| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
skb_header_pointer() does not fully validate negative @offset values.
Use skb_header_pointer_careful() instead.
GangMin Kim provided a report and a repro fooling u32_classify():
BUG: KASAN: slab-out-of-bounds in u32_classify+0x1180/0x11b0
net/sched/cls_u32.c:221
Fixes: fbc2e7d9cf49 ("cls_u32: use skb_header_pointer() to dereference data safely")
Reported-by: GangMin Kim <km.kim1503@gmail.com>
Closes: https://lore.kernel.org/netdev/CANn89iJkyUZ=mAzLzC4GdcAgLuPnUoivdLaOs6B9rq5_erj76w@mail.gmail.com/T/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260128141539.3404400-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
tcf_ife_encode() must make sure ife_encode() does not return NULL.
syzbot reported:
Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
RIP: 0010:ife_tlv_meta_encode+0x41/0xa0 net/ife/ife.c:166
CPU: 3 UID: 0 PID: 8990 Comm: syz.0.696 Not tainted syzkaller #0 PREEMPT(full)
Call Trace:
<TASK>
ife_encode_meta_u32+0x153/0x180 net/sched/act_ife.c:101
tcf_ife_encode net/sched/act_ife.c:841 [inline]
tcf_ife_act+0x1022/0x1de0 net/sched/act_ife.c:877
tc_act include/net/tc_wrapper.h:130 [inline]
tcf_action_exec+0x1c0/0xa20 net/sched/act_api.c:1152
tcf_exts_exec include/net/pkt_cls.h:349 [inline]
mall_classify+0x1a0/0x2a0 net/sched/cls_matchall.c:42
tc_classify include/net/tc_wrapper.h:197 [inline]
__tcf_classify net/sched/cls_api.c:1764 [inline]
tcf_classify+0x7f2/0x1380 net/sched/cls_api.c:1860
multiq_classify net/sched/sch_multiq.c:39 [inline]
multiq_enqueue+0xe0/0x510 net/sched/sch_multiq.c:66
dev_qdisc_enqueue+0x45/0x250 net/core/dev.c:4147
__dev_xmit_skb net/core/dev.c:4262 [inline]
__dev_queue_xmit+0x2998/0x46c0 net/core/dev.c:4798
Fixes: 295a6e06d21e ("net/sched: act_ife: Change to use ife module")
Reported-by: syzbot+5cf914f193dffde3bd3c@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/6970d61d.050a0220.706b.0010.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yotam Gigi <yotam.gi@gmail.com>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260121133724.3400020-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
qfq_rm_from_ag
This is more of a preventive patch to make the code more consistent and
to prevent possible exploits that employ child qlen manipulations on qfq.
use cl_is_active instead of relying on the child qdisc's qlen to determine
class activation.
Fixes: 462dbc9101acd ("pkt_sched: QFQ Plus: fair-queueing service at DRR cost")
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260114160243.913069-3-jhs@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Design intent of teql is that it is only supposed to be used as root qdisc.
We need to check for that constraint.
Although not important, I will describe the scenario that unearthed this
issue for the curious.
GangMin Kim <km.kim1503@gmail.com> managed to concot a scenario as follows:
ROOT qdisc 1:0 (QFQ)
├── class 1:1 (weight=15, lmax=16384) netem with delay 6.4s
└── class 1:2 (weight=1, lmax=1514) teql
GangMin sends a packet which is enqueued to 1:1 (netem).
Any invocation of dequeue by QFQ from this class will not return a packet
until after 6.4s. In the meantime, a second packet is sent and it lands on
1:2. teql's enqueue will return success and this will activate class 1:2.
Main issue is that teql only updates the parent visible qlen (sch->q.qlen)
at dequeue. Since QFQ will only call dequeue if peek succeeds (and teql's
peek always returns NULL), dequeue will never be called and thus the qlen
will remain as 0. With that in mind, when GangMin updates 1:2's lmax value,
the qfq_change_class calls qfq_deact_rm_from_agg. Since the child qdisc's
qlen was not incremented, qfq fails to deactivate the class, but still
frees its pointers from the aggregate. So when the first packet is
rescheduled after 6.4 seconds (netem's delay), a dangling pointer is
accessed causing GangMin's causing a UAF.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: GangMin Kim <km.kim1503@gmail.com>
Tested-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260114160243.913069-2-jhs@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Fixes qfq_change_class() error case.
cl->qdisc and cl should only be freed if a new class and qdisc
were allocated, or we risk various UAF.
Fixes: 462dbc9101ac ("pkt_sched: QFQ Plus: fair-queueing service at DRR cost")
Reported-by: syzbot+07f3f38f723c335f106d@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/6965351d.050a0220.eaf7.00c5.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260112175656.17605-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
qfq_reset
`qfq_class->leaf_qdisc->q.qlen > 0` does not imply that the class
itself is active.
Two qfq_class objects may point to the same leaf_qdisc. This happens
when:
1. one QFQ qdisc is attached to the dev as the root qdisc, and
2. another QFQ qdisc is temporarily referenced (e.g., via qdisc_get()
/ qdisc_put()) and is pending to be destroyed, as in function
tc_new_tfilter.
When packets are enqueued through the root QFQ qdisc, the shared
leaf_qdisc->q.qlen increases. At the same time, the second QFQ
qdisc triggers qdisc_put and qdisc_destroy: the qdisc enters
qfq_reset() with its own q->q.qlen == 0, but its class's leaf
qdisc->q.qlen > 0. Therefore, the qfq_reset would wrongly deactivate
an inactive aggregate and trigger a null-deref in qfq_deactivate_agg:
[ 0.903172] BUG: kernel NULL pointer dereference, address: 0000000000000000
[ 0.903571] #PF: supervisor write access in kernel mode
[ 0.903860] #PF: error_code(0x0002) - not-present page
[ 0.904177] PGD 10299b067 P4D 10299b067 PUD 10299c067 PMD 0
[ 0.904502] Oops: Oops: 0002 [#1] SMP NOPTI
[ 0.904737] CPU: 0 UID: 0 PID: 135 Comm: exploit Not tainted 6.19.0-rc3+ #2 NONE
[ 0.905157] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014
[ 0.905754] RIP: 0010:qfq_deactivate_agg (include/linux/list.h:992 (discriminator 2) include/linux/list.h:1006 (discriminator 2) net/sched/sch_qfq.c:1367 (discriminator 2) net/sched/sch_qfq.c:1393 (discriminator 2))
[ 0.906046] Code: 0f 84 4d 01 00 00 48 89 70 18 8b 4b 10 48 c7 c2 ff ff ff ff 48 8b 78 08 48 d3 e2 48 21 f2 48 2b 13 48 8b 30 48 d3 ea 8b 4b 18 0
Code starting with the faulting instruction
===========================================
0: 0f 84 4d 01 00 00 je 0x153
6: 48 89 70 18 mov %rsi,0x18(%rax)
a: 8b 4b 10 mov 0x10(%rbx),%ecx
d: 48 c7 c2 ff ff ff ff mov $0xffffffffffffffff,%rdx
14: 48 8b 78 08 mov 0x8(%rax),%rdi
18: 48 d3 e2 shl %cl,%rdx
1b: 48 21 f2 and %rsi,%rdx
1e: 48 2b 13 sub (%rbx),%rdx
21: 48 8b 30 mov (%rax),%rsi
24: 48 d3 ea shr %cl,%rdx
27: 8b 4b 18 mov 0x18(%rbx),%ecx
...
