| 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: <20241203124945.22508-3-justin.iurman@uliege.be>
Date: Tue, 3 Dec 2024 13:49:43 +0100
From: Justin Iurman <justin.iurman@...ege.be>
To: netdev@...r.kernel.org
Cc: davem@...emloft.net,
dsahern@...nel.org,
edumazet@...gle.com,
kuba@...nel.org,
pabeni@...hat.com,
horms@...nel.org,
linux-kernel@...r.kernel.org,
justin.iurman@...ege.be
Subject: [RESEND PATCH net-next v5 2/4] net: ipv6: ioam6_iptunnel: mitigate 2-realloc issue
This patch mitigates the two-reallocations issue with ioam6_iptunnel by
providing the dst_entry (in the cache) to the first call to
skb_cow_head(). As a result, the very first iteration may still trigger
two reallocations (i.e., empty cache), while next iterations would only
trigger a single reallocation.
Performance tests before/after applying this patch, which clearly shows
the improvement:
- inline mode:
- before: https://ibb.co/LhQ8V63
- after: https://ibb.co/x5YT2bS
- encap mode:
- before: https://ibb.co/3Cjm5m0
- after: https://ibb.co/TwpsxTC
- encap mode with tunsrc:
- before: https://ibb.co/Gpy9QPg
- after: https://ibb.co/PW1bZFT
This patch also fixes an incorrect behavior: after the insertion, the
second call to skb_cow_head() makes sure that the dev has enough
headroom in the skb for layer 2 and stuff. In that case, the "old"
dst_entry was used, which is now fixed. After discussing with Paolo, it
appears that both patches can be merged into a single one -this one-
(for the sake of readability) and target net-next.
Signed-off-by: Justin Iurman <justin.iurman@...ege.be>
---
net/ipv6/ioam6_iptunnel.c | 73 ++++++++++++++++++++-------------------
1 file changed, 37 insertions(+), 36 deletions(-)
diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index 9d8422e350f8..28e5a89dc255 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -253,14 +253,15 @@ static int ioam6_do_fill(struct net *net, struct sk_buff *skb)
}
static int ioam6_do_inline(struct net *net, struct sk_buff *skb,
- struct ioam6_lwt_encap *tuninfo)
+ struct ioam6_lwt_encap *tuninfo,
+ struct dst_entry *cache_dst)
{
struct ipv6hdr *oldhdr, *hdr;
int hdrlen, err;
hdrlen = (tuninfo->eh.hdrlen + 1) << 3;
- err = skb_cow_head(skb, hdrlen + skb->mac_len);
+ err = skb_cow_head(skb, hdrlen + dst_dev_overhead(cache_dst, skb));
if (unlikely(err))
return err;
@@ -291,7 +292,8 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
struct ioam6_lwt_encap *tuninfo,
bool has_tunsrc,
struct in6_addr *tunsrc,
- struct in6_addr *tundst)
+ struct in6_addr *tundst,
+ struct dst_entry *cache_dst)
{
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *hdr, *inner_hdr;
@@ -300,7 +302,7 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
hdrlen = (tuninfo->eh.hdrlen + 1) << 3;
len = sizeof(*hdr) + hdrlen;
- err = skb_cow_head(skb, len + skb->mac_len);
+ err = skb_cow_head(skb, len + dst_dev_overhead(cache_dst, skb));
if (unlikely(err))
return err;
@@ -334,7 +336,7 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct dst_entry *dst = skb_dst(skb);
+ struct dst_entry *dst = skb_dst(skb), *cache_dst;
struct in6_addr orig_daddr;
struct ioam6_lwt *ilwt;
int err = -EINVAL;
@@ -352,6 +354,10 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
orig_daddr = ipv6_hdr(skb)->daddr;
+ local_bh_disable();
+ cache_dst = dst_cache_get(&ilwt->cache);
+ local_bh_enable();
+
switch (ilwt->mode) {
case IOAM6_IPTUNNEL_MODE_INLINE:
do_inline:
@@ -359,7 +365,7 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
if (ipv6_hdr(skb)->nexthdr == NEXTHDR_HOP)
goto out;
- err = ioam6_do_inline(net, skb, &ilwt->tuninfo);
+ err = ioam6_do_inline(net, skb, &ilwt->tuninfo, cache_dst);
if (unlikely(err))
goto drop;
@@ -369,7 +375,7 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
/* Encapsulation (ip6ip6) */
err = ioam6_do_encap(net, skb, &ilwt->tuninfo,
ilwt->has_tunsrc, &ilwt->tunsrc,
- &ilwt->tundst);
+ &ilwt->tundst, cache_dst);
if (unlikely(err))
goto drop;
@@ -387,41 +393,36 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
goto drop;
}
- err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
- if (unlikely(err))
- goto drop;
+ if (unlikely(!cache_dst)) {
+ struct ipv6hdr *hdr = ipv6_hdr(skb);
+ struct flowi6 fl6;
+
+ memset(&fl6, 0, sizeof(fl6));
+ fl6.daddr = hdr->daddr;
+ fl6.saddr = hdr->saddr;
+ fl6.flowlabel = ip6_flowinfo(hdr);
+ fl6.flowi6_mark = skb->mark;
+ fl6.flowi6_proto = hdr->nexthdr;
+
+ cache_dst = ip6_route_output(net, NULL, &fl6);
+ if (cache_dst->error) {
+ err = cache_dst->error;
+ dst_release(cache_dst);
+ goto drop;
+ }
- if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr)) {
local_bh_disable();
- dst = dst_cache_get(&ilwt->cache);
+ dst_cache_set_ip6(&ilwt->cache, cache_dst, &fl6.saddr);
local_bh_enable();
- if (unlikely(!dst)) {
- struct ipv6hdr *hdr = ipv6_hdr(skb);
- struct flowi6 fl6;
-
- memset(&fl6, 0, sizeof(fl6));
- fl6.daddr = hdr->daddr;
- fl6.saddr = hdr->saddr;
- fl6.flowlabel = ip6_flowinfo(hdr);
- fl6.flowi6_mark = skb->mark;
- fl6.flowi6_proto = hdr->nexthdr;
-
- dst = ip6_route_output(net, NULL, &fl6);
- if (dst->error) {
- err = dst->error;
- dst_release(dst);
- goto drop;
- }
-
- local_bh_disable();
- dst_cache_set_ip6(&ilwt->cache, dst, &fl6.saddr);
- local_bh_enable();
- }
+ err = skb_cow_head(skb, LL_RESERVED_SPACE(cache_dst->dev));
+ if (unlikely(err))
+ goto drop;
+ }
+ if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr)) {
skb_dst_drop(skb);
- skb_dst_set(skb, dst);
-
+ skb_dst_set(skb, cache_dst);
return dst_output(net, sk, skb);
}
out:
--
2.34.1
Powered by blists - more mailing lists