The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From d4b09acf924b84bae77cad090a9d108e70b43643 Mon Sep 17 00:00:00 2001
From: Vasily Averin <vvs(a)virtuozzo.com>
Date: Mon, 24 Dec 2018 14:44:52 +0300
Subject: [PATCH] sunrpc: use-after-free in svc_process_common()
if node have NFSv41+ mounts inside several net namespaces
it can lead to use-after-free in svc_process_common()
svc_process_common()
/* Setup reply header */
rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp); <<< HERE
svc_process_common() can use incorrect rqstp->rq_xprt,
its caller function bc_svc_process() takes it from serv->sv_bc_xprt.
The problem is that serv is global structure but sv_bc_xprt
is assigned per-netnamespace.
According to Trond, the whole "let's set up rqstp->rq_xprt
for the back channel" is nothing but a giant hack in order
to work around the fact that svc_process_common() uses it
to find the xpt_ops, and perform a couple of (meaningless
for the back channel) tests of xpt_flags.
All we really need in svc_process_common() is to be able to run
rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr()
Bruce J Fields points that this xpo_prep_reply_hdr() call
is an awfully roundabout way just to do "svc_putnl(resv, 0);"
in the tcp case.
This patch does not initialiuze rqstp->rq_xprt in bc_svc_process(),
now it calls svc_process_common() with rqstp->rq_xprt = NULL.
To adjust reply header svc_process_common() just check
rqstp->rq_prot and calls svc_tcp_prep_reply_hdr() for tcp case.
To handle rqstp->rq_xprt = NULL case in functions called from
svc_process_common() patch intruduces net namespace pointer
svc_rqst->rq_bc_net and adjust SVC_NET() definition.
Some other function was also adopted to properly handle described case.
Signed-off-by: Vasily Averin <vvs(a)virtuozzo.com>
Cc: stable(a)vger.kernel.org
Fixes: 23c20ecd4475 ("NFS: callback up - users counting cleanup")
Signed-off-by: J. Bruce Fields <bfields(a)redhat.com>
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 73e130a840ce..fdb6b317d974 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -295,9 +295,12 @@ struct svc_rqst {
struct svc_cacherep * rq_cacherep; /* cache info */
struct task_struct *rq_task; /* service thread */
spinlock_t rq_lock; /* per-request lock */
+ struct net *rq_bc_net; /* pointer to backchannel's
+ * net namespace
+ */
};
-#define SVC_NET(svc_rqst) (svc_rqst->rq_xprt->xpt_net)
+#define SVC_NET(rqst) (rqst->rq_xprt ? rqst->rq_xprt->xpt_net : rqst->rq_bc_net)
/*
* Rigorous type checking on sockaddr type conversions
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 28e384186c35..8617f4fd6b70 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -569,7 +569,8 @@ TRACE_EVENT(svc_process,
__field(u32, vers)
__field(u32, proc)
__string(service, name)
- __string(addr, rqst->rq_xprt->xpt_remotebuf)
+ __string(addr, rqst->rq_xprt ?
+ rqst->rq_xprt->xpt_remotebuf : "(null)")
),
TP_fast_assign(
@@ -577,7 +578,8 @@ TRACE_EVENT(svc_process,
__entry->vers = rqst->rq_vers;
__entry->proc = rqst->rq_proc;
__assign_str(service, name);
- __assign_str(addr, rqst->rq_xprt->xpt_remotebuf);
+ __assign_str(addr, rqst->rq_xprt ?
+ rqst->rq_xprt->xpt_remotebuf : "(null)");
),
TP_printk("addr=%s xid=0x%08x service=%s vers=%u proc=%u",
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index d13e05f1a990..fb647bc01fc5 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1172,7 +1172,8 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
clear_bit(RQ_DROPME, &rqstp->rq_flags);
/* Setup reply header */
- rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
+ if (rqstp->rq_prot == IPPROTO_TCP)
+ svc_tcp_prep_reply_hdr(rqstp);
svc_putu32(resv, rqstp->rq_xid);
@@ -1244,7 +1245,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
* for lower versions. RPC_PROG_MISMATCH seems to be the closest
* fit.
