[PATCH ipsec-next 0/2] xfrm: policy: replace session decode with flow dissector

[PATCH ipsec-next 0/2] xfrm: policy: replace session decode with flow dissector

[Florian Westphal]

Remove the ipv4+ipv6 session decode functions and use generic flow
dissector to populate the flowi for the policy lookup.

Changes since RFC:

 - Drop mobility header support.  I don't think that anyone uses
   this.  MOBIKE doesn't appear to need this either.
 - Drop fl6->flowlabel assignment, original code leaves it as 0.

There is no reason for this change other than to remove code.

Florian Westphal (2):
  xfrm: move mark and oif flowi decode into common code
  xfrm: policy: replace session decode with flow dissector

Florian Westphal (2):
  xfrm: move mark and oif flowi decode into common code
  xfrm: policy: replace session decode with flow dissector

 net/xfrm/xfrm_policy.c | 277 ++++++++++++++++-------------------------
 1 file changed, 107 insertions(+), 170 deletions(-)

-- 
2.41.0

[PATCH ipsec-next 1/2] xfrm: move mark and oif flowi decode into common code

[Florian Westphal]

flowi4_oif/flowi6_oif and mark are aliased to flowi_common field, i.e.
all can be used interchangeably.

Instead of duplicating place this in common code.
No functional changes intended.

Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/xfrm/xfrm_policy.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index c4c4fc29ccf5..a014783f6d8a 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3373,14 +3373,8 @@ decode_session4(struct sk_buff *skb, struct flowi *fl, bool reverse)
 	int ihl = iph->ihl;
 	u8 *xprth = skb_network_header(skb) + ihl * 4;
 	struct flowi4 *fl4 = &fl->u.ip4;
-	int oif = 0;
-
-	if (skb_dst(skb) && skb_dst(skb)->dev)
-		oif = skb_dst(skb)->dev->ifindex;
 
 	memset(fl4, 0, sizeof(struct flowi4));
-	fl4->flowi4_mark = skb->mark;
-	fl4->flowi4_oif = reverse ? skb->skb_iif : oif;
 
 	fl4->flowi4_proto = iph->protocol;
 	fl4->daddr = reverse ? iph->saddr : iph->daddr;
@@ -3451,7 +3445,6 @@ decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse)
 	struct ipv6_opt_hdr *exthdr;
 	const unsigned char *nh = skb_network_header(skb);
 	u16 nhoff = IP6CB(skb)->nhoff;
-	int oif = 0;
 	u8 nexthdr;
 
 	if (!nhoff)
@@ -3459,12 +3452,7 @@ decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse)
 
 	nexthdr = nh[nhoff];
 
-	if (skb_dst(skb) && skb_dst(skb)->dev)
-		oif = skb_dst(skb)->dev->ifindex;
-
 	memset(fl6, 0, sizeof(struct flowi6));
-	fl6->flowi6_mark = skb->mark;
-	fl6->flowi6_oif = reverse ? skb->skb_iif : oif;
 
 	fl6->daddr = reverse ? hdr->saddr : hdr->daddr;
 	fl6->saddr = reverse ? hdr->daddr : hdr->saddr;
@@ -3570,6 +3558,18 @@ int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl,
 		return -EAFNOSUPPORT;
 	}
 
+	fl->flowi_mark = skb->mark;
+	if (reverse) {
+		fl->flowi_oif = skb->skb_iif;
+	} else {
+		int oif = 0;
+
+		if (skb_dst(skb) && skb_dst(skb)->dev)
+			oif = skb_dst(skb)->dev->ifindex;
+
+		fl->flowi_oif = oif;
+	}
+
 	return security_xfrm_decode_session(skb, &fl->flowi_secid);
 }
 EXPORT_SYMBOL(__xfrm_decode_session);
-- 
2.41.0

[PATCH ipsec-next 2/2] xfrm: policy: replace session decode with flow dissector

[Florian Westphal]

xfrm needs to populate ipv4/v6 flow struct for route lookup.
In the past there were several bugs in this code:

1. callers that forget to reload header pointers after
   xfrm_decode_session() (it may pull headers).
2. bugs in decoding where accesses past skb->data occurred.

Meanwhile network core gained a packet dissector as well.
This switches xfrm to the flow dissector.

Changes since RFC:
Drop ipv6 mobiliy header support, AFAIU noone uses this.

Drop extraction of flowlabel, replaced code doesn't set it either.

