From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mx0b-001b2d01.pphosted.com (mx0b-001b2d01.pphosted.com [148.163.158.5]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id CFE16481A97; Mon, 5 Oct 2026 13:12:55 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=148.163.158.5 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1791205977; cv=none; b=rFEbDemW8dKoRcv7JyGVuToRlY/yRsl4NPqD46t88EDVFBoZrZf0ahGQ8ZcL0R4cWuK6YLc87jDGWlrNuP8MmYzj/HhdojcfdVdYb0xbHsc3twBldtp05q+Nc0f43Kmqqlm5w/Kew5sCKgFX0XOVJG3ILVALW1NL8onouvaDiVo= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1791205977; c=relaxed/simple; bh=0OQ1xzhDS95czbutR18GtxiMav3uyLz+5oCIJzvmaZc=; h=From:To:Cc:Subject:Date:Message-ID:MIME-Version; b=gYlTDo4Fhr+mXQ7DgdOpAbiPk17euGmpswERD7rNNDqq+7osLyWwl2a/uWI/sjnHheUNXHaTSgiqsL++okXQlE/83IrJzUD5ln6zZb4ZDU7eZg82CLECRu7UCH/BLFt8aFDe+raRBDpCY8I8/5TOyksiG0AaWcrad/EWY3ZYEZ0= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.ibm.com; spf=pass smtp.mailfrom=linux.ibm.com; dkim=pass (2048-bit key) header.d=ibm.com header.i=@ibm.com header.b=pLoOoK7m; arc=none smtp.client-ip=148.163.158.5 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.ibm.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.ibm.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=ibm.com header.i=@ibm.com header.b="pLoOoK7m" Received: from pps.filterd (m0356516.ppops.net [127.0.0.1]) by mx0a-001b2d01.pphosted.com (8.18.1.11/8.18.1.11) with ESMTP id 695CZikh504152; Mon, 5 Oct 2026 13:12:48 GMT DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ibm.com; h=cc :content-transfer-encoding:date:from:message-id:mime-version :subject:to; s=pp1; bh=obiFoDbcelCUjEHJPePscGKeoNedIO7JFFVKJBO8h 3o=; b=pLoOoK7mcUjtwg45Rb+yvf9OVmWHiXalkvleHcPS6rNTSyzxPphzHtzWW 8xPMliXCsX898LfxUQxsrN7KBd3kSA+y0AlrV9jWHQhW/loPUHGim1GZ+G0rXF1o owx59+P3nZEr+jLDkhYYPpLy/wng05xyXF9B7q6eF/0bhVitDLx8na3pZ9X4mo21 LeprSdrtU1eG/WvfRNTVsc70i311v7awkfcRvY8Zt/GYvYcyb8D3wLwSAGAeaVN2 NEn2KCdbfiKJtFqg9S+471yZhOQnkclRCwje/EZ4PYDzXTuc10F1BafgK2mL39sd dwY9PX3CIRkacepes3Vm9pvhNQHmA== Received: from ppma11.dal12v.mail.ibm.com (db.9e.1632.ip4.static.sl-reverse.com [50.22.158.219]) by mx0a-001b2d01.pphosted.com (PPS) with ESMTPS id 4h2q4jj0nt-1 (version=TLSv1.3 cipher=TLS_AES_256_GCM_SHA384 bits=256 verify=NOT); Mon, 05 Oct 2026 13:12:47 +0000 (GMT) Received: from pps.filterd (ppma11.dal12v.mail.ibm.com [127.0.0.1]) by ppma11.dal12v.mail.ibm.com (8.18.1.11/8.18.1.11) with ESMTP id 695CHnZT2913114; Mon, 5 Oct 2026 13:12:46 GMT Received: from smtprelay02.fra02v.mail.ibm.com ([9.218.2.226]) by ppma11.dal12v.mail.ibm.com (PPS) with ESMTPS id 4h3eqy5b16-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Mon, 05 Oct 2026 13:12:46 +0000 (GMT) Received: from smtpav07.fra02v.mail.ibm.com (smtpav07.fra02v.mail.ibm.com [10.20.54.106]) by smtprelay02.fra02v.mail.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id 695DCh5c52887846 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Mon, 5 Oct 2026 13:12:43 GMT Received: from smtpav07.fra02v.mail.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id E93262004B; Mon, 5 Oct 2026 13:12:42 +0000 (GMT) Received: from smtpav07.fra02v.mail.