*/
- if (versp->vs_need_cong_ctrl &&
+ if (versp->vs_need_cong_ctrl && rqstp->rq_xprt &&
!test_bit(XPT_CONG_CTRL, &rqstp->rq_xprt->xpt_flags))
goto err_bad_vers;
@@ -1336,7 +1337,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
return 0;
close:
- if (test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
+ if (rqstp->rq_xprt && test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
svc_close_xprt(rqstp->rq_xprt);
dprintk("svc: svc_process close\n");
return 0;
@@ -1459,10 +1460,10 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req,
dprintk("svc: %s(%p)\n", __func__, req);
/* Build the svc_rqst used by the common processing routine */
- rqstp->rq_xprt = serv->sv_bc_xprt;
rqstp->rq_xid = req->rq_xid;
rqstp->rq_prot = req->rq_xprt->prot;
rqstp->rq_server = serv;
+ rqstp->rq_bc_net = req->rq_xprt->xprt_net;
rqstp->rq_addrlen = sizeof(req->rq_xprt->addr);
memcpy(&rqstp->rq_addr, &req->rq_xprt->addr, rqstp->rq_addrlen);
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 51d36230b6e3..bd42da287c26 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -468,10 +468,11 @@ static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
*/
void svc_reserve(struct svc_rqst *rqstp, int space)
{
+ struct svc_xprt *xprt = rqstp->rq_xprt;
+
space += rqstp->rq_res.head[0].iov_len;
- if (space < rqstp->rq_reserved) {
- struct svc_xprt *xprt = rqstp->rq_xprt;
+ if (xprt && space < rqstp->rq_reserved) {
atomic_sub((rqstp->rq_reserved - space), &xprt->xpt_reserved);
rqstp->rq_reserved = space;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 986f3ed7d1a2..793149ba1bda 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1173,7 +1173,7 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
/*
* Setup response header. TCP has a 4B record length field.
*/
-static void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp)
+void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp)
{
struct kvec *resv = &rqstp->rq_res.head[0];
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From d4b09acf924b84bae77cad090a9d108e70b43643 Mon Sep 17 00:00:00 2001
From: Vasily Averin <vvs(a)virtuozzo.com>
Date: Mon, 24 Dec 2018 14:44:52 +0300
Subject: [PATCH] sunrpc: use-after-free in svc_process_common()
if node have NFSv41+ mounts inside several net namespaces
it can lead to use-after-free in svc_process_common()
svc_process_common()
/* Setup reply header */
rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp); <<< HERE
svc_process_common() can use incorrect rqstp->rq_xprt,
its caller function bc_svc_process() takes it from serv->sv_bc_xprt.
The problem is that serv is global structure but sv_bc_xprt
is assigned per-netnamespace.
According to Trond, the whole "let's set up rqstp->rq_xprt
for the back channel" is nothing but a giant hack in order
to work around the fact that svc_process_common() uses it
to find the xpt_ops, and perform a couple of (meaningless
for the back channel) tests of xpt_flags.
All we really need in svc_process_common() is to be able to run
rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr()
Bruce J Fields points that this xpo_prep_reply_hdr() call
is an awfully roundabout way just to do "svc_putnl(resv, 0);"
in the tcp case.
This patch does not initialiuze rqstp->rq_xprt in bc_svc_process(),
now it calls svc_process_common() with rqstp->rq_xprt = NULL.
To adjust reply header svc_process_common() just check
rqstp->rq_prot and calls svc_tcp_prep_reply_hdr() for tcp case.
To handle rqstp->rq_xprt = NULL case in functions called from
svc_process_common() patch intruduces net namespace pointer
svc_rqst->rq_bc_net and adjust SVC_NET() definition.
Some other function was also adopted to properly handle described case.
Signed-off-by: Vasily Averin <vvs(a)virtuozzo.com>
Cc: stable(a)vger.kernel.org
Fixes: 23c20ecd4475 ("NFS: callback up - users counting cleanup")
Signed-off-by: J. Bruce Fields <bfields(a)redhat.com>
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 73e130a840ce..fdb6b317d974 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -295,9 +295,12 @@ struct svc_rqst {
struct svc_cacherep * rq_cacherep; /* cache info */
struct task_struct *rq_task; /* service thread */
spinlock_t rq_lock; /* per-request lock */
+ struct net *rq_bc_net; /* pointer to backchannel's
+ * net namespace
+ */
};
-#define SVC_NET(svc_rqst) (svc_rqst->rq_xprt->xpt_net)
+#define SVC_NET(rqst) (rqst->rq_xprt ? rqst->rq_xprt->xpt_net : rqst->rq_bc_net)
/*
* Rigorous type checking on sockaddr type conversions
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 28e384186c35..8617f4fd6b70 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -569,7 +569,8 @@ TRACE_EVENT(svc_process,
__field(u32, vers)
__field(u32, proc)
__string(service, name)
- __string(addr, rqst->rq_xprt->xpt_remotebuf)
+ __string(addr, rqst->rq_xprt ?
+ rqst->rq_xprt->xpt_remotebuf : "(null)")
),
TP_fast_assign(
@@ -577,7 +578,8 @@ TRACE_EVENT(svc_process,
__entry->vers = rqst->rq_vers;
__entry->proc = rqst->rq_proc;
__assign_str(service, name);
- __assign_str(addr, rqst->rq_xprt->xpt_remotebuf);
+ __assign_str(addr, rqst->rq_xprt ?
+ rqst->rq_xprt->xpt_remotebuf : "(null)");
),
TP_printk("addr=%s xid=0x%08x service=%s vers=%u proc=%u",
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index d13e05f1a990..fb647bc01fc5 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1172,7 +1172,8 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
clear_bit(RQ_DROPME, &rqstp->rq_flags);
/* Setup reply header */
- rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
+ if (rqstp->rq_prot == IPPROTO_TCP)
+ svc_tcp_prep_reply_hdr(rqstp);
svc_putu32(resv, rqstp->rq_xid);
@@ -1244,7 +1245,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
* for lower versions. RPC_PROG_MISMATCH seems to be the closest
* fit.
