From ddbfe3a2e2f0ae22a214dfe84dc0ff619be30566 Mon Sep 17 00:00:00 2001 From: trociny Date: Tue, 24 Apr 2012 19:08:40 +0000 Subject: [PATCH] MFC r232317: Introduce VOP_UNP_BIND(), VOP_UNP_CONNECT(), and VOP_UNP_DETACH() operations for setting and accessing vnode's v_socket field. The operations are necessary to implement proper unix socket handling on layered file systems like nullfs(5). This change fixes the long standing issue with nullfs(5) being in that unix sockets did not work between lower and upper layers: if we bound to a socket on the lower layer we could connect only to the lower path; if we bound to the upper layer we could connect only to the upper path. The new behavior is one can connect to both the lower and the upper paths regardless what layer path one binds to. PR: kern/51583, kern/159663 Suggested by: kib Reviewed by: arch git-svn-id: svn://svn.freebsd.org/base/stable/9@234660 ccf9f872-aa2e-dd11-9fc8-001c23d0bc1f --- UPDATING | 8 ++++++++ sys/kern/uipc_usrreq.c | 14 ++++++-------- sys/kern/vfs_default.c | 27 +++++++++++++++++++++++++++ sys/kern/vnode_if.src | 22 +++++++++++++++------- sys/sys/vnode.h | 3 +++ 5 files changed, 59 insertions(+), 15 deletions(-) diff --git a/UPDATING b/UPDATING index 72650a6ae..eb08fe31c 100644 --- a/UPDATING +++ b/UPDATING @@ -9,6 +9,14 @@ handbook. Items affecting the ports and packages system can be found in /usr/ports/UPDATING. Please read that file before running portupgrade. +20120422: + Now unix domain sockets behave "as expected" on nullfs(5). Previously + nullfs(5) did not pass through all behaviours to the underlying layer, + as a result if we bound to a socket on the lower layer we could connect + only to the lower path; if we bound to the upper layer we could connect + only to the upper path. The new behavior is one can connect to both the + lower and the upper paths regardless what layer path one binds to. + 20120109: The acpi_wmi(4) status device /dev/wmistat has been renamed to /dev/wmistat0. diff --git a/sys/kern/uipc_usrreq.c b/sys/kern/uipc_usrreq.c index 1e06eeb44..c4f6117b9 100644 --- a/sys/kern/uipc_usrreq.c +++ b/sys/kern/uipc_usrreq.c @@ -541,7 +541,7 @@ restart: UNP_LINK_WLOCK(); UNP_PCB_LOCK(unp); - vp->v_socket = unp->unp_socket; + VOP_UNP_BIND(vp, unp->unp_socket); unp->unp_vnode = vp; unp->unp_addr = soun; unp->unp_flags &= ~UNP_BINDING; @@ -637,7 +637,7 @@ uipc_detach(struct socket *so) * XXXRW: Should assert vp->v_socket == so. */ if ((vp = unp->unp_vnode) != NULL) { - unp->unp_vnode->v_socket = NULL; + VOP_UNP_DETACH(vp); unp->unp_vnode = NULL; } unp2 = unp->unp_conn; @@ -1307,7 +1307,7 @@ unp_connect(struct socket *so, struct sockaddr *nam, struct thread *td) * and to protect simultaneous locking of multiple pcbs. */ UNP_LINK_WLOCK(); - so2 = vp->v_socket; + VOP_UNP_CONNECT(vp, &so2); if (so2 == NULL) { error = ECONNREFUSED; goto bad2; @@ -2317,17 +2317,15 @@ vfs_unp_reclaim(struct vnode *vp) active = 0; UNP_LINK_WLOCK(); - so = vp->v_socket; + VOP_UNP_CONNECT(vp, &so); if (so == NULL) goto done; unp = sotounpcb(so); if (unp == NULL) goto done; UNP_PCB_LOCK(unp); - if (unp->unp_vnode != NULL) { - KASSERT(unp->unp_vnode == vp, - ("vfs_unp_reclaim: vp != unp->unp_vnode")); - vp->v_socket = NULL; + if (unp->unp_vnode == vp) { + VOP_UNP_DETACH(vp); unp->unp_vnode = NULL; active = 1; } diff --git a/sys/kern/vfs_default.c b/sys/kern/vfs_default.c index e47498eeb..25278c860 100644 --- a/sys/kern/vfs_default.c +++ b/sys/kern/vfs_default.c @@ -123,6 +123,9 @@ struct vop_vector default_vnodeops = { .vop_unlock = vop_stdunlock, .vop_vptocnp = vop_stdvptocnp, .vop_vptofh = vop_stdvptofh, + .vop_unp_bind = vop_stdunp_bind, + .vop_unp_connect = vop_stdunp_connect, + .vop_unp_detach = vop_stdunp_detach, }; /* @@ -1037,6 +1040,30 @@ vop_stdadvise(struct vop_advise_args *ap) return (error); } +int +vop_stdunp_bind(struct vop_unp_bind_args *ap) +{ + + ap->a_vp->v_socket = ap->a_socket; + return (0); +} + +int +vop_stdunp_connect(struct vop_unp_connect_args *ap) +{ + + *ap->a_socket = ap->a_vp->v_socket; + return (0); +} + +int +vop_stdunp_detach(struct vop_unp_detach_args *ap) +{ + + ap->a_vp->v_socket = NULL; + return (0); +} + /* * vfs default ops * used to fill the vfs function table to get reasonable default return values. diff --git a/sys/kern/vnode_if.src b/sys/kern/vnode_if.src index 5da4c1c44..8224c461e 100644 --- a/sys/kern/vnode_if.src +++ b/sys/kern/vnode_if.src @@ -640,23 +640,31 @@ vop_advise { IN int advice; }; -# The VOPs below are spares at the end of the table to allow new VOPs to be -# added in stable branches without breaking the KBI. New VOPs in HEAD should -# be added above these spares. When merging a new VOP to a stable branch, -# the new VOP should replace one of the spares. +%% unp_bind vp E E E -vop_spare1 { +vop_unp_bind { IN struct vnode *vp; + IN struct socket *socket; }; -vop_spare2 { +%% unp_connect vp L L L + +vop_unp_connect { IN struct vnode *vp; + OUT struct socket **socket; }; -vop_spare3 { +%% unp_detach vp = = = + +vop_unp_detach { IN struct vnode *vp; }; +# The VOPs below are spares at the end of the table to allow new VOPs to be +# added in stable branches without breaking the KBI. New VOPs in HEAD should +# be added above these spares. When merging a new VOP to a stable branch, +# the new VOP should replace one of the spares. + vop_spare4 { IN struct vnode *vp; }; diff --git a/sys/sys/vnode.h b/sys/sys/vnode.h index b56d44a4c..41abaf101 100644 --- a/sys/sys/vnode.h +++ b/sys/sys/vnode.h @@ -707,6 +707,9 @@ int vop_stdpathconf(struct vop_pathconf_args *); int vop_stdpoll(struct vop_poll_args *); int vop_stdvptocnp(struct vop_vptocnp_args *ap); int vop_stdvptofh(struct vop_vptofh_args *ap); +int vop_stdunp_bind(struct vop_unp_bind_args *ap); +int vop_stdunp_connect(struct vop_unp_connect_args *ap); +int vop_stdunp_detach(struct vop_unp_detach_args *ap); int vop_eopnotsupp(struct vop_generic_args *ap); int vop_ebadf(struct vop_generic_args *ap); int vop_einval(struct vop_generic_args *ap); -- 2.45.0