Link: https://lore.kernel.org/netdev/20230908120628.26164-3-fw@strlen.de/
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/xfrm/xfrm_policy.c | 253 ++++++++++++++++-------------------------
 1 file changed, 95 insertions(+), 158 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index a014783f6d8a..1ca4ca5b1367 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -149,6 +149,21 @@ struct xfrm_pol_inexact_candidates {
 	struct hlist_head *res[XFRM_POL_CAND_MAX];
 };
 
+struct xfrm_flow_keys {
+	struct flow_dissector_key_basic basic;
+	struct flow_dissector_key_control control;
+	union {
+		struct flow_dissector_key_ipv4_addrs ipv4;
+		struct flow_dissector_key_ipv6_addrs ipv6;
+	} addrs;
+	struct flow_dissector_key_ip ip;
+	struct flow_dissector_key_icmp icmp;
+	struct flow_dissector_key_ports ports;
+	struct flow_dissector_key_keyid gre;
+};
+
+static struct flow_dissector xfrm_session_dissector __ro_after_init;
+
 static DEFINE_SPINLOCK(xfrm_if_cb_lock);
 static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly;
 
@@ -3367,191 +3382,74 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star
 }
 
 static void
-decode_session4(struct sk_buff *skb, struct flowi *fl, bool reverse)
+decode_session4(const struct xfrm_flow_keys *flkeys, struct flowi *fl, bool reverse)
 {
-	const struct iphdr *iph = ip_hdr(skb);
-	int ihl = iph->ihl;
-	u8 *xprth = skb_network_header(skb) + ihl * 4;
 	struct flowi4 *fl4 = &fl->u.ip4;
 
 	memset(fl4, 0, sizeof(struct flowi4));
 
-	fl4->flowi4_proto = iph->protocol;
-	fl4->daddr = reverse ? iph->saddr : iph->daddr;
-	fl4->saddr = reverse ? iph->daddr : iph->saddr;
-	fl4->flowi4_tos = iph->tos & ~INET_ECN_MASK;
-
-	if (!ip_is_fragment(iph)) {
-		switch (iph->protocol) {
-		case IPPROTO_UDP:
-		case IPPROTO_UDPLITE:
-		case IPPROTO_TCP:
-		case IPPROTO_SCTP:
-		case IPPROTO_DCCP:
-			if (xprth + 4 < skb->data ||
-			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
-				__be16 *ports;
-
-				xprth = skb_network_header(skb) + ihl * 4;
-				ports = (__be16 *)xprth;
-
-				fl4->fl4_sport = ports[!!reverse];
-				fl4->fl4_dport = ports[!reverse];
-			}
-			break;
-		case IPPROTO_ICMP:
-			if (xprth + 2 < skb->data ||
-			    pskb_may_pull(skb, xprth + 2 - skb->data)) {
-				u8 *icmp;
-
-				xprth = skb_network_header(skb) + ihl * 4;
-				icmp = xprth;
-
-				fl4->fl4_icmp_type = icmp[0];
-				fl4->fl4_icmp_code = icmp[1];
-			}
-			break;
-		case IPPROTO_GRE:
-			if (xprth + 12 < skb->data ||
-			    pskb_may_pull(skb, xprth + 12 - skb->data)) {
-				__be16 *greflags;
-				__be32 *gre_hdr;
-
-				xprth = skb_network_header(skb) + ihl * 4;
-				greflags = (__be16 *)xprth;
-				gre_hdr = (__be32 *)xprth;
-
-				if (greflags[0] & GRE_KEY) {
-					if (greflags[0] & GRE_CSUM)
-						gre_hdr++;
-					fl4->fl4_gre_key = gre_hdr[1];
-				}
-			}
-			break;
-		default:
-			break;
-		}
+	if (reverse) {
+		fl4->saddr = flkeys->addrs.ipv4.dst;
+		fl4->daddr = flkeys->addrs.ipv4.src;
+		fl4->fl4_sport = flkeys->ports.dst;
+		fl4->fl4_dport = flkeys->ports.src;
+	} else {
+		fl4->saddr = flkeys->addrs.ipv4.src;
+		fl4->daddr = flkeys->addrs.ipv4.dst;
+		fl4->fl4_sport = flkeys->ports.src;
+		fl4->fl4_dport = flkeys->ports.dst;
 	}
+
+	fl4->flowi4_proto = flkeys->basic.ip_proto;
+	fl4->flowi4_tos = flkeys->ip.tos;
+	fl4->fl4_icmp_type = flkeys->icmp.type;
+	fl4->fl4_icmp_type = flkeys->icmp.code;
+	fl4->fl4_gre_key = flkeys->gre.keyid;
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
 static void
-decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse)
+decode_session6(const struct xfrm_flow_keys *flkeys, struct flowi *fl, bool reverse)
 {
 	struct flowi6 *fl6 = &fl->u.ip6;
-	int onlyproto = 0;
-	const struct ipv6hdr *hdr = ipv6_hdr(skb);
-	u32 offset = sizeof(*hdr);
-	struct ipv6_opt_hdr *exthdr;
-	const unsigned char *nh = skb_network_header(skb);
-	u16 nhoff = IP6CB(skb)->nhoff;
-	u8 nexthdr;
-
-	if (!nhoff)
-		nhoff = offsetof(struct ipv6hdr, nexthdr);
-
-	nexthdr = nh[nhoff];
 
 	memset(fl6, 0, sizeof(struct flowi6));
 
