| 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: <1ed21e6d-7cbc-43e3-8933-fc40562b70b2@gmail.com>
Date: Mon, 6 May 2024 11:47:09 +0200
From: Richard Gobert <richardbgobert@...il.com>
To: davem@...emloft.net, edumazet@...gle.com,
willemdebruijn.kernel@...il.com, kuba@...nel.org, pabeni@...hat.com,
dsahern@...nel.org, alobakin@...me, shuah@...nel.org,
netdev@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-kselftest@...r.kernel.org
Subject: [PATCH net-next v8 2/3] net: gro: move L3 flush checks to
tcp_gro_receive and udp_gro_receive_segment
{inet,ipv6}_gro_receive functions perform flush checks (ttl, flags,
iph->id, ...) against all packets in a loop. These flush checks are used in
all merging UDP and TCP flows.
These checks need to be done only once and only against the found p skb,
since they only affect flush and not same_flow.
This patch leverages correct network header offsets from the cb for both
outer and inner network headers - allowing these checks to be done only
once, in tcp_gro_receive and udp_gro_receive_segment. As a result,
NAPI_GRO_CB(p)->flush is not used at all. In addition, flush_id checks are
more declarative and contained in inet_gro_flush, thus removing the need
for flush_id in napi_gro_cb.
This results in less parsing code for non-loop flush tests for TCP and UDP
flows.
To make sure results are not within noise range - I've made netfilter drop
all TCP packets, and measured CPU performance in GRO (in this case GRO is
responsible for about 50% of the CPU utilization).
perf top while replaying 64 parallel IP/TCP streams merging in GRO:
(gro_network_flush is compiled inline to tcp_gro_receive)
net-next:
6.94% [kernel] [k] inet_gro_receive
3.02% [kernel] [k] tcp_gro_receive
patch applied:
4.27% [kernel] [k] tcp_gro_receive
4.22% [kernel] [k] inet_gro_receive
perf top while replaying 64 parallel IP/IP/TCP streams merging in GRO (same
results for any encapsulation, in this case inet_gro_receive is top
offender in net-next)
net-next:
10.09% [kernel] [k] inet_gro_receive
2.08% [kernel] [k] tcp_gro_receive
patch applied:
6.97% [kernel] [k] inet_gro_receive
3.68% [kernel] [k] tcp_gro_receive
Signed-off-by: Richard Gobert <richardbgobert@...il.com>
---
include/net/gro.h | 66 ++++++++++++++++++++++++++++++++++++++----
net/core/gro.c | 3 --
net/ipv4/af_inet.c | 41 +-------------------------
net/ipv4/tcp_offload.c | 15 ++--------
net/ipv4/udp_offload.c | 10 ++-----
net/ipv6/ip6_offload.c | 11 -------
6 files changed, 65 insertions(+), 81 deletions(-)
diff --git a/include/net/gro.h b/include/net/gro.h
index 1faff23b66e8..0565dd716ab7 100644
--- a/include/net/gro.h
+++ b/include/net/gro.h
@@ -36,15 +36,15 @@ struct napi_gro_cb {
/* This is non-zero if the packet cannot be merged with the new skb. */
u16 flush;
- /* Save the IP ID here and check when we get to the transport layer */
- u16 flush_id;
-
/* Number of segments aggregated. */
u16 count;
/* Used in ipv6_gro_receive() and foo-over-udp and esp-in-udp */
u16 proto;
+ /* used to support CHECKSUM_COMPLETE for tunneling protocols */
+ __wsum csum;
+
/* Used in napi_gro_cb::free */
#define NAPI_GRO_FREE 1
#define NAPI_GRO_FREE_STOLEN_HEAD 2
@@ -85,9 +85,6 @@ struct napi_gro_cb {
u8 is_flist:1;
);
- /* used to support CHECKSUM_COMPLETE for tunneling protocols */
- __wsum csum;
-
/* L3 offsets */
union {
struct {
@@ -442,6 +439,63 @@ static inline __wsum ip6_gro_compute_pseudo(const struct sk_buff *skb,
skb_gro_len(skb), proto, 0));
}
+static inline int inet_gro_flush(const struct iphdr *iph, const struct iphdr *iph2,
+ struct sk_buff *p, bool outer)
+{
+ const u32 id = ntohl(*(__be32 *)&iph->id);
+ const u32 id2 = ntohl(*(__be32 *)&iph2->id);
+ const u16 flush_id = (id >> 16) - (id2 >> 16);
+ const u16 count = NAPI_GRO_CB(p)->count;
+ const u32 df = id & IP_DF;
+ u32 is_atomic;
+ int flush;
+
+ /* All fields must match except length and checksum. */
+ flush = (iph->ttl ^ iph2->ttl) | (iph->tos ^ iph2->tos) | (df ^ (id2 & IP_DF));
+
+ if (outer && df)
+ return flush;
+
+ /* When we receive our second frame we can make a decision on if we
+ * continue this flow as an atomic flow with a fixed ID or if we use
+ * an incrementing ID.