*/
- if (versp->vs_need_cong_ctrl &&
+ if (versp->vs_need_cong_ctrl && rqstp->rq_xprt &&
!test_bit(XPT_CONG_CTRL, &rqstp->rq_xprt->xpt_flags))
goto err_bad_vers;
@@ -1336,7 +1337,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
return 0;
close:
- if (test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
+ if (rqstp->rq_xprt && test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
svc_close_xprt(rqstp->rq_xprt);
dprintk("svc: svc_process close\n");
return 0;
@@ -1459,10 +1460,10 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req,
dprintk("svc: %s(%p)\n", __func__, req);
/* Build the svc_rqst used by the common processing routine */
- rqstp->rq_xprt = serv->sv_bc_xprt;
rqstp->rq_xid = req->rq_xid;
rqstp->rq_prot = req->rq_xprt->prot;
rqstp->rq_server = serv;
+ rqstp->rq_bc_net = req->rq_xprt->xprt_net;
rqstp->rq_addrlen = sizeof(req->rq_xprt->addr);
memcpy(&rqstp->rq_addr, &req->rq_xprt->addr, rqstp->rq_addrlen);
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 51d36230b6e3..bd42da287c26 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -468,10 +468,11 @@ static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
*/
void svc_reserve(struct svc_rqst *rqstp, int space)
{
+ struct svc_xprt *xprt = rqstp->rq_xprt;
+
space += rqstp->rq_res.head[0].iov_len;
- if (space < rqstp->rq_reserved) {
- struct svc_xprt *xprt = rqstp->rq_xprt;
+ if (xprt && space < rqstp->rq_reserved) {
atomic_sub((rqstp->rq_reserved - space), &xprt->xpt_reserved);
rqstp->rq_reserved = space;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 986f3ed7d1a2..793149ba1bda 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1173,7 +1173,7 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
/*
* Setup response header. TCP has a 4B record length field.
*/
-static void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp)
+void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp)
{
struct kvec *resv = &rqstp->rq_res.head[0];
The patch below does not apply to the 4.20-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From d4b09acf924b84bae77cad090a9d108e70b43643 Mon Sep 17 00:00:00 2001
From: Vasily Averin <vvs(a)virtuozzo.com>
Date: Mon, 24 Dec 2018 14:44:52 +0300
Subject: [PATCH] sunrpc: use-after-free in svc_process_common()
if node have NFSv41+ mounts inside several net namespaces
it can lead to use-after-free in svc_process_common()
svc_process_common()
/* Setup reply header */
rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp); <<< HERE
svc_process_common() can use incorrect rqstp->rq_xprt,
its caller function bc_svc_process() takes it from serv->sv_bc_xprt.
The problem is that serv is global structure but sv_bc_xprt
is assigned per-netnamespace.
According to Trond, the whole "let's set up rqstp->rq_xprt
for the back channel" is nothing but a giant hack in order
to work around the fact that svc_process_common() uses it
to find the xpt_ops, and perform a couple of (meaningless
for the back channel) tests of xpt_flags.
All we really need in svc_process_common() is to be able to run
rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr()
Bruce J Fields points that this xpo_prep_reply_hdr() call
is an awfully roundabout way just to do "svc_putnl(resv, 0);"
in the tcp case.
This patch does not initialiuze rqstp->rq_xprt in bc_svc_process(),
now it calls svc_process_common() with rqstp->rq_xprt = NULL.
To adjust reply header svc_process_common() just check
rqstp->rq_prot and calls svc_tcp_prep_reply_hdr() for tcp case.
To handle rqstp->rq_xprt = NULL case in functions called from
svc_process_common() patch intruduces net namespace pointer
svc_rqst->rq_bc_net and adjust SVC_NET() definition.
Some other function was also adopted to properly handle described case.
Signed-off-by: Vasily Averin <vvs(a)virtuozzo.com>
Cc: stable(a)vger.kernel.org
Fixes: 23c20ecd4475 ("NFS: callback up - users counting cleanup")
Signed-off-by: J. Bruce Fields <bfields(a)redhat.com>
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 73e130a840ce..fdb6b317d974 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -295,9 +295,12 @@ struct svc_rqst {
struct svc_cacherep * rq_cacherep; /* cache info */
struct task_struct *rq_task; /* service thread */
spinlock_t rq_lock; /* per-request lock */
+ struct net *rq_bc_net; /* pointer to backchannel's
+ * net namespace
+ */
};
-#define SVC_NET(svc_rqst) (svc_rqst->rq_xprt->xpt_net)
+#define SVC_NET(rqst) (rqst->rq_xprt ? rqst->rq_xprt->xpt_net : rqst->rq_bc_net)
/*
* Rigorous type checking on sockaddr type conversions
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 28e384186c35..8617f4fd6b70 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -569,7 +569,8 @@ TRACE_EVENT(svc_process,
__field(u32, vers)
__field(u32, proc)
__string(service, name)
- __string(addr, rqst->rq_xprt->xpt_remotebuf)
+ __string(addr, rqst->rq_xprt ?
