Description
In the Linux kernel, the following vulnerability has been resolved:

net: consume xmit errors of GSO frames

udpgro_frglist.sh and udpgro_bench.sh are the flakiest tests
currently in NIPA. They fail in the same exact way, TCP GRO
test stalls occasionally and the test gets killed after 10min.

These tests use veth to simulate GRO. They attach a trivial
("return XDP_PASS;") XDP program to the veth to force TSO off
and NAPI on.

Digging into the failure mode we can see that the connection
is completely stuck after a burst of drops. The sender's snd_nxt
is at sequence number N [1], but the receiver claims to have
received (rcv_nxt) up to N + 3 * MSS [2]. Last piece of the puzzle
is that senders rtx queue is not empty (let's say the block in
the rtx queue is at sequence number N - 4 * MSS [3]).

In this state, sender sends a retransmission from the rtx queue
with a single segment, and sequence numbers N-4*MSS:N-3*MSS [3].
Receiver sees it and responds with an ACK all the way up to
N + 3 * MSS [2]. But sender will reject this ack as TCP_ACK_UNSENT_DATA
because it has no recollection of ever sending data that far out [1].
And we are stuck.

The root cause is the mess of the xmit return codes. veth returns
an error when it can't xmit a frame. We end up with a loss event
like this:

-------------------------------------------------
| GSO super frame 1 | GSO super frame 2 |
|-----------------------------------------------|
| seg | seg | seg | seg | seg | seg | seg | seg |
| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
-------------------------------------------------
x ok ok <ok>| ok ok ok <x>
\\
snd_nxt

"x" means packet lost by veth, and "ok" means it went thru.
Since veth has TSO disabled in this test it sees individual segments.
Segment 1 is on the retransmit queue and will be resent.

So why did the sender not advance snd_nxt even tho it clearly did
send up to seg 8? tcp_write_xmit() interprets the return code
from the core to mean that data has not been sent at all. Since
TCP deals with GSO super frames, not individual segment the crux
of the problem is that loss of a single segment can be interpreted
as loss of all. TCP only sees the last return code for the last
segment of the GSO frame (in <> brackets in the diagram above).

Of course for the problem to occur we need a setup or a device
without a Qdisc. Otherwise Qdisc layer disconnects the protocol
layer from the device errors completely.

We have multiple ways to fix this.

1) make veth not return an error when it lost a packet.
While this is what I think we did in the past, the issue keeps
reappearing and it's annoying to debug. The game of whack
a mole is not great.

2) fix the damn return codes
We only talk about NETDEV_TX_OK and NETDEV_TX_BUSY in the
documentation, so maybe we should make the return code from
ndo_start_xmit() a boolean. I like that the most, but perhaps
some ancient, not-really-networking protocol would suffer.

3) make TCP ignore the errors
It is not entirely clear to me what benefit TCP gets from
interpreting the result of ip_queue_xmit()? Specifically once
the connection is established and we're pushing data - packet
loss is just packet loss?

4) this fix
Ignore the rc in the Qdisc-less+GSO case, since it's unreliable.
We already always return OK in the TCQ_F_CAN_BYPASS case.
In the Qdisc-less case let's be a bit more conservative and only
mask the GSO errors. This path is taken by non-IP-"networks"
like CAN, MCTP etc, so we could regress some ancient thing.
This is the simplest, but also maybe the hackiest fix?

Similar fix has been proposed by Eric in the past but never committed
because original reporter was working with an OOT driver and wasn't
providing feedback (see Link).
Published: 2026-05-06
Score: 7.5 High
EPSS: < 1% Very Low
KEV: No
Impact: n/a
Action: n/a
AI Analysis

Impact

The Linux kernel misinterprets transmission return codes from virtual interfaces that do not use a queuing discipline when Generic Segmentation Offload (GSO) frames are transmitted. When a single segment of a GSO super frame fails, the kernel records the failure as if the entire frame failed, causing the TCP send buffer to remain stuck and the connection to never progress. This results in a denial of service and can effectively halt network traffic or a long‑running application using that connection. The faulty handling of return codes is a classic example of CWE-544 and is also annotated with NVD-CWE-noinfo.

Affected Systems

All recent Linux kernels that use the standard networking stack are affected, especially when traffic passes through veth or similar virtual devices that lack a qdisc. The issue does not have a version list in the advisory, so all builds until the patch are vulnerable. Systems employing container or virtual networking that defaults to no qdisc are most likely to experience the problem.

Risk and Exploitability

The CVSS score of 7.5 indicates high severity, and the vulnerability is not listed in CISA’s KEV catalog. The EPSS score of < 1% indicates a very low probability of exploitation. Based on the description, it is inferred that exploitation requires an attacker to generate traffic that triggers GSO on a qdisc‑less interface, which can be done from within the same host or from a remote machine if the interface is exposed. The design flaw is internal to the kernel, but an able adversary could force a persistent TCP stall on target links, causing denial of service to users or services depending on those connections.

Generated by OpenCVE AI on May 11, 2026 at 22:55 UTC.

Remediation

No vendor fix or workaround currently provided.