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id AC63620040; Mon, 5 Oct 2026 13:12:42 +0000 (GMT) Received: from tuxmaker.boeblingen.de.ibm.com (unknown [9.87.85.9]) by smtpav07.fra02v.mail.ibm.com (Postfix) with SMTP; Mon, 5 Oct 2026 13:12:42 +0000 (GMT) Received: by tuxmaker.boeblingen.de.ibm.com (Postfix, from userid 56341) id 9469C1612C8; Mon, 05 Oct 2026 15:12:42 +0200 (CEST) From: Mahanta Jambigi To: andrew+netdev@lunn.ch, davem@davemloft.net, edumazet@google.com, kuba@kernel.org, pabeni@redhat.com, alibuda@linux.alibaba.com, dust.li@linux.alibaba.com, sidraya@linux.ibm.com Cc: hidayath@linux.ibm.com, pasic@linux.ibm.com, horms@kernel.org, tonylu@linux.alibaba.com, guwen@linux.alibaba.com, stable@vger.kernel.org, netdev@vger.kernel.org, linux-s390@vger.kernel.org, linux-rdma@vger.kernel.org, Mahanta Jambigi Subject: [PATCH net v8] net/smc: fix lgr/lnk lifetime vs diag reader race Date: Mon, 5 Oct 2026 15:12:41 +0200 Message-ID: <20261005131241.1575131-1-mjambigi@linux.ibm.com> X-Mailer: git-send-email 2.53.0 Precedence: bulk X-Mailing-List: linux-rdma@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-TM-AS-GCONF: 00 X-Proofpoint-Reinject: loops=2 maxloops=12 X-Proofpoint-ORIG-GUID: 1v9joWk1UBtkQXO1bawf4baJj1wuDR7Y X-Proofpoint-GUID: Um2IjovbMZLOJW6b51o1-jJJfI6h42uK X-Proofpoint-Spam-Info: AW1haW4tMjYxMDA1MDA1MSBTYWx0ZWRfX68Vd1HfkOPzo KqApgHAAd+RpG2uwRe2UgiUCWVSPykQ8kbKUX1fdDxWmiaRwg773vusHxh4DvOWyXpM25KUqmVs Prrql/5qKsJE+BFskP1mAqqnD4cKBC8= X-Proofpoint-Spam-Details-Enc: AW1haW4tMjYxMDA1MDA1MSBTYWx0ZWRfXy3Ckk27Vlbv+ dDJ90VQVBvHEr2f2PY/ZRAkGBkRlP603XLQ3xGgSu0GIEkUUG7Crxdb0MHkqAXmzJdbNa6ooAw+ 03gxbWd42nP51z+nYep9RCBB4ccZBYZ+UrPaUKlLkb/lSgx6MppqsWmlMu0B3mnCaazxO4r8twk Ub9MzGp8RRPGlEXPUaX/OcyqnTXt6X3VPYb/Nr8dUUbt9FkqUuqi7dCACweUVB37MkgxDZ5znvF r6DYTz/eR8dAxPZGS3x1jc3TXwlUmWf/8tfsNWPJSZDFdcA2uhFmeEOeUQC09zZzraYd1qWFaDP dldu4OL4pkrbfUh+OMQ8PKyoZpMzCETQh0AYgj/xdXhnUfpU6CqAOr7HVoWUvzwGfBEA5U5s8kD BdLfCZSyDfzK+sn1FLd0UJzHJNWXOa1kCyHOXjhvuhkbLxLv8K5frmSMm0fLZ6K8NNf2F0GTZ77 GT9dd2AsZ0jAh/nlJRg== X-Authority-Analysis: v=2.4 cv=eYeo7LEH c=1 sm=1 tr=0 ts=6ac3a24f cx=c_pps a=aDMHemPKRhS1OARIsFnwRA==:117 a=aDMHemPKRhS1OARIsFnwRA==:17 a=660iZSQnnn4A:10 a=VkNPw1HP01LnGYTKEx00:22 a=RnoormkPH1_aCDwRdu11:22 a=Y2IxJ9c9Rs8Kov3niI8_:22 a=VwQbUJbxAAAA:8 a=VnNF1IyMAAAA:8 a=BXWiJY1A4b8lTG70euYA:9 X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.293,Aquarius:18.0.1176,Hydra:6.1.134,FMLib:17.12.100.49 definitions=2026-10-05_03,2026-10-05_01,2025-10-01_01 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 adultscore=0 lowpriorityscore=0 phishscore=0 bulkscore=0 clxscore=1015 spamscore=0 malwarescore=0 priorityscore=1501 impostorscore=0 suspectscore=0 classifier=typeunknown authscore=0 authtc= authcc= route=outbound adjust=0 reason=mlx scancount=1 engine=8.22.0-2609040000 definitions=main-2610050051 The diag dump walks the socket hash table under a read_lock and dereferen= ces conn->lgr and conn->lnk. Three paths expose a window where a hashed socke= t has freed or partially freed conn/lgr/lnk state. First, smc_conn_abort() calls smc_conn_free() during early handshake abor= ts while the socket is still hashed in SMC_INIT, synchronously freeing the l= gr on the smc_lgr_cleanup_early() path without holding the hash write_lock. A concurrent diag reader can load a non-NULL conn->lgr and dereference lgr->is_smcd after the kfree. Guard the conn/lgr/lnk blocks in __smc_diag= _dump() for SMC_INIT and SMC_CLOSED sockets; smcss already suppresses these attri= butes for closed/unconnected sockets so there is no observability regression. U= se smp_load_acquire() / smp_store_release() on sk_state to prevent speculati= ve load reordering on weakly ordered CPUs (e.g. ARM64) during fallback. Second, in smc_conn_kill() on SMC-D with dmb_nocopy, smcd_buf_detach() NU= LLs and frees conn->sndbuf_desc before the socket is unhashed. A concurrent diag = reader entering the CONNINFO block can dereference the freed descriptor. Unhash = the socket at the top of