+ */
+ NAPI_GRO_CB(p)->is_atomic |= (count == 1 && df && flush_id == 0);
+ is_atomic = (df && NAPI_GRO_CB(p)->is_atomic) - 1;
+
+ return flush | (flush_id ^ (count & is_atomic));
+}
+
+static inline int ipv6_gro_flush(const struct ipv6hdr *iph, const struct ipv6hdr *iph2)
+{
+ /* <Version:4><Traffic_Class:8><Flow_Label:20> */
+ __be32 first_word = *(__be32 *)iph ^ *(__be32 *)iph2;
+
+ /* Flush if Traffic Class fields are different. */
+ return !!((first_word & htonl(0x0FF00000)) |
+ (__force __be32)(iph->hop_limit ^ iph2->hop_limit));
+}
+
+static inline int gro_network_flush(const void *th, const void *th2, struct sk_buff *p, int off)
+{
+ const bool encap_mark = NAPI_GRO_CB(p)->encap_mark;
+ int flush = 0;
+ int i;
+
+ for (i = 0; i <= encap_mark; i++) {
+ const u16 diff = off - NAPI_GRO_CB(p)->network_offsets[i];
+ const void *nh = th - diff;
+ const void *nh2 = th2 - diff;
+
+ if (((struct iphdr *)nh)->version == 6)
+ flush |= ipv6_gro_flush(nh, nh2);
+ else
+ flush |= inet_gro_flush(nh, nh2, p, i != encap_mark);
+ }
+
+ return flush;
+}
+
int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb);
/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
diff --git a/net/core/gro.c b/net/core/gro.c
index 99a45a5211c9..3e9422c23bc9 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -331,8 +331,6 @@ static void gro_list_prepare(const struct list_head *head,
list_for_each_entry(p, head, list) {
unsigned long diffs;
- NAPI_GRO_CB(p)->flush = 0;
-
if (hash != skb_get_hash_raw(p)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
@@ -472,7 +470,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
sizeof(u32))); /* Avoid slow unaligned acc */
*(u32 *)&NAPI_GRO_CB(skb)->zeroed = 0;
NAPI_GRO_CB(skb)->flush = skb_has_frag_list(skb);
- NAPI_GRO_CB(skb)->is_atomic = 1;
NAPI_GRO_CB(skb)->count = 1;
if (unlikely(skb_is_gso(skb))) {
NAPI_GRO_CB(skb)->count = skb_shinfo(skb)->gso_segs;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 428196e1541f..44564d009e95 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1482,7 +1482,6 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
struct sk_buff *p;
unsigned int hlen;
unsigned int off;
- unsigned int id;
int flush = 1;
int proto;
@@ -1508,13 +1507,10 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
goto out;
NAPI_GRO_CB(skb)->proto = proto;
- id = ntohl(*(__be32 *)&iph->id);
- flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF));
- id >>= 16;
+ flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (ntohl(*(__be32 *)&iph->id) & ~IP_DF));
list_for_each_entry(p, head, list) {
struct iphdr *iph2;
- u16 flush_id;
if (!NAPI_GRO_CB(p)->same_flow)
continue;
@@ -1531,43 +1527,8 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
-
- /* All fields must match except length and checksum. */
- NAPI_GRO_CB(p)->flush |=
- (iph->ttl ^ iph2->ttl) |
- (iph->tos ^ iph2->tos) |
- ((iph->frag_off ^ iph2->frag_off) & htons(IP_DF));
-
- NAPI_GRO_CB(p)->flush |= flush;
-
- /* We need to store of the IP ID check to be included later
- * when we can verify that this packet does in fact belong
- * to a given flow.