OpenCVE Recommended Actions

  • Upgrade the Linux kernel to a release that includes the patch for net: consume xmit errors of GSO frames.
  • Configure virtual network interfaces, such as veth, to use a queuing discipline (qdisc) or otherwise ensure that GSO is enabled only when a qdisc is present.
  • Disable GSO on the virtual interface or use a non‑qdisc‑based method to enforce packet delivery without reliance on GSO so that segment failures are handled correctly.

Generated by OpenCVE AI on May 11, 2026 at 22:55 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories yet.

History

Mon, 11 May 2026 20:15:00 +0000

Type Values Removed Values Added
Weaknesses NVD-CWE-noinfo
CPEs cpe:2.3:o:linux:linux_kernel:7.0:rc1:*:*:*:*:*:*

Fri, 08 May 2026 13:00:00 +0000

Type Values Removed Values Added
Metrics cvssV3_1

{'score': 5.5, 'vector': 'CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H'}

cvssV3_1

{'score': 7.5, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H'}


Thu, 07 May 2026 00:15:00 +0000

Type Values Removed Values Added
Weaknesses CWE-544
References
Metrics threat_severity

None

cvssV3_1

{'score': 5.5, 'vector': 'CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H'}

threat_severity

Low


Wed, 06 May 2026 12:15:00 +0000

Type Values Removed Values Added
Description In the Linux kernel, the following vulnerability has been resolved: net: consume xmit errors of GSO frames udpgro_frglist.sh and udpgro_bench.sh are the flakiest tests currently in NIPA. They fail in the same exact way, TCP GRO test stalls occasionally and the test gets killed after 10min. These tests use veth to simulate GRO. They attach a trivial ("return XDP_PASS;") XDP program to the veth to force TSO off and NAPI on. Digging into the failure mode we can see that the connection is completely stuck after a burst of drops. The sender's snd_nxt is at sequence number N [1], but the receiver claims to have received (rcv_nxt) up to N + 3 * MSS [2]. Last piece of the puzzle is that senders rtx queue is not empty (let's say the block in the rtx queue is at sequence number N - 4 * MSS [3]). In this state, sender sends a retransmission from the rtx queue with a single segment, and sequence numbers N-4*MSS:N-3*MSS [3]. Receiver sees it and responds with an ACK all the way up to N + 3 * MSS [2]. But sender will reject this ack as TCP_ACK_UNSENT_DATA because it has no recollection of ever sending data that far out [1]. And we are stuck. The root cause is the mess of the xmit return codes. veth returns an error when it can't xmit a frame. We end up with a loss event like this: ------------------------------------------------- | GSO super frame 1 | GSO super frame 2 | |-----------------------------------------------| | seg | seg | seg | seg | seg | seg | seg | seg | | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | ------------------------------------------------- x ok ok <ok>| ok ok ok <x> \\ snd_nxt "x" means packet lost by veth, and "ok" means it went thru. Since veth has TSO disabled in this test it sees individual segments. Segment 1 is on the retransmit queue and will be resent. So why did the sender not advance snd_nxt even tho it clearly did send up to seg 8? tcp_write_xmit() interprets the return code from the core to mean that data has not been sent at all. Since TCP deals with GSO super frames, not individual segment the crux of the problem is that loss of a single segment can be interpreted as loss of all. TCP only sees the last return code for the last segment of the GSO frame (in <> brackets in the diagram above). Of course for the problem to occur we need a setup or a device without a Qdisc. Otherwise Qdisc layer disconnects the protocol layer from the device errors completely. We have multiple ways to fix this. 1) make veth not return an error when it lost a packet. While this is what I think we did in the past, the issue keeps reappearing and it's annoying to debug. The game of whack a mole is not great. 2) fix the damn return codes We only talk about NETDEV_TX_OK and NETDEV_TX_BUSY in the documentation, so maybe we should make the return code from ndo_start_xmit() a boolean. I like that the most, but perhaps some ancient, not-really-networking protocol would suffer. 3) make TCP ignore the errors It is not entirely clear to me what benefit TCP gets from interpreting the result of ip_queue_xmit()? Specifically once the connection is established and we're pushing data - packet loss is just packet loss? 4) this fix Ignore the rc in the Qdisc-less+GSO case, since it's unreliable. We already always return OK in the TCQ_F_CAN_BYPASS case. In the Qdisc-less case let's be a bit more conservative and only mask the GSO errors. This path is taken by non-IP-"networks" like CAN, MCTP etc, so we could regress some ancient thing. This is the simplest, but also maybe the hackiest fix? Similar fix has been proposed by Eric in the past but never committed because original reporter was working with an OOT driver and wasn't providing feedback (see Link).
Title net: consume xmit errors of GSO frames
First Time appeared Linux
Linux linux Kernel
CPEs cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*
Vendors & Products Linux
Linux linux Kernel
References

Subscriptions

Linux Linux Kernel
cve-icon MITRE

Status: PUBLISHED

Assigner: Linux

Published:

Updated: 2026-05-11T22:19:39.800Z

Reserved: 2026-05-01T14:12:55.992Z

Link: CVE-2026-43194

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Analyzed

Published: 2026-05-06T12:16:38.310

Modified: 2026-05-11T20:11:10.707

Link: CVE-2026-43194

cve-icon Redhat

Severity : Low

Publid Date: 2026-05-06T00:00:00Z

Links: CVE-2026-43194 - Bugzilla

cve-icon OpenCVE Enrichment

Updated: 2026-05-11T23:00:19Z

Weaknesses