smc_conn_kill(), before smcd_buf_detach(). Third, in the terminal teardown branches of smc_close_active_abort() (PEERCLOSEWAIT and PROCESSABORT groups) and in smc_close_passive_work(), smc_conn_free() drops lgr and lnk references while the socket is still ha= shed. Unhash immediately before each smc_conn_free() call at those two sites. Additionally, in __smc_diag_dump(), use cached link->ibname instead of ch= asing link->smcibdev->ibdev->name to avoid racing with link clearing during SMC= -R link failover. Fixes: f16a7dd5cf27 ("smc: netlink interface for SMC sockets") Fixes: 9dbe086c69b8 ("net/smc: fix invalid link access in dumping SMC-R c= onnections") Fixes: ae2be35cbed2 ("net/smc: {at|de}tach sndbuf to peer DMB if supporte= d") Cc: stable@vger.kernel.org Reviewed-by: Hidayath Khan Reviewed-by: Sidraya Jayagond Signed-off-by: Mahanta Jambigi --- Changes in v8: - smc_diag.c: use smp_load_acquire(&sk->sk_state) to prevent speculative load reordering on weakly ordered CPUs (such as arm64) during handshake abort fallback - af_smc.c: pair with smp_store_release(&sk->sk_state, SMC_ACTIVE) when transitioning out of SMC_INIT - smc_diag.c: copy cached link->ibname instead of chasing link->smcibdev->ibdev->name to prevent NULL pointer dereference / UAF if __smcr_link_clear() zeroes the link during link failover Changes in v7: - no code changes; commit message only - document the SMC_CLOSED leg of the early-exit guard and the rationale that smcss already skips CLOSED sockets on the userspace side; add Fixes: ae2be35cbed2 for the smc_conn_kill() hunk since smcd_buf_detach() was introduced by that commit Changes in v6: - smc_diag.c: inline sk->sk_state !=3D SMC_INIT into the else-if conditio= n so conn->lgr->is_smcd is never loaded for SMC_INIT sockets; retain the SMC_INIT || SMC_CLOSED early-exit guard and out: label from v5 to defensively skip the CONNINFO/LGRINFO/DMBINFO blocks for sockets with no live connection - smc_close.c: remove the unconditional unhash from the top of smc_close_active_abort(); place it scoped immediately before each of the two smc_conn_free() calls in the PEERCLOSEWAIT and PROCESSABORT branches, and before smc_conn_free() in smc_close_passive_work(); this avoids prematurely hiding live SMC_ACTIVE/APPCLOSEWAIT sockets from smcss - smc_core.c: unhash at the top of smc_conn_kill(), before smcd_buf_detach(), so the socket is off the hash table before conn->sndbuf_desc is freed on the dmb_nocopy path Changes in v5: - guard conn/lgr/lnk blocks in __smc_diag_dump() with an (SMC_INIT || SMC_CLOSED) state check placed after the SMC_DIAG_FALLBACK nla_put; SMC_INIT can coexist with fallback (smc_sendmsg() MSG_FASTOPEN path), so the guard must not suppress the fallback reason Changes in v4: - dropped smc_conn_unhash() wrapper, conn->unhashed flag, and all changes to af_smc.c, smc.h, smc_core.c and smc_core.h; smc_unhash_sk() is already idempotent via sk_hashed(), so direct calls at the two teardown sites in smc_close.c are sufficient - dropped the __smc_release() hunk: it needs no change since the subsequent unhash there is already a safe no-op - fixed premature-unhash issue present in v3: smc_conn_free() must not unhash because smc_conn_abort() calls it before smc_switch_to_fallback() in both smc_listen_decline() and smc_connect_rdma() error paths; unhashing there would make live fallback sockets invisible to smcss - likewise, the ISM/RDMA retry loops (smc_find_ism_v2_device_serv(), smc_find_rdma_v2_device_serv()) call smc_conn_abort() on a failed attempt and then smc_conn_create() on the next device; unhashing in