diff mbox series

[net-next,v3,1/3] net: ipv6: ioam6_iptunnel: mitigate 2-realloc issue

Message ID 20241028223611.26599-2-justin.iurman@uliege.be (mailing list archive)
State Changes Requested
Delegated to: Netdev Maintainers
Headers show
Series Mitigate the two-reallocations issue for iptunnels | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 5 this patch: 5
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers success CCed 6 of 6 maintainers
netdev/build_clang success Errors and warnings before: 3 this patch: 3
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 4 this patch: 4
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 166 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline fail Was 0 now: 1

Commit Message

Justin Iurman Oct. 28, 2024, 10:36 p.m. UTC 
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 would 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@uliege.be>
---
 net/ipv6/ioam6_iptunnel.c | 90 +++++++++++++++++++++------------------
 1 file changed, 49 insertions(+), 41 deletions(-)

Comments

Vadim Fedorenko Oct. 29, 2024, 10:58 a.m. UTC | #1 
On 28/10/2024 22:36, Justin Iurman wrote:
> 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 would 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@uliege.be>
> ---
>   net/ipv6/ioam6_iptunnel.c | 90 +++++++++++++++++++++------------------
>   1 file changed, 49 insertions(+), 41 deletions(-)
> 
> diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
> index beb6b4cfc551..07bfd557e08a 100644
> --- a/net/ipv6/ioam6_iptunnel.c
> +++ b/net/ipv6/ioam6_iptunnel.c
> @@ -254,15 +254,24 @@ static int ioam6_do_fill(struct net *net, struct sk_buff *skb)
>   	return 0;
>   }
>   
> +static inline int dev_overhead(struct dst_entry *dst, struct sk_buff *skb)
> +{
> +	if (likely(dst))
> +		return LL_RESERVED_SPACE(dst->dev);
> +
> +	return skb->mac_len;
> +}

static inline functions in .c files are not welcome.
consider to move this helper to some header, probably dev.h or dst.h
and reuse it in other tunnels.

And please honor 24h rule before the next submission.


>   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 *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 + dev_overhead(dst, skb));
>   	if (unlikely(err))
>   		return err;
>   
[.. snip ..]
diff mbox series

Patch

diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index beb6b4cfc551..07bfd557e08a 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -254,15 +254,24 @@  static int ioam6_do_fill(struct net *net, struct sk_buff *skb)
 	return 0;
 }
 
+static inline int dev_overhead(struct dst_entry *dst, struct sk_buff *skb)
+{
+	if (likely(dst))
+		return LL_RESERVED_SPACE(dst->dev);
+
+	return skb->mac_len;
+}
+
 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 *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 + dev_overhead(dst, skb));
 	if (unlikely(err))
 		return err;
 
@@ -293,16 +302,16 @@  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 *dst)
 {
-	struct dst_entry *dst = skb_dst(skb);
 	struct ipv6hdr *hdr, *inner_hdr;
 	int hdrlen, len, err;
 
 	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 + dev_overhead(dst, skb));
 	if (unlikely(err))
 		return err;
 
@@ -326,7 +335,7 @@  static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
 	if (has_tunsrc)
 		memcpy(&hdr->saddr, tunsrc, sizeof(*tunsrc));
 	else
-		ipv6_dev_get_saddr(net, dst->dev, &hdr->daddr,
+		ipv6_dev_get_saddr(net, skb_dst(skb)->dev, &hdr->daddr,
 				   IPV6_PREFER_SRC_PUBLIC, &hdr->saddr);
 
 	skb_postpush_rcsum(skb, hdr, len);
@@ -336,7 +345,7 @@  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, *orig_dst = skb_dst(skb);
 	struct in6_addr orig_daddr;
 	struct ioam6_lwt *ilwt;
 	int err = -EINVAL;
@@ -345,7 +354,7 @@  static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (skb->protocol != htons(ETH_P_IPV6))
 		goto drop;
 
-	ilwt = ioam6_lwt_state(dst->lwtstate);
+	ilwt = ioam6_lwt_state(orig_dst->lwtstate);
 
 	/* Check for insertion frequency (i.e., "k over n" insertions) */
 	pkt_cnt = atomic_fetch_inc(&ilwt->pkt_cnt);
@@ -354,6 +363,10 @@  static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 
 	orig_daddr = ipv6_hdr(skb)->daddr;
 
+	local_bh_disable();
+	dst = dst_cache_get(&ilwt->cache);
+	local_bh_enable();
+
 	switch (ilwt->mode) {
 	case IOAM6_IPTUNNEL_MODE_INLINE:
 do_inline:
@@ -361,7 +374,7 @@  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, dst);
 		if (unlikely(err))
 			goto drop;
 
@@ -371,7 +384,7 @@  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, dst);
 		if (unlikely(err))
 			goto drop;
 
@@ -389,45 +402,40 @@  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(!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;
+		}
 
-	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, 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(dst->dev));
+		if (unlikely(err))
+			goto drop;
+	}
 
-		skb_dst_drop(skb);
-		skb_dst_set(skb, dst);
+	skb_dst_drop(skb);
+	skb_dst_set(skb, dst);
 
+	if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr))
 		return dst_output(net, sk, skb);
-	}
 out:
-	return dst->lwtstate->orig_output(net, sk, skb);
+	return orig_dst->lwtstate->orig_output(net, sk, skb);
 drop:
 	kfree_skb(skb);
 	return err;