+ rqst->rq_xprt->xpt_remotebuf : "(null)")
),
TP_fast_assign(
@@ -577,7 +578,8 @@ TRACE_EVENT(svc_process,
__entry->vers = rqst->rq_vers;
__entry->proc = rqst->rq_proc;
__assign_str(service, name);
- __assign_str(addr, rqst->rq_xprt->xpt_remotebuf);
+ __assign_str(addr, rqst->rq_xprt ?
+ rqst->rq_xprt->xpt_remotebuf : "(null)");
),
TP_printk("addr=%s xid=0x%08x service=%s vers=%u proc=%u",
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index d13e05f1a990..fb647bc01fc5 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1172,7 +1172,8 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
clear_bit(RQ_DROPME, &rqstp->rq_flags);
/* Setup reply header */
- rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
+ if (rqstp->rq_prot == IPPROTO_TCP)
+ svc_tcp_prep_reply_hdr(rqstp);
svc_putu32(resv, rqstp->rq_xid);
@@ -1244,7 +1245,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
* for lower versions. RPC_PROG_MISMATCH seems to be the closest
* fit.
*/
- if (versp->vs_need_cong_ctrl &&
+ if (versp->vs_need_cong_ctrl && rqstp->rq_xprt &&
!test_bit(XPT_CONG_CTRL, &rqstp->rq_xprt->xpt_flags))
goto err_bad_vers;
@@ -1336,7 +1337,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
return 0;
close:
- if (test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
+ if (rqstp->rq_xprt && test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
svc_close_xprt(rqstp->rq_xprt);
dprintk("svc: svc_process close\n");
return 0;
@@ -1459,10 +1460,10 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req,
dprintk("svc: %s(%p)\n", __func__, req);
/* Build the svc_rqst used by the common processing routine */
- rqstp->rq_xprt = serv->sv_bc_xprt;
rqstp->rq_xid = req->rq_xid;
rqstp->rq_prot = req->rq_xprt->prot;
rqstp->rq_server = serv;
+ rqstp->rq_bc_net = req->rq_xprt->xprt_net;
rqstp->rq_addrlen = sizeof(req->rq_xprt->addr);
memcpy(&rqstp->rq_addr, &req->rq_xprt->addr, rqstp->rq_addrlen);
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 51d36230b6e3..bd42da287c26 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -468,10 +468,11 @@ static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
*/
void svc_reserve(struct svc_rqst *rqstp, int space)
{
+ struct svc_xprt *xprt = rqstp->rq_xprt;
+
space += rqstp->rq_res.head[0].iov_len;
- if (space < rqstp->rq_reserved) {
- struct svc_xprt *xprt = rqstp->rq_xprt;
+ if (xprt && space < rqstp->rq_reserved) {
atomic_sub((rqstp->rq_reserved - space), &xprt->xpt_reserved);
rqstp->rq_reserved = space;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 986f3ed7d1a2..793149ba1bda 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1173,7 +1173,7 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
/*
* Setup response header. TCP has a 4B record length field.
*/
-static void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp)
+void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp)
{
struct kvec *resv = &rqstp->rq_res.head[0];
The patch below does not apply to the 4.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From c86aa7bbfd5568ba8a82d3635d8f7b8a8e06fe54 Mon Sep 17 00:00:00 2001
From: Mike Kravetz <mike.kravetz(a)oracle.com>
Date: Fri, 28 Dec 2018 00:39:42 -0800
Subject: [PATCH] hugetlbfs: Use i_mmap_rwsem to fix page fault/truncate race
hugetlbfs page faults can race with truncate and hole punch operations.
Current code in the page fault path attempts to handle this by 'backing
out' operations if we encounter the race. One obvious omission in the
current code is removing a page newly added to the page cache. This is
pretty straight forward to address, but there is a more subtle and
difficult issue of backing out hugetlb reservations. To handle this
correctly, the 'reservation state' before page allocation needs to be
noted so that it can be properly backed out. There are four distinct
possibilities for reservation state: shared/reserved, shared/no-resv,
private/reserved and private/no-resv. Backing out a reservation may
require memory allocation which could fail so that needs to be taken into
account as well.
Instead of writing the required complicated code for this rare occurrence,
just eliminate the race. i_mmap_rwsem is now held in read mode for the
duration of page fault processing. Hold i_mmap_rwsem longer in truncation
and hold punch code to cover the call to remove_inode_hugepages.
With this modification, code in remove_inode_hugepages checking for races
becomes 'dead' as it can not longer happen. Remove the dead code and
expand comments to explain reasoning. Similarly, checks for races with
truncation in the page fault path can be simplified and removed.