[ 0.907095] RSP: 0018:ffffc900004a39a0 EFLAGS: 00010246
[ 0.907368] RAX: ffff8881043a0880 RBX: ffff888102953340 RCX: 0000000000000000
[ 0.907723] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[ 0.908100] RBP: ffff888102952180 R08: 0000000000000000 R09: 0000000000000000
[ 0.908451] R10: ffff8881043a0000 R11: 0000000000000000 R12: ffff888102952000
[ 0.908804] R13: ffff888102952180 R14: ffff8881043a0ad8 R15: ffff8881043a0880
[ 0.909179] FS: 000000002a1a0380(0000) GS:ffff888196d8d000(0000) knlGS:0000000000000000
[ 0.909572] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 0.909857] CR2: 0000000000000000 CR3: 0000000102993002 CR4: 0000000000772ef0
[ 0.910247] PKRU: 55555554
[ 0.910391] Call Trace:
[ 0.910527] <TASK>
[ 0.910638] qfq_reset_qdisc (net/sched/sch_qfq.c:357 net/sched/sch_qfq.c:1485)
[ 0.910826] qdisc_reset (include/linux/skbuff.h:2195 include/linux/skbuff.h:2501 include/linux/skbuff.h:3424 include/linux/skbuff.h:3430 net/sched/sch_generic.c:1036)
[ 0.911040] __qdisc_destroy (net/sched/sch_generic.c:1076)
[ 0.911236] tc_new_tfilter (net/sched/cls_api.c:2447)
[ 0.911447] rtnetlink_rcv_msg (net/core/rtnetlink.c:6958)
[ 0.911663] ? __pfx_rtnetlink_rcv_msg (net/core/rtnetlink.c:6861)
[ 0.911894] netlink_rcv_skb (net/netlink/af_netlink.c:2550)
[ 0.912100] netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344)
[ 0.912296] ? __alloc_skb (net/core/skbuff.c:706)
[ 0.912484] netlink_sendmsg (net/netlink/af_netlink.c:1894)
[ 0.912682] sock_write_iter (net/socket.c:727 (discriminator 1) net/socket.c:742 (discriminator 1) net/socket.c:1195 (discriminator 1))
[ 0.912880] vfs_write (fs/read_write.c:593 fs/read_write.c:686)
[ 0.913077] ksys_write (fs/read_write.c:738)
[ 0.913252] do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1))
[ 0.913438] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:131)
[ 0.913687] RIP: 0033:0x424c34
[ 0.913844] Code: 89 02 48 c7 c0 ff ff ff ff eb bd 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 80 3d 2d 44 09 00 00 74 13 b8 01 00 00 00 0f 05 9
Code starting with the faulting instruction
===========================================
0: 89 02 mov %eax,(%rdx)
2: 48 c7 c0 ff ff ff ff mov $0xffffffffffffffff,%rax
9: eb bd jmp 0xffffffffffffffc8
b: 66 2e 0f 1f 84 00 00 cs nopw 0x0(%rax,%rax,1)
12: 00 00 00
15: 90 nop
16: f3 0f 1e fa endbr64
1a: 80 3d 2d 44 09 00 00 cmpb $0x0,0x9442d(%rip) # 0x9444e
21: 74 13 je 0x36
23: b8 01 00 00 00 mov $0x1,%eax
28: 0f 05 syscall
2a: 09 .byte 0x9
[ 0.914807] RSP: 002b:00007ffea1938b78 EFLAGS: 00000202 ORIG_RAX: 0000000000000001
[ 0.915197] RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 0000000000424c34
[ 0.915556] RDX: 000000000000003c RSI: 000000002af378c0 RDI: 0000000000000003
[ 0.915912] RBP: 00007ffea1938bc0 R08: 00000000004b8820 R09: 0000000000000000
[ 0.916297] R10: 0000000000000001 R11: 0000000000000202 R12: 00007ffea1938d28
[ 0.916652] R13: 00007ffea1938d38 R14: 00000000004b3828 R15: 0000000000000001
[ 0.917039] </TASK>
[ 0.917158] Modules linked in:
[ 0.917316] CR2: 0000000000000000
[ 0.917484] ---[ end trace 0000000000000000 ]---
[ 0.917717] RIP: 0010:qfq_deactivate_agg (include/linux/list.h:992 (discriminator 2) include/linux/list.h:1006 (discriminator 2) net/sched/sch_qfq.c:1367 (discriminator 2) net/sched/sch_qfq.c:1393 (discriminator 2))
[ 0.917978] Code: 0f 84 4d 01 00 00 48 89 70 18 8b 4b 10 48 c7 c2 ff ff ff ff 48 8b 78 08 48 d3 e2 48 21 f2 48 2b 13 48 8b 30 48 d3 ea 8b 4b 18 0
Code starting with the faulting instruction
===========================================
0: 0f 84 4d 01 00 00 je 0x153
6: 48 89 70 18 mov %rsi,0x18(%rax)
a: 8b 4b 10 mov 0x10(%rbx),%ecx
d: 48 c7 c2 ff ff ff ff mov $0xffffffffffffffff,%rdx
14: 48 8b 78 08 mov 0x8(%rax),%rdi
18: 48 d3 e2 shl %cl,%rdx
1b: 48 21 f2 and %rsi,%rdx
1e: 48 2b 13 sub (%rbx),%rdx
21: 48 8b 30 mov (%rax),%rsi
24: 48 d3 ea shr %cl,%rdx
27: 8b 4b 18 mov 0x18(%rbx),%ecx
...
[ 0.918902] RSP: 0018:ffffc900004a39a0 EFLAGS: 00010246
[ 0.919198] RAX: ffff8881043a0880 RBX: ffff888102953340 RCX: 0000000000000000
[ 0.919559] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[ 0.919908] RBP: ffff888102952180 R08: 0000000000000000 R09: 0000000000000000
[ 0.920289] R10: ffff8881043a0000 R11: 0000000000000000 R12: ffff888102952000
[ 0.920648] R13: ffff888102952180 R14: ffff8881043a0ad8 R15: ffff8881043a0880
[ 0.921014] FS: 000000002a1a0380(0000) GS:ffff888196d8d000(0000) knlGS:0000000000000000
[ 0.921424] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 0.921710] CR2: 0000000000000000 CR3: 0000000102993002 CR4: 0000000000772ef0
[ 0.922097] PKRU: 55555554
[ 0.922240] Kernel panic - not syncing: Fatal exception
[ 0.922590] Kernel Offset: disabled
Fixes: 0545a3037773 ("pkt_sched: QFQ - quick fair queue scheduler")
Signed-off-by: Xiang Mei <xmei5@asu.edu>
Link: https://patch.msgid.link/20260106034100.1780779-1-xmei5@asu.edu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
syzbot reported a crash in tc_act_in_hw() during netns teardown where
tcf_idrinfo_destroy() passed an ERR_PTR(-EBUSY) value as a tc_action
pointer, leading to an invalid dereference.
Guard against ERR_PTR entries when iterating the action IDR so teardown
does not call tc_act_in_hw() on an error pointer.
Fixes: 84a7d6797e6a ("net/sched: acp_api: no longer acquire RTNL in tc_action_net_exit()")
Link: https://syzkaller.appspot.com/bug?extid=8f1c492ffa4644ff3826
Reported-by: syzbot+8f1c492ffa4644ff3826@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=8f1c492ffa4644ff3826
Signed-off-by: Shivani Gupta <shivani07g@gmail.com>
Link: https://patch.msgid.link/20260105005905.243423-1-shivani07g@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Whenever a mirred redirect to self on egress happens, mirred allocates a
new skb (skb_to_send). The loop to self check was done after that
allocation, but was not freeing the newly allocated skb, causing a leak.
Fix this by moving the if-statement to before the allocation of the new
skb.
The issue was found by running the accompanying tdc test in 2/2
with config kmemleak enabled.
After a few minutes the kmemleak thread ran and reported the leak coming from
mirred.
Fixes: 1d856251a009 ("net/sched: act_mirred: fix loop detection")
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260101135608.253079-2-jhs@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Fix a loop scenario of ethx:egress->ethx:egress
Example setup to reproduce:
tc qdisc add dev ethx root handle 1: drr
tc filter add dev ethx parent 1: protocol ip prio 1 matchall \
action mirred egress redirect dev ethx
Now ping out of ethx and you get a deadlock:
[ 116.892898][ T307] ============================================
[ 116.893182][ T307] WARNING: possible recursive locking detected
[ 116.893418][ T307] 6.18.0-rc6-01205-ge05021a829b8-dirty #204 Not tainted
[ 116.893682][ T307] --------------------------------------------
[ 116.893926][ T307] ping/307 is trying to acquire lock:
[ 116.894133][ T307] ffff88800c122908 (&sch->root_lock_key){+...}-{3:3}, at: __dev_queue_xmit+0x2210/0x3b50
[ 116.894517][ T307]
[ 116.894517][ T307] but task is already holding lock:
[ 116.894836][ T307] ffff88800c122908 (&sch->root_lock_key){+...}-{3:3}, at: __dev_queue_xmit+0x2210/0x3b50
[ 116.895252][ T307]
[ 116.895252][ T307] other info that might help us debug this:
[ 116.895608][ T307] Possible unsafe locking scenario:
[ 116.895608][ T307]
[ 116.895901][ T307] CPU0
[ 116.896057][ T307] ----
[ 116.896200][ T307] lock(&sch->root_lock_key);
[ 116.896392][ T307] lock(&sch->root_lock_key);
[ 116.896605][ T307]
[ 116.896605][ T307] *** DEADLOCK ***
[ 116.896605][ T307]
[ 116.896864][ T307] May be due to missing lock nesting notation
[ 116.896864][ T307]
[ 116.897123][ T307] 6 locks held by ping/307:
[ 116.897302][ T307] #0: ffff88800b4b0250 (sk_lock-AF_INET){+.+.}-{0:0}, at: raw_sendmsg+0xb20/0x2cf0
[ 116.897808][ T307] #1: ffffffff88c839c0 (rcu_read_lock){....}-{1:3}, at: ip_output+0xa9/0x600
[ 116.898138][ T307] #2: ffffffff88c839c0 (rcu_read_lock){....}-{1:3}, at: ip_finish_output2+0x2c6/0x1ee0
[ 116.898459][ T307] #3: ffffffff88c83960 (rcu_read_lock_bh){....}-{1:3}, at: __dev_queue_xmit+0x200/0x3b50
[ 116.898782][ T307] #4: ffff88800c122908 (&sch->root_lock_key){+...}-{3:3}, at: __dev_queue_xmit+0x2210/0x3b50
[ 116.899132][ T307] #5: ffffffff88c83960 (rcu_read_lock_bh){....}-{1:3}, at: __dev_queue_xmit+0x200/0x3b50
[ 116.899442][ T307]
[ 116.899442][ T307] stack backtrace:
[ 116.899667][ T307] CPU: 2 UID: 0 PID: 307 Comm: ping Not tainted 6.18.0-rc6-01205-ge05021a829b8-dirty #204 PREEMPT(voluntary)
[ 116.899672][ T307] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[ 116.899675][ T307] Call Trace:
[ 116.899678][ T307] <TASK>
[ 116.899680][ T307] dump_stack_lvl+0x6f/0xb0
[ 116.899688][ T307] print_deadlock_bug.cold+0xc0/0xdc
[ 116.899695][ T307] __lock_acquire+0x11f7/0x1be0
[ 116.899704][ T307] lock_acquire+0x162/0x300
[ 116.899707][ T307] ? __dev_queue_xmit+0x2210/0x3b50
[ 116.899713][ T307] ? srso_alias_return_thunk+0x5/0xfbef5
[ 116.899717][ T307] ? stack_trace_save+0x93/0xd0
[ 116.899723][ T307] _raw_spin_lock+0x30/0x40
[ 116.899728][ T307] ? __dev_queue_xmit+0x2210/0x3b50
[ 116.899731][ T307] __dev_queue_xmit+0x2210/0x3b50
Fixes: 178ca30889a1 ("Revert "net/sched: Fix mirred deadlock on device recursion"")
Tested-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20251210162255.1057663-1-jhs@mojatatu.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
Whenever a user issues an ets qdisc change command, transforming a
drr class into a strict one, the ets code isn't checking whether that
class was in the active list and removing it. This means that, if a
user changes a strict class (which was in the active list) back to a drr
one, that class will be added twice to the active list [1].
