From c1aca3080e382886e2e58e809787441984a2f89b Mon Sep 17 00:00:00 2001 From: Yan Yan Date: Tue, 18 Jan 2022 16:00:13 -0800 Subject: xfrm: Check if_id in xfrm_migrate This patch enables distinguishing SAs and SPs based on if_id during the xfrm_migrate flow. This ensures support for xfrm interfaces throughout the SA/SP lifecycle. When there are multiple existing SPs with the same direction, the same xfrm_selector and different endpoint addresses, xfrm_migrate might fail with ENODATA. Specifically, the code path for performing xfrm_migrate is: Stage 1: find policy to migrate with xfrm_migrate_policy_find(sel, dir, type, net) Stage 2: find and update state(s) with xfrm_migrate_state_find(mp, net) Stage 3: update endpoint address(es) of template(s) with xfrm_policy_migrate(pol, m, num_migrate) Currently "Stage 1" always returns the first xfrm_policy that matches, and "Stage 3" looks for the xfrm_tmpl that matches the old endpoint address. Thus if there are multiple xfrm_policy with same selector, direction, type and net, "Stage 1" might rertun a wrong xfrm_policy and "Stage 3" will fail with ENODATA because it cannot find a xfrm_tmpl with the matching endpoint address. The fix is to allow userspace to pass an if_id and add if_id to the matching rule in Stage 1 and Stage 2 since if_id is a unique ID for xfrm_policy and xfrm_state. For compatibility, if_id will only be checked if the attribute is set. Tested with additions to Android's kernel unit test suite: https://android-review.googlesource.com/c/kernel/tests/+/1668886 Signed-off-by: Yan Yan Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index fdb41e8bb626..743dd1da506e 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1681,14 +1681,15 @@ int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k, const struct xfrm_encap_tmpl *encap); -struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net); +struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net, + u32 if_id); struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m, struct xfrm_encap_tmpl *encap); int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, struct xfrm_kmaddress *k, struct net *net, - struct xfrm_encap_tmpl *encap); + struct xfrm_encap_tmpl *encap, u32 if_id); #endif int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport); -- cgit v1.2.3-58-ga151 From a6d95c5a628a09be129f25d5663a7e9db8261f51 Mon Sep 17 00:00:00 2001 From: Jiri Bohac Date: Wed, 26 Jan 2022 16:00:18 +0100 Subject: Revert "xfrm: xfrm_state_mtu should return at least 1280 for ipv6" This reverts commit b515d2637276a3810d6595e10ab02c13bfd0b63a. Commit b515d2637276a3810d6595e10ab02c13bfd0b63a ("xfrm: xfrm_state_mtu should return at least 1280 for ipv6") in v5.14 breaks the TCP MSS calculation in ipsec transport mode, resulting complete stalls of TCP connections. This happens when the (P)MTU is 1280 or slighly larger. The desired formula for the MSS is: MSS = (MTU - ESP_overhead) - IP header - TCP header However, the above commit clamps the (MTU - ESP_overhead) to a minimum of 1280, turning the formula into MSS = max(MTU - ESP overhead, 1280) - IP header - TCP header With the (P)MTU near 1280, the calculated MSS is too large and the resulting TCP packets never make it to the destination because they are over the actual PMTU. The above commit also causes suboptimal double fragmentation in xfrm tunnel mode, as described in https://lore.kernel.org/netdev/20210429202529.codhwpc7w6kbudug@dwarf.suse.cz/ The original problem the above commit was trying to fix is now fixed by commit 6596a0229541270fb8d38d989f91b78838e5e9da ("xfrm: fix MTU regression"). Signed-off-by: Jiri Bohac Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 1 - net/ipv4/esp4.c | 2 +- net/ipv6/esp6.c | 2 +- net/xfrm/xfrm_state.c | 14 ++------------ 4 files changed, 4 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 743dd1da506e..76aa6f11a540 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1568,7 +1568,6 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq); int xfrm_init_replay(struct xfrm_state *x); -u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu); u32 xfrm_state_mtu(struct xfrm_state *x, int mtu); int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload); int xfrm_init_state(struct xfrm_state *x); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 851f542928a3..e1b1d080e908 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -671,7 +671,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb); u32 padto; - padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached)); + padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached)); if (skb->len < padto) esp.tfclen = padto - skb->len; } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 8bb2c407b46b..7591160edce1 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -707,7 +707,7 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb); u32 padto; - padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached)); + padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached)); if (skb->len < padto) esp.tfclen = padto - skb->len; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 1ba6fbfe8cdb..b749935152ba 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2579,7 +2579,7 @@ void xfrm_state_delete_tunnel(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_delete_tunnel); -u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu) +u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) { const struct xfrm_type *type = READ_ONCE(x->type); struct crypto_aead *aead; @@ -2610,17 +2610,7 @@ u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu) return ((mtu - x->props.header_len - crypto_aead_authsize(aead) - net_adj) & ~(blksize - 1)) + net_adj - 2; } -EXPORT_SYMBOL_GPL(__xfrm_state_mtu); - -u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) -{ - mtu = __xfrm_state_mtu(x, mtu); - - if (x->props.family == AF_INET6 && mtu < IPV6_MIN_MTU) - return IPV6_MIN_MTU; - - return mtu; -} +EXPORT_SYMBOL_GPL(xfrm_state_mtu); int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload) { -- cgit v1.2.3-58-ga151 From 7c76ecd9c99b6e9a771d813ab1aa7fa428b3ade1 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 8 Feb 2022 16:14:32 +0200 Subject: xfrm: enforce validity of offload input flags struct xfrm_user_offload has flags variable that received user input, but kernel didn't check if valid bits were provided. It caused a situation where not sanitized input was forwarded directly to the drivers. For example, XFRM_OFFLOAD_IPV6 define that was exposed, was used by strongswan, but not implemented in the kernel at all. As a solution, check and sanitize input flags to forward XFRM_OFFLOAD_INBOUND to the drivers. Fixes: d77e38e612a0 ("xfrm: Add an IPsec hardware offloading API") Signed-off-by: Leon Romanovsky Signed-off-by: Steffen Klassert --- include/uapi/linux/xfrm.h | 6 ++++++ net/xfrm/xfrm_device.c | 6 +++++- 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 4e29d7851890..65e13a099b1a 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -511,6 +511,12 @@ struct xfrm_user_offload { int ifindex; __u8 flags; }; +/* This flag was exposed without any kernel code that supporting it. + * Unfortunately, strongswan has the code that uses sets this flag, + * which makes impossible to reuse this bit. + * + * So leave it here to make sure that it won't be reused by mistake. + */ #define XFRM_OFFLOAD_IPV6 1 #define XFRM_OFFLOAD_INBOUND 2 diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 3fa066419d37..39bce5d764de 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -223,6 +223,9 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, if (x->encap || x->tfcpad) return -EINVAL; + if (xuo->flags & ~(XFRM_OFFLOAD_IPV6 | XFRM_OFFLOAD_INBOUND)) + return -EINVAL; + dev = dev_get_by_index(net, xuo->ifindex); if (!dev) { if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) { @@ -262,7 +265,8 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, netdev_tracker_alloc(dev, &xso->dev_tracker, GFP_ATOMIC); xso->real_dev = dev; xso->num_exthdrs = 1; - xso->flags = xuo->flags; + /* Don't forward bit that is not implemented */ + xso->flags = xuo->flags & ~XFRM_OFFLOAD_IPV6; err = dev->xfrmdev_ops->xdo_dev_state_add(x); if (err) { -- cgit v1.2.3-58-ga151