From 25a91d8d91911f84a03a039339b29537e7f1970d Mon Sep 17 00:00:00 2001 From: Fan Du Date: Sat, 18 Jan 2014 09:54:23 +0800 Subject: [PATCH 01/13] skbuff: Introduce skb_to_sgvec_nomark to map skb without mark new end As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given sglist without mark the sg which contain last skb data as the end. So the caller can mannipulate sg list as will when padding new data after the first call without calling sg_unmark_end to expend sg list. Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- include/linux/skbuff.h | 2 ++ net/core/skbuff.c | 26 ++++++++++++++++++++++++++ 2 files changed, 28 insertions(+) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f589c9af8cbf..c574bf3bd6f6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -691,6 +691,8 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); +int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, + int offset, int len); int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5976ef0846bd..f28c37996aad 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3281,6 +3281,32 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) return elt; } +/* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given + * sglist without mark the sg which contain last skb data as the end. + * So the caller can mannipulate sg list as will when padding new data after + * the first call without calling sg_unmark_end to expend sg list. + * + * Scenario to use skb_to_sgvec_nomark: + * 1. sg_init_table + * 2. skb_to_sgvec_nomark(payload1) + * 3. skb_to_sgvec_nomark(payload2) + * + * This is equivalent to: + * 1. sg_init_table + * 2. skb_to_sgvec(payload1) + * 3. sg_unmark_end + * 4. skb_to_sgvec(payload2) + * + * When mapping mutilple payload conditionally, skb_to_sgvec_nomark + * is more preferable. + */ +int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, + int offset, int len) +{ + return __skb_to_sgvec(skb, sg, offset, len); +} +EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark); + int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { int nsg = __skb_to_sgvec(skb, sg, offset, len); From d4d573d0334d07341beffdcf97e2b85d3955d8ae Mon Sep 17 00:00:00 2001 From: Fan Du Date: Sat, 18 Jan 2014 09:54:24 +0800 Subject: [PATCH 02/13] {IPv4,xfrm} Add ESN support for AH egress part This patch add esn support for AH output stage by attaching upper 32bits sequence number right after packet payload as specified by RFC 4302. Then the ICV value will guard upper 32bits sequence number as well when packet going out. Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- net/ipv4/ah4.c | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 717902669d2f..c6accacc3a2b 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -155,6 +155,10 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) struct iphdr *iph, *top_iph; struct ip_auth_hdr *ah; struct ah_data *ahp; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; ahp = x->data; ahash = ahp->ahash; @@ -167,14 +171,19 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) ah = ip_auth_hdr(skb); ihl = ip_hdrlen(skb); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } err = -ENOMEM; - iph = ah_alloc_tmp(ahash, nfrags, ihl); + iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + seqhi_len); if (!iph) goto out; - - icv = ah_tmp_icv(ahash, iph, ihl); + seqhi = (__be32 *)((char *)iph + ihl); + icv = ah_tmp_icv(ahash, seqhi, seqhi_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; memset(ah->auth_data, 0, ahp->icv_trunc_len); @@ -210,10 +219,15 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) ah->spi = x->id.spi; ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); - ahash_request_set_crypt(req, sg, icv, skb->len); + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi); + sg_set_buf(seqhisg, seqhi, seqhi_len); + } + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah_output_done, skb); AH_SKB_CB(skb)->tmp = iph; From d8b2a8600b0ea002985d65bba4a94642a01bfe4c Mon Sep 17 00:00:00 2001 From: Fan Du Date: Sat, 18 Jan 2014 09:54:25 +0800 Subject: [PATCH 03/13] {IPv4,xfrm} Add ESN support for AH ingress part This patch add esn support for AH input stage by attaching upper 32bits sequence number right after packet payload as specified by RFC 4302. Then the ICV value will guard upper 32bits sequence number as well when packet getting in. Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- net/ipv4/ah4.c | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index c6accacc3a2b..54b965ddcb19 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -309,6 +309,10 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) struct ip_auth_hdr *ah; struct ah_data *ahp; int err = -ENOMEM; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; if (!pskb_may_pull(skb, sizeof(*ah))) goto out; @@ -349,14 +353,22 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) iph = ip_hdr(skb); ihl = ip_hdrlen(skb); - work_iph = ah_alloc_tmp(ahash, nfrags, ihl + ahp->icv_trunc_len); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } + + work_iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + + ahp->icv_trunc_len + seqhi_len); if (!work_iph) goto out; - auth_data = ah_tmp_auth(work_iph, ihl); + seqhi = (__be32 *)((char *)work_iph + ihl); + auth_data = ah_tmp_auth(seqhi, seqhi_len); icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; memcpy(work_iph, iph, ihl); memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); @@ -375,10 +387,15 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) skb_push(skb, ihl); - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); - ahash_request_set_crypt(req, sg, icv, skb->len); + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = XFRM_SKB_CB(skb)->seq.input.hi; + sg_set_buf(seqhisg, seqhi, seqhi_len); + } + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah_input_done, skb); AH_SKB_CB(skb)->tmp = work_iph; From 26dd70c3fad36f4b1aa124080d5907db10ed287c Mon Sep 17 00:00:00 2001 From: Fan Du Date: Sat, 18 Jan 2014 09:54:26 +0800 Subject: [PATCH 04/13] {IPv6,xfrm} Add ESN support for AH egress part This patch add esn support for AH output stage by attaching upper 32bits sequence number right after packet payload as specified by RFC 4302. Then the ICV value will guard upper 32bits sequence number as well when packet going out. Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- net/ipv6/ah6.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 81e496a2e008..89298124c136 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -346,6 +346,10 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) struct ip_auth_hdr *ah; struct ah_data *ahp; struct tmp_ext *iph_ext; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; ahp = x->data; ahash = ahp->ahash; @@ -359,15 +363,22 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) if (extlen) extlen += sizeof(*iph_ext); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } err = -ENOMEM; - iph_base = ah_alloc_tmp(ahash, nfrags, IPV6HDR_BASELEN + extlen); + iph_base = ah_alloc_tmp(ahash, nfrags + sglists, IPV6HDR_BASELEN + + extlen + seqhi_len); if (!iph_base) goto out; iph_ext = ah_tmp_ext(iph_base); - icv = ah_tmp_icv(ahash, iph_ext, extlen); + seqhi = (__be32 *)((char *)iph_ext + extlen); + icv = ah_tmp_icv(ahash, seqhi, seqhi_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; ah = ip_auth_hdr(skb); memset(ah->auth_data, 0, ahp->icv_trunc_len); @@ -411,10 +422,15 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) ah->spi = x->id.spi; ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); - ahash_request_set_crypt(req, sg, icv, skb->len); + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi); + sg_set_buf(seqhisg, seqhi, seqhi_len); + } + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah6_output_done, skb); AH_SKB_CB(skb)->tmp = iph_base; From 8d6da6f325572664107601a3c9782f8c23c1bfc5 Mon Sep 17 00:00:00 2001 From: Fan Du Date: Sat, 18 Jan 2014 09:54:27 +0800 Subject: [PATCH 05/13] {IPv6,xfrm} Add ESN support for AH ingress part This patch add esn support for AH input stage by attaching upper 32bits sequence number right after packet payload as specified by RFC 4302. Then the ICV value will guard upper 32bits sequence number as well when packet going in. Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- net/ipv6/ah6.c | 30 ++++++++++++++++++++++++------ 1 file changed, 24 insertions(+), 6 deletions(-) diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 89298124c136..6c5f0949e0ab 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -530,6 +530,10 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) int nexthdr; int nfrags; int err = -ENOMEM; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; if (!pskb_may_pull(skb, sizeof(struct ip_auth_hdr))) goto out; @@ -566,14 +570,22 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) skb_push(skb, hdr_len); - work_iph = ah_alloc_tmp(ahash, nfrags, hdr_len + ahp->icv_trunc_len); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } + + work_iph = ah_alloc_tmp(ahash, nfrags + sglists, hdr_len + + ahp->icv_trunc_len + seqhi_len); if (!work_iph) goto out; - auth_data = ah_tmp_auth(work_iph, hdr_len); - icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len); + auth_data = ah_tmp_auth((u8 *)work_iph, hdr_len); + seqhi = (__be32 *)(auth_data + ahp->icv_trunc_len); + icv = ah_tmp_icv(ahash, seqhi, seqhi_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; memcpy(work_iph, ip6h, hdr_len); memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); @@ -588,10 +600,16 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) ip6h->flow_lbl[2] = 0; ip6h->hop_limit = 0; - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); - ahash_request_set_crypt(req, sg, icv, skb->len); + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = XFRM_SKB_CB(skb)->seq.input.hi; + sg_set_buf(seqhisg, seqhi, seqhi_len); + } + + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah6_input_done, skb); AH_SKB_CB(skb)->tmp = work_iph; From 01714109ea7e7ff4142f98a91114a97a91d34cdf Mon Sep 17 00:00:00 2001 From: Fan Du Date: Sat, 18 Jan 2014 09:54:28 +0800 Subject: [PATCH 06/13] xfrm: Don't prohibit AH from using ESN feature Clear checking when user try to use ESN through netlink keymgr for AH. As only ESP and AH support ESN feature according to RFC. Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_user.