CVE-2023-52474 json
IB/hfi1: Fix bugs with non-PAGE_SIZE-end multi-iovec user SDMA requests
published 2024-02-26 2 y ago modified 2026-08-05 3 mo ago also EUVD-2023-57099
- cvss
- 7.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.3%
- EPSS 0.3% chance of exploitation in 30 days, percentile 16%
- public exploits
- 0
- none known
Summary
In the Linux kernel, the following vulnerability has been resolved:
IB/hfi1: Fix bugs with non-PAGE_SIZE-end multi-iovec user SDMA requests
hfi1 user SDMA request processing has two bugs that can cause data corruption for user SDMA requests that have multiple payload iovecs where an iovec other than the tail iovec does not run up to the page boundary for the buffer pointed to by that iovec.a
Here are the specific bugs: 1. user_sdma_txadd() does not use struct user_sdma_iovec->iov.iov_len. Rather, user_sdma_txadd() will add up to PAGE_SIZE bytes from iovec to the packet, even if some of those bytes are past iovec->iov.iov_len and are thus not intended to be in the packet. 2. user_sdma_txadd() and user_sdma_send_pkts() fail to advance to the next iovec in user_sdma_request->iovs when the current iovec is not PAGE_SIZE and does not contain enough data to complete the packet. The transmitted packet will contain the wrong data from the iovec pages.
This has not been an issue with SDMA packets from hfi1 Verbs or PSM2 because they only produce iovecs that end short of PAGE_SIZE as the tail iovec of an SDMA request.
Fixing these bugs exposes other bugs with the SDMA pin cache (struct mmu_rb_handler) that get in way of supporting user SDMA requests with multiple payload iovecs whose buffers do not end at PAGE_SIZE. So this commit fixes those issues as well.
Here are the mmu_rb_handler bugs that non-PAGE_SIZE-end multi-iovec payload user SDMA requests can hit: 1. Overlapping memory ranges in mmu_rb_handler will result in duplicate pinnings. 2. When extending an existing mmu_rb_handler entry (struct mmu_rb_node), the mmu_rb code (1) removes the existing entry under a lock, (2) releases that lock, pins the new pages, (3) then reacquires the lock to insert the extended mmu_rb_node.
If someone else comes in and inserts an overlapping entry between (2) and (3), insert in (3) will fail.
The failure path code in this case unpins _all_ pages in either the original mmu_rb_node or the new mmu_rb_node that was inserted between (2) and (3). 3. In hfi1_mmu_rb_remove_unless_exact(), mmu_rb_node->refcount is incremented outside of mmu_rb_handler->lock. As a result, mmu_rb_node could be evicted by another thread that gets mmu_rb_handler->lock and checks mmu_rb_node->refcount before mmu_rb_node->refcount is incremented. 4. Related to #2 above, SDMA request submission failure path does not check mmu_rb_node->refcount before freeing mmu_rb_node object.
If there are other SDMA requests in progress whose iovecs have pointers to the now-freed mmu_rb_node(s), those pointers to the now-freed mmu_rb nodes will be dereferenced when those SDMA requests complete.
