| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <28452040.xEi3pLPik0@sifl>
Date: Tue, 09 Apr 2013 09:19:30 -0400
From: Paul Moore <pmoore@...hat.com>
To: Casey Schaufler <casey@...aufler-ca.com>
Cc: Eric Dumazet <eric.dumazet@...il.com>,
David Miller <davem@...emloft.net>, netdev@...r.kernel.org,
mvadkert@...hat.com, selinux@...ho.nsa.gov,
linux-security-module@...r.kernel.org
Subject: Re: [PATCH] tcp: assign the sock correctly to an outgoing SYNACK packet
On Monday, April 08, 2013 06:24:59 PM Casey Schaufler wrote:
> On 4/8/2013 6:09 PM, Eric Dumazet wrote:
> > On Mon, 2013-04-08 at 17:59 -0700, Casey Schaufler wrote:
> >> I don't see that with adding 4 bytes. Again, I'm willing to be
> >> educated if I'm wrong.
> >
> > Feel free to add 4 bytes without having the 'align to 8 bytes' problem
> > on 64 bit arches. Show us your patch.
>
> Recall that it's replacing an existing 4 byte value with an 8 byte value.
> My compiler days were quite short and long ago, but it would seem that
> an 8 byte value ought not have an 'align to 8 bytes' problem.
>
> Again, I'm willing to be educated.
Armed with a cup of coffee I took a look at the sk_buff structure this morning
with the pahole tool and using the current sk_buff if we turn on all the
#ifdefs here is what I see on x86_64:
struct sk_buff {
struct sk_buff * next; /* 0 8 */
struct sk_buff * prev; /* 8 8 */
ktime_t tstamp; /* 16 8 */
struct sock * sk; /* 24 8 */
struct net_device * dev; /* 32 8 */
char cb[48]; /* 40 48 */
/* --- cacheline 1 boundary (64 bytes) was 24 bytes ago --- */
long unsigned int _skb_refdst; /* 88 8 */
struct sec_path * sp; /* 96 8 */
unsigned int len; /* 104 4 */
unsigned int data_len; /* 108 4 */
__u16 mac_len; /* 112 2 */
__u16 hdr_len; /* 114 2 */
union {
__wsum csum; /* 4 */
struct {
__u16 csum_start; /* 116 2 */
__u16 csum_offset; /* 118 2 */
}; /* 4 */
}; /* 116 4 */
__u32 priority; /* 120 4 */
int flags1_begin[0]; /* 124 0 */
__u8 local_df:1; /* 124: 7 1 */
__u8 cloned:1; /* 124: 6 1 */
__u8 ip_summed:2; /* 124: 4 1 */
__u8 nohdr:1; /* 124: 3 1 */
__u8 nfctinfo:3; /* 124: 0 1 */
__u8 pkt_type:3; /* 125: 5 1 */
__u8 fclone:2; /* 125: 3 1 */
__u8 ipvs_property:1; /* 125: 2 1 */
__u8 peeked:1; /* 125: 1 1 */
__u8 nf_trace:1; /* 125: 0 1 */
/* XXX 2 bytes hole, try to pack */
/* --- cacheline 2 boundary (128 bytes) --- */
int flags1_end[0]; /* 128 0 */
__be16 protocol; /* 128 2 */
/* XXX 6 bytes hole, try to pack */
void (*destructor)(struct sk_buff *); /* 136
8 */
struct nf_conntrack * nfct; /* 144 8 */
struct sk_buff * nfct_reasm; /* 152 8 */
struct nf_bridge_info * nf_bridge; /* 160 8 */
int skb_iif; /* 168 4 */
__u32 rxhash; /* 172 4 */
__u16 vlan_tci; /* 176 2 */
__u16 tc_index; /* 178 2 */
__u16 tc_verd; /* 180 2 */
__u16 queue_mapping; /* 182 2 */
int flags2_begin[0]; /* 184 0 */
__u8 ndisc_nodetype:2; /* 184: 6 1 */
__u8 pfmemalloc:1; /* 184: 5 1 */
__u8 ooo_okay:1; /* 184: 4 1 */
__u8 l4_rxhash:1; /* 184: 3 1 */
__u8 wifi_acked_valid:1; /* 184: 2 1 */
__u8 wifi_acked:1; /* 184: 1 1 */
__u8 no_fcs:1; /* 184: 0 1 */
__u8 head_frag:1; /* 185: 7 1 */
__u8 encapsulation:1; /* 185: 6 1 */
/* XXX 6 bits hole, try to pack */
/* XXX 2 bytes hole, try to pack */
int flags2_end[0]; /* 188 0 */
dma_cookie_t dma_cookie; /* 188 4 */
/* --- cacheline 3 boundary (192 bytes) --- */
__u32 secmark; /* 192 4 */
union {
__u32 mark; /* 4 */
__u32 dropcount; /* 4 */
__u32 reserved_tailroom; /* 4 */
}; /* 196 4 */
sk_buff_data_t inner_transport_header; /* 200 8 */
sk_buff_data_t inner_network_header; /* 208 8 */
sk_buff_data_t transport_header; /* 216 8 */
sk_buff_data_t network_header; /* 224 8 */
sk_buff_data_t mac_header; /* 232 8 */
sk_buff_data_t tail; /* 240 8 */
sk_buff_data_t end; /* 248 8 */