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 1ae3ec7c18b0..ade9988f6e33 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -142,7 +142,8 @@ static inline int verify_replay(struct xfrm_usersa_info *p, if (!rt) return 0; - if (p->id.proto != IPPROTO_ESP) + /* As only ESP and AH support ESN feature. */ + if ((p->id.proto != IPPROTO_ESP) && (p->id.proto != IPPROTO_AH)) return -EINVAL; if (p->replay_window != 0) From ca925cf1534ebcec332c08719a7dee6ee1782ce4 Mon Sep 17 00:00:00 2001 From: Fan Du Date: Sat, 18 Jan 2014 09:55:27 +0800 Subject: [PATCH 07/13] flowcache: Make flow cache name space aware Inserting a entry into flowcache, or flushing flowcache should be based on per net scope. The reason to do so is flushing operation from fat netns crammed with flow entries will also making the slim netns with only a few flow cache entries go away in original implementation. Since flowcache is tightly coupled with IPsec, so it would be easier to put flow cache global parameters into xfrm namespace part. And one last thing needs to do is bumping flow cache genid, and flush flow cache should also be made in per net style. Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- include/net/flow.h | 5 +- include/net/flowcache.h | 25 +++++++ include/net/netns/xfrm.h | 11 +++ net/core/flow.c | 127 ++++++++++++++------------------ net/xfrm/xfrm_policy.c | 7 +- security/selinux/include/xfrm.h | 5 +- 6 files changed, 103 insertions(+), 77 deletions(-) create mode 100644 include/net/flowcache.h diff --git a/include/net/flow.h b/include/net/flow.h index d23e7fa2042e..bee3741e5a6f 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -218,9 +218,10 @@ struct flow_cache_object *flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, flow_resolve_t resolver, void *ctx); +int flow_cache_init(struct net *net); -void flow_cache_flush(void); -void flow_cache_flush_deferred(void); +void flow_cache_flush(struct net *net); +void flow_cache_flush_deferred(struct net *net); extern atomic_t flow_cache_genid; #endif diff --git a/include/net/flowcache.h b/include/net/flowcache.h new file mode 100644 index 000000000000..c8f665ec6e0d --- /dev/null +++ b/include/net/flowcache.h @@ -0,0 +1,25 @@ +#ifndef _NET_FLOWCACHE_H +#define _NET_FLOWCACHE_H + +#include +#include +#include +#include + +struct flow_cache_percpu { + struct hlist_head *hash_table; + int hash_count; + u32 hash_rnd; + int hash_rnd_recalc; + struct tasklet_struct flush_tasklet; +}; + +struct flow_cache { + u32 hash_shift; + struct flow_cache_percpu __percpu *percpu; + struct notifier_block hotcpu_notifier; + int low_watermark; + int high_watermark; + struct timer_list rnd_timer; +}; +#endif /* _NET_FLOWCACHE_H */ diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 1006a265beb3..52d0086d55d3 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -6,6 +6,7 @@ #include #include #include +#include struct ctl_table_header; @@ -61,6 +62,16 @@ struct netns_xfrm { spinlock_t xfrm_policy_sk_bundle_lock; rwlock_t xfrm_policy_lock; struct mutex xfrm_cfg_mutex; + + /* flow cache part */ + struct flow_cache flow_cache_global; + struct kmem_cache *flow_cachep; + atomic_t flow_cache_genid; + struct list_head flow_cache_gc_list; + spinlock_t flow_cache_gc_lock; + struct work_struct flow_cache_gc_work; + struct work_struct flow_cache_flush_work; + struct mutex flow_flush_sem; }; #endif diff --git a/net/core/flow.c b/net/core/flow.c index dfa602ceb8cd..344a184011fd 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -24,6 +24,7 @@ #include #include #include +#include struct flow_cache_entry { union { @@ -38,37 +39,12 @@ struct flow_cache_entry { struct flow_cache_object *object; }; -struct flow_cache_percpu { - struct hlist_head *hash_table; - int hash_count; - u32 hash_rnd; - int hash_rnd_recalc; - struct tasklet_struct flush_tasklet; -}; - struct flow_flush_info { struct flow_cache *cache; atomic_t cpuleft; struct completion completion; }; -struct flow_cache { - u32 hash_shift; - struct flow_cache_percpu __percpu *percpu; - struct notifier_block hotcpu_notifier; - int low_watermark; - int high_watermark; - struct timer_list rnd_timer; -}; - -atomic_t flow_cache_genid = ATOMIC_INIT(0); -EXPORT_SYMBOL(flow_cache_genid); -static struct flow_cache flow_cache_global; -static struct kmem_cache *flow_cachep __read_mostly; - -static DEFINE_SPINLOCK(flow_cache_gc_lock); -static LIST_HEAD(flow_cache_gc_list); - #define flow_cache_hash_size(cache) (1 << (cache)->hash_shift) #define FLOW_HASH_RND_PERIOD (10 * 60 * HZ) @@ -84,46 +60,50 @@ static void flow_cache_new_hashrnd(unsigned long arg) add_timer(&fc->rnd_timer); } -static int flow_entry_valid(struct flow_cache_entry *fle) +static int flow_entry_valid(struct flow_cache_entry *fle, + struct netns_xfrm *xfrm) { - if (atomic_read(&flow_cache_genid) != fle->genid) + if (atomic_read(&xfrm->flow_cache_genid) != fle->genid) return 0; if (fle->object && !fle->object->ops->check(fle->object)) return 0; return 1; } -static void flow_entry_kill(struct flow_cache_entry *fle) +static void flow_entry_kill(struct flow_cache_entry *fle, + struct netns_xfrm *xfrm) { if (fle->object) fle->object->ops->delete(fle->object); - kmem_cache_free(flow_cachep, fle); + kmem_cache_free(xfrm->flow_cachep, fle); } static void flow_cache_gc_task(struct work_struct *work) { struct list_head gc_list; struct flow_cache_entry *fce, *n; + struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm, + flow_cache_gc_work); INIT_LIST_HEAD(&gc_list); - spin_lock_bh(&flow_cache_gc_lock); - list_splice_tail_init(&flow_cache_gc_list, &gc_list); - spin_unlock_bh(&flow_cache_gc_lock); + spin_lock_bh(&xfrm->flow_cache_gc_lock); + list_splice_tail_init(&xfrm->flow_cache_gc_list, &gc_list); + spin_unlock_bh(&xfrm->flow_cache_gc_lock); list_for_each_entry_safe(fce, n, &gc_list, u.gc_list) - flow_entry_kill(fce); + flow_entry_kill(fce, xfrm); } -static