summaryrefslogtreecommitdiff
path: root/net/sunrpc
diff options
context:
space:
mode:
authorJ. Bruce Fields <bfields@redhat.com>2011-11-29 17:00:26 -0500
committerGreg Kroah-Hartman <gregkh@suse.de>2012-01-25 16:13:32 -0800
commitdd96317396ccb415ff4d540d0e69fd1d455a889f (patch)
treea020d0999aae0d5260a3dbf6d026c1d07d20e0e6 /net/sunrpc
parent0832fe15fcb1360f977681569c6493a59d19dd3c (diff)
svcrpc: avoid memory-corruption on pool shutdown
commit b4f36f88b3ee7cf26bf0be84e6c7fc15f84dcb71 upstream. Socket callbacks use svc_xprt_enqueue() to add an xprt to a pool->sp_sockets list. In normal operation a server thread will later come along and take the xprt off that list. On shutdown, after all the threads have exited, we instead manually walk the sv_tempsocks and sv_permsocks lists to find all the xprt's and delete them. So the sp_sockets lists don't really matter any more. As a result, we've mostly just ignored them and hoped they would go away. Which has gotten us into trouble; witness for example ebc63e531cc6 "svcrpc: fix list-corrupting race on nfsd shutdown", the result of Ben Greear noticing that a still-running svc_xprt_enqueue() could re-add an xprt to an sp_sockets list just before it was deleted. The fix was to remove it from the list at the end of svc_delete_xprt(). But that only made corruption less likely--I can see nothing that prevents a svc_xprt_enqueue() from adding another xprt to the list at the same moment that we're removing this xprt from the list. In fact, despite the earlier xpo_detach(), I don't even see what guarantees that svc_xprt_enqueue() couldn't still be running on this xprt. So, instead, note that svc_xprt_enqueue() essentially does: lock sp_lock if XPT_BUSY unset add to sp_sockets unlock sp_lock So, if we do: set XPT_BUSY on every xprt. Empty every sp_sockets list, under the sp_socks locks. Then we're left knowing that the sp_sockets lists are all empty and will stay that way, since any svc_xprt_enqueue() will check XPT_BUSY under the sp_lock and see it set. And *then* we can continue deleting the xprt's. (Thanks to Jeff Layton for being correctly suspicious of this code....) Cc: Ben Greear <greearb@candelatech.com> Cc: Jeff Layton <jlayton@redhat.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Diffstat (limited to 'net/sunrpc')
-rw-r--r--net/sunrpc/svc.c10
-rw-r--r--net/sunrpc/svc_xprt.c48
2 files changed, 38 insertions, 20 deletions
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 7ddfb04ca2a6..d4ad50ece9bc 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -530,7 +530,15 @@ svc_destroy(struct svc_serv *serv)
printk("svc_destroy: no threads for serv=%p!\n", serv);
del_timer_sync(&serv->sv_temptimer);
-
+ /*
+ * The set of xprts (contained in the sv_tempsocks and
+ * sv_permsocks lists) is now constant, since it is modified
+ * only by accepting new sockets (done by service threads in
+ * svc_recv) or aging old ones (done by sv_temptimer), or
+ * configuration changes (excluded by whatever locking the
+ * caller is using--nfsd_mutex in the case of nfsd). So it's
+ * safe to traverse those lists and shut everything down:
+ */
svc_close_all(serv);
if (serv->sv_shutdown)
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index dcdc8df1fa2a..9ed2cd069f45 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -893,14 +893,7 @@ void svc_delete_xprt(struct svc_xprt *xprt)
spin_lock_bh(&serv->sv_lock);
if (!test_and_set_bit(XPT_DETACHED, &xprt->xpt_flags))
list_del_init(&xprt->xpt_list);
- /*
- * The only time we're called while xpt_ready is still on a list
- * is while the list itself is about to be destroyed (in
- * svc_destroy). BUT svc_xprt_enqueue could still be attempting
- * to add new entries to the sp_sockets list, so we can't leave
- * a freed xprt on it.
- */
- list_del_init(&xprt->xpt_ready);
+ BUG_ON(!list_empty(&xprt->xpt_ready));
if (test_bit(XPT_TEMP, &xprt->xpt_flags))
serv->sv_tmpcnt--;
spin_unlock_bh(&serv->sv_lock);
@@ -931,28 +924,45 @@ EXPORT_SYMBOL_GPL(svc_close_xprt);
static void svc_close_list(struct list_head *xprt_list)
{
struct svc_xprt *xprt;
- struct svc_xprt *tmp;
- /*
- * The server is shutting down, and no more threads are running.
- * svc_xprt_enqueue() might still be running, but at worst it
- * will re-add the xprt to sp_sockets, which will soon get
- * freed. So we don't bother with any more locking, and don't
- * leave the close to the (nonexistent) server threads:
- */
- list_for_each_entry_safe(xprt, tmp, xprt_list, xpt_list) {
+ list_for_each_entry(xprt, xprt_list, xpt_list) {
set_bit(XPT_CLOSE, &xprt->xpt_flags);
- svc_delete_xprt(xprt);
+ set_bit(XPT_BUSY, &xprt->xpt_flags);
}
}
void svc_close_all(struct svc_serv *serv)
{
+ struct svc_pool *pool;
+ struct svc_xprt *xprt;
+ struct svc_xprt *tmp;
+ int i;
+
svc_close_list(&serv->sv_tempsocks);
svc_close_list(&serv->sv_permsocks);
+
+ for (i = 0; i < serv->sv_nrpools; i++) {
+ pool = &serv->sv_pools[i];
+
+ spin_lock_bh(&pool->sp_lock);
+ while (!list_empty(&pool->sp_sockets)) {
+ xprt = list_first_entry(&pool->sp_sockets, struct svc_xprt, xpt_ready);
+ list_del_init(&xprt->xpt_ready);
+ }
+ spin_unlock_bh(&pool->sp_lock);
+ }
+ /*
+ * At this point the sp_sockets lists will stay empty, since
+ * svc_enqueue will not add new entries without taking the
+ * sp_lock and checking XPT_BUSY.
+ */
+ list_for_each_entry_safe(xprt, tmp, &serv->sv_tempsocks, xpt_list)
+ svc_delete_xprt(xprt);
+ list_for_each_entry_safe(xprt, tmp, &serv->sv_permsocks, xpt_list)
+ svc_delete_xprt(xprt);
+
BUG_ON(!list_empty(&serv->sv_permsocks));
BUG_ON(!list_empty(&serv->sv_tempsocks));
-
}
/*