[PATCH ipsec-next 0/6] xfrm: remove xfrm_state_get_afinfo conditional rcu locking

[PATCH ipsec-next 0/6] xfrm: remove xfrm_state_get_afinfo conditional rcu locking

[Florian Westphal]

xfrm_state_get_afinfo still uses a conditional locking scheme
dating back to when this still used an rwlock:

If return value is NULL, no lock (rcu readlock) was taken,
otherwise, rcu_read_unlock has to be called.

This series moves rcu read lock/unlock responsibility to the callers.

xfrm_state_put_afinfo is removed (it is equivalent
to rcu_read_unlock so thats what will be used instead).

xfrm_state_get_afinfo is renamed to xfrm_state_afinfo_get_rcu()
and is only a rcu dereference wrapper.

In one case, rcu read/unlock can be avoided as we're always
called with rcu read lock held.

[PATCH ipsec-next 1/6] xfrm: remove unused function

[Florian Westphal]

Has been ifdef'd out for more than 10 years, remove it.

Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/ipv4/xfrm4_state.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index 542074c00c78..d6660a8c0ea5 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -90,11 +90,3 @@ void __init xfrm4_state_init(void)
 {
 	xfrm_state_register_afinfo(&xfrm4_state_afinfo);
 }
-
-#if 0
-void __exit xfrm4_state_fini(void)
-{
-	xfrm_state_unregister_afinfo(&xfrm4_state_afinfo);
-}
-#endif  /*  0  */
-
-- 
2.7.3

[PATCH ipsec-next 2/6] xfrm: avoid rcu sparse warning

[Florian Westphal]

xfrm/xfrm_state.c:1973:21: error: incompatible types in comparison expression (different address spaces)

Harmless, but lets fix it to reduce the noise.

While at it, get rid of unneeded NULL check, its never hit:

net/ipv4/xfrm4_state.c: xfrm_state_register_afinfo(&xfrm4_state_afinfo);
net/ipv6/xfrm6_state.c: return xfrm_state_register_afinfo(&xfrm6_state_afinfo);
net/ipv6/xfrm6_state.c: xfrm_state_unregister_afinfo(&xfrm6_state_afinfo);

... are the only callsites.

Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/xfrm/xfrm_state.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 64e3c82eedf6..e3c15ad1b246 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1932,10 +1932,10 @@ EXPORT_SYMBOL(xfrm_unregister_km);
 int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo)
 {
 	int err = 0;
-	if (unlikely(afinfo == NULL))
-		return -EINVAL;
-	if (unlikely(afinfo->family >= NPROTO))
+
+	if (WARN_ON(afinfo->family >= NPROTO))
 		return -EAFNOSUPPORT;
+
 	spin_lock_bh(&xfrm_state_afinfo_lock);
 	if (unlikely(xfrm_state_afinfo[afinfo->family] != NULL))
 		err = -EEXIST;
@@ -1948,14 +1948,14 @@ EXPORT_SYMBOL(xfrm_state_register_afinfo);
 
 int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo)
 {
-	int err = 0;
-	if (unlikely(afinfo == NULL))
-		return -EINVAL;
-	if (unlikely(afinfo->family >= NPROTO))
+	int err = 0, family = afinfo->family;
+
+	if (WARN_ON(family >= NPROTO))
 		return -EAFNOSUPPORT;
+
 	spin_lock_bh(&xfrm_state_afinfo_lock);
 	if (likely(xfrm_state_afinfo[afinfo->family] != NULL)) {
-		if (unlikely(xfrm_state_afinfo[afinfo->family] != afinfo))
+		if (rcu_access_pointer(xfrm_state_afinfo[family]) != afinfo)
 			err = -EINVAL;
 		else
 			RCU_INIT_POINTER(xfrm_state_afinfo[afinfo->family], NULL);
-- 
2.7.3

[PATCH ipsec-next 3/6] xfrm: remove xfrm_state_put_afinfo

[Florian Westphal]

commit 44abdc3047aecafc141dfbaf1ed
("xfrm: replace rwlock on xfrm_state_afinfo with rcu") made
xfrm_state_put_afinfo equivalent to rcu_read_unlock.

