From 9b3eb54106cf6acd03f07cf0ab01c13676a226c2 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Wed, 3 May 2017 16:43:19 +0200 Subject: xfrm: fix stack access out of bounds with CONFIG_XFRM_SUB_POLICY When CONFIG_XFRM_SUB_POLICY=y, xfrm_dst stores a copy of the flowi for that dst. Unfortunately, the code that allocates and fills this copy doesn't care about what type of flowi (flowi, flowi4, flowi6) gets passed. In multiple code paths (from raw_sendmsg, from TCP when replying to a FIN, in vxlan, geneve, and gre), the flowi that gets passed to xfrm is actually an on-stack flowi4, so we end up reading stuff from the stack past the end of the flowi4 struct. Since xfrm_dst->origin isn't used anywhere following commit ca116922afa8 ("xfrm: Eliminate "fl" and "pol" args to xfrm_bundle_ok()."), just get rid of it. xfrm_dst->partner isn't used either, so get rid of that too. Fixes: 9d6ec938019c ("ipv4: Use flowi4 in public route lookup interfaces.") Signed-off-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 6793a30c66b1..7e7e2b0d2915 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -979,10 +979,6 @@ struct xfrm_dst { struct flow_cache_object flo; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int num_pols, num_xfrms; -#ifdef CONFIG_XFRM_SUB_POLICY - struct flowi *origin; - struct xfrm_selector *partner; -#endif u32 xfrm_genid; u32 policy_genid; u32 route_mtu_cached; @@ -998,12 +994,6 @@ static inline void xfrm_dst_destroy(struct xfrm_dst *xdst) dst_release(xdst->route); if (likely(xdst->u.dst.xfrm)) xfrm_state_put(xdst->u.dst.xfrm); -#ifdef CONFIG_XFRM_SUB_POLICY - kfree(xdst->origin); - xdst->origin = NULL; - kfree(xdst->partner); - xdst->partner = NULL; -#endif } #endif -- cgit v1.3-14-g43fede From d91fc59cd77c719f33eda65c194ad8f95a055190 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sun, 7 May 2017 22:01:55 +0800 Subject: netfilter: introduce nf_conntrack_helper_put helper function And convert module_put invocation to nf_conntrack_helper_put, this is prepared for the followup patch, which will add a refcnt for cthelper, so we can reject the deleting request when cthelper is in use. Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_helper.h | 2 ++ net/netfilter/nf_conntrack_helper.c | 6 ++++++ net/netfilter/nft_ct.c | 4 ++-- net/netfilter/xt_CT.c | 6 +++--- net/openvswitch/conntrack.c | 4 ++-- 5 files changed, 15 insertions(+), 7 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index e04fa7691e5d..c1c12411103a 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -79,6 +79,8 @@ struct nf_conntrack_helper *__nf_conntrack_helper_find(const char *name, struct nf_conntrack_helper *nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum); +void nf_conntrack_helper_put(struct nf_conntrack_helper *helper); + void nf_ct_helper_init(struct nf_conntrack_helper *helper, u16 l3num, u16 protonum, const char *name, u16 default_port, u16 spec_port, u32 id, diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 3a60efa7799b..e17006b6e434 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -181,6 +181,12 @@ nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum) } EXPORT_SYMBOL_GPL(nf_conntrack_helper_try_module_get); +void nf_conntrack_helper_put(struct nf_conntrack_helper *helper) +{ + module_put(helper->me); +} +EXPORT_SYMBOL_GPL(nf_conntrack_helper_put); + struct nf_conn_help * nf_ct_helper_ext_add(struct nf_conn *ct, struct nf_conntrack_helper *helper, gfp_t gfp) diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index a34ceb38fc55..1678e9e75e8e 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -826,9 +826,9 @@ static void nft_ct_helper_obj_destroy(struct nft_object *obj) struct nft_ct_helper_obj *priv = nft_obj_data(obj); if (priv->helper4) - module_put(priv->helper4->me); + nf_conntrack_helper_put(priv->helper4); if (priv->helper6) - module_put(priv->helper6->me); + nf_conntrack_helper_put(priv->helper6); } static void nft_ct_helper_obj_eval(struct nft_object *obj, diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index bb7ad82dcd56..623ef37de886 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -96,7 +96,7 @@ xt_ct_set_helper(struct nf_conn *ct, const char *helper_name, help = nf_ct_helper_ext_add(ct, helper, GFP_KERNEL); if (help == NULL) { - module_put(helper->me); + nf_conntrack_helper_put(helper); return -ENOMEM; } @@ -263,7 +263,7 @@ out: err4: help = nfct_help(ct); if (help) - module_put(help->helper->me); + nf_conntrack_helper_put(help->helper); err3: nf_ct_tmpl_free(ct); err2: @@ -346,7 +346,7 @@ static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par, if (ct) { help = nfct_help(ct); if (help) - module_put(help->helper->me); + nf_conntrack_helper_put(help->helper); nf_ct_netns_put(par->net, par->family); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index bf602e33c40a..08679ebb3068 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1123,7 +1123,7 @@ static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, help = nf_ct_helper_ext_add(info->ct, helper, GFP_KERNEL); if (!help) { - module_put(helper->me); + nf_conntrack_helper_put(helper); return -ENOMEM; } @@ -1584,7 +1584,7 @@ void ovs_ct_free_action(const struct nlattr *a) static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info) { if (ct_info->helper) - module_put(ct_info->helper->me); + nf_conntrack_helper_put(ct_info->helper); if (ct_info->ct) nf_ct_tmpl_free(ct_info->ct); } -- cgit v1.3-14-g43fede From 9338d7b4418e9996a7642867d8f6b482a6040ed6 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sun, 7 May 2017 22:01:56 +0800 Subject: netfilter: nfnl_cthelper: reject del request if helper obj is in use We can still delete the ct helper even if it is in use, this will cause a use-after-free error. In more detail, I mean: # nfct helper add ssdp inet udp # iptables -t raw -A OUTPUT -p udp -j CT --helper ssdp # nfct helper delete ssdp //--> oops, succeed! BUG: unable to handle kernel paging request at 000026ca IP: 0x26ca [...] Call Trace: ? ipv4_helper+0x62/0x80 [nf_conntrack_ipv4] nf_hook_slow+0x21/0xb0 ip_output+0xe9/0x100 ? ip_fragment.constprop.54+0xc0/0xc0 ip_local_out+0x33/0x40 ip_send_skb+0x16/0x80 udp_send_skb+0x84/0x240 udp_sendmsg+0x35d/0xa50 So add reference count to fix this issue, if ct helper is used by others, reject the delete request. Apply this patch: # nfct helper delete ssdp nfct v1.4.3: netlink error: Device or resource busy Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_helper.h | 2 ++ net/netfilter/nf_conntrack_helper.c | 6 ++++++ net/netfilter/nfnetlink_cthelper.c | 17 +++++++++++------ 3 files changed, 19 insertions(+), 6 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index c1c12411103a..c519bb5b5bb8 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -9,6 +9,7 @@ #ifndef _NF_CONNTRACK_HELPER_H #define _NF_CONNTRACK_HELPER_H +#include #include #include #include @@ -26,6 +27,7 @@ struct nf_conntrack_helper { struct hlist_node hnode; /* Internal use. */ char name[NF_CT_HELPER_NAME_LEN]; /* name of the module */ + refcount_t refcnt; struct module *me; /* pointer to self */ const struct nf_conntrack_expect_policy *expect_policy; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index e17006b6e434..7f6100ca63be 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -174,6 +174,10 @@ nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum) #endif if (h != NULL && !try_module_get(h->me)) h = NULL; + if (h != NULL && !refcount_inc_not_zero(&h->refcnt)) { + module_put(h->me); + h = NULL; + } rcu_read_unlock(); @@ -183,6 +187,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_helper_try_module_get); void nf_conntrack_helper_put(struct nf_conntrack_helper *helper) { + refcount_dec(&helper->refcnt); module_put(helper->me); } EXPORT_SYMBOL_GPL(nf_conntrack_helper_put); @@ -423,6 +428,7 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) } } } + refcount_set(&me->refcnt, 1); hlist_add_head_rcu(&me->hnode, &nf_ct_helper_hash[h]); nf_ct_helper_count++; out: diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 950bf6eadc65..be678a323598 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -686,6 +686,7 @@ static int nfnl_cthelper_del(struct net *net, struct sock *nfnl, tuple_set = true; } + ret = -ENOENT; list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) { cur = &nlcth->helper; j++; @@ -699,16 +700,20 @@ static int nfnl_cthelper_del(struct net *net, struct sock *nfnl, tuple.dst.protonum != cur->tuple.dst.protonum)) continue; - found = true; - nf_conntrack_helper_unregister(cur); - kfree(cur->expect_policy); + if (refcount_dec_if_one(&cur->refcnt)) { + found = true; + nf_conntrack_helper_unregister(cur); + kfree(cur->expect_policy); - list_del(&nlcth->list); - kfree(nlcth); + list_del(&nlcth->list); + kfree(nlcth); + } else { + ret = -EBUSY; + } } /* Make sure we return success if we flush and there is no helpers */ - return (found || j == 0) ? 0 : -ENOENT; + return (found || j == 0) ? 0 : ret; } static const struct nla_policy nfnl_cthelper_policy[NFCTH_MAX+1] = { -- cgit v1.3-14-g43fede From 591054469b3eef34bc097c30fae8ededddf8d796 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 15 May 2017 11:17:34 +0100 Subject: netfilter: nf_tables: revisit chain/object refcounting from elements Andreas reports that the following incremental update using our commit protocol doesn't work. # nft -f incremental-update.nft delete element ip filter client_to_any { 10.180.86.22 : goto CIn_1 } delete chain ip filter CIn_1 ... Error: Could not process rule: Device or resource busy The existing code is not well-integrated into the commit phase protocol, since element deletions do not result in refcount decrement from the preparation phase. This results in bogus EBUSY errors like the one above. Two new functions come with this patch: * nft_set_elem_activate() function is used from the abort path, to restore the set element refcounting on objects that occurred from the preparation phase. * nft_set_elem_deactivate() that is called from nft_del_setelem() to decrement set element refcounting on objects from the preparation phase in the commit protocol. The nft_data_uninit() has been renamed to nft_data_release() since this function does not uninitialize any data store in the data register, instead just releases the references to objects. Moreover, a new function nft_data_hold() has been introduced to be used from nft_set_elem_activate(). Reported-by: Andreas Schultz Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 +- net/netfilter/nf_tables_api.c | 82 ++++++++++++++++++++++++++++++++++----- net/netfilter/nft_bitwise.c | 4 +- net/netfilter/nft_cmp.c | 2 +- net/netfilter/nft_immediate.c | 5 ++- net/netfilter/nft_range.c | 4 +- 6 files changed, 81 insertions(+), 18 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 028faec8fc27..8a8bab8d7b15 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -176,7 +176,7 @@ struct nft_data_desc { int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data, unsigned int size, struct nft_data_desc *desc, const struct nlattr *nla); -void nft_data_uninit(const struct nft_data *data, enum nft_data_types type); +void nft_data_release(const struct nft_data *data, enum nft_data_types type); int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data, enum nft_data_types type, unsigned int len); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5f4a4d48b871..da314be0c048 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3627,9 +3627,9 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, { struct nft_set_ext *ext = nft_set_elem_ext(set, elem); - nft_data_uninit(nft_set_ext_key(ext), NFT_DATA_VALUE); + nft_data_release(nft_set_ext_key(ext), NFT_DATA_VALUE); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) - nft_data_uninit(nft_set_ext_data(ext), set->dtype); + nft_data_release(nft_set_ext_data(ext), set->dtype); if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) nf_tables_expr_destroy(NULL, nft_set_ext_expr(ext)); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) @@ -3638,6 +3638,18 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); +/* Only called from commit path, nft_set_elem_deactivate() already deals with + * the refcounting from the preparation phase. + */ +static void nf_tables_set_elem_destroy(const struct nft_set *set, void *elem) +{ + struct nft_set_ext *ext = nft_set_elem_ext(set, elem); + + if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) + nf_tables_expr_destroy(NULL, nft_set_ext_expr(ext)); + kfree(elem); +} + static int nft_setelem_parse_flags(const struct nft_set *set, const struct nlattr *attr, u32 *flags) { @@ -3849,9 +3861,9 @@ err4: kfree(elem.priv); err3: if (nla[NFTA_SET_ELEM_DATA] != NULL) - nft_data_uninit(&data, d2.type); + nft_data_release(&data, d2.type); err2: - nft_data_uninit(&elem.key.val, d1.type); + nft_data_release(&elem.key.val, d1.type); err1: return err; } @@ -3896,6 +3908,53 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, return err; } +/** + * nft_data_hold - hold a nft_data item + * + * @data: struct nft_data to release + * @type: type of data + * + * Hold a nft_data item. NFT_DATA_VALUE types can be silently discarded, + * NFT_DATA_VERDICT bumps the reference to chains in case of NFT_JUMP and + * NFT_GOTO verdicts. This function must be called on active data objects + * from the second phase of the commit protocol. + */ +static void nft_data_hold(const struct nft_data *data, enum nft_data_types type) +{ + if (type == NFT_DATA_VERDICT) { + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + data->verdict.chain->use++; + break; + } + } +} + +static void nft_set_elem_activate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) +{ + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + + if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) + nft_data_hold(nft_set_ext_data(ext), set->dtype); + if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) + (*nft_set_ext_obj(ext))->use++; +} + +static void nft_set_elem_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) +{ + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + + if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) + nft_data_release(nft_set_ext_data(ext), set->dtype); + if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) + (*nft_set_ext_obj(ext))->use--; +} + static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr) { @@ -3961,6 +4020,8 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, kfree(elem.priv); elem.priv = priv; + nft_set_elem_deactivate(ctx->net, set, &elem); + nft_trans_elem(trans) = elem; list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; @@ -3970,7 +4031,7 @@ err4: err3: kfree(elem.priv); err2: - nft_data_uninit(&elem.key.val, desc.type); + nft_data_release(&elem.key.val, desc.type); err1: return err; } @@ -4777,8 +4838,8 @@ static void nf_tables_commit_release(struct nft_trans *trans) nft_set_destroy(nft_trans_set(trans)); break; case NFT_MSG_DELSETELEM: - nft_set_elem_destroy(nft_trans_elem_set(trans), - nft_trans_elem(trans).priv, true); + nf_tables_set_elem_destroy(nft_trans_elem_set(trans), + nft_trans_elem(trans).priv); break; case NFT_MSG_DELOBJ: nft_obj_destroy(nft_trans_obj(trans)); @@ -5013,6 +5074,7 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb) case NFT_MSG_DELSETELEM: te = (struct nft_trans_elem *)trans->data; + nft_set_elem_activate(net, te->set, &te->elem); te->set->ops->activate(net, te->set, &te->elem); te->set->ndeact--; @@ -5498,7 +5560,7 @@ int nft_data_init(const struct nft_ctx *ctx, EXPORT_SYMBOL_GPL(nft_data_init); /** - * nft_data_uninit - release a nft_data item + * nft_data_release - release a nft_data item * * @data: struct nft_data to release * @type: type of data @@ -5506,7 +5568,7 @@ EXPORT_SYMBOL_GPL(nft_data_init); * Release a nft_data item. NFT_DATA_VALUE types can be silently discarded, * all others need to be released by calling this function. */ -void nft_data_uninit(const struct nft_data *data, enum nft_data_types type) +void nft_data_release(const struct nft_data *data, enum nft_data_types type) { if (type < NFT_DATA_VERDICT) return; @@ -5517,7 +5579,7 @@ void nft_data_uninit(const struct nft_data *data, enum nft_data_types type) WARN_ON(1); } } -EXPORT_SYMBOL_GPL(nft_data_uninit); +EXPORT_SYMBOL_GPL(nft_data_release); int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data, enum nft_data_types type, unsigned int len) diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 96bd4f325b0f..fff8073e2a56 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -99,9 +99,9 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, return 0; err2: - nft_data_uninit(&priv->xor, d2.type); + nft_data_release(&priv->xor, d2.type); err1: - nft_data_uninit(&priv->mask, d1.type); + nft_data_release(&priv->mask, d1.type); return err; } diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index 8c9d0fb19118..c2945eb3397c 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -211,7 +211,7 @@ nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) return &nft_cmp_ops; err1: - nft_data_uninit(&data, desc.type); + nft_data_release(&data, desc.type); return ERR_PTR(-EINVAL); } diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 728baf88295a..4717d7796927 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -65,7 +65,7 @@ static int nft_immediate_init(const struct nft_ctx *ctx, return 0; err1: - nft_data_uninit(&priv->data, desc.type); + nft_data_release(&priv->data, desc.type); return err; } @@ -73,7 +73,8 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); - return nft_data_uninit(&priv->data, nft_dreg_to_type(priv->dreg)); + + return nft_data_release(&priv->data, nft_dreg_to_type(priv->dreg)); } static int nft_immediate_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index 9edc74eedc10..cedb96c3619f 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -102,9 +102,9 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr priv->len = desc_from.len; return 0; err2: - nft_data_uninit(&priv->data_to, desc_to.type); + nft_data_release(&priv->data_to, desc_to.type); err1: - nft_data_uninit(&priv->data_from, desc_from.type); + nft_data_release(&priv->data_from, desc_from.type); return err; } -- cgit v1.3-14-g43fede From 8b0d3ea555876533b6aa61479335be2c9bdb47e7 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 16 May 2017 14:10:33 -0400 Subject: net: dsa: store CPU port pointer in the tree A dsa_switch_tree instance holds a dsa_switch pointer and a port index to identify the switch port to which the CPU is attached. Now that the DSA layer has a dsa_port structure to hold this data, use it to point the switch CPU port. This patch simply substitutes s/dst->cpu_switch/dst->cpu_dp->ds/ and s/dst->cpu_port/dst->cpu_dp->index/. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/b53/b53_common.c | 4 ++-- drivers/net/dsa/bcm_sf2.c | 4 ++-- drivers/net/dsa/mv88e6060.c | 2 +- drivers/net/dsa/qca8k.c | 2 +- include/net/dsa.h | 13 ++++++------- net/dsa/dsa2.c | 14 ++++++-------- net/dsa/legacy.c | 10 ++++------ net/dsa/slave.c | 10 +++++----- net/dsa/tag_brcm.c | 2 +- net/dsa/tag_qca.c | 2 +- net/dsa/tag_trailer.c | 2 +- 11 files changed, 30 insertions(+), 35 deletions(-) (limited to 'include/net') diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index fa0eece21eef..658a12c888a8 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1344,7 +1344,7 @@ EXPORT_SYMBOL(b53_fdb_dump); int b53_br_join(struct dsa_switch *ds, int port, struct net_device *br) { struct b53_device *dev = ds->priv; - s8 cpu_port = ds->dst->cpu_port; + s8 cpu_port = ds->dst->cpu_dp->index; u16 pvlan, reg; unsigned int i; @@ -1390,7 +1390,7 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *br) { struct b53_device *dev = ds->priv; struct b53_vlan *vl = &dev->vlans[0]; - s8 cpu_port = ds->dst->cpu_port; + s8 cpu_port = ds->dst->cpu_dp->index; unsigned int i; u16 pvlan, reg, pvid; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 2be963252ca5..215d41c1e71f 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -228,7 +228,7 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port, struct phy_device *phy) { struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); - s8 cpu_port = ds->dst[ds->index].cpu_port; + s8 cpu_port = ds->dst->cpu_dp->index; unsigned int i; u32 reg; @@ -832,7 +832,7 @@ static int bcm_sf2_sw_set_wol(struct dsa_switch *ds, int port, { struct net_device *p = ds->dst[ds->index].master_netdev; struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); - s8 cpu_port = ds->dst[ds->index].cpu_port; + s8 cpu_port = ds->dst->cpu_dp->index; struct ethtool_wolinfo pwol; p->ethtool_ops->get_wol(p, &pwol); diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c index 5934b7a4c448..dce7fa57eb55 100644 --- a/drivers/net/dsa/mv88e6060.c +++ b/drivers/net/dsa/mv88e6060.c @@ -176,7 +176,7 @@ static int mv88e6060_setup_port(struct dsa_switch *ds, int p) ((p & 0xf) << PORT_VLAN_MAP_DBNUM_SHIFT) | (dsa_is_cpu_port(ds, p) ? ds->enabled_port_mask : - BIT(ds->dst->cpu_port))); + BIT(ds->dst->cpu_dp->index))); /* Port Association Vector: when learning source addresses * of packets, add the address to the address database using diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index a4fd4ccf7b67..942b9ac7f92a 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -507,7 +507,7 @@ qca8k_setup(struct dsa_switch *ds) pr_warn("regmap initialization failed"); /* Initialize CPU port pad mode (xMII type, delays...) */ - phy_mode = of_get_phy_mode(ds->ports[ds->dst->cpu_port].dn); + phy_mode = of_get_phy_mode(ds->dst->cpu_dp->dn); if (phy_mode < 0) { pr_err("Can't find phy-mode for master device\n"); return phy_mode; diff --git a/include/net/dsa.h b/include/net/dsa.h index 8e24677b1c62..118a8bd2fd9a 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -137,10 +137,9 @@ struct dsa_switch_tree { const struct ethtool_ops *master_orig_ethtool_ops; /* - * The switch and port to which the CPU is attached. + * The switch port to which the CPU is attached. */ - struct dsa_switch *cpu_switch; - s8 cpu_port; + struct dsa_port *cpu_dp; /* * Data for the individual switch chips. @@ -251,7 +250,7 @@ struct dsa_switch { static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) { - return !!(ds == ds->dst->cpu_switch && p == ds->dst->cpu_port); + return ds->dst->cpu_dp == &ds->ports[p]; } static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) @@ -279,10 +278,10 @@ static inline u8 dsa_upstream_port(struct dsa_switch *ds) * Else return the (DSA) port number that connects to the * switch that is one hop closer to the cpu. */ - if (dst->cpu_switch == ds) - return dst->cpu_port; + if (dst->cpu_dp->ds == ds) + return dst->cpu_dp->index; else - return ds->rtable[dst->cpu_switch->index]; + return ds->rtable[dst->cpu_dp->ds->index]; } struct switchdev_trans; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 033b3bfb63dc..2ac62349ba12 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -443,8 +443,8 @@ static int dsa_dst_apply(struct dsa_switch_tree *dst) return err; } - if (dst->cpu_switch) { - err = dsa_cpu_port_ethtool_setup(dst->cpu_switch); + if (dst->cpu_dp) { + err = dsa_cpu_port_ethtool_setup(dst->cpu_dp->ds); if (err) return err; } @@ -484,8 +484,8 @@ static void dsa_dst_unapply(struct dsa_switch_tree *dst) dsa_ds_unapply(dst, ds); } - if (dst->cpu_switch) - dsa_cpu_port_ethtool_restore(dst->cpu_switch); + if (dst->cpu_dp) + dsa_cpu_port_ethtool_restore(dst->cpu_dp->ds); pr_info("DSA: tree %d unapplied\n", dst->tree); dst->applied = false; @@ -518,10 +518,8 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, if (!dst->master_netdev) dst->master_netdev = ethernet_dev; - if (!dst->cpu_switch) { - dst->cpu_switch = ds; - dst->cpu_port = index; - } + if (!dst->cpu_dp) + dst->cpu_dp = port; tag_protocol = ds->ops->get_tag_protocol(ds); dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol); diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index ad345c8b0b06..bb28b011ba5a 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -115,13 +115,12 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) continue; if (!strcmp(name, "cpu")) { - if (dst->cpu_switch) { + if (dst->cpu_dp) { netdev_err(dst->master_netdev, "multiple cpu ports?!\n"); return -EINVAL; } - dst->cpu_switch = ds; - dst->cpu_port = i; + dst->cpu_dp = &ds->ports[i]; ds->cpu_port_mask |= 1 << i; } else if (!strcmp(name, "dsa")) { ds->dsa_port_mask |= 1 << i; @@ -144,7 +143,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) * tagging protocol to the preferred tagging format of this * switch. */ - if (dst->cpu_switch == ds) { + if (dst->cpu_dp->ds == ds) { enum dsa_tag_protocol tag_protocol; tag_protocol = ops->get_tag_protocol(ds); @@ -624,7 +623,6 @@ static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, dst->pd = pd; dst->master_netdev = dev; - dst->cpu_port = -1; for (i = 0; i < pd->nr_chips; i++) { struct dsa_switch *ds; @@ -735,7 +733,7 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) dsa_switch_destroy(ds); } - dsa_cpu_port_ethtool_restore(dst->cpu_switch); + dsa_cpu_port_ethtool_restore(dst->cpu_dp->ds); dev_put(dst->master_netdev); } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 7693182df81e..77324c483d14 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -821,8 +821,8 @@ static void dsa_cpu_port_get_ethtool_stats(struct net_device *dev, uint64_t *data) { struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds = dst->cpu_switch; - s8 cpu_port = dst->cpu_port; + struct dsa_switch *ds = dst->cpu_dp->ds; + s8 cpu_port = dst->cpu_dp->index; int count = 0; if (dst->master_ethtool_ops.get_sset_count) { @@ -838,7 +838,7 @@ static void dsa_cpu_port_get_ethtool_stats(struct net_device *dev, static int dsa_cpu_port_get_sset_count(struct net_device *dev, int sset) { struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds = dst->cpu_switch; + struct dsa_switch *ds = dst->cpu_dp->ds; int count = 0; if (dst->master_ethtool_ops.get_sset_count) @@ -854,8 +854,8 @@ static void dsa_cpu_port_get_strings(struct net_device *dev, uint32_t stringset, uint8_t *data) { struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds = dst->cpu_switch; - s8 cpu_port = dst->cpu_port; + struct dsa_switch *ds = dst->cpu_dp->ds; + s8 cpu_port = dst->cpu_dp->index; int len = ETH_GSTRING_LEN; int mcount = 0, count; unsigned int i; diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 2a9b52c5af86..658ddee63dc9 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -101,7 +101,7 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, int source_port; u8 *brcm_tag; - ds = dst->cpu_switch; + ds = dst->cpu_dp->ds; if (unlikely(!pskb_may_pull(skb, BRCM_TAG_LEN))) goto out_drop; diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 3ba3f59f7a34..be3b67750ac8 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -99,7 +99,7 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, /* This protocol doesn't support cascading multiple switches so it's * safe to assume the switch is first in the tree */ - ds = dst->cpu_switch; + ds = dst->cpu_dp->ds; if (!ds) goto out_drop; diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index aafc2fc74c30..aa05e276ea22 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -67,7 +67,7 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, u8 *trailer; int source_port; - ds = dst->cpu_switch; + ds = dst->cpu_dp->ds; if (skb_linearize(skb)) goto out_drop; -- cgit v1.3-14-g43fede From eb7b721129f1dc67041662da229a28dfc5c3c1dd Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 16 May 2017 22:40:07 +0200 Subject: net: dsa: Sort DSA tagging protocol drivers With more tag protocols being added, regain some order by sorting the entries in various places. Signed-off-by: Andrew Lunn Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 8 ++++---- net/dsa/Kconfig | 8 ++++---- net/dsa/Makefile | 6 +++--- net/dsa/dsa.c | 18 +++++++++--------- net/dsa/dsa_priv.h | 18 +++++++++--------- 5 files changed, 29 insertions(+), 29 deletions(-) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index 118a8bd2fd9a..ed767beca9c6 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -27,13 +27,13 @@ struct fixed_phy_status; enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = 0, + DSA_TAG_PROTO_BRCM, DSA_TAG_PROTO_DSA, - DSA_TAG_PROTO_TRAILER, DSA_TAG_PROTO_EDSA, - DSA_TAG_PROTO_BRCM, - DSA_TAG_PROTO_QCA, - DSA_TAG_PROTO_MTK, DSA_TAG_PROTO_LAN9303, + DSA_TAG_PROTO_MTK, + DSA_TAG_PROTO_QCA, + DSA_TAG_PROTO_TRAILER, DSA_TAG_LAST, /* MUST BE LAST */ }; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 81a0868edb1d..297389b2ab35 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -25,16 +25,16 @@ config NET_DSA_TAG_DSA config NET_DSA_TAG_EDSA bool -config NET_DSA_TAG_TRAILER +config NET_DSA_TAG_LAN9303 bool -config NET_DSA_TAG_QCA +config NET_DSA_TAG_MTK bool -config NET_DSA_TAG_MTK +config NET_DSA_TAG_TRAILER bool -config NET_DSA_TAG_LAN9303 +config NET_DSA_TAG_QCA bool endif diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 0b747d75e65a..f8c0251d1f43 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -6,7 +6,7 @@ dsa_core-y += dsa.o slave.o dsa2.o switch.o legacy.o dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o -dsa_core-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o -dsa_core-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o -dsa_core-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o dsa_core-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o +dsa_core-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o +dsa_core-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o +dsa_core-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 26130ae438da..c0a1307c87dd 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -40,26 +40,26 @@ static const struct dsa_device_ops none_ops = { }; const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = { +#ifdef CONFIG_NET_DSA_TAG_BRCM + [DSA_TAG_PROTO_BRCM] = &brcm_netdev_ops, +#endif #ifdef CONFIG_NET_DSA_TAG_DSA [DSA_TAG_PROTO_DSA] = &dsa_netdev_ops, #endif #ifdef CONFIG_NET_DSA_TAG_EDSA [DSA_TAG_PROTO_EDSA] = &edsa_netdev_ops, #endif -#ifdef CONFIG_NET_DSA_TAG_TRAILER - [DSA_TAG_PROTO_TRAILER] = &trailer_netdev_ops, +#ifdef CONFIG_NET_DSA_TAG_LAN9303 + [DSA_TAG_PROTO_LAN9303] = &lan9303_netdev_ops, #endif -#ifdef CONFIG_NET_DSA_TAG_BRCM - [DSA_TAG_PROTO_BRCM] = &brcm_netdev_ops, +#ifdef CONFIG_NET_DSA_TAG_MTK + [DSA_TAG_PROTO_MTK] = &mtk_netdev_ops, #endif #ifdef CONFIG_NET_DSA_TAG_QCA [DSA_TAG_PROTO_QCA] = &qca_netdev_ops, #endif -#ifdef CONFIG_NET_DSA_TAG_MTK - [DSA_TAG_PROTO_MTK] = &mtk_netdev_ops, -#endif -#ifdef CONFIG_NET_DSA_TAG_LAN9303 - [DSA_TAG_PROTO_LAN9303] = &lan9303_netdev_ops, +#ifdef CONFIG_NET_DSA_TAG_TRAILER + [DSA_TAG_PROTO_TRAILER] = &trailer_netdev_ops, #endif [DSA_TAG_PROTO_NONE] = &none_ops, }; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index f4a88e485213..e9003b79cbbc 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -75,25 +75,25 @@ void dsa_slave_unregister_notifier(void); int dsa_switch_register_notifier(struct dsa_switch *ds); void dsa_switch_unregister_notifier(struct dsa_switch *ds); +/* tag_brcm.c */ +extern const struct dsa_device_ops brcm_netdev_ops; + /* tag_dsa.c */ extern const struct dsa_device_ops dsa_netdev_ops; /* tag_edsa.c */ extern const struct dsa_device_ops edsa_netdev_ops; -/* tag_trailer.c */ -extern const struct dsa_device_ops trailer_netdev_ops; +/* tag_lan9303.c */ +extern const struct dsa_device_ops lan9303_netdev_ops; -/* tag_brcm.c */ -extern const struct dsa_device_ops brcm_netdev_ops; +/* tag_mtk.c */ +extern const struct dsa_device_ops mtk_netdev_ops; /* tag_qca.c */ extern const struct dsa_device_ops qca_netdev_ops; -/* tag_mtk.c */ -extern const struct dsa_device_ops mtk_netdev_ops; - -/* tag_lan9303.c */ -extern const struct dsa_device_ops lan9303_netdev_ops; +/* tag_trailer.c */ +extern const struct dsa_device_ops trailer_netdev_ops; #endif -- cgit v1.3-14-g43fede From 87d83093bfc2f4938ff21524ebb50ecf53c15a64 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 May 2017 11:07:54 +0200 Subject: net: sched: move tc_classify function to cls_api.c Move tc_classify function to cls_api.c where it belongs, rename it to fit the namespace. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 9 +++++++++ include/net/pkt_sched.h | 3 --- net/core/dev.c | 5 +++-- net/sched/cls_api.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ net/sched/sch_api.c | 48 ------------------------------------------------ net/sched/sch_atm.c | 2 +- net/sched/sch_cbq.c | 2 +- net/sched/sch_drr.c | 2 +- net/sched/sch_dsmark.c | 2 +- net/sched/sch_fq_codel.c | 2 +- net/sched/sch_hfsc.c | 2 +- net/sched/sch_htb.c | 2 +- net/sched/sch_multiq.c | 2 +- net/sched/sch_prio.c | 2 +- net/sched/sch_qfq.c | 2 +- net/sched/sch_sfb.c | 2 +- net/sched/sch_sfq.c | 2 +- 17 files changed, 72 insertions(+), 65 deletions(-) (limited to 'include/net') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 269fd78bb0ae..cb745067feb3 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -19,10 +19,19 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); #ifdef CONFIG_NET_CLS void tcf_destroy_chain(struct tcf_proto __rcu **fl); +int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, + struct tcf_result *res, bool compat_mode); + #else static inline void tcf_destroy_chain(struct tcf_proto __rcu **fl) { } + +static inline int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, + struct tcf_result *res, bool compat_mode) +{ + return TC_ACT_UNSPEC; +} #endif static inline unsigned long diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index bec46f63f10c..2579c209ea51 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -113,9 +113,6 @@ static inline void qdisc_run(struct Qdisc *q) __qdisc_run(q); } -int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res, bool compat_mode); - static inline __be16 tc_skb_protocol(const struct sk_buff *skb) { /* We need to take extra care in case the skb came via diff --git a/net/core/dev.c b/net/core/dev.c index fca407b4a6ea..acd594c56f0a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -105,6 +105,7 @@ #include #include #include +#include #include #include #include @@ -3178,7 +3179,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */ qdisc_bstats_cpu_update(cl->q, skb); - switch (tc_classify(skb, cl, &cl_res, false)) { + switch (tcf_classify(skb, cl, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); @@ -3948,7 +3949,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, skb->tc_at_ingress = 1; qdisc_bstats_cpu_update(cl->q, skb); - switch (tc_classify(skb, cl, &cl_res, false)) { + switch (tcf_classify(skb, cl, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 22f88b35a546..af58bbef6610 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -196,6 +196,54 @@ void tcf_destroy_chain(struct tcf_proto __rcu **fl) } EXPORT_SYMBOL(tcf_destroy_chain); +/* Main classifier routine: scans classifier chain attached + * to this qdisc, (optionally) tests for protocol and asks + * specific classifiers. + */ +int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, + struct tcf_result *res, bool compat_mode) +{ + __be16 protocol = tc_skb_protocol(skb); +#ifdef CONFIG_NET_CLS_ACT + const int max_reclassify_loop = 4; + const struct tcf_proto *old_tp = tp; + int limit = 0; + +reclassify: +#endif + for (; tp; tp = rcu_dereference_bh(tp->next)) { + int err; + + if (tp->protocol != protocol && + tp->protocol != htons(ETH_P_ALL)) + continue; + + err = tp->classify(skb, tp, res); +#ifdef CONFIG_NET_CLS_ACT + if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) + goto reset; +#endif + if (err >= 0) + return err; + } + + return TC_ACT_UNSPEC; /* signal: continue lookup */ +#ifdef CONFIG_NET_CLS_ACT +reset: + if (unlikely(limit++ >= max_reclassify_loop)) { + net_notice_ratelimited("%s: reclassify loop, rule prio %u, protocol %02x\n", + tp->q->ops->id, tp->prio & 0xffff, + ntohs(tp->protocol)); + return TC_ACT_SHOT; + } + + tp = old_tp; + protocol = tc_skb_protocol(skb); + goto reclassify; +#endif +} +EXPORT_SYMBOL(tcf_classify); + /* Add/change/delete/get a filter node */ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index e88342fde1bc..a3bcd972d940 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1878,54 +1878,6 @@ done: return skb->len; } -/* Main classifier routine: scans classifier chain attached - * to this qdisc, (optionally) tests for protocol and asks - * specific classifiers. - */ -int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res, bool compat_mode) -{ - __be16 protocol = tc_skb_protocol(skb); -#ifdef CONFIG_NET_CLS_ACT - const int max_reclassify_loop = 4; - const struct tcf_proto *old_tp = tp; - int limit = 0; - -reclassify: -#endif - for (; tp; tp = rcu_dereference_bh(tp->next)) { - int err; - - if (tp->protocol != protocol && - tp->protocol != htons(ETH_P_ALL)) - continue; - - err = tp->classify(skb, tp, res); -#ifdef CONFIG_NET_CLS_ACT - if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) - goto reset; -#endif - if (err >= 0) - return err; - } - - return TC_ACT_UNSPEC; /* signal: continue lookup */ -#ifdef CONFIG_NET_CLS_ACT -reset: - if (unlikely(limit++ >= max_reclassify_loop)) { - net_notice_ratelimited("%s: reclassify loop, rule prio %u, protocol %02x\n", - tp->q->ops->id, tp->prio & 0xffff, - ntohs(tp->protocol)); - return TC_ACT_SHOT; - } - - tp = old_tp; - protocol = tc_skb_protocol(skb); - goto reclassify; -#endif -} -EXPORT_SYMBOL(tc_classify); - #ifdef CONFIG_PROC_FS static int psched_show(struct seq_file *seq, void *v) { diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 40cbceed4de8..89d32fad9f89 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -377,7 +377,7 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, list_for_each_entry(flow, &p->flows, list) { fl = rcu_dereference_bh(flow->filter_list); if (fl) { - result = tc_classify(skb, fl, &res, true); + result = tcf_classify(skb, fl, &res, true); if (result < 0) continue; flow = (struct atm_flow_data *)res.class; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 7415859fd4c3..c543ea3e3043 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -233,7 +233,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) /* * Step 2+n. Apply classifier. */ - result = tc_classify(skb, fl, &res, true); + result = tcf_classify(skb, fl, &res, true); if (!fl || result < 0) goto fallback; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 58a8c32eab23..446d79bb25d9 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -333,7 +333,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch, *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; fl = rcu_dereference_bh(q->filter_list); - result = tc_classify(skb, fl, &res, false); + result = tcf_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 1c0f877f673a..7bc638d2e67f 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -234,7 +234,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, else { struct tcf_result res; struct tcf_proto *fl = rcu_dereference_bh(p->filter_list); - int result = tc_classify(skb, fl, &res, false); + int result = tcf_classify(skb, fl, &res, false); pr_debug("result %d class 0x%04x\n", result, res.classid); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 9201abce928c..42ba81ad327c 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -96,7 +96,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch, return fq_codel_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tc_classify(skb, filter, &res, false); + result = tcf_classify(skb, filter, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 5cb82f6c1b06..b0dcab199205 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1142,7 +1142,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; head = &q->root; tcf = rcu_dereference_bh(q->root.filter_list); - while (tcf && (result = tc_classify(skb, tcf, &res, false)) >= 0) { + while (tcf && (result = tcf_classify(skb, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 570ef3b0c09b..640f5f336195 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -231,7 +231,7 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, } *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - while (tcf && (result = tc_classify(skb, tcf, &res, false)) >= 0) { + while (tcf && (result = tcf_classify(skb, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 43a3a10b3c81..25bb9ffc2df1 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -46,7 +46,7 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) int err; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - err = tc_classify(skb, fl, &res, false); + err = tcf_classify(skb, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 92c2e6d448d7..7997363f7e0d 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -42,7 +42,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; if (TC_H_MAJ(skb->priority) != sch->handle) { fl = rcu_dereference_bh(q->filter_list); - err = tc_classify(skb, fl, &res, false); + err = tcf_classify(skb, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 041eba3006cc..73c7ac37b570 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -720,7 +720,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch, *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; fl = rcu_dereference_bh(q->filter_list); - result = tc_classify(skb, fl, &res, false); + result = tcf_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 0f777273ba29..b287880829e2 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -259,7 +259,7 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl, struct tcf_result res; int result; - result = tc_classify(skb, fl, &res, false); + result = tcf_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 332d94be6e1c..53a641f2ccb5 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -180,7 +180,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, return sfq_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tc_classify(skb, fl, &res, false); + result = tcf_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { -- cgit v1.3-14-g43fede From 6529eaba33f0465fc6d228e1d05b1745f7d0e8c9 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 May 2017 11:07:55 +0200 Subject: net: sched: introduce tcf block infractructure Currently, the filter chains are direcly put into the private structures of qdiscs. In order to be able to have multiple chains per qdisc and to allow filter chains sharing among qdiscs, there is a need for common object that would hold the chains. This introduces such object and calls it "tcf_block". Helpers to get and put the blocks are provided to be called from individual qdisc code. Also, the original filter_list pointers are left in qdisc privs to allow the entry into tcf_block processing without any added overhead of possible multiple pointer dereference on fast path. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 13 ++++++++-- include/net/sch_generic.h | 7 +++++- net/sched/cls_api.c | 48 +++++++++++++++++++++++++++++-------- net/sched/sch_api.c | 2 +- net/sched/sch_atm.c | 27 ++++++++++++++------- net/sched/sch_cbq.c | 19 ++++++++++----- net/sched/sch_drr.c | 13 ++++++---- net/sched/sch_dsmark.c | 17 ++++++++----- net/sched/sch_fq_codel.c | 15 ++++++++---- net/sched/sch_hfsc.c | 19 ++++++++++----- net/sched/sch_htb.c | 26 +++++++++++++------- net/sched/sch_ingress.c | 61 ++++++++++++++++++++++++++++++++++------------- net/sched/sch_multiq.c | 14 +++++++---- net/sched/sch_prio.c | 17 +++++++++---- net/sched/sch_qfq.c | 14 +++++++---- net/sched/sch_sfb.c | 15 ++++++++---- net/sched/sch_sfq.c | 15 ++++++++---- 17 files changed, 243 insertions(+), 99 deletions(-) (limited to 'include/net') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index cb745067feb3..e56e7157c280 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -18,12 +18,21 @@ int register_tcf_proto_ops(struct tcf_proto_ops *ops); int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); #ifdef CONFIG_NET_CLS -void tcf_destroy_chain(struct tcf_proto __rcu **fl); +int tcf_block_get(struct tcf_block **p_block, + struct tcf_proto __rcu **p_filter_chain); +void tcf_block_put(struct tcf_block *block); int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode); #else -static inline void tcf_destroy_chain(struct tcf_proto __rcu **fl) +static inline +int tcf_block_get(struct tcf_block **p_block, + struct tcf_proto __rcu **p_filter_chain) +{ + return 0; +} + +static inline void tcf_block_put(struct tcf_block *block) { } diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 22e52093bfda..98cf2f23602d 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -153,7 +153,7 @@ struct Qdisc_class_ops { void (*walk)(struct Qdisc *, struct qdisc_walker * arg); /* Filter manipulation */ - struct tcf_proto __rcu ** (*tcf_chain)(struct Qdisc *, unsigned long); + struct tcf_block * (*tcf_block)(struct Qdisc *, unsigned long); bool (*tcf_cl_offload)(u32 classid); unsigned long (*bind_tcf)(struct Qdisc *, unsigned long, u32 classid); @@ -236,6 +236,7 @@ struct tcf_proto { struct Qdisc *q; void *data; const struct tcf_proto_ops *ops; + struct tcf_block *block; struct rcu_head rcu; }; @@ -247,6 +248,10 @@ struct qdisc_skb_cb { unsigned char data[QDISC_CB_PRIV_LEN]; }; +struct tcf_block { + struct tcf_proto __rcu **p_filter_chain; +}; + static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) { struct qdisc_skb_cb *qcb; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index af58bbef6610..d30116f77156 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -129,7 +129,8 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) } static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, - u32 prio, u32 parent, struct Qdisc *q) + u32 prio, u32 parent, struct Qdisc *q, + struct tcf_block *block) { struct tcf_proto *tp; int err; @@ -165,6 +166,7 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, tp->prio = prio; tp->classid = parent; tp->q = q; + tp->block = block; err = tp->ops->init(tp); if (err) { @@ -185,7 +187,7 @@ static void tcf_proto_destroy(struct tcf_proto *tp) kfree_rcu(tp, rcu); } -void tcf_destroy_chain(struct tcf_proto __rcu **fl) +static void tcf_destroy_chain(struct tcf_proto __rcu **fl) { struct tcf_proto *tp; @@ -194,7 +196,28 @@ void tcf_destroy_chain(struct tcf_proto __rcu **fl) tcf_proto_destroy(tp); } } -EXPORT_SYMBOL(tcf_destroy_chain); + +int tcf_block_get(struct tcf_block **p_block, + struct tcf_proto __rcu **p_filter_chain) +{ + struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL); + + if (!block) + return -ENOMEM; + block->p_filter_chain = p_filter_chain; + *p_block = block; + return 0; +} +EXPORT_SYMBOL(tcf_block_get); + +void tcf_block_put(struct tcf_block *block) +{ + if (!block) + return; + tcf_destroy_chain(block->p_filter_chain); + kfree(block); +} +EXPORT_SYMBOL(tcf_block_put); /* Main classifier routine: scans classifier chain attached * to this qdisc, (optionally) tests for protocol and asks @@ -260,6 +283,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct Qdisc *q; struct tcf_proto __rcu **back; struct tcf_proto __rcu **chain; + struct tcf_block *block; struct tcf_proto *next; struct tcf_proto *tp; const struct Qdisc_class_ops *cops; @@ -328,7 +352,7 @@ replay: if (!cops) return -EINVAL; - if (cops->tcf_chain == NULL) + if (!cops->tcf_block) return -EOPNOTSUPP; /* Do we search for filter, attached to class? */ @@ -339,11 +363,13 @@ replay: } /* And the last stroke */ - chain = cops->tcf_chain(q, cl); - if (chain == NULL) { + block = cops->tcf_block(q, cl); + if (!block) { err = -EINVAL; goto errout; } + chain = block->p_filter_chain; + if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) { tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER); tcf_destroy_chain(chain); @@ -387,7 +413,7 @@ replay: nprio = TC_H_MAJ(tcf_auto_prio(rtnl_dereference(*back))); tp = tcf_proto_create(nla_data(tca[TCA_KIND]), - protocol, nprio, parent, q); + protocol, nprio, parent, q, block); if (IS_ERR(tp)) { err = PTR_ERR(tp); goto errout; @@ -556,6 +582,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) int s_t; struct net_device *dev; struct Qdisc *q; + struct tcf_block *block; struct tcf_proto *tp, __rcu **chain; struct tcmsg *tcm = nlmsg_data(cb->nlh); unsigned long cl = 0; @@ -577,16 +604,17 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) cops = q->ops->cl_ops; if (!cops) goto errout; - if (cops->tcf_chain == NULL) + if (!cops->tcf_block) goto errout; if (TC_H_MIN(tcm->tcm_parent)) { cl = cops->get(q, tcm->tcm_parent); if (cl == 0) goto errout; } - chain = cops->tcf_chain(q, cl); - if (chain == NULL) + block = cops->tcf_block(q, cl); + if (!block) goto errout; + chain = block->p_filter_chain; s_t = cb->args[0]; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index a3bcd972d940..5d95401bbc02 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -163,7 +163,7 @@ int register_qdisc(struct Qdisc_ops *qops) if (!(cops->get && cops->put && cops->walk && cops->leaf)) goto out_einval; - if (cops->tcf_chain && !(cops->bind_tcf && cops->unbind_tcf)) + if (cops->tcf_block && !