From: David Miller <davem@davemloft.net>
To: stable@vger.kernel.org
Subject: [PATCHES] Networking
Date: Thu, 26 Apr 2018 14:38:48 -0400 (EDT) [thread overview]
Message-ID: <20180426.143848.775817046303070031.davem@davemloft.net> (raw)
[-- Attachment #1: Type: Text/Plain, Size: 107 bytes --]
Please queue up the following networking bug fixes for v4.14 and
v4.16 -stable, respectively.
Thank you.
[-- Attachment #2: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 112995 bytes --]
From 0f41bedcd4ebea2d4af6e1acb19698e32cb06b63 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 22 Apr 2018 19:11:50 +0800
Subject: [PATCH 01/33] bonding: do not set slave_dev npinfo before
slave_enable_netpoll in bond_enslave
[ Upstream commit ddea788c63094f7c483783265563dd5b50052e28 ]
After Commit 8a8efa22f51b ("bonding: sync netpoll code with bridge"), it
would set slave_dev npinfo in slave_enable_netpoll when enslaving a dev
if bond->dev->npinfo was set.
However now slave_dev npinfo is set with bond->dev->npinfo before calling
slave_enable_netpoll. With slave_dev npinfo set, __netpoll_setup called
in slave_enable_netpoll will not call slave dev's .ndo_netpoll_setup().
It causes that the lower dev of this slave dev can't set its npinfo.
One way to reproduce it:
# modprobe bonding
# brctl addbr br0
# brctl addif br0 eth1
# ifconfig bond0 192.168.122.1/24 up
# ifenslave bond0 eth2
# systemctl restart netconsole
# ifenslave bond0 br0
# ifconfig eth2 down
# systemctl restart netconsole
The netpoll won't really work.
This patch is to remove that slave_dev npinfo setting in bond_enslave().
Fixes: 8a8efa22f51b ("bonding: sync netpoll code with bridge")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/bonding/bond_main.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 82f28ffccddf..bf3be2e6d4a8 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1656,8 +1656,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
} /* switch(bond_mode) */
#ifdef CONFIG_NET_POLL_CONTROLLER
- slave_dev->npinfo = bond->dev->npinfo;
- if (slave_dev->npinfo) {
+ if (bond->dev->npinfo) {
if (slave_enable_netpoll(new_slave)) {
netdev_info(bond_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n");
res = -EBUSY;
--
2.14.3
From 0b0a03a3ddff319d6f0556868101a8fbf649fadc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 22 Apr 2018 18:29:23 -0700
Subject: [PATCH 02/33] ipv6: add RTA_TABLE and RTA_PREFSRC to rtm_ipv6_policy
[ Upstream commit aa8f8778493c85fff480cdf8b349b1e1dcb5f243 ]
KMSAN reported use of uninit-value that I tracked to lack
of proper size check on RTA_TABLE attribute.
I also believe RTA_PREFSRC lacks a similar check.
Fixes: 86872cb57925 ("[IPv6] route: FIB6 configuration using struct fib6_config")
Fixes: c3968a857a6b ("ipv6: RTA_PREFSRC support for ipv6 route source address selection")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv6/route.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0126d9bfa670..e04c534b573e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2959,6 +2959,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu)
static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_GATEWAY] = { .len = sizeof(struct in6_addr) },
+ [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) },
[RTA_OIF] = { .type = NLA_U32 },
[RTA_IIF] = { .type = NLA_U32 },
[RTA_PRIORITY] = { .type = NLA_U32 },
@@ -2970,6 +2971,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_EXPIRES] = { .type = NLA_U32 },
[RTA_UID] = { .type = NLA_U32 },
[RTA_MARK] = { .type = NLA_U32 },
+ [RTA_TABLE] = { .type = NLA_U32 },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
--
2.14.3
From 2ccb331449140c7ac08eb9244fa9ef3aa3066f9f Mon Sep 17 00:00:00 2001
From: Ahmed Abdelsalam <amsalam20@gmail.com>
Date: Fri, 20 Apr 2018 15:58:05 +0200
Subject: [PATCH 03/33] ipv6: sr: fix NULL pointer dereference in
seg6_do_srh_encap()- v4 pkts
[ Upstream commit a957fa190aa9d9168b33d460a5241a6d088c6265 ]
In case of seg6 in encap mode, seg6_do_srh_encap() calls set_tun_src()
in order to set the src addr of outer IPv6 header.
The net_device is required for set_tun_src(). However calling ip6_dst_idev()
on dst_entry in case of IPv4 traffic results on the following bug.
Using just dst->dev should fix this BUG.
[ 196.242461] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
[ 196.242975] PGD 800000010f076067 P4D 800000010f076067 PUD 10f060067 PMD 0
[ 196.243329] Oops: 0000 [#1] SMP PTI
[ 196.243468] Modules linked in: nfsd auth_rpcgss nfs_acl nfs lockd grace fscache sunrpc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64 crypto_simd cryptd input_leds glue_helper led_class pcspkr serio_raw mac_hid video autofs4 hid_generic usbhid hid e1000 i2c_piix4 ahci pata_acpi libahci
[ 196.244362] CPU: 2 PID: 1089 Comm: ping Not tainted 4.16.0+ #1
[ 196.244606] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[ 196.244968] RIP: 0010:seg6_do_srh_encap+0x1ac/0x300
[ 196.245236] RSP: 0018:ffffb2ce00b23a60 EFLAGS: 00010202
[ 196.245464] RAX: 0000000000000000 RBX: ffff8c7f53eea300 RCX: 0000000000000000
[ 196.245742] RDX: 0000f10000000000 RSI: ffff8c7f52085a6c RDI: ffff8c7f41166850
[ 196.246018] RBP: ffffb2ce00b23aa8 R08: 00000000000261e0 R09: ffff8c7f41166800
[ 196.246294] R10: ffffdce5040ac780 R11: ffff8c7f41166828 R12: ffff8c7f41166808
[ 196.246570] R13: ffff8c7f52085a44 R14: ffffffffb73211c0 R15: ffff8c7e69e44200
[ 196.246846] FS: 00007fc448789700(0000) GS:ffff8c7f59d00000(0000) knlGS:0000000000000000
[ 196.247286] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 196.247526] CR2: 0000000000000000 CR3: 000000010f05a000 CR4: 00000000000406e0
[ 196.247804] Call Trace:
[ 196.247972] seg6_do_srh+0x15b/0x1c0
[ 196.248156] seg6_output+0x3c/0x220
[ 196.248341] ? prandom_u32+0x14/0x20
[ 196.248526] ? ip_idents_reserve+0x6c/0x80
[ 196.248723] ? __ip_select_ident+0x90/0x100
[ 196.248923] ? ip_append_data.part.50+0x6c/0xd0
[ 196.249133] lwtunnel_output+0x44/0x70
[ 196.249328] ip_send_skb+0x15/0x40
[ 196.249515] raw_sendmsg+0x8c3/0xac0
[ 196.249701] ? _copy_from_user+0x2e/0x60
[ 196.249897] ? rw_copy_check_uvector+0x53/0x110
[ 196.250106] ? _copy_from_user+0x2e/0x60
[ 196.250299] ? copy_msghdr_from_user+0xce/0x140
[ 196.250508] sock_sendmsg+0x36/0x40
[ 196.250690] ___sys_sendmsg+0x292/0x2a0
[ 196.250881] ? _cond_resched+0x15/0x30
[ 196.251074] ? copy_termios+0x1e/0x70
[ 196.251261] ? _copy_to_user+0x22/0x30
[ 196.251575] ? tty_mode_ioctl+0x1c3/0x4e0
[ 196.251782] ? _cond_resched+0x15/0x30
[ 196.251972] ? mutex_lock+0xe/0x30
[ 196.252152] ? vvar_fault+0xd2/0x110
[ 196.252337] ? __do_fault+0x1f/0xc0
[ 196.252521] ? __handle_mm_fault+0xc1f/0x12d0
[ 196.252727] ? __sys_sendmsg+0x63/0xa0
[ 196.252919] __sys_sendmsg+0x63/0xa0
[ 196.253107] do_syscall_64+0x72/0x200
[ 196.253305] entry_SYSCALL_64_after_hwframe+0x3d/0xa2
[ 196.253530] RIP: 0033:0x7fc4480b0690
[ 196.253715] RSP: 002b:00007ffde9f252f8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[ 196.254053] RAX: ffffffffffffffda RBX: 0000000000000040 RCX: 00007fc4480b0690
[ 196.254331] RDX: 0000000000000000 RSI: 000000000060a360 RDI: 0000000000000003
[ 196.254608] RBP: 00007ffde9f253f0 R08: 00000000002d1e81 R09: 0000000000000002
[ 196.254884] R10: 00007ffde9f250c0 R11: 0000000000000246 R12: 0000000000b22070
[ 196.255205] R13: 20c49ba5e353f7cf R14: 431bde82d7b634db R15: 00007ffde9f278fe
[ 196.255484] Code: a5 0f b6 45 c0 41 88 41 28 41 0f b6 41 2c 48 c1 e0 04 49 8b 54 01 38 49 8b 44 01 30 49 89 51 20 49 89 41 18 48 8b 83 b0 00 00 00 <48> 8b 30 49 8b 86 08 0b 00 00 48 8b 40 20 48 8b 50 08 48 0b 10
[ 196.256190] RIP: seg6_do_srh_encap+0x1ac/0x300 RSP: ffffb2ce00b23a60
[ 196.256445] CR2: 0000000000000000
[ 196.256676] ---[ end trace 71af7d093603885c ]---
Fixes: 8936ef7604c11 ("ipv6: sr: fix NULL pointer dereference when setting encap source address")
Signed-off-by: Ahmed Abdelsalam <amsalam20@gmail.com>
Acked-by: David Lebrun <dlebrun@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv6/seg6_iptunnel.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index f343e6f0fc95..5fe139484919 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -136,7 +136,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
isrh->nexthdr = proto;
hdr->daddr = isrh->segments[isrh->first_segment];
- set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr);
+ set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr);
#ifdef CONFIG_IPV6_SEG6_HMAC
if (sr_has_hmac(isrh)) {
--
2.14.3
From c52e938d723a063e89e9c0bed593694fab5f3663 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 17 Apr 2018 12:07:06 -0700
Subject: [PATCH 04/33] KEYS: DNS: limit the length of option strings
[ Upstream commit 9c438d7a3a52dcc2b9ed095cb87d3a5e83cf7e60 ]
Adding a dns_resolver key whose payload contains a very long option name
resulted in that string being printed in full. This hit the WARN_ONCE()
in set_precision() during the printk(), because printk() only supports a
precision of up to 32767 bytes:
precision 1000000 too large
WARNING: CPU: 0 PID: 752 at lib/vsprintf.c:2189 vsnprintf+0x4bc/0x5b0
Fix it by limiting option strings (combined name + value) to a much more
reasonable 128 bytes. The exact limit is arbitrary, but currently the
only recognized option is formatted as "dnserror=%lu" which fits well
within this limit.
Also ratelimit the printks.
Reproducer:
perl -e 'print "#", "A" x 1000000, "\x00"' | keyctl padd dns_resolver desc @s
This bug was found using syzkaller.
Reported-by: Mark Rutland <mark.rutland@arm.com>
Fixes: 4a2d789267e0 ("DNS: If the DNS server returns an error, allow that to be cached [ver #2]")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/dns_resolver/dns_key.c | 13 ++++++-------
1 file changed, 6 insertions(+), 7 deletions(-)
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index e1d4d898a007..f0252768ecf4 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -25,6 +25,7 @@
#include <linux/moduleparam.h>
#include <linux/slab.h>
#include <linux/string.h>
+#include <linux/ratelimit.h>
#include <linux/kernel.h>
#include <linux/keyctl.h>
#include <linux/err.h>
@@ -91,9 +92,9 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
next_opt = memchr(opt, '#', end - opt) ?: end;
opt_len = next_opt - opt;
- if (!opt_len) {
- printk(KERN_WARNING
- "Empty option to dns_resolver key\n");
+ if (opt_len <= 0 || opt_len > 128) {
+ pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n",
+ opt_len);
return -EINVAL;
}
@@ -127,10 +128,8 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
}
bad_option_value:
- printk(KERN_WARNING
- "Option '%*.*s' to dns_resolver key:"
- " bad/missing value\n",
- opt_nlen, opt_nlen, opt);
+ pr_warn_ratelimited("Option '%*.*s' to dns_resolver key: bad/missing value\n",
+ opt_nlen, opt_nlen, opt);
return -EINVAL;
} while (opt = next_opt + 1, opt < end);
}
--
2.14.3
From 2b566dcfedba6a04e85bc70ceace0c40765e34c6 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 23 Apr 2018 16:15:14 +0200
Subject: [PATCH 05/33] l2tp: check sockaddr length in pppol2tp_connect()
[ Upstream commit eb1c28c05894a4b1f6b56c5bf072205e64cfa280 ]
Check sockaddr_len before dereferencing sp->sa_protocol, to ensure that
it actually points to valid data.
Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Reported-by: syzbot+a70ac890b23b1bf29f5c@syzkaller.appspotmail.com
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/l2tp/l2tp_ppp.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 0c2738349442..8bef35aa8786 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -591,6 +591,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
lock_sock(sk);
error = -EINVAL;
+
+ if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6))
+ goto end;
+
if (sp->sa_protocol != PX_PROTO_OL2TP)
goto end;
--
2.14.3
From 89e84adfedded9fecf6a331891d0f42f090e5600 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Apr 2018 14:46:00 -0700
Subject: [PATCH 06/33] net: validate attribute sizes in neigh_dump_table()
[ Upstream commit 7dd07c143a4b54d050e748bee4b4b9e94a7b1744 ]
Since neigh_dump_table() calls nlmsg_parse() without giving policy
constraints, attributes can have arbirary size that we must validate
Reported by syzbot/KMSAN :
BUG: KMSAN: uninit-value in neigh_master_filtered net/core/neighbour.c:2292 [inline]
BUG: KMSAN: uninit-value in neigh_dump_table net/core/neighbour.c:2348 [inline]
BUG: KMSAN: uninit-value in neigh_dump_info+0x1af0/0x2250 net/core/neighbour.c:2438
CPU: 1 PID: 3575 Comm: syzkaller268891 Not tainted 4.16.0+ #83
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:17 [inline]
dump_stack+0x185/0x1d0 lib/dump_stack.c:53
kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
__msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
neigh_master_filtered net/core/neighbour.c:2292 [inline]
neigh_dump_table net/core/neighbour.c:2348 [inline]
neigh_dump_info+0x1af0/0x2250 net/core/neighbour.c:2438
netlink_dump+0x9ad/0x1540 net/netlink/af_netlink.c:2225
__netlink_dump_start+0x1167/0x12a0 net/netlink/af_netlink.c:2322
netlink_dump_start include/linux/netlink.h:214 [inline]
rtnetlink_rcv_msg+0x1435/0x1560 net/core/rtnetlink.c:4598
netlink_rcv_skb+0x355/0x5f0 net/netlink/af_netlink.c:2447
rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4653
netlink_unicast_kernel net/netlink/af_netlink.c:1311 [inline]
netlink_unicast+0x1672/0x1750 net/netlink/af_netlink.c:1337
netlink_sendmsg+0x1048/0x1310 net/netlink/af_netlink.c:1900
sock_sendmsg_nosec net/socket.c:630 [inline]
sock_sendmsg net/socket.c:640 [inline]
___sys_sendmsg+0xec0/0x1310 net/socket.c:2046
__sys_sendmsg net/socket.c:2080 [inline]
SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091
SyS_sendmsg+0x54/0x80 net/socket.c:2087
do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x43fed9
RSP: 002b:00007ffddbee2798 EFLAGS: 00000213 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043fed9
RDX: 0000000000000000 RSI: 0000000020005000 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 00000000004002c8 R09: 00000000004002c8
R10: 00000000004002c8 R11: 0000000000000213 R12: 0000000000401800
R13: 0000000000401890 R14: 0000000000000000 R15: 0000000000000000
Uninit was created at:
kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188
kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314
kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321
slab_post_alloc_hook mm/slab.h:445 [inline]
slab_alloc_node mm/slub.c:2737 [inline]
__kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369
__kmalloc_reserve net/core/skbuff.c:138 [inline]
__alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206
alloc_skb include/linux/skbuff.h:984 [inline]
netlink_alloc_large_skb net/netlink/af_netlink.c:1183 [inline]
netlink_sendmsg+0x9a6/0x1310 net/netlink/af_netlink.c:1875
sock_sendmsg_nosec net/socket.c:630 [inline]
sock_sendmsg net/socket.c:640 [inline]
___sys_sendmsg+0xec0/0x1310 net/socket.c:2046
__sys_sendmsg net/socket.c:2080 [inline]
SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091
SyS_sendmsg+0x54/0x80 net/socket.c:2087
do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
Fixes: 21fdd092acc7 ("net: Add support for filtering neigh dump by master device")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: David Ahern <dsa@cumulusnetworks.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/neighbour.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 741ae2554190..a209d834daa2 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2323,12 +2323,16 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL, NULL);
if (!err) {
- if (tb[NDA_IFINDEX])
+ if (tb[NDA_IFINDEX]) {
+ if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32))
+ return -EINVAL;
filter_idx = nla_get_u32(tb[NDA_IFINDEX]);
-
- if (tb[NDA_MASTER])
+ }
+ if (tb[NDA_MASTER]) {
+ if (nla_len(tb[NDA_MASTER]) != sizeof(u32))
+ return -EINVAL;
filter_master_idx = nla_get_u32(tb[NDA_MASTER]);
-
+ }
if (filter_idx || filter_master_idx)
flags |= NLM_F_DUMP_FILTERED;
}
--
2.14.3
From 99a40e31a7c245452f17bfc43efcf14ee436912b Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 19 Apr 2018 12:25:38 -0700
Subject: [PATCH 07/33] llc: delete timers synchronously in llc_sk_free()
[ Upstream commit b905ef9ab90115d001c1658259af4b1c65088779 ]
The connection timers of an llc sock could be still flying
after we delete them in llc_sk_free(), and even possibly
after we free the sock. We could just wait synchronously
here in case of troubles.
Note, I leave other call paths as they are, since they may
not have to wait, at least we can change them to synchronously
when needed.
Also, move the code to net/llc/llc_conn.c, which is apparently
a better place.
Reported-by: <syzbot+f922284c18ea23a8e457@syzkaller.appspotmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/llc_conn.h | 1 +
net/llc/llc_c_ac.c | 9 +--------
net/llc/llc_conn.c | 22 +++++++++++++++++++++-
3 files changed, 23 insertions(+), 9 deletions(-)
diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h
index fe994d2e5286..ea985aa7a6c5 100644
--- a/include/net/llc_conn.h
+++ b/include/net/llc_conn.h
@@ -97,6 +97,7 @@ static __inline__ char llc_backlog_type(struct sk_buff *skb)
struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority,
struct proto *prot, int kern);
+void llc_sk_stop_all_timers(struct sock *sk, bool sync);
void llc_sk_free(struct sock *sk);
void llc_sk_reset(struct sock *sk);
diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c
index ea225bd2672c..f8d4ab8ca1a5 100644
--- a/net/llc/llc_c_ac.c
+++ b/net/llc/llc_c_ac.c
@@ -1096,14 +1096,7 @@ int llc_conn_ac_inc_tx_win_size(struct sock *sk, struct sk_buff *skb)
int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb)
{
- struct llc_sock *llc = llc_sk(sk);
-
- del_timer(&llc->pf_cycle_timer.timer);
- del_timer(&llc->ack_timer.timer);
- del_timer(&llc->rej_sent_timer.timer);
- del_timer(&llc->busy_state_timer.timer);
- llc->ack_must_be_send = 0;
- llc->ack_pf = 0;
+ llc_sk_stop_all_timers(sk, false);
return 0;
}
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 5e91b47f0d2a..9a42448eb182 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -951,6 +951,26 @@ struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority, struct pr
return sk;
}
+void llc_sk_stop_all_timers(struct sock *sk, bool sync)
+{
+ struct llc_sock *llc = llc_sk(sk);
+
+ if (sync) {
+ del_timer_sync(&llc->pf_cycle_timer.timer);
+ del_timer_sync(&llc->ack_timer.timer);
+ del_timer_sync(&llc->rej_sent_timer.timer);
+ del_timer_sync(&llc->busy_state_timer.timer);
+ } else {
+ del_timer(&llc->pf_cycle_timer.timer);
+ del_timer(&llc->ack_timer.timer);
+ del_timer(&llc->rej_sent_timer.timer);
+ del_timer(&llc->busy_state_timer.timer);
+ }
+
+ llc->ack_must_be_send = 0;
+ llc->ack_pf = 0;
+}
+
/**
* llc_sk_free - Frees a LLC socket
* @sk - socket to free
@@ -963,7 +983,7 @@ void llc_sk_free(struct sock *sk)
llc->state = LLC_CONN_OUT_OF_SVC;
/* Stop all (possibly) running timers */
- llc_conn_ac_stop_all_timers(sk, NULL);
+ llc_sk_stop_all_timers(sk, true);
#ifdef DEBUG_LLC_CONN_ALLOC
printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__,
skb_queue_len(&llc->pdu_unack_q),
--
2.14.3
From 4f62f59f792fa9cea140486e3baa551d9297eaf8 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Fri, 20 Apr 2018 15:57:30 +0200
Subject: [PATCH 08/33] tcp: don't read out-of-bounds opsize
[ Upstream commit 7e5a206ab686f098367b61aca989f5cdfa8114a3 ]
The old code reads the "opsize" variable from out-of-bounds memory (first
byte behind the segment) if a broken TCP segment ends directly after an
opcode that is neither EOL nor NOP.
The result of the read isn't used for anything, so the worst thing that
could theoretically happen is a pagefault; and since the physmap is usually
mostly contiguous, even that seems pretty unlikely.
The following C reproducer triggers the uninitialized read - however, you
can't actually see anything happen unless you put something like a
pr_warn() in tcp_parse_md5sig_option() to print the opsize.
====================================
#define _GNU_SOURCE
#include <arpa/inet.h>
#include <stdlib.h>
#include <errno.h>
#include <stdarg.h>
#include <net/if.h>
#include <linux/if.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/in.h>
#include <linux/if_tun.h>
#include <err.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <string.h>
#include <stdio.h>
#include <unistd.h>
#include <sys/ioctl.h>
#include <assert.h>
void systemf(const char *command, ...) {
char *full_command;
va_list ap;
va_start(ap, command);
if (vasprintf(&full_command, command, ap) == -1)
err(1, "vasprintf");
va_end(ap);
printf("systemf: <<<%s>>>\n", full_command);
system(full_command);
}
char *devname;
int tun_alloc(char *name) {
int fd = open("/dev/net/tun", O_RDWR);
if (fd == -1)
err(1, "open tun dev");
static struct ifreq req = { .ifr_flags = IFF_TUN|IFF_NO_PI };
strcpy(req.ifr_name, name);
if (ioctl(fd, TUNSETIFF, &req))
err(1, "TUNSETIFF");
devname = req.ifr_name;
printf("device name: %s\n", devname);
return fd;
}
#define IPADDR(a,b,c,d) (((a)<<0)+((b)<<8)+((c)<<16)+((d)<<24))
void sum_accumulate(unsigned int *sum, void *data, int len) {
assert((len&2)==0);
for (int i=0; i<len/2; i++) {
*sum += ntohs(((unsigned short *)data)[i]);
}
}
unsigned short sum_final(unsigned int sum) {
sum = (sum >> 16) + (sum & 0xffff);
sum = (sum >> 16) + (sum & 0xffff);
return htons(~sum);
}
void fix_ip_sum(struct iphdr *ip) {
unsigned int sum = 0;
sum_accumulate(&sum, ip, sizeof(*ip));
ip->check = sum_final(sum);
}
void fix_tcp_sum(struct iphdr *ip, struct tcphdr *tcp) {
unsigned int sum = 0;
struct {
unsigned int saddr;
unsigned int daddr;
unsigned char pad;
unsigned char proto_num;
unsigned short tcp_len;
} fakehdr = {
.saddr = ip->saddr,
.daddr = ip->daddr,
.proto_num = ip->protocol,
.tcp_len = htons(ntohs(ip->tot_len) - ip->ihl*4)
};
sum_accumulate(&sum, &fakehdr, sizeof(fakehdr));
sum_accumulate(&sum, tcp, tcp->doff*4);
tcp->check = sum_final(sum);
}
int main(void) {
int tun_fd = tun_alloc("inject_dev%d");
systemf("ip link set %s up", devname);
systemf("ip addr add 192.168.42.1/24 dev %s", devname);
struct {
struct iphdr ip;
struct tcphdr tcp;
unsigned char tcp_opts[20];
} __attribute__((packed)) syn_packet = {
.ip = {
.ihl = sizeof(struct iphdr)/4,
.version = 4,
.tot_len = htons(sizeof(syn_packet)),
.ttl = 30,
.protocol = IPPROTO_TCP,
/* FIXUP check */
.saddr = IPADDR(192,168,42,2),
.daddr = IPADDR(192,168,42,1)
},
.tcp = {
.source = htons(1),
.dest = htons(1337),
.seq = 0x12345678,
.doff = (sizeof(syn_packet.tcp)+sizeof(syn_packet.tcp_opts))/4,
.syn = 1,
.window = htons(64),
.check = 0 /*FIXUP*/
},
.tcp_opts = {
/* INVALID: trailing MD5SIG opcode after NOPs */
1, 1, 1, 1, 1,
1, 1, 1, 1, 1,
1, 1, 1, 1, 1,
1, 1, 1, 1, 19
}
};
fix_ip_sum(&syn_packet.ip);
fix_tcp_sum(&syn_packet.ip, &syn_packet.tcp);
while (1) {
int write_res = write(tun_fd, &syn_packet, sizeof(syn_packet));
if (write_res != sizeof(syn_packet))
err(1, "packet write failed");
}
}
====================================
Fixes: cfb6eeb4c860 ("[TCP]: MD5 Signature Option (RFC2385) support.")
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/tcp_input.c | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 14474acea0bb..ebbb54bcbcac 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3892,11 +3892,8 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th)
int length = (th->doff << 2) - sizeof(*th);
const u8 *ptr = (const u8 *)(th + 1);
- /* If the TCP option is too short, we can short cut */
- if (length < TCPOLEN_MD5SIG)
- return NULL;
-
- while (length > 0) {
+ /* If not enough data remaining, we can short cut */
+ while (length >= TCPOLEN_MD5SIG) {
int opcode = *ptr++;
int opsize;
--
2.14.3
From 823b572fd268380adcf60207be5a7797bfe7065e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 15 Apr 2018 17:52:04 -0700
Subject: [PATCH 09/33] net: af_packet: fix race in PACKET_{R|T}X_RING
[ Upstream commit 5171b37d959641bbc619781caf62e61f7b940871 ]
In order to remove the race caught by syzbot [1], we need
to lock the socket before using po->tp_version as this could
change under us otherwise.
This means lock_sock() and release_sock() must be done by
packet_set_ring() callers.
[1] :
BUG: KMSAN: uninit-value in packet_set_ring+0x1254/0x3870 net/packet/af_packet.c:4249
CPU: 0 PID: 20195 Comm: syzkaller707632 Not tainted 4.16.0+ #83
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:17 [inline]
dump_stack+0x185/0x1d0 lib/dump_stack.c:53
kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
__msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
packet_set_ring+0x1254/0x3870 net/packet/af_packet.c:4249
packet_setsockopt+0x12c6/0x5a90 net/packet/af_packet.c:3662
SYSC_setsockopt+0x4b8/0x570 net/socket.c:1849
SyS_setsockopt+0x76/0xa0 net/socket.c:1828
do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x449099
RSP: 002b:00007f42b5307ce8 EFLAGS: 00000246 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 000000000070003c RCX: 0000000000449099
RDX: 0000000000000005 RSI: 0000000000000107 RDI: 0000000000000003
RBP: 0000000000700038 R08: 000000000000001c R09: 0000000000000000
R10: 00000000200000c0 R11: 0000000000000246 R12: 0000000000000000
R13: 000000000080eecf R14: 00007f42b53089c0 R15: 0000000000000001
Local variable description: ----req_u@packet_setsockopt
Variable was created at:
packet_setsockopt+0x13f/0x5a90 net/packet/af_packet.c:3612
SYSC_setsockopt+0x4b8/0x570 net/socket.c:1849
Fixes: f6fb8f100b80 ("af-packet: TPACKET_V3 flexible buffer implementation.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/packet/af_packet.c | 23 ++++++++++++++---------
1 file changed, 14 insertions(+), 9 deletions(-)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index f4a0587b7d5e..e829f4065dbf 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3017,6 +3017,7 @@ static int packet_release(struct socket *sock)
packet_flush_mclist(sk);
+ lock_sock(sk);
if (po->rx_ring.pg_vec) {
memset(&req_u, 0, sizeof(req_u));
packet_set_ring(sk, &req_u, 1, 0);
@@ -3026,6 +3027,7 @@ static int packet_release(struct socket *sock)
memset(&req_u, 0, sizeof(req_u));
packet_set_ring(sk, &req_u, 1, 1);
}
+ release_sock(sk);
f = fanout_release(sk);
@@ -3654,6 +3656,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
union tpacket_req_u req_u;
int len;
+ lock_sock(sk);
switch (po->tp_version) {
case TPACKET_V1:
case TPACKET_V2:
@@ -3664,12 +3667,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
len = sizeof(req_u.req3);
break;
}
- if (optlen < len)
- return -EINVAL;
- if (copy_from_user(&req_u.req, optval, len))
- return -EFAULT;
- return packet_set_ring(sk, &req_u, 0,
- optname == PACKET_TX_RING);
+ if (optlen < len) {
+ ret = -EINVAL;
+ } else {
+ if (copy_from_user(&req_u.req, optval, len))
+ ret = -EFAULT;
+ else
+ ret = packet_set_ring(sk, &req_u, 0,
+ optname == PACKET_TX_RING);
+ }
+ release_sock(sk);
+ return ret;
}
case PACKET_COPY_THRESH:
{
@@ -4219,8 +4227,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
/* Added to avoid minimal code churn */
struct tpacket_req *req = &req_u->req;
- lock_sock(sk);
-
rb = tx_ring ? &po->tx_ring : &po->rx_ring;
rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
@@ -4358,7 +4364,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
if (pg_vec)
free_pg_vec(pg_vec, order, req->tp_block_nr);
out:
- release_sock(sk);
return err;
}
--
2.14.3
From 80420d8f253d07532e645642df17babe950a734a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Apr 2018 14:36:28 -0700
Subject: [PATCH 10/33] tcp: md5: reject TCP_MD5SIG or TCP_MD5SIG_EXT on
established sockets
[ Upstream commit 7212303268918b9a203aebeacfdbd83b5e87b20d ]
syzbot/KMSAN reported an uninit-value in tcp_parse_options() [1]
I believe this was caused by a TCP_MD5SIG being set on live
flow.
This is highly unexpected, since TCP option space is limited.
For instance, presence of TCP MD5 option automatically disables
TCP TimeStamp option at SYN/SYNACK time, which we can not do
once flow has been established.
Really, adding/deleting an MD5 key only makes sense on sockets
in CLOSE or LISTEN state.
[1]
BUG: KMSAN: uninit-value in tcp_parse_options+0xd74/0x1a30 net/ipv4/tcp_input.c:3720
CPU: 1 PID: 6177 Comm: syzkaller192004 Not tainted 4.16.0+ #83
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:17 [inline]
dump_stack+0x185/0x1d0 lib/dump_stack.c:53
kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
__msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
tcp_parse_options+0xd74/0x1a30 net/ipv4/tcp_input.c:3720
tcp_fast_parse_options net/ipv4/tcp_input.c:3858 [inline]
tcp_validate_incoming+0x4f1/0x2790 net/ipv4/tcp_input.c:5184
tcp_rcv_established+0xf60/0x2bb0 net/ipv4/tcp_input.c:5453
tcp_v4_do_rcv+0x6cd/0xd90 net/ipv4/tcp_ipv4.c:1469
sk_backlog_rcv include/net/sock.h:908 [inline]
__release_sock+0x2d6/0x680 net/core/sock.c:2271
release_sock+0x97/0x2a0 net/core/sock.c:2786
tcp_sendmsg+0xd6/0x100 net/ipv4/tcp.c:1464
inet_sendmsg+0x48d/0x740 net/ipv4/af_inet.c:764
sock_sendmsg_nosec net/socket.c:630 [inline]
sock_sendmsg net/socket.c:640 [inline]
SYSC_sendto+0x6c3/0x7e0 net/socket.c:1747
SyS_sendto+0x8a/0xb0 net/socket.c:1715
do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x448fe9
RSP: 002b:00007fd472c64d38 EFLAGS: 00000216 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00000000006e5a30 RCX: 0000000000448fe9
RDX: 000000000000029f RSI: 0000000020a88f88 RDI: 0000000000000004
RBP: 00000000006e5a34 R08: 0000000020e68000 R09: 0000000000000010
R10: 00000000200007fd R11: 0000000000000216 R12: 0000000000000000
R13: 00007fff074899ef R14: 00007fd472c659c0 R15: 0000000000000009
Uninit was created at:
kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188
kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314
kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321
slab_post_alloc_hook mm/slab.h:445 [inline]
slab_alloc_node mm/slub.c:2737 [inline]
__kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369
__kmalloc_reserve net/core/skbuff.c:138 [inline]
__alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206
alloc_skb include/linux/skbuff.h:984 [inline]
tcp_send_ack+0x18c/0x910 net/ipv4/tcp_output.c:3624
__tcp_ack_snd_check net/ipv4/tcp_input.c:5040 [inline]
tcp_ack_snd_check net/ipv4/tcp_input.c:5053 [inline]
tcp_rcv_established+0x2103/0x2bb0 net/ipv4/tcp_input.c:5469
tcp_v4_do_rcv+0x6cd/0xd90 net/ipv4/tcp_ipv4.c:1469
sk_backlog_rcv include/net/sock.h:908 [inline]
__release_sock+0x2d6/0x680 net/core/sock.c:2271
release_sock+0x97/0x2a0 net/core/sock.c:2786
tcp_sendmsg+0xd6/0x100 net/ipv4/tcp.c:1464
inet_sendmsg+0x48d/0x740 net/ipv4/af_inet.c:764
sock_sendmsg_nosec net/socket.c:630 [inline]
sock_sendmsg net/socket.c:640 [inline]
SYSC_sendto+0x6c3/0x7e0 net/socket.c:1747
SyS_sendto+0x8a/0xb0 net/socket.c:1715
do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
Fixes: cfb6eeb4c860 ("[TCP]: MD5 Signature Option (RFC2385) support.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/tcp.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 38b9a6276a9d..e8d8140cd33f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2742,8 +2742,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
#ifdef CONFIG_TCP_MD5SIG
case TCP_MD5SIG:
case TCP_MD5SIG_EXT:
- /* Read the IP->Key mappings from userspace */
- err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
+ if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
+ err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
+ else
+ err = -EINVAL;
break;
#endif
case TCP_USER_TIMEOUT:
--
2.14.3
From 53979b376e60f8cedfad7a8adeff6efa33fc022d Mon Sep 17 00:00:00 2001
From: Wolfgang Bumiller <w.bumiller@proxmox.com>
Date: Thu, 12 Apr 2018 10:46:55 +0200
Subject: [PATCH 11/33] net: fix deadlock while clearing neighbor proxy table
[ Upstream commit 53b76cdf7e8fecec1d09e38aad2f8579882591a8 ]
When coming from ndisc_netdev_event() in net/ipv6/ndisc.c,
neigh_ifdown() is called with &nd_tbl, locking this while
clearing the proxy neighbor entries when eg. deleting an
interface. Calling the table's pndisc_destructor() with the
lock still held, however, can cause a deadlock: When a
multicast listener is available an IGMP packet of type
ICMPV6_MGM_REDUCTION may be sent out. When reaching
ip6_finish_output2(), if no neighbor entry for the target
address is found, __neigh_create() is called with &nd_tbl,
which it'll want to lock.