Doing so with the following commands:
tc qdisc add dev lo root handle 1: ets bands 2 strict 1
tc qdisc add dev lo parent 1:2 handle 20: \
tbf rate 8bit burst 100b latency 1s
tc filter add dev lo parent 1: basic classid 1:2
ping -c1 -W0.01 -s 56 127.0.0.1
tc qdisc change dev lo root handle 1: ets bands 2 strict 2
tc qdisc change dev lo root handle 1: ets bands 2 strict 1
ping -c1 -W0.01 -s 56 127.0.0.1
Will trigger the following splat with list debug turned on:
[ 59.279014][ T365] ------------[ cut here ]------------
[ 59.279452][ T365] list_add double add: new=ffff88801d60e350, prev=ffff88801d60e350, next=ffff88801d60e2c0.
[ 59.280153][ T365] WARNING: CPU: 3 PID: 365 at lib/list_debug.c:35 __list_add_valid_or_report+0x17f/0x220
[ 59.280860][ T365] Modules linked in:
[ 59.281165][ T365] CPU: 3 UID: 0 PID: 365 Comm: tc Not tainted 6.18.0-rc7-00105-g7e9f13163c13-dirty #239 PREEMPT(voluntary)
[ 59.281977][ T365] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[ 59.282391][ T365] RIP: 0010:__list_add_valid_or_report+0x17f/0x220
[ 59.282842][ T365] Code: 89 c6 e8 d4 b7 0d ff 90 0f 0b 90 90 31 c0 e9 31 ff ff ff 90 48 c7 c7 e0 a0 22 9f 48 89 f2 48 89 c1 4c 89 c6 e8 b2 b7 0d ff 90 <0f> 0b 90 90 31 c0 e9 0f ff ff ff 48 89 f7 48 89 44 24 10 4c 89 44
...
[ 59.288812][ T365] Call Trace:
[ 59.289056][ T365] <TASK>
[ 59.289224][ T365] ? srso_alias_return_thunk+0x5/0xfbef5
[ 59.289546][ T365] ets_qdisc_change+0xd2b/0x1e80
[ 59.289891][ T365] ? __lock_acquire+0x7e7/0x1be0
[ 59.290223][ T365] ? __pfx_ets_qdisc_change+0x10/0x10
[ 59.290546][ T365] ? srso_alias_return_thunk+0x5/0xfbef5
[ 59.290898][ T365] ? __mutex_trylock_common+0xda/0x240
[ 59.291228][ T365] ? __pfx___mutex_trylock_common+0x10/0x10
[ 59.291655][ T365] ? srso_alias_return_thunk+0x5/0xfbef5
[ 59.291993][ T365] ? srso_alias_return_thunk+0x5/0xfbef5
[ 59.292313][ T365] ? trace_contention_end+0xc8/0x110
[ 59.292656][ T365] ? srso_alias_return_thunk+0x5/0xfbef5
[ 59.293022][ T365] ? srso_alias_return_thunk+0x5/0xfbef5
[ 59.293351][ T365] tc_modify_qdisc+0x63a/0x1cf0
Fix this by always checking and removing an ets class from the active list
when changing it to strict.
[1] https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git/tree/net/sched/sch_ets.c?id=ce052b9402e461a9aded599f5b47e76bc727f7de#n663
Fixes: cd9b50adc6bb9 ("net/sched: ets: fix crash when flipping from 'strict' to 'quantum'")
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/20251208190125.1868423-1-victor@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
ets_qdisc_change
zdi-disclosures@trendmicro.com says:
The vulnerability is a race condition between `ets_qdisc_dequeue` and
`ets_qdisc_change`. It leads to UAF on `struct Qdisc` object.
Attacker requires the capability to create new user and network namespace
in order to trigger the bug.
See my additional commentary at the end of the analysis.
Analysis:
static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
...
// (1) this lock is preventing .change handler (`ets_qdisc_change`)
//to race with .dequeue handler (`ets_qdisc_dequeue`)
sch_tree_lock(sch);
for (i = nbands; i < oldbands; i++) {
if (i >= q->nstrict && q->classes[i].qdisc->q.qlen)
list_del_init(&q->classes[i].alist);
qdisc_purge_queue(q->classes[i].qdisc);
}
WRITE_ONCE(q->nbands, nbands);
for (i = nstrict; i < q->nstrict; i++) {
if (q->classes[i].qdisc->q.qlen) {
// (2) the class is added to the q->active
list_add_tail(&q->classes[i].alist, &q->active);
q->classes[i].deficit = quanta[i];
}
}
WRITE_ONCE(q->nstrict, nstrict);
memcpy(q->prio2band, priomap, sizeof(priomap));
for (i = 0; i < q->nbands; i++)
WRITE_ONCE(q->classes[i].quantum, quanta[i]);
for (i = oldbands; i < q->nbands; i++) {
q->classes[i].qdisc = queues[i];
if (q->classes[i].qdisc != &noop_qdisc)
qdisc_hash_add(q->classes[i].qdisc, true);
}
// (3) the qdisc is unlocked, now dequeue can be called in parallel
// to the rest of .change handler
sch_tree_unlock(sch);
ets_offload_change(sch);
for (i = q->nbands; i < oldbands; i++) {
// (4) we're reducing the refcount for our class's qdisc and
// freeing it
qdisc_put(q->classes[i].qdisc);
// (5) If we call .dequeue between (4) and (5), we will have
// a strong UAF and we can control RIP
q->classes[i].qdisc = NULL;
WRITE_ONCE(q->classes[i].quantum, 0);
q->classes[i].deficit = 0;
gnet_stats_basic_sync_init(&q->classes[i].bstats);
memset(&q->classes[i].qstats, 0, sizeof(q->classes[i].qstats));
}
return 0;
}
Comment:
This happens because some of the classes have their qdiscs assigned to
NULL, but remain in the active list. This commit fixes this issue by always
removing the class from the active list before deleting and freeing its
associated qdisc
Reproducer Steps
(trimmed version of what was sent by zdi-disclosures@trendmicro.com)
```
DEV="${DEV:-lo}"
ROOT_HANDLE="${ROOT_HANDLE:-1:}"
BAND2_HANDLE="${BAND2_HANDLE:-20:}" # child under 1:2
PING_BYTES="${PING_BYTES:-48}"
PING_COUNT="${PING_COUNT:-200000}"
PING_DST="${PING_DST:-127.0.0.1}"
SLOW_TBF_RATE="${SLOW_TBF_RATE:-8bit}"
SLOW_TBF_BURST="${SLOW_TBF_BURST:-100b}"
SLOW_TBF_LAT="${SLOW_TBF_LAT:-1s}"
cleanup() {
tc qdisc del dev "$DEV" root 2>/dev/null
}
trap cleanup EXIT
ip link set "$DEV" up
tc qdisc del dev "$DEV" root 2>/dev/null || true
tc qdisc add dev "$DEV" root handle "$ROOT_HANDLE" ets bands 2 strict 2
tc qdisc add dev "$DEV" parent 1:2 handle "$BAND2_HANDLE" \
tbf rate "$SLOW_TBF_RATE" burst "$SLOW_TBF_BURST" latency "$SLOW_TBF_LAT"
tc filter add dev "$DEV" parent 1: protocol all prio 1 u32 match u32 0 0 flowid 1:2
tc -s qdisc ls dev $DEV
ping -I "$DEV" -f -c "$PING_COUNT" -s "$PING_BYTES" -W 0.001 "$PING_DST" \
>/dev/null 2>&1 &
tc qdisc change dev "$DEV" root handle "$ROOT_HANDLE" ets bands 2 strict 0
tc qdisc change dev "$DEV" root handle "$ROOT_HANDLE" ets bands 2 strict 2
tc -s qdisc ls dev $DEV
tc qdisc del dev "$DEV" parent 1:2 || true
tc -s qdisc ls dev $DEV
tc qdisc change dev "$DEV" root handle "$ROOT_HANDLE" ets bands 1 strict 1
```
KASAN report
```
==================================================================
BUG: KASAN: slab-use-after-free in ets_qdisc_dequeue+0x1071/0x11b0 kernel/net/sched/sch_ets.c:481
Read of size 8 at addr ffff8880502fc018 by task ping/12308
>
CPU: 0 UID: 0 PID: 12308 Comm: ping Not tainted 6.18.0-rc4-dirty #1 PREEMPT(full)
Hardware name: QEMU Ubuntu 25.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
Call Trace:
<IRQ>
__dump_stack kernel/lib/dump_stack.c:94
dump_stack_lvl+0x100/0x190 kernel/lib/dump_stack.c:120
print_address_description kernel/mm/kasan/report.c:378
print_report+0x156/0x4c9 kernel/mm/kasan/report.c:482
kasan_report+0xdf/0x110 kernel/mm/kasan/report.c:595
ets_qdisc_dequeue+0x1071/0x11b0 kernel/net/sched/sch_ets.c:481
dequeue_skb kernel/net/sched/sch_generic.c:294
qdisc_restart kernel/net/sched/sch_generic.c:399
__qdisc_run+0x1c9/0x1b00 kernel/net/sched/sch_generic.c:417
__dev_xmit_skb kernel/net/core/dev.c:4221
__dev_queue_xmit+0x2848/0x4410 kernel/net/core/dev.c:4729
dev_queue_xmit kernel/./include/linux/netdevice.h:3365
[...]