(cops->bind_tcf && cops->unbind_tcf)) goto out_einval; } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 89d32fad9f89..f435546c3864 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -43,6 +43,7 @@ struct atm_flow_data { struct Qdisc *q; /* FIFO, TBF, etc. */ struct tcf_proto __rcu *filter_list; + struct tcf_block *block; struct atm_vcc *vcc; /* VCC; NULL if VCC is closed */ void (*old_pop)(struct atm_vcc *vcc, struct sk_buff *skb); /* chaining */ @@ -143,7 +144,7 @@ static void atm_tc_put(struct Qdisc *sch, unsigned long cl) list_del_init(&flow->list); pr_debug("atm_tc_put: qdisc %p\n", flow->q); qdisc_destroy(flow->q); - tcf_destroy_chain(&flow->filter_list); + tcf_block_put(flow->block); if (flow->sock) { pr_debug("atm_tc_put: f_count %ld\n", file_count(flow->sock->file)); @@ -274,7 +275,13 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, error = -ENOBUFS; goto err_out; } - RCU_INIT_POINTER(flow->filter_list, NULL); + + error = tcf_block_get(&flow->block, &flow->filter_list); + if (error) { + kfree(flow); + goto err_out; + } + flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); if (!flow->q) flow->q = &noop_qdisc; @@ -346,14 +353,13 @@ static void atm_tc_walk(struct Qdisc *sch, struct qdisc_walker *walker) } } -static struct tcf_proto __rcu **atm_tc_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *atm_tc_tcf_block(struct Qdisc *sch, unsigned long cl) { struct atm_qdisc_data *p = qdisc_priv(sch); struct atm_flow_data *flow = (struct atm_flow_data *)cl; pr_debug("atm_tc_find_tcf(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - return flow ? &flow->filter_list : &p->link.filter_list; + return flow ? flow->block : p->link.block; } /* --------------------------- Qdisc operations ---------------------------- */ @@ -524,6 +530,7 @@ static struct sk_buff *atm_tc_peek(struct Qdisc *sch) static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) { struct atm_qdisc_data *p = qdisc_priv(sch); + int err; pr_debug("atm_tc_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); INIT_LIST_HEAD(&p->flows); @@ -534,7 +541,11 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) if (!p->link.q) p->link.q = &noop_qdisc; pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); - RCU_INIT_POINTER(p->link.filter_list, NULL); + + err = tcf_block_get(&p->link.block, &p->link.filter_list); + if (err) + return err; + p->link.vcc = NULL; p->link.sock = NULL; p->link.classid = sch->handle; @@ -561,7 +572,7 @@ static void atm_tc_destroy(struct Qdisc *sch) pr_debug("atm_tc_destroy(sch %p,[qdisc %p])\n", sch, p); list_for_each_entry(flow, &p->flows, list) - tcf_destroy_chain(&flow->filter_list); + tcf_block_put(flow->block); list_for_each_entry_safe(flow, tmp, &p->flows, list) { if (flow->ref > 1) @@ -646,7 +657,7 @@ static const struct Qdisc_class_ops atm_class_ops = { .change = atm_tc_change, .delete = atm_tc_delete, .walk = atm_tc_walk, - .tcf_chain = atm_tc_find_tcf, + .tcf_block = atm_tc_tcf_block, .bind_tcf = atm_tc_bind_filter, .unbind_tcf = atm_tc_put, .dump = atm_tc_dump_class, diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index c543ea3e3043..8dd6d0aca678 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -127,6 +127,7 @@ struct cbq_class { struct tc_cbq_xstats xstats; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; int refcnt; int filters; @@ -1405,7 +1406,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) WARN_ON(cl->filters); - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); qdisc_destroy(cl->q); qdisc_put_rtab(cl->R_tab); gen_kill_estimator(&cl->rate_est); @@ -1430,7 +1431,7 @@ static void cbq_destroy(struct Qdisc *sch) */ for (h = 0; h < q->clhash.hashsize; h++) { hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); } for (h = 0; h < q->clhash.hashsize; h++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[h], @@ -1585,12 +1586,19 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (cl == NULL) goto failure; + err = tcf_block_get(&cl->block, &cl->filter_list); + if (err) { + kfree(cl); + return err; + } + if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) { + tcf_block_put(cl->block); kfree(cl); goto failure; } @@ -1688,8 +1696,7 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg) return 0; } -static struct tcf_proto __rcu **cbq_find_tcf(struct Qdisc *sch, - unsigned long arg) +static struct tcf_block *cbq_tcf_block(struct Qdisc *sch, unsigned long arg) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl = (struct cbq_class *)arg; @@ -1697,7 +1704,7 @@ static struct tcf_proto __rcu **cbq_find_tcf(struct Qdisc *sch, if (cl == NULL) cl = &q->link; - return &cl->filter_list; + return cl->block; } static unsigned long cbq_bind_filter(struct Qdisc *sch, unsigned long parent, @@ -1756,7 +1763,7 @@ static const struct Qdisc_class_ops cbq_class_ops = { .change = cbq_change_class, .delete = cbq_delete, .walk = cbq_walk, - .tcf_chain = cbq_find_tcf, + .tcf_block = cbq_tcf_block, .bind_tcf = cbq_bind_filter, .unbind_tcf = cbq_unbind_filter, .dump = cbq_dump_class, diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 446d79bb25d9..5db2a2843c66 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -36,6 +36,7 @@ struct drr_class { struct drr_sched { struct list_head active; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; struct Qdisc_class_hash clhash; }; @@ -190,15 +191,14 @@ static void drr_put_class(struct Qdisc *sch, unsigned long arg) drr_destroy_class(sch, cl); } -static struct tcf_proto __rcu **drr_tcf_chain(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *drr_tcf_block(struct Qdisc *sch, unsigned long cl) { struct drr_sched *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static unsigned long drr_bind_tcf(struct Qdisc *sch, unsigned long parent, @@ -431,6 +431,9 @@ static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt) struct drr_sched *q = qdisc_priv(sch); int err; + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; err = qdisc_class_hash_init(&q->clhash); if (err < 0) return err; @@ -462,7 +465,7 @@ static void drr_destroy_qdisc(struct Qdisc *sch) struct hlist_node *next; unsigned int i; - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], @@ -477,7 +480,7 @@ static const struct Qdisc_class_ops drr_class_ops = { .delete = drr_delete_class, .get = drr_get_class, .put = drr_put_class, - .tcf_chain = drr_tcf_chain, + .tcf_block = drr_tcf_block, .bind_tcf = drr_bind_tcf, .unbind_tcf = drr_unbind_tcf, .graft = drr_graft_class, diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 7bc638d2e67f..ba45102cff94 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -44,6 +44,7 @@ struct mask_value { struct dsmark_qdisc_data { struct Qdisc *q; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; struct mask_value *mv; u16 indices; u8 set_tc_index; @@ -183,11 +184,11 @@ ignore: } } -static inline struct tcf_proto __rcu **dsmark_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl) { struct dsmark_qdisc_data *p = qdisc_priv(sch); - return &p->filter_list; + + return p->block; } /* --------------------------- Qdisc operations ---------------------------- */ @@ -332,7 +333,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) { struct dsmark_qdisc_data *p = qdisc_priv(sch); struct nlattr *tb[TCA_DSMARK_MAX + 1]; - int err = -EINVAL; + int err; u32 default_index = NO_DEFAULT_INDEX; u16 indices; int i; @@ -342,6 +343,10 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) goto errout; + err = tcf_block_get(&p->block, &p->filter_list); + if (err) + return err; + err = nla_parse_nested(tb, TCA_DSMARK_MAX, opt, dsmark_policy, NULL); if (err < 0) goto errout; @@ -400,7 +405,7 @@ static void dsmark_destroy(struct Qdisc *sch) pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - tcf_destroy_chain(&p->filter_list); + tcf_block_put(p->block); qdisc_destroy(p->q); if (p->mv != p->embedded) kfree(p->mv); @@ -468,7 +473,7 @@ static const struct Qdisc_class_ops dsmark_class_ops = { .change = dsmark_change, .delete = dsmark_delete, .walk = dsmark_walk, - .tcf_chain = dsmark_find_tcf, + .tcf_block = dsmark_tcf_block, .bind_tcf = dsmark_bind_filter, .unbind_tcf = dsmark_put, .dump = dsmark_dump_class, diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 42ba81ad327c..f201e73947fb 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -55,6 +55,7 @@ struct fq_codel_flow { struct fq_codel_sched_data { struct tcf_proto __rcu *filter_list; /* optional external classifier */ + struct tcf_block *block; struct fq_codel_flow *flows; /* Flows table [flows_cnt] */ u32 *backlogs; /* backlog table [flows_cnt] */ u32 flows_cnt; /* number of flows */ @@ -450,7 +451,7 @@ static void fq_codel_destroy(struct Qdisc *sch) { struct fq_codel_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); kvfree(q->backlogs); kvfree(q->flows); } @@ -459,6 +460,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) { struct fq_codel_sched_data *q = qdisc_priv(sch); int i; + int err; sch->limit = 10*1024; q->flows_cnt = 1024; @@ -478,6 +480,10 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) return err; } + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; + if (!q->flows) { q->flows = kvzalloc(q->flows_cnt * sizeof(struct fq_codel_flow), GFP_KERNEL); @@ -589,14 +595,13 @@ static void fq_codel_put(struct Qdisc *q, unsigned long cl) { } -static struct tcf_proto __rcu **fq_codel_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *fq_codel_tcf_block(struct Qdisc *sch, unsigned long cl) { struct fq_codel_sched_data *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static int fq_codel_dump_class(struct Qdisc *sch, unsigned long cl, @@ -679,7 +684,7 @@ static const struct Qdisc_class_ops fq_codel_class_ops = { .leaf = fq_codel_leaf, .get = fq_codel_get, .put = fq_codel_put, - .tcf_chain = fq_codel_find_tcf, + .tcf_block = fq_codel_tcf_block, .bind_tcf = fq_codel_bind, .unbind_tcf = fq_codel_put, .dump = fq_codel_dump_class, diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index b0dcab199205..a324f84b1ccd 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -116,6 +116,7 @@ struct hfsc_class { struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct tcf_proto __rcu *filter_list; /* filter list */ + struct tcf_block *block; unsigned int filter_cnt; /* filter count */ unsigned int level; /* class level in hierarchy */ @@ -1040,12 +1041,19 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; + err = tcf_block_get(&cl->block, &cl->filter_list); + if (err) { + kfree(cl); + return err; + } + if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) { + tcf_block_put(cl->block); kfree(cl); return err; } @@ -1091,7 +1099,7 @@ hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl) { struct hfsc_sched *q = qdisc_priv(sch); - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); qdisc_destroy(cl->qdisc); gen_kill_estimator(&cl->rate_est); if (cl != &q->root) @@ -1261,8 +1269,7 @@ hfsc_unbind_tcf(struct Qdisc *sch, unsigned long arg) cl->filter_cnt--; } -static struct tcf_proto __rcu ** -hfsc_tcf_chain(struct Qdisc *sch, unsigned long arg) +static struct tcf_block *hfsc_tcf_block(struct Qdisc *sch, unsigned long arg) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl = (struct hfsc_class *)arg; @@ -1270,7 +1277,7 @@ hfsc_tcf_chain(struct Qdisc *sch, unsigned long arg) if (cl == NULL) cl = &q->root; - return &cl->filter_list; + return cl->block; } static int @@ -1515,7 +1522,7 @@ hfsc_destroy_qdisc(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); } for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], @@ -1662,7 +1669,7 @@ static const struct Qdisc_class_ops hfsc_class_ops = { .put = hfsc_put_class, .bind_tcf = hfsc_bind_tcf, .unbind_tcf = hfsc_unbind_tcf, - .tcf_chain = hfsc_tcf_chain, + .tcf_block = hfsc_tcf_block, .dump = hfsc_dump_class, .dump_stats = hfsc_dump_class_stats, .walk = hfsc_walk diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 640f5f336195..195bbca9eb0b 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -105,6 +105,7 @@ struct htb_class { int quantum; /* but stored for parent-to-leaf return */ struct tcf_proto __rcu *filter_list; /* class attached filters */ + struct tcf_block *block; int filter_cnt; int refcnt; /* usage count of this class */ @@ -156,6 +157,7 @@ struct htb_sched { /* filters for qdisc itself */ struct tcf_proto __rcu *filter_list; + struct tcf_block *block; #define HTB_WARN_TOOMANYEVENTS 0x1 unsigned int warned; /* only one warning */ @@ -1017,6 +1019,10 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) return -EINVAL; + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; + err = nla_parse_nested(tb, TCA_HTB_MAX, opt, htb_policy, NULL); if (err < 0) return err; @@ -1230,7 +1236,7 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) qdisc_destroy(cl->un.leaf.q); } gen_kill_estimator(&cl->rate_est); - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); kfree(cl); } @@ -1248,11 +1254,11 @@ static void htb_destroy(struct Qdisc *sch) * because filter need its target class alive to be able to call * unbind_filter on it (without Oops). */ - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); } for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], @@ -1396,6 +1402,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!cl) goto failure; + err = tcf_block_get(&cl->block, &cl->filter_list); + if (err) { + kfree(cl); + goto failure; + } if (htb_rate_est || tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, @@ -1403,6 +1414,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, qdisc_root_sleeping_running(sch), tca[TCA_RATE] ? : &est.nla); if (err) { + tcf_block_put(cl->block); kfree(cl); goto failure; } @@ -1521,14 +1533,12 @@ failure: return err; } -static struct tcf_proto __rcu **htb_find_tcf(struct Qdisc *sch, - unsigned long arg) +static struct tcf_block *htb_tcf_block(struct Qdisc *sch, unsigned long arg) { struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)arg; - struct tcf_proto __rcu **fl = cl ? &cl->filter_list : &q->filter_list; - return fl; + return cl ? cl->block : q->block; } static unsigned long htb_bind_filter(struct Qdisc *sch, unsigned long parent, @@ -1591,7 +1601,7 @@ static const struct Qdisc_class_ops htb_class_ops = { .change = htb_change_class, .delete = htb_delete, .walk = htb_walk, - .tcf_chain = htb_find_tcf, + .tcf_block = htb_tcf_block, .bind_tcf = htb_bind_filter, .unbind_tcf = htb_unbind_filter, .dump = htb_dump_class, diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 3bab5f66c392..d8a9bebcab90 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -18,6 +18,10 @@ #include #include +struct ingress_sched_data { + struct tcf_block *block; +}; + static struct Qdisc *ingress_leaf(struct Qdisc *sch, unsigned long arg) { return NULL; @@ -47,16 +51,23 @@ static void ingress_walk(struct Qdisc *sch, struct qdisc_walker *walker) { } -static struct tcf_proto __rcu **ingress_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *ingress_tcf_block(struct Qdisc *sch, unsigned long cl) { - struct net_device *dev = qdisc_dev(sch); + struct ingress_sched_data *q = qdisc_priv(sch); - return &dev->ingress_cl_list; + return q->block; } static int ingress_init(struct Qdisc *sch, struct nlattr *opt) { + struct ingress_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int err; + + err = tcf_block_get(&q->block, &dev->ingress_cl_list); + if (err) + return err; + net_inc_ingress_queue(); sch->flags |= TCQ_F_CPUSTATS; @@ -65,9 +76,9 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt) static void ingress_destroy(struct Qdisc *sch) { - struct net_device *dev = qdisc_dev(sch); + struct ingress_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&dev->ingress_cl_list); + tcf_block_put(q->block); net_dec_ingress_queue(); } @@ -91,7 +102,7 @@ static const struct Qdisc_class_ops ingress_class_ops = { .get = ingress_get, .put = ingress_put, .walk = ingress_walk, - .tcf_chain = ingress_find_tcf, + .tcf_block = ingress_tcf_block, .tcf_cl_offload = ingress_cl_offload, .bind_tcf = ingress_bind_filter, .unbind_tcf = ingress_put, @@ -100,12 +111,18 @@ static const struct Qdisc_class_ops ingress_class_ops = { static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { .cl_ops = &ingress_class_ops, .id = "ingress", + .priv_size = sizeof(struct ingress_sched_data), .init = ingress_init, .destroy = ingress_destroy, .dump = ingress_dump, .owner = THIS_MODULE, }; +struct clsact_sched_data { + struct tcf_block *ingress_block; + struct tcf_block *egress_block; +}; + static unsigned long clsact_get(struct Qdisc *sch, u32 classid) { switch (TC_H_MIN(classid)) { @@ -128,16 +145,15 @@ static unsigned long clsact_bind_filter(struct Qdisc *sch, return clsact_get(sch, classid); } -static struct tcf_proto __rcu **clsact_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *clsact_tcf_block(struct Qdisc *sch, unsigned long cl) { - struct net_device *dev = qdisc_dev(sch); + struct clsact_sched_data *q = qdisc_priv(sch); switch (cl) { case TC_H_MIN(TC_H_MIN_INGRESS): - return &dev->ingress_cl_list; + return q->ingress_block; case TC_H_MIN(TC_H_MIN_EGRESS): - return &dev->egress_cl_list; + return q->egress_block; default: return NULL; } @@ -145,6 +161,18 @@ static struct tcf_proto __rcu **clsact_find_tcf(struct Qdisc *sch, static int clsact_init(struct Qdisc *sch, struct nlattr *opt) { + struct clsact_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int err; + + err = tcf_block_get(&q->ingress_block, &dev->ingress_cl_list); + if (err) + return err; + + err = tcf_block_get(&q->egress_block, &dev->egress_cl_list); + if (err) + return err; + net_inc_ingress_queue(); net_inc_egress_queue(); @@ -155,10 +183,10 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) static void clsact_destroy(struct Qdisc *sch) { - struct net_device *dev = qdisc_dev(sch); + struct clsact_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&dev->ingress_cl_list); - tcf_destroy_chain(&dev->egress_cl_list); + tcf_block_put(q->egress_block); + tcf_block_put(q->ingress_block); net_dec_ingress_queue(); net_dec_egress_queue(); @@ -169,7 +197,7 @@ static const struct Qdisc_class_ops clsact_class_ops = { .get = clsact_get, .put = ingress_put, .walk = ingress_walk, - .tcf_chain = clsact_find_tcf, + .tcf_block = clsact_tcf_block, .tcf_cl_offload = clsact_cl_offload, .bind_tcf = clsact_bind_filter, .unbind_tcf = ingress_put, @@ -178,6 +206,7 @@ static const struct Qdisc_class_ops clsact_class_ops = { static struct Qdisc_ops clsact_qdisc_ops __read_mostly = { .cl_ops = &clsact_class_ops, .id = "clsact", + .priv_size = sizeof(struct clsact_sched_data), .init = clsact_init, .destroy = clsact_destroy, .dump = ingress_dump, diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 25bb9ffc2df1..604767482ad0 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -32,6 +32,7 @@ struct multiq_sched_data { u16 max_bands; u16 curband; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; struct Qdisc **queues; }; @@ -170,7 +171,7 @@ multiq_destroy(struct Qdisc *sch) int band; struct multiq_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); for (band = 0; band < q->bands; band++) qdisc_destroy(q->queues[band]); @@ -243,6 +244,10 @@ static int multiq_init(struct Qdisc *sch, struct nlattr *opt) if (opt == NULL) return -EINVAL; + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; + q->max_bands = qdisc_dev(sch)->num_tx_queues; q->queues = kcalloc(q->max_bands, sizeof(struct Qdisc *), GFP_KERNEL); @@ -367,14 +372,13 @@ static void multiq_walk(struct Qdisc *sch, struct qdisc_walker *arg) } } -static struct tcf_proto __rcu **multiq_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *multiq_tcf_block(struct Qdisc *sch, unsigned long cl) { struct multiq_sched_data *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static const struct Qdisc_class_ops