Move the elements into their own list, then unlock the table
and perform the destruction.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=199289
Fixes: 6fd6ce2056de ("ipv6: Do not depend on rt->n in ip6_finish_output2().")
Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/neighbour.c | 28 ++++++++++++++++++----------
1 file changed, 18 insertions(+), 10 deletions(-)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index a209d834daa2..514d697d4691 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -55,7 +55,8 @@ static void neigh_timer_handler(unsigned long arg);
static void __neigh_notify(struct neighbour *n, int type, int flags,
u32 pid);
static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid);
-static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
+static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
+ struct net_device *dev);
#ifdef CONFIG_PROC_FS
static const struct file_operations neigh_stat_seq_fops;
@@ -291,8 +292,7 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
{
write_lock_bh(&tbl->lock);
neigh_flush_dev(tbl, dev);
- pneigh_ifdown(tbl, dev);
- write_unlock_bh(&tbl->lock);
+ pneigh_ifdown_and_unlock(tbl, dev);
del_timer_sync(&tbl->proxy_timer);
pneigh_queue_purge(&tbl->proxy_queue);
@@ -681,9 +681,10 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey,
return -ENOENT;
}
-static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
+static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
+ struct net_device *dev)
{
- struct pneigh_entry *n, **np;
+ struct pneigh_entry *n, **np, *freelist = NULL;
u32 h;
for (h = 0; h <= PNEIGH_HASHMASK; h++) {
@@ -691,16 +692,23 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
while ((n = *np) != NULL) {
if (!dev || n->dev == dev) {
*np = n->next;
- if (tbl->pdestructor)
- tbl->pdestructor(n);
- if (n->dev)
- dev_put(n->dev);
- kfree(n);
+ n->next = freelist;
+ freelist = n;
continue;
}
np = &n->next;
}
}
+ write_unlock_bh(&tbl->lock);
+ while ((n = freelist)) {
+ freelist = n->next;
+ n->next = NULL;
+ if (tbl->pdestructor)
+ tbl->pdestructor(n);
+ if (n->dev)
+ dev_put(n->dev);
+ kfree(n);
+ }
return -ENOENT;
}
--
2.14.3
From d50bdc53151e33ede3068aeabab651e96dbccc81 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 13 Apr 2018 13:59:25 +0200
Subject: [PATCH 12/33] team: avoid adding twice the same option to the event
list
[ Upstream commit 4fb0534fb7bbc2346ba7d3a072b538007f4135a5 ]
When parsing the options provided by the user space,
team_nl_cmd_options_set() insert them in a temporary list to send
multiple events with a single message.
While each option's attribute is correctly validated, the code does
not check for duplicate entries before inserting into the event
list.
Exploiting the above, the syzbot was able to trigger the following
splat:
kernel BUG at lib/list_debug.c:31!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
(ftrace buffer empty)
Modules linked in:
CPU: 0 PID: 4466 Comm: syzkaller556835 Not tainted 4.16.0+ #17
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
RIP: 0010:__list_add_valid+0xaa/0xb0 lib/list_debug.c:29
RSP: 0018:ffff8801b04bf248 EFLAGS: 00010286
RAX: 0000000000000058 RBX: ffff8801c8fc7a90 RCX: 0000000000000000
RDX: 0000000000000058 RSI: ffffffff815fbf41 RDI: ffffed0036097e3f
RBP: ffff8801b04bf260 R08: ffff8801b0b2a700 R09: ffffed003b604f90
R10: ffffed003b604f90 R11: ffff8801db027c87 R12: ffff8801c8fc7a90
R13: ffff8801c8fc7a90 R14: dffffc0000000000 R15: 0000000000000000
FS: 0000000000b98880(0000) GS:ffff8801db000000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000000043fc30 CR3: 00000001afe8e000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
__list_add include/linux/list.h:60 [inline]
list_add include/linux/list.h:79 [inline]
team_nl_cmd_options_set+0x9ff/0x12b0 drivers/net/team/team.c:2571
genl_family_rcv_msg+0x889/0x1120 net/netlink/genetlink.c:599
genl_rcv_msg+0xc6/0x170 net/netlink/genetlink.c:624
netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2448
genl_rcv+0x28/0x40 net/netlink/genetlink.c:635
netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
netlink_unicast+0x58b/0x740 net/netlink/af_netlink.c:1336
netlink_sendmsg+0x9f0/0xfa0 net/netlink/af_netlink.c:1901
sock_sendmsg_nosec net/socket.c:629 [inline]
sock_sendmsg+0xd5/0x120 net/socket.c:639
___sys_sendmsg+0x805/0x940 net/socket.c:2117
__sys_sendmsg+0x115/0x270 net/socket.c:2155
SYSC_sendmsg net/socket.c:2164 [inline]
SyS_sendmsg+0x29/0x30 net/socket.c:2162
do_syscall_64+0x29e/0x9d0 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x4458b9
RSP: 002b:00007ffd1d4a7278 EFLAGS: 00000213 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 000000000000001b RCX: 00000000004458b9
RDX: 0000000000000010 RSI: 0000000020000d00 RDI: 0000000000000004
RBP: 00000000004a74ed R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000213 R12: 00007ffd1d4a7348
R13: 0000000000402a60 R14: 0000000000000000 R15: 0000000000000000
Code: 75 e8 eb a9 48 89 f7 48 89 75 e8 e8 d1 85 7b fe 48 8b 75 e8 eb bb 48
89 f2 48 89 d9 4c 89 e6 48 c7 c7 a0 84 d8 87 e8 ea 67 28 fe <0f> 0b 0f 1f
40 00 48 b8 00 00 00 00 00 fc ff df 55 48 89 e5 41
RIP: __list_add_valid+0xaa/0xb0 lib/list_debug.c:29 RSP: ffff8801b04bf248
This changeset addresses the avoiding list_add() if the current
option is already present in the event list.
Reported-and-tested-by: syzbot+4d4af685432dc0e56c91@syzkaller.appspotmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Fixes: 2fcdb2c9e659 ("team: allow to send multiple set events in one message")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/team/team.c | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 2a366554c503..91a0209756d5 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -261,6 +261,17 @@ static void __team_option_inst_mark_removed_port(struct team *team,
}
}
+static bool __team_option_inst_tmp_find(const struct list_head *opts,
+ const struct team_option_inst *needle)
+{
+ struct team_option_inst *opt_inst;
+
+ list_for_each_entry(opt_inst, opts, tmp_list)
+ if (opt_inst == needle)
+ return true;
+ return false;
+}
+
static int __team_options_register(struct team *team,
const struct team_option *option,
size_t option_count)
@@ -2561,6 +2572,14 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
if (err)
goto team_put;
opt_inst->changed = true;
+
+ /* dumb/evil user-space can send us duplicate opt,
+ * keep only the last one
+ */
+ if (__team_option_inst_tmp_find(&opt_inst_list,
+ opt_inst))
+ continue;
+
list_add(&opt_inst->tmp_list, &opt_inst_list);
}
if (!opt_found) {
--
2.14.3
From 86ebbd49923a1558295f5f26d08274e3530342cc Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.vnet.ibm.com>
Date: Thu, 19 Apr 2018 15:56:40 +0200
Subject: [PATCH 13/33] net/smc: fix shutdown in state SMC_LISTEN
[ Upstream commit 1255fcb2a655f05e02f3a74675a6d6525f187afd ]
Calling shutdown with SHUT_RD and SHUT_RDWR for a listening SMC socket
crashes, because
commit 127f49705823 ("net/smc: release clcsock from tcp_listen_worker")
releases the internal clcsock in smc_close_active() and sets smc->clcsock
to NULL.
For SHUT_RD the smc_close_active() call is removed.
For SHUT_RDWR the kernel_sock_shutdown() call is omitted, since the
clcsock is already released.
Fixes: 127f49705823 ("net/smc: release clcsock from tcp_listen_worker")
Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Reported-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/smc/af_smc.c | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index a6d604fd9695..f9c289e05707 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1203,14 +1203,12 @@ static int smc_shutdown(struct socket *sock, int how)
rc = smc_close_shutdown_write(smc);
break;
case SHUT_RD:
- if (sk->sk_state == SMC_LISTEN)
- rc = smc_close_active(smc);
- else
- rc = 0;
- /* nothing more to do because peer is not involved */
+ rc = 0;
+ /* nothing more to do because peer is not involved */
break;
}
- rc1 = kernel_sock_shutdown(smc->clcsock, how);
+ if (smc->clcsock)
+ rc1 = kernel_sock_shutdown(smc->clcsock, how);
/* map sock_shutdown_cmd constants to sk_shutdown value range */
sk->sk_shutdown |= how + 1;
--
2.14.3
From ce48a9c76359d43a7fa011502a2f032caf2ea47d Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 24 Apr 2018 14:33:37 +0800
Subject: [PATCH 14/33] team: fix netconsole setup over team
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
[ Upstream commit 9cf2f437ca5b39828984064fad213e68fc17ef11 ]
The same fix in Commit dbe173079ab5 ("bridge: fix netconsole
setup over bridge") is also needed for team driver.
While at it, remove the unnecessary parameter *team from
team_port_enable_netpoll().
v1->v2:
- fix it in a better way, as does bridge.
Fixes: 0fb52a27a04a ("team: cleanup netpoll clode")
Reported-by: João Avelino Bellomo Filho <jbellomo@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/team/team.c | 19 ++++++++++++-------
1 file changed, 12 insertions(+), 7 deletions(-)
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 91a0209756d5..8a222ae5950e 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1072,14 +1072,11 @@ static void team_port_leave(struct team *team, struct team_port *port)
}
#ifdef CONFIG_NET_POLL_CONTROLLER
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int __team_port_enable_netpoll(struct team_port *port)
{
struct netpoll *np;
int err;
- if (!team->dev->npinfo)
- return 0;
-
np = kzalloc(sizeof(*np), GFP_KERNEL);
if (!np)
return -ENOMEM;
@@ -1093,6 +1090,14 @@ static int team_port_enable_netpoll(struct team *team, struct team_port *port)
return err;
}
+static int team_port_enable_netpoll(struct team_port *port)
+{
+ if (!port->team->dev->npinfo)
+ return 0;
+
+ return __team_port_enable_netpoll(port);
+}
+
static void team_port_disable_netpoll(struct team_port *port)
{
struct netpoll *np = port->np;
@@ -1107,7 +1112,7 @@ static void team_port_disable_netpoll(struct team_port *port)
kfree(np);
}
#else
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int team_port_enable_netpoll(struct team_port *port)
{
return 0;
}
@@ -1215,7 +1220,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
goto err_vids_add;
}
- err = team_port_enable_netpoll(team, port);
+ err = team_port_enable_netpoll(port);
if (err) {
netdev_err(dev, "Failed to enable netpoll on device %s\n",
portname);
@@ -1912,7 +1917,7 @@ static int team_netpoll_setup(struct net_device *dev,
mutex_lock(&team->lock);
list_for_each_entry(port, &team->port_list, list) {
- err = team_port_enable_netpoll(team, port);
+ err = __team_port_enable_netpoll(port);
if (err) {
__team_netpoll_cleanup(team);
break;
--
2.14.3
From e8d5d257c7d14c562fcb8a11e29822d25c421bec Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 23 Apr 2018 17:37:03 -0400
Subject: [PATCH 15/33] packet: fix bitfield update race
[ Upstream commit a6361f0ca4b25460f2cdf3235ebe8115f622901e ]
Updates to the bitfields in struct packet_sock are not atomic.
Serialize these read-modify-write cycles.
Move po->running into a separate variable. Its writes are protected by
po->bind_lock (except for one startup case at packet_create). Also
replace a textual precondition warning with lockdep annotation.
All others are set only in packet_setsockopt. Serialize these
updates by holding the socket lock. Analogous to other field updates,
also hold the lock when testing whether a ring is active (pg_vec).
Fixes: 8dc419447415 ("[PACKET]: Add optional checksum computation for recvmsg")
Reported-by: DaeRyong Jeong <threeearcat@gmail.com>
Reported-by: Byoungyoung Lee <byoungyoung@purdue.edu>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/packet/af_packet.c | 60 ++++++++++++++++++++++++++++++++++++--------------
net/packet/internal.h | 10 ++++-----
2 files changed, 49 insertions(+), 21 deletions(-)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e829f4065dbf..3994b71f8197 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -331,11 +331,11 @@ static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
skb_set_queue_mapping(skb, queue_index);
}
-/* register_prot_hook must be invoked with the po->bind_lock held,
+/* __register_prot_hook must be invoked through register_prot_hook
* or from a context in which asynchronous accesses to the packet
* socket is not possible (packet_create()).
*/
-static void register_prot_hook(struct sock *sk)
+static void __register_prot_hook(struct sock *sk)
{
struct packet_sock *po = pkt_sk(sk);
@@ -350,8 +350,13 @@ static void register_prot_hook(struct sock *sk)
}
}
-/* {,__}unregister_prot_hook() must be invoked with the po->bind_lock
- * held. If the sync parameter is true, we will temporarily drop
+static void register_prot_hook(struct sock *sk)
+{
+ lockdep_assert_held_once(&pkt_sk(sk)->bind_lock);
+ __register_prot_hook(sk);
+}
+
+/* If the sync parameter is true, we will temporarily drop
* the po->bind_lock and do a synchronize_net to make sure no
* asynchronous packet processing paths still refer to the elements
* of po->prot_hook. If the sync parameter is false, it is the
@@ -361,6 +366,8 @@ static void __unregister_prot_hook(struct sock *sk, bool sync)
{
struct packet_sock *po = pkt_sk(sk);
+ lockdep_assert_held_once(&po->bind_lock);
+
po->running = 0;
if (po->fanout)
@@ -3261,7 +3268,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
if (proto) {
po->prot_hook.type = proto;
- register_prot_hook(sk);
+ __register_prot_hook(sk);
}
mutex_lock(&net->packet.sklist_lock);
@@ -3743,12 +3750,18 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (optlen != sizeof(val))
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->tp_loss = !!val;
- return 0;
+
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->tp_loss = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
+ return ret;
}
case PACKET_AUXDATA:
{
@@ -3759,7 +3772,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
+ lock_sock(sk);
po->auxdata = !!val;
+ release_sock(sk);
return 0;
}
case PACKET_ORIGDEV:
@@ -3771,7 +3786,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
+ lock_sock(sk);
po->origdev = !!val;
+ release_sock(sk);
return 0;
}
case PACKET_VNET_HDR:
@@ -3780,15 +3797,20 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (sock->type != SOCK_RAW)
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (optlen < sizeof(val))
return -EINVAL;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->has_vnet_hdr = !!val;
- return 0;
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->has_vnet_hdr = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
+ return ret;
}
case PACKET_TIMESTAMP:
{
@@ -3826,11 +3848,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (optlen != sizeof(val))
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->tp_tx_has_off = !!val;
+
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->tp_tx_has_off = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
return 0;
}
case PACKET_QDISC_BYPASS:
diff --git a/net/packet/internal.h b/net/packet/internal.h
index a1d2b2319ae9..3bb7c5fb3bff 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -112,10 +112,12 @@ struct packet_sock {
int copy_thresh;
spinlock_t bind_lock;
struct mutex pg_vec_lock;
- unsigned int running:1, /* prot_hook is attached*/
- auxdata:1,
+ unsigned int running; /* bind_lock must be held */
+ unsigned int auxdata:1, /* writer must hold sock lock */
origdev:1,
- has_vnet_hdr:1;
+ has_vnet_hdr:1,
+ tp_loss:1,
+ tp_tx_has_off:1;
int pressure;
int ifindex; /* bound device */
__be16 num;
@@ -125,8 +127,6 @@ struct packet_sock {
enum tpacket_versions tp_version;
unsigned int tp_hdrlen;
unsigned int tp_reserve;
- unsigned int tp_loss:1;
- unsigned int tp_tx_has_off:1;
unsigned int tp_tstamp;
struct net_device __rcu *cached_dev;
int (*xmit)(struct sk_buff *skb);
--
2.14.3
From 8689a2f272f3975e6f45aa9182560722396195e1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 16 Apr 2018 08:29:42 -0700
Subject: [PATCH 16/33] tipc: add policy for TIPC_NLA_NET_ADDR
[ Upstream commit ec518f21cb1a1b1f8a516499ea05c60299e04963 ]
Before syzbot/KMSAN bites, add the missing policy for TIPC_NLA_NET_ADDR
Fixes: 27c21416727a ("tipc: add net set to new netlink api")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Cc: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/tipc/netlink.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index b76f13f6fea1..d4e0bbeee727 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -79,7 +79,8 @@ const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = {
const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = {
[TIPC_NLA_NET_UNSPEC] = { .type = NLA_UNSPEC },
- [TIPC_NLA_NET_ID] = { .type = NLA_U32 }
+ [TIPC_NLA_NET_ID] = { .type = NLA_U32 },
+ [TIPC_NLA_NET_ADDR] = { .type = NLA_U32 },
};
const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = {
--
2.14.3
From 69f0b01bc35ca918cc897dafe9d502cc0fd42458 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 23 Apr 2018 16:38:27 +0200
Subject: [PATCH 17/33] pppoe: check sockaddr length in pppoe_connect()
[ Upstream commit a49e2f5d5fb141884452ddb428f551b123d436b5 ]
We must validate sockaddr_len, otherwise userspace can pass fewer data
than we expect and we end up accessing invalid data.
Fixes: 224cf5ad14c0 ("ppp: Move the PPP drivers")
Reported-by: syzbot+4f03bdf92fdf9ef5ddab@syzkaller.appspotmail.com
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ppp/pppoe.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 5aa59f41bf8c..71e2aef6b7a1 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -620,6 +620,10 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
lock_sock(sk);
error = -EINVAL;
+
+ if (sockaddr_len != sizeof(struct sockaddr_pppox))
+ goto end;
+
if (sp->sa_protocol != PX_PROTO_OE)
goto end;
--
2.14.3
From d9f57759f1be077579edb14c54265a38288a72fe Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 17 Apr 2018 18:46:14 +0900
Subject: [PATCH 18/33] vlan: Fix reading memory beyond skb->tail in
skb_vlan_tagged_multi
[ Upstream commit 7ce2367254e84753bceb07327aaf5c953cfce117 ]
Syzkaller spotted an old bug which leads to reading skb beyond tail by 4
bytes on vlan tagged packets.
This is caused because skb_vlan_tagged_multi() did not check
skb_headlen.
BUG: KMSAN: uninit-value in eth_type_vlan include/linux/if_vlan.h:283 [inline]
BUG: KMSAN: uninit-value in skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline]
BUG: KMSAN: uninit-value in vlan_features_check include/linux/if_vlan.h:672 [inline]
BUG: KMSAN: uninit-value in dflt_features_check net/core/dev.c:2949 [inline]
BUG: KMSAN: uninit-value in netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009
CPU: 1 PID: 3582 Comm: syzkaller435149 Not tainted 4.16.0+ #82
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:17 [inline]
dump_stack+0x185/0x1d0 lib/dump_stack.c:53
kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
__msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
eth_type_vlan include/linux/if_vlan.h:283 [inline]
skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline]
vlan_features_check include/linux/if_vlan.h:672 [inline]
dflt_features_check net/core/dev.c:2949 [inline]
netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009
validate_xmit_skb+0x89/0x1320 net/core/dev.c:3084
__dev_queue_xmit+0x1cb2/0x2b60 net/core/dev.c:3549
dev_queue_xmit+0x4b/0x60 net/core/dev.c:3590
packet_snd net/packet/af_packet.c:2944 [inline]
packet_sendmsg+0x7c57/0x8a10 net/packet/af_packet.c:2969
sock_sendmsg_nosec net/socket.c:630 [inline]
sock_sendmsg net/socket.c:640 [inline]
sock_write_iter+0x3b9/0x470 net/socket.c:909
do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776
do_iter_write+0x30d/0xd40 fs/read_write.c:932
vfs_writev fs/read_write.c:977 [inline]
do_writev+0x3c9/0x830 fs/read_write.c:1012
SYSC_writev+0x9b/0xb0 fs/read_write.c:1085
SyS_writev+0x56/0x80 fs/read_write.c:1082
do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x43ffa9
RSP: 002b:00007fff2cff3948 EFLAGS: 00000217 ORIG_RAX: 0000000000000014
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043ffa9
RDX: 0000000000000001 RSI: 0000000020000080 RDI: 0000000000000003
RBP: 00000000006cb018 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000217 R12: 00000000004018d0
R13: 0000000000401960 R14: 0000000000000000 R15: 0000000000000000
Uninit was created at:
kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188
kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314
kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321
slab_post_alloc_hook mm/slab.h:445 [inline]
slab_alloc_node mm/slub.c:2737 [inline]
__kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369
__kmalloc_reserve net/core/skbuff.c:138 [inline]
__alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206
alloc_skb include/linux/skbuff.h:984 [inline]
alloc_skb_with_frags+0x1d4/0xb20 net/core/skbuff.c:5234
sock_alloc_send_pskb+0xb56/0x1190 net/core/sock.c:2085
packet_alloc_skb net/packet/af_packet.c:2803 [inline]
packet_snd net/packet/af_packet.c:2894 [inline]
packet_sendmsg+0x6444/0x8a10 net/packet/af_packet.c:2969
sock_sendmsg_nosec net/socket.c:630 [inline]
sock_sendmsg net/socket.c:640 [inline]
sock_write_iter+0x3b9/0x470 net/socket.c:909
do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776
do_iter_write+0x30d/0xd40 fs/read_write.c:932
vfs_writev fs/read_write.c:977 [inline]
do_writev+0x3c9/0x830 fs/read_write.c:1012
SYSC_writev+0x9b/0xb0 fs/read_write.c:1085
SyS_writev+0x56/0x80 fs/read_write.c:1082
do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
Fixes: 58e998c6d239 ("offloading: Force software GSO for multiple vlan tags.")
Reported-and-tested-by: syzbot+0bbe42c764feafa82c5a@syzkaller.appspotmail.com
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/linux/if_vlan.h | 7 +++++--
net/core/dev.c | 2 +-
2 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 5e6a2d4dc366..ab927383c99d 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -584,7 +584,7 @@ static inline bool skb_vlan_tagged(const struct sk_buff *skb)
* Returns true if the skb is tagged with multiple vlan headers, regardless
* of whether it is hardware accelerated or not.
*/
-static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
+static inline bool skb_vlan_tagged_multi(struct sk_buff *skb)
{
__be16 protocol = skb->protocol;
@@ -594,6 +594,9 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
if (likely(!eth_type_vlan(protocol)))
return false;
+ if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN)))
+ return false;
+
veh = (struct vlan_ethhdr *)skb->data;
protocol = veh->h_vlan_encapsulated_proto;
}
@@ -611,7 +614,7 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
*
* Returns features without unsafe ones if the skb has multiple tags.
*/
-static inline netdev_features_t vlan_features_check(const struct sk_buff *skb,
+static inline netdev_features_t vlan_features_check(struct sk_buff *skb,
netdev_features_t features)
{
if (skb_vlan_tagged_multi(skb)) {
diff --git a/net/core/dev.c b/net/core/dev.c
index 4be2a4047640..e7d56c5adde6 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2903,7 +2903,7 @@ netdev_features_t passthru_features_check(struct sk_buff *skb,
}
EXPORT_SYMBOL(passthru_features_check);
-static netdev_features_t dflt_features_check(const struct sk_buff *skb,
+static netdev_features_t dflt_features_check(struct sk_buff *skb,
struct net_device *dev,
netdev_features_t features)
{
--
2.14.3
From fbe15968a850f6df3fb1c7202b69f4ea2ffab17b Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Mon, 23 Apr 2018 11:43:08 -0500
Subject: [PATCH 19/33] amd-xgbe: Add pre/post auto-negotiation phy hooks
[ Upstream commit 4d945663a6a0acf3cbe45940503f2eb9584bfee7 ]
Add hooks to the driver auto-negotiation (AN) flow to allow the different
phy implementations to perform any steps necessary to improve AN.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 16 ++++++++++++++--
drivers/net/ethernet/amd/xgbe/xgbe.h | 5 +++++
2 files changed, 19 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 072b9f664597..e3d361e242aa 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -437,6 +437,9 @@ static void xgbe_an73_disable(struct xgbe_prv_data *pdata)
static void xgbe_an_restart(struct xgbe_prv_data *pdata)
{
+ if (pdata->phy_if.phy_impl.an_pre)
+ pdata->phy_if.phy_impl.an_pre(pdata);
+
switch (pdata->an_mode) {
case XGBE_AN_MODE_CL73:
case XGBE_AN_MODE_CL73_REDRV:
@@ -453,6 +456,9 @@ static void xgbe_an_restart(struct xgbe_prv_data *pdata)
static void xgbe_an_disable(struct xgbe_prv_data *pdata)
{
+ if (pdata->phy_if.phy_impl.an_post)
+ pdata->phy_if.phy_impl.an_post(pdata);
+
switch (pdata->an_mode) {
case XGBE_AN_MODE_CL73:
case XGBE_AN_MODE_CL73_REDRV:
@@ -637,11 +643,11 @@ static enum xgbe_an xgbe_an73_incompat_link(struct xgbe_prv_data *pdata)
return XGBE_AN_NO_LINK;
}
- xgbe_an73_disable(pdata);
+ xgbe_an_disable(pdata);
xgbe_switch_mode(pdata);
- xgbe_an73_restart(pdata);
+ xgbe_an_restart(pdata);
return XGBE_AN_INCOMPAT_LINK;
}
@@ -820,6 +826,9 @@ static void xgbe_an37_state_machine(struct xgbe_prv_data *pdata)
pdata->an_result = pdata->an_state;
pdata->an_state = XGBE_AN_READY;
+ if (pdata->phy_if.phy_impl.an_post)
+ pdata->phy_if.phy_impl.an_post(pdata);
+
netif_dbg(pdata, link, pdata->netdev, "CL37 AN result: %s\n",
xgbe_state_as_string(pdata->an_result));
}
@@ -903,6 +912,9 @@ static void xgbe_an73_state_machine(struct xgbe_prv_data *pdata)
pdata->kx_state = XGBE_RX_BPA;
pdata->an_start = 0;
+ if (pdata->phy_if.phy_impl.an_post)
+ pdata->phy_if.phy_impl.an_post(pdata);
+
netif_dbg(pdata, link, pdata->netdev, "CL73 AN result: %s\n",
xgbe_state_as_string(pdata->an_result));
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index ad102c8bac7b..fa0b51ea1b95 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -833,6 +833,7 @@ struct xgbe_hw_if {
/* This structure represents implementation specific routines for an
* implementation of a PHY. All routines are required unless noted below.
* Optional routines:
+ * an_pre, an_post
* kr_training_pre, kr_training_post
*/
struct xgbe_phy_impl_if {
@@ -875,6 +876,10 @@ struct xgbe_phy_impl_if {
/* Process results of auto-negotiation */
enum xgbe_mode (*an_outcome)(struct xgbe_prv_data *);
+ /* Pre/Post auto-negotiation support */
+ void (*an_pre)(struct xgbe_prv_data *);
+ void (*an_post)(struct xgbe_prv_data *);
+
/* Pre/Post KR training enablement support */
void (*kr_training_pre)(struct xgbe_prv_data *);
void (*kr_training_post)(struct xgbe_prv_data *);
--
2.14.3
From 0407ee4dbb753a97459488083f7d00ead7a7d776 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 12 Apr 2018 14:24:31 +0800
Subject: [PATCH 20/33] sctp: do not check port in sctp_inet6_cmp_addr
[ Upstream commit 1071ec9d453a38023579714b64a951a2fb982071 ]
pf->cmp_addr() is called before binding a v6 address to the sock. It
should not check ports, like in sctp_inet_cmp_addr.
But sctp_inet6_cmp_addr checks the addr by invoking af(6)->cmp_addr,
sctp_v6_cmp_addr where it also compares the ports.
This would cause that setsockopt(SCTP_SOCKOPT_BINDX_ADD) could bind
multiple duplicated IPv6 addresses after Commit 40b4f0fd74e4 ("sctp:
lack the check for ports in sctp_v6_cmp_addr").
This patch is to remove af->cmp_addr called in sctp_inet6_cmp_addr,
but do the proper check for both v6 addrs and v4mapped addrs.
v1->v2:
- define __sctp_v6_cmp_addr to do the common address comparison
used for both pf and af v6 cmp_addr.
Fixes: 40b4f0fd74e4 ("sctp: lack the check for ports in sctp_v6_cmp_addr")
Reported-by: Jianwen Ji <jiji@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sctp/ipv6.c | 60 ++++++++++++++++++++++++++++-----------------------------
1 file changed, 30 insertions(+), 30 deletions(-)
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 08b5705e7381..7219a1c041f7 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -521,46 +521,49 @@ static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr,
addr->v6.sin6_scope_id = 0;
}
-/* Compare addresses exactly.
- * v4-mapped-v6 is also in consideration.
- */
-static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
- const union sctp_addr *addr2)
+static int __sctp_v6_cmp_addr(const union sctp_addr *addr1,
+ const union sctp_addr *addr2)
{
if (addr1->sa.sa_family != addr2->sa.sa_family) {
if (addr1->sa.sa_family == AF_INET &&
addr2->sa.sa_family == AF_INET6 &&
- ipv6_addr_v4mapped(&addr2->v6.sin6_addr)) {
- if (addr2->v6.sin6_port == addr1->v4.sin_port &&
- addr2->v6.sin6_addr.s6_addr32[3] ==
- addr1->v4.sin_addr.s_addr)
- return 1;
- }
+ ipv6_addr_v4mapped(&addr2->v6.sin6_addr) &&
+ addr2->v6.sin6_addr.s6_addr32[3] ==
+ addr1->v4.sin_addr.s_addr)
+ return 1;
+
if (addr2->sa.sa_family == AF_INET &&
addr1->sa.sa_family == AF_INET6 &&
- ipv6_addr_v4mapped(&addr1->v6.sin6_addr)) {
- if (addr1->v6.sin6_port == addr2->v4.sin_port &&
- addr1->v6.sin6_addr.s6_addr32[3] ==
- addr2->v4.sin_addr.s_addr)
- return 1;
- }
+ ipv6_addr_v4mapped(&addr1->v6.sin6_addr) &&
+ addr1->v6.sin6_addr.s6_addr32[3] ==
+ addr2->v4.sin_addr.s_addr)
+ return 1;
+
return 0;
}
- if (addr1->v6.sin6_port != addr2->v6.sin6_port)
- return 0;
+
if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr))
return 0;
+
/* If this is a linklocal address, compare the scope_id. */
- if (ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) {
- if (addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id &&
- (addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)) {
- return 0;
- }
- }
+ if ((ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) &&
+ addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id &&
+ addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)
+ return 0;
return 1;
}
+/* Compare addresses exactly.
+ * v4-mapped-v6 is also in consideration.
+ */
+static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
+ const union sctp_addr *addr2)
+{
+ return __sctp_v6_cmp_addr(addr1, addr2) &&
+ addr1->v6.sin6_port == addr2->v6.sin6_port;
+}
+
/* Initialize addr struct to INADDR_ANY. */
static void sctp_v6_inaddr_any(union sctp_addr *addr, __be16 port)
{
@@ -845,8 +848,8 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1,
const union sctp_addr *addr2,
struct sctp_sock *opt)
{
- struct sctp_af *af1, *af2;
struct sock *sk = sctp_opt2sk(opt);
+ struct sctp_af *af1, *af2;
af1 = sctp_get_af_specific(addr1->sa.sa_family);
af2 = sctp_get_af_specific(addr2->sa.sa_family);
@@ -862,10 +865,7 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1,
if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2))
return 1;
- if (addr1->sa.sa_family != addr2->sa.sa_family)
- return 0;
-
- return af1->cmp_addr(addr1, addr2);
+ return __sctp_v6_cmp_addr(addr1, addr2);
}
/* Verify that the provided sockaddr looks bindable. Common verification,
--
2.14.3
From 6ef5ae8ff07cb4b80818887917d8178cb699c9b6 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Mon, 23 Apr 2018 11:43:17 -0500
Subject: [PATCH 21/33] amd-xgbe: Improve KR auto-negotiation and training
[ Upstream commit 96f4d430c507ed4856048c2dc9c1a2ea5b5e74e4 ]
Update xgbe-phy-v2.c to make use of the auto-negotiation (AN) phy hooks
to improve the ability to successfully complete Clause 73 AN when running
at 10gbps. Hardware can sometimes have issues with CDR lock when the
AN DME page exchange is being performed.
The AN and KR training hooks are used as follows:
- The pre AN hook is used to disable CDR tracking in the PHY so that the
DME page exchange can be successfully and consistently completed.
- The post KR training hook is used to re-enable the CDR tracking so that
KR training can successfully complete.
- The post AN hook is used to check for an unsuccessful AN which will
increase a CDR tracking enablement delay (up to a maximum value).
Add two debugfs entries to allow control over use of the CDR tracking
workaround. The debugfs entries allow the CDR tracking workaround to
be disabled and determine whether to re-enable CDR tracking before or
after link training has been initiated.