[mike.kravetz(a)oracle.com: incorporat suggestions from Kirill]
Link: http://lkml.kernel.org/r/20181222223013.22193-3-mike.kravetz@oracle.com
Link: http://lkml.kernel.org/r/20181218223557.5202-3-mike.kravetz@oracle.com
Fixes: ebed4bfc8da8 ("hugetlb: fix absurd HugePages_Rsvd")
Signed-off-by: Mike Kravetz <mike.kravetz(a)oracle.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com>
Cc: Michal Hocko <mhocko(a)kernel.org>
Cc: Hugh Dickins <hughd(a)google.com>
Cc: Naoya Horiguchi <n-horiguchi(a)ah.jp.nec.com>
Cc: "Aneesh Kumar K . V" <aneesh.kumar(a)linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange(a)redhat.com>
Cc: Davidlohr Bueso <dave(a)stgolabs.net>
Cc: Prakash Sangappa <prakash.sangappa(a)oracle.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org>
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 32920a10100e..a2fcea5f8225 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -383,17 +383,16 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end)
* truncation is indicated by end of range being LLONG_MAX
* In this case, we first scan the range and release found pages.
* After releasing pages, hugetlb_unreserve_pages cleans up region/reserv
- * maps and global counts. Page faults can not race with truncation
- * in this routine. hugetlb_no_page() prevents page faults in the
- * truncated range. It checks i_size before allocation, and again after
- * with the page table lock for the page held. The same lock must be
- * acquired to unmap a page.
+ * maps and global counts.
* hole punch is indicated if end is not LLONG_MAX
* In the hole punch case we scan the range and release found pages.
* Only when releasing a page is the associated region/reserv map
* deleted. The region/reserv map for ranges without associated
- * pages are not modified. Page faults can race with hole punch.
- * This is indicated if we find a mapped page.
+ * pages are not modified.
+ *
+ * Callers of this routine must hold the i_mmap_rwsem in write mode to prevent
+ * races with page faults.
+ *
* Note: If the passed end of range value is beyond the end of file, but
* not LLONG_MAX this routine still performs a hole punch operation.
*/
@@ -423,32 +422,14 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
for (i = 0; i < pagevec_count(&pvec); ++i) {
struct page *page = pvec.pages[i];
- u32 hash;
index = page->index;
- hash = hugetlb_fault_mutex_hash(h, current->mm,
- &pseudo_vma,
- mapping, index, 0);
- mutex_lock(&hugetlb_fault_mutex_table[hash]);
-
/*
- * If page is mapped, it was faulted in after being
- * unmapped in caller. Unmap (again) now after taking
- * the fault mutex. The mutex will prevent faults
- * until we finish removing the page.
- *
- * This race can only happen in the hole punch case.
- * Getting here in a truncate operation is a bug.
+ * A mapped page is impossible as callers should unmap
+ * all references before calling. And, i_mmap_rwsem
+ * prevents the creation of additional mappings.
*/
- if (unlikely(page_mapped(page))) {
- BUG_ON(truncate_op);
-
- i_mmap_lock_write(mapping);
- hugetlb_vmdelete_list(&mapping->i_mmap,
- index * pages_per_huge_page(h),
- (index + 1) * pages_per_huge_page(h));
- i_mmap_unlock_write(mapping);
- }
+ VM_BUG_ON(page_mapped(page));
lock_page(page);
/*
@@ -470,7 +451,6 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
}
unlock_page(page);
- mutex_unlock(&hugetlb_fault_mutex_table[hash]);
}
huge_pagevec_release(&pvec);
cond_resched();
@@ -482,9 +462,20 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
static void hugetlbfs_evict_inode(struct inode *inode)
{
+ struct address_space *mapping = inode->i_mapping;
struct resv_map *resv_map;
+ /*
+ * The vfs layer guarantees that there are no other users of this
+ * inode. Therefore, it would be safe to call remove_inode_hugepages
+ * without holding i_mmap_rwsem. We acquire and hold here to be
+ * consistent with other callers. Since there will be no contention
+ * on the semaphore, overhead is negligible.
+ */
+ i_mmap_lock_write(mapping);
remove_inode_hugepages(inode, 0, LLONG_MAX);
+ i_mmap_unlock_write(mapping);
+
resv_map = (struct resv_map *)inode->i_mapping->private_data;
/* root inode doesn't have the resv_map, so we should check it */
if (resv_map)
@@ -505,8 +496,8 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
i_mmap_lock_write(mapping);
if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0);
- i_mmap_unlock_write(mapping);
remove_inode_hugepages(inode, offset, LLONG_MAX);
+ i_mmap_unlock_write(mapping);
return 0;
}
@@ -540,8 +531,8 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
hugetlb_vmdelete_list(&mapping->i_mmap,
hole_start >> PAGE_SHIFT,
hole_end >> PAGE_SHIFT);
- i_mmap_unlock_write(mapping);
remove_inode_hugepages(inode, hole_start, hole_end);
+ i_mmap_unlock_write(mapping);
inode_unlock(inode);
}
@@ -624,7 +615,11 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
/* addr is the offset within the file (zero based) */
addr = index * hpage_size;
- /* mutex taken here, fault path and hole punch */
+ /*
+ * fault mutex taken here, protects against fault path
+ * and hole punch. inode_lock previously taken protects
+ * against truncation.
