{"id":"CVE-2026-98070","published":"2026-09-25T11:17:36.193","lastModified":"2026-09-25T15:18:05.427","description":"In the Linux kernel, the following vulnerability has been resolved:\n\nnet/rds: acquire RDS_IN_XMIT in rds_tcp_reset_callbacks()\n\nrds_tcp_reset_callbacks() quiesces the transmit path by setting the\npath state to RDS_CONN_RESETTING and then waiting for RDS_IN_XMIT to\nbe sampled clear before swapping the underlying socket and calling\nrds_send_path_reset().\n\nSampling the bit clear is not the same as owning it: rds_send_xmit()\ncan re-acquire RDS_IN_XMIT right after the wait_event() returns.  Its\nstate recheck after taking the lock is a store-buffering pattern (the\nresetter writes the state and reads the bit, the sender writes the\nbit and reads the state) and acquire_in_xmit() is only an acquire\noperation, so on weakly ordered architectures both sides can miss\neach other's write and the transmit path then runs concurrently with\nrds_send_path_reset() rewriting cp_xmit_* state - which is exactly\nwhat the comment above rds_send_path_reset() tells its callers to\nprevent.\n\nTake the lock instead, hold it across the socket swap and\nrds_send_path_reset(), and release it with a wake-up at the end.  The\nlock-ordering constraint documented above the wait still holds: the\nlock is acquired before lock_sock(), so a sender inside tcp_sendmsg()\ncan never be waited on while we hold the socket lock.\n\nTwo details of the old code go away with the same change:\n\n - t_sock is now read only after the lock is acquired.  The old code\n   cached it before waiting; the teardown in rds_conn_shutdown()\n   releases that socket and clears t_sock, so a pointer cached before\n   the wait can be stale by the time the accept path resumes.  Reading\n   it under RDS_IN_XMIT is what makes the exclusion complete once the\n   teardown owns the same lock, which the next patch arranges; until\n   then the teardown still only samples the bit, and the two paths\n   remain as exposed to each other as they are today.\n\n - The old !osock early path called rds_send_path_reset() with no\n   serialization at all.  It now runs under the lock like the normal\n   path.  The conditional RDS_CONN_RESETTING transition of the\n   previous patch happens before the socket check either way: a path\n   found without a socket is either still connecting (its reconnect\n   worker blocked on t_conn_path_lock) and legitimately goes\n   RESETTING -> UP on the new socket, or it has been torn down\n   meanwhile and is dropped.\n\nThe in-function comment describing the old wait-based quiesce is\nrewritten to describe the lock-based one, and the stale block comment\nabove the function (which still described a return value and an\nincomplete list of t_sock writers) is refreshed to name all four\nwriters - the connect, accept, teardown and swap paths - and what\nserializes each of them.","cvssScore":8.1,"cvssSeverity":"HIGH","cvssVector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H","cwes":[],"vendors":[],"products":[],"references":[{"url":"https://git.kernel.org/stable/c/02c5f9dc2efd823e061954d564ce00bacd1bebeb","tags":[]},{"url":"https://git.kernel.org/stable/c/062d9e008c67289e8e1b221ecdd8f9d60566d012","tags":[]},{"url":"https://git.kernel.org/stable/c/8e4c3b7844c906c7097b4cfedd9dd1f48c9a6a92","tags":[]},{"url":"https://git.kernel.org/stable/c/d625112564c3e980e02504270222b49b82690cee","tags":[]}],"exploitRefs":[],"hasPoc":false,"ai":null}