CVE Catalog

CVE-2026-97952

Low risk· EPSS 7%
Published: Updated: Translated: NVD NIST

Exploitation Probability (EPSS)

Low risk
0.18%

7th percentile - higher than 7% of all known CVEs

Summary

In the Linux kernel, when __vdc_tx_trigger() fails inside sunvdc's __send_request(), the descriptor remains marked VIO_DESC_READY and the mapped pages (cookies) are never unmapped from the LDC channel's map table. Because the descriptor is never completed by the peer and dr->prod is not advanced, entries in the fixed-size map table (8192 per channel) are leaked permanently. With trigger failures occurring under load (notably after commit a11f6ca9aef9), every I/O error leaks entries, causing fragmentation, failure of large multi-segment requests, and eventually a dead disk until reboot.

Risk Assessment

Leaking map table entries in the LDC channel exhausts resources and renders the sunvdc disk permanently unavailable until the system is rebooted. Retry-based recovery worsens the issue by draining the table at the retry rate, preventing recovery.

Recommendation

Apply the kernel fix that, on trigger failure, unmaps the cookies, marks the descriptor FREE, and clears the request entry (skipping rollback on -ENOTCONN when the port has already been reset). Until patched, avoid heavy load and minimize I/O on sunvdc devices.

Related vulnerabilities

Original NVD description (English source)

In the Linux kernel, the following vulnerability has been resolved: sunvdc: unmap LDC cookies when the descriptor send fails __send_request() maps the request's pages into the LDC channel's map table (ldc_map_sg()), fills in the descriptor and marks it VIO_DESC_READY before ringing the doorbell via __vdc_tx_trigger(). When the trigger fails, the error path only prints a message: the descriptor stays READY and the cookies are never unmapped. The mapping is normally released in vdc_end_one() when the peer completes the descriptor - but a descriptor whose doorbell was never sent will never complete, and since dr->prod is not advanced on failure, the reset path (vdc_requeue_inflight(), which walks [cons, prod)) never visits it either. The map table entries are leaked permanently. Since commit a11f6ca9aef9 ("sunvdc: Do not spin in an infinite loop when vio_ldc_send() returns EAGAIN") trigger failures occur in practice under load, so every resulting I/O error also leaks one request's worth of entries from the fixed-size (8192 entries per channel) map table. Because the allocator hands out contiguous ranges, fragmentation makes large multi-segment requests fail first as the table drains, until ldc_map_sg() fails permanently and the disk is dead until reboot. It also makes any retry-based recovery unusable: requeuing the request on -EAGAIN remaps the pages on every attempt, overwriting desc->cookies and orphaning the previous mapping, so the table drains at the retry rate. This is the memory exhaustion observed when the requeue approach was first tested in October 2025. Roll back on failure: unmap the cookies, mark the descriptor FREE again and clear the request entry. If the trigger failed with -ENOTCONN, __vdc_tx_trigger() has already reset the port, which tears down and reallocates both the dring and the LDC channel including its map table - nothing to roll back, and the stale descriptor must not be touched.

Vulnerability data from NVD (NIST) · CISA KEV · EPSS