-	fl6->daddr = reverse ? hdr->saddr : hdr->daddr;
-	fl6->saddr = reverse ? hdr->daddr : hdr->saddr;
-
-	while (nh + offset + sizeof(*exthdr) < skb->data ||
-	       pskb_may_pull(skb, nh + offset + sizeof(*exthdr) - skb->data)) {
-		nh = skb_network_header(skb);
-		exthdr = (struct ipv6_opt_hdr *)(nh + offset);
-
-		switch (nexthdr) {
-		case NEXTHDR_FRAGMENT:
-			onlyproto = 1;
-			fallthrough;
-		case NEXTHDR_ROUTING:
-		case NEXTHDR_HOP:
-		case NEXTHDR_DEST:
-			offset += ipv6_optlen(exthdr);
-			nexthdr = exthdr->nexthdr;
-			break;
-		case IPPROTO_UDP:
-		case IPPROTO_UDPLITE:
-		case IPPROTO_TCP:
-		case IPPROTO_SCTP:
-		case IPPROTO_DCCP:
-			if (!onlyproto && (nh + offset + 4 < skb->data ||
-			     pskb_may_pull(skb, nh + offset + 4 - skb->data))) {
-				__be16 *ports;
-
-				nh = skb_network_header(skb);
-				ports = (__be16 *)(nh + offset);
-				fl6->fl6_sport = ports[!!reverse];
-				fl6->fl6_dport = ports[!reverse];
-			}
-			fl6->flowi6_proto = nexthdr;
-			return;
-		case IPPROTO_ICMPV6:
-			if (!onlyproto && (nh + offset + 2 < skb->data ||
-			    pskb_may_pull(skb, nh + offset + 2 - skb->data))) {
-				u8 *icmp;
-
-				nh = skb_network_header(skb);
-				icmp = (u8 *)(nh + offset);
-				fl6->fl6_icmp_type = icmp[0];
-				fl6->fl6_icmp_code = icmp[1];
-			}
-			fl6->flowi6_proto = nexthdr;
-			return;
-		case IPPROTO_GRE:
-			if (!onlyproto &&
-			    (nh + offset + 12 < skb->data ||
-			     pskb_may_pull(skb, nh + offset + 12 - skb->data))) {
-				struct gre_base_hdr *gre_hdr;
-				__be32 *gre_key;
-
-				nh = skb_network_header(skb);
-				gre_hdr = (struct gre_base_hdr *)(nh + offset);
-				gre_key = (__be32 *)(gre_hdr + 1);
-
-				if (gre_hdr->flags & GRE_KEY) {
-					if (gre_hdr->flags & GRE_CSUM)
-						gre_key++;
-					fl6->fl6_gre_key = *gre_key;
-				}
-			}
-			fl6->flowi6_proto = nexthdr;
-			return;
-
-#if IS_ENABLED(CONFIG_IPV6_MIP6)
-		case IPPROTO_MH:
-			offset += ipv6_optlen(exthdr);
-			if (!onlyproto && (nh + offset + 3 < skb->data ||
-			    pskb_may_pull(skb, nh + offset + 3 - skb->data))) {
-				struct ip6_mh *mh;
-
-				nh = skb_network_header(skb);
-				mh = (struct ip6_mh *)(nh + offset);
-				fl6->fl6_mh_type = mh->ip6mh_type;
-			}
-			fl6->flowi6_proto = nexthdr;
-			return;
-#endif
-		default:
-			fl6->flowi6_proto = nexthdr;
-			return;
-		}
+	if (reverse) {
+		fl6->saddr = flkeys->addrs.ipv6.dst;
+		fl6->daddr = flkeys->addrs.ipv6.src;
+		fl6->fl6_sport = flkeys->ports.dst;
+		fl6->fl6_dport = flkeys->ports.src;
+	} else {
+		fl6->saddr = flkeys->addrs.ipv6.src;
+		fl6->daddr = flkeys->addrs.ipv6.dst;
+		fl6->fl6_sport = flkeys->ports.src;
+		fl6->fl6_dport = flkeys->ports.dst;
 	}
+
+	fl6->flowi6_proto = flkeys->basic.ip_proto;
+	fl6->fl6_icmp_type = flkeys->icmp.type;
+	fl6->fl6_icmp_type = flkeys->icmp.code;
+	fl6->fl6_gre_key = flkeys->gre.keyid;
 }
 #endif
 
 int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl,
 			  unsigned int family, int reverse)
 {
+	struct xfrm_flow_keys flkeys;
+
+	memset(&flkeys, 0, sizeof(flkeys));
+
+	skb_flow_dissect(skb, &xfrm_session_dissector, &flkeys, FLOW_DISSECTOR_F_STOP_AT_ENCAP);
+
 	switch (family) {
 	case AF_INET:
-		decode_session4(skb, fl, reverse);
+		decode_session4(&flkeys, fl, reverse);
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
-		decode_session6(skb, fl, reverse);
+		decode_session6(&flkeys, fl, reverse);
 		break;
 #endif
 	default:
@@ -4253,8 +4151,47 @@ static struct pernet_operations __net_initdata xfrm_net_ops = {
 	.exit = xfrm_net_exit,
 };
 