Also, with these changes the receiver reset cycle that is performed during
the link status check can be performed less often.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/amd/xgbe/xgbe-common.h | 8 ++
drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c | 16 ++++
drivers/net/ethernet/amd/xgbe/xgbe-main.c | 1 +
drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 8 +-
drivers/net/ethernet/amd/xgbe/xgbe-pci.c | 2 +
drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 125 ++++++++++++++++++++++++++-
drivers/net/ethernet/amd/xgbe/xgbe.h | 4 +
7 files changed, 160 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 7ea72ef11a55..d272dc6984ac 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -1321,6 +1321,10 @@
#define MDIO_VEND2_AN_STAT 0x8002
#endif
+#ifndef MDIO_VEND2_PMA_CDR_CONTROL
+#define MDIO_VEND2_PMA_CDR_CONTROL 0x8056
+#endif
+
#ifndef MDIO_CTRL1_SPEED1G
#define MDIO_CTRL1_SPEED1G (MDIO_CTRL1_SPEED10G & ~BMCR_SPEED100)
#endif
@@ -1369,6 +1373,10 @@
#define XGBE_AN_CL37_TX_CONFIG_MASK 0x08
#define XGBE_AN_CL37_MII_CTRL_8BIT 0x0100
+#define XGBE_PMA_CDR_TRACK_EN_MASK 0x01
+#define XGBE_PMA_CDR_TRACK_EN_OFF 0x00
+#define XGBE_PMA_CDR_TRACK_EN_ON 0x01
+
/* Bit setting and getting macros
* The get macro will extract the current bit field value from within
* the variable
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
index 7d128be61310..b91143947ed2 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
@@ -519,6 +519,22 @@ void xgbe_debugfs_init(struct xgbe_prv_data *pdata)
"debugfs_create_file failed\n");
}
+ if (pdata->vdata->an_cdr_workaround) {
+ pfile = debugfs_create_bool("an_cdr_workaround", 0600,
+ pdata->xgbe_debugfs,
+ &pdata->debugfs_an_cdr_workaround);
+ if (!pfile)
+ netdev_err(pdata->netdev,
+ "debugfs_create_bool failed\n");
+
+ pfile = debugfs_create_bool("an_cdr_track_early", 0600,
+ pdata->xgbe_debugfs,
+ &pdata->debugfs_an_cdr_track_early);
+ if (!pfile)
+ netdev_err(pdata->netdev,
+ "debugfs_create_bool failed\n");
+ }
+
kfree(buf);
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
index d91fa595be98..e31d9d1fb6a6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
@@ -349,6 +349,7 @@ int xgbe_config_netdev(struct xgbe_prv_data *pdata)
XGMAC_SET_BITS(pdata->rss_options, MAC_RSSCR, UDP4TE, 1);
/* Call MDIO/PHY initialization routine */
+ pdata->debugfs_an_cdr_workaround = pdata->vdata->an_cdr_workaround;
ret = pdata->phy_if.phy_init(pdata);
if (ret)
return ret;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index e3d361e242aa..1b45cd73a258 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -432,6 +432,8 @@ static void xgbe_an73_disable(struct xgbe_prv_data *pdata)
xgbe_an73_set(pdata, false, false);
xgbe_an73_disable_interrupts(pdata);
+ pdata->an_start = 0;
+
netif_dbg(pdata, link, pdata->netdev, "CL73 AN disabled\n");
}
@@ -511,11 +513,11 @@ static enum xgbe_an xgbe_an73_tx_training(struct xgbe_prv_data *pdata,
XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL,
reg);
- if (pdata->phy_if.phy_impl.kr_training_post)
- pdata->phy_if.phy_impl.kr_training_post(pdata);
-
netif_dbg(pdata, link, pdata->netdev,
"KR training initiated\n");
+
+ if (pdata->phy_if.phy_impl.kr_training_post)
+ pdata->phy_if.phy_impl.kr_training_post(pdata);
}
return XGBE_AN_PAGE_RECEIVED;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
index eb23f9ba1a9a..82d1f416ee2a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -456,6 +456,7 @@ static const struct xgbe_version_data xgbe_v2a = {
.irq_reissue_support = 1,
.tx_desc_prefetch = 5,
.rx_desc_prefetch = 5,
+ .an_cdr_workaround = 1,
};
static const struct xgbe_version_data xgbe_v2b = {
@@ -470,6 +471,7 @@ static const struct xgbe_version_data xgbe_v2b = {
.irq_reissue_support = 1,
.tx_desc_prefetch = 5,
.rx_desc_prefetch = 5,
+ .an_cdr_workaround = 1,
};
static const struct pci_device_id xgbe_pci_table[] = {
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 3304a291aa96..b48efc04c4da 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -147,6 +147,14 @@
/* Rate-change complete wait/retry count */
#define XGBE_RATECHANGE_COUNT 500
+/* CDR delay values for KR support (in usec) */
+#define XGBE_CDR_DELAY_INIT 10000
+#define XGBE_CDR_DELAY_INC 10000
+#define XGBE_CDR_DELAY_MAX 100000
+
+/* RRC frequency during link status check */
+#define XGBE_RRC_FREQUENCY 10
+
enum xgbe_port_mode {
XGBE_PORT_MODE_RSVD = 0,
XGBE_PORT_MODE_BACKPLANE,
@@ -355,6 +363,10 @@ struct xgbe_phy_data {
unsigned int redrv_addr;
unsigned int redrv_lane;
unsigned int redrv_model;
+
+ /* KR AN support */
+ unsigned int phy_cdr_notrack;
+ unsigned int phy_cdr_delay;
};
/* I2C, MDIO and GPIO lines are muxed, so only one device at a time */
@@ -2361,7 +2373,7 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
return 1;
/* No link, attempt a receiver reset cycle */
- if (phy_data->rrc_count++) {
+ if (phy_data->rrc_count++ > XGBE_RRC_FREQUENCY) {
phy_data->rrc_count = 0;
xgbe_phy_rrc(pdata);
}
@@ -2669,6 +2681,103 @@ static bool xgbe_phy_port_enabled(struct xgbe_prv_data *pdata)
return true;
}
+static void xgbe_phy_cdr_track(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ if (!pdata->debugfs_an_cdr_workaround)
+ return;
+
+ if (!phy_data->phy_cdr_notrack)
+ return;
+
+ usleep_range(phy_data->phy_cdr_delay,
+ phy_data->phy_cdr_delay + 500);
+
+ XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL,
+ XGBE_PMA_CDR_TRACK_EN_MASK,
+ XGBE_PMA_CDR_TRACK_EN_ON);
+
+ phy_data->phy_cdr_notrack = 0;
+}
+
+static void xgbe_phy_cdr_notrack(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ if (!pdata->debugfs_an_cdr_workaround)
+ return;
+
+ if (phy_data->phy_cdr_notrack)
+ return;
+
+ XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL,
+ XGBE_PMA_CDR_TRACK_EN_MASK,
+ XGBE_PMA_CDR_TRACK_EN_OFF);
+
+ xgbe_phy_rrc(pdata);
+
+ phy_data->phy_cdr_notrack = 1;
+}
+
+static void xgbe_phy_kr_training_post(struct xgbe_prv_data *pdata)
+{
+ if (!pdata->debugfs_an_cdr_track_early)
+ xgbe_phy_cdr_track(pdata);
+}
+
+static void xgbe_phy_kr_training_pre(struct xgbe_prv_data *pdata)
+{
+ if (pdata->debugfs_an_cdr_track_early)
+ xgbe_phy_cdr_track(pdata);
+}
+
+static void xgbe_phy_an_post(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ case XGBE_AN_MODE_CL73_REDRV:
+ if (phy_data->cur_mode != XGBE_MODE_KR)
+ break;
+
+ xgbe_phy_cdr_track(pdata);
+
+ switch (pdata->an_result) {
+ case XGBE_AN_READY:
+ case XGBE_AN_COMPLETE:
+ break;
+ default:
+ if (phy_data->phy_cdr_delay < XGBE_CDR_DELAY_MAX)
+ phy_data->phy_cdr_delay += XGBE_CDR_DELAY_INC;
+ else
+ phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT;
+ break;
+ }
+ break;
+ default:
+ break;
+ }
+}
+
+static void xgbe_phy_an_pre(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ case XGBE_AN_MODE_CL73_REDRV:
+ if (phy_data->cur_mode != XGBE_MODE_KR)
+ break;
+
+ xgbe_phy_cdr_notrack(pdata);
+ break;
+ default:
+ break;
+ }
+}
+
static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
{
struct xgbe_phy_data *phy_data = pdata->phy_data;
@@ -2680,6 +2789,9 @@ static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
xgbe_phy_sfp_reset(phy_data);
xgbe_phy_sfp_mod_absent(pdata);
+ /* Reset CDR support */
+ xgbe_phy_cdr_track(pdata);
+
/* Power off the PHY */
xgbe_phy_power_off(pdata);
@@ -2712,6 +2824,9 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata)
/* Start in highest supported mode */
xgbe_phy_set_mode(pdata, phy_data->start_mode);
+ /* Reset CDR support */
+ xgbe_phy_cdr_track(pdata);
+
/* After starting the I2C controller, we can check for an SFP */
switch (phy_data->port_mode) {
case XGBE_PORT_MODE_SFP:
@@ -3019,6 +3134,8 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata)
}
}
+ phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT;
+
/* Register for driving external PHYs */
mii = devm_mdiobus_alloc(pdata->dev);
if (!mii) {
@@ -3071,4 +3188,10 @@ void xgbe_init_function_ptrs_phy_v2(struct xgbe_phy_if *phy_if)
phy_impl->an_advertising = xgbe_phy_an_advertising;
phy_impl->an_outcome = xgbe_phy_an_outcome;
+
+ phy_impl->an_pre = xgbe_phy_an_pre;
+ phy_impl->an_post = xgbe_phy_an_post;
+
+ phy_impl->kr_training_pre = xgbe_phy_kr_training_pre;
+ phy_impl->kr_training_post = xgbe_phy_kr_training_post;
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index fa0b51ea1b95..95d4b56448c6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -994,6 +994,7 @@ struct xgbe_version_data {
unsigned int irq_reissue_support;
unsigned int tx_desc_prefetch;
unsigned int rx_desc_prefetch;
+ unsigned int an_cdr_workaround;
};
struct xgbe_vxlan_data {
@@ -1262,6 +1263,9 @@ struct xgbe_prv_data {
unsigned int debugfs_xprop_reg;
unsigned int debugfs_xi2c_reg;
+
+ bool debugfs_an_cdr_workaround;
+ bool debugfs_an_cdr_track_early;
};
/* Function prototypes*/
--
2.14.3
From b363ff5316f334777236e7dd428c5f885b1b89bf Mon Sep 17 00:00:00 2001
From: Doron Roberts-Kedes <doronrk@fb.com>
Date: Fri, 20 Apr 2018 12:11:11 -0700
Subject: [PATCH 22/33] strparser: Do not call mod_delayed_work with a timeout
of LONG_MAX
[ Upstream commit 7c5aba211dd61f41d737a2c51729eb9fdcd3edf4 ]
struct sock's sk_rcvtimeo is initialized to
LONG_MAX/MAX_SCHEDULE_TIMEOUT in sock_init_data. Calling
mod_delayed_work with a timeout of LONG_MAX causes spurious execution of
the work function. timer->expires is set equal to jiffies + LONG_MAX.
When timer_base->clk falls behind the current value of jiffies,
the delta between timer_base->clk and jiffies + LONG_MAX causes the
expiration to be in the past. Returning early from strp_start_timer if
timeo == LONG_MAX solves this problem.
Found while testing net/tls_sw recv path.
Fixes: 43a0c6751a322847 ("strparser: Stream parser for messages")
Reviewed-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/strparser/strparser.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 4a3a3f1331ee..6b5a7fffc62c 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -67,7 +67,7 @@ static void strp_abort_strp(struct strparser *strp, int err)
static void strp_start_timer(struct strparser *strp, long timeo)
{
- if (timeo)
+ if (timeo && timeo != LONG_MAX)
mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo);
}
--
2.14.3
From 8b549d4fc15b4d9d83b387ade57506615e80f544 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Mon, 23 Apr 2018 11:43:34 -0500
Subject: [PATCH 23/33] amd-xgbe: Only use the SFP supported transceiver
signals
[ Upstream commit 117df655f8ed51adb6e6b163812a06ebeae9f453 ]
The SFP eeprom indicates the transceiver signals (Rx LOS, Tx Fault, etc.)
that it supports. Update the driver to include checking the eeprom data
when deciding whether to use a transceiver signal.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 71 ++++++++++++++++++++++-------
1 file changed, 54 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index b48efc04c4da..aac884314000 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -253,6 +253,10 @@ enum xgbe_sfp_speed {
#define XGBE_SFP_BASE_VENDOR_SN 4
#define XGBE_SFP_BASE_VENDOR_SN_LEN 16
+#define XGBE_SFP_EXTD_OPT1 1
+#define XGBE_SFP_EXTD_OPT1_RX_LOS BIT(1)
+#define XGBE_SFP_EXTD_OPT1_TX_FAULT BIT(3)
+
#define XGBE_SFP_EXTD_DIAG 28
#define XGBE_SFP_EXTD_DIAG_ADDR_CHANGE BIT(2)
@@ -332,6 +336,7 @@ struct xgbe_phy_data {
unsigned int sfp_gpio_address;
unsigned int sfp_gpio_mask;
+ unsigned int sfp_gpio_inputs;
unsigned int sfp_gpio_rx_los;
unsigned int sfp_gpio_tx_fault;
unsigned int sfp_gpio_mod_absent;
@@ -986,6 +991,49 @@ static void xgbe_phy_sfp_external_phy(struct xgbe_prv_data *pdata)
phy_data->sfp_phy_avail = 1;
}
+static bool xgbe_phy_check_sfp_rx_los(struct xgbe_phy_data *phy_data)
+{
+ u8 *sfp_extd = phy_data->sfp_eeprom.extd;
+
+ if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_RX_LOS))
+ return false;
+
+ if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS)
+ return false;
+
+ if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_rx_los))
+ return true;
+
+ return false;
+}
+
+static bool xgbe_phy_check_sfp_tx_fault(struct xgbe_phy_data *phy_data)
+{
+ u8 *sfp_extd = phy_data->sfp_eeprom.extd;
+
+ if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_TX_FAULT))
+ return false;
+
+ if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT)
+ return false;
+
+ if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_tx_fault))
+ return true;
+
+ return false;
+}
+
+static bool xgbe_phy_check_sfp_mod_absent(struct xgbe_phy_data *phy_data)
+{
+ if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT)
+ return false;
+
+ if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_mod_absent))
+ return true;
+
+ return false;
+}
+
static bool xgbe_phy_belfuse_parse_quirks(struct xgbe_prv_data *pdata)
{
struct xgbe_phy_data *phy_data = pdata->phy_data;
@@ -1031,6 +1079,10 @@ static void xgbe_phy_sfp_parse_eeprom(struct xgbe_prv_data *pdata)
if (sfp_base[XGBE_SFP_BASE_EXT_ID] != XGBE_SFP_EXT_ID_SFP)
return;
+ /* Update transceiver signals (eeprom extd/options) */
+ phy_data->sfp_tx_fault = xgbe_phy_check_sfp_tx_fault(phy_data);
+ phy_data->sfp_rx_los = xgbe_phy_check_sfp_rx_los(phy_data);
+
if (xgbe_phy_sfp_parse_quirks(pdata))
return;
@@ -1196,7 +1248,6 @@ static int xgbe_phy_sfp_read_eeprom(struct xgbe_prv_data *pdata)
static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata)
{
struct xgbe_phy_data *phy_data = pdata->phy_data;
- unsigned int gpio_input;
u8 gpio_reg, gpio_ports[2];
int ret;
@@ -1211,23 +1262,9 @@ static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata)
return;
}
- gpio_input = (gpio_ports[1] << 8) | gpio_ports[0];
-
- if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT) {
- /* No GPIO, just assume the module is present for now */
- phy_data->sfp_mod_absent = 0;
- } else {
- if (!(gpio_input & (1 << phy_data->sfp_gpio_mod_absent)))
- phy_data->sfp_mod_absent = 0;
- }
-
- if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS) &&
- (gpio_input & (1 << phy_data->sfp_gpio_rx_los)))
- phy_data->sfp_rx_los = 1;
+ phy_data->sfp_gpio_inputs = (gpio_ports[1] << 8) | gpio_ports[0];
- if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT) &&
- (gpio_input & (1 << phy_data->sfp_gpio_tx_fault)))
- phy_data->sfp_tx_fault = 1;
+ phy_data->sfp_mod_absent = xgbe_phy_check_sfp_mod_absent(phy_data);
}
static void xgbe_phy_sfp_mod_absent(struct xgbe_prv_data *pdata)
--
2.14.3
From 79d8b3c61e2dd7c6b500d0145cb45379ebcb06a1 Mon Sep 17 00:00:00 2001
From: Doron Roberts-Kedes <doronrk@fb.com>
Date: Wed, 11 Apr 2018 15:05:16 -0700
Subject: [PATCH 24/33] strparser: Fix incorrect strp->need_bytes value.
[ Upstream commit 9d0c75bf6e03d9bf80c55b0f677dc9b982958fd5 ]
strp_data_ready resets strp->need_bytes to 0 if strp_peek_len indicates
that the remainder of the message has been received. However,
do_strp_work does not reset strp->need_bytes to 0. If do_strp_work
completes a partial message, the value of strp->need_bytes will continue
to reflect the needed bytes of the previous message, causing
future invocations of strp_data_ready to return early if
strp->need_bytes is less than strp_peek_len. Resetting strp->need_bytes
to 0 in __strp_recv on handing a full message to the upper layer solves
this problem.
__strp_recv also calculates strp->need_bytes using stm->accum_len before
stm->accum_len has been incremented by cand_len. This can cause
strp->need_bytes to be equal to the full length of the message instead
of the full length minus the accumulated length. This, in turn, causes
strp_data_ready to return early, even when there is sufficient data to
complete the partial message. Incrementing stm->accum_len before using
it to calculate strp->need_bytes solves this problem.
Found while testing net/tls_sw recv path.
Fixes: 43a0c6751a322847 ("strparser: Stream parser for messages")
Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/strparser/strparser.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 6b5a7fffc62c..c741365f77da 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -296,9 +296,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
strp_start_timer(strp, timeo);
}
+ stm->accum_len += cand_len;
strp->need_bytes = stm->strp.full_len -
stm->accum_len;
- stm->accum_len += cand_len;
stm->early_eaten = cand_len;
STRP_STATS_ADD(strp->stats.bytes, cand_len);
desc->count = 0; /* Stop reading socket */
@@ -321,6 +321,7 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
/* Hurray, we have a new message! */
cancel_delayed_work(&strp->msg_timer_work);
strp->skb_head = NULL;
+ strp->need_bytes = 0;
STRP_STATS_INCR(strp->stats.msgs);
/* Give skb to upper layer */
@@ -410,9 +411,7 @@ void strp_data_ready(struct strparser *strp)
return;
if (strp->need_bytes) {
- if (strp_peek_len(strp) >= strp->need_bytes)
- strp->need_bytes = 0;
- else
+ if (strp_peek_len(strp) < strp->need_bytes)
return;
}
--
2.14.3
From b5e16d864bdff4badb26b6e9eeca443e797b0c2b Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Fri, 20 Apr 2018 15:15:03 -0400
Subject: [PATCH 25/33] net: sched: ife: signal not finding metaid
[ Upstream commit f6cd14537ff9919081be19b9c53b9b19c0d3ea97 ]
We need to record stats for received metadata that we dont know how
to process. Have find_decode_metaid() return -ENOENT to capture this.
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Reviewed-by: Yotam Gigi <yotam.gi@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/act_ife.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 8ccd35825b6b..4b4e4d490f42 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -605,7 +605,7 @@ static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
}
}
- return 0;
+ return -ENOENT;
}
static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
--
2.14.3
From 589282abaf79d2e031835e5c78381163d7e43b68 Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Sat, 14 Apr 2018 20:45:20 -0400
Subject: [PATCH 26/33] tcp: clear tp->packets_out when purging write queue
Clear tp->packets_out when purging the write queue, otherwise
tcp_rearm_rto() mistakenly assumes TCP write queue is not empty.
This results in NULL pointer dereference.
Also, remove the redundant `tp->packets_out = 0` from
tcp_disconnect(), since tcp_disconnect() calls
tcp_write_queue_purge().
Fixes: a27fd7a8ed38 (tcp: purge write queue upon RST)
Reported-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Reported-by: Sami Farin <hvtaifwkbgefbaei@gmail.com>
Tested-by: Sami Farin <hvtaifwkbgefbaei@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
---
include/net/tcp.h | 1 +
net/ipv4/tcp.c | 1 -
2 files changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index d323d4fa742c..fb653736f335 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1616,6 +1616,7 @@ static inline void tcp_write_queue_purge(struct sock *sk)
sk_mem_reclaim(sk);
tcp_clear_all_retrans_hints(tcp_sk(sk));
tcp_init_send_head(sk);
+ tcp_sk(sk)->packets_out = 0;
}
static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e8d8140cd33f..d023f879e7bb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2354,7 +2354,6 @@ int tcp_disconnect(struct sock *sk, int flags)
icsk->icsk_backoff = 0;
tp->snd_cwnd = 2;
icsk->icsk_probes_out = 0;
- tp->packets_out = 0;
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_cnt = 0;
tp->window_clamp = 0;
--
2.14.3
From 8de1c00b2f638406f831e187f9a2d4e194a423cc Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Fri, 20 Apr 2018 15:15:04 -0400
Subject: [PATCH 27/33] net: sched: ife: handle malformed tlv length
[ Upstream commit cc74eddd0ff325d57373cea99f642b787d7f76f5 ]
There is currently no handling to check on a invalid tlv length. This
patch adds such handling to avoid killing the kernel with a malformed
ife packet.
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Reviewed-by: Yotam Gigi <yotam.gi@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/ife.h | 3 ++-
net/ife/ife.c | 35 +++++++++++++++++++++++++++++++++--
net/sched/act_ife.c | 7 ++++++-
3 files changed, 41 insertions(+), 4 deletions(-)
diff --git a/include/net/ife.h b/include/net/ife.h
index 44b9c00f7223..e117617e3c34 100644
--- a/include/net/ife.h
+++ b/include/net/ife.h
@@ -12,7 +12,8 @@
void *ife_encode(struct sk_buff *skb, u16 metalen);
void *ife_decode(struct sk_buff *skb, u16 *metalen);
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen);
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+ u16 *dlen, u16 *totlen);
int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen,
const void *dval);
diff --git a/net/ife/ife.c b/net/ife/ife.c
index 7d1ec76e7f43..7fbe70a0af4b 100644
--- a/net/ife/ife.c
+++ b/net/ife/ife.c
@@ -92,12 +92,43 @@ struct meta_tlvhdr {
__be16 len;
};
+static bool __ife_tlv_meta_valid(const unsigned char *skbdata,
+ const unsigned char *ifehdr_end)
+{
+ const struct meta_tlvhdr *tlv;
+ u16 tlvlen;
+
+ if (unlikely(skbdata + sizeof(*tlv) > ifehdr_end))
+ return false;
+
+ tlv = (const struct meta_tlvhdr *)skbdata;
+ tlvlen = ntohs(tlv->len);
+
+ /* tlv length field is inc header, check on minimum */
+ if (tlvlen < NLA_HDRLEN)
+ return false;
+
+ /* overflow by NLA_ALIGN check */
+ if (NLA_ALIGN(tlvlen) < tlvlen)
+ return false;
+
+ if (unlikely(skbdata + NLA_ALIGN(tlvlen) > ifehdr_end))
+ return false;
+
+ return true;
+}
+
/* Caller takes care of presenting data in network order
*/
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen)
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+ u16 *dlen, u16 *totlen)
{
- struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata;
+ struct meta_tlvhdr *tlv;
+
+ if (!__ife_tlv_meta_valid(skbdata, ifehdr_end))
+ return NULL;
+ tlv = (struct meta_tlvhdr *)skbdata;
*dlen = ntohs(tlv->len) - NLA_HDRLEN;
*attrtype = ntohs(tlv->type);
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 4b4e4d490f42..85757af7f150 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -639,7 +639,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
u16 mtype;
u16 dlen;
- curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL);
+ curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype,
+ &dlen, NULL);
+ if (!curr_data) {
+ qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
+ return TC_ACT_SHOT;
+ }
if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) {
/* abuse overlimits to count when we receive metadata
--
2.14.3
From 4fcbc47231764affb7c4a4f2974c2189dac037e4 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Fri, 20 Apr 2018 15:15:05 -0400
Subject: [PATCH 28/33] net: sched: ife: check on metadata length
[ Upstream commit d57493d6d1be26c8ac8516a4463bfe24956978eb ]
This patch checks if sk buffer is available to dererence ife header. If
not then NULL will returned to signal an malformed ife packet. This
avoids to crashing the kernel from outside.
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Reviewed-by: Yotam Gigi <yotam.gi@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ife/ife.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/net/ife/ife.c b/net/ife/ife.c
index 7fbe70a0af4b..13bbf8cb6a39 100644
--- a/net/ife/ife.c
+++ b/net/ife/ife.c
@@ -69,6 +69,9 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen)
int total_pull;
u16 ifehdrln;
+ if (!pskb_may_pull(skb, skb->dev->hard_header_len + IFE_METAHDRLEN))
+ return NULL;
+
ifehdr = (struct ifeheadr *) (skb->data + skb->dev->hard_header_len);
ifehdrln = ntohs(ifehdr->metalen);
total_pull = skb->dev->hard_header_len + ifehdrln;
--
2.14.3
From 61b133bcdff0e35598f855ff1d1b2647be94cc85 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 18 Apr 2018 11:51:56 -0700
Subject: [PATCH 29/33] llc: hold llc_sap before release_sock()
[ Upstream commit f7e43672683b097bb074a8fe7af9bc600a23f231 ]
syzbot reported we still access llc->sap in llc_backlog_rcv()
after it is freed in llc_sap_remove_socket():
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x1b9/0x294 lib/dump_stack.c:113
print_address_description+0x6c/0x20b mm/kasan/report.c:256
kasan_report_error mm/kasan/report.c:354 [inline]
kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412
__asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:430
llc_conn_ac_send_sabme_cmd_p_set_x+0x3a8/0x460 net/llc/llc_c_ac.c:785
llc_exec_conn_trans_actions net/llc/llc_conn.c:475 [inline]
llc_conn_service net/llc/llc_conn.c:400 [inline]
llc_conn_state_process+0x4e1/0x13a0 net/llc/llc_conn.c:75
llc_backlog_rcv+0x195/0x1e0 net/llc/llc_conn.c:891
sk_backlog_rcv include/net/sock.h:909 [inline]
__release_sock+0x12f/0x3a0 net/core/sock.c:2335
release_sock+0xa4/0x2b0 net/core/sock.c:2850
llc_ui_release+0xc8/0x220 net/llc/af_llc.c:204
llc->sap is refcount'ed and llc_sap_remove_socket() is paired
with llc_sap_add_socket(). This can be amended by holding its refcount
before llc_sap_remove_socket() and releasing it after release_sock().
Reported-by: <syzbot+6e181fc95081c2cf9051@syzkaller.appspotmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/llc/af_llc.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index c38d16f22d2a..c8950d88a695 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -189,6 +189,7 @@ static int llc_ui_release(struct socket *sock)
{
struct sock *sk = sock->sk;
struct llc_sock *llc;
+ struct llc_sap *sap;
if (unlikely(sk == NULL))
goto out;
@@ -199,9 +200,15 @@ static int llc_ui_release(struct socket *sock)
llc->laddr.lsap, llc->daddr.lsap);
if (!llc_send_disc(sk))
llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo);
+ sap = llc->sap;
+ /* Hold this for release_sock(), so that llc_backlog_rcv() could still
+ * use it.
+ */
+ llc_sap_hold(sap);
if (!sock_flag(sk, SOCK_ZAPPED))
llc_sap_remove_socket(llc->sap, sk);
release_sock(sk);
+ llc_sap_put(sap);
if (llc->dev)
dev_put(llc->dev);
sock_put(sk);
--
2.14.3
From b9dcfb57501053a4eaa182fa4b78bbb01b439e36 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 19 Apr 2018 21:54:34 -0700
Subject: [PATCH 30/33] llc: fix NULL pointer deref for SOCK_ZAPPED
[ Upstream commit 3a04ce7130a7e5dad4e78d45d50313747f8c830f ]
For SOCK_ZAPPED socket, we don't need to care about llc->sap,
so we should just skip these refcount functions in this case.
Fixes: f7e43672683b ("llc: hold llc_sap before release_sock()")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/llc/af_llc.c | 21 ++++++++++++---------
1 file changed, 12 insertions(+), 9 deletions(-)
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index c8950d88a695..cf41d9b4a0b8 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -189,7 +189,6 @@ static int llc_ui_release(struct socket *sock)
{
struct sock *sk = sock->sk;
struct llc_sock *llc;
- struct llc_sap *sap;
if (unlikely(sk == NULL))
goto out;
@@ -200,15 +199,19 @@ static int llc_ui_release(struct socket *sock)
llc->laddr.lsap, llc->daddr.lsap);
if (!llc_send_disc(sk))
llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo);
- sap = llc->sap;
- /* Hold this for release_sock(), so that llc_backlog_rcv() could still
- * use it.
- */
- llc_sap_hold(sap);
- if (!sock_flag(sk, SOCK_ZAPPED))
+ if (!sock_flag(sk, SOCK_ZAPPED)) {
+ struct llc_sap *sap = llc->sap;
+
+ /* Hold this for release_sock(), so that llc_backlog_rcv()
+ * could still use it.
+ */
+ llc_sap_hold(sap);
llc_sap_remove_socket(llc->sap, sk);
- release_sock(sk);
- llc_sap_put(sap);
+ release_sock(sk);
+ llc_sap_put(sap);
+ } else {
+ release_sock(sk);
+ }
if (llc->dev)
dev_put(llc->dev);
sock_put(sk);
--
2.14.3
From f42442ae5628cd7fd6b52deff7a952355a81be9e Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Thu, 19 Apr 2018 22:49:09 +0300
Subject: [PATCH 31/33] net: ethernet: ti: cpsw: fix tx vlan priority mapping
[ Upstream commit 5e391dc5a8d801a2410d0032ad4a428d1d61800c ]
The CPDMA_TX_PRIORITY_MAP in real is vlan pcp field priority mapping
register and basically replaces vlan pcp field for tagged packets.
So, set it to be 1:1 mapping. Otherwise, it will cause unexpected
change of egress vlan tagged packets, like prio 2 -> prio 5.
Fixes: e05107e6b747 ("net: ethernet: ti: cpsw: add multi queue support")
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/ti/cpsw.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index a5bb7b19040e..992c43b1868f 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -124,7 +124,7 @@ do { \
#define RX_PRIORITY_MAPPING 0x76543210
#define TX_PRIORITY_MAPPING 0x33221100
-#define CPDMA_TX_PRIORITY_MAP 0x01234567
+#define CPDMA_TX_PRIORITY_MAP 0x76543210
#define CPSW_VLAN_AWARE BIT(1)
#define CPSW_ALE_VLAN_AWARE 1
--
2.14.3
From ddad4ef8904cabd725a3b05f8ce6f32053688f36 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 19 Apr 2018 08:30:48 +0300
Subject: [PATCH 32/33] virtio_net: split out ctrl buffer
[ Upstream commit 12e571693837d6164bda61e316b1944972ee0d97 ]
When sending control commands, virtio net sets up several buffers for
DMA. The buffers are all part of the net device which means it's
actually allocated by kvmalloc so it's in theory (on extreme memory
pressure) possible to get a vmalloc'ed buffer which on some platforms
means we can't DMA there.
Fix up by moving the DMA buffers into a separate structure.
Reported-by: Mikulas Patocka <mpatocka@redhat.com>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/virtio_net.c | 68 +++++++++++++++++++++++++++---------------------
1 file changed, 39 insertions(+), 29 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index b0a038e6fda0..63b096c47f1e 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -116,6 +116,17 @@ struct receive_queue {
char name[40];
};
+/* Control VQ buffers: protected by the rtnl lock */
+struct control_buf {
+ struct virtio_net_ctrl_hdr hdr;
+ virtio_net_ctrl_ack status;
+ struct virtio_net_ctrl_mq mq;
+ u8 promisc;
+ u8 allmulti;
+ u16 vid;
+ u64 offloads;
+};
+
struct virtnet_info {
struct virtio_device *vdev;
struct virtqueue *cvq;
@@ -164,14 +175,7 @@ struct virtnet_info {
struct hlist_node node;
struct hlist_node node_dead;
- /* Control VQ buffers: protected by the rtnl lock */
- struct virtio_net_ctrl_hdr ctrl_hdr;
- virtio_net_ctrl_ack ctrl_status;
- struct virtio_net_ctrl_mq ctrl_mq;
- u8 ctrl_promisc;
- u8 ctrl_allmulti;
- u16 ctrl_vid;
- u64 ctrl_offloads;
+ struct control_buf *ctrl;
/* Ethtool settings */
u8 duplex;
@@ -1340,25 +1344,25 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
/* Caller should know better */
BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ));
- vi->ctrl_status = ~0;
- vi->ctrl_hdr.class = class;
- vi->ctrl_hdr.cmd = cmd;
+ vi->ctrl->status = ~0;
+ vi->ctrl->hdr.class = class;
+ vi->ctrl->hdr.cmd = cmd;
/* Add header */
- sg_init_one(&hdr, &vi->ctrl_hdr, sizeof(vi->ctrl_hdr));
+ sg_init_one(&hdr, &vi->ctrl->hdr, sizeof(vi->ctrl->hdr));
sgs[out_num++] = &hdr;
if (out)
sgs[out_num++] = out;
/* Add return status. */
- sg_init_one(&stat, &vi->ctrl_status, sizeof(vi->ctrl_status));
+ sg_init_one(&stat, &vi->ctrl->status, sizeof(vi->ctrl->status));
sgs[out_num] = &stat;
BUG_ON(out_num + 1 > ARRAY_SIZE(sgs));
virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC);
if (unlikely(!virtqueue_kick(vi->cvq)))
- return vi->ctrl_status == VIRTIO_NET_OK;
+ return vi->ctrl->status == VIRTIO_NET_OK;
/* Spin for a response, the kick causes an ioport write, trapping
* into the hypervisor, so the request should be handled immediately.
@@ -1367,7 +1371,7 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
!virtqueue_is_broken(vi->cvq))
cpu_relax();
- return vi->ctrl_status == VIRTIO_NET_OK;
+ return vi->ctrl->status == VIRTIO_NET_OK;
}
static int virtnet_set_mac_address(struct net_device *dev, void *p)
@@ -1478,8 +1482,8 @@ static int _virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
return 0;
- vi->ctrl_mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs);
- sg_init_one(&sg, &vi->ctrl_mq, sizeof(vi->ctrl_mq));
+ vi->ctrl->mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs);
+ sg_init_one(&sg, &vi->ctrl->mq, sizeof(vi->ctrl->mq));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg)) {
@@ -1537,22 +1541,22 @@ static void virtnet_set_rx_mode(struct net_device *dev)
if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX))
return;
- vi->ctrl_promisc = ((dev->flags & IFF_PROMISC) != 0);
- vi->ctrl_allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
+ vi->ctrl->promisc = ((dev->flags & IFF_PROMISC) != 0);
+ vi->ctrl->allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
- sg_init_one(sg, &vi->ctrl_promisc, sizeof(vi->ctrl_promisc));
+ sg_init_one(sg, &vi->ctrl->promisc, sizeof(vi->ctrl->promisc));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
VIRTIO_NET_CTRL_RX_PROMISC, sg))
dev_warn(&dev->dev, "Failed to %sable promisc mode.\n",
- vi->ctrl_promisc ? "en" : "dis");
+ vi->ctrl->promisc ? "en" : "dis");
- sg_init_one(sg, &vi->ctrl_allmulti, sizeof(vi->ctrl_allmulti));
+ sg_init_one(sg, &vi->ctrl->allmulti, sizeof(vi->ctrl->allmulti));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
VIRTIO_NET_CTRL_RX_ALLMULTI, sg))
dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
- vi->ctrl_allmulti ? "en" : "dis");
+ vi->ctrl->allmulti ? "en" : "dis");
uc_count = netdev_uc_count(dev);
mc_count = netdev_mc_count(dev);
@@ -1598,8 +1602,8 @@ static int virtnet_vlan_rx_add_vid(struct net_device *dev,
struct virtnet_info *vi = netdev_priv(dev);
struct scatterlist sg;
- vi->ctrl_vid = vid;
- sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid));
+ vi->ctrl->vid = vid;
+ sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
VIRTIO_NET_CTRL_VLAN_ADD, &sg))
@@ -1613,8 +1617,8 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev,
struct virtnet_info *vi = netdev_priv(dev);
struct scatterlist sg;
- vi->ctrl_vid = vid;
- sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid));
+ vi->ctrl->vid = vid;
+ sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
VIRTIO_NET_CTRL_VLAN_DEL, &sg))
@@ -1912,9 +1916,9 @@ static int virtnet_restore_up(struct virtio_device *vdev)
static int virtnet_set_guest_offloads(struct virtnet_info *vi, u64 offloads)
{
struct scatterlist sg;
- vi->ctrl_offloads = cpu_to_virtio64(vi->vdev, offloads);
+ vi->ctrl->offloads = cpu_to_virtio64(vi->vdev, offloads);
- sg_init_one(&sg, &vi->ctrl_offloads, sizeof(vi->ctrl_offloads));
+ sg_init_one(&sg, &vi->ctrl->offloads, sizeof(vi->ctrl->offloads));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_GUEST_OFFLOADS,
VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET, &sg)) {
@@ -2134,6 +2138,7 @@ static void virtnet_free_queues(struct virtnet_info *vi)
kfree(vi->rq);
kfree(vi->sq);
+ kfree(vi->ctrl);
}
static void _free_receive_bufs(struct virtnet_info *vi)
@@ -2326,6 +2331,9 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
{
int i;
+ vi->ctrl = kzalloc(sizeof(*vi->ctrl), GFP_KERNEL);
+ if (!vi->ctrl)
+ goto err_ctrl;
vi->sq = kzalloc(sizeof(*vi->sq) * vi->max_queue_pairs, GFP_KERNEL);
if (!vi->sq)
goto err_sq;
@@ -2351,6 +2359,8 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
err_rq:
kfree(vi->sq);
err_sq:
+ kfree(vi->ctrl);
+err_ctrl:
return -ENOMEM;
}
--
2.14.3
From 7feb36d308ae629b9470458590b4a1c0362d2315 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 19 Apr 2018 08:30:49 +0300
Subject: [PATCH 33/33] virtio_net: fix adding vids on big-endian
[ Upstream commit d7fad4c840f33a6bd333dd7fbb3006edbcf0017a ]
Programming vids (adding or removing them) still passes
guest-endian values in the DMA buffer. That's wrong
if guest is big-endian and when virtio 1 is enabled.
