N. IV because the OGM submissions are intertwined.

Instead it has to stop submitting the OGM when it detect that the buffer pointer is set to NULL.

Reported-by: syzbot+a98f2016f40b9cd3818a@syzkaller.appspotmail.com Reported-by: syzbot+ac36b6a33c28a491e929@syzkaller.appspotmail.com Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol") Signed-off-by: Sven Eckelmann sven@narfation.org Cc: Hillf Danton hdanton@sina.com Signed-off-by: Simon Wunderlich sw@simonwunderlich.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/batman-adv/bat_iv_ogm.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -961,6 +961,10 @@ static void batadv_iv_ogm_schedule_buff(

lockdep_assert_held(&hard_iface->bat_iv.ogm_buff_mutex);

+ /* interface already disabled by batadv_iv_ogm_iface_disable */ + if (!*ogm_buff) + return; + /* the interface gets activated here to avoid race conditions between * the moment of activating the interface in * hardif_activate_interface() where the originator mac is set and

From: Jean Delvare jdelvare@suse.de

[ Upstream commit 3f9e12e0df012c4a9a7fd7eb0d3ae69b459d6b2c ]

In case the WDAT interface is broken, give the user an option to ignore it to let a native driver bind to the watchdog device instead.

Signed-off-by: Jean Delvare jdelvare@suse.de Acked-by: Mika Westerberg mika.westerberg@linux.intel.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- Documentation/admin-guide/kernel-parameters.txt | 4 ++++ drivers/acpi/acpi_watchdog.c | 12 +++++++++++- 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 7e0a4be3503d6..ae51b1b7b67fb 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -137,6 +137,10 @@ dynamic table installation which will install SSDT tables to /sys/firmware/acpi/tables/dynamic.

+ acpi_no_watchdog [HW,ACPI,WDT] + Ignore the ACPI-based watchdog interface (WDAT) and let + a native driver control the watchdog device instead. + acpi_rsdp= [ACPI,EFI,KEXEC] Pass the RSDP address to the kernel, mostly used on machines running EFI runtime service to boot the diff --git a/drivers/acpi/acpi_watchdog.c b/drivers/acpi/acpi_watchdog.c index 23cde3d8e8fbb..0bd1899a287f3 100644 --- a/drivers/acpi/acpi_watchdog.c +++ b/drivers/acpi/acpi_watchdog.c @@ -58,12 +58,14 @@ static bool acpi_watchdog_uses_rtc(const struct acpi_table_wdat *wdat) } #endif

+static bool acpi_no_watchdog; + static const struct acpi_table_wdat *acpi_watchdog_get_wdat(void) { const struct acpi_table_wdat *wdat = NULL; acpi_status status;

- if (acpi_disabled) + if (acpi_disabled || acpi_no_watchdog) return NULL;

status = acpi_get_table(ACPI_SIG_WDAT, 0, @@ -91,6 +93,14 @@ bool acpi_has_watchdog(void) } EXPORT_SYMBOL_GPL(acpi_has_watchdog);

+/* ACPI watchdog can be disabled on boot command line */ +static int __init disable_acpi_watchdog(char *str) +{ + acpi_no_watchdog = true; + return 1; +} +__setup("acpi_no_watchdog", disable_acpi_watchdog); + void __init acpi_watchdog_init(void) { const struct acpi_wdat_entry *entries;

From: Kai-Heng Feng kai.heng.feng@canonical.com

[ Upstream commit be0aba826c4a6ba5929def1962a90d6127871969 ]

The Surfbook E11B uses the SIPODEV SP1064 touchpad, which does not supply descriptors, so it has to be added to the override list.

BugLink: https://bugs.launchpad.net/bugs/1858299 Signed-off-by: Kai-Heng Feng kai.heng.feng@canonical.com Reviewed-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Benjamin Tissoires benjamin.tissoires@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c index 10af8585c820d..95052373a8282 100644 --- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c +++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c @@ -341,6 +341,14 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = { }, .driver_data = (void *)&sipodev_desc }, + { + .ident = "Trekstor SURFBOOK E11B", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TREKSTOR"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SURFBOOK E11B"), + }, + .driver_data = (void *)&sipodev_desc + }, { .ident = "Direkt-Tek DTLAPY116-2", .matches = {

From: Igor Druzhinin igor.druzhinin@citrix.com

[ Upstream commit ff6993bb79b9f99bdac0b5378169052931b65432 ]

fc_disc_gpn_id_resp() should be the last function using it so free it here to avoid memory leak.