smc_conn_free() would permanently hide the established connection from smc_diag since smc_conn_create() does not re-hash the socket Changes in v3: - redesigned as a single patch; dropped the lgr_lnk_lock spinlock approach and the 2-patch split - fix is now at the socket hash layer: introduce smc_conn_unhash() with a per-connection unhashed flag; smc_conn_free() unhashes before dropping lgr/lnk refs, so any socket visible to the diag reader under the hash read_lock has valid conn->lgr and conn->lnk pointers - __smc_release() updated to call smc_conn_unhash() for non-fallback sockets so the flag is honoured when smc_conn_free() already ran first - smc_diag.c needs no changes; the hash read_lock invariant is sufficient without any per-connection lock in the dump path - dropped the clcsock/mutex_trylock fix as that will be addressed separately Changes in v2: - this is v2 of the 2-patch series; the earlier submission was mislabelled [PATCH v3] but was in fact the first version sent to the list - split into a 2-patch series; patch 1/2 adds per-connection lgr_lnk_lock infrastructure to smc_core, patch 2/2 fixes the diag dump path using it - dropped lock_sock()/release_sock() from __smc_diag_dump(); v1 held the socket lock across all lgr/lnk dereferences, requiring the hash read_lock to be dropped and re-acquired around each socket - dropped the restart-from-head loop in smc_diag_dump_proto(); the new design does not drop the hash read_lock mid-walk so the hlist truncation concern no longer applies - dropped refcount_inc_not_zero() socket pinning from the dump loop for the same reason: the hash read_lock is now held for the full walk - added per-connection lgr_lnk_lock spinlock to struct smc_connection; conn->lgr and conn->lnk are NULLed under this lock in smc_conn_free() before borrowed references are released, establishing the invariant: a non-NULL conn->lgr seen under lgr_lnk_lock guarantees the lgr is alive - added lgr_lnk_lock to smc_switch_link_and_count() to protect the conn->lnk pointer swap from concurrent diag readers - replaced mutex_lock() on clcsock_release_lock in smc_diag_msg_common_fill() with mutex_trylock(); mutex_lock() was valid in v1 because the hash spinlock had been dropped, but the new design holds the hash read_lock throughout so only a non-sleeping trylock is safe; a failed trylock leaves address fields zeroed, which is acceptable for a monitoring tool - all conn->lgr and conn->lnk accesses in __smc_diag_dump() use a snapshot-then-use pattern: fields are copied into local stack variables under lgr_lnk_lock and nla_put() is called after releasing the lock, avoiding any sleeping operation under the spinlock net/smc/af_smc.c | 8 ++++---- net/smc/smc_close.c | 3 +++ net/smc/smc_core.c | 1 + net/smc/smc_diag.c | 9 +++++++-- 4 files changed, 15 insertions(+), 7 deletions(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 23d46797b536..3c9b74301d01 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -976,7 +976,7 @@ static int smc_connect_fallback(struct smc_sock *smc,= int reason_code) smc_copy_sock_settings_to_clc(smc); smc->connect_nonblock =3D 0; if (smc->sk.sk_state =3D=3D SMC_INIT) - smc->sk.sk_state =3D SMC_ACTIVE; + smp_store_release(&smc->sk.sk_state, SMC_ACTIVE); return 0; } @@ -1381,7 +1381,7 @@ int smc_conn_create(struct smc_sock *smc, struct sm= c_init_info *ini) smc_copy_sock_settings_to_clc(smc); smc->connect_nonblock =3D 0; if (smc->sk.sk_state =3D=3D SMC_INIT) - smc->sk.sk_state =3D SMC_ACTIVE; + smp_store_release(&smc->sk.sk_state, SMC_ACTIVE); return 0; connect_abort: @@ -1484,7 +1484,7 @@ static