+ */
hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping,
index, addr);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 87fd3ab809c6..e37efd5d8318 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3755,16 +3755,16 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
}
/*
- * Use page lock to guard against racing truncation
- * before we get page_table_lock.
+ * We can not race with truncation due to holding i_mmap_rwsem.
+ * Check once here for faults beyond end of file.
*/
+ size = i_size_read(mapping->host) >> huge_page_shift(h);
+ if (idx >= size)
+ goto out;
+
retry:
page = find_lock_page(mapping, idx);
if (!page) {
- size = i_size_read(mapping->host) >> huge_page_shift(h);
- if (idx >= size)
- goto out;
-
/*
* Check for page in userfault range
*/
@@ -3854,9 +3854,6 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
}
ptl = huge_pte_lock(h, mm, ptep);
- size = i_size_read(mapping->host) >> huge_page_shift(h);
- if (idx >= size)
- goto backout;
ret = 0;
if (!huge_pte_none(huge_ptep_get(ptep)))
@@ -3959,8 +3956,10 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
/*
* Acquire i_mmap_rwsem before calling huge_pte_alloc and hold
- * until finished with ptep. This prevents huge_pmd_unshare from
- * being called elsewhere and making the ptep no longer valid.
+ * until finished with ptep. This serves two purposes:
+ * 1) It prevents huge_pmd_unshare from being called elsewhere
+ * and making the ptep no longer valid.
+ * 2) It synchronizes us with file truncation.
*
* ptep could have already be assigned via huge_pte_offset. That
* is OK, as huge_pte_alloc will return the same value unless
Hello,
We ran automated tests on a patchset that was proposed for merging into this
kernel tree. The patches were applied to:
Kernel repo: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
Commit: 8c3f48e8c288 Linux 4.20.1
The results of these automated tests are provided below.
Overall result: FAILED (see details below)
Patch merge: OK
Compile: FAILED
We attempted to compile the kernel for multiple architectures, but the compile
failed on one or more architectures:
s390x: FAILED (build log attached: build_s390.log.gz)
powerpc64le: FAILED (build log attached: build_powerpc.log.gz)
aarch64: FAILED (build log attached: build_arm64.log.gz)
x86_64: FAILED (build log attached: build_x86_64.log.gz)
We hope that these logs can help you find the problem quickly. For the full
detail on our testing procedures, please scroll to the bottom of this message.
Please reply to this email if you have any questions about the tests that we
ran or if you have any suggestions on how to make future tests more effective.
,-. ,-.
( C ) ( K ) Continuous
`-',-.`-' Kernel
( I ) Integration
`-'
______________________________________________________________________________
Merge testing
-------------
We cloned this repository and checked out a ref:
Repo: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
Ref: 8c3f48e8c288 Linux 4.20.1
We then merged the following patches with `git am`:
scsi-zfcp-fix-posting-too-many-status-read-buffers-leading-to-adapter-shutdown.patch
scsi-lpfc-do-not-set-queue-page_count-to-0-if-pc_sli4_params.wqpcnt-is-invalid.patch
fork-record-start_time-late.patch
zram-fix-double-free-backing-device.patch
hwpoison-memory_hotplug-allow-hwpoisoned-pages-to-be-offlined.patch
mm-devm_memremap_pages-mark-devm_memremap_pages-export_symbol_gpl.patch
mm-devm_memremap_pages-kill-mapping-system-ram-support.patch
mm-devm_memremap_pages-fix-shutdown-handling.patch
hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization.patch
hugetlbfs-use-i_mmap_rwsem-to-fix-page-fault-truncate-race.patch
memcg-oom-notify-on-oom-killer-invocation-from-the-charge-path.patch
sunrpc-fix-cache_head-leak-due-to-queued-request.patch
sunrpc-use-svc_net-in-svcauth_gss_-functions.patch
sunrpc-use-after-free-in-svc_process_common.patch
mm-devm_memremap_pages-add-memory_device_private-support.patch
mm-hmm-use-devm-semantics-for-hmm_devmem_-add-remove.patch
mm-hmm-replace-hmm_devmem_pages_create-with-devm_memremap_pages.patch
mm-hmm-mark-hmm_devmem_-add-add_resource-export_symbol_gpl.patch
mm-swap-fix-swapoff-with-ksm-pages.patch
Compile testing
---------------
We compiled the kernel for 4 architectures:
s390x:
make options: make INSTALL_MOD_STRIP=1 -j64 targz-pkg -j64
configuration:
powerpc64le:
make options: make INSTALL_MOD_STRIP=1 -j64 targz-pkg -j64
configuration:
aarch64:
make options: make INSTALL_MOD_STRIP=1 -j64 targz-pkg -j64
configuration:
x86_64:
make options: make INSTALL_MOD_STRIP=1 -j64 targz-pkg -j64
configuration:
Hardware testing
----------------
We booted each kernel and ran the following tests:
s390:
powerpc:
arm64:
x86_64:
While reading through the sysvipc implementation, I noticed that the n32
semctl/shmctl/msgctl system calls behave differently based on whether
o32 support is enabled or not: Without o32, the IPC_64 flag passed by
user space is rejected but calls without that flag get IPC_64 behavior.