Use spatch to replace it with direct calls to rcu_read_unlock:

@@
struct xfrm_state_afinfo *a;
@@

-  xfrm_state_put_afinfo(a);
+  rcu_read_unlock();

old:
 text    data     bss     dec     hex filename
22570      72     424   23066    5a1a xfrm_state.o
 1612       0       0    1612     64c xfrm_output.o
new:
22554      72     424   23050    5a0a xfrm_state.o
 1596       0       0    1596     63c xfrm_output.o

Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/xfrm.h     |  1 -
 net/xfrm/xfrm_output.c |  8 +++-----
 net/xfrm/xfrm_state.c  | 31 +++++++++++++------------------
 3 files changed, 16 insertions(+), 24 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 31947b9c21d6..957d0cc30691 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -343,7 +343,6 @@ struct xfrm_state_afinfo {
 int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo);
 int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo);
 struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family);
-void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo);
 
 struct xfrm_input_afinfo {
 	unsigned int		family;
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 637387bbaaea..8ba29fe58352 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -246,10 +246,8 @@ void xfrm_local_error(struct sk_buff *skb, int mtu)
 		return;
 
 	afinfo = xfrm_state_get_afinfo(proto);
-	if (!afinfo)
-		return;
-
-	afinfo->local_error(skb, mtu);
-	xfrm_state_put_afinfo(afinfo);
+	if (afinfo)
+		afinfo->local_error(skb, mtu);
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(xfrm_local_error);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index e3c15ad1b246..8a9ec1b80bf5 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -192,7 +192,7 @@ int xfrm_register_type(const struct xfrm_type *type, unsigned short family)
 	else
 		err = -EEXIST;
 	spin_unlock_bh(&xfrm_type_lock);
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(xfrm_register_type);
@@ -213,7 +213,7 @@ int xfrm_unregister_type(const struct xfrm_type *type, unsigned short family)
 	else
 		typemap[type->proto] = NULL;
 	spin_unlock_bh(&xfrm_type_lock);
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(xfrm_unregister_type);
@@ -235,13 +235,13 @@ static const struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family)
 	if (unlikely(type && !try_module_get(type->owner)))
 		type = NULL;
 	if (!type && !modload_attempted) {
-		xfrm_state_put_afinfo(afinfo);
+		rcu_read_unlock();
 		request_module("xfrm-type-%d-%d", family, proto);
 		modload_attempted = 1;
 		goto retry;
 	}
 
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 	return type;
 }
 
@@ -280,7 +280,7 @@ int xfrm_register_mode(struct xfrm_mode *mode, int family)
 
 out:
 	spin_unlock_bh(&xfrm_mode_lock);
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(xfrm_register_mode);
@@ -308,7 +308,7 @@ int xfrm_unregister_mode(struct xfrm_mode *mode, int family)
 	}
 
 	spin_unlock_bh(&xfrm_mode_lock);
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(xfrm_unregister_mode);
@@ -331,13 +331,13 @@ static struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family)
 	if (unlikely(mode && !try_module_get(mode->owner)))
 		mode = NULL;
 	if (!mode && !modload_attempted) {
-		xfrm_state_put_afinfo(afinfo);
+		rcu_read_unlock();
 		request_module("xfrm-mode-%d-%d", family, encap);
 		modload_attempted = 1;
 		goto retry;
 	}
 
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 	return mode;
 }
 
@@ -651,13 +651,13 @@ xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl,
 	afinfo->init_tempsel(&x->sel, fl);
 
 	if (family != tmpl->encap_family) {
-		xfrm_state_put_afinfo(afinfo);
+		rcu_read_unlock();
 		afinfo = xfrm_state_get_afinfo(tmpl->encap_family);
 		if (!afinfo)
 			return -1;
 	}
 	afinfo->init_temprop(x, tmpl, daddr, saddr);
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 	return 0;
 }
 
@@ -1474,7 +1474,7 @@ xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n,
 	if (afinfo->tmpl_sort)
 		err = afinfo->tmpl_sort(dst, src, n);
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(xfrm_tmpl_sort);
@@ -1494,7 +1494,7 @@ xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
 	if (afinfo->state_sort)
 		err = afinfo->state_sort(dst, src, n);
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(xfrm_state_sort);
@@ -1978,11 +1978,6 @@ struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family)
 	return afinfo;
 }
 
-void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo)
-{
-	rcu_read_unlock();
-}
-
 /* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */
 void xfrm_state_delete_tunnel(struct xfrm_state *x)
 {
@@ -2028,7 +2023,7 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay)
 	if (afinfo->init_flags)
 		err = afinfo->init_flags(x);
 
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 
 	if (err)
 		goto error;
-- 
2.7.3

[PATCH ipsec-next 4/6] xfrm: add and use xfrm_state_afinfo_get_rcu

[Florian Westphal]

xfrm_init_tempstate is always called from within rcu read side section.
We can thus use a simpler function that doesn't call rcu_read_lock
again.

While at it, also make xfrm_init_tempstate return value void, the
return value was never tested.

A followup patch will replace remaining callers of xfrm_state_get_afinfo
with xfrm_state_afinfo_get_rcu variant and then remove the 'old'
get_afinfo interface.

Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/xfrm.h    |  1 +
 net/xfrm/xfrm_state.c | 25 +++++++++++++++----------
 2 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 957d0cc30691..c52197cf51dc 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -343,6 +343,7 @@ struct xfrm_state_afinfo {
 int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo);
 int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo);
 struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family);
+struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family);
 
 struct xfrm_input_afinfo {
 	unsigned int		family;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 8a9ec1b80bf5..ee1309e2b8b5 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -639,26 +639,23 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si)
 }
 EXPORT_SYMBOL(xfrm_sad_getinfo);
 
-static int
+static void
 xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl,
 		    const struct xfrm_tmpl *tmpl,
 		    const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 		    unsigned short family)
 {
-	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
-	if (!afinfo)
-		return -1;
-	afinfo->init_tempsel(&x->sel, fl);
+	struct xfrm_state_afinfo *afinfo = xfrm_state_afinfo_get_rcu(family);
+
+	if (afinfo)
+		afinfo->init_tempsel(&x->sel, fl);
 
 	if (family != tmpl->encap_family) {
-		rcu_read_unlock();
-		afinfo = xfrm_state_get_afinfo(tmpl->encap_family);
+		afinfo = xfrm_state_afinfo_get_rcu(tmpl->encap_family);
 		if (!afinfo)
-			return -1;
+			return;
 	}
 	afinfo->init_temprop(x, tmpl, daddr, saddr);
-	rcu_read_unlock();
-	return 0;
 }
 
 static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark,
@@ -1966,6 +1963,14 @@ int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo)
 }
 EXPORT_SYMBOL(xfrm_state_unregister_afinfo);
 
+struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family)
+{
+	if (unlikely(family >= NPROTO))
+		return NULL;
+
+	return rcu_dereference(xfrm_state_afinfo[family]);
+}
+
 struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family)
 {
 	struct xfrm_state_afinfo *afinfo;
-- 
2.7.3

[PATCH ipsec-next 5/6] xfrm: state: simplify rcu_read_unlock handling in two spots

[Florian Westphal]

Instead of:
  if (foo) {
      unlock();
      return bar();
   }
   unlock();
do:
   unlock();
   if (foo)
       return bar();

This is ok because rcu protected structure is only dereferenced before
the conditional.

Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/xfrm/xfrm_state.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index ee1309e2b8b5..0245df063bd7 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -231,17 +231,18 @@ static const struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family)
 		return NULL;
 	typemap = afinfo->type_map;
 
-	type = typemap[proto];
+	type = READ_ONCE(typemap[proto]);
 	if (unlikely(type && !try_module_get(type->owner)))
 		type = NULL;
+
+	rcu_read_unlock();
+
 	if (!type && !modload_attempted) {
-		rcu_read_unlock();
 		request_module("xfrm-type-%d-%d", family, proto);
 		modload_attempted = 1;
 		goto retry;
 	}
 
-	rcu_read_unlock();
 	return type;
 }
 
@@ -327,17 +328,17 @@ static struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family)
 	if (unlikely(afinfo == NULL))
 		return NULL;
 
-	mode = afinfo->mode_map[encap];
+	mode = READ_ONCE(afinfo->mode_map[encap]);
 	if (unlikely(mode && !try_module_get(mode->owner)))
 		mode = NULL;
+
+	rcu_read_unlock();
 	if (!mode && !modload_attempted) {
-		rcu_read_unlock();
 		request_module("xfrm-mode-%d-%d", family, encap);
 		modload_attempted = 1;
 		goto retry;
 	}
 
-	rcu_read_unlock();
 	return mode;
 }
 
-- 
2.7.3

[PATCH ipsec-next 6/6] xfrm: remove xfrm_state_get_afinfo

[Florian Westphal]

Use xfrm_state_afinfo_get_rcu() everywhere, this also moves
rcu read (un)lock responsibility to the callers.