/* --- cacheline 4 boundary (256 bytes) --- */
unsigned char * head; /* 256 8 */
unsigned char * data; /* 264 8 */
unsigned int truesize; /* 272 4 */
atomic_t users; /* 276 4 */
/* size: 280, cachelines: 5, members: 62 */
/* sum members: 270, holes: 3, sum holes: 10 */
/* bit holes: 1, sum bit holes: 6 bits */
/* last cacheline: 24 bytes */
};
It looks like there some holes we might be able to capitalize on. If we
remove "secmark" (we can handle it inside a security blob) and move "protocol"
to after the flags2 bit field we can make an aligned 8 byte hold for a
security blob before "destructor". According to pahole the structure size
stays the same and the only field which moves to a different cacheline is
"dma_cookie" which moves from cacheline 2 to 3. Here is the pahole output:
struct sk_buff_test {
struct sk_buff * next; /* 0 8 */
struct sk_buff * prev; /* 8 8 */
ktime_t tstamp; /* 16 8 */
struct sock * sk; /* 24 8 */
struct net_device * dev; /* 32 8 */
char cb[48]; /* 40 48 */
/* --- cacheline 1 boundary (64 bytes) was 24 bytes ago --- */
long unsigned int _skb_refdst; /* 88 8 */
struct sec_path * sp; /* 96 8 */
unsigned int len; /* 104 4 */
unsigned int data_len; /* 108 4 */
__u16 mac_len; /* 112 2 */
__u16 hdr_len; /* 114 2 */
union {
__wsum csum; /* 4 */
struct {
__u16 csum_start; /* 116 2 */
__u16 csum_offset; /* 118 2 */
}; /* 4 */
}; /* 116 4 */
__u32 priority; /* 120 4 */
int flags1_begin[0]; /* 124 0 */
__u8 local_df:1; /* 124: 7 1 */
__u8 cloned:1; /* 124: 6 1 */
__u8 ip_summed:2; /* 124: 4 1 */
__u8 nohdr:1; /* 124: 3 1 */
__u8 nfctinfo:3; /* 124: 0 1 */
__u8 pkt_type:3; /* 125: 5 1 */
__u8 fclone:2; /* 125: 3 1 */
__u8 ipvs_property:1; /* 125: 2 1 */
__u8 peeked:1; /* 125: 1 1 */
__u8 nf_trace:1; /* 125: 0 1 */
/* XXX 2 bytes hole, try to pack */
/* --- cacheline 2 boundary (128 bytes) --- */
int flags1_end[0]; /* 128 0 */
void * security; /* 128 8 */
void (*destructor)(struct sk_buff *); /* 136
8 */
struct nf_conntrack * nfct; /* 144 8 */
struct sk_buff * nfct_reasm; /* 152 8 */
struct nf_bridge_info * nf_bridge; /* 160 8 */
int skb_iif; /* 168 4 */
__u32 rxhash; /* 172 4 */
__u16 vlan_tci; /* 176 2 */
__u16 tc_index; /* 178 2 */
__u16 tc_verd; /* 180 2 */
__u16 queue_mapping; /* 182 2 */
int flags2_begin[0]; /* 184 0 */
__u8 ndisc_nodetype:2; /* 184: 6 1 */
__u8 pfmemalloc:1; /* 184: 5 1 */
__u8 ooo_okay:1; /* 184: 4 1 */
__u8 l4_rxhash:1; /* 184: 3 1 */
__u8 wifi_acked_valid:1; /* 184: 2 1 */
__u8 wifi_acked:1; /* 184: 1 1 */
__u8 no_fcs:1; /* 184: 0 1 */
__u8 head_frag:1; /* 185: 7 1 */
__u8 encapsulation:1; /* 185: 6 1 */
/* XXX 6 bits hole, try to pack */
/* XXX 2 bytes hole, try to pack */
int flags2_end[0]; /* 188 0 */
__be16 protocol; /* 188 2 */
/* XXX 2 bytes hole, try to pack */
/* --- cacheline 3 boundary (192 bytes) --- */
dma_cookie_t dma_cookie; /* 192 4 */
union {
__u32 mark; /* 4 */
__u32 dropcount; /* 4 */
__u32 reserved_tailroom; /* 4 */
}; /* 196 4 */
sk_buff_data_t inner_transport_header; /* 200 8 */
sk_buff_data_t inner_network_header; /* 208 8 */
sk_buff_data_t transport_header; /* 216 8 */
sk_buff_data_t network_header; /* 224 8 */
sk_buff_data_t mac_header; /* 232 8 */
sk_buff_data_t tail; /* 240 8 */
sk_buff_data_t end; /* 248 8 */
/* --- cacheline 4 boundary (256 bytes) --- */
unsigned char * head; /* 256 8 */
unsigned char * data; /* 264 8 */
unsigned int truesize; /* 272 4 */
atomic_t users; /* 276 4 */
/* size: 280, cachelines: 5, members: 62 */
/* sum members: 274, holes: 3, sum holes: 6 */
/* bit holes: 1, sum bit holes: 6 bits */
/* last cacheline: 24 bytes */
};
As Casey already mentioned, if this isn't acceptable please help me understand
why.
--
paul moore
security and virtualization @ redhat
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists