From cc41c84b7e7f2d7f6698bccc84890943fd021265 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 14 Apr 2017 20:31:08 +0200 Subject: netfilter: kill the fake untracked conntrack objects resurrect an old patch from Pablo Neira to remove the untracked objects. Currently, there are four possible states of an skb wrt. conntrack. 1. No conntrack attached, ct is NULL. 2. Normal (kmem cache allocated) ct attached. 3. a template (kmalloc'd), not in any hash tables at any point in time 4. the 'untracked' conntrack, a percpu nf_conn object, tagged via IPS_UNTRACKED_BIT in ct->status. Untracked is supposed to be identical to case 1. It exists only so users can check -m conntrack --ctstate UNTRACKED vs. -m conntrack --ctstate INVALID e.g. attempts to set connmark on INVALID or UNTRACKED conntracks is supposed to be a no-op. Thus currently we need to check ct == NULL || nf_ct_is_untracked(ct) in a lot of places in order to avoid altering untracked objects. The other consequence of the percpu untracked object is that all -j NOTRACK (and, later, kfree_skb of such skbs) result in an atomic op (inc/dec the untracked conntracks refcount). This adds a new kernel-private ctinfo state, IP_CT_UNTRACKED, to make the distinction instead. The (few) places that care about packet invalid (ct is NULL) vs. packet untracked now need to test ct == NULL vs. ctinfo == IP_CT_UNTRACKED, but all other places can omit the nf_ct_is_untracked() check. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_conntrack_common.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index 6a8e33dd4ecb..b4a0a1940118 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -28,12 +28,14 @@ enum ip_conntrack_info { /* only for userspace compatibility */ #ifndef __KERNEL__ IP_CT_NEW_REPLY = IP_CT_NUMBER, +#else + IP_CT_UNTRACKED = 7, #endif }; #define NF_CT_STATE_INVALID_BIT (1 << 0) #define NF_CT_STATE_BIT(ctinfo) (1 << ((ctinfo) % IP_CT_IS_REPLY + 1)) -#define NF_CT_STATE_UNTRACKED_BIT (1 << (IP_CT_NUMBER + 1)) +#define NF_CT_STATE_UNTRACKED_BIT (1 << (IP_CT_UNTRACKED + 1)) /* Bitset representing status of connection. */ enum ip_conntrack_status { @@ -94,7 +96,7 @@ enum ip_conntrack_status { IPS_TEMPLATE_BIT = 11, IPS_TEMPLATE = (1 << IPS_TEMPLATE_BIT), - /* Conntrack is a fake untracked entry */ + /* Conntrack is a fake untracked entry. Obsolete and not used anymore */ IPS_UNTRACKED_BIT = 12, IPS_UNTRACKED = (1 << IPS_UNTRACKED_BIT), -- cgit v1.2.3 From 694a0055f039bc1d73aba10606ea74e798d2d759 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 15 Apr 2017 19:26:10 +0200 Subject: netfilter: nft_ct: allow to set ctnetlink event types of a connection By default the kernel emits all ctnetlink events for a connection. This allows to select the types of events to generate. This can be used to e.g. only send DESTROY events but no NEW/UPDATE ones and will work even if sysctl net.netfilter.nf_conntrack_events is set to 0. This was already possible via iptables' CT target, but the nft version has the advantage that it can also be used with already-established conntracks. The added nf_ct_is_template() check isn't a bug fix as we only support mark and labels (and unlike ecache the conntrack core doesn't copy those). Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ net/netfilter/nft_ct.c | 25 ++++++++++++++++++++++++- 2 files changed, 26 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 8f3842690d17..683f6f88fcac 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -901,6 +901,7 @@ enum nft_rt_attributes { * @NFT_CT_BYTES: conntrack bytes * @NFT_CT_AVGPKT: conntrack average bytes per packet * @NFT_CT_ZONE: conntrack zone + * @NFT_CT_EVENTMASK: ctnetlink events to be generated for this conntrack */ enum nft_ct_keys { NFT_CT_STATE, @@ -921,6 +922,7 @@ enum nft_ct_keys { NFT_CT_BYTES, NFT_CT_AVGPKT, NFT_CT_ZONE, + NFT_CT_EVENTMASK, }; /** diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 6c6fd48b024c..a34ceb38fc55 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -264,7 +264,7 @@ static void nft_ct_set_eval(const struct nft_expr *expr, struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); - if (ct == NULL) + if (ct == NULL || nf_ct_is_template(ct)) return; switch (priv->key) { @@ -283,6 +283,22 @@ static void nft_ct_set_eval(const struct nft_expr *expr, ®s->data[priv->sreg], NF_CT_LABELS_MAX_SIZE / sizeof(u32)); break; +#endif +#ifdef CONFIG_NF_CONNTRACK_EVENTS + case NFT_CT_EVENTMASK: { + struct nf_conntrack_ecache *e = nf_ct_ecache_find(ct); + u32 ctmask = regs->data[priv->sreg]; + + if (e) { + if (e->ctmask != ctmask) + e->ctmask = ctmask; + break; + } + + if (ctmask && !nf_ct_is_confirmed(ct)) + nf_ct_ecache_ext_add(ct, ctmask, 0, GFP_ATOMIC); + break; + } #endif default: break; @@ -538,6 +554,13 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, nft_ct_pcpu_template_refcnt++; len = sizeof(u16); break; +#endif +#ifdef CONFIG_NF_CONNTRACK_EVENTS + case NFT_CT_EVENTMASK: + if (tb[NFTA_CT_DIRECTION]) + return -EINVAL; + len = sizeof(u32); + break; #endif default: return -EOPNOTSUPP; -- cgit v1.2.3 From 01026edef9062b7d26ace74a5b4a5a33a2399501 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 18 Apr 2017 17:27:32 +0200 Subject: nefilter: eache: reduce struct size from 32 to 24 byte Only "cache" needs to use ulong (its used with set_bit()), missed can use u16. Also add build-time assertion to ensure event bits fit. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_ecache.h | 4 ++-- include/uapi/linux/netfilter/nf_conntrack_common.h | 3 +++ net/netfilter/nf_conntrack_ecache.c | 3 +++ 3 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 12d967b58726..2a10c6570fcc 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -20,11 +20,11 @@ enum nf_ct_ecache_state { struct nf_conntrack_ecache { unsigned long cache; /* bitops want long */ - unsigned long missed; /* missed events */ + u16 missed; /* missed events */ u16 ctmask; /* bitmask of ct events to be delivered */ u16 expmask; /* bitmask of expect events to be delivered */ + enum nf_ct_ecache_state state:8;/* ecache state */ u32 portid; /* netlink portid of destroyer */ - enum nf_ct_ecache_state state; /* ecache state */ }; static inline struct nf_conntrack_ecache * diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index b4a0a1940118..a8072cc7fa0b 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -119,6 +119,9 @@ enum ip_conntrack_events { IPCT_NATSEQADJ = IPCT_SEQADJ, IPCT_SECMARK, /* new security mark has been set */ IPCT_LABEL, /* new connlabel has been set */ +#ifdef __KERNEL__ + __IPCT_MAX +#endif }; enum ip_conntrack_expect_events { diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 6161e92d2980..515212948125 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -420,6 +420,9 @@ int nf_conntrack_ecache_init(void) int ret = nf_ct_extend_register(&event_extend); if (ret < 0) pr_err("nf_ct_event: Unable to register event extension.\n"); + + BUILD_BUG_ON(__IPCT_MAX >= 16); /* ctmask, missed use u16 */ + return ret; } -- cgit v1.2.3