Note: this is on top of a previous patch:
virtio_net: split out ctrl buffer
Fixes: 9465a7a6f ("virtio_net: enable v1.0 support")
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/virtio_net.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 63b096c47f1e..bb15b3012aa5 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -123,7 +123,7 @@ struct control_buf {
struct virtio_net_ctrl_mq mq;
u8 promisc;
u8 allmulti;
- u16 vid;
+ __virtio16 vid;
u64 offloads;
};
@@ -1602,7 +1602,7 @@ static int virtnet_vlan_rx_add_vid(struct net_device *dev,
struct virtnet_info *vi = netdev_priv(dev);
struct scatterlist sg;
- vi->ctrl->vid = vid;
+ vi->ctrl->vid = cpu_to_virtio16(vi->vdev, vid);
sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
@@ -1617,7 +1617,7 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev,
struct virtnet_info *vi = netdev_priv(dev);
struct scatterlist sg;
- vi->ctrl->vid = vid;
+ vi->ctrl->vid = cpu_to_virtio16(vi->vdev, vid);
sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
--
2.14.3
[-- Attachment #3: net_416.mbox --]
[-- Type: Application/Octet-Stream, Size: 170289 bytes --]
From e86f8717907274fba14fbc0d31beec7e907d1f83 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 22 Apr 2018 19:11:50 +0800
Subject: [PATCH 01/52] bonding: do not set slave_dev npinfo before
slave_enable_netpoll in bond_enslave
[ Upstream commit ddea788c63094f7c483783265563dd5b50052e28 ]
After Commit 8a8efa22f51b ("bonding: sync netpoll code with bridge"), it
would set slave_dev npinfo in slave_enable_netpoll when enslaving a dev
if bond->dev->npinfo was set.
However now slave_dev npinfo is set with bond->dev->npinfo before calling
slave_enable_netpoll. With slave_dev npinfo set, __netpoll_setup called
in slave_enable_netpoll will not call slave dev's .ndo_netpoll_setup().
It causes that the lower dev of this slave dev can't set its npinfo.
One way to reproduce it:
# modprobe bonding
# brctl addbr br0
# brctl addif br0 eth1
# ifconfig bond0 192.168.122.1/24 up
# ifenslave bond0 eth2
# systemctl restart netconsole
# ifenslave bond0 br0
# ifconfig eth2 down
# systemctl restart netconsole
The netpoll won't really work.
This patch is to remove that slave_dev npinfo setting in bond_enslave().
Fixes: 8a8efa22f51b ("bonding: sync netpoll code with bridge")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/bonding/bond_main.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b7b113018853..718e4914e3a0 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1660,8 +1660,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
} /* switch(bond_mode) */
#ifdef CONFIG_NET_POLL_CONTROLLER
- slave_dev->npinfo = bond->dev->npinfo;
- if (slave_dev->npinfo) {
+ if (bond->dev->npinfo) {
if (slave_enable_netpoll(new_slave)) {
netdev_info(bond_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n");
res = -EBUSY;
--
2.14.3
From 32a4c23d2263624258b04a23b588ebdbfaa46d15 Mon Sep 17 00:00:00 2001
From: Olivier Gayot <olivier.gayot@sigexec.com>
Date: Wed, 18 Apr 2018 22:03:06 +0200
Subject: [PATCH 02/52] docs: ip-sysctl.txt: fix name of some ipv6 variables
[ Upstream commit ab913455dd59b81204b6a0d387a44697b0e0bd85 ]
The name of the following proc/sysctl entries were incorrectly
documented:
/proc/sys/net/ipv6/conf/<interface>/max_dst_opts_number
/proc/sys/net/ipv6/conf/<interface>/max_hbt_opts_number
/proc/sys/net/ipv6/conf/<interface>/max_dst_opts_length
/proc/sys/net/ipv6/conf/<interface>/max_hbt_length
Their name was set to the name of the symbol in the .data field of the
control table instead of their .proc name.
Signed-off-by: Olivier Gayot <olivier.gayot@sigexec.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
Documentation/networking/ip-sysctl.txt | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index a553d4e4a0fb..f778901c4297 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1386,26 +1386,26 @@ mld_qrv - INTEGER
Default: 2 (as specified by RFC3810 9.1)
Minimum: 1 (as specified by RFC6636 4.5)
-max_dst_opts_cnt - INTEGER
+max_dst_opts_number - INTEGER
Maximum number of non-padding TLVs allowed in a Destination
options extension header. If this value is less than zero
then unknown options are disallowed and the number of known
TLVs allowed is the absolute value of this number.
Default: 8
-max_hbh_opts_cnt - INTEGER
+max_hbh_opts_number - INTEGER
Maximum number of non-padding TLVs allowed in a Hop-by-Hop
options extension header. If this value is less than zero
then unknown options are disallowed and the number of known
TLVs allowed is the absolute value of this number.
Default: 8
-max dst_opts_len - INTEGER
+max_dst_opts_length - INTEGER
Maximum length allowed for a Destination options extension
header.
Default: INT_MAX (unlimited)
-max hbh_opts_len - INTEGER
+max_hbh_length - INTEGER
Maximum length allowed for a Hop-by-Hop options extension
header.
Default: INT_MAX (unlimited)
--
2.14.3
From 2fbea7337be736e70f0a204774f667a29f41464a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 22 Apr 2018 18:29:23 -0700
Subject: [PATCH 03/52] ipv6: add RTA_TABLE and RTA_PREFSRC to rtm_ipv6_policy
[ Upstream commit aa8f8778493c85fff480cdf8b349b1e1dcb5f243 ]
KMSAN reported use of uninit-value that I tracked to lack
of proper size check on RTA_TABLE attribute.
I also believe RTA_PREFSRC lacks a similar check.
Fixes: 86872cb57925 ("[IPv6] route: FIB6 configuration using struct fib6_config")
Fixes: c3968a857a6b ("ipv6: RTA_PREFSRC support for ipv6 route source address selection")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv6/route.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index fc74352fac12..74a2e37412b2 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3862,6 +3862,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu)
static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_GATEWAY] = { .len = sizeof(struct in6_addr) },
+ [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) },
[RTA_OIF] = { .type = NLA_U32 },
[RTA_IIF] = { .type = NLA_U32 },
[RTA_PRIORITY] = { .type = NLA_U32 },
@@ -3873,6 +3874,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_EXPIRES] = { .type = NLA_U32 },
[RTA_UID] = { .type = NLA_U32 },
[RTA_MARK] = { .type = NLA_U32 },
+ [RTA_TABLE] = { .type = NLA_U32 },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
--
2.14.3
From 7ffaf45d34621cad340c65a87104a01277525e20 Mon Sep 17 00:00:00 2001
From: Ahmed Abdelsalam <amsalam20@gmail.com>
Date: Fri, 20 Apr 2018 15:58:05 +0200
Subject: [PATCH 04/52] ipv6: sr: fix NULL pointer dereference in
seg6_do_srh_encap()- v4 pkts
[ Upstream commit a957fa190aa9d9168b33d460a5241a6d088c6265 ]
In case of seg6 in encap mode, seg6_do_srh_encap() calls set_tun_src()
in order to set the src addr of outer IPv6 header.
The net_device is required for set_tun_src(). However calling ip6_dst_idev()
on dst_entry in case of IPv4 traffic results on the following bug.
Using just dst->dev should fix this BUG.
[ 196.242461] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
[ 196.242975] PGD 800000010f076067 P4D 800000010f076067 PUD 10f060067 PMD 0
[ 196.243329] Oops: 0000 [#1] SMP PTI
[ 196.243468] Modules linked in: nfsd auth_rpcgss nfs_acl nfs lockd grace fscache sunrpc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64 crypto_simd cryptd input_leds glue_helper led_class pcspkr serio_raw mac_hid video autofs4 hid_generic usbhid hid e1000 i2c_piix4 ahci pata_acpi libahci
[ 196.244362] CPU: 2 PID: 1089 Comm: ping Not tainted 4.16.0+ #1
[ 196.244606] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[ 196.244968] RIP: 0010:seg6_do_srh_encap+0x1ac/0x300
[ 196.245236] RSP: 0018:ffffb2ce00b23a60 EFLAGS: 00010202
[ 196.245464] RAX: 0000000000000000 RBX: ffff8c7f53eea300 RCX: 0000000000000000
[ 196.245742] RDX: 0000f10000000000 RSI: ffff8c7f52085a6c RDI: ffff8c7f41166850
[ 196.246018] RBP: ffffb2ce00b23aa8 R08: 00000000000261e0 R09: ffff8c7f41166800
[ 196.246294] R10: ffffdce5040ac780 R11: ffff8c7f41166828 R12: ffff8c7f41166808
[ 196.246570] R13: ffff8c7f52085a44 R14: ffffffffb73211c0 R15: ffff8c7e69e44200
[ 196.246846] FS: 00007fc448789700(0000) GS:ffff8c7f59d00000(0000) knlGS:0000000000000000
[ 196.247286] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 196.247526] CR2: 0000000000000000 CR3: 000000010f05a000 CR4: 00000000000406e0
[ 196.247804] Call Trace:
[ 196.247972] seg6_do_srh+0x15b/0x1c0
[ 196.248156] seg6_output+0x3c/0x220
[ 196.248341] ? prandom_u32+0x14/0x20
[ 196.248526] ? ip_idents_reserve+0x6c/0x80
[ 196.248723] ? __ip_select_ident+0x90/0x100
[ 196.248923] ? ip_append_data.part.50+0x6c/0xd0
[ 196.249133] lwtunnel_output+0x44/0x70
[ 196.249328] ip_send_skb+0x15/0x40
[ 196.249515] raw_sendmsg+0x8c3/0xac0
[ 196.249701] ? _copy_from_user+0x2e/0x60
[ 196.249897] ? rw_copy_check_uvector+0x53/0x110
[ 196.250106] ? _copy_from_user+0x2e/0x60
[ 196.250299] ? copy_msghdr_from_user+0xce/0x140
[ 196.250508] sock_sendmsg+0x36/0x40
[ 196.250690] ___sys_sendmsg+0x292/0x2a0
[ 196.250881] ? _cond_resched+0x15/0x30
[ 196.251074] ? copy_termios+0x1e/0x70
[ 196.251261] ? _copy_to_user+0x22/0x30
[ 196.251575] ? tty_mode_ioctl+0x1c3/0x4e0
[ 196.251782] ? _cond_resched+0x15/0x30
[ 196.251972] ? mutex_lock+0xe/0x30
[ 196.252152] ? vvar_fault+0xd2/0x110
[ 196.252337] ? __do_fault+0x1f/0xc0
[ 196.252521] ? __handle_mm_fault+0xc1f/0x12d0
[ 196.252727] ? __sys_sendmsg+0x63/0xa0
[ 196.252919] __sys_sendmsg+0x63/0xa0
[ 196.253107] do_syscall_64+0x72/0x200
[ 196.253305] entry_SYSCALL_64_after_hwframe+0x3d/0xa2
[ 196.253530] RIP: 0033:0x7fc4480b0690
[ 196.253715] RSP: 002b:00007ffde9f252f8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[ 196.254053] RAX: ffffffffffffffda RBX: 0000000000000040 RCX: 00007fc4480b0690
[ 196.254331] RDX: 0000000000000000 RSI: 000000000060a360 RDI: 0000000000000003
[ 196.254608] RBP: 00007ffde9f253f0 R08: 00000000002d1e81 R09: 0000000000000002
[ 196.254884] R10: 00007ffde9f250c0 R11: 0000000000000246 R12: 0000000000b22070
[ 196.255205] R13: 20c49ba5e353f7cf R14: 431bde82d7b634db R15: 00007ffde9f278fe
[ 196.255484] Code: a5 0f b6 45 c0 41 88 41 28 41 0f b6 41 2c 48 c1 e0 04 49 8b 54 01 38 49 8b 44 01 30 49 89 51 20 49 89 41 18 48 8b 83 b0 00 00 00 <48> 8b 30 49 8b 86 08 0b 00 00 48 8b 40 20 48 8b 50 08 48 0b 10
[ 196.256190] RIP: seg6_do_srh_encap+0x1ac/0x300 RSP: ffffb2ce00b23a60
[ 196.256445] CR2: 0000000000000000
[ 196.256676] ---[ end trace 71af7d093603885c ]---
Fixes: 8936ef7604c11 ("ipv6: sr: fix NULL pointer dereference when setting encap source address")
Signed-off-by: Ahmed Abdelsalam <amsalam20@gmail.com>
Acked-by: David Lebrun <dlebrun@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv6/seg6_iptunnel.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index f343e6f0fc95..5fe139484919 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -136,7 +136,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
isrh->nexthdr = proto;
hdr->daddr = isrh->segments[isrh->first_segment];
- set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr);
+ set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr);
#ifdef CONFIG_IPV6_SEG6_HMAC
if (sr_has_hmac(isrh)) {
--
2.14.3
From 7c218e33e819c1c86f98913779d47b8ef1df96b0 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 17 Apr 2018 12:07:06 -0700
Subject: [PATCH 05/52] KEYS: DNS: limit the length of option strings
[ Upstream commit 9c438d7a3a52dcc2b9ed095cb87d3a5e83cf7e60 ]
Adding a dns_resolver key whose payload contains a very long option name
resulted in that string being printed in full. This hit the WARN_ONCE()
in set_precision() during the printk(), because printk() only supports a
precision of up to 32767 bytes:
precision 1000000 too large
WARNING: CPU: 0 PID: 752 at lib/vsprintf.c:2189 vsnprintf+0x4bc/0x5b0
Fix it by limiting option strings (combined name + value) to a much more
reasonable 128 bytes. The exact limit is arbitrary, but currently the
only recognized option is formatted as "dnserror=%lu" which fits well
within this limit.
Also ratelimit the printks.
Reproducer:
perl -e 'print "#", "A" x 1000000, "\x00"' | keyctl padd dns_resolver desc @s
This bug was found using syzkaller.
Reported-by: Mark Rutland <mark.rutland@arm.com>
Fixes: 4a2d789267e0 ("DNS: If the DNS server returns an error, allow that to be cached [ver #2]")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/dns_resolver/dns_key.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index e1d4d898a007..ed372d550137 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -91,9 +91,9 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
next_opt = memchr(opt, '#', end - opt) ?: end;
opt_len = next_opt - opt;
- if (!opt_len) {
- printk(KERN_WARNING
- "Empty option to dns_resolver key\n");
+ if (opt_len <= 0 || opt_len > 128) {
+ pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n",
+ opt_len);
return -EINVAL;
}
@@ -127,10 +127,8 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
}
bad_option_value:
- printk(KERN_WARNING
- "Option '%*.*s' to dns_resolver key:"
- " bad/missing value\n",
- opt_nlen, opt_nlen, opt);
+ pr_warn_ratelimited("Option '%*.*s' to dns_resolver key: bad/missing value\n",
+ opt_nlen, opt_nlen, opt);
return -EINVAL;
} while (opt = next_opt + 1, opt < end);
}
--
2.14.3
From c9f914c82f047bbdec34c810e1d943dc24ef4783 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 23 Apr 2018 16:15:14 +0200
Subject: [PATCH 06/52] l2tp: check sockaddr length in pppol2tp_connect()
[ Upstream commit eb1c28c05894a4b1f6b56c5bf072205e64cfa280 ]
Check sockaddr_len before dereferencing sp->sa_protocol, to ensure that
it actually points to valid data.
Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Reported-by: syzbot+a70ac890b23b1bf29f5c@syzkaller.appspotmail.com
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/l2tp/l2tp_ppp.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 3d7887cc599b..fc3b8b8fe1c4 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -619,6 +619,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
lock_sock(sk);
error = -EINVAL;
+
+ if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6))
+ goto end;
+
if (sp->sa_protocol != PX_PROTO_OL2TP)
goto end;
--
2.14.3
From 06165dc633470e3c05e5a12fb7a735cb57fadb1a Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 19 Apr 2018 12:25:38 -0700
Subject: [PATCH 07/52] llc: delete timers synchronously in llc_sk_free()
[ Upstream commit b905ef9ab90115d001c1658259af4b1c65088779 ]
The connection timers of an llc sock could be still flying
after we delete them in llc_sk_free(), and even possibly
after we free the sock. We could just wait synchronously
here in case of troubles.
Note, I leave other call paths as they are, since they may
not have to wait, at least we can change them to synchronously
when needed.
Also, move the code to net/llc/llc_conn.c, which is apparently
a better place.
Reported-by: <syzbot+f922284c18ea23a8e457@syzkaller.appspotmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/llc_conn.h | 1 +
net/llc/llc_c_ac.c | 9 +--------
net/llc/llc_conn.c | 22 +++++++++++++++++++++-
3 files changed, 23 insertions(+), 9 deletions(-)
diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h
index 5c40f118c0fa..df528a623548 100644
--- a/include/net/llc_conn.h
+++ b/include/net/llc_conn.h
@@ -97,6 +97,7 @@ static __inline__ char llc_backlog_type(struct sk_buff *skb)
struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority,
struct proto *prot, int kern);
+void llc_sk_stop_all_timers(struct sock *sk, bool sync);
void llc_sk_free(struct sock *sk);
void llc_sk_reset(struct sock *sk);
diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c
index 163121192aca..4d78375f9872 100644
--- a/net/llc/llc_c_ac.c
+++ b/net/llc/llc_c_ac.c
@@ -1099,14 +1099,7 @@ int llc_conn_ac_inc_tx_win_size(struct sock *sk, struct sk_buff *skb)
int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb)
{
- struct llc_sock *llc = llc_sk(sk);
-
- del_timer(&llc->pf_cycle_timer.timer);
- del_timer(&llc->ack_timer.timer);
- del_timer(&llc->rej_sent_timer.timer);
- del_timer(&llc->busy_state_timer.timer);
- llc->ack_must_be_send = 0;
- llc->ack_pf = 0;
+ llc_sk_stop_all_timers(sk, false);
return 0;
}
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 110e32bcb399..c0ac522b48a1 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -961,6 +961,26 @@ struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority, struct pr
return sk;
}
+void llc_sk_stop_all_timers(struct sock *sk, bool sync)
+{
+ struct llc_sock *llc = llc_sk(sk);
+
+ if (sync) {
+ del_timer_sync(&llc->pf_cycle_timer.timer);
+ del_timer_sync(&llc->ack_timer.timer);
+ del_timer_sync(&llc->rej_sent_timer.timer);
+ del_timer_sync(&llc->busy_state_timer.timer);
+ } else {
+ del_timer(&llc->pf_cycle_timer.timer);
+ del_timer(&llc->ack_timer.timer);
+ del_timer(&llc->rej_sent_timer.timer);
+ del_timer(&llc->busy_state_timer.timer);
+ }
+
+ llc->ack_must_be_send = 0;
+ llc->ack_pf = 0;
+}
+
/**
* llc_sk_free - Frees a LLC socket
* @sk - socket to free
@@ -973,7 +993,7 @@ void llc_sk_free(struct sock *sk)
llc->state = LLC_CONN_OUT_OF_SVC;
/* Stop all (possibly) running timers */
- llc_conn_ac_stop_all_timers(sk, NULL);
+ llc_sk_stop_all_timers(sk, true);
#ifdef DEBUG_LLC_CONN_ALLOC
printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__,
skb_queue_len(&llc->pdu_unack_q),
--
2.14.3
From 2a8778dca6dbb619bf4b877e26f722aaa5f8e73f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 15 Apr 2018 17:52:04 -0700
Subject: [PATCH 08/52] net: af_packet: fix race in PACKET_{R|T}X_RING
[ Upstream commit 5171b37d959641bbc619781caf62e61f7b940871 ]
In order to remove the race caught by syzbot [1], we need
to lock the socket before using po->tp_version as this could
change under us otherwise.
This means lock_sock() and release_sock() must be done by
packet_set_ring() callers.
[1] :
BUG: KMSAN: uninit-value in packet_set_ring+0x1254/0x3870 net/packet/af_packet.c:4249
CPU: 0 PID: 20195 Comm: syzkaller707632 Not tainted 4.16.0+ #83
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:17 [inline]
dump_stack+0x185/0x1d0 lib/dump_stack.c:53
kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
__msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
packet_set_ring+0x1254/0x3870 net/packet/af_packet.c:4249
packet_setsockopt+0x12c6/0x5a90 net/packet/af_packet.c:3662
SYSC_setsockopt+0x4b8/0x570 net/socket.c:1849
SyS_setsockopt+0x76/0xa0 net/socket.c:1828
do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x449099
RSP: 002b:00007f42b5307ce8 EFLAGS: 00000246 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 000000000070003c RCX: 0000000000449099
RDX: 0000000000000005 RSI: 0000000000000107 RDI: 0000000000000003
RBP: 0000000000700038 R08: 000000000000001c R09: 0000000000000000
R10: 00000000200000c0 R11: 0000000000000246 R12: 0000000000000000
R13: 000000000080eecf R14: 00007f42b53089c0 R15: 0000000000000001
Local variable description: ----req_u@packet_setsockopt
Variable was created at:
packet_setsockopt+0x13f/0x5a90 net/packet/af_packet.c:3612
SYSC_setsockopt+0x4b8/0x570 net/socket.c:1849
Fixes: f6fb8f100b80 ("af-packet: TPACKET_V3 flexible buffer implementation.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/packet/af_packet.c | 23 ++++++++++++++---------
1 file changed, 14 insertions(+), 9 deletions(-)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e0f3f4aeeb4f..19e5875fce89 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3008,6 +3008,7 @@ static int packet_release(struct socket *sock)
packet_flush_mclist(sk);
+ lock_sock(sk);
if (po->rx_ring.pg_vec) {
memset(&req_u, 0, sizeof(req_u));
packet_set_ring(sk, &req_u, 1, 0);
@@ -3017,6 +3018,7 @@ static int packet_release(struct socket *sock)
memset(&req_u, 0, sizeof(req_u));
packet_set_ring(sk, &req_u, 1, 1);
}
+ release_sock(sk);
f = fanout_release(sk);
@@ -3645,6 +3647,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
union tpacket_req_u req_u;
int len;
+ lock_sock(sk);
switch (po->tp_version) {
case TPACKET_V1:
case TPACKET_V2:
@@ -3655,12 +3658,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
len = sizeof(req_u.req3);
break;
}
- if (optlen < len)
- return -EINVAL;
- if (copy_from_user(&req_u.req, optval, len))
- return -EFAULT;
- return packet_set_ring(sk, &req_u, 0,
- optname == PACKET_TX_RING);
+ if (optlen < len) {
+ ret = -EINVAL;
+ } else {
+ if (copy_from_user(&req_u.req, optval, len))
+ ret = -EFAULT;
+ else
+ ret = packet_set_ring(sk, &req_u, 0,
+ optname == PACKET_TX_RING);
+ }
+ release_sock(sk);
+ return ret;
}
case PACKET_COPY_THRESH:
{
@@ -4210,8 +4218,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
/* Added to avoid minimal code churn */
struct tpacket_req *req = &req_u->req;
- lock_sock(sk);
-
rb = tx_ring ? &po->tx_ring : &po->rx_ring;
rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
@@ -4349,7 +4355,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
if (pg_vec)
free_pg_vec(pg_vec, order, req->tp_block_nr);
out:
- release_sock(sk);
return err;
}
--
2.14.3
From 744a265e08f085cbf31c7d8337de26b2c3dddfeb Mon Sep 17 00:00:00 2001
From: Wolfgang Bumiller <w.bumiller@proxmox.com>
Date: Thu, 12 Apr 2018 10:46:55 +0200
Subject: [PATCH 09/52] net: fix deadlock while clearing neighbor proxy table
[ Upstream commit 53b76cdf7e8fecec1d09e38aad2f8579882591a8 ]
When coming from ndisc_netdev_event() in net/ipv6/ndisc.c,
neigh_ifdown() is called with &nd_tbl, locking this while
clearing the proxy neighbor entries when eg. deleting an
interface. Calling the table's pndisc_destructor() with the
lock still held, however, can cause a deadlock: When a
multicast listener is available an IGMP packet of type
ICMPV6_MGM_REDUCTION may be sent out. When reaching
ip6_finish_output2(), if no neighbor entry for the target
address is found, __neigh_create() is called with &nd_tbl,
which it'll want to lock.
Move the elements into their own list, then unlock the table
and perform the destruction.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=199289
Fixes: 6fd6ce2056de ("ipv6: Do not depend on rt->n in ip6_finish_output2().")
Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/neighbour.c | 28 ++++++++++++++++++----------
1 file changed, 18 insertions(+), 10 deletions(-)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 7b7a14abba28..e22d2aefbd78 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -55,7 +55,8 @@ static void neigh_timer_handler(struct timer_list *t);
static void __neigh_notify(struct neighbour *n, int type, int flags,
u32 pid);
static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid);
-static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
+static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
+ struct net_device *dev);
#ifdef CONFIG_PROC_FS
static const struct file_operations neigh_stat_seq_fops;
@@ -291,8 +292,7 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
{
write_lock_bh(&tbl->lock);
neigh_flush_dev(tbl, dev);
- pneigh_ifdown(tbl, dev);
- write_unlock_bh(&tbl->lock);
+ pneigh_ifdown_and_unlock(tbl, dev);
del_timer_sync(&tbl->proxy_timer);
pneigh_queue_purge(&tbl->proxy_queue);
@@ -681,9 +681,10 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey,
return -ENOENT;
}
-static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
+static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
+ struct net_device *dev)
{
- struct pneigh_entry *n, **np;
+ struct pneigh_entry *n, **np, *freelist = NULL;
u32 h;
for (h = 0; h <= PNEIGH_HASHMASK; h++) {
@@ -691,16 +692,23 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
while ((n = *np) != NULL) {
if (!dev || n->dev == dev) {
*np = n->next;
- if (tbl->pdestructor)
- tbl->pdestructor(n);
- if (n->dev)
- dev_put(n->dev);
- kfree(n);
+ n->next = freelist;
+ freelist = n;
continue;
}
np = &n->next;
}
}
+ write_unlock_bh(&tbl->lock);
+ while ((n = freelist)) {
+ freelist = n->next;
+ n->next = NULL;
+ if (tbl->pdestructor)
+ tbl->pdestructor(n);
+ if (n->dev)
+ dev_put(n->dev);
+ kfree(n);
+ }
return -ENOENT;
}
--
2.14.3
From 301cd2e890168886e6aaf5c4122c5a96e01f4259 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 18 Apr 2018 11:14:44 +0200
Subject: [PATCH 10/52] net: mvpp2: Fix DMA address mask size
[ Upstream commit da42bb271305d68df6cbf99eed90542f1f1ee1c9 ]
PPv2 TX/RX descriptors uses 40bits DMA addresses, but 41 bits masks were
used (GENMASK_ULL(40, 0)).
This commit fixes that by using the correct mask.
Fixes: e7c5359f2eed ("net: mvpp2: introduce PPv2.2 HW descriptors and adapt accessors")
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/marvell/mvpp2.c | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index 5a1668cdb461..7f1083ce23da 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -838,6 +838,8 @@ enum mvpp2_bm_type {
#define MVPP2_MIB_COUNTERS_STATS_DELAY (1 * HZ)
+#define MVPP2_DESC_DMA_MASK DMA_BIT_MASK(40)
+
/* Definitions */
/* Shared Packet Processor resources */
@@ -1336,7 +1338,7 @@ static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port,
if (port->priv->hw_version == MVPP21)
return tx_desc->pp21.buf_dma_addr;
else
- return tx_desc->pp22.buf_dma_addr_ptp & GENMASK_ULL(40, 0);
+ return tx_desc->pp22.buf_dma_addr_ptp & MVPP2_DESC_DMA_MASK;
}
static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
@@ -1354,7 +1356,7 @@ static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
} else {
u64 val = (u64)addr;
- tx_desc->pp22.buf_dma_addr_ptp &= ~GENMASK_ULL(40, 0);
+ tx_desc->pp22.buf_dma_addr_ptp &= ~MVPP2_DESC_DMA_MASK;
tx_desc->pp22.buf_dma_addr_ptp |= val;
tx_desc->pp22.packet_offset = offset;
}
@@ -1414,7 +1416,7 @@ static dma_addr_t mvpp2_rxdesc_dma_addr_get(struct mvpp2_port *port,
if (port->priv->hw_version == MVPP21)
return rx_desc->pp21.buf_dma_addr;
else
- return rx_desc->pp22.buf_dma_addr_key_hash & GENMASK_ULL(40, 0);
+ return rx_desc->pp22.buf_dma_addr_key_hash & MVPP2_DESC_DMA_MASK;
}
static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port,
@@ -1423,7 +1425,7 @@ static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port,
if (port->priv->hw_version == MVPP21)
return rx_desc->pp21.buf_cookie;
else
- return rx_desc->pp22.buf_cookie_misc & GENMASK_ULL(40, 0);
+ return rx_desc->pp22.buf_cookie_misc & MVPP2_DESC_DMA_MASK;
}
static size_t mvpp2_rxdesc_size_get(struct mvpp2_port *port,
@@ -8347,7 +8349,7 @@ static int mvpp2_probe(struct platform_device *pdev)
}
if (priv->hw_version == MVPP22) {
- err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(40));
+ err = dma_set_mask(&pdev->dev, MVPP2_DESC_DMA_MASK);
if (err)
goto err_mg_clk;
/* Sadly, the BM pools all share the same register to
--
2.14.3
From d33374833e8f9556904a4e13ed26f1259ae93ceb Mon Sep 17 00:00:00 2001
From: Pawel Dembicki <paweldembicki@gmail.com>
Date: Wed, 18 Apr 2018 16:03:24 +0200
Subject: [PATCH 11/52] net: qmi_wwan: add Wistron Neweb D19Q1
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
[ Upstream commit 4ec7eb3ff6eb5c9af3a84288a8d808a857fbc22b ]
This modem is embedded on dlink dwr-960 router.
The oem configuration states:
T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 2 Spd=480 MxCh= 0
D: Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1
P: Vendor=1435 ProdID=d191 Rev=ff.ff
S: Manufacturer=Android
S: Product=Android
S: SerialNumber=0123456789ABCDEF
C:* #Ifs= 6 Cfg#= 1 Atr=80 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)
E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none)
E: Ad=84(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none)
E: Ad=86(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E: Ad=88(I) Atr=03(Int.) MxPS= 8 Ivl=32ms
E: Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=(none)
E: Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=125us
Tested on openwrt distribution
Signed-off-by: Pawel Dembicki <paweldembicki@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/usb/qmi_wwan.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index ca066b785e9f..c853e7410f5a 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1107,6 +1107,7 @@ static const struct usb_device_id products[] = {
{QMI_FIXED_INTF(0x1435, 0xd181, 3)}, /* Wistron NeWeb D18Q1 */
{QMI_FIXED_INTF(0x1435, 0xd181, 4)}, /* Wistron NeWeb D18Q1 */
{QMI_FIXED_INTF(0x1435, 0xd181, 5)}, /* Wistron NeWeb D18Q1 */
+ {QMI_FIXED_INTF(0x1435, 0xd191, 4)}, /* Wistron NeWeb D19Q1 */
{QMI_FIXED_INTF(0x16d8, 0x6003, 0)}, /* CMOTech 6003 */
{QMI_FIXED_INTF(0x16d8, 0x6007, 0)}, /* CMOTech CHE-628S */
{QMI_FIXED_INTF(0x16d8, 0x6008, 0)}, /* CMOTech CMU-301 */
--
2.14.3
From a1ae1071cc833782c2d11c03430f0ac1dba40b75 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.vnet.ibm.com>
Date: Thu, 19 Apr 2018 15:56:40 +0200
Subject: [PATCH 12/52] net/smc: fix shutdown in state SMC_LISTEN
[ Upstream commit 1255fcb2a655f05e02f3a74675a6d6525f187afd ]
Calling shutdown with SHUT_RD and SHUT_RDWR for a listening SMC socket
crashes, because
commit 127f49705823 ("net/smc: release clcsock from tcp_listen_worker")
releases the internal clcsock in smc_close_active() and sets smc->clcsock
to NULL.
For SHUT_RD the smc_close_active() call is removed.
For SHUT_RDWR the kernel_sock_shutdown() call is omitted, since the
clcsock is already released.
Fixes: 127f49705823 ("net/smc: release clcsock from tcp_listen_worker")
Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Reported-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/smc/af_smc.c | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 1e0d780855c3..afd5a935bbcb 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1254,14 +1254,12 @@ static int smc_shutdown(struct socket *sock, int how)
rc = smc_close_shutdown_write(smc);
break;
case SHUT_RD:
- if (sk->sk_state == SMC_LISTEN)
- rc = smc_close_active(smc);
- else
- rc = 0;
- /* nothing more to do because peer is not involved */
+ rc = 0;
+ /* nothing more to do because peer is not involved */
break;
}
- rc1 = kernel_sock_shutdown(smc->clcsock, how);
+ if (smc->clcsock)
+ rc1 = kernel_sock_shutdown(smc->clcsock, how);
/* map sock_shutdown_cmd constants to sk_shutdown value range */
sk->sk_shutdown |= how + 1;
--
2.14.3
From de508e9e83f758fefa0f33b8c138d9bf32f5c482 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Wed, 18 Apr 2018 10:57:55 +0100
Subject: [PATCH 13/52] net: stmmac: Disable ACS Feature for GMAC >= 4
[ Upstream commit 565020aaeebfa7c8b3ec077bee38f4c15acc9905 ]
ACS Feature is currently enabled for GMAC >= 4 but the llc_snap status
is never checked in descriptor rx_status callback. This will cause
stmmac to always strip packets even that ACS feature is already
stripping them.
Lets be safe and disable the ACS feature for GMAC >= 4 and always strip
the packets for this GMAC version.