This avoids the conditional locking scheme we currently have.

Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/xfrm.h     |  1 -
 net/xfrm/xfrm_output.c |  3 +-
 net/xfrm/xfrm_state.c  | 97 +++++++++++++++++++++++++++++++-------------------
 3 files changed, 62 insertions(+), 39 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index c52197cf51dc..d81e153bfeee 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -342,7 +342,6 @@ struct xfrm_state_afinfo {
 
 int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo);
 int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo);
-struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family);
 struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family);
 
 struct xfrm_input_afinfo {
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 8ba29fe58352..351efd207d88 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -245,7 +245,8 @@ void xfrm_local_error(struct sk_buff *skb, int mtu)
 	else
 		return;
 
-	afinfo = xfrm_state_get_afinfo(proto);
+	rcu_read_lock();
+	afinfo = xfrm_state_afinfo_get_rcu(proto);
 	if (afinfo)
 		afinfo->local_error(skb, mtu);
 	rcu_read_unlock();
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 0245df063bd7..1a7f0c0ec3bd 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -178,12 +178,17 @@ void km_state_expired(struct xfrm_state *x, int hard, u32 portid);
 static DEFINE_SPINLOCK(xfrm_type_lock);
 int xfrm_register_type(const struct xfrm_type *type, unsigned short family)
 {
-	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
+	struct xfrm_state_afinfo *afinfo;
 	const struct xfrm_type **typemap;
 	int err = 0;
 
-	if (unlikely(afinfo == NULL))
+	rcu_read_lock();
+
+	afinfo = xfrm_state_afinfo_get_rcu(family);
+	if (!afinfo) {
+		rcu_read_unlock();
 		return -EAFNOSUPPORT;
+	}
 	typemap = afinfo->type_map;
 	spin_lock_bh(&xfrm_type_lock);
 
@@ -199,12 +204,17 @@ EXPORT_SYMBOL(xfrm_register_type);
 
 int xfrm_unregister_type(const struct xfrm_type *type, unsigned short family)
 {
-	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
+	struct xfrm_state_afinfo *afinfo;
 	const struct xfrm_type **typemap;
 	int err = 0;
 
-	if (unlikely(afinfo == NULL))
+	rcu_read_lock();
+
+	afinfo = xfrm_state_afinfo_get_rcu(family);
+	if (!afinfo) {
+		rcu_read_unlock();
 		return -EAFNOSUPPORT;
+	}
 	typemap = afinfo->type_map;
 	spin_lock_bh(&xfrm_type_lock);
 
@@ -226,9 +236,13 @@ static const struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family)
 	int modload_attempted = 0;
 
 retry:
-	afinfo = xfrm_state_get_afinfo(family);
-	if (unlikely(afinfo == NULL))
+	rcu_read_lock();
+	afinfo = xfrm_state_afinfo_get_rcu(family);
+	if (unlikely(!afinfo)) {
+		rcu_read_unlock();
 		return NULL;
+	}
+
 	typemap = afinfo->type_map;
 
 	type = READ_ONCE(typemap[proto]);
@@ -261,9 +275,12 @@ int xfrm_register_mode(struct xfrm_mode *mode, int family)
 	if (unlikely(mode->encap >= XFRM_MODE_MAX))
 		return -EINVAL;
 
-	afinfo = xfrm_state_get_afinfo(family);
-	if (unlikely(afinfo == NULL))
+	rcu_read_lock();
+	afinfo = xfrm_state_afinfo_get_rcu(family);
+	if (!afinfo) {
+		rcu_read_unlock();
 		return -EAFNOSUPPORT;
+	}
 
 	err = -EEXIST;
 	modemap = afinfo->mode_map;
@@ -295,9 +312,12 @@ int xfrm_unregister_mode(struct xfrm_mode *mode, int family)
 	if (unlikely(mode->encap >= XFRM_MODE_MAX))
 		return -EINVAL;
 