+static const struct flow_dissector_key xfrm_flow_dissector_keys[] = {
+	{
+		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
+		.offset = offsetof(struct xfrm_flow_keys, control),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_BASIC,
+		.offset = offsetof(struct xfrm_flow_keys, basic),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+		.offset = offsetof(struct xfrm_flow_keys, addrs.ipv4),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+		.offset = offsetof(struct xfrm_flow_keys, addrs.ipv6),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_PORTS,
+		.offset = offsetof(struct xfrm_flow_keys, ports),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_GRE_KEYID,
+		.offset = offsetof(struct xfrm_flow_keys, gre),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IP,
+		.offset = offsetof(struct xfrm_flow_keys, ip),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_ICMP,
+		.offset = offsetof(struct xfrm_flow_keys, icmp),
+	},
+};
+
 void __init xfrm_init(void)
 {
+	skb_flow_dissector_init(&xfrm_session_dissector,
+				xfrm_flow_dissector_keys,
+				ARRAY_SIZE(xfrm_flow_dissector_keys));
+
 	register_pernet_subsys(&xfrm_net_ops);
 	xfrm_dev_init();
 	xfrm_input_init();
-- 
2.41.0

Re: [PATCH ipsec-next 0/2] xfrm: policy: replace session decode with flow dissector

[Simon Horman]

On Mon, Sep 18, 2023 at 02:59:07PM +0200, Florian Westphal wrote:
> Remove the ipv4+ipv6 session decode functions and use generic flow
> dissector to populate the flowi for the policy lookup.
> 
> Changes since RFC:
> 
>  - Drop mobility header support.  I don't think that anyone uses
>    this.  MOBIKE doesn't appear to need this either.
>  - Drop fl6->flowlabel assignment, original code leaves it as 0.
> 
> There is no reason for this change other than to remove code.
> 
> Florian Westphal (2):
>   xfrm: move mark and oif flowi decode into common code
>   xfrm: policy: replace session decode with flow dissector
> 
> Florian Westphal (2):
>   xfrm: move mark and oif flowi decode into common code
>   xfrm: policy: replace session decode with flow dissector
> 
>  net/xfrm/xfrm_policy.c | 277 ++++++++++++++++-------------------------
>  1 file changed, 107 insertions(+), 170 deletions(-)

For series,

Reviewed-by: Simon Horman <horms@kernel.org>

Re: [PATCH ipsec-next 2/2] xfrm: policy: replace session decode with flow dissector

[kernel test robot]

Hello,

kernel test robot noticed "WARNING:at_net/core/flow_dissector.c:#__skb_flow_dissect" on:

commit: 7a6420ac36c0355d4d370cce83343dcefa58a1c4 ("[PATCH ipsec-next 2/2] xfrm: policy: replace session decode with flow dissector")
url: https://github.com/intel-lab-lkp/linux/commits/Florian-Westphal/xfrm-move-mark-and-oif-flowi-decode-into-common-code/20230918-210254
base: https://git.kernel.org/cgit/linux/kernel/git/klassert/ipsec.git master
patch link: https://lore.kernel.org/all/20230918125914.21391-3-fw@strlen.de/
patch subject: [PATCH ipsec-next 2/2] xfrm: policy: replace session decode with flow dissector

in testcase: kernel-selftests
version: kernel-selftests-x86_64-60acb023-1_20230329
with following parameters:

	group: netfilter
	test: nft_synproxy.sh



compiler: gcc-12
test machine: 36 threads 1 sockets Intel(R) Core(TM) i9-10980XE CPU @ 3.00GHz (Cascade Lake) with 32G memory

(please refer to attached dmesg/kmsg for entire log/backtrace)



If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <oliver.sang@intel.com>
| Closes: https://lore.kernel.org/oe-lkp/202309271628.27fd2187-oliver.sang@intel.com


