Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next

Steffen Klassert says:

====================
pull request (net-next): ipsec-next 2015-10-30

1) The flow cache is limited by the flow cache limit which
   depends on the number of cpus and the xfrm garbage collector
   threshold which is independent of the number of cpus. This
   leads to the fact that on systems with more than 16 cpus
   we hit the xfrm garbage collector limit and refuse new
   allocations, so new flows are dropped. On systems with 16
   or less cpus, we hit the flowcache limit. In this case, we
   shrink the flow cache instead of refusing new flows.

   We increase the xfrm garbage collector threshold to INT_MAX
   to get the same behaviour, independent of the number of cpus.

2) Fix some unaligned accesses on sparc systems.
   From Sowmini Varadhan.

3) Fix some header checks in _decode_session4. We may call
   pskb_may_pull with a negative value converted to unsigened
   int from pskb_may_pull. This can lead to incorrect policy
   lookups. We fix this by a check of the data pointer position
   before we call pskb_may_pull.

4) Reload skb header pointers after calling pskb_may_pull
   in _decode_session4 as this may change the pointers into
   the packet.

5) Add a missing statistic counter on inner mode errors.

Please pull or let me know if there are problems.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 49 insertions, 18 deletions

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 85752c81c5ec..05915be86235 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1216,7 +1216,8 @@ tag - INTEGER
 xfrm4_gc_thresh - INTEGER
 	The threshold at which we will start garbage collecting for IPv4
 	destination cache entries.  At twice this value the system will
-	refuse new allocations.
+	refuse new allocations. The value must be set below the flowcache
+	limit (4096 * number of online cpus) to take effect.
 
 igmp_link_local_mcast_reports - BOOLEAN
 	Enable IGMP reports for link local multicast groups in the
@@ -1662,7 +1663,8 @@ ratelimit - INTEGER
 xfrm6_gc_thresh - INTEGER
 	The threshold at which we will start garbage collecting for IPv6
 	destination cache entries.  At twice this value the system will
-	refuse new allocations.
+	refuse new allocations. The value must be set below the flowcache
+	limit (4096 * number of online cpus) to take effect.
 
 
 IPv6 Update by:
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index f2606b9056bb..1e0c3c835a63 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -127,7 +127,10 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 		case IPPROTO_DCCP:
 			if (xprth + 4 < skb->data ||
 			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
-				__be16 *ports = (__be16 *)xprth;
+				__be16 *ports;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				ports = (__be16 *)xprth;
 
 				fl4->fl4_sport = ports[!!reverse];
 				fl4->fl4_dport = ports[!reverse];
@@ -135,8 +138,12 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			break;
 
 		case IPPROTO_ICMP:
-			if (pskb_may_pull(skb, xprth + 2 - skb->data)) {
-				u8 *icmp = xprth;
+			if (xprth + 2 < skb->data ||
+			    pskb_may_pull(skb, xprth + 2 - skb->data)) {
+				u8 *icmp;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				icmp = xprth;
 
 				fl4->fl4_icmp_type = icmp[0];
 				fl4->fl4_icmp_code = icmp[1];
@@ -144,33 +151,50 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			break;
 
 		case IPPROTO_ESP:
-			if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
-				__be32 *ehdr = (__be32 *)xprth;
+			if (xprth + 4 < skb->data ||
+			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
+				__be32 *ehdr;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				ehdr = (__be32 *)xprth;
 
 				fl4->fl4_ipsec_spi = ehdr[0];
 			}
 			break;
 
 		case IPPROTO_AH:
-			if (pskb_may_pull(skb, xprth + 8 - skb->data)) {
-				__be32 *ah_hdr = (__be32 *)xprth;
+			if (xprth + 8 < skb->data ||
+			    pskb_may_pull(skb, xprth + 8 - skb->data)) {
+				__be32 *ah_hdr;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				ah_hdr = (__be32 *)xprth;
 
 				fl4->fl4_ipsec_spi = ah_hdr[1];
 			}
 			break;
 
 		case IPPROTO_COMP:
-			if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
-				__be16 *ipcomp_hdr = (__be16 *)xprth;
+			if (xprth + 4 < skb->data ||
+			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
+				__be16 *ipcomp_hdr;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				ipcomp_hdr = (__be16 *)xprth;
 
 				fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
 			}
 			break;
 
 		case IPPROTO_GRE:
-			if (pskb_may_pull(skb, xprth + 12 - skb->data)) {
-				__be16 *greflags = (__be16 *)xprth;
-				__be32 *gre_hdr = (__be32 *)xprth;
+			if (xprth + 12 < skb->data ||
+			    pskb_may_pull(skb, xprth + 12 - skb->data)) {
+				__be16 *greflags;
+				__be32 *gre_hdr;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				greflags = (__be16 *)xprth;
+				gre_hdr = (__be32 *)xprth;
 
 				if (greflags[0] & GRE_KEY) {
 					if (greflags[0] & GRE_CSUM)
@@ -244,7 +268,7 @@ static struct dst_ops xfrm4_dst_ops = {
 	.destroy =		xfrm4_dst_destroy,
 	.ifdown =		xfrm4_dst_ifdown,
 	.local_out =		__ip_local_out,
-	.gc_thresh =		32768,
+	.gc_thresh =		INT_MAX,
 };
 
 static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 2cc5840f943d..5643423fe67a 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -288,7 +288,7 @@ static struct dst_ops xfrm6_dst_ops = {
 	.destroy =		xfrm6_dst_destroy,
 	.ifdown =		xfrm6_dst_ifdown,
 	.local_out =		__ip6_local_out,
-	.gc_thresh =		32768,
+	.gc_thresh =		INT_MAX,
 };
 
 static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 60ce7014e1b0..ad7f5b3f9b61 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -330,8 +330,10 @@ resume:
 
 		if (x->sel.family == AF_UNSPEC) {
 			inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
-			if (inner_mode == NULL)
+			if (inner_mode == NULL) {
+				XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
 				goto drop;
+			}
 		}
 
 		if (inner_mode->input(x, skb)) {
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 24e06a2377f6..805681a7d356 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -31,6 +31,7 @@
 #if IS_ENABLED(CONFIG_IPV6)
 #include <linux/in6.h>
 #endif
+#include <asm/unaligned.h>
 
 static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type)
 {
@@ -728,7 +729,9 @@ static void copy_to_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p)
 	memcpy(&p->sel, &x->sel, sizeof(p->sel));
 	memcpy(&p->lft, &x->lft, sizeof(p->lft));
 	memcpy(&p->curlft, &x->curlft, sizeof(p->curlft));
-	memcpy(&p->stats, &x->stats, sizeof(p->stats));
+	put_unaligned(x->stats.replay_window, &p->stats.replay_window);
+	put_unaligned(x->stats.replay, &p->stats.replay);
+	put_unaligned(x->stats.integrity_failed, &p->stats.integrity_failed);
 	memcpy(&p->saddr, &x->props.saddr, sizeof(p->saddr));
 	p->mode = x->props.mode;
 	p->replay_window = x->props.replay_window;