DECLARE_WORK(flow_cache_gc_work, flow_cache_gc_task); static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp, - int deleted, struct list_head *gc_list) + int deleted, struct list_head *gc_list, + struct netns_xfrm *xfrm) { if (deleted) { fcp->hash_count -= deleted; - spin_lock_bh(&flow_cache_gc_lock); - list_splice_tail(gc_list, &flow_cache_gc_list); - spin_unlock_bh(&flow_cache_gc_lock); - schedule_work(&flow_cache_gc_work); + spin_lock_bh(&xfrm->flow_cache_gc_lock); + list_splice_tail(gc_list, &xfrm->flow_cache_gc_list); + spin_unlock_bh(&xfrm->flow_cache_gc_lock); + schedule_work(&xfrm->flow_cache_gc_work); } } @@ -135,6 +115,8 @@ static void __flow_cache_shrink(struct flow_cache *fc, struct hlist_node *tmp; LIST_HEAD(gc_list); int i, deleted = 0; + struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm, + flow_cache_global); for (i = 0; i < flow_cache_hash_size(fc); i++) { int saved = 0; @@ -142,7 +124,7 @@ static void __flow_cache_shrink(struct flow_cache *fc, hlist_for_each_entry_safe(fle, tmp, &fcp->hash_table[i], u.hlist) { if (saved < shrink_to && - flow_entry_valid(fle)) { + flow_entry_valid(fle, xfrm)) { saved++; } else { deleted++; @@ -152,7 +134,7 @@ static void __flow_cache_shrink(struct flow_cache *fc, } } - flow_cache_queue_garbage(fcp, deleted, &gc_list); + flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm); } static void flow_cache_shrink(struct flow_cache *fc, @@ -208,7 +190,7 @@ struct flow_cache_object * flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, flow_resolve_t resolver, void *ctx) { - struct flow_cache *fc = &flow_cache_global; + struct flow_cache *fc = &net->xfrm.flow_cache_global; struct flow_cache_percpu *fcp; struct flow_cache_entry *fle, *tfle; struct flow_cache_object *flo; @@ -248,7 +230,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, if (fcp->hash_count > fc->high_watermark) flow_cache_shrink(fc, fcp); - fle = kmem_cache_alloc(flow_cachep, GFP_ATOMIC); + fle = kmem_cache_alloc(net->xfrm.flow_cachep, GFP_ATOMIC); if (fle) { fle->net = net; fle->family = family; @@ -258,7 +240,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]); fcp->hash_count++; } - } else if (likely(fle->genid == atomic_read(&flow_cache_genid))) { + } else if (likely(fle->genid == atomic_read(&net->xfrm.flow_cache_genid))) { flo = fle->object; if (!flo) goto ret_object; @@ -279,7 +261,7 @@ nocache: } flo = resolver(net, key, family, dir, flo, ctx); if (fle) { - fle->genid = atomic_read(&flow_cache_genid); + fle->genid = atomic_read(&net->xfrm.flow_cache_genid); if (!IS_ERR(flo)) fle->object = flo; else @@ -303,12 +285,14 @@ static void flow_cache_flush_tasklet(unsigned long data) struct hlist_node *tmp; LIST_HEAD(gc_list); int i, deleted = 0; + struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm, + flow_cache_global); fcp = this_cpu_ptr(fc->percpu); for (i = 0; i < flow_cache_hash_size(fc); i++) { hlist_for_each_entry_safe(fle, tmp, &fcp->hash_table[i], u.hlist) { - if (flow_entry_valid(fle)) + if (flow_entry_valid(fle, xfrm)) continue; deleted++; @@ -317,7 +301,7 @@ static void flow_cache_flush_tasklet(unsigned long data) } } - flow_cache_queue_garbage(fcp, deleted, &gc_list); + flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm); if (atomic_dec_and_test(&info->cpuleft)) complete(&info->completion); @@ -351,10 +335,9 @@ static void flow_cache_flush_per_cpu(void *data) tasklet_schedule(tasklet); } -void flow_cache_flush(void) +void flow_cache_flush(struct net *net) { struct flow_flush_info info; - static DEFINE_MUTEX(flow_flush_sem); cpumask_var_t mask; int i, self; @@ -365,8 +348,8 @@ void flow_cache_flush(void) /* Don't want cpus going down or up during this. */ get_online_cpus(); - mutex_lock(&flow_flush_sem); - info.cache = &flow_cache_global; + mutex_lock(&net->xfrm.flow_flush_sem); + info.cache = &net->xfrm.flow_cache_global; for_each_online_cpu(i) if (!flow_cache_percpu_empty(info.cache, i)) cpumask_set_cpu(i, mask); @@ -386,21 +369,23 @@ void flow_cache_flush(void) wait_for_completion(&info.completion); done: - mutex_unlock(&flow_flush_sem); + mutex_unlock(&net->xfrm.flow_flush_sem); put_online_cpus(); free_cpumask_var(mask); } static void flow_cache_flush_task(struct work_struct *work) { - flow_cache_flush(); + struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm, + flow_cache_gc_work); + struct net *net = container_of(xfrm, struct net, xfrm); + + flow_cache_flush(net); } -static DECLARE_WORK(flow_cache_flush_work, flow_cache_flush_task); - -void flow_cache_flush_deferred(void) +void flow_cache_flush_deferred(struct net *net) { - schedule_work(&flow_cache_flush_work); + schedule_work(&net->xfrm.flow_cache_flush_work); } static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) @@ -425,7 +410,8 @@ static int flow_cache_cpu(struct notifier_block *nfb, unsigned long action, void *hcpu) { - struct flow_cache *fc = container_of(nfb, struct flow_cache, hotcpu_notifier); + struct flow_cache *fc = container_of(nfb, struct flow_cache, + hotcpu_notifier); int res, cpu = (unsigned long) hcpu; struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu); @@ -444,9 +430,20 @@ static int flow_cache_cpu(struct notifier_block *nfb, return NOTIFY_OK; } -static int __init flow_cache_init(struct flow_cache *fc) +int flow_cache_init(struct net *net) { int i; + struct flow_cache *fc = &net->xfrm.flow_cache_global; + + /* Initialize per-net flow cache global variables here */ + net->xfrm.flow_cachep = kmem_cache_create("flow_cache", + sizeof(struct flow_cache_entry), + 0, SLAB_PANIC, NULL); + spin_lock_init(&net->xfrm.flow_cache_gc_lock); + INIT_LIST_HEAD(&net->xfrm.flow_cache_gc_list); + INIT_WORK(&net->xfrm.flow_cache_gc_work, flow_cache_gc_task); + INIT_WORK(&net->xfrm.flow_cache_flush_work, flow_cache_flush_task); + mutex_init(&net->xfrm.flow_flush_sem); fc->hash_shift = 10; fc->low_watermark = 2 * flow_cache_hash_size(fc); @@ -484,14 +481,4 @@ err: return -ENOMEM; } - -static int __init flow_cache_init_global(void) -{ - flow_cachep = kmem_cache_create("flow_cache", - sizeof(struct flow_cache_entry), - 0, SLAB_PANIC, NULL); - - return flow_cache_init(&flow_cache_global); -} - -module_init(flow_cache_init_global); +EXPORT_SYMBOL(flow_cache_init); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 4b98b25793c5..2232c6f26aff 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -661,7 +661,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) hlist_add_head(&policy->bydst, chain); xfrm_pol_hold(policy); net->xfrm.policy_count[dir]++; - atomic_inc(&flow_cache_genid); + atomic_inc(&net->xfrm.flow_cache_genid); /* After previous checking, family can either be AF_INET or AF_INET6 */ if (policy->family == AF_INET) @@ -2567,14 +2567,14 @@ static void __xfrm_garbage_collect(struct net *net) void xfrm_garbage_collect(struct net *net) { - flow_cache_flush(); + flow_cache_flush(net); __xfrm_garbage_collect(net); } EXPORT_SYMBOL(xfrm_garbage_collect); static void xfrm_garbage_collect_deferred(struct net *net) { - flow_cache_flush_deferred(); + flow_cache_flush_deferred(net); __xfrm_garbage_collect(net); } @@ -2947,6 +2947,7 @@ static int __net_init xfrm_net_init(struct net *net) spin_lock_init(&net->xfrm.xfrm_policy_sk_bundle_lock); mutex_init(&net->xfrm.xfrm_cfg_mutex); + flow_cache_init(net); return 0; out_sysctl: diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h index 48c3cc94c168..dfe3fda7e5f7 100644 --- a/security/selinux/include/xfrm.h +++ b/security/selinux/include/xfrm.h @@ -45,10 +45,11 @@ static inline void selinux_xfrm_notify_policyload(void) { struct net *net; - atomic_inc(&flow_cache_genid); rtnl_lock(); - for_each_net(net) + for_each_net(net) { + atomic_inc(&net->xfrm.flow_cache_genid); rt_genid_bump_all(net); + } rtnl_unlock(); } #else From 5826bdd1816fa2baa122b62e14905c0ad8e7b96a Mon Sep 17 00:00:00 2001 From: Fan Du Date: Sat, 18 Jan 2014 09:55:28 +0800 Subject: [PATCH 08/13] flowcache: Bring net/core/flow.c under IPsec maintain scope As flow cache is mainly manipulated from IPsec. Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 091b50edaf35..f6bc6184ed6f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5992,6 +5992,7 @@ L: netdev@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next.git S: Maintained +F: net/core/flow.c F: net/xfrm/ F: net/key/ F: net/ipv4/xfrm* From 0f24558e91563888d51e9be5b70981da920c37ac Mon Sep 17 00:00:00 2001 From: Horia Geanta Date: Wed, 12 Feb 2014 16:20:06 +0200 Subject: [PATCH 09/13] xfrm: avoid creating temporary SA when there are no listeners In the case when KMs have no listeners, km_query() will fail and temporary SAs are garbage collected immediately after their allocation. This causes strain on memory allocation, leading even to OOM since temporary SA alloc/free cycle is performed for every packet and garbage collection does not keep up the pace. The sane thing to do is to make sure we have audience before temporary SA allocation. Signed-off-by: Horia Geanta Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 15 +++++++++++++++ net/key/af_key.c | 19 +++++++++++++++++++ net/xfrm/xfrm_state.c | 31 +++++++++++++++++++++++++++++++ net/xfrm/xfrm_user.c | 6 ++++++ 4 files changed, 71 insertions(+) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index afa5730fb3bd..5313ccfdeedf 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -594,6 +594,7 @@ struct xfrm_mgr { const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k); + bool (*is_alive)(const struct km_event *c); }; int xfrm_register_km(struct xfrm_mgr *km); @@ -1646,6 +1647,20 @@ static inline int xfrm_aevent_is_on(struct net *net) rcu_read_unlock(); return ret; } + +static inline int xfrm_acquire_is_on(struct net *net) +{ + struct sock *nlsk; + int ret = 0; + + rcu_read_lock(); + nlsk = rcu_dereference(net->xfrm.nlsk); + if (nlsk) + ret = netlink_has_listeners(nlsk, XFRMNLGRP_ACQUIRE); + rcu_read_unlock(); + + return ret; +} #endif static inline int xfrm_alg_len(const struct xfrm_algo *alg) diff --git a/net/key/af_key.c b/net/key/af_key.c index 1a04c1329362..e1c69d024197 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3059,6 +3059,24 @@ static u32 get_acqseq(void) return res; } +static bool pfkey_is_alive(const struct km_event *c) +{ + struct netns_pfkey *net_pfkey = net_generic(c->net, pfkey_net_id); + struct sock *sk; + bool is_alive = false; + + rcu_read_lock(); + sk_for_each_rcu(sk, &net_pfkey->table) { + if (pfkey_sk(sk)->registered) { + is_alive = true; + break; + } + } + rcu_read_unlock(); + + return is_alive; +} + static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *xp) { struct sk_buff *skb; @@ -3784,6 +3802,7 @@ static struct xfrm_mgr pfkeyv2_mgr = .new_mapping = pfkey_send_new_mapping, .notify_policy = pfkey_send_policy_notify, .migrate = pfkey_send_migrate, + .is_alive = pfkey_is_alive, }; static int __net_init pfkey_net_init(struct net *net) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index a26b7aa79475..0bf12f665b9b 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -161,6 +161,7 @@ static DEFINE_SPINLOCK(xfrm_state_gc_lock); int __xfrm_state_delete(struct xfrm_state *x); int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); +bool km_is_alive(const struct km_event *c); void km_state_expired(struct xfrm_state *x, int hard, u32 portid); static DEFINE_SPINLOCK(xfrm_type_lock); @@ -788,6 +789,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, struct xfrm_state *best = NULL; u32 mark = pol->mark.v & pol->mark.m; unsigned short encap_family = tmpl->encap_family; + struct km_event c; to_put = NULL; @@ -832,6 +834,17 @@ found: error = -EEXIST; goto out; } + + c.net = net; + /* If the KMs have no listeners (yet...), avoid allocating an SA + * for each and every packet - garbage collection might not + * handle the flood. + */ + if (!km_is_alive(&c)) { + error = -ESRCH; + goto out; + } + x = xfrm_state_alloc(net); if (x == NULL) { error = -ENOMEM; @@ -1793,6 +1806,24 @@ int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address } EXPORT_SYMBOL(km_report); +bool km_is_alive(const struct km_event *c) +{ + struct xfrm_mgr *km; + bool is_alive = false; + + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) { + if (km->is_alive && km->is_alive(c)) { + is_alive = true; + break; + } + } + rcu_read_unlock(); + + return is_alive; +} +EXPORT_SYMBOL(km_is_alive); + int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen) { int err; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index ade9988f6e33..d7694f258294 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2982,6 +2982,11 @@ static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MAPPING, GFP_ATOMIC); } +static bool xfrm_is_alive(const struct km_event *c) +{ + return (bool)xfrm_acquire_is_on(c->net); +} + static struct xfrm_mgr netlink_mgr = { .id = "netlink", .notify = xfrm_send_state_notify, @@ -2991,6 +2996,7 @@ static struct xfrm_mgr netlink_mgr = { .report = xfrm_send_report, .migrate = xfrm_send_migrate, .new_mapping = xfrm_send_mapping, + .is_alive = xfrm_is_alive, }; static int __net_init xfrm_user_net_init(struct net *net) From d3623099d3509fa68fa28235366049dd3156c63a Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 14 Feb 2014 15:30:36 +0100 Subject: [PATCH 10/13] ipsec: add support of limited SA dump The goal of this patch is to allow userland to dump only a part of SA by specifying a filter during the dump. The kernel is in charge to filter SA, this avoids to generate useless netlink traffic (it save also some cpu cycles). This is particularly useful when there is a big number of SA set on the system. Note that I removed the union in struct xfrm_state_walk to fix a problem on arm. struct netlink_callback->args is defined as a array of 6 long and the first long is used in xfrm code to flag the cb as initialized. Hence, we must have: sizeof(struct xfrm_state_walk) <= sizeof(long) * 5. With the union, it was false on arm (sizeof(struct xfrm_state_walk) was sizeof(long) * 7), due to the padding. In fact, whatever the arch is, this union seems useless, there will be always padding after it. Removing it will not increase the size of this struct (and reduce it on arm). Signed-off-by: Nicolas Dichtel Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 10 +++++----- include/uapi/linux/pfkeyv2.h | 15 ++++++++++++++- include/uapi/linux/xfrm.h | 10 ++++++++++ net/key/af_key.c | 19 ++++++++++++++++++- net/xfrm/xfrm_state.c | 25 ++++++++++++++++++++++++- net/xfrm/xfrm_user.c | 28 +++++++++++++++++++++++++++- 6 files changed, 98 insertions(+), 9 deletions(-) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 5313ccfdeedf..45332acac022 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -118,11 +118,10 @@ struct xfrm_state_walk { struct list_head all; u8 state; - union { - u8 dying; - u8 proto; - }; + u8 dying; + u8 proto; u32 seq; + struct xfrm_filter *filter; }; /* Full description of state of transformer. */ @@ -1406,7 +1405,8 @@ static inline void xfrm_sysctl_fini(struct net *net) } #endif -void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto); +void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto, + struct xfrm_filter *filter); int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *); void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net); diff --git a/include/uapi/linux/pfkeyv2.h b/include/uapi/linux/pfkeyv2.h index 0b80c806631f..ada7f0171ccc 100644 --- a/include/uapi/linux/pfkeyv2.h +++ b/include/uapi/linux/pfkeyv2.h @@ -235,6 +235,18 @@ struct sadb_x_kmaddress { } __attribute__((packed)); /* sizeof(struct sadb_x_kmaddress) == 8 */ +/* To specify the SA dump filter */ +struct sadb_x_filter { + __u16 sadb_x_filter_len; + __u16 sadb_x_filter_exttype; + __u32 sadb_x_filter_saddr[4]; + __u32 sadb_x_filter_daddr[4]; + __u16 sadb_x_filter_family; + __u8 sadb_x_filter_splen; + __u8 sadb_x_filter_dplen; +} __attribute__((packed)); +/* sizeof(struct sadb_x_filter) == 40 */ + /* Message types */ #define SADB_RESERVED 0 #define SADB_GETSPI 1 @@ -358,7 +370,8 @@ struct sadb_x_kmaddress { #define SADB_X_EXT_SEC_CTX 24 /* Used with MIGRATE to pass @ to IKE for