multiq_class_ops = { @@ -383,7 +387,7 @@ static const struct Qdisc_class_ops multiq_class_ops = { .get = multiq_get, .put = multiq_put, .walk = multiq_walk, - .tcf_chain = multiq_find_tcf, + .tcf_block = multiq_tcf_block, .bind_tcf = multiq_bind, .unbind_tcf = multiq_put, .dump = multiq_dump_class, diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 7997363f7e0d..a2404688dd01 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -25,6 +25,7 @@ struct prio_sched_data { int bands; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; u8 prio2band[TC_PRIO_MAX+1]; struct Qdisc *queues[TCQ_PRIO_BANDS]; }; @@ -145,7 +146,7 @@ prio_destroy(struct Qdisc *sch) int prio; struct prio_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); for (prio = 0; prio < q->bands; prio++) qdisc_destroy(q->queues[prio]); } @@ -204,9 +205,16 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) static int prio_init(struct Qdisc *sch, struct nlattr *opt) { + struct prio_sched_data *q = qdisc_priv(sch); + int err; + if (!opt) return -EINVAL; + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; + return prio_tune(sch, opt); } @@ -317,14 +325,13 @@ static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg) } } -static struct tcf_proto __rcu **prio_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *prio_tcf_block(struct Qdisc *sch, unsigned long cl) { struct prio_sched_data *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static const struct Qdisc_class_ops prio_class_ops = { @@ -333,7 +340,7 @@ static const struct Qdisc_class_ops prio_class_ops = { .get = prio_get, .put = prio_put, .walk = prio_walk, - .tcf_chain = prio_find_tcf, + .tcf_block = prio_tcf_block, .bind_tcf = prio_bind, .unbind_tcf = prio_put, .dump = prio_dump_class, diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 73c7ac37b570..076ad032befb 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -182,6 +182,7 @@ struct qfq_group { struct qfq_sched { struct tcf_proto __rcu *filter_list; + struct tcf_block *block; struct Qdisc_class_hash clhash; u64 oldV, V; /* Precise virtual times. */ @@ -582,15 +583,14 @@ static void qfq_put_class(struct Qdisc *sch, unsigned long arg) qfq_destroy_class(sch, cl); } -static struct tcf_proto __rcu **qfq_tcf_chain(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *qfq_tcf_block(struct Qdisc *sch, unsigned long cl) { struct qfq_sched *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static unsigned long qfq_bind_tcf(struct Qdisc *sch, unsigned long parent, @@ -1438,6 +1438,10 @@ static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt) int i, j, err; u32 max_cl_shift, maxbudg_shift, max_classes; + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; + err = qdisc_class_hash_init(&q->clhash); if (err < 0) return err; @@ -1492,7 +1496,7 @@ static void qfq_destroy_qdisc(struct Qdisc *sch) struct hlist_node *next; unsigned int i; - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], @@ -1508,7 +1512,7 @@ static const struct Qdisc_class_ops qfq_class_ops = { .delete = qfq_delete_class, .get = qfq_get_class, .put = qfq_put_class, - .tcf_chain = qfq_tcf_chain, + .tcf_block = qfq_tcf_block, .bind_tcf = qfq_bind_tcf, .unbind_tcf = qfq_unbind_tcf, .graft = qfq_graft_class, diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index b287880829e2..9756b1ccd345 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -56,6 +56,7 @@ struct sfb_bins { struct sfb_sched_data { struct Qdisc *qdisc; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; unsigned long rehash_interval; unsigned long warmup_time; /* double buffering warmup time in jiffies */ u32 max; @@ -465,7 +466,7 @@ static void sfb_destroy(struct Qdisc *sch) { struct sfb_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); qdisc_destroy(q->qdisc); } @@ -549,6 +550,11 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt) static int sfb_init(struct Qdisc *sch, struct nlattr *opt) { struct sfb_sched_data *q = qdisc_priv(sch); + int err; + + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; q->qdisc = &noop_qdisc; return sfb_change(sch, opt); @@ -657,14 +663,13 @@ static void sfb_walk(struct Qdisc *sch, struct qdisc_walker *walker) } } -static struct tcf_proto __rcu **sfb_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *sfb_tcf_block(struct Qdisc *sch, unsigned long cl) { struct sfb_sched_data *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static unsigned long sfb_bind(struct Qdisc *sch, unsigned long parent, @@ -682,7 +687,7 @@ static const struct Qdisc_class_ops sfb_class_ops = { .change = sfb_change_class, .delete = sfb_delete, .walk = sfb_walk, - .tcf_chain = sfb_find_tcf, + .tcf_block = sfb_tcf_block, .bind_tcf = sfb_bind, .unbind_tcf = sfb_put, .dump = sfb_dump_class, diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 53a641f2ccb5..66dfd15b7946 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -126,6 +126,7 @@ struct sfq_sched_data { u8 flags; unsigned short scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */ struct tcf_proto __rcu *filter_list; + struct tcf_block *block; sfq_index *ht; /* Hash table ('divisor' slots) */ struct sfq_slot *slots; /* Flows table ('maxflows' entries) */ @@ -697,7 +698,7 @@ static void sfq_destroy(struct Qdisc *sch) { struct sfq_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); q->perturb_period = 0; del_timer_sync(&q->perturb_timer); sfq_free(q->ht); @@ -709,6 +710,11 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) { struct sfq_sched_data *q = qdisc_priv(sch); int i; + int err; + + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; setup_deferrable_timer(&q->perturb_timer, sfq_perturbation, (unsigned long)sch); @@ -815,14 +821,13 @@ static void sfq_put(struct Qdisc *q, unsigned long cl) { } -static struct tcf_proto __rcu **sfq_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *sfq_tcf_block(struct Qdisc *sch, unsigned long cl) { struct sfq_sched_data *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static int sfq_dump_class(struct Qdisc *sch, unsigned long cl, @@ -878,7 +883,7 @@ static const struct Qdisc_class_ops sfq_class_ops = { .leaf = sfq_leaf, .get = sfq_get, .put = sfq_put, - .tcf_chain = sfq_find_tcf, + .tcf_block = sfq_tcf_block, .bind_tcf = sfq_bind, .unbind_tcf = sfq_put, .dump = sfq_dump_class, -- cgit v1.3-14-g43fede From 2190d1d0944f84c55cdfdb89c7920f8f9311bdde Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 May 2017 11:07:59 +0200 Subject: net: sched: introduce helpers to work with filter chains Introduce struct tcf_chain object and set of helpers around it. Wraps up insertion, deletion and search in the filter chain. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/sch_generic.h | 7 ++- net/sched/cls_api.c | 148 +++++++++++++++++++++++++++++++++------------- 2 files changed, 113 insertions(+), 42 deletions(-) (limited to 'include/net') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 98cf2f23602d..52bceede534b 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -248,10 +248,15 @@ struct qdisc_skb_cb { unsigned char data[QDISC_CB_PRIV_LEN]; }; -struct tcf_block { +struct tcf_chain { + struct tcf_proto __rcu *filter_chain; struct tcf_proto __rcu **p_filter_chain; }; +struct tcf_block { + struct tcf_chain *chain; +}; + static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) { struct qdisc_skb_cb *qcb; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 690457c988b2..fee3d7faeb79 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -106,13 +106,12 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, - struct tcf_proto __rcu **chain, int event) + struct tcf_chain *chain, int event) { - struct tcf_proto __rcu **it_chain; struct tcf_proto *tp; - for (it_chain = chain; (tp = rtnl_dereference(*it_chain)) != NULL; - it_chain = &tp->next) + for (tp = rtnl_dereference(chain->filter_chain); + tp; tp = rtnl_dereference(tp->next)) tfilter_notify(net, oskb, n, tp, 0, event, false); } @@ -187,26 +186,49 @@ static void tcf_proto_destroy(struct tcf_proto *tp) kfree_rcu(tp, rcu); } -static void tcf_chain_destroy(struct tcf_proto __rcu **fl) +static struct tcf_chain *tcf_chain_create(void) +{ + return kzalloc(sizeof(struct tcf_chain), GFP_KERNEL); +} + +static void tcf_chain_destroy(struct tcf_chain *chain) { struct tcf_proto *tp; - while ((tp = rtnl_dereference(*fl)) != NULL) { - RCU_INIT_POINTER(*fl, tp->next); + while ((tp = rtnl_dereference(chain->filter_chain)) != NULL) { + RCU_INIT_POINTER(chain->filter_chain, tp->next); tcf_proto_destroy(tp); } + kfree(chain); +} + +static void +tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain, + struct tcf_proto __rcu **p_filter_chain) +{ + chain->p_filter_chain = p_filter_chain; } int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain) { struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL); + int err; if (!block) return -ENOMEM; - block->p_filter_chain = p_filter_chain; + block->chain = tcf_chain_create(); + if (!block->chain) { + err = -ENOMEM; + goto err_chain_create; + } + tcf_chain_filter_chain_ptr_set(block->chain, p_filter_chain); *p_block = block; return 0; + +err_chain_create: + kfree(block); + return err; } EXPORT_SYMBOL(tcf_block_get); @@ -214,7 +236,7 @@ void tcf_block_put(struct tcf_block *block) { if (!block) return; - tcf_chain_destroy(block->p_filter_chain); + tcf_chain_destroy(block->chain); kfree(block); } EXPORT_SYMBOL(tcf_block_put); @@ -267,6 +289,65 @@ reset: } EXPORT_SYMBOL(tcf_classify); +struct tcf_chain_info { + struct tcf_proto __rcu **pprev; + struct tcf_proto __rcu *next; +}; + +static struct tcf_proto *tcf_chain_tp_prev(struct tcf_chain_info *chain_info) +{ + return rtnl_dereference(*chain_info->pprev); +} + +static void tcf_chain_tp_insert(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + struct tcf_proto *tp) +{ + if (chain->p_filter_chain && + *chain_info->pprev == chain->filter_chain) + *chain->p_filter_chain = tp; + RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info)); + rcu_assign_pointer(*chain_info->pprev, tp); +} + +static void tcf_chain_tp_remove(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + struct tcf_proto *tp) +{ + struct tcf_proto *next = rtnl_dereference(chain_info->next); + + if (chain->p_filter_chain && tp == chain->filter_chain) + *chain->p_filter_chain = next; + RCU_INIT_POINTER(*chain_info->pprev, next); +} + +static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + u32 protocol, u32 prio, + bool prio_allocate) +{ + struct tcf_proto **pprev; + struct tcf_proto *tp; + + /* Check the chain for existence of proto-tcf with this priority */ + for (pprev = &chain->filter_chain; + (tp = rtnl_dereference(*pprev)); pprev = &tp->next) { + if (tp->prio >= prio) { + if (tp->prio == prio) { + if (prio_allocate || + (tp->protocol != protocol && protocol)) + return ERR_PTR(-EINVAL); + } else { + tp = NULL; + } + break; + } + } + chain_info->pprev = pprev; + chain_info->next = tp ? tp->next : NULL; + return tp; +} + /* Add/change/delete/get a filter node */ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, @@ -281,10 +362,9 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, u32 parent; struct net_device *dev; struct Qdisc *q; - struct tcf_proto __rcu **back; - struct tcf_proto __rcu **chain; + struct tcf_chain_info chain_info; + struct tcf_chain *chain; struct tcf_block *block; - struct tcf_proto *next; struct tcf_proto *tp; const struct Qdisc_class_ops *cops; unsigned long cl; @@ -369,7 +449,7 @@ replay: err = -EINVAL; goto errout; } - chain = block->p_filter_chain; + chain = block->chain; if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) { tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER); @@ -378,22 +458,11 @@ replay: goto errout; } - /* Check the chain for existence of proto-tcf with this priority */ - for (back = chain; - (tp = rtnl_dereference(*back)) != NULL; - back = &tp->next) { - if (tp->prio >= prio) { - if (tp->prio == prio) { - if (prio_allocate || - (tp->protocol != protocol && protocol)) { - err = -EINVAL; - goto errout; - } - } else { - tp = NULL; - } - break; - } + tp = tcf_chain_tp_find(chain, &chain_info, protocol, + prio, prio_allocate); + if (IS_ERR(tp)) { + err = PTR_ERR(tp); + goto errout; } if (tp == NULL) { @@ -411,7 +480,7 @@ replay: } if (prio_allocate) - prio = tcf_auto_prio(rtnl_dereference(*back)); + prio = tcf_auto_prio(tcf_chain_tp_prev(&chain_info)); tp = tcf_proto_create(nla_data(tca[TCA_KIND]), protocol, prio, parent, q, block); @@ -429,8 +498,7 @@ replay: if (fh == 0) { if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) { - next = rtnl_dereference(tp->next); - RCU_INIT_POINTER(*back, next); + tcf_chain_tp_remove(chain, &chain_info, tp); tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER, false); tcf_proto_destroy(tp); @@ -459,11 +527,10 @@ replay: err = tp->ops->delete(tp, fh, &last); if (err) goto errout; - next = rtnl_dereference(tp->next); tfilter_notify(net, skb, n, tp, t->tcm_handle, RTM_DELTFILTER, false); if (last) { - RCU_INIT_POINTER(*back, next); + tcf_chain_tp_remove(chain, &chain_info, tp); tcf_proto_destroy(tp); } goto errout; @@ -480,10 +547,8 @@ replay: err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE); if (err == 0) { - if (tp_created) { - RCU_INIT_POINTER(tp->next, rtnl_dereference(*back)); - rcu_assign_pointer(*back, tp); - } + if (tp_created) + tcf_chain_tp_insert(chain, &chain_info, tp); tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER, false); } else { if (tp_created) @@ -584,7 +649,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) struct net_device *dev; struct Qdisc *q; struct tcf_block *block; - struct tcf_proto *tp, __rcu **chain; + struct tcf_proto *tp; + struct tcf_chain *chain; struct tcmsg *tcm = nlmsg_data(cb->nlh); unsigned long cl = 0; const struct Qdisc_class_ops *cops; @@ -615,11 +681,11 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) block = cops->tcf_block(q, cl); if (!block) goto errout; - chain = block->p_filter_chain; + chain = block->chain; s_t = cb->args[0]; - for (tp = rtnl_dereference(*chain), t = 0; + for (tp = rtnl_dereference(chain->filter_chain), t = 0; tp; tp = rtnl_dereference(tp->next), t++) { if (t < s_t) continue; -- cgit v1.3-14-g43fede From 5bc1701881e395cec51811d07ec6961f3d1b2612 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 May 2017 11:08:01 +0200 Subject: net: sched: introduce multichain support for filters Instead of having only one filter per block, introduce a list of chains for every block. Create chain 0 by default. UAPI is extended so the user can specify which chain he wants to change. If the new attribute is not specified, chain 0 is used. That allows to maintain backward compatibility. If chain does not exist and user wants to manipulate with it, new chain is created with specified index. Also, when last filter is removed from the chain, the chain is destroyed. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 2 + include/net/sch_generic.h | 9 +++- include/uapi/linux/rtnetlink.h | 1 + net/sched/cls_api.c | 104 ++++++++++++++++++++++++++++++++++------- 4 files changed, 98 insertions(+), 18 deletions(-) (limited to 'include/net') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index e56e7157c280..2c213a69c196 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -18,6 +18,8 @@ int register_tcf_proto_ops(struct tcf_proto_ops *ops); int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); #ifdef CONFIG_NET_CLS +struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index); +void tcf_chain_put(struct tcf_chain *chain); int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain); void tcf_block_put(struct tcf_block *block); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 52bceede534b..569b5654c30c 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -236,7 +237,7 @@ struct tcf_proto { struct Qdisc *q; void *data; const struct tcf_proto_ops *ops; - struct tcf_block *block; + struct tcf_chain *chain; struct rcu_head rcu; }; @@ -251,10 +252,14 @@ struct qdisc_skb_cb { struct tcf_chain { struct tcf_proto __rcu *filter_chain; struct tcf_proto __rcu **p_filter_chain; + struct list_head list; + struct tcf_block *block; + u32 index; /* chain index */ + unsigned int refcnt; }; struct tcf_block { - struct tcf_chain *chain; + struct list_head chain_list; }; static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index cce061382e40..6487b21b2c1e 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -549,6 +549,7 @@ enum { TCA_STAB, TCA_PAD, TCA_DUMP_INVISIBLE, + TCA_CHAIN, __TCA_MAX }; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 63aa2ea5f00c..adacaf299c4a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -129,7 +129,7 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, u32 prio, u32 parent, struct Qdisc *q, - struct tcf_block *block) + struct tcf_chain *chain) { struct tcf_proto *tp; int err; @@ -165,7 +165,7 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, tp->prio = prio; tp->classid = parent; tp->q = q; - tp->block = block; + tp->chain = chain; err = tp->ops->init(tp); if (err) { @@ -186,15 +186,26 @@ static void tcf_proto_destroy(struct tcf_proto *tp) kfree_rcu(tp, rcu); } -static struct tcf_chain *tcf_chain_create(void) +static struct tcf_chain *tcf_chain_create(struct tcf_block *block, + u32 chain_index) { - return kzalloc(sizeof(struct tcf_chain), GFP_KERNEL); + struct tcf_chain *chain; + + chain = kzalloc(sizeof(*chain), GFP_KERNEL); + if (!chain) + return NULL; + list_add_tail(&chain->list, &block->chain_list); + chain->block = block; + chain->index = chain_index; + chain->refcnt = 1; + return chain; } static void tcf_chain_destroy(struct tcf_chain *chain) { struct tcf_proto *tp; + list_del(&chain->list); while ((tp = rtnl_dereference(chain->filter_chain)) != NULL) { RCU_INIT_POINTER(chain->filter_chain, tp->next); tcf_proto_destroy(tp); @@ -202,6 +213,30 @@ static void tcf_chain_destroy(struct tcf_chain *chain) kfree(chain); } +struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index) +{ + struct tcf_chain *chain; + + list_for_each_entry(chain, &block->chain_list, list) { + if (chain->index == chain_index) { + chain->refcnt++; + return chain; + } + } + return tcf_chain_create(block, chain_index); +} +EXPORT_SYMBOL(tcf_chain_get); + +void tcf_chain_put(struct tcf_chain *chain) +{ + /* Destroy unused chain, with exception of chain 0, which is the + * default one and has to be always present. + */ + if (--chain->refcnt == 0 && !chain->filter_chain && chain->index != 0) + tcf_chain_destroy(chain); +} +EXPORT_SYMBOL(tcf_chain_put); + static void tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain, struct tcf_proto __rcu **p_filter_chain) @@ -213,16 +248,19 @@ int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain) { struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL); + struct tcf_chain *chain; int err; if (!block) return -ENOMEM; - block->chain = tcf_chain_create(); - if (!block->chain) { + INIT_LIST_HEAD(&block->chain_list); + /* Create chain 0 by default, it has to be always present. */ + chain = tcf_chain_create(block, 0); + if (!chain) { err = -ENOMEM; goto err_chain_create; } - tcf_chain_filter_chain_ptr_set(block->chain, p_filter_chain); + tcf_chain_filter_chain_ptr_set(chain, p_filter_chain); *p_block = block; return 0; @@ -234,9 +272,13 @@ EXPORT_SYMBOL(tcf_block_get); void tcf_block_put(struct tcf_block *block) { + struct tcf_chain *chain, *tmp; + if (!block) return; - tcf_chain_destroy(block->chain); + + list_for_each_entry_safe(chain, tmp, &block->chain_list, list) + tcf_chain_destroy(chain); kfree(block); } EXPORT_SYMBOL(tcf_block_put); @@ -360,10 +402,11 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, u32 prio; bool prio_allocate; u32 parent; + u32 chain_index; struct net_device *dev; struct Qdisc *q; struct tcf_chain_info chain_info; - struct tcf_chain *chain; + struct tcf_chain *chain = NULL; struct tcf_block *block; struct tcf_proto *tp; const struct Qdisc_class_ops *cops; @@ -449,7 +492,17 @@ replay: err = -EINVAL; goto errout; } - chain = block->chain; + + chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; + if (chain_index > TC_ACT_EXT_VAL_MASK) { + err = -EINVAL; + goto errout; + } + chain = tcf_chain_get(block, chain_index); + if (!chain) { + err = -ENOMEM; + goto errout; + } if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) { tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER); @@ -483,7 +536,7 @@ replay: prio = tcf_auto_prio(tcf_chain_tp_prev(&chain_info)); tp = tcf_proto_create(nla_data(tca[TCA_KIND]), - protocol, prio, parent, q, block); + protocol, prio, parent, q, chain); if (IS_ERR(tp)) { err = PTR_ERR(tp); goto errout; @@ -556,6 +609,8 @@ replay: } errout: + if (chain) + tcf_chain_put(chain); if (cl) cops->put(q, cl); if (err == -EAGAIN) @@ -584,6 +639,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol); if (nla_put_string(skb, TCA_KIND, tp->ops->kind)) goto nla_put_failure; + if (nla_put_u32(skb, TCA_CHAIN, tp->chain->index)) + goto nla_put_failure; tcm->tcm_handle = fh; if (RTM_DELTFILTER != event) { tcm->tcm_handle = 0; @@ -640,7 +697,7 @@ static int tcf_node_dump(struct tcf_proto *tp, unsigned long n, RTM_NEWTFILTER); } -static void tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, +static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, struct netlink_callback *cb, long index_start, long *p_index) { @@ -667,7 +724,7 @@ static void tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER) <= 0) - break; + return false; cb->args[1] = 1; } @@ -682,14 +739,16 @@ static void tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, tp->ops->walk(tp, &arg.w); cb->args[1] = arg.w.count + 1; if (arg.w.stop) - break; + return false; } + return true; } /* called with RTNL */ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); + struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; struct Qdisc *q; struct tcf_block *block; @@ -699,9 +758,15 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) const struct Qdisc_class_ops *cops; long index_start; long index; + int err; if (nlmsg_len(cb->nlh) < sizeof(*tcm)) return skb->len; + + err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL); + if (err) + return err; + dev = __dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return skb->len; @@ -725,11 +790,18 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) block = cops->tcf_block(q, cl); if (!block) goto errout; - chain = block->chain; index_start = cb->args[0]; index = 0; - tcf_chain_dump(chain, skb, cb, index_start, &index); + + list_for_each_entry(chain, &block->chain_list, list) { + if (tca[TCA_CHAIN] && + nla_get_u32(tca[TCA_CHAIN]) != chain->index) + continue; + if (!tcf_chain_dump(chain, skb, cb, index_start, &index)) + break; + } + cb->args[0] = index; errout: -- cgit v1.3-14-g43fede From 9fb9f251d229f6cabd9dbe4214eb7f1e6a4e8a9d Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 May 2017 11:08:02 +0200 Subject: net: sched: push tp down to action init Tp pointer will be needed by the next patch in order to get the chain. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/act_api.h | 12 ++++++------ net/sched/act_api.c | 15 ++++++++------- net/sched/cls_api.c | 9 +++++---- 3 files changed, 19 insertions(+), 17 deletions(-) (limited to 'include/net') diff --git a/include/net/act_api.h b/include/net/act_api.h index cfa2ae33da9a..b22c6f3d6710 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -180,12 +180,12 @@ int tcf_unregister_action(struct tc_action_ops *a, int tcf_action_destroy(struct list_head *actions, int bind); int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, int nr_actions, struct tcf_result *res); -int tcf_action_init(struct net *net, struct nlattr *nla, - struct nlattr *est, char *n, int ovr, - int bind, struct list_head *); -struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, - struct nlattr *est, char *n, int ovr, - int bind); +int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, + struct nlattr *est, char *name, int ovr, int bind, + struct list_head *actions); +struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, + struct nlattr *nla, struct nlattr *est, + char *name, int ovr, int bind); int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int); int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index a90e8f355c00..e389eb45b484 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -570,9 +570,9 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) return c; } -struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, - struct nlattr *est, char *name, int ovr, - int bind) +struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, + struct nlattr *nla, struct nlattr *est, + char *name, int ovr, int bind) { struct tc_action *a; struct tc_action_ops *a_o; @@ -680,8 +680,9 @@ static void cleanup_a(struct list_head *actions, int ovr) a->tcfa_refcnt--; } -int tcf_action_init(struct net *net, struct nlattr *nla, struct nlattr *est, - char *name, int ovr, int bind, struct list_head *actions) +int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, + struct nlattr *est, char *name, int ovr, int bind, + struct list_head *actions) { struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *act; @@ -693,7 +694,7 @@ int tcf_action_init(struct net *net, struct nlattr *nla, struct nlattr *est, return err; for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { - act = tcf_action_init_1(net, tb[i], est, name, ovr, bind); + act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind); if (IS_ERR(act)) { err = PTR_ERR(act); goto err; @@ -1020,7 +1021,7 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, int ret = 0; LIST_HEAD(actions); - ret = tcf_action_init(net, nla, NULL, NULL, ovr, 0, &actions); + ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions); if (ret) return ret; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index adacaf299c4a..9e0c4bb82528 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -832,8 +832,9 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct tc_action *act; if (exts->police && tb[exts->police]) { - act = tcf_action_init_1(net, tb[exts->police], rate_tlv, - "police", ovr, TCA_ACT_BIND); + act = tcf_action_init_1(net, tp, tb[exts->police], + rate_tlv, "police", ovr, + TCA_ACT_BIND); if (IS_ERR(act)) return PTR_ERR(act); @@ -844,8 +845,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, LIST_HEAD(actions); int err, i = 0; - err = tcf_action_init(net, tb[exts->action], rate_tlv, - NULL, ovr, TCA_ACT_BIND, + err = tcf_action_init(net, tp, tb[exts->action], + rate_tlv, NULL, ovr, TCA_ACT_BIND, &actions); if (err) return err; -- cgit v1.3-14-g43fede From db50514f9a9c7ef1f17e9921b1cc0902746872f3 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 May 2017 11:08:03 +0200 Subject: net: sched: add termination action to allow goto chain Introduce new type of termination action called "goto_chain". This allows user to specify a chain to be processed. This action type is then processed as a return value in tcf_classify loop in similar way as "reclassify" is, only it does not reset to the first filter in chain but rather reset to the first filter of the desired chain. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/act_api.h | 1 + include/net/sch_generic.h | 9 +++++++-- include/uapi/linux/pkt_cls.h | 1 + net/sched/act_api.c | 40 ++++++++++++++++++++++++++++++++++++++++ net/sched/cls_api.c | 6 +++++- 5 files changed, 54 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/act_api.h b/include/net/act_api.h index b22c6f3d6710..26ffd8333f50 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -42,6 +42,7 @@ struct tc_action { struct gnet_stats_basic_cpu __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; struct tc_cookie *act_cookie; + struct tcf_chain *goto_chain; }; #define tcf_head common.tcfa_head #define tcf_index common.tcfa_index diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 569b5654c30c..368850194c94 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -193,8 +193,13 @@ struct Qdisc_ops { struct tcf_result { - unsigned long class; - u32 classid; + union { + struct { + unsigned long class; + u32 classid; + }; + const struct tcf_proto *goto_tp; + }; }; struct tcf_proto_ops { diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index d613be3b3239..1b9aa9e6b4fd 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -51,6 +51,7 @@ enum { (((combined) & (~TC_ACT_EXT_VAL_MASK)) == opcode) #define TC_ACT_JUMP __TC_ACT_EXT(1) +#define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2) /* Action type identifiers*/ enum { diff --git a/net/sched/act_api.c b/net/sched/act_api.c index e389eb45b484..0ecf2a858767 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -28,6 +28,31 @@ #include #include +static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp) +{ + u32 chain_index = a->tcfa_action & TC_ACT_EXT_VAL_MASK; + + if (!tp) + return -EINVAL; + a->goto_chain = tcf_chain_get(tp->chain->block, chain_index); + if (!a->goto_chain) + return -ENOMEM; + return 0; +} + +static void tcf_action_goto_chain_fini(struct tc_action *a) +{ + tcf_chain_put(a->goto_chain); +} + +static void tcf_action_goto_chain_exec(const struct tc_action *a, + struct tcf_result *res) +{ + const struct tcf_chain *chain = a->goto_chain; + + res->goto_tp = rcu_dereference_bh(chain->filter_chain); +} + static void free_tcf(struct rcu_head *head) { struct tc_action *p = container_of(head, struct tc_action, tcfa_rcu); @@ -39,6 +64,8 @@ static void free_tcf(struct rcu_head *head) kfree(p->act_cookie->data); kfree(p->act_cookie); } + if (p->goto_chain) + tcf_action_goto_chain_fini(p); kfree(p); } @@ -465,6 +492,8 @@ repeat: else /* faulty graph, stop pipeline */ return TC_ACT_OK; } + } else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) { + tcf_action_goto_chain_exec(a, res); } if (ret != TC_ACT_PIPE) @@ -657,6 +686,17 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, if (err != ACT_P_CREATED) module_put(a_o->owner); + if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) { + err = tcf_action_goto_chain_init(a, tp); + if (err) { + LIST_HEAD(actions); + + list_add_tail(&a->list, &actions); + tcf_action_destroy(&actions, bind); + return ERR_PTR(err); + } + } + return a; err_mod: diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 9e0c4bb82528..4020b8d932a1 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -307,8 +307,12 @@ reclassify: err = tp->classify(skb, tp, res); #ifdef CONFIG_NET_CLS_ACT - if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) + if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) { goto reset; + } else if (unlikely(TC_ACT_EXT_CMP(err, TC_ACT_GOTO_CHAIN))) { + old_tp = res->goto_tp; + goto reset; + } #endif if (err >= 0) return err; -- cgit v1.3-14-g43fede From ec66eda82d4b0c552bf40005d8f53b63b2b07de4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 May 2017 14:00:01 -0700 Subject: tcp: introduce tcp_jiffies32 We abuse tcp_time_stamp for two different cases : 1) base to generate TCP Timestamp options (RFC 7323) 2) A 32bit version of jiffies since some TCP fields are 32bit wide to save memory. Since we want in the future to have 1ms TCP TS clock, regardless of HZ value, we want to cleanup things. tcp_jiffies32 is the truncated jiffies value, which will be used only in places where we want a 'host' timestamp. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/net/tcp.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index b4dc93dae98c..4b45be570821 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -700,11 +700,14 @@ u32 __tcp_select_window(struct sock *sk); void tcp_send_window_probe(struct sock *sk); -/* TCP timestamps are only 32-bits, this causes a slight - * complication on 64-bit systems since we store a snapshot - * of jiffies in the buffer control blocks below. We decided - * to use only the low 32-bits of jiffies and hide the ugly - * casts with the following macro. +/* TCP uses 32bit jiffies to save some space. + * Note that this is different from tcp_time_stamp, which + * historically has been the same until linux-4.13. + */ +#define tcp_jiffies32 ((u32)jiffies) + +/* Generator for TCP TS option (RFC 7323) + * Currently tied to 'jiffies' but will soon be driven by 1 ms clock. */ #define tcp_time_stamp ((__u32)(jiffies)) -- cgit v1.3-14-g43fede From d635fbe27ebee0f4b845abe5e9620c9400785a5c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 May 2017 14:00:03 -0700 Subject: tcp: use tcp_jiffies32 to feed tp->lsndtime Use tcp_jiffies32 instead of tcp_time_stamp to feed tp->lsndtime. tcp_time_stamp will soon be a litle bit more expensive than simply reading 'jiffies'. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_cubic.c | 2 +- net/ipv4/tcp_input.c | 4 ++-- net/ipv4/tcp_output.c | 4 ++-- net/ipv4/tcp_timer.c | 4 ++-- 6 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index 4b45be570821..feba4c0406e5 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1245,7 +1245,7 @@ static inline void tcp_slow_start_after_idle_check(struct sock *sk) if (!sysctl_tcp_slow_start_after_idle || tp->packets_out || ca_ops->cong_control) return; - delta = tcp_time_stamp - tp->lsndtime; + delta = tcp_jiffies32 - tp->lsndtime; if (delta > inet_csk(sk)->icsk_rto) tcp_cwnd_restart(sk, delta); } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1e4c76d2b827..d0bb61ee28bb 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2841,7 +2841,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_retrans = tp->retrans_out; info->tcpi_fackets = tp->fackets_out; - now = tcp_time_stamp; + now = tcp_jiffies32; info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime); info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime); info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 0683ba447d77..2052ca740916 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -155,7 +155,7 @@ static void bictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) { if (event == CA_EVENT_TX_START) { struct bictcp *ca = inet_csk_ca(sk); - u32 now = tcp_time_stamp; + u32 now = tcp_jiffies32; s32 delta; delta = now - tcp_sk(sk)->lsndtime; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 06e2dbc2b4a2..c0b3f909df39 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5571,7 +5571,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) /* Prevent spurious tcp_cwnd_restart() on first data * packet. */ - tp->lsndtime = tcp_time_stamp; + tp->lsndtime = tcp_jiffies32; tcp_init_buffer_space(sk); @@ -6008,7 +6008,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_update_pacing_rate(sk); /* Prevent spurious tcp_cwnd_restart() on first data packet */ - tp->lsndtime = tcp_time_stamp; + tp->lsndtime = tcp_jiffies32; tcp_initialize_rcv_mss(sk); tcp_fast_path_on(tp); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4c8a6eaba6b3..be9f8f483e21 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -160,7 +160,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp, struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - const u32 now = tcp_time_stamp; + const u32 now = tcp_jiffies32; if (tcp_packets_in_flight(tp) == 0) tcp_ca_event(sk, CA_EVENT_TX_START); @@ -1918,7 +1918,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, /* Avoid bursty behavior by allowing defer * only if the last write was recent. */ - if ((s32)(tcp_time_stamp - tp->lsndtime) > 0) + if ((s32)(tcp_jiffies32 - tp->lsndtime) > 0) goto send_now; in_flight = tcp_packets_in_flight(tp); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index ec7c5473c788..5f6f219a431e 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -63,7 +63,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) /* If peer does not open window for long time, or did not transmit * anything for long time, penalize it. */ - if ((s32)(tcp_time_stamp - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset) + if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset) shift++; /* If some dubious ICMP arrived, penalize even more. */ @@ -73,7 +73,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) if (tcp_check_oom(sk, shift)) { /* Catch exceptional cases, when connection requires reset. * 1. Last segment was sent recently. */ - if ((s32)(tcp_time_stamp - tp->lsndtime) <= TCP_TIMEWAIT_LEN || + if ((s32)(tcp_jiffies32 - tp->lsndtime) <= TCP_TIMEWAIT_LEN || /* 2. Window is closed. */ (!tp->snd_wnd && !tp->packets_out)) do_reset = true; -- cgit v1.3-14-g43fede From 70eabf0e1b8fe11519f793416655266605f700b9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 May 2017 14:00:07 -0700 Subject: tcp: use tcp_jiffies32 for rcv_tstamp and lrcvtime Use tcp_jiffies32 instead of tcp_time_stamp, since tcp_time_stamp will soon be only used for TCP TS option. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/net/tcp.h | 4 ++-- net/ipv4/tcp_input.c | 6 +++--- net/ipv4/tcp_minisocks.c | 2 +- net/ipv4/tcp_output.c | 2 +- net/ipv4/tcp_timer.c | 2 +- 5 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index feba4c0406e5..5b2932b8363f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1307,8 +1307,8 @@ static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) { const struct inet_connection_sock *icsk = &tp->inet_conn; - return min_t(u32, tcp_time_stamp - icsk->icsk_ack.lrcvtime, - tcp_time_stamp - tp->rcv_tstamp); + return min_t(u32, tcp_jiffies32 - icsk->icsk_ack.lrcvtime, + tcp_jiffies32 - tp->rcv_tstamp); } static inline int tcp_fin_time(const struct sock *sk) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 6a15c9b80b09..eeb4967df25a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -672,7 +672,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) tcp_rcv_rtt_measure(tp); - now = tcp_time_stamp; + now = tcp_jiffies32; if (!icsk->icsk_ack.ato) { /* The _first_ data packet received, initialize @@ -3636,7 +3636,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) */ sk->sk_err_soft = 0; icsk->icsk_probes_out = 0; - tp->rcv_tstamp = tcp_time_stamp; + tp->rcv_tstamp = tcp_jiffies32; if (!prior_packets) goto no_queue; @@ -5554,7 +5554,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) struct inet_connection_sock *icsk = inet_csk(sk); tcp_set_state(sk, TCP_ESTABLISHED); - icsk->icsk_ack.lrcvtime = tcp_time_stamp; + icsk->icsk_ack.lrcvtime = tcp_jiffies32; if (skb) { icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 717be4de5324..59c32e0086c0 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -447,7 +447,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U); newicsk->icsk_rto = TCP_TIMEOUT_INIT; - newicsk->icsk_ack.lrcvtime = tcp_time_stamp; + newicsk->icsk_ack.lrcvtime = tcp_jiffies32; newtp->packets_out = 0; newtp->retrans_out = 0; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4bd50f0b236b..cbda5de16449 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3324,7 +3324,7 @@ static void tcp_connect_init(struct sock *sk) if (likely(!tp->repair)) tp->rcv_nxt = 0; else - tp->rcv_tstamp = tcp_time_stamp; + tp->rcv_tstamp = tcp_jiffies32; tp->rcv_wup = tp->rcv_nxt; tp->copied_seq = tp->rcv_nxt; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 5f6f219a431e..9e0616cb8c17 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -451,7 +451,7 @@ void tcp_retransmit_timer(struct sock *sk) tp->snd_una, tp->snd_nxt); } #endif - if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) { + if (tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX) { tcp_write_err(sk); goto out; } -- cgit v1.3-14-g43fede From 9a568de4818dea9a05af141046bd3e589245ab83 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 May 2017 14:00:14 -0700 Subject: tcp: switch TCP TS option (RFC 7323) to 1ms clock TCP Timestamps option is defined in RFC 7323 Traditionally on linux, it has been tied to the internal 'jiffies' variable, because it had been a cheap and good enough generator. For TCP flows on the Internet, 1 ms resolution would be much better than 4ms or 10ms (HZ=250 or HZ=100 respectively) For TCP flows in the DC, Google has used usec resolution for more than two years with great success [1] Receive size autotuning (DRS) is indeed more precise and converges faster to optimal window size. This patch converts tp->tcp_mstamp to a plain u64 value storing a 1 usec TCP clock. This choice will allow us to upstream the 1 usec TS option as discussed in IETF 97. [1] https://www.ietf.org/proceedings/97/slides/slides-97-tcpm-tcp-options-for-low-latency-00.pdf Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/linux/skbuff.h | 62 +------------------------- include/linux/tcp.h | 22 ++++----- include/net/tcp.h | 59 ++++++++++++++++++++---- net/ipv4/syncookies.c | 8 ++-- net/ipv4/tcp.c | 4 +- net/ipv4/tcp_bbr.c | 22 ++++----- net/ipv4/tcp_input.c | 96 ++++++++++++++++++++-------------------- net/ipv4/tcp_ipv4.c | 17 +++---- net/ipv4/tcp_lp.c | 12 ++--- net/ipv4/tcp_minisocks.c | 4 +- net/ipv4/tcp_output.c | 16 +++---- net/ipv4/tcp_rate.c | 16 +++---- net/ipv4/tcp_recovery.c | 23 +++++----- net/ipv4/tcp_timer.c | 8 ++-- net/ipv6/syncookies.c | 2 +- net/ipv6/tcp_ipv6.c | 4 +- net/netfilter/nf_synproxy_core.c | 2 +- 17 files changed, 178 insertions(+), 199 deletions(-) (limited to 'include/net') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bfc7892f6c33..7c0cb2ce8b01 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -506,66 +506,6 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif -/** - * struct skb_mstamp - multi resolution time stamps - * @stamp_us: timestamp in us resolution - * @stamp_jiffies: timestamp in jiffies - */ -struct skb_mstamp { - union { - u64 v64; - struct { - u32 stamp_us; - u32 stamp_jiffies; - }; - }; -}; - -/** - * skb_mstamp_get - get current timestamp - * @cl: place to store timestamps - */ -static inline void skb_mstamp_get(struct skb_mstamp *cl) -{ - u64 val = local_clock(); - - do_div(val, NSEC_PER_USEC); - cl->stamp_us = (u32)val; - cl->stamp_jiffies = (u32)jiffies; -} - -/** - * skb_mstamp_delta - compute the difference in usec between two skb_mstamp - * @t1: pointer to newest sample - * @t0: pointer to oldest sample - */ -static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, - const struct skb_mstamp *t0) -{ - s32 delta_us = t1->stamp_us - t0->stamp_us; - u32 delta_jiffies = t1->stamp_jiffies - t0->stamp_jiffies; - - /* If delta_us is negative, this might be because interval is too big, - * or local_clock() drift is too big : fallback using jiffies. - */ - if (delta_us <= 0 || - delta_jiffies >= (INT_MAX / (USEC_PER_SEC / HZ))) - - delta_us = jiffies_to_usecs(delta_jiffies); - - return delta_us; -} - -static inline bool skb_mstamp_after(const struct skb_mstamp *t1, - const struct skb_mstamp *t0) -{ - s32 diff = t1->stamp_jiffies - t0->stamp_jiffies; - - if (!diff) - diff = t1->stamp_us - t0->stamp_us; - return diff > 0; -} - /** * struct sk_buff - socket buffer * @next: Next buffer in list @@ -646,7 +586,7 @@ struct sk_buff { union { ktime_t tstamp; - struct skb_mstamp skb_mstamp; + u64 skb_mstamp; }; }; struct rb_node rbnode; /* used in netem & tcp stack */ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 22854f028434..542ca1ae02c4 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -123,7 +123,7 @@ struct tcp_request_sock_ops; struct tcp_request_sock { struct inet_request_sock req; const struct tcp_request_sock_ops *af_specific; - struct skb_mstamp snt_synack; /* first SYNACK sent time */ + u64 snt_synack; /* first SYNACK sent time */ bool tfo_listener; u32 txhash; u32 rcv_isn; @@ -211,7 +211,7 @@ struct tcp_sock { /* Information of the most recently (s)acked skb */ struct tcp_rack { - struct skb_mstamp mstamp; /* (Re)sent time of the skb */ + u64 mstamp; /* (Re)sent time of the skb */ u32 rtt_us; /* Associated RTT */ u32 end_seq; /* Ending TCP sequence of the skb */ u8 advanced; /* mstamp advanced since last lost marking */ @@ -240,7 +240,7 @@ struct tcp_sock { u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ /* RTT measurement */ - struct skb_mstamp tcp_mstamp; /* most recent packet received/sent */ + u64 tcp_mstamp; /* most recent packet received/sent */ u32 srtt_us; /* smoothed round trip time << 3 in usecs */ u32 mdev_us; /* medium deviation */ u32 mdev_max_us; /* maximal mdev for the last rtt period */ @@ -280,8 +280,8 @@ struct tcp_sock { u32 delivered; /* Total data packets delivered incl. rexmits */ u32 lost; /* Total data packets lost incl. rexmits */ u32 app_limited; /* limited until "delivered" reaches this val */ - struct skb_mstamp first_tx_mstamp; /* start of window send phase */ - struct skb_mstamp delivered_mstamp; /* time we reached "delivered" */ + u64 first_tx_mstamp; /* start of window send phase */ + u64 delivered_mstamp; /* time we reached "delivered" */ u32 rate_delivered; /* saved rate sample: packets delivered */ u32 rate_interval_us; /* saved rate sample: time elapsed */ @@ -335,16 +335,16 @@ struct tcp_sock { /* Receiver side RTT estimation */ struct { - u32 rtt_us; - u32 seq; - struct skb_mstamp time; + u32 rtt_us; + u32 seq; + u64 time; } rcv_rtt_est; /* Receiver queue space */ struct { - int space; - u32 seq; - struct skb_mstamp time; + int space; + u32 seq; + u64 time; } rcvq_space; /* TCP-specific MTU probe information. */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 5b2932b8363f..82462db97183 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -519,7 +519,7 @@ static inline u32 tcp_cookie_time(void) u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); -__u32 cookie_init_timestamp(struct request_sock *req); +u64 cookie_init_timestamp(struct request_sock *req); bool cookie_timestamp_decode(struct tcp_options_received *opt); bool cookie_ecn_ok(const struct tcp_options_received *opt, const struct net *net, const struct dst_entry *dst); @@ -706,14 +706,55 @@ void tcp_send_window_probe(struct sock *sk); */ #define tcp_jiffies32 ((u32)jiffies) -/* Generator for TCP TS option (RFC 7323) - * Currently tied to 'jiffies' but will soon be driven by 1 ms clock. +/* + * Deliver a 32bit value for TCP timestamp option (RFC 7323) + * It is no longer tied to jiffies, but to 1 ms clock. + * Note: double check if you want to use tcp_jiffies32 instead of this. + */ +#define TCP_TS_HZ 1000 + +static inline u64 tcp_clock_ns(void) +{ + return local_clock(); +} + +static inline u64 tcp_clock_us(void) +{ + return div_u64(tcp_clock_ns(), NSEC_PER_USEC); +} + +/* This should only be used in contexts where tp->tcp_mstamp is up to date */ +static inline u32 tcp_time_stamp(const struct tcp_sock *tp) +{ + return div_u64(tp->tcp_mstamp, USEC_PER_SEC / TCP_TS_HZ); +} + +/* Could use tcp_clock_us() / 1000, but this version uses a single divide */ +static inline u32 tcp_time_stamp_raw(void) +{ + return div_u64(tcp_clock_ns(), NSEC_PER_SEC / TCP_TS_HZ); +} + + +/* Refresh 1us clock of a TCP socket, + * ensuring monotically increasing values. */ -#define tcp_time_stamp ((__u32)(jiffies)) +static inline void tcp_mstamp_refresh(struct tcp_sock *tp) +{ + u64 val = tcp_clock_us(); + + if (val > tp->tcp_mstamp) + tp->tcp_mstamp = val; +} + +static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) +{ + return max_t(s64, t1 - t0, 0); +} static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) { - return skb->skb_mstamp.stamp_jiffies; + return div_u64(skb->skb_mstamp, USEC_PER_SEC / TCP_TS_HZ); } @@ -778,9 +819,9 @@ struct tcp_skb_cb { /* pkts S/ACKed so far upon tx of skb, incl retrans: */ __u32 delivered; /* start of send pipeline phase */ - struct skb_mstamp first_tx_mstamp; + u64 first_tx_mstamp; /* when we reached the "delivered" count */ - struct skb_mstamp delivered_mstamp; + u64 delivered_mstamp; } tx; /* only used for outgoing skbs */ union { struct inet_skb_parm h4; @@ -896,7 +937,7 @@ struct ack_sample { * A sample is invalid if "delivered" or "interval_us" is negative. */ struct rate_sample { - struct skb_mstamp prior_mstamp; /* starting timestamp for interval */ + u64 prior_mstamp; /* starting timestamp for interval */ u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ s32 delivered; /* number of packets delivered over interval */ long interval_us; /* time for tp->delivered to incr "delivered" */ @@ -1862,7 +1903,7 @@ void tcp_init(void); /* tcp_recovery.c */ extern void tcp_rack_mark_lost(struct sock *sk); extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, - const struct skb_mstamp *xmit_time); + u64 xmit_time); extern void tcp_rack_reo_timeout(struct sock *sk); /* diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 0257d965f111..6426250a58ea 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -66,10 +66,10 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, * Since subsequent timestamps use the normal tcp_time_stamp value, we * must make sure that the resulting initial timestamp is <= tcp_time_stamp. */ -__u32 cookie_init_timestamp(struct request_sock *req) +u64 cookie_init_timestamp(struct request_sock *req) { struct inet_request_sock *ireq; - u32 ts, ts_now = tcp_time_stamp; + u32 ts, ts_now = tcp_time_stamp_raw(); u32 options = 0; ireq = inet_rsk(req); @@ -88,7 +88,7 @@ __u32 cookie_init_timestamp(struct request_sock *req) ts <<= TSBITS; ts |= options; } - return ts; + return (u64)ts * (USEC_PER_SEC / TCP_TS_HZ); } @@ -343,7 +343,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok = tcp_opt.wscale_ok; ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - treq->snt_synack.v64 = 0; + treq->snt_synack = 0; treq->tfo_listener = false; ireq->ir_iif = inet_request_bound_dev_if(sk, skb); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 850054800526..b5d18484746d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2706,7 +2706,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, if (!tp->repair) err = -EPERM; else - tp->tsoffset = val - tcp_time_stamp; + tp->tsoffset = val - tcp_time_stamp_raw(); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); @@ -3072,7 +3072,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_TIMESTAMP: - val = tcp_time_stamp + tp->tsoffset; + val = tcp_time_stamp_raw() + tp->tsoffset; break; case TCP_NOTSENT_LOWAT: val = tp->notsent_lowat; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 40dc4fc5f6ac..dbcc9352a48f 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -91,7 +91,7 @@ struct bbr { struct minmax bw; /* Max recent delivery rate in pkts/uS << 24 */ u32 rtt_cnt; /* count of packet-timed rounds elapsed */ u32 next_rtt_delivered; /* scb->tx.delivered at end of round */ - struct skb_mstamp cycle_mstamp; /* time of this cycle phase start */ + u64 cycle_mstamp; /* time of this cycle phase start */ u32 mode:3, /* current bbr_mode in state machine */ prev_ca_state:3, /* CA state on previous ACK */ packet_conservation:1, /* use packet conservation? */ @@ -411,7 +411,7 @@ static bool bbr_is_next_cycle_phase(struct sock *sk, struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); bool is_full_length = - skb_mstamp_us_delta(&tp->delivered_mstamp, &bbr->cycle_mstamp) > + tcp_stamp_us_delta(tp->delivered_mstamp, bbr->cycle_mstamp) > bbr->min_rtt_us; u32 inflight, bw; @@ -497,7 +497,7 @@ static void bbr_reset_lt_bw_sampling_interval(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); - bbr->lt_last_stamp = tp->delivered_mstamp.stamp_jiffies; + bbr->lt_last_stamp = div_u64(tp->delivered_mstamp, USEC_PER_MSEC); bbr->lt_last_delivered = tp->delivered; bbr->lt_last_lost = tp->lost; bbr->lt_rtt_cnt = 0; @@ -551,7 +551,7 @@ static void bbr_lt_bw_sampling(struct sock *sk, const struct rate_sample *rs) struct bbr *bbr = inet_csk_ca(sk); u32 lost, delivered; u64 bw; - s32 t; + u32 t; if (bbr->lt_use_bw) { /* already using long-term rate, lt_bw? */ if (bbr->mode == BBR_PROBE_BW && bbr->round_start && @@ -603,15 +603,15 @@ static void bbr_lt_bw_sampling(struct