Patch / fix
- Linux Linux 5.10.180, 5.15.111, 6.1.28, 6.2.15, 6.3.2, 6.4
- linux Debian 12 6.1.37-1
- linux Debian 14, Debian 13 6.3.7-1
debian advisories DEBIAN-CVE-2023-52474
- linux Ubuntu 22.04 LTS 5.15.0-79.86
- linux-aws Ubuntu 22.04 LTS 5.15.0-1042.47
- linux-gcp Ubuntu 22.04 LTS 5.15.0-1039.47
- linux-gke Ubuntu 22.04 LTS 5.15.0-1039.44
- linux-ibm Ubuntu 22.04 LTS 5.15.0-1035.38
- linux-kvm Ubuntu 22.04 LTS 5.15.0-1039.44
- linux-azure Ubuntu 22.04 LTS 5.15.0-1045.52
- linux-gkeop Ubuntu 22.04 LTS 5.15.0-1025.30
ubuntu advisories UBUNTU-CVE-2023-52474
Ubuntu security data © Canonical Ltd., from https://github.com/canonical/ubuntu-security-notices via OSV; changed: normalised to fixed package versions per release. CC BY-SA 4.0
- kernel-syms SLES for SAP 12 SP5, SLES 12 SP5 4.12.14-122.216.1
- kernel-source SLES for SAP 12 SP5, SLES 12 SP5 4.12.14-122.216.1
- kernel-default SLES for SAP 12 SP5, SLES 12 SP5, SLE Workstation Extension 12 SP5 +2 more 4.12.14-122.216.1
- kernel-obs-build SLE Software Development Kit 12 SP5 4.12.14-122.216.1
- kernel-rt SLE Real Time 12 SP5 4.12.14-10.182.1
- kernel-syms-rt SLE Real Time 12 SP5 4.12.14-10.182.1
- kernel-rt_debug SLE Real Time 12 SP5 4.12.14-10.182.1
- kernel-source-rt SLE Real Time 12 SP5 4.12.14-10.182.1
suse advisories SUSE-SU-2024:1870-1SUSE-SU-2024:1646-1SUSE-SU-2024:1643-1SUSE-SU-2024:1490-1SUSE-SU-2024:1489-1SUSE-SU-2024:1480-1
- git.kernel.org/stable/c/9c4c6512d7330b743c4ffd18bd999a86ca26db0d commit
- git.kernel.org/stable/c/a2bd706ab63509793b5cd5065e685b7ef5cba678 commit
- git.kernel.org/stable/c/dce59b5443700fbd0d2433ec6e4d4cf063448844 commit
- git.kernel.org/stable/c/c76cb8f4bdf26d04cfa5485a93ce297dba5e6a80 commit
- git.kernel.org/stable/c/7e6010f79b58f45b204cf18aa58f4b73c3f30adc commit
- git.kernel.org/stable/c/00cbce5cbf88459cd1aa1d60d0f1df15477df127 commit
Vendor advisories
What the vendors themselves say about their products: affected, fixed or not affected, and what to do.
red hat product security vex CVE-2023-52474 updated
kernel: non-PAGE_SIZE-end multi-iovec user SDMA requests
-
Red Hat Enterprise Linux 6 perf, kernel, python-perf, kernel-kdump, kernel-firmware, kernel-bootwrapper, +1 more Red Hat Enterprise Linux 7 perf, kernel, bpftool, kernel-rt, python-perf, kernel-kdump, +8 moreaffected: no fix planned “Out of support scope”
-
Red Hat Enterprise Linux 8 perf, kernel, bpftool, kernel-rt, kernel-core, kernel-tools, +29 moreaffected: no fix available “Fix deferred”
-
Red Hat Enterprise Linux 9 rv, perf, rtla, kernel, bpftool, libperf, +82 morenot affected: vulnerable code not present
Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf
cisa ICSA-24-165-06 updated cvss 7.8
Siemens TIM 1531 IRC
-
Siemens SIPLUS TIM 1531 IRC (6AG1543-1MX00-7XE0) <V2.4.8 Siemens TIM 1531 IRC (6GK7543-1MX00-0XE0) <V2.4.8affected: fixed in V2.4.8 support.industry.siemens.com
Facts from CISA's republication of the vendor's own advisory (CSAF); the linked advisory is the authoritative source. CISA notification · csaf
CISA SSVC
- Exploitation
- none
- Automatable
- no
- Technical impact
- partial
- Assessed
- 2 y ago
Exploit prediction
0.25% chance of exploitation in the next 30 days, higher than 16% of all scored CVEs (FIRST EPSS, 2026-11-08).
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 7.8 | CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H |
| NVD | 3.1 | 7.8 | CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H |
Affected products
- Linux Linux
Classification
- Technology feeds
References
-
git.kernel.org
/stable/c/9c4c6512d7330b743c4ffd18bd999a86ca26db0d
patch
-
git.kernel.org
/stable/c/a2bd706ab63509793b5cd5065e685b7ef5cba678
patch
-
git.kernel.org
/stable/c/dce59b5443700fbd0d2433ec6e4d4cf063448844
patch
-
git.kernel.org
/stable/c/c76cb8f4bdf26d04cfa5485a93ce297dba5e6a80
patch
-
git.kernel.org
/stable/c/7e6010f79b58f45b204cf18aa58f4b73c3f30adc
patch
-
git.kernel.org
/stable/c/00cbce5cbf88459cd1aa1d60d0f1df15477df127
patch
Sources
- CVE List CVE-2023-52474
- NVD CVE-2023-52474
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.