Link: https://lore.kernel.org/r/1579013000-14570-2-git-send-email-igor.druzhinin@c... Reviewed-by: Hannes Reinecke hare@suse.de Signed-off-by: Igor Druzhinin igor.druzhinin@citrix.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/libfc/fc_disc.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c index bb9c1c0166439..28b50ab2fbb01 100644 --- a/drivers/scsi/libfc/fc_disc.c +++ b/drivers/scsi/libfc/fc_disc.c @@ -652,6 +652,8 @@ static void fc_disc_gpn_id_resp(struct fc_seq *sp, struct fc_frame *fp, } out: kref_put(&rdata->kref, fc_rport_destroy); + if (!IS_ERR(fp)) + fc_frame_free(fp); }

/**

From: Marek Vasut marex@denx.de

[ Upstream commit 44343418d0f2f623cb9da6f5000df793131cbe3b ]

The KS8851 requires that packet RX and TX are mutually exclusive. Currently, the driver hopes to achieve this by disabling interrupt from the card by writing the card registers and by disabling the interrupt on the interrupt controller. This however is racy on SMP.

Replace this approach by expanding the spinlock used around the ks_start_xmit() TX path to ks_irq() RX path to assure true mutual exclusion and remove the interrupt enabling/disabling, which is now not needed anymore. Furthermore, disable interrupts also in ks_net_stop(), which was missing before.

Note that a massive improvement here would be to re-use the KS8851 driver approach, which is to move the TX path into a worker thread, interrupt handling to threaded interrupt, and synchronize everything with mutexes, but that would be a much bigger rework, for a separate patch.

Signed-off-by: Marek Vasut marex@denx.de Cc: David S. Miller davem@davemloft.net Cc: Lukas Wunner lukas@wunner.de Cc: Petr Stetiar ynezz@true.cz Cc: YueHaibing yuehaibing@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/micrel/ks8851_mll.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c index 799154d7c0470..c699a779757eb 100644 --- a/drivers/net/ethernet/micrel/ks8851_mll.c +++ b/drivers/net/ethernet/micrel/ks8851_mll.c @@ -831,14 +831,17 @@ static irqreturn_t ks_irq(int irq, void *pw) { struct net_device *netdev = pw; struct ks_net *ks = netdev_priv(netdev); + unsigned long flags; u16 status;

+ spin_lock_irqsave(&ks->statelock, flags); /*this should be the first in IRQ handler */ ks_save_cmd_reg(ks);

status = ks_rdreg16(ks, KS_ISR); if (unlikely(!status)) { ks_restore_cmd_reg(ks); + spin_unlock_irqrestore(&ks->statelock, flags); return IRQ_NONE; }

@@ -864,6 +867,7 @@ static irqreturn_t ks_irq(int irq, void *pw) ks->netdev->stats.rx_over_errors++; /* this should be the last in IRQ handler*/ ks_restore_cmd_reg(ks); + spin_unlock_irqrestore(&ks->statelock, flags); return IRQ_HANDLED; }

@@ -933,6 +937,7 @@ static int ks_net_stop(struct net_device *netdev)

/* shutdown RX/TX QMU */ ks_disable_qmu(ks); + ks_disable_int(ks);

/* set powermode to soft power down to save power */ ks_set_powermode(ks, PMECR_PM_SOFTDOWN); @@ -989,10 +994,9 @@ static netdev_tx_t ks_start_xmit(struct sk_buff *skb, struct net_device *netdev) { netdev_tx_t retv = NETDEV_TX_OK; struct ks_net *ks = netdev_priv(netdev); + unsigned long flags;

- disable_irq(netdev->irq); - ks_disable_int(ks); - spin_lock(&ks->statelock); + spin_lock_irqsave(&ks->statelock, flags);

/* Extra space are required: * 4 byte for alignment, 4 for status/length, 4 for CRC @@ -1006,9 +1010,7 @@ static netdev_tx_t ks_start_xmit(struct sk_buff *skb, struct net_device *netdev) dev_kfree_skb(skb); } else retv = NETDEV_TX_BUSY; - spin_unlock(&ks->statelock); - ks_enable_int(ks); - enable_irq(netdev->irq); + spin_unlock_irqrestore(&ks->statelock, flags); return retv; }

From: Linus Torvalds torvalds@linux-foundation.org

[ Upstream commit fda31c50292a5062332fa0343c084bd9f46604d9 ]

When queueing a signal, we increment both the users count of pending signals (for RLIMIT_SIGPENDING tracking) and we increment the refcount of the user struct itself (because we keep a reference to the user in the signal structure in order to correctly account for it when freeing).