int smc_connect_ism(struct smc_sock *smc, st= ruct smc_init_info *ini) smc_copy_sock_settings_to_clc(smc); smc->connect_nonblock =3D 0; if (smc->sk.sk_state =3D=3D SMC_INIT) - smc->sk.sk_state =3D SMC_ACTIVE; + smp_store_release(&smc->sk.sk_state, SMC_ACTIVE); return 0; connect_abort: @@ -1951,7 +1951,7 @@ static void smc_listen_out_connected(struct smc_soc= k *new_smc) struct sock *newsmcsk =3D &new_smc->sk; if (newsmcsk->sk_state =3D=3D SMC_INIT) - newsmcsk->sk_state =3D SMC_ACTIVE; + smp_store_release(&newsmcsk->sk_state, SMC_ACTIVE); smc_listen_out(new_smc); } diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index bb0313ef5f7c..aa6363abdd74 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -154,6 +154,7 @@ void smc_close_active_abort(struct smc_sock *smc) if (sk->sk_state !=3D SMC_PEERABORTWAIT) break; sk->sk_state =3D SMC_CLOSED; + sk->sk_prot->unhash(sk); smc_conn_free(&smc->conn); release_clcsock =3D true; sock_put(sk); /* passive closing */ @@ -165,6 +166,7 @@ void smc_close_active_abort(struct smc_sock *smc) if (sk->sk_state !=3D SMC_PEERABORTWAIT) break; sk->sk_state =3D SMC_CLOSED; + sk->sk_prot->unhash(sk); smc_conn_free(&smc->conn); release_clcsock =3D true; break; @@ -433,6 +435,7 @@ static void smc_close_passive_work(struct work_struct= *work) sk->sk_state_change(sk); if ((sk->sk_state =3D=3D SMC_CLOSED) && (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) { + sk->sk_prot->unhash(sk); smc_conn_free(conn); if (smc->clcsock) release_clcsock =3D true; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 04aedd957543..d7bd6d7f428b 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1517,6 +1517,7 @@ static void smc_conn_kill(struct smc_connection *co= nn, bool soft) { struct smc_sock *smc =3D container_of(conn, struct smc_sock, conn); + smc->sk.sk_prot->unhash(&smc->sk); if (conn->lgr->is_smcd && conn->lgr->peer_shutdown) conn->local_tx_ctrl.conn_state_flags.peer_conn_abort =3D 1; else diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index bf0beaa23bdb..6ee51088d227 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -87,10 +87,11 @@ static int __smc_diag_dump(struct sock *sk, struct sk= _buff *skb, r =3D nlmsg_data(nlh); smc_diag_msg_common_fill(r, sk); - r->diag_state =3D sk->sk_state; + r->diag_state =3D smp_load_acquire(&sk->sk_state); if (smc->use_fallback) r->diag_mode =3D SMC_DIAG_MODE_FALLBACK_TCP; - else if (smc_conn_lgr_valid(&smc->conn) && smc->conn.lgr->is_smcd) + else if (r->diag_state !=3D SMC_INIT && + smc_conn_lgr_valid(&smc->conn) && smc->conn.lgr->is_smcd) r->diag_mode =3D SMC_DIAG_MODE_SMCD; else r->diag_mode =3D SMC_DIAG_MODE_SMCR; @@ -103,6 +104,9 @@ static int __smc_diag_dump(struct sock *sk, struct sk= _buff *skb, if (nla_put(skb, SMC_DIAG_FALLBACK, sizeof(fallback), &fallback) < 0) goto errout; + if (r->diag_state =3D=3D SMC_INIT || r->diag_state =3D=3D SMC_CLOSED) + goto out; + if ((req->diag_ext & (1 << (SMC_DIAG_CONNINFO - 1))) && smc->conn.alert_token_local) { struct smc_connection *conn =3D &smc->conn; @@ -154,7 +158,6 @@ static int __smc_diag_dump(struct sock *sk, struct sk= _buff *skb, .lnk[0].link_id =3D link->link_id, }; - memcpy(linfo.lnk[0].ibname, link->smcibdev->ibdev->name, - sizeof(link->smcibdev->ibdev->name)); + memcpy(linfo.lnk[0].ibname, link->ibname, sizeof(link->ibname)); smc_gid_be16_convert(linfo.lnk[0].gid, link->gid); smc_gid_be16_convert(linfo.lnk[0].peer_gid, link->peer_gid); @@ -185,6 +189,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk= _buff *skb, goto errout; } +out: nlmsg_end(skb, nlh); return 0; --=20 2.50.1 (Apple Git-155)