kern  :warn  : [  173.147140] ------------[ cut here ]------------
kern :warn : [  173.147759] WARNING: CPU: 12 PID: 2260 at net/core/flow_dissector.c:1096 __skb_flow_dissect (net/core/flow_dissector.c:1096 (discriminator 1)) 
kern  :warn  : [  173.148709] Modules linked in: nft_synproxy nf_synproxy_core nft_ct nf_tables veth nfnetlink openvswitch nf_conncount nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 intel_rapl_msr intel_rapl_common nfit libnvdimm x86_pkg_temp_thermal intel_powerclamp btrfs coretemp kvm_intel blake2b_generic xor raid6_pq kvm zstd_compress irqbypass crct10dif_pclmul libcrc32c crc32_pclmul crc32c_intel ghash_clmulni_intel sha512_ssse3 rapl intel_cstate nvme nvme_core t10_pi crc64_rocksoft_generic crc64_rocksoft ipmi_devintf ahci libahci ipmi_msghandler intel_wmi_thunderbolt wmi_bmof mxm_wmi i2c_i801 wdat_wdt intel_uncore crc64 mei_me i2c_smbus libata ioatdma dca mei wmi binfmt_misc fuse drm ip_tables
kern  :warn  : [  173.154193] CPU: 12 PID: 2260 Comm: iperf3 Not tainted 6.5.0-04033-g7a6420ac36c0-dirty #1
kern  :warn  : [  173.155024] Hardware name: Gigabyte Technology Co., Ltd. X299 UD4 Pro/X299 UD4 Pro-CF, BIOS F8a 04/27/2021
kern :warn : [  173.155977] RIP: 0010:__skb_flow_dissect (net/core/flow_dissector.c:1096 (discriminator 1)) 
kern :warn : [ 173.156562] Code: b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 e4 39 00 00 4d 8b b6 a0 05 00 00 4d 85 f6 0f 85 9d f9 ff ff <0f> 0b e9 0f fb ff ff 66 81 fb 08 06 0f 84 ca fc ff ff 44 8b bd 00
All code
========
   0:	b8 00 00 00 00       	mov    $0x0,%eax
   5:	00 fc                	add    %bh,%ah
   7:	ff                   	(bad)  
   8:	df 48 89             	fisttps -0x77(%rax)
   b:	fa                   	cli    
   c:	48 c1 ea 03          	shr    $0x3,%rdx
  10:	80 3c 02 00          	cmpb   $0x0,(%rdx,%rax,1)
  14:	0f 85 e4 39 00 00    	jne    0x39fe
  1a:	4d 8b b6 a0 05 00 00 	mov    0x5a0(%r14),%r14
  21:	4d 85 f6             	test   %r14,%r14
  24:	0f 85 9d f9 ff ff    	jne    0xfffffffffffff9c7
  2a:*	0f 0b                	ud2    		<-- trapping instruction
  2c:	e9 0f fb ff ff       	jmpq   0xfffffffffffffb40
  31:	66 81 fb 08 06       	cmp    $0x608,%bx
  36:	0f 84 ca fc ff ff    	je     0xfffffffffffffd06
  3c:	44                   	rex.R
  3d:	8b                   	.byte 0x8b
  3e:	bd                   	.byte 0xbd
	...