That turns out to be fairly expensive, because both of them are atomic updates, and particularly under extreme signal handling pressure on big machines, you can get a lot of cache contention on the user struct. That can then cause horrid cacheline ping-pong when you do these multiple accesses.

So change the reference counting to only pin the user for the _first_ pending signal, and to unpin it when the last pending signal is dequeued. That means that when a user sees a lot of concurrent signal queuing - which is the only situation when this matters - the only atomic access needed is generally the 'sigpending' count update.

This was noticed because of a particularly odd timing artifact on a dual-socket 96C/192T Cascade Lake platform: when you get into bad contention, on that machine for some reason seems to be much worse when the contention happens in the upper 32-byte half of the cacheline.

As a result, the kernel test robot will-it-scale 'signal1' benchmark had an odd performance regression simply due to random alignment of the 'struct user_struct' (and pointed to a completely unrelated and apparently nonsensical commit for the regression).

Avoiding the double increments (and decrements on the dequeueing side, of course) makes for much less contention and hugely improved performance on that will-it-scale microbenchmark.

Quoting Feng Tang:

"It makes a big difference, that the performance score is tripled! bump from original 17000 to 54000. Also the gap between 5.0-rc6 and 5.0-rc6+Jiri's patch is reduced to around 2%"

[ The "2% gap" is the odd cacheline placement difference on that platform: under the extreme contention case, the effect of which half of the cacheline was hot was 5%, so with the reduced contention the odd timing artifact is reduced too ]

It does help in the non-contended case too, but is not nearly as noticeable.

Reported-and-tested-by: Feng Tang feng.tang@intel.com Cc: Eric W. Biederman ebiederm@xmission.com Cc: Huang, Ying ying.huang@intel.com Cc: Philip Li philip.li@intel.com Cc: Andi Kleen andi.kleen@intel.com Cc: Jiri Olsa jolsa@redhat.com Cc: Peter Zijlstra peterz@infradead.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/signal.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/kernel/signal.c b/kernel/signal.c index 8fee1f2eba2f9..c066168f88541 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -379,27 +379,32 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi { struct sigqueue *q = NULL; struct user_struct *user; + int sigpending;

/* * Protect access to @t credentials. This can go away when all * callers hold rcu read lock. + * + * NOTE! A pending signal will hold on to the user refcount, + * and we get/put the refcount only when the sigpending count + * changes from/to zero. */ rcu_read_lock(); - user = get_uid(__task_cred(t)->user); - atomic_inc(&user->sigpending); + user = __task_cred(t)->user; + sigpending = atomic_inc_return(&user->sigpending); + if (sigpending == 1) + get_uid(user); rcu_read_unlock();

- if (override_rlimit || - atomic_read(&user->sigpending) <= - task_rlimit(t, RLIMIT_SIGPENDING)) { + if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) { q = kmem_cache_alloc(sigqueue_cachep, flags); } else { print_dropped_signal(sig); }

if (unlikely(q == NULL)) { - atomic_dec(&user->sigpending); - free_uid(user); + if (atomic_dec_and_test(&user->sigpending)) + free_uid(user); } else { INIT_LIST_HEAD(&q->list); q->flags = 0; @@ -413,8 +418,8 @@ static void __sigqueue_free(struct sigqueue *q) { if (q->flags & SIGQUEUE_PREALLOC) return; - atomic_dec(&q->user->sigpending); - free_uid(q->user); + if (atomic_dec_and_test(&q->user->sigpending)) + free_uid(q->user); kmem_cache_free(sigqueue_cachep, q); }

From: Luo bin luobin9@huawei.com

[ Upstream commit d2ed69ce9ed3477e2a9527e6b89fe4689d99510e ]

a reserved field is used to signify prime physical function index in the latest firmware version, so we must assign a value to it correctly

Signed-off-by: Luo bin luobin9@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c | 1 + drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h | 2 +- drivers/net/ethernet/huawei/hinic/hinic_hw_if.h | 1 + 3 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c index 79b5674470842..46aba02b8672b 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c @@ -312,6 +312,7 @@ static int set_hw_ioctxt(struct hinic_hwdev *hwdev, unsigned int rq_depth, }

hw_ioctxt.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + hw_ioctxt.ppf_idx = HINIC_HWIF_PPF_IDX(hwif);

hw_ioctxt.set_cmdq_depth = HW_IOCTXT_SET_CMDQ_DEPTH_DEFAULT; hw_ioctxt.cmdq_depth = 0; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h index 0f5563f3b7798..a011fd2d26270 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h @@ -104,8 +104,8 @@ struct hinic_cmd_hw_ioctxt {