As far as I can tell, this was inadvertently changed by a cleanup patch
but never noticed by anyone, possibly nobody has tried using sysvipc
on n32 after linux-3.19.
Change it back to the old behavior now.
Fixes: 78aaf956ba3a ("MIPS: Compat: Fix build error if CONFIG_MIPS32_COMPAT but no compat ABI.")
Cc: stable(a)vger.kernel.org
Signed-off-by: Arnd Bergmann <arnd(a)arndb.de>
---
As stated above, this was only found by inspection, the patch is not
tested. Please review accordingly.
---
arch/mips/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 787290781b8c..0d14f51d0002 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -3155,6 +3155,7 @@ config MIPS32_O32
config MIPS32_N32
bool "Kernel support for n32 binaries"
depends on 64BIT
+ select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
select COMPAT
select MIPS32_COMPAT
select SYSVIPC_COMPAT if SYSVIPC
--
2.20.0
The io_pgetevents system call was added in linux-4.18 but has
no entry for alpha:
warning: #warning syscall io_pgetevents not implemented [-Wcpp]
Assign a the next system call number here.
Cc: stable(a)vger.kernel.org
Signed-off-by: Arnd Bergmann <arnd(a)arndb.de>
---
arch/alpha/kernel/syscalls/syscall.tbl | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 7b56a53be5e3..e09558edae73 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -451,3 +451,4 @@
520 common preadv2 sys_preadv2
521 common pwritev2 sys_pwritev2
522 common statx sys_statx
+523 common io_pgetevents sys_io_pgetevents
--
2.20.0
Good day,
We have started to compile libbpf as part of our Linux compilation
build plan, however libbpf fails to cross-compile for arm64 on Linux
4.14, but succeeds on Linux 4.19 tree.
We compile libbpf with the following command:
make -C <whatever>/linux-4.14.91/tools/lib/bpf ARCH=arm64
CROSS_COMPILE=aarch64-linux-gnu- install
And get the below output on 4.14 tree:
Auto-detecting system features:
... libelf: [ on ]
... bpf: [ on ]
CC /cfsetup_build/build/arm64/libbpf/libbpf.o
CC /cfsetup_build/build/arm64/libbpf/bpf.o
LD /cfsetup_build/build/arm64/libbpf/libbpf-in.o
ld: /cfsetup_build/build/arm64/libbpf/libbpf.o: Relocations in generic
ELF (EM: 183)
ld: /cfsetup_build/build/arm64/libbpf/libbpf.o: Relocations in generic
ELF (EM: 183)
ld: /cfsetup_build/build/arm64/libbpf/libbpf.o: Relocations in generic
ELF (EM: 183)
ld: /cfsetup_build/build/arm64/libbpf/libbpf.o: Relocations in generic
ELF (EM: 183)
ld: /cfsetup_build/build/arm64/libbpf/libbpf.o: Relocations in generic
ELF (EM: 183)
ld: /cfsetup_build/build/arm64/libbpf/libbpf.o: Relocations in generic
ELF (EM: 183)
/cfsetup_build/build/arm64/libbpf/libbpf.o: error adding symbols: File
in wrong format
/cfsetup_build/build/linux-4.14.91/tools/build/Makefile.build:144:
recipe for target '/cfsetup_build/build/arm64/libbpf/libbpf-in.o'
failed
make[2]: *** [/cfsetup_build/build/arm64/libbpf/libbpf-in.o] Error 1
Makefile:158: recipe for target
'/cfsetup_build/build/arm64/libbpf/libbpf-in.o' failed
make[1]: *** [/cfsetup_build/build/arm64/libbpf/libbpf-in.o] Error 2
Backporting the following commit fixed the build:
7ed1c1901fe52e6c5828deb155920b44b0adabb1: tools: fix cross-compile var
clobbering
Can we have it officially applied to the Linux 4.14 tree, please?
Regards,
Ignat
The patch below does not apply to the 4.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From d4b09acf924b84bae77cad090a9d108e70b43643 Mon Sep 17 00:00:00 2001
From: Vasily Averin <vvs(a)virtuozzo.com>
Date: Mon, 24 Dec 2018 14:44:52 +0300
Subject: [PATCH] sunrpc: use-after-free in svc_process_common()
if node have NFSv41+ mounts inside several net namespaces
it can lead to use-after-free in svc_process_common()
svc_process_common()
/* Setup reply header */
rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp); <<< HERE
svc_process_common() can use incorrect rqstp->rq_xprt,
its caller function bc_svc_process() takes it from serv->sv_bc_xprt.
The problem is that serv is global structure but sv_bc_xprt
is assigned per-netnamespace.
According to Trond, the whole "let's set up rqstp->rq_xprt
for the back channel" is nothing but a giant hack in order
to work around the fact that svc_process_common() uses it
to find the xpt_ops, and perform a couple of (meaningless
for the back channel) tests of xpt_flags.