Code starting with the faulting instruction
===========================================
   0:	0f 0b                	ud2    
   2:	e9 0f fb ff ff       	jmpq   0xfffffffffffffb16
   7:	66 81 fb 08 06       	cmp    $0x608,%bx
   c:	0f 84 ca fc ff ff    	je     0xfffffffffffffcdc
  12:	44                   	rex.R
  13:	8b                   	.byte 0x8b
  14:	bd                   	.byte 0xbd
	...
kern  :warn  : [  173.158315] RSP: 0018:ffffc900008e7e10 EFLAGS: 00010246
kern  :warn  : [  173.158889] RAX: dffffc0000000000 RBX: 0000000000000008 RCX: ffffc900008e8240
kern  :warn  : [  173.159631] RDX: 1ffff1103c1ac95b RSI: 0000000000000000 RDI: ffff8881e0d64ad8
kern  :warn  : [  173.160365] RBP: ffffc900008e81e0 R08: 0000000000000000 R09: 0000000000000000
kern  :warn  : [  173.161114] R10: ffffc900008e81f8 R11: ffffc900008e8240 R12: ffff8881e0d64ac0
kern  :warn  : [  173.161871] R13: ffffffff8472b660 R14: 0000000000000000 R15: 0000000000000038
kern  :warn  : [  173.162612] FS:  00007f4db0039740(0000) GS:ffff88880ea00000(0000) knlGS:0000000000000000
kern  :warn  : [  173.163426] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
kern  :warn  : [  173.164051] CR2: 00007f4db0741f8c CR3: 000000087dbda001 CR4: 00000000003706e0
kern  :warn  : [  173.164808] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
kern  :warn  : [  173.165549] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
kern  :warn  : [  173.166282] Call Trace:
kern  :warn  : [  173.166620]  <IRQ>
kern :warn : [  173.166916] ? __warn (kernel/panic.c:673) 
kern :warn : [  173.167316] ? __skb_flow_dissect (net/core/flow_dissector.c:1096 (discriminator 1)) 
kern :warn : [  173.167837] ? report_bug (lib/bug.c:180 lib/bug.c:219) 
kern :warn : [  173.168293] ? handle_bug (arch/x86/kernel/traps.c:324) 
kern :warn : [  173.168724] ? exc_invalid_op (arch/x86/kernel/traps.c:345 (discriminator 1)) 
kern :warn : [  173.169173] ? asm_exc_invalid_op (arch/x86/include/asm/idtentry.h:568) 
kern :warn : [  173.169668] ? __skb_flow_dissect (net/core/flow_dissector.c:1096 (discriminator 1)) 
kern :warn : [  173.170170] ? arch_stack_walk (arch/x86/kernel/stacktrace.c:27 (discriminator 1)) 
kern :warn : [  173.170643] ? bpf_flow_dissect (net/core/flow_dissector.c:1029) 
kern :warn : [  173.171125] ? native_queued_spin_lock_slowpath (arch/x86/include/asm/atomic.h:23 include/linux/atomic/atomic-arch-fallback.h:444 include/linux/atomic/atomic-instrumented.h:33 arch/x86/include/asm/qspinlock.h:25 kernel/locking/qspinlock.c:353) 
kern :warn : [  173.171729] ? .slowpath (kernel/locking/qspinlock.c:317) 
kern :warn : [  173.172143] ? lock_acquire (kernel/locking/lockdep.c:467 kernel/locking/lockdep.c:5763 kernel/locking/lockdep.c:5726) 
kern :warn : [  173.172601] ? __create_object (mm/kmemleak.c:678) 
kern :warn : [  173.173076] ? set_track_prepare (mm/slub.c:3016) 
kern :warn : [  173.173555] ? mark_lock (arch/x86/include/asm/bitops.h:228 (discriminator 3) arch/x86/include/asm/bitops.h:240 (discriminator 3) include/asm-generic/bitops/instrumented-non-atomic.h:142 (discriminator 3) kernel/locking/lockdep.c:228 (discriminator 3) kernel/locking/lockdep.c:4663 (discriminator 3)) 
kern :warn : [  173.173978] ? mark_lock (arch/x86/include/asm/bitops.h:228 (discriminator 3) arch/x86/include/asm/bitops.h:240 (discriminator 3) include/asm-generic/bitops/instrumented-non-atomic.h:142 (discriminator 3) kernel/locking/lockdep.c:228 (discriminator 3) kernel/locking/lockdep.c:4663 (discriminator 3)) 
kern :warn : [  173.174398] ? reacquire_held_locks (kernel/locking/lockdep.c:5412) 
kern :warn : [  173.174913] ? mark_lock_irq (kernel/locking/lockdep.c:4646) 
kern :warn : [  173.175373] ? mark_held_locks (kernel/locking/lockdep.c:4281) 
kern :warn : [  173.175841] ? mark_held_locks (kernel/locking/lockdep.c:4281) 
kern :warn : [  173.176296] ? _raw_spin_unlock_irqrestore (arch/x86/include/asm/irqflags.h:42 arch/x86/include/asm/irqflags.h:77 arch/x86/include/asm/irqflags.h:135 include/linux/spinlock_api_smp.h:151 kernel/locking/spinlock.c:194) 
kern :warn : [  173.176849] ? lockdep_hardirqs_on_prepare (kernel/locking/lockdep.c:4574) 
kern :warn : [  173.177468] ? rt_cache_route (net/ipv4/route.c:1485) 
kern :warn : [  173.177925] ? find_held_lock (kernel/locking/lockdep.c:5251) 
kern :warn : [  173.178384] ? __lock_release+0x111/0x440 