Allocated by task 17115:
kasan_save_stack+0x30/0x50 kernel/mm/kasan/common.c:56
kasan_save_track+0x14/0x30 kernel/mm/kasan/common.c:77
poison_kmalloc_redzone kernel/mm/kasan/common.c:400
__kasan_kmalloc+0xaa/0xb0 kernel/mm/kasan/common.c:417
kasan_kmalloc kernel/./include/linux/kasan.h:262
__do_kmalloc_node kernel/mm/slub.c:5642
__kmalloc_node_noprof+0x34e/0x990 kernel/mm/slub.c:5648
kmalloc_node_noprof kernel/./include/linux/slab.h:987
qdisc_alloc+0xb8/0xc30 kernel/net/sched/sch_generic.c:950
qdisc_create_dflt+0x93/0x490 kernel/net/sched/sch_generic.c:1012
ets_class_graft+0x4fd/0x800 kernel/net/sched/sch_ets.c:261
qdisc_graft+0x3e4/0x1780 kernel/net/sched/sch_api.c:1196
[...]
Freed by task 9905:
kasan_save_stack+0x30/0x50 kernel/mm/kasan/common.c:56
kasan_save_track+0x14/0x30 kernel/mm/kasan/common.c:77
__kasan_save_free_info+0x3b/0x70 kernel/mm/kasan/generic.c:587
kasan_save_free_info kernel/mm/kasan/kasan.h:406
poison_slab_object kernel/mm/kasan/common.c:252
__kasan_slab_free+0x5f/0x80 kernel/mm/kasan/common.c:284
kasan_slab_free kernel/./include/linux/kasan.h:234
slab_free_hook kernel/mm/slub.c:2539
slab_free kernel/mm/slub.c:6630
kfree+0x144/0x700 kernel/mm/slub.c:6837
rcu_do_batch kernel/kernel/rcu/tree.c:2605
rcu_core+0x7c0/0x1500 kernel/kernel/rcu/tree.c:2861
handle_softirqs+0x1ea/0x8a0 kernel/kernel/softirq.c:622
__do_softirq kernel/kernel/softirq.c:656
[...]
Commentary:
1. Maher Azzouzi working with Trend Micro Zero Day Initiative was reported as
the person who found the issue. I requested to get a proper email to add to the
reported-by tag but got no response. For this reason i will credit the person
i exchanged emails with i.e zdi-disclosures@trendmicro.com
2. Neither i nor Victor who did a much more thorough testing was able to
reproduce a UAF with the PoC or other approaches we tried. We were both able to
reproduce a null ptr deref. After exchange with zdi-disclosures@trendmicro.com
they sent a small change to be made to the code to add an extra delay which
was able to simulate the UAF. i.e, this:
qdisc_put(q->classes[i].qdisc);
mdelay(90);
q->classes[i].qdisc = NULL;
I was informed by Thomas Gleixner(tglx@linutronix.de) that adding delays was
acceptable approach for demonstrating the bug, quote:
"Adding such delays is common exploit validation practice"
The equivalent delay could happen "by virt scheduling the vCPU out, SMIs,
NMIs, PREEMPT_RT enabled kernel"
3. I asked the OP to test and report back but got no response and after a
few days gave up and proceeded to submit this fix.
Fixes: de6d25924c2a ("net/sched: sch_ets: don't peek at classes beyond 'nbands'")
Reported-by: zdi-disclosures@trendmicro.com
Tested-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: Davide Caratti <dcaratti@redhat.com>
Link: https://patch.msgid.link/20251128151919.576920-1-jhs@mojatatu.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
Merge in late fixes in preparation for the net-next PR.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In cake_drop(), qdisc_tree_reduce_backlog() is used to update the qlen
and backlog of the qdisc hierarchy. Its caller, cake_enqueue(), assumes
that the parent qdisc will enqueue the current packet. However, this
assumption breaks when cake_enqueue() returns NET_XMIT_CN: the parent
qdisc stops enqueuing current packet, leaving the tree qlen/backlog
accounting inconsistent. This mismatch can lead to a NULL dereference
(e.g., when the parent Qdisc is qfq_qdisc).
This patch computes the qlen/backlog delta in a more robust way by
observing the difference before and after the series of cake_drop()
calls, and then compensates the qdisc tree accounting if cake_enqueue()
returns NET_XMIT_CN.
To ensure correct compensation when ACK thinning is enabled, a new
variable is introduced to keep qlen unchanged.
Fixes: 15de71d06a40 ("net/sched: Make cake_enqueue return NET_XMIT_CN when past buffer_limit")
Signed-off-by: Xiang Mei <xmei5@asu.edu>
Reviewed-by: Toke Høiland-Jørgensen <toke@toke.dk>
Link: https://patch.msgid.link/20251128001415.377823-1-xmei5@asu.edu
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
Conflicts:
net/xdp/xsk.c
0ebc27a4c67d ("xsk: avoid data corruption on cq descriptor number")
8da7bea7db69 ("xsk: add indirect call for xsk_destruct_skb")
30ed05adca4a ("xsk: use a smaller new lock for shared pool case")
https://lore.kernel.org/20251127105450.4a1665ec@canb.auug.org.au
https://lore.kernel.org/eb4eee14-7e24-4d1b-b312-e9ea738fefee@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can
Marc Kleine-Budde says:
====================
pull-request: can 2025-11-26
this is a pull request of 8 patches for net/main.
Seungjin Bae provides a patch for the kvaser_usb driver to fix a
potential infinite loop in the USB data stream command parser.
Thomas Mühlbacher's patch for the sja1000 driver IRQ handler's max
loop handling, that might lead to unhandled interrupts.
3 patches by me for the gs_usb driver fix handling of failed transmit
URBs and add checking of the actual length of received URBs before
accessing the data.
The next patch is by me and is a port of Thomas Mühlbacher's patch
(fix IRQ handler's max loop handling, that might lead to unhandled
interrupts.) to the sun4i_can driver.
Biju Das provides a patch for the rcar_canfd driver to fix the CAN-FD
mode setting.
The last patch is by Shaurya Rane for the em_canid filter to ensure
that the complete CAN frame is present in the linear data buffer
before accessing it.
* tag 'linux-can-fixes-for-6.18-20251126' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can:
net/sched: em_canid: fix uninit-value in em_canid_match
can: rcar_canfd: Fix CAN-FD mode as default
can: sun4i_can: sun4i_can_interrupt(): fix max irq loop handling
can: gs_usb: gs_usb_receive_bulk_callback(): check actual_length before accessing data
can: gs_usb: gs_usb_receive_bulk_callback(): check actual_length before accessing header
can: gs_usb: gs_usb_xmit_callback(): fix handling of failed transmitted URBs
can: sja1000: fix max irq loop handling
can: kvaser_usb: leaf: Fix potential infinite loop in command parsers
====================
Link: https://patch.msgid.link/20251126155713.217105-1-mkl@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Use pskb_may_pull() to ensure a complete CAN frame is present in the
linear data buffer before reading the CAN ID. A simple skb->len check
is insufficient because it only verifies the total data length but does
not guarantee the data is present in skb->data (it could be in
fragments).
pskb_may_pull() both validates the length and pulls fragmented data
into the linear buffer if necessary, making it safe to directly
access skb->data.