-	afinfo = xfrm_state_get_afinfo(family);
-	if (unlikely(afinfo == NULL))
+	rcu_read_lock();
+	afinfo = xfrm_state_afinfo_get_rcu(family);
+	if (!afinfo) {
+		rcu_read_unlock();
 		return -EAFNOSUPPORT;
+	}
 
 	err = -ENOENT;
 	modemap = afinfo->mode_map;
@@ -322,17 +342,21 @@ static struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family)
 
 	if (unlikely(encap >= XFRM_MODE_MAX))
 		return NULL;
-
 retry:
-	afinfo = xfrm_state_get_afinfo(family);
-	if (unlikely(afinfo == NULL))
+	rcu_read_lock();
+
+	afinfo = xfrm_state_afinfo_get_rcu(family);
+	if (unlikely(!afinfo)) {
+		rcu_read_unlock();
 		return NULL;
+	}
 
 	mode = READ_ONCE(afinfo->mode_map[encap]);
 	if (unlikely(mode && !try_module_get(mode->owner)))
 		mode = NULL;
 
 	rcu_read_unlock();
+
 	if (!mode && !modload_attempted) {
 		request_module("xfrm-mode-%d-%d", family, encap);
 		modload_attempted = 1;
@@ -1463,15 +1487,21 @@ int
 xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n,
 	       unsigned short family, struct net *net)
 {
-	int err = 0;
-	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
+	struct xfrm_state_afinfo *afinfo;
+	int err = -EAFNOSUPPORT;
+
+	rcu_read_lock();
+
+	afinfo = xfrm_state_afinfo_get_rcu(family);
 	if (!afinfo)
-		return -EAFNOSUPPORT;
+		goto error;
 
+	err = 0;
 	spin_lock_bh(&net->xfrm.xfrm_state_lock); /*FIXME*/
 	if (afinfo->tmpl_sort)
 		err = afinfo->tmpl_sort(dst, src, n);
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+error:
 	rcu_read_unlock();
 	return err;
 }
@@ -1481,17 +1511,20 @@ int
 xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
 		unsigned short family)
 {
-	int err = 0;
-	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
+	struct xfrm_state_afinfo *afinfo;
 	struct net *net = xs_net(*src);
+	int err = -EAFNOSUPPORT;
 
+	afinfo = xfrm_state_afinfo_get_rcu(family);
 	if (!afinfo)
-		return -EAFNOSUPPORT;
+		goto error;
 
+	err = 0;
 	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	if (afinfo->state_sort)
 		err = afinfo->state_sort(dst, src, n);
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+error:
 	rcu_read_unlock();
 	return err;
 }
@@ -1972,18 +2005,6 @@ struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family)
 	return rcu_dereference(xfrm_state_afinfo[family]);
 }
 
-struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family)
-{
-	struct xfrm_state_afinfo *afinfo;
-	if (unlikely(family >= NPROTO))
-		return NULL;
-	rcu_read_lock();
-	afinfo = rcu_dereference(xfrm_state_afinfo[family]);
-	if (unlikely(!afinfo))
-		rcu_read_unlock();
-	return afinfo;
-}
-
 /* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */
 void xfrm_state_delete_tunnel(struct xfrm_state *x)
 {
@@ -2018,14 +2039,16 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay)
 	struct xfrm_state_afinfo *afinfo;
 	struct xfrm_mode *inner_mode;
 	int family = x->props.family;
-	int err;
+	int err = 0;
 
-	err = -EAFNOSUPPORT;
-	afinfo = xfrm_state_get_afinfo(family);
-	if (!afinfo)
-		goto error;
+	rcu_read_lock();
+
+	afinfo = xfrm_state_afinfo_get_rcu(family);
+	if (!afinfo) {
+		rcu_read_unlock();
+		return -EAFNOSUPPORT;
+	}
 
-	err = 0;
 	if (afinfo->init_flags)
 		err = afinfo->init_flags(x);
 
-- 
2.7.3

Re: [PATCH ipsec-next 0/6] xfrm: remove xfrm_state_get_afinfo conditional rcu locking

[Steffen Klassert]

On Mon, Jan 09, 2017 at 02:20:44PM +0100, Florian Westphal wrote:
> xfrm_state_get_afinfo still uses a conditional locking scheme
> dating back to when this still used an rwlock:
> 
> If return value is NULL, no lock (rcu readlock) was taken,
> otherwise, rcu_read_unlock has to be called.
> 
> This series moves rcu read lock/unlock responsibility to the callers.
> 
> xfrm_state_put_afinfo is removed (it is equivalent
> to rcu_read_unlock so thats what will be used instead).
> 
> xfrm_state_get_afinfo is renamed to xfrm_state_afinfo_get_rcu()
> and is only a rcu dereference wrapper.
> 
> In one case, rcu read/unlock can be avoided as we're always
> called with rcu read lock held.

All applied to ipsec-next, thanks a lot!