- */
- flush_id = (u16)(id - ntohs(iph2->id));
-
- /* This bit of code makes it much easier for us to identify
- * the cases where we are doing atomic vs non-atomic IP ID
- * checks. Specifically an atomic check can return IP ID
- * values 0 - 0xFFFF, while a non-atomic check can only
- * return 0 or 0xFFFF.
- */
- if (!NAPI_GRO_CB(p)->is_atomic ||
- !(iph->frag_off & htons(IP_DF))) {
- flush_id ^= NAPI_GRO_CB(p)->count;
- flush_id = flush_id ? 0xFFFF : 0;
- }
-
- /* If the previous IP ID value was based on an atomic
- * datagram we can overwrite the value and ignore it.
- */
- if (NAPI_GRO_CB(skb)->is_atomic)
- NAPI_GRO_CB(p)->flush_id = flush_id;
- else
- NAPI_GRO_CB(p)->flush_id |= flush_id;
}
- NAPI_GRO_CB(skb)->is_atomic = !!(iph->frag_off & htons(IP_DF));
NAPI_GRO_CB(skb)->flush |= flush;
NAPI_GRO_CB(skb)->inner_network_offset = off;
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index b70ae50e658d..625b4800b3ed 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -232,9 +232,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
goto out_check_final;
found:
- /* Include the IP ID check below from the inner most IP hdr */
- flush = NAPI_GRO_CB(p)->flush;
- flush |= (__force int)(flags & TCP_FLAG_CWR);
+ flush = (__force int)(flags & TCP_FLAG_CWR);
flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));
flush |= (__force int)(th->ack_seq ^ th2->ack_seq);
@@ -242,16 +240,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
flush |= *(u32 *)((u8 *)th + i) ^
*(u32 *)((u8 *)th2 + i);
- /* When we receive our second frame we can made a decision on if we
- * continue this flow as an atomic flow with a fixed ID or if we use
- * an incrementing ID.
- */
- if (NAPI_GRO_CB(p)->flush_id != 1 ||
- NAPI_GRO_CB(p)->count != 1 ||
- !NAPI_GRO_CB(p)->is_atomic)
- flush |= NAPI_GRO_CB(p)->flush_id;
- else
- NAPI_GRO_CB(p)->is_atomic = false;
+ flush |= gro_network_flush(th, th2, p, off);
mss = skb_shinfo(p)->gso_size;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 8721fe5beca2..5d9696eaab8a 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -466,6 +466,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
struct sk_buff *skb)
{
struct udphdr *uh = udp_gro_udphdr(skb);
+ int off = skb_gro_offset(skb);
struct sk_buff *pp = NULL;
struct udphdr *uh2;
struct sk_buff *p;
@@ -505,14 +506,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
return p;
}
- flush = NAPI_GRO_CB(p)->flush;
-
- if (NAPI_GRO_CB(p)->flush_id != 1 ||
- NAPI_GRO_CB(p)->count != 1 ||
- !NAPI_GRO_CB(p)->is_atomic)
- flush |= NAPI_GRO_CB(p)->flush_id;
- else
- NAPI_GRO_CB(p)->is_atomic = false;
+ flush = gro_network_flush(uh, uh2, p, off);
/* Terminate the flow on len mismatch or if it grow "too much".
* Under small packet flood GRO count could elsewhere grow a lot
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 5d6b875a4638..72991a02cb30 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -290,19 +290,8 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
nlen - sizeof(struct ipv6hdr)))
goto not_same_flow;
}
- /* flush if Traffic Class fields are different */
- NAPI_GRO_CB(p)->flush |= !!((first_word & htonl(0x0FF00000)) |
- (__force __be32)(iph->hop_limit ^ iph2->hop_limit));
- NAPI_GRO_CB(p)->flush |= flush;
-
- /* If the previous IP ID value was based on an atomic
- * datagram we can overwrite the value and ignore it.
- */
- if (NAPI_GRO_CB(skb)->is_atomic)
- NAPI_GRO_CB(p)->flush_id = 0;
}
- NAPI_GRO_CB(skb)->is_atomic = true;
NAPI_GRO_CB(skb)->flush |= flush;
skb_gro_postpull_rcsum(skb, iph, nlen);
--
2.36.1
Powered by blists - more mailing lists