[PATCH 3.2 010/152] ipv6: mld: fix add_grhead skb_over_panic for devs with large MTUs

[Ben Hutchings <ben@decadent.org.uk>]

3.2.67-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Daniel Borkmann <dborkman@redhat.com>

commit 4c672e4b42bc8046d63a6eb0a2c6a450a501af32 upstream.

It has been reported that generating an MLD listener report on
devices with large MTUs (e.g. 9000) and a high number of IPv6
addresses can trigger a skb_over_panic():

skbuff: skb_over_panic: text:ffffffff80612a5d len:3776 put:20
head:ffff88046d751000 data:ffff88046d751010 tail:0xed0 end:0xec0
dev:port1
 ------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:100!
invalid opcode: 0000 [#1] SMP
Modules linked in: ixgbe(O)
CPU: 3 PID: 0 Comm: swapper/3 Tainted: G O 3.14.23+ #4
[...]
Call Trace:
 <IRQ>
 [<ffffffff80578226>] ? skb_put+0x3a/0x3b
 [<ffffffff80612a5d>] ? add_grhead+0x45/0x8e
 [<ffffffff80612e3a>] ? add_grec+0x394/0x3d4
 [<ffffffff80613222>] ? mld_ifc_timer_expire+0x195/0x20d
 [<ffffffff8061308d>] ? mld_dad_timer_expire+0x45/0x45
 [<ffffffff80255b5d>] ? call_timer_fn.isra.29+0x12/0x68
 [<ffffffff80255d16>] ? run_timer_softirq+0x163/0x182
 [<ffffffff80250e6f>] ? __do_softirq+0xe0/0x21d
 [<ffffffff8025112b>] ? irq_exit+0x4e/0xd3
 [<ffffffff802214bb>] ? smp_apic_timer_interrupt+0x3b/0x46
 [<ffffffff8063f10a>] ? apic_timer_interrupt+0x6a/0x70

mld_newpack() skb allocations are usually requested with dev->mtu
in size, since commit 72e09ad107e7 ("ipv6: avoid high order allocations")
we have changed the limit in order to be less likely to fail.

However, in MLD/IGMP code, we have some rather ugly AVAILABLE(skb)
macros, which determine if we may end up doing an skb_put() for
adding another record. To avoid possible fragmentation, we check
the skb's tailroom as skb->dev->mtu - skb->len, which is a wrong
assumption as the actual max allocation size can be much smaller.

The IGMP case doesn't have this issue as commit 57e1ab6eaddc
("igmp: refine skb allocations") stores the allocation size in
the cb[].

Set a reserved_tailroom to make it fit into the MTU and use
skb_availroom() helper instead. This also allows to get rid of
igmp_skb_size().

Reported-by: Wei Liu <lw1a2.jing@gmail.com>
Fixes: 72e09ad107e7 ("ipv6: avoid high order allocations")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Cc: David L Stevens <david.stevens@oracle.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
[bwh: Backported to 3.2: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 net/ipv4/igmp.c  | 11 +++++------
 net/ipv6/mcast.c |  9 +++++----
 2 files changed, 10 insertions(+), 10 deletions(-)

--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -294,9 +294,7 @@ igmp_scount(struct ip_mc_list *pmc, int
 	return scount;
 }
 
-#define igmp_skb_size(skb) (*(unsigned int *)((skb)->cb))
-
-static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
+static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 {
 	struct sk_buff *skb;
 	struct rtable *rt;
@@ -306,6 +304,7 @@ static struct sk_buff *igmpv3_newpack(st
 	struct flowi4 fl4;
 	int hlen = LL_RESERVED_SPACE(dev);
 	int tlen = dev->needed_tailroom;
+	unsigned int size = mtu;
 
 	while (1) {
 		skb = alloc_skb(size + hlen + tlen,
@@ -316,7 +315,6 @@ static struct sk_buff *igmpv3_newpack(st
 		if (size < 256)
 			return NULL;
 	}
-	igmp_skb_size(skb) = size;
 
 	rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0,
 				   0, 0,
@@ -329,6 +327,8 @@ static struct sk_buff *igmpv3_newpack(st
 	skb_dst_set(skb, &rt->dst);
 	skb->dev = dev;
 
+	skb->reserved_tailroom = skb_end_offset(skb) -
+				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
 
 	skb_reset_network_header(skb);
@@ -398,8 +398,7 @@ static struct sk_buff *add_grhead(struct
 	return skb;
 }
 
-#define AVAILABLE(skb) ((skb) ? ((skb)->dev ? igmp_skb_size(skb) - (skb)->len : \
-	skb_tailroom(skb)) : 0)
+#define AVAILABLE(skb)	((skb) ? skb_availroom(skb) : 0)
 
 static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
 	int type, int gdeleted, int sdeleted)
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1334,7 +1334,7 @@ mld_scount(struct ifmcaddr6 *pmc, int ty
 	return scount;
 }
 
-static struct sk_buff *mld_newpack(struct inet6_dev *idev, int size)
+static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu)
 {
 	struct net_device *dev = idev->dev;
 	struct net *net = dev_net(dev);
@@ -1345,13 +1345,13 @@ static struct sk_buff *mld_newpack(struc
 	const struct in6_addr *saddr;
 	int hlen = LL_RESERVED_SPACE(dev);
 	int tlen = dev->needed_tailroom;
+	unsigned int size = mtu + hlen + tlen;
 	int err;
 	u8 ra[8] = { IPPROTO_ICMPV6, 0,
 		     IPV6_TLV_ROUTERALERT, 2, 0, 0,
 		     IPV6_TLV_PADN, 0 };
 
 	/* we assume size > sizeof(ra) here */
-	size += hlen + tlen;
 	/* limit our allocations to order-0 page */
 	size = min_t(int, size, SKB_MAX_ORDER(0, 0));
 	skb = sock_alloc_send_skb(sk, size, 1, &err);
@@ -1359,6 +1359,8 @@ static struct sk_buff *mld_newpack(struc
 	if (!skb)
 		return NULL;
 
+	skb->reserved_tailroom = skb_end_offset(skb) -
+				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
 
 	if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) {
@@ -1479,8 +1481,7 @@ static struct sk_buff *add_grhead(struct
 	return skb;
 }
 
-#define AVAILABLE(skb) ((skb) ? ((skb)->dev ? (skb)->dev->mtu - (skb)->len : \
-	skb_tailroom(skb)) : 0)
+#define AVAILABLE(skb)	((skb) ? skb_availroom(skb) : 0)
 
 static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 	int type, int gdeleted, int sdeleted)