Fixes: 477286b53f55 ("stmmac: add GMAC4 core support")
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/stmicro/stmmac/dwmac4.h | 2 +-
drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 7 -------
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 7 ++++++-
3 files changed, 7 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index 7761a26ec9c5..e7565416639b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -343,7 +343,7 @@ enum power_event {
#define MTL_RX_OVERFLOW_INT BIT(16)
/* Default operating mode of the MAC */
-#define GMAC_CORE_INIT (GMAC_CONFIG_JD | GMAC_CONFIG_PS | GMAC_CONFIG_ACS | \
+#define GMAC_CORE_INIT (GMAC_CONFIG_JD | GMAC_CONFIG_PS | \
GMAC_CONFIG_BE | GMAC_CONFIG_DCRS)
/* To dump the core regs excluding the Address Registers */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 63795ecafc8d..26dfb75e927a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -30,13 +30,6 @@ static void dwmac4_core_init(struct mac_device_info *hw,
value |= GMAC_CORE_INIT;
- /* Clear ACS bit because Ethernet switch tagging formats such as
- * Broadcom tags can look like invalid LLC/SNAP packets and cause the
- * hardware to truncate packets on reception.
- */
- if (netdev_uses_dsa(dev))
- value &= ~GMAC_CONFIG_ACS;
-
if (mtu > 1500)
value |= GMAC_CONFIG_2K;
if (mtu > 2000)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 7ad841434ec8..3ea343b45d93 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3435,8 +3435,13 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
/* ACS is set; GMAC core strips PAD/FCS for IEEE 802.3
* Type frames (LLC/LLC-SNAP)
+ *
+ * llc_snap is never checked in GMAC >= 4, so this ACS
+ * feature is always disabled and packets need to be
+ * stripped manually.
*/
- if (unlikely(status != llc_snap))
+ if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00) ||
+ unlikely(status != llc_snap))
frame_len -= ETH_FCS_LEN;
if (netif_msg_rx_status(priv)) {
--
2.14.3
From 498507ae4b92a783be680ef9df3d10a737a8253a Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 23 Apr 2018 17:37:03 -0400
Subject: [PATCH 14/52] packet: fix bitfield update race
[ Upstream commit a6361f0ca4b25460f2cdf3235ebe8115f622901e ]
Updates to the bitfields in struct packet_sock are not atomic.
Serialize these read-modify-write cycles.
Move po->running into a separate variable. Its writes are protected by
po->bind_lock (except for one startup case at packet_create). Also
replace a textual precondition warning with lockdep annotation.
All others are set only in packet_setsockopt. Serialize these
updates by holding the socket lock. Analogous to other field updates,
also hold the lock when testing whether a ring is active (pg_vec).
Fixes: 8dc419447415 ("[PACKET]: Add optional checksum computation for recvmsg")
Reported-by: DaeRyong Jeong <threeearcat@gmail.com>
Reported-by: Byoungyoung Lee <byoungyoung@purdue.edu>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/packet/af_packet.c | 60 ++++++++++++++++++++++++++++++++++++--------------
net/packet/internal.h | 10 ++++-----
2 files changed, 49 insertions(+), 21 deletions(-)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 19e5875fce89..3b43b1fcd618 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -329,11 +329,11 @@ static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
skb_set_queue_mapping(skb, queue_index);
}
-/* register_prot_hook must be invoked with the po->bind_lock held,
+/* __register_prot_hook must be invoked through register_prot_hook
* or from a context in which asynchronous accesses to the packet
* socket is not possible (packet_create()).
*/
-static void register_prot_hook(struct sock *sk)
+static void __register_prot_hook(struct sock *sk)
{
struct packet_sock *po = pkt_sk(sk);
@@ -348,8 +348,13 @@ static void register_prot_hook(struct sock *sk)
}
}
-/* {,__}unregister_prot_hook() must be invoked with the po->bind_lock
- * held. If the sync parameter is true, we will temporarily drop
+static void register_prot_hook(struct sock *sk)
+{
+ lockdep_assert_held_once(&pkt_sk(sk)->bind_lock);
+ __register_prot_hook(sk);
+}
+
+/* If the sync parameter is true, we will temporarily drop
* the po->bind_lock and do a synchronize_net to make sure no
* asynchronous packet processing paths still refer to the elements
* of po->prot_hook. If the sync parameter is false, it is the
@@ -359,6 +364,8 @@ static void __unregister_prot_hook(struct sock *sk, bool sync)
{
struct packet_sock *po = pkt_sk(sk);
+ lockdep_assert_held_once(&po->bind_lock);
+
po->running = 0;
if (po->fanout)
@@ -3252,7 +3259,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
if (proto) {
po->prot_hook.type = proto;
- register_prot_hook(sk);
+ __register_prot_hook(sk);
}
mutex_lock(&net->packet.sklist_lock);
@@ -3734,12 +3741,18 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (optlen != sizeof(val))
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->tp_loss = !!val;
- return 0;
+
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->tp_loss = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
+ return ret;
}
case PACKET_AUXDATA:
{
@@ -3750,7 +3763,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
+ lock_sock(sk);
po->auxdata = !!val;
+ release_sock(sk);
return 0;
}
case PACKET_ORIGDEV:
@@ -3762,7 +3777,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
+ lock_sock(sk);
po->origdev = !!val;
+ release_sock(sk);
return 0;
}
case PACKET_VNET_HDR:
@@ -3771,15 +3788,20 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (sock->type != SOCK_RAW)
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (optlen < sizeof(val))
return -EINVAL;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->has_vnet_hdr = !!val;
- return 0;
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->has_vnet_hdr = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
+ return ret;
}
case PACKET_TIMESTAMP:
{
@@ -3817,11 +3839,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (optlen != sizeof(val))
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->tp_tx_has_off = !!val;
+
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->tp_tx_has_off = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
return 0;
}
case PACKET_QDISC_BYPASS:
diff --git a/net/packet/internal.h b/net/packet/internal.h
index a1d2b2319ae9..3bb7c5fb3bff 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -112,10 +112,12 @@ struct packet_sock {
int copy_thresh;
spinlock_t bind_lock;
struct mutex pg_vec_lock;
- unsigned int running:1, /* prot_hook is attached*/
- auxdata:1,
+ unsigned int running; /* bind_lock must be held */
+ unsigned int auxdata:1, /* writer must hold sock lock */
origdev:1,
- has_vnet_hdr:1;
+ has_vnet_hdr:1,
+ tp_loss:1,
+ tp_tx_has_off:1;
int pressure;
int ifindex; /* bound device */
__be16 num;
@@ -125,8 +127,6 @@ struct packet_sock {
enum tpacket_versions tp_version;
unsigned int tp_hdrlen;
unsigned int tp_reserve;
- unsigned int tp_loss:1;
- unsigned int tp_tx_has_off:1;
unsigned int tp_tstamp;
struct net_device __rcu *cached_dev;
int (*xmit)(struct sk_buff *skb);
--
2.14.3
From 65719bc47ebd0c536e648c3c27a3b015bc033d92 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 23 Apr 2018 16:38:27 +0200
Subject: [PATCH 15/52] pppoe: check sockaddr length in pppoe_connect()
[ Upstream commit a49e2f5d5fb141884452ddb428f551b123d436b5 ]
We must validate sockaddr_len, otherwise userspace can pass fewer data
than we expect and we end up accessing invalid data.
Fixes: 224cf5ad14c0 ("ppp: Move the PPP drivers")
Reported-by: syzbot+4f03bdf92fdf9ef5ddab@syzkaller.appspotmail.com
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ppp/pppoe.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 5aa59f41bf8c..71e2aef6b7a1 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -620,6 +620,10 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
lock_sock(sk);
error = -EINVAL;
+
+ if (sockaddr_len != sizeof(struct sockaddr_pppox))
+ goto end;
+
if (sp->sa_protocol != PX_PROTO_OE)
goto end;
--
2.14.3
From aca388e7d1b01598375ec96e62e1e4f35f55524c Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 16 Apr 2018 13:17:50 +0300
Subject: [PATCH 16/52] Revert "macsec: missing dev_put() on error in
macsec_newlink()"
[ Upstream commit bd28899dd34f9283c567f7eeb31bb546f10820b5 ]
This patch is just wrong, sorry. I was trying to fix a static checker
warning and misread the code. The reference taken in macsec_newlink()
is released in macsec_free_netdev() when the netdevice is destroyed.
This reverts commit 5dcd8400884cc4a043a6d4617e042489e5d566a9.
Reported-by: Laura Abbott <labbott@redhat.com>
Fixes: 5dcd8400884c ("macsec: missing dev_put() on error in macsec_newlink()")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/macsec.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 9cbb0c8a896a..7de88b33d5b9 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -3277,7 +3277,7 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
err = netdev_upper_dev_link(real_dev, dev, extack);
if (err < 0)
- goto put_dev;
+ goto unregister;
/* need to be already registered so that ->init has run and
* the MAC addr is set
@@ -3316,8 +3316,7 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
macsec_del_dev(macsec);
unlink:
netdev_upper_dev_unlink(real_dev, dev);
-put_dev:
- dev_put(real_dev);
+unregister:
unregister_netdevice(dev);
return err;
}
--
2.14.3
From b11149153fb18bc177045720b25104b17655f787 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 12 Apr 2018 14:24:31 +0800
Subject: [PATCH 17/52] sctp: do not check port in sctp_inet6_cmp_addr
[ Upstream commit 1071ec9d453a38023579714b64a951a2fb982071 ]
pf->cmp_addr() is called before binding a v6 address to the sock. It
should not check ports, like in sctp_inet_cmp_addr.
But sctp_inet6_cmp_addr checks the addr by invoking af(6)->cmp_addr,
sctp_v6_cmp_addr where it also compares the ports.
This would cause that setsockopt(SCTP_SOCKOPT_BINDX_ADD) could bind
multiple duplicated IPv6 addresses after Commit 40b4f0fd74e4 ("sctp:
lack the check for ports in sctp_v6_cmp_addr").
This patch is to remove af->cmp_addr called in sctp_inet6_cmp_addr,
but do the proper check for both v6 addrs and v4mapped addrs.
v1->v2:
- define __sctp_v6_cmp_addr to do the common address comparison
used for both pf and af v6 cmp_addr.
Fixes: 40b4f0fd74e4 ("sctp: lack the check for ports in sctp_v6_cmp_addr")
Reported-by: Jianwen Ji <jiji@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sctp/ipv6.c | 60 ++++++++++++++++++++++++++++-----------------------------
1 file changed, 30 insertions(+), 30 deletions(-)
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index f6d3d0c1e133..07b64719d1bc 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -521,46 +521,49 @@ static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr,
addr->v6.sin6_scope_id = 0;
}
-/* Compare addresses exactly.
- * v4-mapped-v6 is also in consideration.
- */
-static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
- const union sctp_addr *addr2)
+static int __sctp_v6_cmp_addr(const union sctp_addr *addr1,
+ const union sctp_addr *addr2)
{
if (addr1->sa.sa_family != addr2->sa.sa_family) {
if (addr1->sa.sa_family == AF_INET &&
addr2->sa.sa_family == AF_INET6 &&
- ipv6_addr_v4mapped(&addr2->v6.sin6_addr)) {
- if (addr2->v6.sin6_port == addr1->v4.sin_port &&
- addr2->v6.sin6_addr.s6_addr32[3] ==
- addr1->v4.sin_addr.s_addr)
- return 1;
- }
+ ipv6_addr_v4mapped(&addr2->v6.sin6_addr) &&
+ addr2->v6.sin6_addr.s6_addr32[3] ==
+ addr1->v4.sin_addr.s_addr)
+ return 1;
+
if (addr2->sa.sa_family == AF_INET &&
addr1->sa.sa_family == AF_INET6 &&
- ipv6_addr_v4mapped(&addr1->v6.sin6_addr)) {
- if (addr1->v6.sin6_port == addr2->v4.sin_port &&
- addr1->v6.sin6_addr.s6_addr32[3] ==
- addr2->v4.sin_addr.s_addr)
- return 1;
- }
+ ipv6_addr_v4mapped(&addr1->v6.sin6_addr) &&
+ addr1->v6.sin6_addr.s6_addr32[3] ==
+ addr2->v4.sin_addr.s_addr)
+ return 1;
+
return 0;
}
- if (addr1->v6.sin6_port != addr2->v6.sin6_port)
- return 0;
+
if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr))
return 0;
+
/* If this is a linklocal address, compare the scope_id. */
- if (ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) {
- if (addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id &&
- (addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)) {
- return 0;
- }
- }
+ if ((ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) &&
+ addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id &&
+ addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)
+ return 0;
return 1;
}
+/* Compare addresses exactly.
+ * v4-mapped-v6 is also in consideration.
+ */
+static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
+ const union sctp_addr *addr2)
+{
+ return __sctp_v6_cmp_addr(addr1, addr2) &&
+ addr1->v6.sin6_port == addr2->v6.sin6_port;
+}
+
/* Initialize addr struct to INADDR_ANY. */
static void sctp_v6_inaddr_any(union sctp_addr *addr, __be16 port)
{
@@ -846,8 +849,8 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1,
const union sctp_addr *addr2,
struct sctp_sock *opt)
{
- struct sctp_af *af1, *af2;
struct sock *sk = sctp_opt2sk(opt);
+ struct sctp_af *af1, *af2;
af1 = sctp_get_af_specific(addr1->sa.sa_family);
af2 = sctp_get_af_specific(addr2->sa.sa_family);
@@ -863,10 +866,7 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1,
if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2))
return 1;
- if (addr1->sa.sa_family != addr2->sa.sa_family)
- return 0;
-
- return af1->cmp_addr(addr1, addr2);
+ return __sctp_v6_cmp_addr(addr1, addr2);
}
/* Verify that the provided sockaddr looks bindable. Common verification,
--
2.14.3
From ab82cd30093b5c0b818a9288d07e49794b3c6fc8 Mon Sep 17 00:00:00 2001
From: Doron Roberts-Kedes <doronrk@fb.com>
Date: Fri, 20 Apr 2018 12:11:11 -0700
Subject: [PATCH 18/52] strparser: Do not call mod_delayed_work with a timeout
of LONG_MAX
[ Upstream commit 7c5aba211dd61f41d737a2c51729eb9fdcd3edf4 ]
struct sock's sk_rcvtimeo is initialized to
LONG_MAX/MAX_SCHEDULE_TIMEOUT in sock_init_data. Calling
mod_delayed_work with a timeout of LONG_MAX causes spurious execution of
the work function. timer->expires is set equal to jiffies + LONG_MAX.
When timer_base->clk falls behind the current value of jiffies,
the delta between timer_base->clk and jiffies + LONG_MAX causes the
expiration to be in the past. Returning early from strp_start_timer if
timeo == LONG_MAX solves this problem.
Found while testing net/tls_sw recv path.
Fixes: 43a0c6751a322847 ("strparser: Stream parser for messages")
Reviewed-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/strparser/strparser.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index b9283ce5cd85..8d177506901c 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -67,7 +67,7 @@ static void strp_abort_strp(struct strparser *strp, int err)
static void strp_start_timer(struct strparser *strp, long timeo)
{
- if (timeo)
+ if (timeo && timeo != LONG_MAX)
mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo);
}
--
2.14.3
From 1351b051b050a83d344bbf7212e41e2fbbd8c439 Mon Sep 17 00:00:00 2001
From: Doron Roberts-Kedes <doronrk@fb.com>
Date: Wed, 11 Apr 2018 15:05:16 -0700
Subject: [PATCH 19/52] strparser: Fix incorrect strp->need_bytes value.
[ Upstream commit 9d0c75bf6e03d9bf80c55b0f677dc9b982958fd5 ]
strp_data_ready resets strp->need_bytes to 0 if strp_peek_len indicates
that the remainder of the message has been received. However,
do_strp_work does not reset strp->need_bytes to 0. If do_strp_work
completes a partial message, the value of strp->need_bytes will continue
to reflect the needed bytes of the previous message, causing
future invocations of strp_data_ready to return early if
strp->need_bytes is less than strp_peek_len. Resetting strp->need_bytes
to 0 in __strp_recv on handing a full message to the upper layer solves
this problem.
__strp_recv also calculates strp->need_bytes using stm->accum_len before
stm->accum_len has been incremented by cand_len. This can cause
strp->need_bytes to be equal to the full length of the message instead
of the full length minus the accumulated length. This, in turn, causes
strp_data_ready to return early, even when there is sufficient data to
complete the partial message. Incrementing stm->accum_len before using
it to calculate strp->need_bytes solves this problem.
Found while testing net/tls_sw recv path.
Fixes: 43a0c6751a322847 ("strparser: Stream parser for messages")
Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/strparser/strparser.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 8d177506901c..092bebc70048 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -296,9 +296,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
strp_start_timer(strp, timeo);
}
+ stm->accum_len += cand_len;
strp->need_bytes = stm->strp.full_len -
stm->accum_len;
- stm->accum_len += cand_len;
stm->early_eaten = cand_len;
STRP_STATS_ADD(strp->stats.bytes, cand_len);
desc->count = 0; /* Stop reading socket */
@@ -321,6 +321,7 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
/* Hurray, we have a new message! */
cancel_delayed_work(&strp->msg_timer_work);
strp->skb_head = NULL;
+ strp->need_bytes = 0;
STRP_STATS_INCR(strp->stats.msgs);
/* Give skb to upper layer */
@@ -410,9 +411,7 @@ void strp_data_ready(struct strparser *strp)
return;
if (strp->need_bytes) {
- if (strp_peek_len(strp) >= strp->need_bytes)
- strp->need_bytes = 0;
- else
+ if (strp_peek_len(strp) < strp->need_bytes)
return;
}
--
2.14.3
From 5b3d401fff61174f7bf2031ef9a9a34d2426aa86 Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Sat, 14 Apr 2018 20:44:46 -0400
Subject: [PATCH 20/52] tcp: clear tp->packets_out when purging write queue
[ Upstream commit bffd168c3fc5cc7d2bad4c668fa90e7a9010db4b ]
Clear tp->packets_out when purging the write queue, otherwise
tcp_rearm_rto() mistakenly assumes TCP write queue is not empty.
This results in NULL pointer dereference.
Also, remove the redundant `tp->packets_out = 0` from
tcp_disconnect(), since tcp_disconnect() calls
tcp_write_queue_purge().
Fixes: a27fd7a8ed38 (tcp: purge write queue upon RST)
Reported-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Reported-by: Sami Farin <hvtaifwkbgefbaei@gmail.com>
Tested-by: Sami Farin <hvtaifwkbgefbaei@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/tcp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8b8059b7af4d..bb48cd142b92 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2385,6 +2385,7 @@ void tcp_write_queue_purge(struct sock *sk)
INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue);
sk_mem_reclaim(sk);
tcp_clear_all_retrans_hints(tcp_sk(sk));
+ tcp_sk(sk)->packets_out = 0;
}
int tcp_disconnect(struct sock *sk, int flags)
@@ -2434,7 +2435,6 @@ int tcp_disconnect(struct sock *sk, int flags)
icsk->icsk_backoff = 0;
tp->snd_cwnd = 2;
icsk->icsk_probes_out = 0;
- tp->packets_out = 0;
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_cnt = 0;
tp->window_clamp = 0;
--
2.14.3
From ae7fbd1857dee4b878e3b3087d0a8481d751b9d3 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Fri, 20 Apr 2018 15:57:30 +0200
Subject: [PATCH 21/52] tcp: don't read out-of-bounds opsize
[ Upstream commit 7e5a206ab686f098367b61aca989f5cdfa8114a3 ]
The old code reads the "opsize" variable from out-of-bounds memory (first
byte behind the segment) if a broken TCP segment ends directly after an
opcode that is neither EOL nor NOP.
The result of the read isn't used for anything, so the worst thing that
could theoretically happen is a pagefault; and since the physmap is usually
mostly contiguous, even that seems pretty unlikely.
The following C reproducer triggers the uninitialized read - however, you
can't actually see anything happen unless you put something like a
pr_warn() in tcp_parse_md5sig_option() to print the opsize.
====================================
#define _GNU_SOURCE
#include <arpa/inet.h>
#include <stdlib.h>
#include <errno.h>
#include <stdarg.h>
#include <net/if.h>
#include <linux/if.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/in.h>
#include <linux/if_tun.h>
#include <err.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <string.h>
#include <stdio.h>
#include <unistd.h>
#include <sys/ioctl.h>
#include <assert.h>
void systemf(const char *command, ...) {
char *full_command;
va_list ap;
va_start(ap, command);
if (vasprintf(&full_command, command, ap) == -1)
err(1, "vasprintf");
va_end(ap);
printf("systemf: <<<%s>>>\n", full_command);
system(full_command);
}
char *devname;
int tun_alloc(char *name) {
int fd = open("/dev/net/tun", O_RDWR);
if (fd == -1)
err(1, "open tun dev");
static struct ifreq req = { .ifr_flags = IFF_TUN|IFF_NO_PI };
strcpy(req.ifr_name, name);
if (ioctl(fd, TUNSETIFF, &req))
err(1, "TUNSETIFF");
devname = req.ifr_name;
printf("device name: %s\n", devname);
return fd;
}
#define IPADDR(a,b,c,d) (((a)<<0)+((b)<<8)+((c)<<16)+((d)<<24))
void sum_accumulate(unsigned int *sum, void *data, int len) {
assert((len&2)==0);
for (int i=0; i<len/2; i++) {
*sum += ntohs(((unsigned short *)data)[i]);
}
}
unsigned short sum_final(unsigned int sum) {
sum = (sum >> 16) + (sum & 0xffff);
sum = (sum >> 16) + (sum & 0xffff);
return htons(~sum);
}
void fix_ip_sum(struct iphdr *ip) {
unsigned int sum = 0;
sum_accumulate(&sum, ip, sizeof(*ip));
ip->check = sum_final(sum);
}
void fix_tcp_sum(struct iphdr *ip, struct tcphdr *tcp) {
unsigned int sum = 0;
struct {
unsigned int saddr;
unsigned int daddr;
unsigned char pad;
unsigned char proto_num;
unsigned short tcp_len;
} fakehdr = {
.saddr = ip->saddr,
.daddr = ip->daddr,
.proto_num = ip->protocol,
.tcp_len = htons(ntohs(ip->tot_len) - ip->ihl*4)
};
sum_accumulate(&sum, &fakehdr, sizeof(fakehdr));
sum_accumulate(&sum, tcp, tcp->doff*4);
tcp->check = sum_final(sum);
}
int main(void) {
int tun_fd = tun_alloc("inject_dev%d");
systemf("ip link set %s up", devname);
systemf("ip addr add 192.168.42.1/24 dev %s", devname);
struct {
struct iphdr ip;
struct tcphdr tcp;
unsigned char tcp_opts[20];
} __attribute__((packed)) syn_packet = {
.ip = {
.ihl = sizeof(struct iphdr)/4,
.version = 4,
.tot_len = htons(sizeof(syn_packet)),
.ttl = 30,
.protocol = IPPROTO_TCP,
/* FIXUP check */
.saddr = IPADDR(192,168,42,2),
.daddr = IPADDR(192,168,42,1)
},
.tcp = {
.source = htons(1),
.dest = htons(1337),
.seq = 0x12345678,
.doff = (sizeof(syn_packet.tcp)+sizeof(syn_packet.tcp_opts))/4,
.syn = 1,
.window = htons(64),
.check = 0 /*FIXUP*/
},
.tcp_opts = {
/* INVALID: trailing MD5SIG opcode after NOPs */
1, 1, 1, 1, 1,
1, 1, 1, 1, 1,
1, 1, 1, 1, 1,
1, 1, 1, 1, 19
}
};
fix_ip_sum(&syn_packet.ip);
fix_tcp_sum(&syn_packet.ip, &syn_packet.tcp);
while (1) {
int write_res = write(tun_fd, &syn_packet, sizeof(syn_packet));
if (write_res != sizeof(syn_packet))
err(1, "packet write failed");
}
}
====================================
Fixes: cfb6eeb4c860 ("[TCP]: MD5 Signature Option (RFC2385) support.")
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/tcp_input.c | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ff6cd98ce8d5..31ca27fdde66 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3871,11 +3871,8 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th)
int length = (th->doff << 2) - sizeof(*th);
const u8 *ptr = (const u8 *)(th + 1);
- /* If the TCP option is too short, we can short cut */
- if (length < TCPOLEN_MD5SIG)
- return NULL;
-
- while (length > 0) {
+ /* If not enough data remaining, we can short cut */
+ while (length >= TCPOLEN_MD5SIG) {
int opcode = *ptr++;
int opsize;
--
2.14.3
From a1c88dab7ea2feddfe1465666d766bf7eb913ce6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Apr 2018 14:36:28 -0700
Subject: [PATCH 22/52] tcp: md5: reject TCP_MD5SIG or TCP_MD5SIG_EXT on
established sockets
[ Upstream commit 7212303268918b9a203aebeacfdbd83b5e87b20d ]
syzbot/KMSAN reported an uninit-value in tcp_parse_options() [1]
I believe this was caused by a TCP_MD5SIG being set on live
flow.
This is highly unexpected, since TCP option space is limited.
For instance, presence of TCP MD5 option automatically disables
TCP TimeStamp option at SYN/SYNACK time, which we can not do
once flow has been established.
Really, adding/deleting an MD5 key only makes sense on sockets
in CLOSE or LISTEN state.
[1]
BUG: KMSAN: uninit-value in tcp_parse_options+0xd74/0x1a30 net/ipv4/tcp_input.c:3720
CPU: 1 PID: 6177 Comm: syzkaller192004 Not tainted 4.16.0+ #83
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:17 [inline]
dump_stack+0x185/0x1d0 lib/dump_stack.c:53
kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
__msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
tcp_parse_options+0xd74/0x1a30 net/ipv4/tcp_input.c:3720
tcp_fast_parse_options net/ipv4/tcp_input.c:3858 [inline]
tcp_validate_incoming+0x4f1/0x2790 net/ipv4/tcp_input.c:5184
tcp_rcv_established+0xf60/0x2bb0 net/ipv4/tcp_input.c:5453
tcp_v4_do_rcv+0x6cd/0xd90 net/ipv4/tcp_ipv4.c:1469
sk_backlog_rcv include/net/sock.h:908 [inline]
__release_sock+0x2d6/0x680 net/core/sock.c:2271
release_sock+0x97/0x2a0 net/core/sock.c:2786
tcp_sendmsg+0xd6/0x100 net/ipv4/tcp.c:1464
inet_sendmsg+0x48d/0x740 net/ipv4/af_inet.c:764
sock_sendmsg_nosec net/socket.c:630 [inline]
sock_sendmsg net/socket.c:640 [inline]
SYSC_sendto+0x6c3/0x7e0 net/socket.c:1747
SyS_sendto+0x8a/0xb0 net/socket.c:1715
do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x448fe9
RSP: 002b:00007fd472c64d38 EFLAGS: 00000216 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00000000006e5a30 RCX: 0000000000448fe9
RDX: 000000000000029f RSI: 0000000020a88f88 RDI: 0000000000000004
RBP: 00000000006e5a34 R08: 0000000020e68000 R09: 0000000000000010
R10: 00000000200007fd R11: 0000000000000216 R12: 0000000000000000
R13: 00007fff074899ef R14: 00007fd472c659c0 R15: 0000000000000009
Uninit was created at:
kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188
kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314
kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321
slab_post_alloc_hook mm/slab.h:445 [inline]
slab_alloc_node mm/slub.c:2737 [inline]
__kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369
__kmalloc_reserve net/core/skbuff.c:138 [inline]
__alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206
alloc_skb include/linux/skbuff.h:984 [inline]
tcp_send_ack+0x18c/0x910 net/ipv4/tcp_output.c:3624
__tcp_ack_snd_check net/ipv4/tcp_input.c:5040 [inline]
tcp_ack_snd_check net/ipv4/tcp_input.c:5053 [inline]
tcp_rcv_established+0x2103/0x2bb0 net/ipv4/tcp_input.c:5469
tcp_v4_do_rcv+0x6cd/0xd90 net/ipv4/tcp_ipv4.c:1469
sk_backlog_rcv include/net/sock.h:908 [inline]
__release_sock+0x2d6/0x680 net/core/sock.c:2271
release_sock+0x97/0x2a0 net/core/sock.c:2786
tcp_sendmsg+0xd6/0x100 net/ipv4/tcp.c:1464
inet_sendmsg+0x48d/0x740 net/ipv4/af_inet.c:764
sock_sendmsg_nosec net/socket.c:630 [inline]
sock_sendmsg net/socket.c:640 [inline]
SYSC_sendto+0x6c3/0x7e0 net/socket.c:1747
SyS_sendto+0x8a/0xb0 net/socket.c:1715
do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
Fixes: cfb6eeb4c860 ("[TCP]: MD5 Signature Option (RFC2385) support.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/tcp.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bb48cd142b92..1ab8733dac5f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2830,8 +2830,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
#ifdef CONFIG_TCP_MD5SIG
case TCP_MD5SIG:
case TCP_MD5SIG_EXT:
- /* Read the IP->Key mappings from userspace */
- err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
+ if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
+ err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
+ else
+ err = -EINVAL;
break;
#endif
case TCP_USER_TIMEOUT:
--
2.14.3
From 97c9b9642efbd260679e7eb52558ade9fb64b045 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 13 Apr 2018 13:59:25 +0200
Subject: [PATCH 23/52] team: avoid adding twice the same option to the event
list
[ Upstream commit 4fb0534fb7bbc2346ba7d3a072b538007f4135a5 ]
When parsing the options provided by the user space,
team_nl_cmd_options_set() insert them in a temporary list to send
multiple events with a single message.
While each option's attribute is correctly validated, the code does
not check for duplicate entries before inserting into the event
list.
Exploiting the above, the syzbot was able to trigger the following
splat:
kernel BUG at lib/list_debug.c:31!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
(ftrace buffer empty)
Modules linked in:
CPU: 0 PID: 4466 Comm: syzkaller556835 Not tainted 4.16.0+ #17
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
RIP: 0010:__list_add_valid+0xaa/0xb0 lib/list_debug.c:29
RSP: 0018:ffff8801b04bf248 EFLAGS: 00010286
RAX: 0000000000000058 RBX: ffff8801c8fc7a90 RCX: 0000000000000000
RDX: 0000000000000058 RSI: ffffffff815fbf41 RDI: ffffed0036097e3f
RBP: ffff8801b04bf260 R08: ffff8801b0b2a700 R09: ffffed003b604f90
R10: ffffed003b604f90 R11: ffff8801db027c87 R12: ffff8801c8fc7a90
R13: ffff8801c8fc7a90 R14: dffffc0000000000 R15: 0000000000000000
FS: 0000000000b98880(0000) GS:ffff8801db000000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000000043fc30 CR3: 00000001afe8e000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
__list_add include/linux/list.h:60 [inline]
list_add include/linux/list.h:79 [inline]
team_nl_cmd_options_set+0x9ff/0x12b0 drivers/net/team/team.c:2571
genl_family_rcv_msg+0x889/0x1120 net/netlink/genetlink.c:599
genl_rcv_msg+0xc6/0x170 net/netlink/genetlink.c:624
netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2448
genl_rcv+0x28/0x40 net/netlink/genetlink.c:635
netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
netlink_unicast+0x58b/0x740 net/netlink/af_netlink.c:1336
netlink_sendmsg+0x9f0/0xfa0 net/netlink/af_netlink.c:1901
sock_sendmsg_nosec net/socket.c:629 [inline]
sock_sendmsg+0xd5/0x120 net/socket.c:639
___sys_sendmsg+0x805/0x940 net/socket.c:2117
__sys_sendmsg+0x115/0x270 net/socket.c:2155
SYSC_sendmsg net/socket.c:2164 [inline]
SyS_sendmsg+0x29/0x30 net/socket.c:2162
do_syscall_64+0x29e/0x9d0 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x4458b9
RSP: 002b:00007ffd1d4a7278 EFLAGS: 00000213 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 000000000000001b RCX: 00000000004458b9
RDX: 0000000000000010 RSI: 0000000020000d00 RDI: 0000000000000004
RBP: 00000000004a74ed R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000213 R12: 00007ffd1d4a7348
R13: 0000000000402a60 R14: 0000000000000000 R15: 0000000000000000
Code: 75 e8 eb a9 48 89 f7 48 89 75 e8 e8 d1 85 7b fe 48 8b 75 e8 eb bb 48
89 f2 48 89 d9 4c 89 e6 48 c7 c7 a0 84 d8 87 e8 ea 67 28 fe <0f> 0b 0f 1f
40 00 48 b8 00 00 00 00 00 fc ff df 55 48 89 e5 41
RIP: __list_add_valid+0xaa/0xb0 lib/list_debug.c:29 RSP: ffff8801b04bf248
This changeset addresses the avoiding list_add() if the current
option is already present in the event list.
Reported-and-tested-by: syzbot+4d4af685432dc0e56c91@syzkaller.appspotmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Fixes: 2fcdb2c9e659 ("team: allow to send multiple set events in one message")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/team/team.c | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index befed2d22bf4..13eaae7005e8 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -261,6 +261,17 @@ static void __team_option_inst_mark_removed_port(struct team *team,
}
}
+static bool __team_option_inst_tmp_find(const struct list_head *opts,
+ const struct team_option_inst *needle)
+{
+ struct team_option_inst *opt_inst;
+
+ list_for_each_entry(opt_inst, opts, tmp_list)
+ if (opt_inst == needle)
+ return true;
+ return false;
+}
+
static int __team_options_register(struct team *team,
const struct team_option *option,
size_t option_count)
@@ -2562,6 +2573,14 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
if (err)
goto team_put;
opt_inst->changed = true;
+
+ /* dumb/evil user-space can send us duplicate opt,
+ * keep only the last one
+ */
+ if (__team_option_inst_tmp_find(&opt_inst_list,
+ opt_inst))
+ continue;
+
list_add(&opt_inst->tmp_list, &opt_inst_list);
}
if (!opt_found) {
--
2.14.3
From e85b25a45eefcc0e488d0a7364aa6736173865d7 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 24 Apr 2018 14:33:37 +0800
Subject: [PATCH 24/52] team: fix netconsole setup over team
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
[ Upstream commit 9cf2f437ca5b39828984064fad213e68fc17ef11 ]
The same fix in Commit dbe173079ab5 ("bridge: fix netconsole
setup over bridge") is also needed for team driver.
While at it, remove the unnecessary parameter *team from
team_port_enable_netpoll().
v1->v2:
- fix it in a better way, as does bridge.