kern :warn : [  173.178905] ? ip_route_output_key_hash (include/linux/rcupdate.h:781 net/ipv4/route.c:2643) 
kern :warn : [  173.179442] ? reacquire_held_locks (kernel/locking/lockdep.c:5412) 
kern :warn : [  173.179960] ? __mkroute_output (include/net/lwtunnel.h:140 net/ipv4/route.c:2618) 
kern :warn : [  173.181387] ? __xfrm_decode_session (net/xfrm/xfrm_policy.c:3451) 
kern :warn : [  173.181904] __xfrm_decode_session (net/xfrm/xfrm_policy.c:3451) 
kern :warn : [  173.182398] ? ip_route_output_key_hash_rcu (net/ipv4/route.c:2629) 
kern :warn : [  173.182972] ? rt6_get_cookie (net/core/dst_cache.c:29) 
kern :warn : [  173.183449] ip_route_me_harder (include/linux/skbuff.h:1121 net/ipv4/netfilter.c:66) 
kern :warn : [  173.183941] ? nf_ip_route (net/ipv4/netfilter.c:21) 
kern :warn : [  173.184369] ? mark_held_locks (kernel/locking/lockdep.c:4281) 
kern :warn : [  173.184831] ? mark_held_locks (kernel/locking/lockdep.c:4281) 
kern :warn : [  173.185293] ? _raw_spin_unlock_irqrestore (arch/x86/include/asm/irqflags.h:42 arch/x86/include/asm/irqflags.h:77 arch/x86/include/asm/irqflags.h:135 include/linux/spinlock_api_smp.h:151 kernel/locking/spinlock.c:194) 
kern :warn : [  173.185849] ? cookie_timestamp_decode (net/ipv4/syncookies.c:48) 
kern :warn : [  173.186377] ? __alloc_skb (net/core/skbuff.c:666) 
kern :warn : [  173.186829] ? lock_is_held_type (kernel/locking/lockdep.c:5502 kernel/locking/lockdep.c:5832) 
kern :warn : [  173.187312] synproxy_send_tcp+0x2aa/0x540 nf_synproxy_core
kern :warn : [  173.187988] synproxy_send_client_synack (net/netfilter/nf_synproxy_core.c:484) nf_synproxy_core
kern :warn : [  173.188699] ? synproxy_send_client_synack_ipv6 (net/netfilter/nf_synproxy_core.c:450) nf_synproxy_core
kern :warn : [  173.189444] ? hrtimer_nanosleep (kernel/time/hrtimer.c:337 include/linux/hrtimer.h:255 kernel/time/hrtimer.c:2099) 
kern :warn : [  173.189947] ? ktime_get (kernel/time/timekeeping.c:379 (discriminator 4) kernel/time/timekeeping.c:389 (discriminator 4) kernel/time/timekeeping.c:848 (discriminator 4)) 
kern :warn : [  173.190388] nft_synproxy_do_eval (net/netfilter/nft_synproxy.c:60 net/netfilter/nft_synproxy.c:141) nft_synproxy
kern :warn : [  173.191004] ? nft_synproxy_obj_destroy (net/netfilter/nft_synproxy.c:109) nft_synproxy
kern :warn : [  173.191653] ? mark_lock (arch/x86/include/asm/bitops.h:228 (discriminator 3) arch/x86/include/asm/bitops.h:240 (discriminator 3) include/asm-generic/bitops/instrumented-non-atomic.h:142 (discriminator 3) kernel/locking/lockdep.c:228 (discriminator 3) kernel/locking/lockdep.c:4663 (discriminator 3)) 
kern :warn : [  173.192073] ? lock_is_held_type (kernel/locking/lockdep.c:5502 kernel/locking/lockdep.c:5832) 
kern :warn : [  173.192563] nft_do_chain (net/netfilter/nf_tables_core.c:290) nf_tables
kern :warn : [  173.193119] ? nft_update_chain_stats (net/netfilter/nf_tables_core.c:254) nf_tables
kern :warn : [  173.193784] ? __create_object (mm/kmemleak.c:678) 
kern :warn : [  173.194274] nft_do_chain_inet (net/netfilter/nft_chain_filter.c:145) nf_tables
kern :warn : [  173.194856] ? nft_do_chain_arp (net/netfilter/nft_chain_filter.c:145) nf_tables
kern :warn : [  173.195420] ? NF_HOOK+0xca/0x2b0 
kern :warn : [  173.195924] ? lock_sync (kernel/locking/lockdep.c:5729) 
kern :warn : [  173.196354] ? skb_release_data (arch/x86/include/asm/atomic.h:85 arch/x86/include/asm/atomic.h:91 include/linux/atomic/atomic-arch-fallback.h:778 include/linux/atomic/atomic-instrumented.h:290 net/core/skbuff.c:968) 
kern :warn : [  173.196837] nf_hook_slow (include/linux/netfilter.h:144 net/netfilter/core.c:626) 
kern :warn : [  173.197269] NF_HOOK+0x17f/0x2b0 
kern :warn : [  173.197763] ? ip_forward_finish (include/linux/netfilter.h:298) 
kern :warn : [  173.198248] ? ip_route_input_slow (net/ipv4/route.c:2487) 
kern :warn : [  173.198772] ? ip4_obj_hashfn (net/ipv4/ip_forward.c:66) 
kern :warn : [  173.199237] ? tcp_v4_early_demux (net/ipv4/tcp_ipv4.c:1796) 
kern :warn : [  173.199739] ? lock_is_held_type (kernel/locking/lockdep.c:5502 kernel/locking/lockdep.c:5832) 
kern :warn : [  173.200221] ip_forward (net/ipv4/ip_forward.c:162) 
kern :warn : [  173.200665] ? lock_is_held_type (kernel/locking/lockdep.c:5502 kernel/locking/lockdep.c:5832) 
kern :warn : [  173.201143] ? __xfrm_policy_check2+0x460/0x460 