Reported-by: syzbot+5d8269a1e099279152bc@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=5d8269a1e099279152bc
Fixes: f057bbb6f9ed ("net: em_canid: Ematch rule to match CAN frames according to their identifiers")
Signed-off-by: Shaurya Rane <ssrane_b23@ee.vjti.ac.in>
Link: https://patch.msgid.link/20251126085718.50808-1-ssranevjti@gmail.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
|
|
cake, codel and fq_codel can drop many packets from dequeue().
Use qdisc_dequeue_drop() so that the freeing can happen
outside of the qdisc spinlock scope.
Add TCQ_F_DEQUEUE_DROPS to sch->flags.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251121083256.674562-15-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
prefetch the skb that we are likely to dequeue at the next dequeue().
Also call fq_dequeue_skb() a bit sooner in fq_dequeue().
This reduces the window between read of q.qlen and
changes of fields in the cache line that could be dirtied
by another cpu trying to queue a packet.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251121083256.674562-10-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
Group together changes to qdisc fields to reduce chances of false sharing
if another cpu attempts to acquire the qdisc spinlock.
qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
qdisc_bstats_update(sch, skb);
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251121083256.674562-9-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
Use new qdisc_pkt_segs() to avoid a cache line miss in cake_enqueue()
for non GSO packets.
cake_overhead() does not have to recompute it.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251121083256.674562-7-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
Avoid up to two cache line misses in qdisc dequeue() to fetch
skb_shinfo(skb)->gso_segs/gso_size while qdisc spinlock is held.
This gives a 5 % improvement in a TX intensive workload.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251121083256.674562-6-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
qdisc_pkt_len_init() is currently initalizing qdisc_skb_cb(skb)->pkt_len.
Add qdisc_skb_cb(skb)->pkt_segs initialization and rename this function
to qdisc_pkt_len_segs_init().
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251121083256.674562-4-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
Add a new u16 field, next to pkt_len : pkt_segs
This will cache shinfo->gso_segs to speed up qdisc deqeue().
Move slave_dev_queue_mapping at the end of qdisc_skb_cb,
and move three bits from tc_skb_cb :
- post_ct
- post_ct_snat
- post_ct_dnat
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251121083256.674562-2-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
syzbot reported that tcf_get_base_ptr() can be called while transport
header is not set [1].
Instead of returning a dangling pointer, return NULL.
Fix tcf_get_base_ptr() callers to handle this NULL value.
[1]
WARNING: CPU: 1 PID: 6019 at ./include/linux/skbuff.h:3071 skb_transport_header include/linux/skbuff.h:3071 [inline]
WARNING: CPU: 1 PID: 6019 at ./include/linux/skbuff.h:3071 tcf_get_base_ptr include/net/pkt_cls.h:539 [inline]
WARNING: CPU: 1 PID: 6019 at ./include/linux/skbuff.h:3071 em_nbyte_match+0x2d8/0x3f0 net/sched/em_nbyte.c:43
Modules linked in:
CPU: 1 UID: 0 PID: 6019 Comm: syz.0.17 Not tainted syzkaller #0 PREEMPT(full)
Call Trace:
<TASK>
tcf_em_match net/sched/ematch.c:494 [inline]
__tcf_em_tree_match+0x1ac/0x770 net/sched/ematch.c:520
tcf_em_tree_match include/net/pkt_cls.h:512 [inline]
basic_classify+0x115/0x2d0 net/sched/cls_basic.c:50
tc_classify include/net/tc_wrapper.h:197 [inline]
__tcf_classify net/sched/cls_api.c:1764 [inline]
tcf_classify+0x4cf/0x1140 net/sched/cls_api.c:1860
multiq_classify net/sched/sch_multiq.c:39 [inline]
multiq_enqueue+0xfd/0x4c0 net/sched/sch_multiq.c:66
dev_qdisc_enqueue+0x4e/0x260 net/core/dev.c:4118
__dev_xmit_skb net/core/dev.c:4214 [inline]
__dev_queue_xmit+0xe83/0x3b50 net/core/dev.c:4729
packet_snd net/packet/af_packet.c:3076 [inline]
packet_sendmsg+0x3e33/0x5080 net/packet/af_packet.c:3108
sock_sendmsg_nosec net/socket.c:727 [inline]
__sock_sendmsg+0x21c/0x270 net/socket.c:742
____sys_sendmsg+0x505/0x830 net/socket.c:2630
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+f3a497f02c389d86ef16@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/6920855a.a70a0220.2ea503.0058.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20251121154100.1616228-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Cross-merge networking fixes after downstream PR (net-6.18-rc7).
No conflicts, adjacent changes:
tools/testing/selftests/net/af_unix/Makefile
e1bb28bf13f4 ("selftest: af_unix: Add test for SO_PEEK_OFF.")
45a1cd8346ca ("selftests: af_unix: Add tests for ECONNRESET and EOF semantics")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Pull bpf fixes from Alexei Starovoitov:
- Fix interaction between livepatch and BPF fexit programs (Song Liu)
With Steven and Masami acks.
- Fix stack ORC unwind from BPF kprobe_multi (Jiri Olsa)
With Steven and Masami acks.
- Fix out of bounds access in widen_imprecise_scalars() in the verifier
(Eduard Zingerman)
- Fix conflicts between MPTCP and BPF sockmap (Jiayuan Chen)
- Fix net_sched storage collision with BPF data_meta/data_end (Eric
Dumazet)
- Add _impl suffix to BPF kfuncs with implicit args to avoid breaking
them in bpf-next when KF_IMPLICIT_ARGS is added (Mykyta Yatsenko)
* tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
selftests/bpf: Test widen_imprecise_scalars() with different stack depth
bpf: account for current allocated stack depth in widen_imprecise_scalars()
bpf: Add bpf_prog_run_data_pointers()
selftests/bpf: Add mptcp test with sockmap
mptcp: Fix proto fallback detection with BPF
mptcp: Disallow MPTCP subflows from sockmap
selftests/bpf: Add stacktrace ips test for raw_tp
selftests/bpf: Add stacktrace ips test for kprobe_multi/kretprobe_multi
x86/fgraph,bpf: Fix stack ORC unwind from kprobe_multi return probe
Revert "perf/x86: Always store regs->ip in perf_callchain_kernel()"
bpf: add _impl suffix for bpf_stream_vprintk() kfunc
bpf:add _impl suffix for bpf_task_work_schedule* kfuncs
selftests/bpf: Add tests for livepatch + bpf trampoline
ftrace: bpf: Fix IPMODIFY + DIRECT in modify_ftrace_direct()
ftrace: Fix BPF fexit with livepatch
|
|
syzbot found that cls_bpf_classify() is able to change
tc_skb_cb(skb)->drop_reason triggering a warning in sk_skb_reason_drop().
WARNING: CPU: 0 PID: 5965 at net/core/skbuff.c:1192 __sk_skb_reason_drop net/core/skbuff.c:1189 [inline]
WARNING: CPU: 0 PID: 5965 at net/core/skbuff.c:1192 sk_skb_reason_drop+0x76/0x170 net/core/skbuff.c:1214
struct tc_skb_cb has been added in commit ec624fe740b4 ("net/sched:
Extend qdisc control block with tc control block"), which added a wrong
interaction with db58ba459202 ("bpf: wire in data and data_end for
cls_act_bpf").
drop_reason was added later.
Add bpf_prog_run_data_pointers() helper to save/restore the net_sched
storage colliding with BPF data_meta/data_end.
Fixes: ec624fe740b4 ("net/sched: Extend qdisc control block with tc control block")
Reported-by: syzbot <syzkaller@googlegroups.com>
Closes: https://lore.kernel.org/netdev/6913437c.a70a0220.22f260.013b.GAE@google.com/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20251112125516.1563021-1-edumazet@google.com
|
|
Replace comma between expressions with semicolons.
Using a ',' in place of a ';' can have unintended side effects.
Although that is not the case here, it is seems best to use ';'
unless ',' is intended.
Found by inspection.
No functional change intended.
Compile tested only.
Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20251112072709.73755-1-nichen@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Cross-merge networking fixes after downstream PR (net-6.18-rc6).
No conflicts, adjacent changes in:
drivers/net/phy/micrel.c
96a9178a29a6 ("net: phy: micrel: lan8814 fix reset of the QSGMII interface")
61b7ade9ba8c ("net: phy: micrel: Add support for non PTP SKUs for lan8814")
and a trivial one in tools/testing/selftests/drivers/net/Makefile.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
After commit 100dfa74cad9 ("inet: dev_queue_xmit() llist adoption")
I started seeing many qdisc requeues on IDPF under high TX workload.