Fixes: 0fb52a27a04a ("team: cleanup netpoll clode")
Reported-by: João Avelino Bellomo Filho <jbellomo@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/team/team.c | 19 ++++++++++++-------
1 file changed, 12 insertions(+), 7 deletions(-)
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 13eaae7005e8..3175f7410baf 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1072,14 +1072,11 @@ static void team_port_leave(struct team *team, struct team_port *port)
}
#ifdef CONFIG_NET_POLL_CONTROLLER
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int __team_port_enable_netpoll(struct team_port *port)
{
struct netpoll *np;
int err;
- if (!team->dev->npinfo)
- return 0;
-
np = kzalloc(sizeof(*np), GFP_KERNEL);
if (!np)
return -ENOMEM;
@@ -1093,6 +1090,14 @@ static int team_port_enable_netpoll(struct team *team, struct team_port *port)
return err;
}
+static int team_port_enable_netpoll(struct team_port *port)
+{
+ if (!port->team->dev->npinfo)
+ return 0;
+
+ return __team_port_enable_netpoll(port);
+}
+
static void team_port_disable_netpoll(struct team_port *port)
{
struct netpoll *np = port->np;
@@ -1107,7 +1112,7 @@ static void team_port_disable_netpoll(struct team_port *port)
kfree(np);
}
#else
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int team_port_enable_netpoll(struct team_port *port)
{
return 0;
}
@@ -1215,7 +1220,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
goto err_vids_add;
}
- err = team_port_enable_netpoll(team, port);
+ err = team_port_enable_netpoll(port);
if (err) {
netdev_err(dev, "Failed to enable netpoll on device %s\n",
portname);
@@ -1912,7 +1917,7 @@ static int team_netpoll_setup(struct net_device *dev,
mutex_lock(&team->lock);
list_for_each_entry(port, &team->port_list, list) {
- err = team_port_enable_netpoll(team, port);
+ err = __team_port_enable_netpoll(port);
if (err) {
__team_netpoll_cleanup(team);
break;
--
2.14.3
From 0d041d2cbf9e1d21ef724ee068eb59d5270f594a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 16 Apr 2018 08:29:42 -0700
Subject: [PATCH 25/52] tipc: add policy for TIPC_NLA_NET_ADDR
[ Upstream commit ec518f21cb1a1b1f8a516499ea05c60299e04963 ]
Before syzbot/KMSAN bites, add the missing policy for TIPC_NLA_NET_ADDR
Fixes: 27c21416727a ("tipc: add net set to new netlink api")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Cc: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/tipc/netlink.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index b76f13f6fea1..d4e0bbeee727 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -79,7 +79,8 @@ const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = {
const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = {
[TIPC_NLA_NET_UNSPEC] = { .type = NLA_UNSPEC },
- [TIPC_NLA_NET_ID] = { .type = NLA_U32 }
+ [TIPC_NLA_NET_ID] = { .type = NLA_U32 },
+ [TIPC_NLA_NET_ADDR] = { .type = NLA_U32 },
};
const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = {
--
2.14.3
From c20a56e9ae8c4545dafcbd64f658cebe6a61dbf2 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 17 Apr 2018 18:46:14 +0900
Subject: [PATCH 26/52] vlan: Fix reading memory beyond skb->tail in
skb_vlan_tagged_multi
[ Upstream commit 7ce2367254e84753bceb07327aaf5c953cfce117 ]
Syzkaller spotted an old bug which leads to reading skb beyond tail by 4
bytes on vlan tagged packets.
This is caused because skb_vlan_tagged_multi() did not check
skb_headlen.
BUG: KMSAN: uninit-value in eth_type_vlan include/linux/if_vlan.h:283 [inline]
BUG: KMSAN: uninit-value in skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline]
BUG: KMSAN: uninit-value in vlan_features_check include/linux/if_vlan.h:672 [inline]
BUG: KMSAN: uninit-value in dflt_features_check net/core/dev.c:2949 [inline]
BUG: KMSAN: uninit-value in netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009
CPU: 1 PID: 3582 Comm: syzkaller435149 Not tainted 4.16.0+ #82
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:17 [inline]
dump_stack+0x185/0x1d0 lib/dump_stack.c:53
kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
__msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
eth_type_vlan include/linux/if_vlan.h:283 [inline]
skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline]
vlan_features_check include/linux/if_vlan.h:672 [inline]
dflt_features_check net/core/dev.c:2949 [inline]
netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009
validate_xmit_skb+0x89/0x1320 net/core/dev.c:3084
__dev_queue_xmit+0x1cb2/0x2b60 net/core/dev.c:3549
dev_queue_xmit+0x4b/0x60 net/core/dev.c:3590
packet_snd net/packet/af_packet.c:2944 [inline]
packet_sendmsg+0x7c57/0x8a10 net/packet/af_packet.c:2969
sock_sendmsg_nosec net/socket.c:630 [inline]
sock_sendmsg net/socket.c:640 [inline]
sock_write_iter+0x3b9/0x470 net/socket.c:909
do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776
do_iter_write+0x30d/0xd40 fs/read_write.c:932
vfs_writev fs/read_write.c:977 [inline]
do_writev+0x3c9/0x830 fs/read_write.c:1012
SYSC_writev+0x9b/0xb0 fs/read_write.c:1085
SyS_writev+0x56/0x80 fs/read_write.c:1082
do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x43ffa9
RSP: 002b:00007fff2cff3948 EFLAGS: 00000217 ORIG_RAX: 0000000000000014
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043ffa9
RDX: 0000000000000001 RSI: 0000000020000080 RDI: 0000000000000003
RBP: 00000000006cb018 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000217 R12: 00000000004018d0
R13: 0000000000401960 R14: 0000000000000000 R15: 0000000000000000
Uninit was created at:
kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188
kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314
kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321
slab_post_alloc_hook mm/slab.h:445 [inline]
slab_alloc_node mm/slub.c:2737 [inline]
__kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369
__kmalloc_reserve net/core/skbuff.c:138 [inline]
__alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206
alloc_skb include/linux/skbuff.h:984 [inline]
alloc_skb_with_frags+0x1d4/0xb20 net/core/skbuff.c:5234
sock_alloc_send_pskb+0xb56/0x1190 net/core/sock.c:2085
packet_alloc_skb net/packet/af_packet.c:2803 [inline]
packet_snd net/packet/af_packet.c:2894 [inline]
packet_sendmsg+0x6444/0x8a10 net/packet/af_packet.c:2969
sock_sendmsg_nosec net/socket.c:630 [inline]
sock_sendmsg net/socket.c:640 [inline]
sock_write_iter+0x3b9/0x470 net/socket.c:909
do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776
do_iter_write+0x30d/0xd40 fs/read_write.c:932
vfs_writev fs/read_write.c:977 [inline]
do_writev+0x3c9/0x830 fs/read_write.c:1012
SYSC_writev+0x9b/0xb0 fs/read_write.c:1085
SyS_writev+0x56/0x80 fs/read_write.c:1082
do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
Fixes: 58e998c6d239 ("offloading: Force software GSO for multiple vlan tags.")
Reported-and-tested-by: syzbot+0bbe42c764feafa82c5a@syzkaller.appspotmail.com
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/linux/if_vlan.h | 7 +++++--
net/core/dev.c | 2 +-
2 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 7d30892da064..87b8c20d5b27 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -639,7 +639,7 @@ static inline bool skb_vlan_tagged(const struct sk_buff *skb)
* Returns true if the skb is tagged with multiple vlan headers, regardless
* of whether it is hardware accelerated or not.
*/
-static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
+static inline bool skb_vlan_tagged_multi(struct sk_buff *skb)
{
__be16 protocol = skb->protocol;
@@ -649,6 +649,9 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
if (likely(!eth_type_vlan(protocol)))
return false;
+ if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN)))
+ return false;
+
veh = (struct vlan_ethhdr *)skb->data;
protocol = veh->h_vlan_encapsulated_proto;
}
@@ -666,7 +669,7 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
*
* Returns features without unsafe ones if the skb has multiple tags.
*/
-static inline netdev_features_t vlan_features_check(const struct sk_buff *skb,
+static inline netdev_features_t vlan_features_check(struct sk_buff *skb,
netdev_features_t features)
{
if (skb_vlan_tagged_multi(skb)) {
diff --git a/net/core/dev.c b/net/core/dev.c
index c4aa2941dbfd..3e550507e9f0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2942,7 +2942,7 @@ netdev_features_t passthru_features_check(struct sk_buff *skb,
}
EXPORT_SYMBOL(passthru_features_check);
-static netdev_features_t dflt_features_check(const struct sk_buff *skb,
+static netdev_features_t dflt_features_check(struct sk_buff *skb,
struct net_device *dev,
netdev_features_t features)
{
--
2.14.3
From ab29416f31d6c071732f17fe2a123ba83c86e49b Mon Sep 17 00:00:00 2001
From: Ronak Doshi <doshir@vmware.com>
Date: Wed, 18 Apr 2018 12:48:04 -0700
Subject: [PATCH 27/52] vmxnet3: fix incorrect dereference when rxvlan is
disabled
[ Upstream commit 65ec0bd1c7c14522670a5294de35710fb577a7fd ]
vmxnet3_get_hdr_len() is used to calculate the header length which in
turn is used to calculate the gso_size for skb. When rxvlan offload is
disabled, vlan tag is present in the header and the function references
ip header from sizeof(ethhdr) and leads to incorrect pointer reference.
This patch fixes this issue by taking sizeof(vlan_ethhdr) into account
if vlan tag is present and correctly references the ip hdr.
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Guolin Yang <gyang@vmware.com>
Acked-by: Louis Luo <llouis@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/vmxnet3/vmxnet3_drv.c | 17 +++++++++++++----
drivers/net/vmxnet3/vmxnet3_int.h | 4 ++--
2 files changed, 15 insertions(+), 6 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index e04937f44f33..9ebe2a689966 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1218,6 +1218,7 @@ vmxnet3_get_hdr_len(struct vmxnet3_adapter *adapter, struct sk_buff *skb,
union {
void *ptr;
struct ethhdr *eth;
+ struct vlan_ethhdr *veth;
struct iphdr *ipv4;
struct ipv6hdr *ipv6;
struct tcphdr *tcp;
@@ -1228,16 +1229,24 @@ vmxnet3_get_hdr_len(struct vmxnet3_adapter *adapter, struct sk_buff *skb,
if (unlikely(sizeof(struct iphdr) + sizeof(struct tcphdr) > maplen))
return 0;
+ if (skb->protocol == cpu_to_be16(ETH_P_8021Q) ||
+ skb->protocol == cpu_to_be16(ETH_P_8021AD))
+ hlen = sizeof(struct vlan_ethhdr);
+ else
+ hlen = sizeof(struct ethhdr);
+
hdr.eth = eth_hdr(skb);
if (gdesc->rcd.v4) {
- BUG_ON(hdr.eth->h_proto != htons(ETH_P_IP));
- hdr.ptr += sizeof(struct ethhdr);
+ BUG_ON(hdr.eth->h_proto != htons(ETH_P_IP) &&
+ hdr.veth->h_vlan_encapsulated_proto != htons(ETH_P_IP));
+ hdr.ptr += hlen;
BUG_ON(hdr.ipv4->protocol != IPPROTO_TCP);
hlen = hdr.ipv4->ihl << 2;
hdr.ptr += hdr.ipv4->ihl << 2;
} else if (gdesc->rcd.v6) {
- BUG_ON(hdr.eth->h_proto != htons(ETH_P_IPV6));
- hdr.ptr += sizeof(struct ethhdr);
+ BUG_ON(hdr.eth->h_proto != htons(ETH_P_IPV6) &&
+ hdr.veth->h_vlan_encapsulated_proto != htons(ETH_P_IPV6));
+ hdr.ptr += hlen;
/* Use an estimated value, since we also need to handle
* TSO case.
*/
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 59ec34052a65..a3326463b71f 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -69,10 +69,10 @@
/*
* Version numbers
*/
-#define VMXNET3_DRIVER_VERSION_STRING "1.4.13.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING "1.4.14.0-k"
/* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM 0x01040d00
+#define VMXNET3_DRIVER_VERSION_NUM 0x01040e00
#if defined(CONFIG_PCI_MSI)
/* RSS only makes sense if MSI-X is supported. */
--
2.14.3
From 2a05c7ffe02cc331cea7bc510822dd6e44166761 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Mon, 23 Apr 2018 11:43:08 -0500
Subject: [PATCH 28/52] amd-xgbe: Add pre/post auto-negotiation phy hooks
[ Upstream commit 4d945663a6a0acf3cbe45940503f2eb9584bfee7 ]
Add hooks to the driver auto-negotiation (AN) flow to allow the different
phy implementations to perform any steps necessary to improve AN.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 16 ++++++++++++++--
drivers/net/ethernet/amd/xgbe/xgbe.h | 5 +++++
2 files changed, 19 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 072b9f664597..e3d361e242aa 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -437,6 +437,9 @@ static void xgbe_an73_disable(struct xgbe_prv_data *pdata)
static void xgbe_an_restart(struct xgbe_prv_data *pdata)
{
+ if (pdata->phy_if.phy_impl.an_pre)
+ pdata->phy_if.phy_impl.an_pre(pdata);
+
switch (pdata->an_mode) {
case XGBE_AN_MODE_CL73:
case XGBE_AN_MODE_CL73_REDRV:
@@ -453,6 +456,9 @@ static void xgbe_an_restart(struct xgbe_prv_data *pdata)
static void xgbe_an_disable(struct xgbe_prv_data *pdata)
{
+ if (pdata->phy_if.phy_impl.an_post)
+ pdata->phy_if.phy_impl.an_post(pdata);
+
switch (pdata->an_mode) {
case XGBE_AN_MODE_CL73:
case XGBE_AN_MODE_CL73_REDRV:
@@ -637,11 +643,11 @@ static enum xgbe_an xgbe_an73_incompat_link(struct xgbe_prv_data *pdata)
return XGBE_AN_NO_LINK;
}
- xgbe_an73_disable(pdata);
+ xgbe_an_disable(pdata);
xgbe_switch_mode(pdata);
- xgbe_an73_restart(pdata);
+ xgbe_an_restart(pdata);
return XGBE_AN_INCOMPAT_LINK;
}
@@ -820,6 +826,9 @@ static void xgbe_an37_state_machine(struct xgbe_prv_data *pdata)
pdata->an_result = pdata->an_state;
pdata->an_state = XGBE_AN_READY;
+ if (pdata->phy_if.phy_impl.an_post)
+ pdata->phy_if.phy_impl.an_post(pdata);
+
netif_dbg(pdata, link, pdata->netdev, "CL37 AN result: %s\n",
xgbe_state_as_string(pdata->an_result));
}
@@ -903,6 +912,9 @@ static void xgbe_an73_state_machine(struct xgbe_prv_data *pdata)
pdata->kx_state = XGBE_RX_BPA;
pdata->an_start = 0;
+ if (pdata->phy_if.phy_impl.an_post)
+ pdata->phy_if.phy_impl.an_post(pdata);
+
netif_dbg(pdata, link, pdata->netdev, "CL73 AN result: %s\n",
xgbe_state_as_string(pdata->an_result));
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index ad102c8bac7b..fa0b51ea1b95 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -833,6 +833,7 @@ struct xgbe_hw_if {
/* This structure represents implementation specific routines for an
* implementation of a PHY. All routines are required unless noted below.
* Optional routines:
+ * an_pre, an_post
* kr_training_pre, kr_training_post
*/
struct xgbe_phy_impl_if {
@@ -875,6 +876,10 @@ struct xgbe_phy_impl_if {
/* Process results of auto-negotiation */
enum xgbe_mode (*an_outcome)(struct xgbe_prv_data *);
+ /* Pre/Post auto-negotiation support */
+ void (*an_pre)(struct xgbe_prv_data *);
+ void (*an_post)(struct xgbe_prv_data *);
+
/* Pre/Post KR training enablement support */
void (*kr_training_pre)(struct xgbe_prv_data *);
void (*kr_training_post)(struct xgbe_prv_data *);
--
2.14.3
From e5e8a2b11dbfc3da0f0ba1f68cdb8a561131a7a2 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Mon, 23 Apr 2018 11:43:17 -0500
Subject: [PATCH 29/52] amd-xgbe: Improve KR auto-negotiation and training
[ Upstream commit 96f4d430c507ed4856048c2dc9c1a2ea5b5e74e4 ]
Update xgbe-phy-v2.c to make use of the auto-negotiation (AN) phy hooks
to improve the ability to successfully complete Clause 73 AN when running
at 10gbps. Hardware can sometimes have issues with CDR lock when the
AN DME page exchange is being performed.
The AN and KR training hooks are used as follows:
- The pre AN hook is used to disable CDR tracking in the PHY so that the
DME page exchange can be successfully and consistently completed.
- The post KR training hook is used to re-enable the CDR tracking so that
KR training can successfully complete.
- The post AN hook is used to check for an unsuccessful AN which will
increase a CDR tracking enablement delay (up to a maximum value).
Add two debugfs entries to allow control over use of the CDR tracking
workaround. The debugfs entries allow the CDR tracking workaround to
be disabled and determine whether to re-enable CDR tracking before or
after link training has been initiated.
Also, with these changes the receiver reset cycle that is performed during
the link status check can be performed less often.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/amd/xgbe/xgbe-common.h | 8 ++
drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c | 16 ++++
drivers/net/ethernet/amd/xgbe/xgbe-main.c | 1 +
drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 8 +-
drivers/net/ethernet/amd/xgbe/xgbe-pci.c | 2 +
drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 125 ++++++++++++++++++++++++++-
drivers/net/ethernet/amd/xgbe/xgbe.h | 4 +
7 files changed, 160 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 7ea72ef11a55..d272dc6984ac 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -1321,6 +1321,10 @@
#define MDIO_VEND2_AN_STAT 0x8002
#endif
+#ifndef MDIO_VEND2_PMA_CDR_CONTROL
+#define MDIO_VEND2_PMA_CDR_CONTROL 0x8056
+#endif
+
#ifndef MDIO_CTRL1_SPEED1G
#define MDIO_CTRL1_SPEED1G (MDIO_CTRL1_SPEED10G & ~BMCR_SPEED100)
#endif
@@ -1369,6 +1373,10 @@
#define XGBE_AN_CL37_TX_CONFIG_MASK 0x08
#define XGBE_AN_CL37_MII_CTRL_8BIT 0x0100
+#define XGBE_PMA_CDR_TRACK_EN_MASK 0x01
+#define XGBE_PMA_CDR_TRACK_EN_OFF 0x00
+#define XGBE_PMA_CDR_TRACK_EN_ON 0x01
+
/* Bit setting and getting macros
* The get macro will extract the current bit field value from within
* the variable
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
index 7d128be61310..b91143947ed2 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
@@ -519,6 +519,22 @@ void xgbe_debugfs_init(struct xgbe_prv_data *pdata)
"debugfs_create_file failed\n");
}
+ if (pdata->vdata->an_cdr_workaround) {
+ pfile = debugfs_create_bool("an_cdr_workaround", 0600,
+ pdata->xgbe_debugfs,
+ &pdata->debugfs_an_cdr_workaround);
+ if (!pfile)
+ netdev_err(pdata->netdev,
+ "debugfs_create_bool failed\n");
+
+ pfile = debugfs_create_bool("an_cdr_track_early", 0600,
+ pdata->xgbe_debugfs,
+ &pdata->debugfs_an_cdr_track_early);
+ if (!pfile)
+ netdev_err(pdata->netdev,
+ "debugfs_create_bool failed\n");
+ }
+
kfree(buf);
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
index d91fa595be98..e31d9d1fb6a6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
@@ -349,6 +349,7 @@ int xgbe_config_netdev(struct xgbe_prv_data *pdata)
XGMAC_SET_BITS(pdata->rss_options, MAC_RSSCR, UDP4TE, 1);
/* Call MDIO/PHY initialization routine */
+ pdata->debugfs_an_cdr_workaround = pdata->vdata->an_cdr_workaround;
ret = pdata->phy_if.phy_init(pdata);
if (ret)
return ret;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index e3d361e242aa..1b45cd73a258 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -432,6 +432,8 @@ static void xgbe_an73_disable(struct xgbe_prv_data *pdata)
xgbe_an73_set(pdata, false, false);
xgbe_an73_disable_interrupts(pdata);
+ pdata->an_start = 0;
+
netif_dbg(pdata, link, pdata->netdev, "CL73 AN disabled\n");
}
@@ -511,11 +513,11 @@ static enum xgbe_an xgbe_an73_tx_training(struct xgbe_prv_data *pdata,
XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL,
reg);
- if (pdata->phy_if.phy_impl.kr_training_post)
- pdata->phy_if.phy_impl.kr_training_post(pdata);
-
netif_dbg(pdata, link, pdata->netdev,
"KR training initiated\n");
+
+ if (pdata->phy_if.phy_impl.kr_training_post)
+ pdata->phy_if.phy_impl.kr_training_post(pdata);
}
return XGBE_AN_PAGE_RECEIVED;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
index eb23f9ba1a9a..82d1f416ee2a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -456,6 +456,7 @@ static const struct xgbe_version_data xgbe_v2a = {
.irq_reissue_support = 1,
.tx_desc_prefetch = 5,
.rx_desc_prefetch = 5,
+ .an_cdr_workaround = 1,
};
static const struct xgbe_version_data xgbe_v2b = {
@@ -470,6 +471,7 @@ static const struct xgbe_version_data xgbe_v2b = {
.irq_reissue_support = 1,
.tx_desc_prefetch = 5,
.rx_desc_prefetch = 5,
+ .an_cdr_workaround = 1,
};
static const struct pci_device_id xgbe_pci_table[] = {
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 3304a291aa96..b48efc04c4da 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -147,6 +147,14 @@
/* Rate-change complete wait/retry count */
#define XGBE_RATECHANGE_COUNT 500
+/* CDR delay values for KR support (in usec) */
+#define XGBE_CDR_DELAY_INIT 10000
+#define XGBE_CDR_DELAY_INC 10000
+#define XGBE_CDR_DELAY_MAX 100000
+
+/* RRC frequency during link status check */
+#define XGBE_RRC_FREQUENCY 10
+
enum xgbe_port_mode {
XGBE_PORT_MODE_RSVD = 0,
XGBE_PORT_MODE_BACKPLANE,
@@ -355,6 +363,10 @@ struct xgbe_phy_data {
unsigned int redrv_addr;
unsigned int redrv_lane;
unsigned int redrv_model;
+
+ /* KR AN support */
+ unsigned int phy_cdr_notrack;
+ unsigned int phy_cdr_delay;
};
/* I2C, MDIO and GPIO lines are muxed, so only one device at a time */
@@ -2361,7 +2373,7 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
return 1;
/* No link, attempt a receiver reset cycle */
- if (phy_data->rrc_count++) {
+ if (phy_data->rrc_count++ > XGBE_RRC_FREQUENCY) {
phy_data->rrc_count = 0;
xgbe_phy_rrc(pdata);
}
@@ -2669,6 +2681,103 @@ static bool xgbe_phy_port_enabled(struct xgbe_prv_data *pdata)
return true;
}
+static void xgbe_phy_cdr_track(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ if (!pdata->debugfs_an_cdr_workaround)
+ return;
+
+ if (!phy_data->phy_cdr_notrack)
+ return;
+
+ usleep_range(phy_data->phy_cdr_delay,
+ phy_data->phy_cdr_delay + 500);
+
+ XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL,
+ XGBE_PMA_CDR_TRACK_EN_MASK,
+ XGBE_PMA_CDR_TRACK_EN_ON);
+
+ phy_data->phy_cdr_notrack = 0;
+}
+
+static void xgbe_phy_cdr_notrack(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ if (!pdata->debugfs_an_cdr_workaround)
+ return;
+
+ if (phy_data->phy_cdr_notrack)
+ return;
+
+ XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL,
+ XGBE_PMA_CDR_TRACK_EN_MASK,
+ XGBE_PMA_CDR_TRACK_EN_OFF);
+
+ xgbe_phy_rrc(pdata);
+
+ phy_data->phy_cdr_notrack = 1;
+}
+
+static void xgbe_phy_kr_training_post(struct xgbe_prv_data *pdata)
+{
+ if (!pdata->debugfs_an_cdr_track_early)
+ xgbe_phy_cdr_track(pdata);
+}
+
+static void xgbe_phy_kr_training_pre(struct xgbe_prv_data *pdata)
+{
+ if (pdata->debugfs_an_cdr_track_early)
+ xgbe_phy_cdr_track(pdata);
+}
+
+static void xgbe_phy_an_post(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ case XGBE_AN_MODE_CL73_REDRV:
+ if (phy_data->cur_mode != XGBE_MODE_KR)
+ break;
+
+ xgbe_phy_cdr_track(pdata);
+
+ switch (pdata->an_result) {
+ case XGBE_AN_READY:
+ case XGBE_AN_COMPLETE:
+ break;
+ default:
+ if (phy_data->phy_cdr_delay < XGBE_CDR_DELAY_MAX)
+ phy_data->phy_cdr_delay += XGBE_CDR_DELAY_INC;
+ else
+ phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT;
+ break;
+ }
+ break;
+ default:
+ break;
+ }
+}
+
+static void xgbe_phy_an_pre(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ case XGBE_AN_MODE_CL73_REDRV:
+ if (phy_data->cur_mode != XGBE_MODE_KR)
+ break;
+
+ xgbe_phy_cdr_notrack(pdata);
+ break;
+ default:
+ break;
+ }
+}
+
static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
{
struct xgbe_phy_data *phy_data = pdata->phy_data;
@@ -2680,6 +2789,9 @@ static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
xgbe_phy_sfp_reset(phy_data);
xgbe_phy_sfp_mod_absent(pdata);
+ /* Reset CDR support */
+ xgbe_phy_cdr_track(pdata);
+
/* Power off the PHY */
xgbe_phy_power_off(pdata);
@@ -2712,6 +2824,9 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata)
/* Start in highest supported mode */
xgbe_phy_set_mode(pdata, phy_data->start_mode);
+ /* Reset CDR support */
+ xgbe_phy_cdr_track(pdata);
+
/* After starting the I2C controller, we can check for an SFP */
switch (phy_data->port_mode) {
case XGBE_PORT_MODE_SFP:
@@ -3019,6 +3134,8 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata)
}
}
+ phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT;
+
/* Register for driving external PHYs */
mii = devm_mdiobus_alloc(pdata->dev);
if (!mii) {
@@ -3071,4 +3188,10 @@ void xgbe_init_function_ptrs_phy_v2(struct xgbe_phy_if *phy_if)
phy_impl->an_advertising = xgbe_phy_an_advertising;
phy_impl->an_outcome = xgbe_phy_an_outcome;
+
+ phy_impl->an_pre = xgbe_phy_an_pre;
+ phy_impl->an_post = xgbe_phy_an_post;
+
+ phy_impl->kr_training_pre = xgbe_phy_kr_training_pre;
+ phy_impl->kr_training_post = xgbe_phy_kr_training_post;
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index fa0b51ea1b95..95d4b56448c6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -994,6 +994,7 @@ struct xgbe_version_data {
unsigned int irq_reissue_support;
unsigned int tx_desc_prefetch;
unsigned int rx_desc_prefetch;
+ unsigned int an_cdr_workaround;
};
struct xgbe_vxlan_data {
@@ -1262,6 +1263,9 @@ struct xgbe_prv_data {
unsigned int debugfs_xprop_reg;
unsigned int debugfs_xi2c_reg;
+
+ bool debugfs_an_cdr_workaround;
+ bool debugfs_an_cdr_track_early;
};
/* Function prototypes*/
--
2.14.3
From 596ca73bcf0784b2c09e8e246709e6cb52b47a52 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Mon, 23 Apr 2018 11:43:34 -0500
Subject: [PATCH 30/52] amd-xgbe: Only use the SFP supported transceiver
signals
[ Upstream commit 117df655f8ed51adb6e6b163812a06ebeae9f453 ]
The SFP eeprom indicates the transceiver signals (Rx LOS, Tx Fault, etc.)
that it supports. Update the driver to include checking the eeprom data
when deciding whether to use a transceiver signal.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 71 ++++++++++++++++++++++-------
1 file changed, 54 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index b48efc04c4da..aac884314000 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -253,6 +253,10 @@ enum xgbe_sfp_speed {
#define XGBE_SFP_BASE_VENDOR_SN 4
#define XGBE_SFP_BASE_VENDOR_SN_LEN 16
+#define XGBE_SFP_EXTD_OPT1 1
+#define XGBE_SFP_EXTD_OPT1_RX_LOS BIT(1)
+#define XGBE_SFP_EXTD_OPT1_TX_FAULT BIT(3)
+
#define XGBE_SFP_EXTD_DIAG 28
#define XGBE_SFP_EXTD_DIAG_ADDR_CHANGE BIT(2)
@@ -332,6 +336,7 @@ struct xgbe_phy_data {
unsigned int sfp_gpio_address;
unsigned int sfp_gpio_mask;
+ unsigned int sfp_gpio_inputs;
unsigned int sfp_gpio_rx_los;
unsigned int sfp_gpio_tx_fault;
unsigned int sfp_gpio_mod_absent;
@@ -986,6 +991,49 @@ static void xgbe_phy_sfp_external_phy(struct xgbe_prv_data *pdata)
phy_data->sfp_phy_avail = 1;
}
+static bool xgbe_phy_check_sfp_rx_los(struct xgbe_phy_data *phy_data)
+{
+ u8 *sfp_extd = phy_data->sfp_eeprom.extd;
+
+ if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_RX_LOS))
+ return false;
+
+ if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS)
+ return false;
+
+ if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_rx_los))
+ return true;
+
+ return false;
+}
+
+static bool xgbe_phy_check_sfp_tx_fault(struct xgbe_phy_data *phy_data)
+{
+ u8 *sfp_extd = phy_data->sfp_eeprom.extd;
+
+ if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_TX_FAULT))
+ return false;
+
+ if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT)
+ return false;
+
+ if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_tx_fault))
+ return true;
+
+ return false;
+}
+
+static bool xgbe_phy_check_sfp_mod_absent(struct xgbe_phy_data *phy_data)
+{
+ if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT)
+ return false;
+
+ if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_mod_absent))
+ return true;
+
+ return false;
+}
+
static bool xgbe_phy_belfuse_parse_quirks(struct xgbe_prv_data *pdata)
{
struct xgbe_phy_data *phy_data = pdata->phy_data;
@@ -1031,6 +1079,10 @@ static void xgbe_phy_sfp_parse_eeprom(struct xgbe_prv_data *pdata)
if (sfp_base[XGBE_SFP_BASE_EXT_ID] != XGBE_SFP_EXT_ID_SFP)
return;
+ /* Update transceiver signals (eeprom extd/options) */
+ phy_data->sfp_tx_fault = xgbe_phy_check_sfp_tx_fault(phy_data);
+ phy_data->sfp_rx_los = xgbe_phy_check_sfp_rx_los(phy_data);
+
if (xgbe_phy_sfp_parse_quirks(pdata))
return;
@@ -1196,7 +1248,6 @@ static int xgbe_phy_sfp_read_eeprom(struct xgbe_prv_data *pdata)
static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata)
{
struct xgbe_phy_data *phy_data = pdata->phy_data;
- unsigned int gpio_input;
u8 gpio_reg, gpio_ports[2];
int ret;
@@ -1211,23 +1262,9 @@ static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata)
return;
}
- gpio_input = (gpio_ports[1] << 8) | gpio_ports[0];
-
- if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT) {
- /* No GPIO, just assume the module is present for now */
- phy_data->sfp_mod_absent = 0;
- } else {
- if (!(gpio_input & (1 << phy_data->sfp_gpio_mod_absent)))
- phy_data->sfp_mod_absent = 0;
- }
-
- if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS) &&
- (gpio_input & (1 << phy_data->sfp_gpio_rx_los)))
- phy_data->sfp_rx_los = 1;
+ phy_data->sfp_gpio_inputs = (gpio_ports[1] << 8) | gpio_ports[0];
- if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT) &&
- (gpio_input & (1 << phy_data->sfp_gpio_tx_fault)))
- phy_data->sfp_tx_fault = 1;
+ phy_data->sfp_mod_absent = xgbe_phy_check_sfp_mod_absent(phy_data);
}
static void xgbe_phy_sfp_mod_absent(struct xgbe_prv_data *pdata)
--
2.14.3
From f09b880b6f9c1cbcf1a3be8e2a0a6ce3502e9e6c Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Fri, 20 Apr 2018 15:15:03 -0400
Subject: [PATCH 31/52] net: sched: ife: signal not finding metaid
[ Upstream commit f6cd14537ff9919081be19b9c53b9b19c0d3ea97 ]
We need to record stats for received metadata that we dont know how
to process. Have find_decode_metaid() return -ENOENT to capture this.
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Reviewed-by: Yotam Gigi <yotam.gi@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/act_ife.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 5954e992685a..3c046d505e86 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -652,7 +652,7 @@ static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
}
}
- return 0;
+ return -ENOENT;
}
static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
--
2.14.3
From 59640becb4adda781621f7ddf5fe3f0ad05377e8 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Fri, 20 Apr 2018 15:15:04 -0400
Subject: [PATCH 32/52] net: sched: ife: handle malformed tlv length
[ Upstream commit cc74eddd0ff325d57373cea99f642b787d7f76f5 ]
There is currently no handling to check on a invalid tlv length. This
patch adds such handling to avoid killing the kernel with a malformed
ife packet.
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Reviewed-by: Yotam Gigi <yotam.gi@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/ife.h | 3 ++-
net/ife/ife.c | 35 +++++++++++++++++++++++++++++++++--
net/sched/act_ife.c | 7 ++++++-
3 files changed, 41 insertions(+), 4 deletions(-)
diff --git a/include/net/ife.h b/include/net/ife.h
index 44b9c00f7223..e117617e3c34 100644
--- a/include/net/ife.h
+++ b/include/net/ife.h
@@ -12,7 +12,8 @@
void *ife_encode(struct sk_buff *skb, u16 metalen);
void *ife_decode(struct sk_buff *skb, u16 *metalen);
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen);
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+ u16 *dlen, u16 *totlen);
int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen,
const void *dval);
diff --git a/net/ife/ife.c b/net/ife/ife.c
index 7d1ec76e7f43..7fbe70a0af4b 100644
--- a/net/ife/ife.c
+++ b/net/ife/ife.c
@@ -92,12 +92,43 @@ struct meta_tlvhdr {
__be16 len;
};
+static bool __ife_tlv_meta_valid(const unsigned char *skbdata,
+ const unsigned char *ifehdr_end)
+{
+ const struct meta_tlvhdr *tlv;
+ u16 tlvlen;
+
+ if (unlikely(skbdata + sizeof(*tlv) > ifehdr_end))
+ return false;
+
+ tlv = (const struct meta_tlvhdr *)skbdata;
+ tlvlen = ntohs(tlv->len);
+
+ /* tlv length field is inc header, check on minimum */
+ if (tlvlen < NLA_HDRLEN)
+ return false;
+
+ /* overflow by NLA_ALIGN check */
+ if (NLA_ALIGN(tlvlen) < tlvlen)
+ return false;
+
+ if (unlikely(skbdata + NLA_ALIGN(tlvlen) > ifehdr_end))
+ return false;
+
+ return true;
+}
+
/* Caller takes care of presenting data in network order
*/
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen)
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+ u16 *dlen, u16 *totlen)
{
- struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata;
+ struct meta_tlvhdr *tlv;
+
+ if (!__ife_tlv_meta_valid(skbdata, ifehdr_end))
+ return NULL;
+ tlv = (struct meta_tlvhdr *)skbdata;
*dlen = ntohs(tlv->len) - NLA_HDRLEN;
*attrtype = ntohs(tlv->type);
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 3c046d505e86..1d477b054f2e 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -682,7 +682,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
u16 mtype;
u16 dlen;
- curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL);
+ curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype,
+ &dlen, NULL);
+ if (!curr_data) {
+ qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
+ return TC_ACT_SHOT;
+ }
if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) {
/* abuse overlimits to count when we receive metadata
--
2.14.3
From 925118f1943f48d45424a744907a4f8b9a906971 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Fri, 20 Apr 2018 15:15:05 -0400
Subject: [PATCH 33/52] net: sched: ife: check on metadata length
[ Upstream commit d57493d6d1be26c8ac8516a4463bfe24956978eb ]
This patch checks if sk buffer is available to dererence ife header. If
not then NULL will returned to signal an malformed ife packet. This
avoids to crashing the kernel from outside.
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Reviewed-by: Yotam Gigi <yotam.gi@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ife/ife.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/net/ife/ife.c b/net/ife/ife.c
index 7fbe70a0af4b..13bbf8cb6a39 100644
--- a/net/ife/ife.c
+++ b/net/ife/ife.c
@@ -69,6 +69,9 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen)
int total_pull;
u16 ifehdrln;
+ if (!pskb_may_pull(skb, skb->dev->hard_header_len + IFE_METAHDRLEN))
+ return NULL;
+
ifehdr = (struct ifeheadr *) (skb->data + skb->dev->hard_header_len);
ifehdrln = ntohs(ifehdr->metalen);
total_pull = skb->dev->hard_header_len + ifehdrln;
--
2.14.3
From d26b2236a8b444c40ca7777fd3f5692a8d171532 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 12 Apr 2018 20:50:33 +0200
Subject: [PATCH 34/52] l2tp: hold reference on tunnels in netlink dumps
[ Upstream commit 5846c131c39b6d0add36ec19dc8650700690f930 ]
l2tp_tunnel_find_nth() is unsafe: no reference is held on the returned
tunnel, therefore it can be freed whenever the caller uses it.
