From 501b72ae2472a15a80c0f4063ee8341870e1ef55 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Mon, 26 Oct 2020 11:29:45 +0100
Subject: net/sched: act_mpls: Add softdep on mpls_gso.ko
TCA_MPLS_ACT_PUSH and TCA_MPLS_ACT_MAC_PUSH might be used on gso
packets. Such packets will thus require mpls_gso.ko for segmentation.
v2: Drop dependency on CONFIG_NET_MPLS_GSO in Kconfig (from Jakub and
David).
Fixes: 2a2ea50870ba ("net: sched: add mpls manipulation actions to TC")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Link: https://lore.kernel.org/r/1f6cab15bbd15666795061c55563aaf6a386e90e.1603708007.git.gnault@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/sched/act_mpls.c | 1 +
1 file changed, 1 insertion(+)
(limited to 'net/sched')
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index f40bf9771cb9..5c7456e5b5cf 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -426,6 +426,7 @@ static void __exit mpls_cleanup_module(void)
module_init(mpls_init_module);
module_exit(mpls_cleanup_module);
+MODULE_SOFTDEP("post: mpls_gso");
MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("MPLS manipulation actions");
--
cgit v1.2.3-70-g09d2
From d6535dca28859d8d9ef80894eb287b2ac35a32e8 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Mon, 26 Oct 2020 14:33:27 +0200
Subject: net: protect tcf_block_unbind with block lock
The tcf_block_unbind() expects that the caller will take block->cb_lock
before calling it, however the code took RTNL lock and dropped cb_lock
instead. This causes to the following kernel panic.
WARNING: CPU: 1 PID: 13524 at net/sched/cls_api.c:1488 tcf_block_unbind+0x2db/0x420
Modules linked in: mlx5_ib mlx5_core mlxfw ptp pps_core act_mirred act_tunnel_key cls_flower vxlan ip6_udp_tunnel udp_tunnel dummy sch_ingress openvswitch nsh xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 br_netfilter rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi ib_umad ib_ipoib rdma_cm iw_cm ib_cm ib_uverbs ib_core overlay [last unloaded: mlxfw]
CPU: 1 PID: 13524 Comm: test-ecmp-add-v Tainted: G W 5.9.0+ #1
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
RIP: 0010:tcf_block_unbind+0x2db/0x420
Code: ff 48 83 c4 40 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8d bc 24 30 01 00 00 be ff ff ff ff e8 7d 7f 70 00 85 c0 0f 85 7b fd ff ff <0f> 0b e9 74 fd ff ff 48 c7 c7 dc 6a 24 84 e8 02 ec fe fe e9 55 fd
RSP: 0018:ffff888117d17968 EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff88812f713c00 RCX: 1ffffffff0848d5b
RDX: 0000000000000001 RSI: ffff88814fbc8130 RDI: ffff888107f2b878
RBP: 1ffff11022fa2f3f R08: 0000000000000000 R09: ffffffff84115a87
R10: fffffbfff0822b50 R11: ffff888107f2b898 R12: ffff88814fbc8000
R13: ffff88812f713c10 R14: ffff888117d17a38 R15: ffff88814fbc80c0
FS: 00007f6593d36740(0000) GS:ffff8882a4f00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00005607a00758f8 CR3: 0000000131aea006 CR4: 0000000000170ea0
Call Trace:
tc_block_indr_cleanup+0x3e0/0x5a0
? tcf_block_unbind+0x420/0x420
? __mutex_unlock_slowpath+0xe7/0x610
flow_indr_dev_unregister+0x5e2/0x930
? mlx5e_restore_tunnel+0xdf0/0xdf0 [mlx5_core]
? mlx5e_restore_tunnel+0xdf0/0xdf0 [mlx5_core]
? flow_indr_block_cb_alloc+0x3c0/0x3c0
? mlx5_db_free+0x37c/0x4b0 [mlx5_core]
mlx5e_cleanup_rep_tx+0x8b/0xc0 [mlx5_core]
mlx5e_detach_netdev+0xe5/0x120 [mlx5_core]
mlx5e_vport_rep_unload+0x155/0x260 [mlx5_core]
esw_offloads_disable+0x227/0x2b0 [mlx5_core]
mlx5_eswitch_disable_locked.cold+0x38e/0x699 [mlx5_core]
mlx5_eswitch_disable+0x94/0xf0 [mlx5_core]
mlx5_device_disable_sriov+0x183/0x1f0 [mlx5_core]
mlx5_core_sriov_configure+0xfd/0x230 [mlx5_core]
sriov_numvfs_store+0x261/0x2f0
? sriov_drivers_autoprobe_store+0x110/0x110
? sysfs_file_ops+0x170/0x170
? sysfs_file_ops+0x117/0x170
? sysfs_file_ops+0x170/0x170
kernfs_fop_write+0x1ff/0x3f0
? rcu_read_lock_any_held+0x6e/0x90
vfs_write+0x1f3/0x620