u8 rsvd2; u8 rsvd3; + u8 ppf_idx; u8 rsvd4; - u8 rsvd5;

u16 rq_depth; u16 rx_buf_sz_idx; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h index 5b4760c0e9f53..f683ccbdfca02 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h @@ -146,6 +146,7 @@ #define HINIC_HWIF_FUNC_IDX(hwif) ((hwif)->attr.func_idx) #define HINIC_HWIF_PCI_INTF(hwif) ((hwif)->attr.pci_intf_idx) #define HINIC_HWIF_PF_IDX(hwif) ((hwif)->attr.pf_idx) +#define HINIC_HWIF_PPF_IDX(hwif) ((hwif)->attr.ppf_idx)

#define HINIC_FUNC_TYPE(hwif) ((hwif)->attr.func_type) #define HINIC_IS_PF(hwif) (HINIC_FUNC_TYPE(hwif) == HINIC_PF)

From: Qian Cai cai@lca.pw

[ Upstream commit 6c5d911249290f41f7b50b43344a7520605b1acb ]

journal_head::b_transaction and journal_head::b_next_transaction could be accessed concurrently as noticed by KCSAN,

LTP: starting fsync04 /dev/zero: Can't open blockdev EXT4-fs (loop0): mounting ext3 file system using the ext4 subsystem EXT4-fs (loop0): mounted filesystem with ordered data mode. Opts: (null) ================================================================== BUG: KCSAN: data-race in __jbd2_journal_refile_buffer [jbd2] / jbd2_write_access_granted [jbd2]

write to 0xffff99f9b1bd0e30 of 8 bytes by task 25721 on cpu 70: __jbd2_journal_refile_buffer+0xdd/0x210 [jbd2] __jbd2_journal_refile_buffer at fs/jbd2/transaction.c:2569 jbd2_journal_commit_transaction+0x2d15/0x3f20 [jbd2] (inlined by) jbd2_journal_commit_transaction at fs/jbd2/commit.c:1034 kjournald2+0x13b/0x450 [jbd2] kthread+0x1cd/0x1f0 ret_from_fork+0x27/0x50

read to 0xffff99f9b1bd0e30 of 8 bytes by task 25724 on cpu 68: jbd2_write_access_granted+0x1b2/0x250 [jbd2] jbd2_write_access_granted at fs/jbd2/transaction.c:1155 jbd2_journal_get_write_access+0x2c/0x60 [jbd2] __ext4_journal_get_write_access+0x50/0x90 [ext4] ext4_mb_mark_diskspace_used+0x158/0x620 [ext4] ext4_mb_new_blocks+0x54f/0xca0 [ext4] ext4_ind_map_blocks+0xc79/0x1b40 [ext4] ext4_map_blocks+0x3b4/0x950 [ext4] _ext4_get_block+0xfc/0x270 [ext4] ext4_get_block+0x3b/0x50 [ext4] __block_write_begin_int+0x22e/0xae0 __block_write_begin+0x39/0x50 ext4_write_begin+0x388/0xb50 [ext4] generic_perform_write+0x15d/0x290 ext4_buffered_write_iter+0x11f/0x210 [ext4] ext4_file_write_iter+0xce/0x9e0 [ext4] new_sync_write+0x29c/0x3b0 __vfs_write+0x92/0xa0 vfs_write+0x103/0x260 ksys_write+0x9d/0x130 __x64_sys_write+0x4c/0x60 do_syscall_64+0x91/0xb05 entry_SYSCALL_64_after_hwframe+0x49/0xbe

5 locks held by fsync04/25724: #0: ffff99f9911093f8 (sb_writers#13){.+.+}, at: vfs_write+0x21c/0x260 #1: ffff99f9db4c0348 (&sb->s_type->i_mutex_key#15){+.+.}, at: ext4_buffered_write_iter+0x65/0x210 [ext4] #2: ffff99f5e7dfcf58 (jbd2_handle){++++}, at: start_this_handle+0x1c1/0x9d0 [jbd2] #3: ffff99f9db4c0168 (&ei->i_data_sem){++++}, at: ext4_map_blocks+0x176/0x950 [ext4] #4: ffffffff99086b40 (rcu_read_lock){....}, at: jbd2_write_access_granted+0x4e/0x250 [jbd2] irq event stamp: 1407125 hardirqs last enabled at (1407125): [<ffffffff980da9b7>] __find_get_block+0x107/0x790 hardirqs last disabled at (1407124): [<ffffffff980da8f9>] __find_get_block+0x49/0x790 softirqs last enabled at (1405528): [<ffffffff98a0034c>] __do_softirq+0x34c/0x57c softirqs last disabled at (1405521): [<ffffffff97cc67a2>] irq_exit+0xa2/0xc0

Reported by Kernel Concurrency Sanitizer on: CPU: 68 PID: 25724 Comm: fsync04 Tainted: G L 5.6.0-rc2-next-20200221+ #7 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019

The plain reads are outside of jh->b_state_lock critical section which result in data races. Fix them by adding pairs of READ|WRITE_ONCE().