This patch defines l2tp_tunnel_get_nth() which works similarly, but
also takes a reference on the returned tunnel. The caller then has to
drop it after it stops using the tunnel.
Convert netlink dumps to make them safe against concurrent tunnel
deletion.
Fixes: 309795f4bec2 ("l2tp: Add netlink control API for L2TP")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/l2tp/l2tp_core.c | 20 ++++++++++++++++++++
net/l2tp/l2tp_core.h | 2 ++
net/l2tp/l2tp_netlink.c | 11 ++++++++---
3 files changed, 30 insertions(+), 3 deletions(-)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 0fbd3ee26165..c8c4183f0f37 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -183,6 +183,26 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
}
EXPORT_SYMBOL_GPL(l2tp_tunnel_get);
+struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth)
+{
+ const struct l2tp_net *pn = l2tp_pernet(net);
+ struct l2tp_tunnel *tunnel;
+ int count = 0;
+
+ rcu_read_lock_bh();
+ list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
+ if (++count > nth) {
+ l2tp_tunnel_inc_refcount(tunnel);
+ rcu_read_unlock_bh();
+ return tunnel;
+ }
+ }
+ rcu_read_unlock_bh();
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth);
+
/* Lookup a session. A new reference is held on the returned session. */
struct l2tp_session *l2tp_session_get(const struct net *net,
struct l2tp_tunnel *tunnel,
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index ba33cbec71eb..e4896413b2b6 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -212,6 +212,8 @@ static inline void *l2tp_session_priv(struct l2tp_session *session)
}
struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id);
+struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth);
+
void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
struct l2tp_session *l2tp_session_get(const struct net *net,
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index b05dbd9ffcb2..6616c9fd292f 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -487,14 +487,17 @@ static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback
struct net *net = sock_net(skb->sk);
for (;;) {
- tunnel = l2tp_tunnel_find_nth(net, ti);
+ tunnel = l2tp_tunnel_get_nth(net, ti);
if (tunnel == NULL)
goto out;
if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
- tunnel, L2TP_CMD_TUNNEL_GET) < 0)
+ tunnel, L2TP_CMD_TUNNEL_GET) < 0) {
+ l2tp_tunnel_dec_refcount(tunnel);
goto out;
+ }
+ l2tp_tunnel_dec_refcount(tunnel);
ti++;
}
@@ -848,7 +851,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
for (;;) {
if (tunnel == NULL) {
- tunnel = l2tp_tunnel_find_nth(net, ti);
+ tunnel = l2tp_tunnel_get_nth(net, ti);
if (tunnel == NULL)
goto out;
}
@@ -856,6 +859,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
session = l2tp_session_get_nth(tunnel, si);
if (session == NULL) {
ti++;
+ l2tp_tunnel_dec_refcount(tunnel);
tunnel = NULL;
si = 0;
continue;
@@ -865,6 +869,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
cb->nlh->nlmsg_seq, NLM_F_MULTI,
session, L2TP_CMD_SESSION_GET) < 0) {
l2tp_session_dec_refcount(session);
+ l2tp_tunnel_dec_refcount(tunnel);
break;
}
l2tp_session_dec_refcount(session);
--
2.14.3
From b90bee037091ffa776057d64055e927496918421 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 12 Apr 2018 20:50:34 +0200
Subject: [PATCH 35/52] l2tp: hold reference on tunnels printed in pppol2tp
proc file
[ Upstream commit 0e0c3fee3a59a387aeecc4fca6f3a2e9615a5443 ]
Use l2tp_tunnel_get_nth() instead of l2tp_tunnel_find_nth(), to be safe
against concurrent tunnel deletion.
Unlike sessions, we can't drop the reference held on tunnels in
pppol2tp_seq_show(). Tunnels are reused across several calls to
pppol2tp_seq_start() when iterating over sessions. These iterations
need the tunnel for accessing the next session. Therefore the only safe
moment for dropping the reference is just before searching for the next
tunnel.
Normally, the last invocation of pppol2tp_next_tunnel() doesn't find
any new tunnel, so it drops the last tunnel without taking any new
reference. However, in case of error, pppol2tp_seq_stop() is called
directly, so we have to drop the reference there.
Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/l2tp/l2tp_ppp.c | 24 +++++++++++++++++-------
1 file changed, 17 insertions(+), 7 deletions(-)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index fc3b8b8fe1c4..2e59f8efb888 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1559,16 +1559,19 @@ struct pppol2tp_seq_data {
static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd)
{
+ /* Drop reference taken during previous invocation */
+ if (pd->tunnel)
+ l2tp_tunnel_dec_refcount(pd->tunnel);
+
for (;;) {
- pd->tunnel = l2tp_tunnel_find_nth(net, pd->tunnel_idx);
+ pd->tunnel = l2tp_tunnel_get_nth(net, pd->tunnel_idx);
pd->tunnel_idx++;
- if (pd->tunnel == NULL)
- break;
+ /* Only accept L2TPv2 tunnels */
+ if (!pd->tunnel || pd->tunnel->version == 2)
+ return;
- /* Ignore L2TPv3 tunnels */
- if (pd->tunnel->version < 3)
- break;
+ l2tp_tunnel_dec_refcount(pd->tunnel);
}
}
@@ -1617,7 +1620,14 @@ static void *pppol2tp_seq_next(struct seq_file *m, void *v, loff_t *pos)
static void pppol2tp_seq_stop(struct seq_file *p, void *v)
{
- /* nothing to do */
+ struct pppol2tp_seq_data *pd = v;
+
+ if (!pd || pd == SEQ_START_TOKEN)
+ return;
+
+ /* Drop reference taken by last invocation of pppol2tp_next_tunnel() */
+ if (pd->tunnel)
+ l2tp_tunnel_dec_refcount(pd->tunnel);
}
static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v)
--
2.14.3
From fb2b67b40abdd77f3024f1fa728e5651a7a8523a Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 12 Apr 2018 20:50:35 +0200
Subject: [PATCH 36/52] l2tp: hold reference on tunnels printed in l2tp/tunnels
debugfs file
[ Upstream commit f726214d9b23e5fce8c11937577a289a3202498f ]
Use l2tp_tunnel_get_nth() instead of l2tp_tunnel_find_nth(), to be safe
against concurrent tunnel deletion.
Use the same mechanism as in l2tp_ppp.c for dropping the reference
taken by l2tp_tunnel_get_nth(). That is, drop the reference just
before looking up the next tunnel. In case of error, drop the last
accessed tunnel in l2tp_dfs_seq_stop().
That was the last use of l2tp_tunnel_find_nth().
Fixes: 0ad6614048cf ("l2tp: Add debugfs files for dumping l2tp debug info")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/l2tp/l2tp_core.c | 20 --------------------
net/l2tp/l2tp_core.h | 1 -
net/l2tp/l2tp_debugfs.c | 15 +++++++++++++--
3 files changed, 13 insertions(+), 23 deletions(-)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index c8c4183f0f37..40261cb68e83 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -355,26 +355,6 @@ int l2tp_session_register(struct l2tp_session *session,
}
EXPORT_SYMBOL_GPL(l2tp_session_register);
-struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth)
-{
- struct l2tp_net *pn = l2tp_pernet(net);
- struct l2tp_tunnel *tunnel;
- int count = 0;
-
- rcu_read_lock_bh();
- list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- if (++count > nth) {
- rcu_read_unlock_bh();
- return tunnel;
- }
- }
-
- rcu_read_unlock_bh();
-
- return NULL;
-}
-EXPORT_SYMBOL_GPL(l2tp_tunnel_find_nth);
-
/*****************************************************************************
* Receive data handling
*****************************************************************************/
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index e4896413b2b6..c199020f8a8a 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -222,7 +222,6 @@ struct l2tp_session *l2tp_session_get(const struct net *net,
struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth);
struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
const char *ifname);
-struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth);
int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,
u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg,
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 72e713da4733..b8f9d45bfeb1 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -47,7 +47,11 @@ struct l2tp_dfs_seq_data {
static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd)
{
- pd->tunnel = l2tp_tunnel_find_nth(pd->net, pd->tunnel_idx);
+ /* Drop reference taken during previous invocation */
+ if (pd->tunnel)
+ l2tp_tunnel_dec_refcount(pd->tunnel);
+
+ pd->tunnel = l2tp_tunnel_get_nth(pd->net, pd->tunnel_idx);
pd->tunnel_idx++;
}
@@ -96,7 +100,14 @@ static void *l2tp_dfs_seq_next(struct seq_file *m, void *v, loff_t *pos)
static void l2tp_dfs_seq_stop(struct seq_file *p, void *v)
{
- /* nothing to do */
+ struct l2tp_dfs_seq_data *pd = v;
+
+ if (!pd || pd == SEQ_START_TOKEN)
+ return;
+
+ /* Drop reference taken by last invocation of l2tp_dfs_next_tunnel() */
+ if (pd->tunnel)
+ l2tp_tunnel_dec_refcount(pd->tunnel);
}
static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v)
--
2.14.3
From 4e1547b645a6adddb70c0353a5174c986f7bd149 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 19 Apr 2018 16:20:48 +0200
Subject: [PATCH 37/52] l2tp: fix {pppol2tp, l2tp_dfs}_seq_stop() in case of
seq_file overflow
[ Upstream commit 5411b6187adf62909e3b998ac782e722904c7487 ]
Commit 0e0c3fee3a59 ("l2tp: hold reference on tunnels printed in pppol2tp proc file")
assumed that if pppol2tp_seq_stop() was called with non-NULL private
data (the 'v' pointer), then pppol2tp_seq_start() would not be called
again. It turns out that this isn't guaranteed, and overflowing the
seq_file's buffer in pppol2tp_seq_show() is a way to get into this
situation.
Therefore, pppol2tp_seq_stop() needs to reset pd->tunnel, so that
pppol2tp_seq_start() won't drop a reference again if it gets called.
We also have to clear pd->session, because the rest of the code expects
a non-NULL tunnel when pd->session is set.
The l2tp_debugfs module has the same issue. Fix it in the same way.
Fixes: 0e0c3fee3a59 ("l2tp: hold reference on tunnels printed in pppol2tp proc file")
Fixes: f726214d9b23 ("l2tp: hold reference on tunnels printed in l2tp/tunnels debugfs file")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/l2tp/l2tp_debugfs.c | 5 ++++-
net/l2tp/l2tp_ppp.c | 5 ++++-
2 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index b8f9d45bfeb1..7f1e842ef05a 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -106,8 +106,11 @@ static void l2tp_dfs_seq_stop(struct seq_file *p, void *v)
return;
/* Drop reference taken by last invocation of l2tp_dfs_next_tunnel() */
- if (pd->tunnel)
+ if (pd->tunnel) {
l2tp_tunnel_dec_refcount(pd->tunnel);
+ pd->tunnel = NULL;
+ pd->session = NULL;
+ }
}
static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 2e59f8efb888..0c4530ad74be 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1626,8 +1626,11 @@ static void pppol2tp_seq_stop(struct seq_file *p, void *v)
return;
/* Drop reference taken by last invocation of pppol2tp_next_tunnel() */
- if (pd->tunnel)
+ if (pd->tunnel) {
l2tp_tunnel_dec_refcount(pd->tunnel);
+ pd->tunnel = NULL;
+ pd->session = NULL;
+ }
}
static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v)
--
2.14.3
From 5b001dc8735fb25423273a45c95d6a0b22cef29c Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 18 Apr 2018 11:51:56 -0700
Subject: [PATCH 38/52] llc: hold llc_sap before release_sock()
[ Upstream commit f7e43672683b097bb074a8fe7af9bc600a23f231 ]
syzbot reported we still access llc->sap in llc_backlog_rcv()
after it is freed in llc_sap_remove_socket():
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x1b9/0x294 lib/dump_stack.c:113
print_address_description+0x6c/0x20b mm/kasan/report.c:256
kasan_report_error mm/kasan/report.c:354 [inline]
kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412
__asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:430
llc_conn_ac_send_sabme_cmd_p_set_x+0x3a8/0x460 net/llc/llc_c_ac.c:785
llc_exec_conn_trans_actions net/llc/llc_conn.c:475 [inline]
llc_conn_service net/llc/llc_conn.c:400 [inline]
llc_conn_state_process+0x4e1/0x13a0 net/llc/llc_conn.c:75
llc_backlog_rcv+0x195/0x1e0 net/llc/llc_conn.c:891
sk_backlog_rcv include/net/sock.h:909 [inline]
__release_sock+0x12f/0x3a0 net/core/sock.c:2335
release_sock+0xa4/0x2b0 net/core/sock.c:2850
llc_ui_release+0xc8/0x220 net/llc/af_llc.c:204
llc->sap is refcount'ed and llc_sap_remove_socket() is paired
with llc_sap_add_socket(). This can be amended by holding its refcount
before llc_sap_remove_socket() and releasing it after release_sock().
Reported-by: <syzbot+6e181fc95081c2cf9051@syzkaller.appspotmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/llc/af_llc.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index c38d16f22d2a..c8950d88a695 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -189,6 +189,7 @@ static int llc_ui_release(struct socket *sock)
{
struct sock *sk = sock->sk;
struct llc_sock *llc;
+ struct llc_sap *sap;
if (unlikely(sk == NULL))
goto out;
@@ -199,9 +200,15 @@ static int llc_ui_release(struct socket *sock)
llc->laddr.lsap, llc->daddr.lsap);
if (!llc_send_disc(sk))
llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo);
+ sap = llc->sap;
+ /* Hold this for release_sock(), so that llc_backlog_rcv() could still
+ * use it.
+ */
+ llc_sap_hold(sap);
if (!sock_flag(sk, SOCK_ZAPPED))
llc_sap_remove_socket(llc->sap, sk);
release_sock(sk);
+ llc_sap_put(sap);
if (llc->dev)
dev_put(llc->dev);
sock_put(sk);
--
2.14.3
From c7bea639e059b6d7b5e9f9811431253f24d3edd7 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 19 Apr 2018 21:54:34 -0700
Subject: [PATCH 39/52] llc: fix NULL pointer deref for SOCK_ZAPPED
[ Upstream commit 3a04ce7130a7e5dad4e78d45d50313747f8c830f ]
For SOCK_ZAPPED socket, we don't need to care about llc->sap,
so we should just skip these refcount functions in this case.
Fixes: f7e43672683b ("llc: hold llc_sap before release_sock()")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/llc/af_llc.c | 21 ++++++++++++---------
1 file changed, 12 insertions(+), 9 deletions(-)
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index c8950d88a695..cf41d9b4a0b8 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -189,7 +189,6 @@ static int llc_ui_release(struct socket *sock)
{
struct sock *sk = sock->sk;
struct llc_sock *llc;
- struct llc_sap *sap;
if (unlikely(sk == NULL))
goto out;
@@ -200,15 +199,19 @@ static int llc_ui_release(struct socket *sock)
llc->laddr.lsap, llc->daddr.lsap);
if (!llc_send_disc(sk))
llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo);
- sap = llc->sap;
- /* Hold this for release_sock(), so that llc_backlog_rcv() could still
- * use it.
- */
- llc_sap_hold(sap);
- if (!sock_flag(sk, SOCK_ZAPPED))
+ if (!sock_flag(sk, SOCK_ZAPPED)) {
+ struct llc_sap *sap = llc->sap;
+
+ /* Hold this for release_sock(), so that llc_backlog_rcv()
+ * could still use it.
+ */
+ llc_sap_hold(sap);
llc_sap_remove_socket(llc->sap, sk);
- release_sock(sk);
- llc_sap_put(sap);
+ release_sock(sk);
+ llc_sap_put(sap);
+ } else {
+ release_sock(sk);
+ }
if (llc->dev)
dev_put(llc->dev);
sock_put(sk);
--
2.14.3
From 2b71302d432060bbf610da9878c738ef9c3d27cb Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Thu, 19 Apr 2018 12:52:06 +0200
Subject: [PATCH 40/52] s390/qeth: fix error handling in adapter command
callbacks
[ Upstream commit 686c97ee29c886ee07d17987d0059874c5c3b5af ]
Make sure to check both return code fields before(!) processing the
command response. Otherwise we risk operating on invalid data.
This matches an earlier fix for SETASSPARMS commands, see
commit ad3cbf613329 ("s390/qeth: fix error handling in checksum cmd callback").
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/s390/net/qeth_core_main.c | 85 +++++++++++++++++----------------------
1 file changed, 37 insertions(+), 48 deletions(-)
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 3653bea38470..edeff29271b3 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -3037,28 +3037,23 @@ static int qeth_send_startlan(struct qeth_card *card)
return rc;
}
-static int qeth_default_setadapterparms_cb(struct qeth_card *card,
- struct qeth_reply *reply, unsigned long data)
+static int qeth_setadpparms_inspect_rc(struct qeth_ipa_cmd *cmd)
{
- struct qeth_ipa_cmd *cmd;
-
- QETH_CARD_TEXT(card, 4, "defadpcb");
-
- cmd = (struct qeth_ipa_cmd *) data;
- if (cmd->hdr.return_code == 0)
+ if (!cmd->hdr.return_code)
cmd->hdr.return_code =
cmd->data.setadapterparms.hdr.return_code;
- return 0;
+ return cmd->hdr.return_code;
}
static int qeth_query_setadapterparms_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
QETH_CARD_TEXT(card, 3, "quyadpcb");
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
- cmd = (struct qeth_ipa_cmd *) data;
if (cmd->data.setadapterparms.data.query_cmds_supp.lan_type & 0x7f) {
card->info.link_type =
cmd->data.setadapterparms.data.query_cmds_supp.lan_type;
@@ -3066,7 +3061,7 @@ static int qeth_query_setadapterparms_cb(struct qeth_card *card,
}
card->options.adp.supported_funcs =
cmd->data.setadapterparms.data.query_cmds_supp.supported_cmds;
- return qeth_default_setadapterparms_cb(card, reply, (unsigned long)cmd);
+ return 0;
}
static struct qeth_cmd_buffer *qeth_get_adapter_cmd(struct qeth_card *card,
@@ -3158,22 +3153,20 @@ EXPORT_SYMBOL_GPL(qeth_query_ipassists);
static int qeth_query_switch_attributes_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
- struct qeth_switch_info *sw_info;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
struct qeth_query_switch_attributes *attrs;
+ struct qeth_switch_info *sw_info;
QETH_CARD_TEXT(card, 2, "qswiatcb");
- cmd = (struct qeth_ipa_cmd *) data;
- sw_info = (struct qeth_switch_info *)reply->param;
- if (cmd->data.setadapterparms.hdr.return_code == 0) {
- attrs = &cmd->data.setadapterparms.data.query_switch_attributes;
- sw_info->capabilities = attrs->capabilities;
- sw_info->settings = attrs->settings;
- QETH_CARD_TEXT_(card, 2, "%04x%04x", sw_info->capabilities,
- sw_info->settings);
- }
- qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
+ sw_info = (struct qeth_switch_info *)reply->param;
+ attrs = &cmd->data.setadapterparms.data.query_switch_attributes;
+ sw_info->capabilities = attrs->capabilities;
+ sw_info->settings = attrs->settings;
+ QETH_CARD_TEXT_(card, 2, "%04x%04x", sw_info->capabilities,
+ sw_info->settings);
return 0;
}
@@ -4211,16 +4204,13 @@ EXPORT_SYMBOL_GPL(qeth_do_send_packet);
static int qeth_setadp_promisc_mode_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
struct qeth_ipacmd_setadpparms *setparms;
QETH_CARD_TEXT(card, 4, "prmadpcb");
- cmd = (struct qeth_ipa_cmd *) data;
setparms = &(cmd->data.setadapterparms);
-
- qeth_default_setadapterparms_cb(card, reply, (unsigned long)cmd);
- if (cmd->hdr.return_code) {
+ if (qeth_setadpparms_inspect_rc(cmd)) {
QETH_CARD_TEXT_(card, 4, "prmrc%x", cmd->hdr.return_code);
setparms->data.mode = SET_PROMISC_MODE_OFF;
}
@@ -4290,18 +4280,18 @@ EXPORT_SYMBOL_GPL(qeth_get_stats);
static int qeth_setadpparms_change_macaddr_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
QETH_CARD_TEXT(card, 4, "chgmaccb");
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
- cmd = (struct qeth_ipa_cmd *) data;
if (!card->options.layer2 ||
!(card->info.mac_bits & QETH_LAYER2_MAC_READ)) {
ether_addr_copy(card->dev->dev_addr,
cmd->data.setadapterparms.data.change_addr.addr);
card->info.mac_bits |= QETH_LAYER2_MAC_READ;
}
- qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
return 0;
}
@@ -4332,13 +4322,15 @@ EXPORT_SYMBOL_GPL(qeth_setadpparms_change_macaddr);
static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
struct qeth_set_access_ctrl *access_ctrl_req;
int fallback = *(int *)reply->param;
QETH_CARD_TEXT(card, 4, "setaccb");
+ if (cmd->hdr.return_code)
+ return 0;
+ qeth_setadpparms_inspect_rc(cmd);
- cmd = (struct qeth_ipa_cmd *) data;
access_ctrl_req = &cmd->data.setadapterparms.data.set_access_ctrl;
QETH_DBF_TEXT_(SETUP, 2, "setaccb");
QETH_DBF_TEXT_(SETUP, 2, "%s", card->gdev->dev.kobj.name);
@@ -4411,7 +4403,6 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card,
card->options.isolation = card->options.prev_isolation;
break;
}
- qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
return 0;
}
@@ -4699,14 +4690,15 @@ static int qeth_snmp_command(struct qeth_card *card, char __user *udata)
static int qeth_setadpparms_query_oat_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data;
struct qeth_qoat_priv *priv;
char *resdata;
int resdatalen;
QETH_CARD_TEXT(card, 3, "qoatcb");
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
- cmd = (struct qeth_ipa_cmd *)data;
priv = (struct qeth_qoat_priv *)reply->param;
resdatalen = cmd->data.setadapterparms.hdr.cmdlength;
resdata = (char *)data + 28;
@@ -4800,21 +4792,18 @@ static int qeth_query_oat_command(struct qeth_card *card, char __user *udata)
static int qeth_query_card_info_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct carrier_info *carrier_info = (struct carrier_info *)reply->param;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data;
struct qeth_query_card_info *card_info;
- struct carrier_info *carrier_info;
QETH_CARD_TEXT(card, 2, "qcrdincb");
- carrier_info = (struct carrier_info *)reply->param;
- cmd = (struct qeth_ipa_cmd *)data;
- card_info = &cmd->data.setadapterparms.data.card_info;
- if (cmd->data.setadapterparms.hdr.return_code == 0) {
- carrier_info->card_type = card_info->card_type;
- carrier_info->port_mode = card_info->port_mode;
- carrier_info->port_speed = card_info->port_speed;
- }
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
- qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
+ card_info = &cmd->data.setadapterparms.data.card_info;
+ carrier_info->card_type = card_info->card_type;
+ carrier_info->port_mode = card_info->port_mode;
+ carrier_info->port_speed = card_info->port_speed;
return 0;
}
--
2.14.3
From cac8e88617d27c99697d478d4879e8992ea4d050 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Thu, 19 Apr 2018 12:52:07 +0200
Subject: [PATCH 41/52] s390/qeth: avoid control IO completion stalls
[ Upstream commit 901e3f49facbd31b2b3d1786637b4a35e1022e9b ]
For control IO, qeth currently tracks the index of the buffer that it
expects to complete the next IO on each qeth_channel. If the channel
presents an IRQ while this buffer has not yet completed, no completion
processing for _any_ completed buffer takes place.
So if the 'next buffer' is skipped for any sort of reason* (eg. when it
is released due to error conditions, before the IO is started), the
buffer obviously won't switch to PROCESSED until it is eventually
allocated for a _different_ IO and completes.
Until this happens, all completion processing on that channel stalls
and pending requests possibly time out.
As a fix, remove the whole 'next buffer' logic and simply process any
IO buffer right when it completes. A channel will never have more than
one IO pending, so there's no risk of processing out-of-sequence.
*Note: currently just one location in the code really handles this problem,
by advancing the 'next' index manually.
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/s390/net/qeth_core.h | 2 --
drivers/s390/net/qeth_core_main.c | 22 +++++-----------------
2 files changed, 5 insertions(+), 19 deletions(-)
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 959c65cf75d9..e338ce823c44 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -565,7 +565,6 @@ enum qeth_ip_types {
enum qeth_cmd_buffer_state {
BUF_STATE_FREE,
BUF_STATE_LOCKED,
- BUF_STATE_PROCESSED,
};
enum qeth_cq {
@@ -609,7 +608,6 @@ struct qeth_channel {
struct qeth_cmd_buffer iob[QETH_CMD_BUFFER_NO];
atomic_t irq_pending;
int io_buf_no;
- int buf_no;
};
/**
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index edeff29271b3..a5953635a998 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -821,7 +821,6 @@ void qeth_clear_cmd_buffers(struct qeth_channel *channel)
for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++)
qeth_release_buffer(channel, &channel->iob[cnt]);
- channel->buf_no = 0;
channel->io_buf_no = 0;
}
EXPORT_SYMBOL_GPL(qeth_clear_cmd_buffers);
@@ -927,7 +926,6 @@ static int qeth_setup_channel(struct qeth_channel *channel)
kfree(channel->iob[cnt].data);
return -ENOMEM;
}
- channel->buf_no = 0;
channel->io_buf_no = 0;
atomic_set(&channel->irq_pending, 0);
spin_lock_init(&channel->iob_lock);
@@ -1103,11 +1101,9 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
{
int rc;
int cstat, dstat;
- struct qeth_cmd_buffer *buffer;
struct qeth_channel *channel;
struct qeth_card *card;
struct qeth_cmd_buffer *iob;
- __u8 index;
if (__qeth_check_irb_error(cdev, intparm, irb))
return;
@@ -1185,25 +1181,18 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
channel->state = CH_STATE_RCD_DONE;
goto out;
}
- if (intparm) {
- buffer = (struct qeth_cmd_buffer *) __va((addr_t)intparm);
- buffer->state = BUF_STATE_PROCESSED;
- }
if (channel == &card->data)
return;
if (channel == &card->read &&
channel->state == CH_STATE_UP)
__qeth_issue_next_read(card);
- iob = channel->iob;
- index = channel->buf_no;
- while (iob[index].state == BUF_STATE_PROCESSED) {
- if (iob[index].callback != NULL)
- iob[index].callback(channel, iob + index);
-
- index = (index + 1) % QETH_CMD_BUFFER_NO;
+ if (intparm) {
+ iob = (struct qeth_cmd_buffer *) __va((addr_t)intparm);
+ if (iob->callback)
+ iob->callback(iob->channel, iob);
}
- channel->buf_no = index;
+
out:
wake_up(&card->wait_q);
return;
@@ -2217,7 +2206,6 @@ int qeth_send_control_data(struct qeth_card *card, int len,
error:
atomic_set(&card->write.irq_pending, 0);
qeth_release_buffer(iob->channel, iob);
- card->write.buf_no = (card->write.buf_no + 1) % QETH_CMD_BUFFER_NO;
rc = reply->rc;
qeth_put_reply(reply);
return rc;
--
2.14.3
From 6b61fd202cbb0f0968f7726f242396d9d9169f4e Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 19 Apr 2018 12:52:08 +0200
Subject: [PATCH 42/52] s390/qeth: handle failure on workqueue creation
[ Upstream commit a936b1ef37ce1e996533878f4b23944f9444dcdf ]
Creating the global workqueue during driver init may fail, deal with it.
Also, destroy the created workqueue on any subsequent error.
Fixes: 0f54761d167f ("qeth: Support VEPA mode")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/s390/net/qeth_core_main.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index a5953635a998..c11a083cd956 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -6544,10 +6544,14 @@ static int __init qeth_core_init(void)
mutex_init(&qeth_mod_mutex);
qeth_wq = create_singlethread_workqueue("qeth_wq");
+ if (!qeth_wq) {
+ rc = -ENOMEM;
+ goto out_err;
+ }
rc = qeth_register_dbf_views();
if (rc)
- goto out_err;
+ goto dbf_err;
qeth_core_root_dev = root_device_register("qeth");
rc = PTR_ERR_OR_ZERO(qeth_core_root_dev);
if (rc)
@@ -6584,6 +6588,8 @@ static int __init qeth_core_init(void)
root_device_unregister(qeth_core_root_dev);
register_err:
qeth_unregister_dbf_views();
+dbf_err:
+ destroy_workqueue(qeth_wq);
out_err:
pr_err("Initializing the qeth device driver failed\n");
return rc;
--
2.14.3
From 1fd9acf660da7141b45c117e56abe0426ee701b8 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Thu, 19 Apr 2018 22:49:09 +0300
Subject: [PATCH 43/52] net: ethernet: ti: cpsw: fix tx vlan priority mapping
[ Upstream commit 5e391dc5a8d801a2410d0032ad4a428d1d61800c ]
The CPDMA_TX_PRIORITY_MAP in real is vlan pcp field priority mapping
register and basically replaces vlan pcp field for tagged packets.
So, set it to be 1:1 mapping. Otherwise, it will cause unexpected
change of egress vlan tagged packets, like prio 2 -> prio 5.
Fixes: e05107e6b747 ("net: ethernet: ti: cpsw: add multi queue support")
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/ti/cpsw.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index b2b30c9df037..33c35b2df7d5 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -125,7 +125,7 @@ do { \
#define RX_PRIORITY_MAPPING 0x76543210
#define TX_PRIORITY_MAPPING 0x33221100
-#define CPDMA_TX_PRIORITY_MAP 0x01234567
+#define CPDMA_TX_PRIORITY_MAP 0x76543210
#define CPSW_VLAN_AWARE BIT(1)
#define CPSW_ALE_VLAN_AWARE 1
--
2.14.3
From ae3806d902d2d1237a521589ade26511fe88447b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Apr 2018 14:46:00 -0700
Subject: [PATCH 44/52] net: validate attribute sizes in neigh_dump_table()
[ Upstream commit 7dd07c143a4b54d050e748bee4b4b9e94a7b1744 ]
Since neigh_dump_table() calls nlmsg_parse() without giving policy
constraints, attributes can have arbirary size that we must validate
Reported by syzbot/KMSAN :
BUG: KMSAN: uninit-value in neigh_master_filtered net/core/neighbour.c:2292 [inline]
BUG: KMSAN: uninit-value in neigh_dump_table net/core/neighbour.c:2348 [inline]
BUG: KMSAN: uninit-value in neigh_dump_info+0x1af0/0x2250 net/core/neighbour.c:2438
CPU: 1 PID: 3575 Comm: syzkaller268891 Not tainted 4.16.0+ #83
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:17 [inline]
dump_stack+0x185/0x1d0 lib/dump_stack.c:53
kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
__msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
neigh_master_filtered net/core/neighbour.c:2292 [inline]
neigh_dump_table net/core/neighbour.c:2348 [inline]
neigh_dump_info+0x1af0/0x2250 net/core/neighbour.c:2438
netlink_dump+0x9ad/0x1540 net/netlink/af_netlink.c:2225
__netlink_dump_start+0x1167/0x12a0 net/netlink/af_netlink.c:2322
netlink_dump_start include/linux/netlink.h:214 [inline]
rtnetlink_rcv_msg+0x1435/0x1560 net/core/rtnetlink.c:4598
netlink_rcv_skb+0x355/0x5f0 net/netlink/af_netlink.c:2447
rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4653
netlink_unicast_kernel net/netlink/af_netlink.c:1311 [inline]
netlink_unicast+0x1672/0x1750 net/netlink/af_netlink.c:1337
netlink_sendmsg+0x1048/0x1310 net/netlink/af_netlink.c:1900
sock_sendmsg_nosec net/socket.c:630 [inline]
sock_sendmsg net/socket.c:640 [inline]
___sys_sendmsg+0xec0/0x1310 net/socket.c:2046
__sys_sendmsg net/socket.c:2080 [inline]
SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091
SyS_sendmsg+0x54/0x80 net/socket.c:2087
do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x43fed9
RSP: 002b:00007ffddbee2798 EFLAGS: 00000213 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043fed9
RDX: 0000000000000000 RSI: 0000000020005000 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 00000000004002c8 R09: 00000000004002c8
R10: 00000000004002c8 R11: 0000000000000213 R12: 0000000000401800
R13: 0000000000401890 R14: 0000000000000000 R15: 0000000000000000
Uninit was created at:
kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188
kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314
kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321
slab_post_alloc_hook mm/slab.h:445 [inline]
slab_alloc_node mm/slub.c:2737 [inline]
__kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369
__kmalloc_reserve net/core/skbuff.c:138 [inline]
__alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206
alloc_skb include/linux/skbuff.h:984 [inline]
netlink_alloc_large_skb net/netlink/af_netlink.c:1183 [inline]
netlink_sendmsg+0x9a6/0x1310 net/netlink/af_netlink.c:1875
sock_sendmsg_nosec net/socket.c:630 [inline]
sock_sendmsg net/socket.c:640 [inline]
___sys_sendmsg+0xec0/0x1310 net/socket.c:2046
__sys_sendmsg net/socket.c:2080 [inline]
SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091
SyS_sendmsg+0x54/0x80 net/socket.c:2087
do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
Fixes: 21fdd092acc7 ("net: Add support for filtering neigh dump by master device")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: David Ahern <dsa@cumulusnetworks.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/neighbour.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index e22d2aefbd78..ce519861be59 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2331,12 +2331,16 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL, NULL);
if (!err) {
- if (tb[NDA_IFINDEX])
+ if (tb[NDA_IFINDEX]) {
+ if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32))
+ return -EINVAL;
filter_idx = nla_get_u32(tb[NDA_IFINDEX]);
-
- if (tb[NDA_MASTER])
+ }
+ if (tb[NDA_MASTER]) {
+ if (nla_len(tb[NDA_MASTER]) != sizeof(u32))
+ return -EINVAL;
filter_master_idx = nla_get_u32(tb[NDA_MASTER]);
-
+ }
if (filter_idx || filter_master_idx)
flags |= NLM_F_DUMP_FILTERED;
}
--
2.14.3
From 72fa6ac4402ee994a21ad60f27f95588868cc2f3 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Thu, 19 Apr 2018 03:16:16 -0400
Subject: [PATCH 45/52] bnxt_en: Fix memory fault in bnxt_ethtool_init()
[ Upstream commit a60faa60da891e311e19fd3e88d611863f431130 ]
In some firmware images, the length of BNX_DIR_TYPE_PKG_LOG nvram type
could be greater than the fixed buffer length of 4096 bytes allocated by
the driver. This was causing HWRM_NVM_READ to copy more data to the buffer
than the allocated size, causing general protection fault.
Fix the issue by allocating the exact buffer length returned by
HWRM_NVM_FIND_DIR_ENTRY, instead of 4096. Move the kzalloc() call
into the bnxt_get_pkgver() function.