negotiation */ #define SADB_X_EXT_KMADDRESS 25 -#define SADB_EXT_MAX 25 +#define SADB_X_EXT_FILTER 26 +#define SADB_EXT_MAX 26 /* Identity Extension values */ #define SADB_IDENTTYPE_RESERVED 0 diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index a8cd6a4a2970..6550c679584f 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -298,6 +298,8 @@ enum xfrm_attr_type_t { XFRMA_TFCPAD, /* __u32 */ XFRMA_REPLAY_ESN_VAL, /* struct xfrm_replay_esn */ XFRMA_SA_EXTRA_FLAGS, /* __u32 */ + XFRMA_PROTO, /* __u8 */ + XFRMA_FILTER, /* struct xfrm_filter */ __XFRMA_MAX #define XFRMA_MAX (__XFRMA_MAX - 1) @@ -474,6 +476,14 @@ struct xfrm_user_mapping { __be16 new_sport; }; +struct xfrm_filter { + xfrm_address_t saddr; + xfrm_address_t daddr; + __u16 family; + __u8 splen; + __u8 dplen; +}; + #ifndef __KERNEL__ /* backwards compatibility for userspace */ #define XFRMGRP_ACQUIRE 1 diff --git a/net/key/af_key.c b/net/key/af_key.c index e1c69d024197..f0879c19f452 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1798,6 +1798,7 @@ static void pfkey_dump_sa_done(struct pfkey_sock *pfk) static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { u8 proto; + struct xfrm_filter *filter = NULL; struct pfkey_sock *pfk = pfkey_sk(sk); if (pfk->dump.dump != NULL) @@ -1807,11 +1808,27 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms if (proto == 0) return -EINVAL; + if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { + struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; + + filter = kmalloc(sizeof(*filter), GFP_KERNEL); + if (filter == NULL) + return -ENOMEM; + + memcpy(&filter->saddr, &xfilter->sadb_x_filter_saddr, + sizeof(xfrm_address_t)); + memcpy(&filter->daddr, &xfilter->sadb_x_filter_daddr, + sizeof(xfrm_address_t)); + filter->family = xfilter->sadb_x_filter_family; + filter->splen = xfilter->sadb_x_filter_splen; + filter->dplen = xfilter->sadb_x_filter_dplen; + } + pfk->dump.msg_version = hdr->sadb_msg_version; pfk->dump.msg_portid = hdr->sadb_msg_pid; pfk->dump.dump = pfkey_dump_sa; pfk->dump.done = pfkey_dump_sa_done; - xfrm_state_walk_init(&pfk->dump.u.state, proto); + xfrm_state_walk_init(&pfk->dump.u.state, proto, filter); return pfkey_do_dump(pfk); } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 0bf12f665b9b..a750901ac3db 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1603,6 +1603,23 @@ unlock: } EXPORT_SYMBOL(xfrm_alloc_spi); +static bool __xfrm_state_filter_match(struct xfrm_state *x, + struct xfrm_filter *filter) +{ + if (filter) { + if ((filter->family == AF_INET || + filter->family == AF_INET6) && + x->props.family != filter->family) + return false; + + return addr_match(&x->props.saddr, &filter->saddr, + filter->splen) && + addr_match(&x->id.daddr, &filter->daddr, + filter->dplen); + } + return true; +} + int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *data) @@ -1625,6 +1642,8 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, state = container_of(x, struct xfrm_state, km); if (!xfrm_id_proto_match(state->id.proto, walk->proto)) continue; + if (!__xfrm_state_filter_match(state, walk->filter)) + continue; err = func(state, walk->seq, data); if (err) { list_move_tail(&walk->all, &x->all); @@ -1643,17 +1662,21 @@ out: } EXPORT_SYMBOL(xfrm_state_walk); -void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto) +void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto, + struct xfrm_filter *filter) { INIT_LIST_HEAD(&walk->all); walk->proto = proto; walk->state = XFRM_STATE_DEAD; walk->seq = 0; + walk->filter = filter; } EXPORT_SYMBOL(xfrm_state_walk_init); void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net) { + kfree(walk->filter); + if (list_empty(&walk->all)) return; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index d7694f258294..023e5e7ea4c6 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -887,6 +887,7 @@ static int xfrm_dump_sa_done(struct netlink_callback *cb) return 0; } +static const struct nla_policy xfrma_policy[XFRMA_MAX+1]; static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); @@ -902,8 +903,31 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) info.nlmsg_flags = NLM_F_MULTI; if (!cb->args[0]) { + struct nlattr *attrs[XFRMA_MAX+1]; + struct xfrm_filter *filter = NULL; + u8 proto = 0; + int err; + cb->args[0] = 1; - xfrm_state_walk_init(walk, 0); + + err = nlmsg_parse(cb->nlh, 0, attrs, XFRMA_MAX, + xfrma_policy); + if (err < 0) + return err; + + if (attrs[XFRMA_FILTER]) { + filter = kmalloc(sizeof(*filter), GFP_KERNEL); + if (filter == NULL) + return -ENOMEM; + + memcpy(filter, nla_data(attrs[XFRMA_FILTER]), + sizeof(*filter)); + } + + if (attrs[XFRMA_PROTO]) + proto = nla_get_u8(attrs[XFRMA_PROTO]); + + xfrm_state_walk_init(walk, proto, filter); } (void) xfrm_state_walk(net, walk, dump_one_state, &info); @@ -2309,6 +2333,8 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_TFCPAD] = { .type = NLA_U32 }, [XFRMA_REPLAY_ESN_VAL] = { .len = sizeof(struct xfrm_replay_state_esn) }, [XFRMA_SA_EXTRA_FLAGS] = { .type = NLA_U32 }, + [XFRMA_PROTO] = { .type = NLA_U8 }, + [XFRMA_FILTER] = { .len = sizeof(struct xfrm_filter) }, }; static const struct xfrm_link { From 1a1ccc96abb2ed9b8fbb71018e64b97324caef53 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Wed, 19 Feb 2014 10:07:34 +0100 Subject: [PATCH 11/13] xfrm: Remove caching of xfrm_policy_sk_bundles We currently cache socket policy bundles at