$ tc -s qd sh dev eth1 handle 1: ; sleep 1; tc -s qd sh dev eth1 handle 1:
qdisc mq 1: root
Sent 43534617319319 bytes 268186451819 pkt (dropped 0, overlimits 0 requeues 3532840114)
backlog 1056Kb 6675p requeues 3532840114
qdisc mq 1: root
Sent 43554665866695 bytes 268309964788 pkt (dropped 0, overlimits 0 requeues 3537737653)
backlog 781164b 4822p requeues 3537737653
This is caused by try_bulk_dequeue_skb() being only limited by BQL budget.
perf record -C120-239 -e qdisc:qdisc_dequeue sleep 1 ; perf script
...
netperf 75332 [146] 2711.138269: qdisc:qdisc_dequeue: dequeue ifindex=5 qdisc handle=0x80150000 parent=0x10013 txq_state=0x0 packets=1292 skbaddr=0xff378005a1e9f200
netperf 75332 [146] 2711.138953: qdisc:qdisc_dequeue: dequeue ifindex=5 qdisc handle=0x80150000 parent=0x10013 txq_state=0x0 packets=1213 skbaddr=0xff378004d607a500
netperf 75330 [144] 2711.139631: qdisc:qdisc_dequeue: dequeue ifindex=5 qdisc handle=0x80150000 parent=0x10013 txq_state=0x0 packets=1233 skbaddr=0xff3780046be20100
netperf 75333 [147] 2711.140356: qdisc:qdisc_dequeue: dequeue ifindex=5 qdisc handle=0x80150000 parent=0x10013 txq_state=0x0 packets=1093 skbaddr=0xff37800514845b00
netperf 75337 [151] 2711.141037: qdisc:qdisc_dequeue: dequeue ifindex=5 qdisc handle=0x80150000 parent=0x10013 txq_state=0x0 packets=1353 skbaddr=0xff37800460753300
netperf 75337 [151] 2711.141877: qdisc:qdisc_dequeue: dequeue ifindex=5 qdisc handle=0x80150000 parent=0x10013 txq_state=0x0 packets=1367 skbaddr=0xff378004e72c7b00
netperf 75330 [144] 2711.142643: qdisc:qdisc_dequeue: dequeue ifindex=5 qdisc handle=0x80150000 parent=0x10013 txq_state=0x0 packets=1202 skbaddr=0xff3780045bd60000
...
This is bad because :
1) Large batches hold one victim cpu for a very long time.
2) Driver often hit their own TX ring limit (all slots are used).
3) We call dev_requeue_skb()
4) Requeues are using a FIFO (q->gso_skb), breaking qdisc ability to
implement FQ or priority scheduling.
5) dequeue_skb() gets packets from q->gso_skb one skb at a time
with no xmit_more support. This is causing many spinlock games
between the qdisc and the device driver.
Requeues were supposed to be very rare, lets keep them this way.
Limit batch sizes to /proc/sys/net/core/dev_weight (default 64) as
__qdisc_run() was designed to use.
Fixes: 5772e9a3463b ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://patch.msgid.link/20251109161215.2574081-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Fix a KMSAN kernel-infoleak detected by the syzbot .
[net?] KMSAN: kernel-infoleak in __skb_datagram_iter
In tcf_ife_dump(), the variable 'opt' was partially initialized using a
designatied initializer. While the padding bytes are reamined
uninitialized. nla_put() copies the entire structure into a
netlink message, these uninitialized bytes leaked to userspace.
Initialize the structure with memset before assigning its fields
to ensure all members and padding are cleared prior to beign copied.
This change silences the KMSAN report and prevents potential information
leaks from the kernel memory.
This fix has been tested and validated by syzbot. This patch closes the
bug reported at the following syzkaller link and ensures no infoleak.
Reported-by: syzbot+0c85cae3350b7d486aee@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=0c85cae3350b7d486aee
Tested-by: syzbot+0c85cae3350b7d486aee@syzkaller.appspotmail.com
Fixes: ef6980b6becb ("introduce IFE action")
Signed-off-by: Ranganath V N <vnranganath.20@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251109091336.9277-3-vnranganath.20@gmail.com
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
In tcf_connmark_dump(), the variable 'opt' was partially initialized using a
designatied initializer. While the padding bytes are reamined
uninitialized. nla_put() copies the entire structure into a
netlink message, these uninitialized bytes leaked to userspace.
Initialize the structure with memset before assigning its fields
to ensure all members and padding are cleared prior to beign copied.
Reported-by: syzbot+0c85cae3350b7d486aee@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=0c85cae3350b7d486aee
Tested-by: syzbot+0c85cae3350b7d486aee@syzkaller.appspotmail.com
Fixes: 22a5dc0e5e3e ("net: sched: Introduce connmark action")
Signed-off-by: Ranganath V N <vnranganath.20@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251109091336.9277-2-vnranganath.20@gmail.com
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
Wang reported an illegal configuration [1] where the user attempts to add a
child qdisc to the ingress qdisc as follows:
tc qdisc add dev eth0 handle ffff:0 ingress
tc qdisc add dev eth0 handle ffe0:0 parent ffff:a fq
To solve this, we reject any configuration attempt to add a child qdisc to
ingress or clsact.
[1] https://lore.kernel.org/netdev/20251105022213.1981982-1-wangliang74@huawei.com/
Fixes: 5e50da01d0ce ("[NET_SCHED]: Fix endless loops (part 2): "simple" qdiscs")
Reported-by: Wang Liang <wangliang74@huawei.com>
Closes: https://lore.kernel.org/netdev/20251105022213.1981982-1-wangliang74@huawei.com/
Reviewed-by: Pedro Tammela <pctammela@mojatatu.ai>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Reviewed-by: Cong Wang <cwang@multikernel.io>
Link: https://patch.msgid.link/20251106205621.3307639-1-victor@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
As demonstrated by syzbot, WARN_ON_ONCE() in tcf_classify() can
be easily triggered by fault injection. [0]
We should not use WARN_ON_ONCE() for the simple -ENOMEM case.
Also, we provide SKB_DROP_REASON_NOMEM for the same error.
Let's remove WARN_ON_ONCE() there.
[0]:
FAULT_INJECTION: forcing a failure.
name failslab, interval 1, probability 0, space 0, times 0
CPU: 0 UID: 0 PID: 31392 Comm: syz.8.7081 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/02/2025
Call Trace:
<TASK>
dump_stack_lvl+0x189/0x250
should_fail_ex+0x414/0x560
should_failslab+0xa8/0x100
kmem_cache_alloc_noprof+0x74/0x6e0
skb_ext_add+0x148/0x8f0
tcf_classify+0xeba/0x1140
multiq_enqueue+0xfd/0x4c0 net/sched/sch_multiq.c:66
...
WARNING: CPU: 0 PID: 31392 at net/sched/cls_api.c:1869 tcf_classify+0xfd7/0x1140
Modules linked in:
CPU: 0 UID: 0 PID: 31392 Comm: syz.8.7081 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/02/2025
RIP: 0010:tcf_classify+0xfd7/0x1140
Code: e8 03 42 0f b6 04 30 84 c0 0f 85 41 01 00 00 66 41 89 1f eb 05 e8 89 26 75 f8 bb ff ff ff ff e9 04 f9 ff ff e8 7a 26 75 f8 90 <0f> 0b 90 49 83 c5 44 4c 89 eb 49 c1 ed 03 43 0f b6 44 35 00 84 c0
RSP: 0018:ffffc9000b7671f0 EFLAGS: 00010293
RAX: ffffffff894addf6 RBX: 0000000000000002 RCX: ffff888025029e40
RDX: 0000000000000000 RSI: ffffffff8bbf05c0 RDI: ffffffff8bbf0580
RBP: 0000000000000000 R08: 00000000ffffffff R09: 1ffffffff1c0bfd6
R10: dffffc0000000000 R11: fffffbfff1c0bfd7 R12: ffff88805a90de5c
R13: ffff88805a90ddc0 R14: dffffc0000000000 R15: ffffc9000b7672c0
FS: 00007f20739f66c0(0000) GS:ffff88812613e000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000110c2d2a80 CR3: 0000000024e36000 CR4: 00000000003526f0
Call Trace:
<TASK>
multiq_classify net/sched/sch_multiq.c:39 [inline]
multiq_enqueue+0xfd/0x4c0 net/sched/sch_multiq.c:66
dev_qdisc_enqueue+0x4e/0x260 net/core/dev.c:4118
__dev_xmit_skb net/core/dev.c:4214 [inline]
__dev_queue_xmit+0xe83/0x3b50 net/core/dev.c:4729
packet_snd net/packet/af_packet.c:3076 [inline]
packet_sendmsg+0x3e33/0x5080 net/packet/af_packet.c:3108
sock_sendmsg_nosec net/socket.c:727 [inline]
__sock_sendmsg+0x21c/0x270 net/socket.c:742
____sys_sendmsg+0x505/0x830 net/socket.c:2630
___sys_sendmsg+0x21f/0x2a0 net/socket.c:2684
__sys_sendmsg net/socket.c:2716 [inline]
__do_sys_sendmsg net/socket.c:2721 [inline]
__se_sys_sendmsg net/socket.c:2719 [inline]
__x64_sys_sendmsg+0x19b/0x260 net/socket.c:2719
do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
do_syscall_64+0xfa/0xfa0 arch/x86/entry/syscall_64.c:94
entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f207578efc9
Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f20739f6038 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007f20759e5fa0 RCX: 00007f207578efc9
RDX: 0000000000000004 RSI: 00002000000000c0 RDI: 0000000000000008
RBP: 00007f20739f6090 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000001
R13: 00007f20759e6038 R14: 00007f20759e5fa0 R15: 00007f2075b0fa28
</TASK>
Reported-by: syzbot+87e1289a044fcd0c5f62@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/69003e33.050a0220.32483.00e8.GAE@google.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20251028035859.2067690-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Remove busylock spinlock and use a lockless list (llist)
to reduce spinlock contention to the minimum.