Fixes: 3ebf6f0a09a2 ("bnxt_en: Add installed-package firmware version reporting via Ethtool GDRVINFO")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 49 ++++++++++++----------
drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h | 2 -
2 files changed, 27 insertions(+), 24 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 1801582076be..9442605f4fd4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1874,22 +1874,39 @@ static char *bnxt_parse_pkglog(int desired_field, u8 *data, size_t datalen)
return retval;
}
-static char *bnxt_get_pkgver(struct net_device *dev, char *buf, size_t buflen)
+static void bnxt_get_pkgver(struct net_device *dev)
{
+ struct bnxt *bp = netdev_priv(dev);
u16 index = 0;
- u32 datalen;
+ char *pkgver;
+ u32 pkglen;
+ u8 *pkgbuf;
+ int len;
if (bnxt_find_nvram_item(dev, BNX_DIR_TYPE_PKG_LOG,
BNX_DIR_ORDINAL_FIRST, BNX_DIR_EXT_NONE,
- &index, NULL, &datalen) != 0)
- return NULL;
+ &index, NULL, &pkglen) != 0)
+ return;
- memset(buf, 0, buflen);
- if (bnxt_get_nvram_item(dev, index, 0, datalen, buf) != 0)
- return NULL;
+ pkgbuf = kzalloc(pkglen, GFP_KERNEL);
+ if (!pkgbuf) {
+ dev_err(&bp->pdev->dev, "Unable to allocate memory for pkg version, length = %u\n",
+ pkglen);
+ return;
+ }
+
+ if (bnxt_get_nvram_item(dev, index, 0, pkglen, pkgbuf))
+ goto err;
- return bnxt_parse_pkglog(BNX_PKG_LOG_FIELD_IDX_PKG_VERSION, buf,
- datalen);
+ pkgver = bnxt_parse_pkglog(BNX_PKG_LOG_FIELD_IDX_PKG_VERSION, pkgbuf,
+ pkglen);
+ if (pkgver && *pkgver != 0 && isdigit(*pkgver)) {
+ len = strlen(bp->fw_ver_str);
+ snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len - 1,
+ "/pkg %s", pkgver);
+ }
+err:
+ kfree(pkgbuf);
}
static int bnxt_get_eeprom(struct net_device *dev,
@@ -2558,22 +2575,10 @@ void bnxt_ethtool_init(struct bnxt *bp)
struct hwrm_selftest_qlist_input req = {0};
struct bnxt_test_info *test_info;
struct net_device *dev = bp->dev;
- char *pkglog;
int i, rc;
- pkglog = kzalloc(BNX_PKG_LOG_MAX_LENGTH, GFP_KERNEL);
- if (pkglog) {
- char *pkgver;
- int len;
+ bnxt_get_pkgver(dev);
- pkgver = bnxt_get_pkgver(dev, pkglog, BNX_PKG_LOG_MAX_LENGTH);
- if (pkgver && *pkgver != 0 && isdigit(*pkgver)) {
- len = strlen(bp->fw_ver_str);
- snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len - 1,
- "/pkg %s", pkgver);
- }
- kfree(pkglog);
- }
if (bp->hwrm_spec_code < 0x10704 || !BNXT_SINGLE_PF(bp))
return;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h
index 73f2249555b5..83444811d3c6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h
@@ -59,8 +59,6 @@ enum bnxt_nvm_directory_type {
#define BNX_DIR_ATTR_NO_CHKSUM (1 << 0)
#define BNX_DIR_ATTR_PROP_STREAM (1 << 1)
-#define BNX_PKG_LOG_MAX_LENGTH 4096
-
enum bnxnvm_pkglog_field_index {
BNX_PKG_LOG_FIELD_IDX_INSTALLED_TIMESTAMP = 0,
BNX_PKG_LOG_FIELD_IDX_PKG_DESCRIPTION = 1,
--
2.14.3
From 90b6aae662d735d10a2234ef3b7210855d1dcde8 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 13 Apr 2018 14:58:25 +0800
Subject: [PATCH 46/52] virtio-net: add missing virtqueue kick when flushing
packets
[ Upstream commit 9267c430c6b6f4c0120e3c6bb847313d633f02a6 ]
We tends to batch submitting packets during XDP_TX. This requires to
kick virtqueue after a batch, we tried to do it through
xdp_do_flush_map() which only makes sense for devmap not XDP_TX. So
explicitly kick the virtqueue in this case.
Reported-by: Kimitoshi Takahashi <ktaka@nii.ac.jp>
Tested-by: Kimitoshi Takahashi <ktaka@nii.ac.jp>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Fixes: 186b3c998c50 ("virtio-net: support XDP_REDIRECT")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/virtio_net.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 23374603e4d9..d8e1aeab4341 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1269,7 +1269,9 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
{
struct receive_queue *rq =
container_of(napi, struct receive_queue, napi);
- unsigned int received;
+ struct virtnet_info *vi = rq->vq->vdev->priv;
+ struct send_queue *sq;
+ unsigned int received, qp;
bool xdp_xmit = false;
virtnet_poll_cleantx(rq);
@@ -1280,8 +1282,13 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
if (received < budget)
virtqueue_napi_complete(napi, rq->vq, received);
- if (xdp_xmit)
+ if (xdp_xmit) {
+ qp = vi->curr_queue_pairs - vi->xdp_queue_pairs +
+ smp_processor_id();
+ sq = &vi->sq[qp];
+ virtqueue_kick(sq->vq);
xdp_do_flush_map();
+ }
return received;
}
--
2.14.3
From 3568805fd83b56e9c459af3a589c80a007edc5a0 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 17 Apr 2018 14:25:58 +0800
Subject: [PATCH 47/52] VSOCK: make af_vsock.ko removable again
[ Upstream commit 05e489b1596f0aa1025a1fa572676631cd9665da ]
Commit c1eef220c1760762753b602c382127bfccee226d ("vsock: always call
vsock_init_tables()") introduced a module_init() function without a
corresponding module_exit() function.
Modules with an init function can only be removed if they also have an
exit function. Therefore the vsock module was considered "permanent"
and could not be removed.
This patch adds an empty module_exit() function so that "rmmod vsock"
works. No explicit cleanup is required because:
1. Transports call vsock_core_exit() upon exit and cannot be removed
while sockets are still alive.
2. vsock_diag.ko does not perform any action that requires cleanup by
vsock.ko.
Fixes: c1eef220c176 ("vsock: always call vsock_init_tables()")
Reported-by: Xiumei Mu <xmu@redhat.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/vmw_vsock/af_vsock.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index e0fc84daed94..ad17a985f74e 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -2018,7 +2018,13 @@ const struct vsock_transport *vsock_core_get_transport(void)
}
EXPORT_SYMBOL_GPL(vsock_core_get_transport);
+static void __exit vsock_exit(void)
+{
+ /* Do nothing. This function makes this module removable. */
+}
+
module_init(vsock_init_tables);
+module_exit(vsock_exit);
MODULE_AUTHOR("VMware, Inc.");
MODULE_DESCRIPTION("VMware Virtual Socket Family");
--
2.14.3
From 6bfeaae3815960639511ea826da27a7303705d52 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <igor.russkikh@aquantia.com>
Date: Wed, 11 Apr 2018 15:23:24 +0300
Subject: [PATCH 48/52] net: aquantia: Regression on reset with 1.x firmware
[ Upstream commit cce96d1883dae4b79f44890e5118243d806da286 ]
On ASUS XG-C100C with 1.5.44 firmware a special mode called "dirty wake"
is active. With this mode when motherboard gets powered (but no poweron
happens yet), NIC automatically enables powersave link and watches
for WOL packet.
This normally allows to powerup the PC after AC power failures.
Not all motherboards or bios settings gives power to PCI slots,
so this mode is not enabled on all the hardware.
4.16 linux driver introduced full hardware reset sequence
This is required since before that we had no NIC hardware
reset implemented and there were side effects of "not clean start".
But this full reset is incompatible with "dirty wake" WOL feature
it keeps the PHY link in a special mode forever. As a consequence,
driver sees no link and no traffic.
To fix this we forcibly change FW state to idle state before doing
the full reset. This makes FW to restore link state.
Fixes: c8c82eb net: aquantia: Introduce global AQC hardware reset sequence
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
.../net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index d3b847ec7465..c58b2c227260 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -48,6 +48,8 @@
#define FORCE_FLASHLESS 0
static int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual);
+static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
+ enum hal_atl_utils_fw_state_e state);
int hw_atl_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops)
{
@@ -247,6 +249,20 @@ int hw_atl_utils_soft_reset(struct aq_hw_s *self)
self->rbl_enabled = (boot_exit_code != 0);
+ /* FW 1.x may bootup in an invalid POWER state (WOL feature).
+ * We should work around this by forcing its state back to DEINIT
+ */
+ if (!hw_atl_utils_ver_match(HW_ATL_FW_VER_1X,
+ aq_hw_read_reg(self,
+ HW_ATL_MPI_FW_VERSION))) {
+ int err = 0;
+
+ hw_atl_utils_mpi_set_state(self, MPI_DEINIT);
+ AQ_HW_WAIT_FOR((aq_hw_read_reg(self, HW_ATL_MPI_STATE_ADR) &
+ HW_ATL_MPI_STATE_MSK) == MPI_DEINIT,
+ 10, 1000U);
+ }
+
if (self->rbl_enabled)
return hw_atl_utils_soft_reset_rbl(self);
else
--
2.14.3
From bda6d4336167a70055dd4772d682b0b85eae7e6a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Tue, 17 Apr 2018 22:46:38 +0200
Subject: [PATCH 49/52] tun: fix vlan packet truncation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
[ Upstream commit 81c895072d29cd70eea5be1a8587cd6461c3715a ]
Bogus trimming in tun_net_xmit() causes truncated vlan packets.
skb->len is correct whether or not skb_vlan_tag_present() is true. There
is no more reason to adjust the skb length on xmit in this driver than
any other driver. tun_put_user() adds 4 bytes to the total for tagged
packets because it transmits the tag inline to userspace. This is
similar to a nic transmitting the tag inline on the wire.
Reproducing the bug by sending any tagged packet through back-to-back
connected tap interfaces:
socat TUN,tun-type=tap,iff-up,tun-name=in TUN,tun-type=tap,iff-up,tun-name=out &
ip link add link in name in.20 type vlan id 20
ip addr add 10.9.9.9/24 dev in.20
ip link set in.20 up
tshark -nxxi in -f arp -c1 2>/dev/null &
tshark -nxxi out -f arp -c1 2>/dev/null &
ping -c 1 10.9.9.5 >/dev/null 2>&1
The output from the 'in' and 'out' interfaces are different when the
bug is present:
Capturing on 'in'
0000 ff ff ff ff ff ff 76 cf 76 37 d5 0a 81 00 00 14 ......v.v7......
0010 08 06 00 01 08 00 06 04 00 01 76 cf 76 37 d5 0a ..........v.v7..
0020 0a 09 09 09 00 00 00 00 00 00 0a 09 09 05 ..............
Capturing on 'out'
0000 ff ff ff ff ff ff 76 cf 76 37 d5 0a 81 00 00 14 ......v.v7......
0010 08 06 00 01 08 00 06 04 00 01 76 cf 76 37 d5 0a ..........v.v7..
0020 0a 09 09 09 00 00 00 00 00 00 ..........
Fixes: aff3d70a07ff ("tun: allow to attach ebpf socket filter")
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/tun.c | 7 +------
1 file changed, 1 insertion(+), 6 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 28cfa642e39a..6c7bdd0c361a 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1094,12 +1094,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
goto drop;
len = run_ebpf_filter(tun, skb, len);
-
- /* Trim extra bytes since we may insert vlan proto & TCI
- * in tun_put_user().
- */
- len -= skb_vlan_tag_present(skb) ? sizeof(struct veth) : 0;
- if (len <= 0 || pskb_trim(skb, len))
+ if (len == 0 || pskb_trim(skb, len))
goto drop;
if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
--
2.14.3
From 2255c814cccdf75349c4e63fa8131127521a70f9 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <igor.russkikh@aquantia.com>
Date: Wed, 11 Apr 2018 15:23:25 +0300
Subject: [PATCH 50/52] net: aquantia: oops when shutdown on already stopped
device
[ Upstream commit 9a11aff25fd43d5bd2660ababdc9f564b0ba183a ]
In case netdev is closed at the moment of pci shutdown, aq_nic_stop
gets called second time. napi_disable in that case hangs indefinitely.
In other case, if device was never opened at all, we get oops because
of null pointer access.
We should invoke aq_nic_stop conditionally, only if device is running
at the moment of shutdown.
Reported-by: David Arcari <darcari@redhat.com>
Fixes: 90869ddfefeb ("net: aquantia: Implement pci shutdown callback")
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/aquantia/atlantic/aq_nic.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index c96a92118b8b..32f6d2e24d66 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -951,9 +951,11 @@ void aq_nic_shutdown(struct aq_nic_s *self)
netif_device_detach(self->ndev);
- err = aq_nic_stop(self);
- if (err < 0)
- goto err_exit;
+ if (netif_running(self->ndev)) {
+ err = aq_nic_stop(self);
+ if (err < 0)
+ goto err_exit;
+ }
aq_nic_deinit(self);
err_exit:
--
2.14.3
From e18daf5cca8b97e6a766e7b4bf64e1edf60cdc87 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 19 Apr 2018 08:30:48 +0300
Subject: [PATCH 51/52] virtio_net: split out ctrl buffer
[ Upstream commit 12e571693837d6164bda61e316b1944972ee0d97 ]
When sending control commands, virtio net sets up several buffers for
DMA. The buffers are all part of the net device which means it's
actually allocated by kvmalloc so it's in theory (on extreme memory
pressure) possible to get a vmalloc'ed buffer which on some platforms
means we can't DMA there.
Fix up by moving the DMA buffers into a separate structure.
Reported-by: Mikulas Patocka <mpatocka@redhat.com>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/virtio_net.c | 68 +++++++++++++++++++++++++++---------------------
1 file changed, 39 insertions(+), 29 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d8e1aeab4341..2e7e187117b5 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -147,6 +147,17 @@ struct receive_queue {
struct xdp_rxq_info xdp_rxq;
};
+/* Control VQ buffers: protected by the rtnl lock */
+struct control_buf {
+ struct virtio_net_ctrl_hdr hdr;
+ virtio_net_ctrl_ack status;
+ struct virtio_net_ctrl_mq mq;
+ u8 promisc;
+ u8 allmulti;
+ u16 vid;
+ u64 offloads;
+};
+
struct virtnet_info {
struct virtio_device *vdev;
struct virtqueue *cvq;
@@ -192,14 +203,7 @@ struct virtnet_info {
struct hlist_node node;
struct hlist_node node_dead;
- /* Control VQ buffers: protected by the rtnl lock */
- struct virtio_net_ctrl_hdr ctrl_hdr;
- virtio_net_ctrl_ack ctrl_status;
- struct virtio_net_ctrl_mq ctrl_mq;
- u8 ctrl_promisc;
- u8 ctrl_allmulti;
- u16 ctrl_vid;
- u64 ctrl_offloads;
+ struct control_buf *ctrl;
/* Ethtool settings */
u8 duplex;
@@ -1461,25 +1465,25 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
/* Caller should know better */
BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ));
- vi->ctrl_status = ~0;
- vi->ctrl_hdr.class = class;
- vi->ctrl_hdr.cmd = cmd;
+ vi->ctrl->status = ~0;
+ vi->ctrl->hdr.class = class;
+ vi->ctrl->hdr.cmd = cmd;
/* Add header */
- sg_init_one(&hdr, &vi->ctrl_hdr, sizeof(vi->ctrl_hdr));
+ sg_init_one(&hdr, &vi->ctrl->hdr, sizeof(vi->ctrl->hdr));
sgs[out_num++] = &hdr;
if (out)
sgs[out_num++] = out;
/* Add return status. */
- sg_init_one(&stat, &vi->ctrl_status, sizeof(vi->ctrl_status));
+ sg_init_one(&stat, &vi->ctrl->status, sizeof(vi->ctrl->status));
sgs[out_num] = &stat;
BUG_ON(out_num + 1 > ARRAY_SIZE(sgs));
virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC);
if (unlikely(!virtqueue_kick(vi->cvq)))
- return vi->ctrl_status == VIRTIO_NET_OK;
+ return vi->ctrl->status == VIRTIO_NET_OK;
/* Spin for a response, the kick causes an ioport write, trapping
* into the hypervisor, so the request should be handled immediately.
@@ -1488,7 +1492,7 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
!virtqueue_is_broken(vi->cvq))
cpu_relax();
- return vi->ctrl_status == VIRTIO_NET_OK;
+ return vi->ctrl->status == VIRTIO_NET_OK;
}
static int virtnet_set_mac_address(struct net_device *dev, void *p)
@@ -1600,8 +1604,8 @@ static int _virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
return 0;
- vi->ctrl_mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs);
- sg_init_one(&sg, &vi->ctrl_mq, sizeof(vi->ctrl_mq));
+ vi->ctrl->mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs);
+ sg_init_one(&sg, &vi->ctrl->mq, sizeof(vi->ctrl->mq));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg)) {
@@ -1660,22 +1664,22 @@ static void virtnet_set_rx_mode(struct net_device *dev)
if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX))
return;
- vi->ctrl_promisc = ((dev->flags & IFF_PROMISC) != 0);
- vi->ctrl_allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
+ vi->ctrl->promisc = ((dev->flags & IFF_PROMISC) != 0);
+ vi->ctrl->allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
- sg_init_one(sg, &vi->ctrl_promisc, sizeof(vi->ctrl_promisc));
+ sg_init_one(sg, &vi->ctrl->promisc, sizeof(vi->ctrl->promisc));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
VIRTIO_NET_CTRL_RX_PROMISC, sg))
dev_warn(&dev->dev, "Failed to %sable promisc mode.\n",
- vi->ctrl_promisc ? "en" : "dis");
+ vi->ctrl->promisc ? "en" : "dis");
- sg_init_one(sg, &vi->ctrl_allmulti, sizeof(vi->ctrl_allmulti));
+ sg_init_one(sg, &vi->ctrl->allmulti, sizeof(vi->ctrl->allmulti));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
VIRTIO_NET_CTRL_RX_ALLMULTI, sg))
dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
- vi->ctrl_allmulti ? "en" : "dis");
+ vi->ctrl->allmulti ? "en" : "dis");
uc_count = netdev_uc_count(dev);
mc_count = netdev_mc_count(dev);
@@ -1721,8 +1725,8 @@ static int virtnet_vlan_rx_add_vid(struct net_device *dev,
struct virtnet_info *vi = netdev_priv(dev);
struct scatterlist sg;
- vi->ctrl_vid = vid;
- sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid));
+ vi->ctrl->vid = vid;
+ sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
VIRTIO_NET_CTRL_VLAN_ADD, &sg))
@@ -1736,8 +1740,8 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev,
struct virtnet_info *vi = netdev_priv(dev);
struct scatterlist sg;
- vi->ctrl_vid = vid;
- sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid));
+ vi->ctrl->vid = vid;
+ sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
VIRTIO_NET_CTRL_VLAN_DEL, &sg))
@@ -2133,9 +2137,9 @@ static int virtnet_restore_up(struct virtio_device *vdev)
static int virtnet_set_guest_offloads(struct virtnet_info *vi, u64 offloads)
{
struct scatterlist sg;
- vi->ctrl_offloads = cpu_to_virtio64(vi->vdev, offloads);
+ vi->ctrl->offloads = cpu_to_virtio64(vi->vdev, offloads);
- sg_init_one(&sg, &vi->ctrl_offloads, sizeof(vi->ctrl_offloads));
+ sg_init_one(&sg, &vi->ctrl->offloads, sizeof(vi->ctrl->offloads));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_GUEST_OFFLOADS,
VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET, &sg)) {
@@ -2358,6 +2362,7 @@ static void virtnet_free_queues(struct virtnet_info *vi)
kfree(vi->rq);
kfree(vi->sq);
+ kfree(vi->ctrl);
}
static void _free_receive_bufs(struct virtnet_info *vi)
@@ -2550,6 +2555,9 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
{
int i;
+ vi->ctrl = kzalloc(sizeof(*vi->ctrl), GFP_KERNEL);
+ if (!vi->ctrl)
+ goto err_ctrl;
vi->sq = kzalloc(sizeof(*vi->sq) * vi->max_queue_pairs, GFP_KERNEL);
if (!vi->sq)
goto err_sq;
@@ -2578,6 +2586,8 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
err_rq:
kfree(vi->sq);
err_sq:
+ kfree(vi->ctrl);
+err_ctrl:
return -ENOMEM;
}
--
2.14.3
From b36782ab992fe9a1de353752d027e13b7ee34ad5 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 19 Apr 2018 08:30:49 +0300
Subject: [PATCH 52/52] virtio_net: fix adding vids on big-endian
[ Upstream commit d7fad4c840f33a6bd333dd7fbb3006edbcf0017a ]
Programming vids (adding or removing them) still passes
guest-endian values in the DMA buffer. That's wrong
if guest is big-endian and when virtio 1 is enabled.
Note: this is on top of a previous patch:
virtio_net: split out ctrl buffer
Fixes: 9465a7a6f ("virtio_net: enable v1.0 support")
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/virtio_net.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 2e7e187117b5..aa21b2225679 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -154,7 +154,7 @@ struct control_buf {
struct virtio_net_ctrl_mq mq;
u8 promisc;
u8 allmulti;
- u16 vid;
+ __virtio16 vid;
u64 offloads;
};
@@ -1725,7 +1725,7 @@ static int virtnet_vlan_rx_add_vid(struct net_device *dev,
struct virtnet_info *vi = netdev_priv(dev);
struct scatterlist sg;
- vi->ctrl->vid = vid;
+ vi->ctrl->vid = cpu_to_virtio16(vi->vdev, vid);
sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
@@ -1740,7 +1740,7 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev,
struct virtnet_info *vi = netdev_priv(dev);
struct scatterlist sg;
- vi->ctrl->vid = vid;
+ vi->ctrl->vid = cpu_to_virtio16(vi->vdev, vid);
sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
--
2.14.3
next reply other threads:[~2018-04-26 18:38 UTC|newest]
Thread overview: 308+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-04-26 18:38 David Miller [this message]
2018-04-26 18:50 ` [PATCHES] Networking Greg KH
-- strict thread matches above, loose matches on Subject: below --
2020-09-24 21:40 David Miller
2020-09-25 8:38 ` Greg KH
2020-08-24 16:52 David Miller
2020-08-26 10:13 ` Greg KH
2020-08-15 1:36 David Miller
2020-08-17 9:37 ` Greg KH
2020-08-08 1:53 David Miller
2020-08-10 12:08 ` Greg KH
2020-07-29 3:12 David Miller
2020-07-29 11:42 ` Greg KH
2020-07-16 23:07 David Miller
2020-07-17 8:21 ` Greg KH
2020-06-28 0:55 David Miller
2020-06-28 14:15 ` Greg KH
2020-06-16 1:27 David Miller
2020-06-16 7:43 ` Greg KH
2020-06-17 16:16 ` Greg KH
2020-06-10 0:08 David Miller
2020-06-11 10:01 ` Greg KH
2020-06-07 2:55 David Miller
2020-06-07 13:01 ` Greg KH
2020-05-27 6:16 David Miller
2020-05-28 12:21 ` Greg KH
2020-05-16 0:44 David Miller
2020-05-16 16:14 ` Greg KH
2020-05-12 0:41 David Miller
2020-05-12 8:59 ` Greg KH
2020-04-27 1:10 David Miller
2020-04-27 11:40 ` Greg KH
2020-04-17 17:51 David Miller
2020-04-18 9:08 ` Greg KH
2020-04-08 22:05 David Miller
2020-04-09 11:17 ` Greg KH
2020-04-02 20:16 David Miller
2020-04-02 20:23 ` Greg KH
2020-03-27 23:51 David Miller
2020-03-28 8:49 ` Greg KH
2020-03-14 4:52 David Miller
2020-03-15 8:34 ` Greg KH
2020-03-01 5:11 David Miller
2020-03-01 9:27 ` Greg KH
2020-02-18 23:41 David Miller
2020-02-19 20:32 ` Greg KH
2020-02-09 21:21 David Miller
2020-02-09 21:54 ` Greg KH
2020-02-05 14:07 David Miller
2020-02-06 6:54 ` Greg KH
2020-01-30 10:12 David Miller
2020-01-30 10:22 ` Greg KH
2020-01-27 11:16 David Miller
2020-01-27 14:27 ` Greg KH
2020-01-20 19:44 David Miller
2020-01-21 15:29 ` Greg KH
2020-01-11 0:33 David Miller
2020-01-11 8:19 ` Greg KH
2020-01-01 20:13 David Miller
2020-01-01 21:37 ` Greg KH
2019-12-28 8:14 David Miller
2019-12-28 11:23 ` Greg KH
2019-12-16 22:10 David Miller
2019-12-17 7:43 ` Greg KH
2019-12-19 15:42 ` Greg KH
2019-12-03 3:21 David Miller
2019-12-03 6:46 ` Greg KH
2019-11-25 5:54 David Miller
2019-11-25 13:31 ` Greg KH
2019-11-18 8:08 David Miller
2019-11-18 8:16 ` Greg KH
2019-11-10 5:47 David Miller
2019-11-10 15:34 ` Greg KH
2019-10-24 21:30 David Miller
2019-10-25 1:38 ` Greg KH
2019-10-05 21:57 David Miller
2019-10-06 7:50 ` Greg KH
2019-09-29 22:39 David Miller
2019-10-01 13:38 ` Greg KH
2019-09-19 12:07 David Miller
2019-09-19 13:02 ` Greg KH
2019-09-15 19:37 David Miller
2019-09-16 11:05 ` Greg KH
2019-09-05 7:23 David Miller
2019-09-08 10:40 ` Greg KH
2019-08-28 0:42 David Miller
2019-09-02 16:30 ` Greg KH
2019-09-02 17:51 ` David Miller
2019-08-20 23:01 David Miller
2019-08-20 23:19 ` Greg KH
2019-08-07 23:27 David Miller
2019-08-08 6:57 ` Greg KH
2019-07-25 1:55 David Miller
2019-07-26 8:54 ` Greg KH
2019-07-02 1:52 David Miller
2019-07-02 4:40 ` Greg KH
2019-06-18 4:23 David Miller
2019-06-19 12:35 ` Greg KH
2019-06-08 23:27 David Miller
2019-06-09 7:26 ` Greg KH
2019-06-09 19:42 ` David Miller
2019-05-21 6:37 David Miller
2019-05-22 6:36 ` Greg KH
2019-05-14 19:58 David Miller
2019-05-15 6:02 ` Greg KH
2019-05-04 7:01 David Miller
2019-05-04 7:34 ` Greg KH
2019-04-30 2:06 David Miller
2019-04-30 7:53 ` Greg KH
2019-04-18 22:53 David Miller
2019-04-23 20:06 ` Greg KH
2019-04-10 3:55 David Miller
2019-04-10 15:35 ` Sasha Levin
2019-03-28 19:24 David Miller
2019-03-28 20:55 ` Greg KH
2019-03-28 21:51 ` Greg KH
2019-03-28 23:18 ` David Miller
2019-03-29 6:18 ` Greg KH
2019-03-15 1:47 David Miller
2019-03-15 6:30 ` Greg KH
2019-03-19 13:03 ` Greg KH
2019-03-07 22:47 David Miller
2019-03-08 6:38 ` Greg KH
2019-02-24 5:18 David Miller
2019-02-24 7:52 ` Greg KH
2019-02-20 20:42 David Miller
2019-02-21 3:08 ` Sasha Levin
2019-02-21 7:21 ` Greg KH
2019-02-09 23:21 David Miller
2019-02-10 12:21 ` Greg KH
2019-02-01 21:45 David Miller
2019-02-02 9:55 ` Greg KH
2019-01-26 0:18 David Miller
2019-01-26 9:29 ` Greg KH
2019-01-21 23:28 David Miller
2019-01-22 7:18 ` Greg KH
2019-01-23 7:33 ` Greg KH
2019-01-20 19:12 David Miller
2019-01-21 8:00 ` Greg KH
2019-01-04 18:17 David Miller
2019-01-04 18:48 ` Greg KH
2018-12-12 6:31 David Miller
2018-12-13 9:53 ` Greg KH
2018-12-03 7:01 David Miller
2018-12-03 9:13 ` Greg KH
2018-11-21 3:49 David Miller
2018-11-21 17:49 ` Greg KH
2018-11-02 3:55 David Miller
2018-11-02 5:27 ` Greg KH
2018-09-24 16:46 David Miller
2018-09-26 9:32 ` Greg KH
2018-09-18 16:14 David Miller
2018-09-20 5:25 ` Greg KH
2018-09-11 6:15 David Miller
2018-09-11 8:29 ` Greg KH
2018-08-17 19:32 David Miller
2018-08-18 9:43 ` Greg KH
2018-08-04 5:05 David Miller
2018-08-04 7:33 ` Greg KH
2018-08-01 5:32 David Miller
2018-08-01 6:20 ` Greg KH
2018-07-26 23:50 David Miller
2018-07-27 0:06 ` Eric Dumazet
2018-07-27 6:34 ` Greg KH
2018-07-23 3:51 David Miller
2018-07-23 6:21 ` Greg KH
2018-07-18 23:35 David Miller
2018-07-19 6:33 ` Greg KH
2018-06-20 12:37 David Miller
2018-06-21 21:10 ` Greg KH
2018-06-24 11:20 ` Greg KH
2018-06-08 2:18 David Miller
2018-06-08 4:52 ` Greg KH
2018-05-15 20:50 David Miller
2018-05-16 8:40 ` Greg KH
2018-04-13 17:47 David Miller
2018-04-14 14:04 ` Greg KH
2018-04-10 19:39 David Miller
2018-04-10 21:26 ` Greg KH
2018-03-28 15:35 David Miller
2018-03-28 15:40 ` Willy Tarreau
2018-03-28 15:46 ` David Miller
2018-03-28 16:36 ` Greg KH
2018-03-28 16:49 ` Greg KH
2018-03-07 2:28 David Miller
2018-03-07 3:30 ` Greg KH
2018-02-06 20:19 David Miller
2018-02-07 19:39 ` Greg KH
2018-01-28 16:22 David Miller
2018-01-28 16:39 ` Greg KH
2018-01-12 21:12 David Miller
2018-01-13 9:54 ` Greg KH
2017-12-31 4:15 David Miller
2017-12-31 10:14 ` Greg KH
2017-12-12 15:44 David Miller
2017-12-14 17:51 ` Greg KH
2017-11-20 11:47 David Miller
2017-11-21 14:04 ` Greg KH
2017-11-14 6:36 David Miller
2017-11-16 14:12 ` Greg KH
2017-10-09 4:02 David Miller
2017-10-09 7:34 ` Greg KH
2017-10-09 7:56 ` Greg KH
2017-10-09 16:55 ` David Miller
2017-10-09 19:04 ` Greg KH
2017-10-09 22:54 ` David Miller
2017-10-10 14:10 ` Greg KH
2017-09-15 4:57 David Miller
2017-09-15 6:24 ` Greg KH
2018-06-07 7:00 ` Jiri Slaby
2018-06-07 9:21 ` Greg KH
2018-06-07 10:47 ` Ido Schimmel
2018-06-07 10:52 ` Greg KH
2018-07-05 16:15 ` Greg KH
2018-07-05 16:42 ` Ido Schimmel
2017-08-24 3:24 David Miller
2017-08-25 0:55 ` Greg KH
2017-08-11 5:25 David Miller
2017-08-11 16:22 ` Greg KH
2017-08-08 23:21 David Miller
2017-08-08 23:30 ` Greg KH
2017-07-17 16:44 David Miller
2017-07-17 19:23 ` Greg KH
2017-07-19 10:27 ` Greg KH
2017-06-29 16:19 David Miller
2017-06-29 17:34 ` Greg KH
2017-05-30 23:14 David Miller
2017-05-31 0:18 ` Greg KH
2017-05-11 2:41 David Miller
2017-05-11 13:10 ` Greg KH
2017-05-22 10:16 ` Greg KH
2017-04-28 19:41 David Miller
2017-04-29 6:23 ` Greg KH
2017-03-25 7:53 David Miller
2017-03-25 9:26 ` Thomas Backlund
2017-03-25 17:38 ` David Miller
2017-03-26 18:47 ` Thomas Backlund
2017-03-27 16:19 ` Greg KH
2017-03-17 1:48 David Miller
2017-03-18 14:13 ` Greg KH
2017-02-23 19:54 David Miller
2017-02-23 20:19 ` Greg KH
2017-02-13 17:15 David Miller
2017-02-15 17:21 ` Greg KH
2017-01-31 21:50 [PATCHES] networking David Miller
2017-02-01 8:10 ` Greg KH
2017-01-12 18:55 [PATCHES] Networking David Miller
2017-01-12 20:40 ` Greg KH
2016-12-07 23:43 David Miller
2016-12-08 6:34 ` Greg KH
2016-11-18 2:59 David Miller
2016-11-18 10:36 ` Greg KH
2016-11-09 17:19 David Miller
2016-11-10 15:50 ` Greg KH
2016-09-21 5:07 David Miller
2016-09-21 9:23 ` Greg KH
2016-08-12 0:50 David Miller
2016-08-12 7:37 ` Greg KH
2016-07-13 21:43 David Miller
2016-07-13 22:38 ` Greg KH
2016-07-06 5:02 David Miller
2016-07-07 0:35 ` Greg KH
2016-06-17 7:03 David Miller
2016-06-18 1:01 ` Greg KH
2016-05-16 16:35 David Miller
2016-05-16 21:50 ` Greg KH
2016-04-15 4:45 David Miller
2016-04-16 17:49 ` Greg KH
2016-02-29 21:56 David Miller
2016-02-29 22:45 ` Greg KH
2016-01-27 2:00 David Miller
2016-01-27 6:35 ` Greg KH
2015-12-22 21:51 David Miller
2016-01-19 5:20 ` Greg KH
2016-01-19 12:00 ` Josh Boyer
2016-01-19 13:29 ` Josh Boyer
2016-01-19 17:39 ` Greg KH
2016-01-19 17:41 ` Josh Boyer
2015-12-10 19:37 David Miller
2015-12-11 16:49 ` Greg KH
2015-11-13 21:38 David Miller
2015-11-14 15:59 ` Jiri Slaby
2015-11-15 17:55 ` David Miller
2015-12-06 5:25 ` Greg KH
2015-10-21 3:51 David Miller
2015-10-23 16:25 ` Greg KH
2015-09-29 4:54 David Miller
2015-09-30 3:33 ` Greg KH
2015-08-27 6:05 David Miller
2015-08-27 7:29 ` Jiri Slaby
2015-08-27 13:35 ` Luis Henriques
2015-08-27 16:34 ` David Miller
2015-09-28 14:04 ` Greg KH
2015-09-26 19:21 ` Greg KH
2015-07-03 22:31 David Miller
2015-07-04 3:04 ` Greg KH
2015-06-10 3:01 David Miller
2015-06-10 13:26 ` Jiri Slaby
2015-06-19 18:03 ` Greg KH
2015-05-05 17:34 [PATCHES] NETWORKING David Miller
2015-05-06 6:57 ` Jiri Slaby
2015-05-08 11:14 ` Greg KH
2015-05-08 14:42 ` Greg KH
2015-04-29 4:48 [PATCHES] Networking David Miller
2015-04-29 11:09 ` Greg KH
2015-04-29 16:03 ` David Miller
2015-04-30 12:25 ` Jiri Slaby
[not found] <20150421.143012.2106864724544609194.davem@davemloft.net>
2015-04-27 9:23 ` Jiri Slaby
2015-05-04 19:53 ` Ben Hutchings
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180426.143848.775817046303070031.davem@davemloft.net \
--to=davem@davemloft.net \
--cc=stable@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).