Reviewed-by: Jan Kara jack@suse.cz Signed-off-by: Qian Cai cai@lca.pw Link: https://lore.kernel.org/r/20200222043111.2227-1-cai@lca.pw Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/jbd2/transaction.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index f2ff141a4479e..a355ca418e788 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1050,8 +1050,8 @@ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh, /* For undo access buffer must have data copied */ if (undo && !jh->b_committed_data) goto out; - if (jh->b_transaction != handle->h_transaction && - jh->b_next_transaction != handle->h_transaction) + if (READ_ONCE(jh->b_transaction) != handle->h_transaction && + READ_ONCE(jh->b_next_transaction) != handle->h_transaction) goto out; /* * There are two reasons for the barrier here: @@ -2466,8 +2466,8 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh) * our jh reference and thus __jbd2_journal_file_buffer() must not * take a new one. */ - jh->b_transaction = jh->b_next_transaction; - jh->b_next_transaction = NULL; + WRITE_ONCE(jh->b_transaction, jh->b_next_transaction); + WRITE_ONCE(jh->b_next_transaction, NULL); if (buffer_freed(bh)) jlist = BJ_Forget; else if (jh->b_modified)

From: Kees Cook keescook@chromium.org

commit f87b1c49bc675da30d8e1e8f4b60b800312c7b90 upstream.

When the uaccess .fixup section was renamed to .text.fixup, one case was missed. Under ld.bfd, the orphaned section was moved close to .text (since they share the "ax" bits), so things would work normally on uaccess faults. Under ld.lld, the orphaned section was placed outside the .text section, making it unreachable.

Link: https://github.com/ClangBuiltLinux/linux/issues/282 Link: https://bugs.chromium.org/p/chromium/issues/detail?id=1020633#c44 Link: https://lore.kernel.org/r/nycvar.YSQ.7.76.1912032147340.17114@knanqh.ubzr Link: https://lore.kernel.org/lkml/202002071754.F5F073F1D@keescook/

Fixes: c4a84ae39b4a5 ("ARM: 8322/1: keep .text and .fixup regions closer together") Cc: stable@vger.kernel.org Signed-off-by: Kees Cook keescook@chromium.org Reviewed-by: Ard Biesheuvel ardb@kernel.org Reviewed-by: Nick Desaulniers ndesaulniers@google.com Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/lib/copy_from_user.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/arm/lib/copy_from_user.S +++ b/arch/arm/lib/copy_from_user.S @@ -100,7 +100,7 @@ ENTRY(arm_copy_from_user)

ENDPROC(arm_copy_from_user)

- .pushsection .fixup,"ax" + .pushsection .text.fixup,"ax" .align 0 copy_abort_preamble ldmfd sp!, {r1, r2, r3}

From: Matteo Croce mcroce@redhat.com

commit 3e72dfdf8227b052393f71d820ec7599909dddc2 upstream.

Similarly to commit c543cb4a5f07 ("ipv4: ensure rcu_read_lock() in ipv4_link_failure()"), __ip_options_compile() must be called under rcu protection.

Fixes: 3da1ed7ac398 ("net: avoid use IPCB in cipso_v4_error") Suggested-by: Guillaume Nault gnault@redhat.com Signed-off-by: Matteo Croce mcroce@redhat.com Acked-by: Paul Moore paul@paul-moore.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/ipv4/cipso_ipv4.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

--- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1738,6 +1738,7 @@ void cipso_v4_error(struct sk_buff *skb, { unsigned char optbuf[sizeof(struct ip_options) + 40]; struct ip_options *opt = (struct ip_options *)optbuf; + int res;

if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES) return; @@ -1749,7 +1750,11 @@ void cipso_v4_error(struct sk_buff *skb,

memset(opt, 0, sizeof(struct ip_options)); opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); - if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL)) + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), opt, skb, NULL); + rcu_read_unlock(); + + if (res) return;

if (gateway)