kern :warn : [  173.201747] ? ip_rcv_finish (include/linux/skbuff.h:1121 include/net/dst.h:468 net/ipv4/ip_input.c:449) 
kern :warn : [  173.202205] ip_rcv (include/linux/netfilter.h:304 include/linux/netfilter.h:298 net/ipv4/ip_input.c:569) 
kern :warn : [  173.202596] ? ip_local_deliver (net/ipv4/ip_input.c:562) 
kern :warn : [  173.203078] ? ip_sublist_rcv (net/ipv4/ip_input.c:436) 
kern :warn : [  173.203548] ? lock_acquire (kernel/locking/lockdep.c:467 kernel/locking/lockdep.c:5763 kernel/locking/lockdep.c:5726) 
kern :warn : [  173.203997] ? process_backlog (include/linux/skbuff.h:2360 include/linux/skbuff.h:2375 net/core/dev.c:5963) 
kern :warn : [  173.204489] ? ip_local_deliver (net/ipv4/ip_input.c:562) 
kern :warn : [  173.204967] __netif_receive_skb_one_core (net/core/dev.c:5516) 
kern :warn : [  173.205527] ? __netif_receive_skb_list_core (net/core/dev.c:5516) 
kern :warn : [  173.206101] ? mark_held_locks (kernel/locking/lockdep.c:4281) 
kern :warn : [  173.206571] process_backlog (include/linux/rcupdate.h:778 net/core/dev.c:5966) 
kern :warn : [  173.207027] __napi_poll+0xa0/0x530 
kern :warn : [  173.207546] net_rx_action (net/core/dev.c:6596 net/core/dev.c:6727) 
kern :warn : [  173.207995] ? __napi_poll+0x530/0x530 
kern :warn : [  173.208530] ? reacquire_held_locks (kernel/locking/lockdep.c:5412) 
kern :warn : [  173.209039] ? asym_cpu_capacity_scan (kernel/sched/clock.c:389) 
kern :warn : [  173.209581] __do_softirq (arch/x86/include/asm/jump_label.h:27 include/linux/jump_label.h:207 include/trace/events/irq.h:142 kernel/softirq.c:554) 
kern :warn : [  173.210021] ? __lock_text_end (kernel/softirq.c:511) 
kern :warn : [  173.210471] ? irqtime_account_irq (kernel/sched/cputime.c:64) 
kern :warn : [  173.210966] ? __dev_queue_xmit (include/linux/rcupdate.h:308 include/linux/rcupdate.h:817 net/core/dev.c:4367) 
kern :warn : [  173.211454] do_softirq (kernel/softirq.c:454 kernel/softirq.c:441) 
kern  :warn  : [  173.211870]  </IRQ>
kern  :warn  : [  173.212170]  <TASK>
kern :warn : [  173.212479] __local_bh_enable_ip (kernel/softirq.c:381) 
kern :warn : [  173.212965] __dev_queue_xmit (net/core/dev.c:4368) 
kern :warn : [  173.213441] ? mark_lock (arch/x86/include/asm/bitops.h:228 (discriminator 3) arch/x86/include/asm/bitops.h:240 (discriminator 3) include/asm-generic/bitops/instrumented-non-atomic.h:142 (discriminator 3) kernel/locking/lockdep.c:228 (discriminator 3) kernel/locking/lockdep.c:4663 (discriminator 3)) 
kern :warn : [  173.213881] ? mark_lock_irq (kernel/locking/lockdep.c:4646) 
kern :warn : [  173.214352] ? netdev_core_pick_tx (net/core/dev.c:4249) 
kern :warn : [  173.214861] ? reacquire_held_locks (kernel/locking/lockdep.c:5412) 
kern :warn : [  173.215369] ? lock_acquire (kernel/locking/lockdep.c:467 kernel/locking/lockdep.c:5763 kernel/locking/lockdep.c:5726) 
kern :warn : [  173.215828] ? mark_held_locks (kernel/locking/lockdep.c:4281) 
kern :warn : [  173.216286] ? lockdep_hardirqs_on_prepare (kernel/locking/lockdep.c:4573) 
kern :warn : [  173.216902] ? neigh_hh_output (arch/x86/include/asm/irqflags.h:42 arch/x86/include/asm/irqflags.h:77 arch/x86/include/asm/irqflags.h:135 include/linux/seqlock.h:104 include/linux/seqlock.h:837 include/net/neighbour.h:496) 


The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20230927/202309271628.27fd2187-oliver.sang@intel.com



-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH ipsec-next 2/2] xfrm: policy: replace session decode with flow dissector

[Florian Westphal]

kernel test robot <oliver.sang@intel.com> wrote:
> (please refer to attached dmesg/kmsg for entire log/backtrace)
> 
> 
> 
> If you fix the issue in a separate patch/commit (i.e. not just a new version of
> the same patch/commit), kindly add following tags
> | Reported-by: kernel test robot <oliver.sang@intel.com>
> | Closes: https://lore.kernel.org/oe-lkp/202309271628.27fd2187-oliver.sang@intel.com
> 
> 
> kern  :warn  : [  173.147140] ------------[ cut here ]------------
> kern :warn : [  173.147759] WARNING: CPU: 12 PID: 2260 at net/core/flow_dissector.c:1096 __skb_flow_dissect (net/core/flow_dissector.c:1096 (discriminator 1)) 

Two options, more 'guess the right netns' in flow dissector:
derive netns from skb->dst->dev.

Or, pass struct net down to xfrm session decode functions.

I'll have a go at option 2 to see how much noise its going to be.