All we really need in svc_process_common() is to be able to run
rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr()
Bruce J Fields points that this xpo_prep_reply_hdr() call
is an awfully roundabout way just to do "svc_putnl(resv, 0);"
in the tcp case.
This patch does not initialiuze rqstp->rq_xprt in bc_svc_process(),
now it calls svc_process_common() with rqstp->rq_xprt = NULL.
To adjust reply header svc_process_common() just check
rqstp->rq_prot and calls svc_tcp_prep_reply_hdr() for tcp case.
To handle rqstp->rq_xprt = NULL case in functions called from
svc_process_common() patch intruduces net namespace pointer
svc_rqst->rq_bc_net and adjust SVC_NET() definition.
Some other function was also adopted to properly handle described case.
Signed-off-by: Vasily Averin <vvs(a)virtuozzo.com>
Cc: stable(a)vger.kernel.org
Fixes: 23c20ecd4475 ("NFS: callback up - users counting cleanup")
Signed-off-by: J. Bruce Fields <bfields(a)redhat.com>
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 73e130a840ce..fdb6b317d974 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -295,9 +295,12 @@ struct svc_rqst {
struct svc_cacherep * rq_cacherep; /* cache info */
struct task_struct *rq_task; /* service thread */
spinlock_t rq_lock; /* per-request lock */
+ struct net *rq_bc_net; /* pointer to backchannel's
+ * net namespace
+ */
};
-#define SVC_NET(svc_rqst) (svc_rqst->rq_xprt->xpt_net)
+#define SVC_NET(rqst) (rqst->rq_xprt ? rqst->rq_xprt->xpt_net : rqst->rq_bc_net)
/*
* Rigorous type checking on sockaddr type conversions
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 28e384186c35..8617f4fd6b70 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -569,7 +569,8 @@ TRACE_EVENT(svc_process,
__field(u32, vers)
__field(u32, proc)
__string(service, name)
- __string(addr, rqst->rq_xprt->xpt_remotebuf)
+ __string(addr, rqst->rq_xprt ?
+ rqst->rq_xprt->xpt_remotebuf : "(null)")
),
TP_fast_assign(
@@ -577,7 +578,8 @@ TRACE_EVENT(svc_process,
__entry->vers = rqst->rq_vers;
__entry->proc = rqst->rq_proc;
__assign_str(service, name);
- __assign_str(addr, rqst->rq_xprt->xpt_remotebuf);
+ __assign_str(addr, rqst->rq_xprt ?
+ rqst->rq_xprt->xpt_remotebuf : "(null)");
),
TP_printk("addr=%s xid=0x%08x service=%s vers=%u proc=%u",
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index d13e05f1a990..fb647bc01fc5 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1172,7 +1172,8 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
clear_bit(RQ_DROPME, &rqstp->rq_flags);
/* Setup reply header */
- rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
+ if (rqstp->rq_prot == IPPROTO_TCP)
+ svc_tcp_prep_reply_hdr(rqstp);
svc_putu32(resv, rqstp->rq_xid);
@@ -1244,7 +1245,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
* for lower versions. RPC_PROG_MISMATCH seems to be the closest
* fit.
*/
- if (versp->vs_need_cong_ctrl &&
+ if (versp->vs_need_cong_ctrl && rqstp->rq_xprt &&
!test_bit(XPT_CONG_CTRL, &rqstp->rq_xprt->xpt_flags))
goto err_bad_vers;
@@ -1336,7 +1337,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
return 0;
close:
- if (test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
+ if (rqstp->rq_xprt && test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
svc_close_xprt(rqstp->rq_xprt);
dprintk("svc: svc_process close\n");
return 0;
@@ -1459,10 +1460,10 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req,
dprintk("svc: %s(%p)\n", __func__, req);
/* Build the svc_rqst used by the common processing routine */
- rqstp->rq_xprt = serv->sv_bc_xprt;
rqstp->rq_xid = req->rq_xid;
rqstp->rq_prot = req->rq_xprt->prot;
rqstp->rq_server = serv;
+ rqstp->rq_bc_net = req->rq_xprt->xprt_net;
rqstp->rq_addrlen = sizeof(req->rq_xprt->addr);
memcpy(&rqstp->rq_addr, &req->rq_xprt->addr, rqstp->rq_addrlen);
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 51d36230b6e3..bd42da287c26 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -468,10 +468,11 @@ static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
*/
void svc_reserve(struct svc_rqst *rqstp, int space)
{
+ struct svc_xprt *xprt = rqstp->rq_xprt;
+
space += rqstp->rq_res.head[0].iov_len;
- if (space < rqstp->rq_reserved) {
- struct svc_xprt *xprt = rqstp->rq_xprt;
+ if (xprt && space < rqstp->rq_reserved) {
atomic_sub((rqstp->rq_reserved - space), &xprt->xpt_reserved);
rqstp->rq_reserved = space;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 986f3ed7d1a2..793149ba1bda 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1173,7 +1173,7 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
/*
* Setup response header. TCP has a 4B record length field.
*/
-static void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp)
+void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp)
{
struct kvec *resv = &rqstp->rq_res.head[0];