ksys_write+0xf9/0x1d0
? __x64_sys_read+0xb0/0xb0
? lockdep_hardirqs_on_prepare+0x273/0x3f0
? syscall_enter_from_user_mode+0x1d/0x50
do_syscall_64+0x2d/0x40
entry_SYSCALL_64_after_hwframe+0x44/0xa9
<...>
---[ end trace bfdd028ada702879 ]---
Fixes: 0fdcf78d5973 ("net: use flow_indr_dev_setup_offload()")
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20201026123327.1141066-1-leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/sched/cls_api.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
(limited to 'net/sched')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index faeabff283a2..838b3fd94d77 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -652,12 +652,12 @@ static void tc_block_indr_cleanup(struct flow_block_cb *block_cb)
block_cb->indr.binder_type,
&block->flow_block, tcf_block_shared(block),
&extack);
+ rtnl_lock();
down_write(&block->cb_lock);
list_del(&block_cb->driver_list);
list_move(&block_cb->list, &bo.cb_list);
- up_write(&block->cb_lock);
- rtnl_lock();
tcf_block_unbind(block, &bo);
+ up_write(&block->cb_lock);
rtnl_unlock();
}
--
cgit v1.2.3-70-g09d2
From eadd1befdd778a1eca57fad058782bd22b4db804 Mon Sep 17 00:00:00 2001
From: Aleksandr Nogikh <nogikh@google.com>
Date: Wed, 28 Oct 2020 17:07:31 +0000
Subject: netem: fix zero division in tabledist
Currently it is possible to craft a special netlink RTM_NEWQDISC
command that can result in jitter being equal to 0x80000000. It is
enough to set the 32 bit jitter to 0x02000000 (it will later be
multiplied by 2^6) or just set the 64 bit jitter via
TCA_NETEM_JITTER64. This causes an overflow during the generation of
uniformly distributed numbers in tabledist(), which in turn leads to
division by zero (sigma != 0, but sigma * 2 is 0).
The related fragment of code needs 32-bit division - see commit
9b0ed89 ("netem: remove unnecessary 64 bit modulus"), so switching to
64 bit is not an option.
Fix the issue by keeping the value of jitter within the range that can
be adequately handled by tabledist() - [0;INT_MAX]. As negative std
deviation makes no sense, take the absolute value of the passed value
and cap it at INT_MAX. Inside tabledist(), switch to unsigned 32 bit
arithmetic in order to prevent overflows.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Aleksandr Nogikh <nogikh@google.com>
Reported-by: syzbot+ec762a6342ad0d3c0d8f@syzkaller.appspotmail.com
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Link: https://lore.kernel.org/r/20201028170731.1383332-1-aleksandrnogikh@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/sched/sch_netem.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
(limited to 'net/sched')
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 84f82771cdf5..0c345e43a09a 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -330,7 +330,7 @@ static s64 tabledist(s64 mu, s32 sigma,
/* default uniform distribution */
if (dist == NULL)
- return ((rnd % (2 * sigma)) + mu) - sigma;
+ return ((rnd % (2 * (u32)sigma)) + mu) - sigma;
t = dist->table[rnd % dist->size];
x = (sigma % NETEM_DIST_SCALE) * t;
@@ -812,6 +812,10 @@ static void get_slot(struct netem_sched_data *q, const struct nlattr *attr)
q->slot_config.max_packets = INT_MAX;
if (q->slot_config.max_bytes == 0)
q->slot_config.max_bytes = INT_MAX;
+
+ /* capping dist_jitter to the range acceptable by tabledist() */
+ q->slot_config.dist_jitter = min_t(__s64, INT_MAX, abs(q->slot_config.dist_jitter));
+
q->slot.packets_left = q->slot_config.max_packets;
q->slot.bytes_left = q->slot_config.max_bytes;
if (q->slot_config.min_delay | q->slot_config.max_delay |
@@ -1037,6 +1041,9 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
if (tb[TCA_NETEM_SLOT])
get_slot(q, tb[TCA_NETEM_SLOT]);
+ /* capping jitter to the range acceptable by tabledist() */
+ q->jitter = min_t(s64, abs(q->jitter), INT_MAX);
+
return ret;
get_table_failure:
--
cgit v1.2.3-70-g09d2