xfrm_policy_sk_bundles. These cached bundles are never used. Instead we create and cache a new one whenever xfrm_lookup() is called on a socket policy. Most protocols cache the used routes to the socket, so let's remove the unused caching of socket policy bundles in xfrm. Signed-off-by: Steffen Klassert --- include/net/netns/xfrm.h | 1 - net/xfrm/xfrm_policy.c | 28 ---------------------------- 2 files changed, 29 deletions(-) diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 52d0086d55d3..51f0dce7b643 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -59,7 +59,6 @@ struct netns_xfrm { struct dst_ops xfrm6_dst_ops; #endif spinlock_t xfrm_state_lock; - spinlock_t xfrm_policy_sk_bundle_lock; rwlock_t xfrm_policy_lock; struct mutex xfrm_cfg_mutex; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 2232c6f26aff..bb3669d973a7 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -39,8 +39,6 @@ #define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ)) #define XFRM_MAX_QUEUE_LEN 100 -static struct dst_entry *xfrm_policy_sk_bundles; - static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO] __read_mostly; @@ -2109,13 +2107,6 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, goto no_transform; } - dst_hold(&xdst->u.dst); - - spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); - xdst->u.dst.next = xfrm_policy_sk_bundles; - xfrm_policy_sk_bundles = &xdst->u.dst; - spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); - route = xdst->route; } } @@ -2549,33 +2540,15 @@ static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst) return dst; } -static void __xfrm_garbage_collect(struct net *net) -{ - struct dst_entry *head, *next; - - spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); - head = xfrm_policy_sk_bundles; - xfrm_policy_sk_bundles = NULL; - spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); - - while (head) { - next = head->next; - dst_free(head); - head = next; - } -} - void xfrm_garbage_collect(struct net *net) { flow_cache_flush(net); - __xfrm_garbage_collect(net); } EXPORT_SYMBOL(xfrm_garbage_collect); static void xfrm_garbage_collect_deferred(struct net *net) { flow_cache_flush_deferred(net); - __xfrm_garbage_collect(net); } static void xfrm_init_pmtu(struct dst_entry *dst) @@ -2944,7 +2917,6 @@ static int __net_init xfrm_net_init(struct net *net) /* Initialize the per-net locks here */ spin_lock_init(&net->xfrm.xfrm_state_lock); rwlock_init(&net->xfrm.xfrm_policy_lock); - spin_lock_init(&net->xfrm.xfrm_policy_sk_bundle_lock); mutex_init(&net->xfrm.xfrm_cfg_mutex); flow_cache_init(net); From d2c5f6582515362328b33b2a331a17e141ef0d40 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 20 Feb 2014 14:52:41 +0100 Subject: [PATCH 12/13] pfkey: fix SADB_X_EXT_FILTER length check This patch fixes commit d3623099d350 ("ipsec: add support of limited SA dump"). sadb_ext_min_len array should be updated with the new type (SADB_X_EXT_FILTER). Reported-by: Dan Carpenter Signed-off-by: Nicolas Dichtel Signed-off-by: Steffen Klassert --- net/key/af_key.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/key/af_key.c b/net/key/af_key.c index f0879c19f452..a50d979b5926 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -365,6 +365,7 @@ static const u8 sadb_ext_min_len[] = { [SADB_X_EXT_NAT_T_OA] = (u8) sizeof(struct sadb_address), [SADB_X_EXT_SEC_CTX] = (u8) sizeof(struct sadb_x_sec_ctx), [SADB_X_EXT_KMADDRESS] = (u8) sizeof(struct sadb_x_kmaddress), + [SADB_X_EXT_FILTER] = (u8) sizeof(struct sadb_x_filter), }; /* Verify sadb_address_{len,prefixlen} against sa_family. */ From cc9ab60e57964d463ff31b9621c8d7e786aee042 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Wed, 19 Feb 2014 13:33:24 +0100 Subject: [PATCH 13/13] xfrm: Cleanup error handling of xfrm_state_clone The error pointer passed to xfrm_state_clone() is unchecked, so remove it and indicate an error by returning a null pointer. Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_state.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index a750901ac3db..5339c26bb0cf 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1148,10 +1148,9 @@ out: EXPORT_SYMBOL(xfrm_state_add); #ifdef CONFIG_XFRM_MIGRATE -static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) +static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig) { struct net *net = xs_net(orig); - int err = -ENOMEM; struct xfrm_state *x = xfrm_state_alloc(net); if (!x) goto out; @@ -1200,15 +1199,13 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) } if (orig->replay_esn) { - err = xfrm_replay_clone(x, orig); - if (err) + if (xfrm_replay_clone(x, orig)) goto error; } memcpy(&x->mark, &orig->mark, sizeof(x->mark)); - err = xfrm_init_state(x); - if (err) + if (xfrm_init_state(x) < 0) goto error; x->props.flags = orig->props.flags; @@ -1223,8 +1220,6 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) error: xfrm_state_put(x); out: - if (errp) - *errp = err; return NULL; } @@ -1276,9 +1271,8 @@ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m) { struct xfrm_state *xc; - int err; - xc = xfrm_state_clone(x, &err); + xc = xfrm_state_clone(x); if (!xc) return NULL; @@ -1291,7 +1285,7 @@ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, state is to be updated as it is a part of triplet */ xfrm_state_insert(xc); } else { - if ((err = xfrm_state_add(xc)) < 0) + if (xfrm_state_add(xc) < 0) goto error; }