Idea is that only one cpu might spin on the qdisc spinlock,
while others simply add their skb in the llist.
After this patch, we get a 300 % improvement on heavy TX workloads.
- Sending twice the number of packets per second.
- While consuming 50 % less cycles.
Note that this also allows in the future to submit batches
to various qdisc->enqueue() methods.
Tested:
- Dual Intel(R) Xeon(R) 6985P-C (480 hyper threads).
- 100Gbit NIC, 30 TX queues with FQ packet scheduler.
- echo 64 >/sys/kernel/slab/skbuff_small_head/cpu_partial (avoid contention in mm)
- 240 concurrent "netperf -t UDP_STREAM -- -m 120 -n"
Before:
16 Mpps (41 Mpps if each thread is pinned to a different cpu)
vmstat 2 5
procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu-----
r b swpd free buff cache si so bi bo in cs us sy id wa st
243 0 0 2368988672 51036 1100852 0 0 146 1 242 60 0 9 91 0 0
244 0 0 2368988672 51036 1100852 0 0 536 10 487745 14718 0 52 48 0 0
244 0 0 2368988672 51036 1100852 0 0 512 0 503067 46033 0 52 48 0 0
244 0 0 2368988672 51036 1100852 0 0 512 0 494807 12107 0 52 48 0 0
244 0 0 2368988672 51036 1100852 0 0 702 26 492845 10110 0 52 48 0 0
Lock contention (1 second sample taken on 8 cores)
perf lock record -C0-7 sleep 1; perf lock contention
contended total wait max wait avg wait type caller
442111 6.79 s 162.47 ms 15.35 us spinlock dev_hard_start_xmit+0xcd
5961 9.57 ms 8.12 us 1.60 us spinlock __dev_queue_xmit+0x3a0
244 560.63 us 7.63 us 2.30 us spinlock do_softirq+0x5b
13 25.09 us 3.21 us 1.93 us spinlock net_tx_action+0xf8
If netperf threads are pinned, spinlock stress is very high.
perf lock record -C0-7 sleep 1; perf lock contention
contended total wait max wait avg wait type caller
964508 7.10 s 147.25 ms 7.36 us spinlock dev_hard_start_xmit+0xcd
201 268.05 us 4.65 us 1.33 us spinlock __dev_queue_xmit+0x3a0
12 26.05 us 3.84 us 2.17 us spinlock do_softirq+0x5b
@__dev_queue_xmit_ns:
[256, 512) 21 | |
[512, 1K) 631 | |
[1K, 2K) 27328 |@ |
[2K, 4K) 265392 |@@@@@@@@@@@@@@@@ |
[4K, 8K) 417543 |@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[8K, 16K) 826292 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[16K, 32K) 733822 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[32K, 64K) 19055 |@ |
[64K, 128K) 17240 |@ |
[128K, 256K) 25633 |@ |
[256K, 512K) 4 | |
After:
29 Mpps (57 Mpps if each thread is pinned to a different cpu)
vmstat 2 5
procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu-----
r b swpd free buff cache si so bi bo in cs us sy id wa st
78 0 0 2369573632 32896 1350988 0 0 22 0 331 254 0 8 92 0 0
75 0 0 2369573632 32896 1350988 0 0 22 50 425713 280199 0 23 76 0 0
104 0 0 2369573632 32896 1350988 0 0 290 0 430238 298247 0 23 76 0 0
86 0 0 2369573632 32896 1350988 0 0 132 0 428019 291865 0 24 76 0 0
90 0 0 2369573632 32896 1350988 0 0 502 0 422498 278672 0 23 76 0 0
perf lock record -C0-7 sleep 1; perf lock contention
contended total wait max wait avg wait type caller
2524 116.15 ms 486.61 us 46.02 us spinlock __dev_queue_xmit+0x55b
5821 107.18 ms 371.67 us 18.41 us spinlock dev_hard_start_xmit+0xcd
2377 9.73 ms 35.86 us 4.09 us spinlock ___slab_alloc+0x4e0
923 5.74 ms 20.91 us 6.22 us spinlock ___slab_alloc+0x5c9
121 3.42 ms 193.05 us 28.24 us spinlock net_tx_action+0xf8
6 564.33 us 167.60 us 94.05 us spinlock do_softirq+0x5b
If netperf threads are pinned (~54 Mpps)
perf lock record -C0-7 sleep 1; perf lock contention
32907 316.98 ms 195.98 us 9.63 us spinlock dev_hard_start_xmit+0xcd
4507 61.83 ms 212.73 us 13.72 us spinlock __dev_queue_xmit+0x554
2781 23.53 ms 40.03 us 8.46 us spinlock ___slab_alloc+0x5c9
3554 18.94 ms 34.69 us 5.33 us spinlock ___slab_alloc+0x4e0
233 9.09 ms 215.70 us 38.99 us spinlock do_softirq+0x5b
153 930.66 us 48.67 us 6.08 us spinlock net_tx_action+0xfd
84 331.10 us 14.22 us 3.94 us spinlock ___slab_alloc+0x5c9
140 323.71 us 9.94 us 2.31 us spinlock ___slab_alloc+0x4e0
@__dev_queue_xmit_ns:
[128, 256) 1539830 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[256, 512) 2299558 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[512, 1K) 483936 |@@@@@@@@@@ |
[1K, 2K) 265345 |@@@@@@ |
[2K, 4K) 145463 |@@@ |
[4K, 8K) 54571 |@ |
[8K, 16K) 10270 | |
[16K, 32K) 9385 | |
[32K, 64K) 7749 | |
[64K, 128K) 26799 | |
[128K, 256K) 2665 | |
[256K, 512K) 665 | |
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Tested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20251014171907.3554413-7-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
This reverts commits 0f022d32c3eca477fbf79a205243a6123ed0fe11
and 44180feaccf266d9b0b28cc4ceaac019817deb5c.
Prior patch in this series implemented loop detection
in act_mirred, we can remove q->owner to save some cycles
in the fast path.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Tested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20251014171907.3554413-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Commit 0f022d32c3ec ("net/sched: Fix mirred deadlock on device recursion")
added code in the fast path, even when act_mirred is not used.
Prepare its revert by implementing loop detection in act_mirred.
Adds an array of device pointers in struct netdev_xmit.
tcf_mirred_is_act_redirect() can detect if the array
already contains the target device.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Tested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20251014171907.3554413-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
tcfa_qstats is currently only used to hold drops and overlimits counters.
tcf_action_inc_drop_qstats() and tcf_action_inc_overlimit_qstats()
currently acquire a->tcfa_lock to increment these counters.
Switch to two atomic_t to get lock-free accounting.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20250901093141.2093176-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Jamal reported that we had to use BH safety after all,
because stats can be updated from BH handler.
Fixes: 3133d5c15cb5 ("net_sched: remove BH blocking in eight actions")
Fixes: 53df77e78590 ("net_sched: act_skbmod: use RCU in tcf_skbmod_dump()")
Fixes: e97ae742972f ("net_sched: act_tunnel_key: use RCU in tunnel_key_dump()")
Fixes: 48b5e5dbdb23 ("net_sched: act_vlan: use RCU in tcf_vlan_dump()")
Reported-by: Jamal Hadi Salim <jhs@mojatatu.com>
Closes: https://lore.kernel.org/netdev/CAM0EoMmhq66EtVqDEuNik8MVFZqkgxFbMu=fJtbNoYD7YXg4bA@mail.gmail.com/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20250901092608.2032473-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Also storing tcf_action into struct tcf_skbmod_params
makes sure there is no discrepancy in tcf_skbmod_act().
No longer block BH in tcf_skbmod_init() when acquiring tcf_lock.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250827125349.3505302-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Also storing tcf_action into struct tcf_tunnel_key_params
makes sure there is no discrepancy in tunnel_key_act().
No longer block BH in tunnel_key_init() when acquiring tcf_lock.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250827125349.3505302-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Also storing tcf_action into struct tcf_vlan_params
makes sure there is no discrepancy in tcf_vlan_act().
No longer block BH in tcf_vlan_init() when acquiring tcf_lock.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250827125349.3505302-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Followup of f45b45cbfae3 ("Merge branch
'net_sched-act-extend-rcu-use-in-dump-methods'")
We never grab tcf_lock from BH context in these modules:
act_connmark
act_csum
act_ct
act_ctinfo
act_mpls
act_nat
act_pedit
act_skbedit
No longer block BH when acquiring tcf_lock from init functions.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250827125349.3505302-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Cross-merge networking fixes after downstream PR (net-6.17-rc3).
