From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-alma10-1.taild15c8.ts.net [100.103.45.18]) (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 078683A71A8 for ; Thu, 23 Jul 2026 18:19:17 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=100.103.45.18 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1784830761; cv=none; b=ObswhNkivQ+jtCgIWWLcRN3g6bQIrpZUfHhuhBHISp7KFD0arJPWNpyoFn/lt1VGM7o+F1U5Dzwp1Fy0RIIyQKx6S1J8C7YX4y/mRPO8Q+V8El49pSip+3TaHfU/W4DE7VWQJQFYhYcDeA4u7gw3RsrxW1MsdgImW+FuexbAzeQ= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1784830761; c=relaxed/simple; bh=IHH6d2oUVFJuvcw1De0CIxVVGABMx3922z2MFxYFZZc=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=SxvA+2ej+hhuBLeH1nLXxpsxf6okb9YvJ5PdjIAlvwJTaLpQcl6/XhbLey7xdkBCXaYR4kqHz2y4+jj17S6YvZ+gIQ+orcUG4C0fDQOhSuOAI4O2FggluFQVMYVgo9klugrnGZ2Iu5j7FHODVkeI5gwgabgBCmaLH7k0SyNMLPc= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; arc=none smtp.client-ip=100.103.45.18 Received: by smtp.kernel.org (Postfix) with ESMTPSA id A097F1F00A3A; Thu, 23 Jul 2026 18:19:14 +0000 (UTC) From: Sasha Levin To: stable@vger.kernel.org Cc: Jeff Layton , NeilBrown , Chuck Lever , Sasha Levin Subject: [PATCH 6.18.y 2/5] sunrpc: allocate a separate bvec array for socket sends Date: Thu, 23 Jul 2026 14:19:07 -0400 Message-ID: <20260723181911.3438372-2-sashal@kernel.org> X-Mailer: git-send-email 2.53.0 In-Reply-To: <20260723181911.3438372-1-sashal@kernel.org> References: <2026072057-lapped-rebate-93bd@gregkh> <20260723181911.3438372-1-sashal@kernel.org> Precedence: bulk X-Mailing-List: stable@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit From: Jeff Layton [ Upstream commit 6b3b697d65d46a0f640216a3f6c72856c159c567 ] svc_tcp_sendmsg() calls xdr_buf_to_bvec() with the second slot of rq_bvec as the start, but doesn't reduce the array length by one, which could lead to an array overrun. Also, rq_bvec is always rq_maxpages in length, which can be too short in some cases, since the TCP record marker consumes a slot. Fix both problems by adding a separate bvec array to the svc_sock that is specifically for sending. For TCP, make this array one slot longer than rq_maxpages, to account for the record marker. For UDP, only allocate as large an array as we need since it's limited to 64k of payload. Signed-off-by: Jeff Layton Reviewed-by: NeilBrown Signed-off-by: Chuck Lever Stable-dep-of: 18c1cc698861 ("SUNRPC: Return an error from xdr_buf_to_bvec() on overflow") Signed-off-by: Sasha Levin --- include/linux/sunrpc/svcsock.h | 3 ++ net/sunrpc/svcsock.c | 55 +++++++++++++++++++++++++++++----- 2 files changed, 51 insertions(+), 7 deletions(-) diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index 963bbe251e5210..de37069aba9089 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -26,6 +26,9 @@ struct svc_sock { void (*sk_odata)(struct sock *); void (*sk_owspace)(struct sock *); + /* For sends (protected by xpt_mutex) */ + struct bio_vec *sk_bvec; + /* private TCP part */ /* On-the-wire fragment header: */ __be32 sk_marker; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 7b90abc5cf0ee1..48700b99909fac 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -68,6 +68,17 @@ #define RPCDBG_FACILITY RPCDBG_SVCXPRT +/* + * For UDP: + * 1 for header page + * enough pages for RPCSVC_MAXPAYLOAD_UDP + * 1 in case payload is not aligned + * 1 for tail page + */ +enum { + SUNRPC_MAX_UDP_SENDPAGES = 1 + RPCSVC_MAXPAYLOAD_UDP / PAGE_SIZE + 1 + 1 +}; + /* To-do: to avoid tying up an nfsd thread while waiting for a * handshake request, the request could instead be deferred. */ @@ -740,14 +751,14 @@ static int svc_udp_sendto(struct svc_rqst *rqstp) if (svc_xprt_is_dead(xprt)) goto out_notconn; - count = xdr_buf_to_bvec(rqstp->rq_bvec, rqstp->rq_maxpages, xdr); + count = xdr_buf_to_bvec(svsk->sk_bvec, SUNRPC_MAX_UDP_SENDPAGES, xdr); - iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec, + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, svsk->sk_bvec, count, rqstp->rq_res.len); err = sock_sendmsg(svsk->sk_sock, &msg); if (err == -ECONNREFUSED) { /* ICMP error on earlier request. */ - iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec, + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, svsk->sk_bvec, count, rqstp->rq_res.len); err = sock_sendmsg(svsk->sk_sock, &msg); } @@ -1235,19 +1246,19 @@ static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp, int ret; /* The stream record marker is copied into a temporary page - * fragment buffer so that it can be included in rq_bvec. + * fragment buffer so that it can be included in sk_bvec. */ buf = page_frag_alloc(&svsk->sk_frag_cache, sizeof(marker), GFP_KERNEL); if (!buf) return -ENOMEM; memcpy(buf, &marker, sizeof(marker)); - bvec_set_virt(rqstp->rq_bvec, buf, sizeof(marker)); + bvec_set_virt(svsk->sk_bvec, buf, sizeof(marker)); - count = xdr_buf_to_bvec(rqstp->rq_bvec + 1, rqstp->rq_maxpages, + count = xdr_buf_to_bvec(svsk->sk_bvec + 1, rqstp->rq_maxpages, &rqstp->rq_res); - iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec, + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, svsk->sk_bvec, 1 + count, sizeof(marker) + rqstp->rq_res.len); ret = sock_sendmsg(svsk->sk_sock, &msg); page_frag_free(buf); @@ -1392,6 +1403,20 @@ void svc_sock_update_bufs(struct svc_serv *serv) spin_unlock_bh(&serv->sv_lock); } +static int svc_sock_sendpages(struct svc_serv *serv, struct socket *sock, int flags) +{ + switch (sock->type) { + case SOCK_STREAM: + /* +1 for TCP record marker */ + if (flags & SVC_SOCK_TEMPORARY) + return svc_serv_maxpages(serv) + 1; + return 0; + case SOCK_DGRAM: + return SUNRPC_MAX_UDP_SENDPAGES; + } + return -EINVAL; +} + /* * Initialize socket for RPC use and create svc_sock struct */ @@ -1402,12 +1427,26 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, struct svc_sock *svsk; struct sock *inet; int pmap_register = !(flags & SVC_SOCK_ANONYMOUS); + int sendpages; unsigned long pages; + sendpages = svc_sock_sendpages(serv, sock, flags); + if (sendpages < 0) + return ERR_PTR(sendpages); + pages = svc_serv_maxpages(serv); svsk = kzalloc(struct_size(svsk, sk_pages, pages), GFP_KERNEL); if (!svsk) return ERR_PTR(-ENOMEM); + + if (sendpages) { + svsk->sk_bvec = kcalloc(sendpages, sizeof(*svsk->sk_bvec), GFP_KERNEL); + if (!svsk->sk_bvec) { + kfree(svsk); + return ERR_PTR(-ENOMEM); + } + } + svsk->sk_maxpages = pages; inet = sock->sk; @@ -1419,6 +1458,7 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, inet->sk_protocol, ntohs(inet_sk(inet)->inet_sport)); if (err < 0) { + kfree(svsk->sk_bvec); kfree(svsk); return ERR_PTR(err); } @@ -1636,5 +1676,6 @@ static void svc_sock_free(struct svc_xprt *xprt) sock_release(sock); page_frag_cache_drain(&svsk->sk_frag_cache); + kfree(svsk->sk_bvec); kfree(svsk); } -- 2.53.0