No conflicts or adjacent changes.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
htb_activate
The WARN_ON trigger based on !cl->leaf.q->q.qlen is unnecessary in
htb_activate. htb_dequeue_tree already accounts for that scenario.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: William Liu <will@willsroot.io>
Reviewed-by: Savino Dicanosa <savy@syst3mfailure.io>
Link: https://patch.msgid.link/20250819033632.579854-1-will@willsroot.io
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The following setup can trigger a WARNING in htb_activate due to
the condition: !cl->leaf.q->q.qlen
tc qdisc del dev lo root
tc qdisc add dev lo root handle 1: htb default 1
tc class add dev lo parent 1: classid 1:1 \
htb rate 64bit
tc qdisc add dev lo parent 1:1 handle f: \
cake memlimit 1b
ping -I lo -f -c1 -s64 -W0.001 127.0.0.1
This is because the low memlimit leads to a low buffer_limit, which
causes packet dropping. However, cake_enqueue still returns
NET_XMIT_SUCCESS, causing htb_enqueue to call htb_activate with an
empty child qdisc. We should return NET_XMIT_CN when packets are
dropped from the same tin and flow.
I do not believe return value of NET_XMIT_CN is necessary for packet
drops in the case of ack filtering, as that is meant to optimize
performance, not to signal congestion.
Fixes: 046f6fd5daef ("sched: Add Common Applications Kept Enhanced (cake) qdisc")
Signed-off-by: William Liu <will@willsroot.io>
Reviewed-by: Savino Dicanosa <savy@syst3mfailure.io>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20250819033601.579821-1-will@willsroot.io
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
When a user creates a dualpi2 qdisc it automatically sets a timer. This
timer will run constantly and update the qdisc's probability field.
The issue is that the timer acquires the qdisc root lock and runs in
hardirq. The qdisc root lock is also acquired in dev.c whenever a packet
arrives for this qdisc. Since the dualpi2 timer callback runs in hardirq,
it may interrupt the packet processing running in softirq. If that happens
and it runs on the same CPU, it will acquire the same lock and cause a
deadlock. The following splat shows up when running a kernel compiled with
lock debugging:
[ +0.000224] WARNING: inconsistent lock state
[ +0.000224] 6.16.0+ #10 Not tainted
[ +0.000169] --------------------------------
[ +0.000029] inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage.
[ +0.000000] ping/156 [HC0[0]:SC0[2]:HE1:SE0] takes:
[ +0.000000] ffff897841242110 (&sch->root_lock_key){?.-.}-{3:3}, at: __dev_queue_xmit+0x86d/0x1140
[ +0.000000] {IN-HARDIRQ-W} state was registered at:
[ +0.000000] lock_acquire.part.0+0xb6/0x220
[ +0.000000] _raw_spin_lock+0x31/0x80
[ +0.000000] dualpi2_timer+0x6f/0x270
[ +0.000000] __hrtimer_run_queues+0x1c5/0x360
[ +0.000000] hrtimer_interrupt+0x115/0x260
[ +0.000000] __sysvec_apic_timer_interrupt+0x6d/0x1a0
[ +0.000000] sysvec_apic_timer_interrupt+0x6e/0x80
[ +0.000000] asm_sysvec_apic_timer_interrupt+0x1a/0x20
[ +0.000000] pv_native_safe_halt+0xf/0x20
[ +0.000000] default_idle+0x9/0x10
[ +0.000000] default_idle_call+0x7e/0x1e0
[ +0.000000] do_idle+0x1e8/0x250
[ +0.000000] cpu_startup_entry+0x29/0x30
[ +0.000000] rest_init+0x151/0x160
[ +0.000000] start_kernel+0x6f3/0x700
[ +0.000000] x86_64_start_reservations+0x24/0x30
[ +0.000000] x86_64_start_kernel+0xc8/0xd0
[ +0.000000] common_startup_64+0x13e/0x148
[ +0.000000] irq event stamp: 6884
[ +0.000000] hardirqs last enabled at (6883): [<ffffffffa75700b3>] neigh_resolve_output+0x223/0x270
[ +0.000000] hardirqs last disabled at (6882): [<ffffffffa7570078>] neigh_resolve_output+0x1e8/0x270
[ +0.000000] softirqs last enabled at (6880): [<ffffffffa757006b>] neigh_resolve_output+0x1db/0x270
[ +0.000000] softirqs last disabled at (6884): [<ffffffffa755b533>] __dev_queue_xmit+0x73/0x1140
[ +0.000000]
other info that might help us debug this:
[ +0.000000] Possible unsafe locking scenario:
[ +0.000000] CPU0
[ +0.000000] ----
[ +0.000000] lock(&sch->root_lock_key);
[ +0.000000] <Interrupt>
[ +0.000000] lock(&sch->root_lock_key);
[ +0.000000]
*** DEADLOCK ***
[ +0.000000] 4 locks held by ping/156:
[ +0.000000] #0: ffff897842332e08 (sk_lock-AF_INET){+.+.}-{0:0}, at: raw_sendmsg+0x41e/0xf40
[ +0.000000] #1: ffffffffa816f880 (rcu_read_lock){....}-{1:3}, at: ip_output+0x2c/0x190
[ +0.000000] #2: ffffffffa816f880 (rcu_read_lock){....}-{1:3}, at: ip_finish_output2+0xad/0x950
[ +0.000000] #3: ffffffffa816f840 (rcu_read_lock_bh){....}-{1:3}, at: __dev_queue_xmit+0x73/0x1140
I am able to reproduce it consistently when running the following:
tc qdisc add dev lo handle 1: root dualpi2
ping -f 127.0.0.1
To fix it, make the timer run in softirq.
Fixes: 320d031ad6e4 ("sched: Struct definition and parsing of dualpi2 qdisc")
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Link: https://patch.msgid.link/20250815135317.664993-1-victor@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
This issue applies for the following qdiscs: hhf, fq, fq_codel, and
fq_pie, and occurs in their change handlers when adjusting to the new
limit. The problem is the following in the values passed to the
subsequent qdisc_tree_reduce_backlog call given a tbf parent:
When the tbf parent runs out of tokens, skbs of these qdiscs will
be placed in gso_skb. Their peek handlers are qdisc_peek_dequeued,
which accounts for both qlen and backlog. However, in the case of
qdisc_dequeue_internal, ONLY qlen is accounted for when pulling
from gso_skb. This means that these qdiscs are missing a
qdisc_qstats_backlog_dec when dropping packets to satisfy the
new limit in their change handlers.
One can observe this issue with the following (with tc patched to
support a limit of 0):
export TARGET=fq
tc qdisc del dev lo root
tc qdisc add dev lo root handle 1: tbf rate 8bit burst 100b latency 1ms
tc qdisc replace dev lo handle 3: parent 1:1 $TARGET limit 1000
echo ''; echo 'add child'; tc -s -d qdisc show dev lo
ping -I lo -f -c2 -s32 -W0.001 127.0.0.1 2>&1 >/dev/null
echo ''; echo 'after ping'; tc -s -d qdisc show dev lo
tc qdisc change dev lo handle 3: parent 1:1 $TARGET limit 0
echo ''; echo 'after limit drop'; tc -s -d qdisc show dev lo
tc qdisc replace dev lo handle 2: parent 1:1 sfq
echo ''; echo 'post graft'; tc -s -d qdisc show dev lo
The second to last show command shows 0 packets but a positive
number (74) of backlog bytes. The problem becomes clearer in the
last show command, where qdisc_purge_queue triggers
qdisc_tree_reduce_backlog with the positive backlog and causes an
underflow in the tbf parent's backlog (4096 Mb instead of 0).
To fix this issue, the codepath for all clients of qdisc_dequeue_internal
has been simplified: codel, pie, hhf, fq, fq_pie, and fq_codel.
qdisc_dequeue_internal handles the backlog adjustments for all cases that
do not directly use the dequeue handler.
The old fq_codel_change limit adjustment loop accumulated the arguments to
the subsequent qdisc_tree_reduce_backlog call through the cstats field.
However, this is confusing and error prone as fq_codel_dequeue could also
potentially mutate this field (which qdisc_dequeue_internal calls in the
non gso_skb case), so we have unified the code here with other qdiscs.
Fixes: 2d3cbfd6d54a ("net_sched: Flush gso_skb list too during ->change()")
Fixes: 4b549a2ef4be ("fq_codel: Fair Queue Codel AQM")
Fixes: 10239edf86f1 ("net-qdisc-hhf: Heavy-Hitter Filter (HHF) qdisc")
Signed-off-by: William Liu <will@willsroot.io>
Reviewed-by: Savino Dicanosa <savy@syst3mfailure.io>
Link: https://patch.msgid.link/20250812235725.45243-1-will@willsroot.io
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Replace magic number with TC_RTAB_SIZE to make it more informative.
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Link: https://patch.msgid.link/20250813125526.853895-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Cross-merge networking fixes after downstream PR (net-6.17-rc2).
No conflicts.
Adjacent changes:
drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
d7a276a5768f ("net: stmmac: rk: convert to suspend()/resume() methods")
de1e963ad064 ("net: stmmac: rk: put the PHY clock on remove")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