sock *sk, const struct rate_sample *rs) return; /* Find average delivery rate in this sampling interval. */ - t = (s32)(tp->delivered_mstamp.stamp_jiffies - bbr->lt_last_stamp); - if (t < 1) - return; /* interval is less than one jiffy, so wait */ - t = jiffies_to_usecs(t); - /* Interval long enough for jiffies_to_usecs() to return a bogus 0? */ - if (t < 1) { + t = div_u64(tp->delivered_mstamp, USEC_PER_MSEC) - bbr->lt_last_stamp; + if ((s32)t < 1) + return; /* interval is less than one ms, so wait */ + /* Check if can multiply without overflow */ + if (t >= ~0U / USEC_PER_MSEC) { bbr_reset_lt_bw_sampling(sk); /* interval too long; reset */ return; } + t *= USEC_PER_MSEC; bw = (u64)delivered * BW_UNIT; do_div(bw, t); bbr_lt_bw_interval_done(sk, bw); @@ -825,7 +825,7 @@ static void bbr_init(struct sock *sk) bbr->idle_restart = 0; bbr->full_bw = 0; bbr->full_bw_cnt = 0; - bbr->cycle_mstamp.v64 = 0; + bbr->cycle_mstamp = 0; bbr->cycle_idx = 0; bbr_reset_lt_bw_sampling(sk); bbr_reset_startup_mode(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 10e6775464f6..9a5a9e8eda89 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -441,7 +441,7 @@ void tcp_init_buffer_space(struct sock *sk) tcp_sndbuf_expand(sk); tp->rcvq_space.space = tp->rcv_wnd; - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); tp->rcvq_space.time = tp->tcp_mstamp; tp->rcvq_space.seq = tp->copied_seq; @@ -555,11 +555,11 @@ static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp) { u32 delta_us; - if (tp->rcv_rtt_est.time.v64 == 0) + if (tp->rcv_rtt_est.time == 0) goto new_measure; if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq)) return; - delta_us = skb_mstamp_us_delta(&tp->tcp_mstamp, &tp->rcv_rtt_est.time); + delta_us = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcv_rtt_est.time); tcp_rcv_rtt_update(tp, delta_us, 1); new_measure: @@ -571,13 +571,15 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + if (tp->rx_opt.rcv_tsecr && (TCP_SKB_CB(skb)->end_seq - - TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) - tcp_rcv_rtt_update(tp, - jiffies_to_usecs(tcp_time_stamp - - tp->rx_opt.rcv_tsecr), - 0); + TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) { + u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; + u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + + tcp_rcv_rtt_update(tp, delta_us, 0); + } } /* @@ -590,7 +592,7 @@ void tcp_rcv_space_adjust(struct sock *sk) int time; int copied; - time = skb_mstamp_us_delta(&tp->tcp_mstamp, &tp->rcvq_space.time); + time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time); if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0) return; @@ -1134,8 +1136,8 @@ struct tcp_sacktag_state { * that was SACKed. RTO needs the earliest RTT to stay conservative, * but congestion control should still get an accurate delay signal. */ - struct skb_mstamp first_sackt; - struct skb_mstamp last_sackt; + u64 first_sackt; + u64 last_sackt; struct rate_sample *rate; int flag; }; @@ -1200,7 +1202,7 @@ static u8 tcp_sacktag_one(struct sock *sk, struct tcp_sacktag_state *state, u8 sacked, u32 start_seq, u32 end_seq, int dup_sack, int pcount, - const struct skb_mstamp *xmit_time) + u64 xmit_time) { struct tcp_sock *tp = tcp_sk(sk); int fack_count = state->fack_count; @@ -1242,9 +1244,9 @@ static u8 tcp_sacktag_one(struct sock *sk, state->reord); if (!after(end_seq, tp->high_seq)) state->flag |= FLAG_ORIG_SACK_ACKED; - if (state->first_sackt.v64 == 0) - state->first_sackt = *xmit_time; - state->last_sackt = *xmit_time; + if (state->first_sackt == 0) + state->first_sackt = xmit_time; + state->last_sackt = xmit_time; } if (sacked & TCPCB_LOST) { @@ -1304,7 +1306,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, */ tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, start_seq, end_seq, dup_sack, pcount, - &skb->skb_mstamp); + skb->skb_mstamp); tcp_rate_skb_delivered(sk, skb, state->rate); if (skb == tp->lost_skb_hint) @@ -1356,8 +1358,8 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, tcp_advance_highest_sack(sk, skb); tcp_skb_collapse_tstamp(prev, skb); - if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp.v64)) - TCP_SKB_CB(prev)->tx.delivered_mstamp.v64 = 0; + if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp)) + TCP_SKB_CB(prev)->tx.delivered_mstamp = 0; tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); @@ -1587,7 +1589,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, TCP_SKB_CB(skb)->end_seq, dup_sack, tcp_skb_pcount(skb), - &skb->skb_mstamp); + skb->skb_mstamp); tcp_rate_skb_delivered(sk, skb, state->rate); if (!before(TCP_SKB_CB(skb)->seq, @@ -2936,9 +2938,12 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, * See draft-ietf-tcplw-high-performance-00, section 3.3. */ if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && - flag & FLAG_ACKED) - seq_rtt_us = ca_rtt_us = jiffies_to_usecs(tcp_time_stamp - - tp->rx_opt.rcv_tsecr); + flag & FLAG_ACKED) { + u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; + u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + + seq_rtt_us = ca_rtt_us = delta_us; + } if (seq_rtt_us < 0) return false; @@ -2960,12 +2965,8 @@ void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req) { long rtt_us = -1L; - if (req && !req->num_retrans && tcp_rsk(req)->snt_synack.v64) { - struct skb_mstamp now; - - skb_mstamp_get(&now); - rtt_us = skb_mstamp_us_delta(&now, &tcp_rsk(req)->snt_synack); - } + if (req && !req->num_retrans && tcp_rsk(req)->snt_synack) + rtt_us = tcp_stamp_us_delta(tcp_clock_us(), tcp_rsk(req)->snt_synack); tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L, rtt_us); } @@ -3003,7 +3004,7 @@ void tcp_rearm_rto(struct sock *sk) struct sk_buff *skb = tcp_write_queue_head(sk); const u32 rto_time_stamp = tcp_skb_timestamp(skb) + rto; - s32 delta = (s32)(rto_time_stamp - tcp_time_stamp); + s32 delta = (s32)(rto_time_stamp - tcp_jiffies32); /* delta may not be positive if the socket is locked * when the retrans timer fires and is rescheduled. */ @@ -3060,9 +3061,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, struct tcp_sacktag_state *sack) { const struct inet_connection_sock *icsk = inet_csk(sk); - struct skb_mstamp first_ackt, last_ackt; + u64 first_ackt, last_ackt; struct tcp_sock *tp = tcp_sk(sk); - struct skb_mstamp *now = &tp->tcp_mstamp; u32 prior_sacked = tp->sacked_out; u32 reord = tp->packets_out; bool fully_acked = true; @@ -3075,7 +3075,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, bool rtt_update; int flag = 0; - first_ackt.v64 = 0; + first_ackt = 0; while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); @@ -3106,8 +3106,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, flag |= FLAG_RETRANS_DATA_ACKED; } else if (!(sacked & TCPCB_SACKED_ACKED)) { last_ackt = skb->skb_mstamp; - WARN_ON_ONCE(last_ackt.v64 == 0); - if (!first_ackt.v64) + WARN_ON_ONCE(last_ackt == 0); + if (!first_ackt) first_ackt = last_ackt; last_in_flight = TCP_SKB_CB(skb)->tx.in_flight; @@ -3122,7 +3122,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->delivered += acked_pcount; if (!tcp_skb_spurious_retrans(tp, skb)) tcp_rack_advance(tp, sacked, scb->end_seq, - &skb->skb_mstamp); + skb->skb_mstamp); } if (sacked & TCPCB_LOST) tp->lost_out -= acked_pcount; @@ -3165,13 +3165,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; - if (likely(first_ackt.v64) && !(flag & FLAG_RETRANS_DATA_ACKED)) { - seq_rtt_us = skb_mstamp_us_delta(now, &first_ackt); - ca_rtt_us = skb_mstamp_us_delta(now, &last_ackt); + if (likely(first_ackt) && !(flag & FLAG_RETRANS_DATA_ACKED)) { + seq_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, first_ackt); + ca_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, last_ackt); } - if (sack->first_sackt.v64) { - sack_rtt_us = skb_mstamp_us_delta(now, &sack->first_sackt); - ca_rtt_us = skb_mstamp_us_delta(now, &sack->last_sackt); + if (sack->first_sackt) { + sack_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, sack->first_sackt); + ca_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, sack->last_sackt); } sack->rate->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet, or -1 */ rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us, @@ -3201,7 +3201,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->fackets_out -= min(pkts_acked, tp->fackets_out); } else if (skb && rtt_update && sack_rtt_us >= 0 && - sack_rtt_us > skb_mstamp_us_delta(now, &skb->skb_mstamp)) { + sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp)) { /* Do not re-arm RTO if the sack RTT is measured from data sent * after when the head was last (re)transmitted. Otherwise the * timeout may continue to extend in loss recovery. @@ -3553,7 +3553,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) int acked = 0; /* Number of packets newly acked */ int rexmit = REXMIT_NONE; /* Flag to (re)transmit to recover losses */ - sack_state.first_sackt.v64 = 0; + sack_state.first_sackt = 0; sack_state.rate = &rs; /* We very likely will need to access write queue head. */ @@ -5356,7 +5356,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); if (unlikely(!sk->sk_rx_dst)) inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb); /* @@ -5672,7 +5672,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && !between(tp->rx_opt.rcv_tsecr, tp->retrans_stamp, - tcp_time_stamp)) { + tcp_time_stamp(tp))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSACTIVEREJECTED); goto reset_and_undo; @@ -5917,7 +5917,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) case TCP_SYN_SENT: tp->rx_opt.saw_tstamp = 0; - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); queued = tcp_rcv_synsent_state_process(sk, skb, th); if (queued >= 0) return queued; @@ -5929,7 +5929,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) return 0; } - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); tp->rx_opt.saw_tstamp = 0; req = tp->fastopen_rsk; if (req) { @@ -6202,7 +6202,7 @@ static void tcp_openreq_init(struct request_sock *req, req->cookie_ts = 0; tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; - skb_mstamp_get(&tcp_rsk(req)->snt_synack); + tcp_rsk(req)->snt_synack = tcp_clock_us(); tcp_rsk(req)->last_oow_ack_time = 0; req->mss = rx_opt->mss_clamp; req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d8fe25db79f2..191b2f78b19d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -376,8 +376,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) struct sock *sk; struct sk_buff *skb; struct request_sock *fastopen; - __u32 seq, snd_una; - __u32 remaining; + u32 seq, snd_una; + s32 remaining; + u32 delta_us; int err; struct net *net = dev_net(icmp_skb->dev); @@ -483,12 +484,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) skb = tcp_write_queue_head(sk); BUG_ON(!skb); - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); + delta_us = (u32)(tp->tcp_mstamp - skb->skb_mstamp); remaining = icsk->icsk_rto - - min(icsk->icsk_rto, - tcp_time_stamp - tcp_skb_timestamp(skb)); + usecs_to_jiffies(delta_us); - if (remaining) { + if (remaining > 0) { inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, remaining, TCP_RTO_MAX); } else { @@ -812,7 +813,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v4_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcp_time_stamp + tcptw->tw_ts_offset, + tcp_time_stamp_raw() + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), @@ -840,7 +841,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, - tcp_time_stamp + tcp_rsk(req)->ts_off, + tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, 0, tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr, diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index ef3122abb373..ae10ed64fe13 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -37,7 +37,7 @@ #include /* resolution of owd */ -#define LP_RESOL 1000 +#define LP_RESOL TCP_TS_HZ /** * enum tcp_lp_state @@ -147,9 +147,9 @@ static u32 tcp_lp_remote_hz_estimator(struct sock *sk) tp->rx_opt.rcv_tsecr == lp->local_ref_time) goto out; - m = HZ * (tp->rx_opt.rcv_tsval - - lp->remote_ref_time) / (tp->rx_opt.rcv_tsecr - - lp->local_ref_time); + m = TCP_TS_HZ * + (tp->rx_opt.rcv_tsval - lp->remote_ref_time) / + (tp->rx_opt.rcv_tsecr - lp->local_ref_time); if (m < 0) m = -m; @@ -194,7 +194,7 @@ static u32 tcp_lp_owd_calculator(struct sock *sk) if (lp->flag & LP_VALID_RHZ) { owd = tp->rx_opt.rcv_tsval * (LP_RESOL / lp->remote_hz) - - tp->rx_opt.rcv_tsecr * (LP_RESOL / HZ); + tp->rx_opt.rcv_tsecr * (LP_RESOL / TCP_TS_HZ); if (owd < 0) owd = -owd; } @@ -264,7 +264,7 @@ static void tcp_lp_pkts_acked(struct sock *sk, const struct ack_sample *sample) { struct tcp_sock *tp = tcp_sk(sk); struct lp *lp = inet_csk_ca(sk); - u32 now = tcp_time_stamp; + u32 now = tcp_time_stamp(tp); u32 delta; if (sample->rtt_us > 0) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 6504f1082bdf..d0642df73044 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -455,7 +455,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->fackets_out = 0; newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; newtp->tlp_high_seq = 0; - newtp->lsndtime = treq->snt_synack.stamp_jiffies; + newtp->lsndtime = tcp_jiffies32; newsk->sk_txhash = treq->txhash; newtp->last_oow_ack_time = 0; newtp->total_retrans = req->num_retrans; @@ -526,7 +526,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->fastopen_req = NULL; newtp->fastopen_rsk = NULL; newtp->syn_data_acked = 0; - newtp->rack.mstamp.v64 = 0; + newtp->rack.mstamp = 0; newtp->rack.advanced = 0; __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 65472e931a0b..478f75baee31 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1962,7 +1962,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, head = tcp_write_queue_head(sk); - age = skb_mstamp_us_delta(&tp->tcp_mstamp, &head->skb_mstamp); + age = tcp_stamp_us_delta(tp->tcp_mstamp, head->skb_mstamp); /* If next ACK is likely to come too late (half srtt), do not defer */ if (age < (tp->srtt_us >> 4)) goto send_now; @@ -2279,7 +2279,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, } max_segs = tcp_tso_segs(sk, mss_now); - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); while ((skb = tcp_send_head(sk))) { unsigned int limit; @@ -3095,7 +3095,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) skb_reserve(skb, MAX_TCP_HEADER); tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk), TCPHDR_ACK | TCPHDR_RST); - skb_mstamp_get(&tcp_sk(sk)->tcp_mstamp); + tcp_mstamp_refresh(tcp_sk(sk)); /* Send it off. */ if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); @@ -3191,10 +3191,10 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, memset(&opts, 0, sizeof(opts)); #ifdef CONFIG_SYN_COOKIES if (unlikely(req->cookie_ts)) - skb->skb_mstamp.stamp_jiffies = cookie_init_timestamp(req); + skb->skb_mstamp = cookie_init_timestamp(req); else #endif - skb_mstamp_get(&skb->skb_mstamp); + skb->skb_mstamp = tcp_clock_us(); #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); @@ -3453,8 +3453,8 @@ int tcp_connect(struct sock *sk) return -ENOBUFS; tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); - skb_mstamp_get(&tp->tcp_mstamp); - tp->retrans_stamp = tp->tcp_mstamp.stamp_jiffies; + tcp_mstamp_refresh(tp); + tp->retrans_stamp = tcp_time_stamp(tp); tcp_connect_queue_skb(sk, buff); tcp_ecn_send_syn(sk, buff); @@ -3615,7 +3615,7 @@ void tcp_send_window_probe(struct sock *sk) { if (sk->sk_state == TCP_ESTABLISHED) { tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1; - skb_mstamp_get(&tcp_sk(sk)->tcp_mstamp); + tcp_mstamp_refresh(tcp_sk(sk)); tcp_xmit_probe_skb(sk, 0, LINUX_MIB_TCPWINPROBE); } } diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index c6a9fa894646..ad99569d4c1e 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -78,7 +78,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *scb = TCP_SKB_CB(skb); - if (!scb->tx.delivered_mstamp.v64) + if (!scb->tx.delivered_mstamp) return; if (!rs->prior_delivered || @@ -89,9 +89,9 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, rs->is_retrans = scb->sacked & TCPCB_RETRANS; /* Find the duration of the "send phase" of this window: */ - rs->interval_us = skb_mstamp_us_delta( - &skb->skb_mstamp, - &scb->tx.first_tx_mstamp); + rs->interval_us = tcp_stamp_us_delta( + skb->skb_mstamp, + scb->tx.first_tx_mstamp); /* Record send time of most recently ACKed packet: */ tp->first_tx_mstamp = skb->skb_mstamp; @@ -101,7 +101,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, * we don't need to reset since it'll be freed soon. */ if (scb->sacked & TCPCB_SACKED_ACKED) - scb->tx.delivered_mstamp.v64 = 0; + scb->tx.delivered_mstamp = 0; } /* Update the connection delivery information and generate a rate sample. */ @@ -125,7 +125,7 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, rs->acked_sacked = delivered; /* freshly ACKed or SACKed */ rs->losses = lost; /* freshly marked lost */ /* Return an invalid sample if no timing information is available. */ - if (!rs->prior_mstamp.v64) { + if (!rs->prior_mstamp) { rs->delivered = -1; rs->interval_us = -1; return; @@ -138,8 +138,8 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, * longer phase. */ snd_us = rs->interval_us; /* send phase */ - ack_us = skb_mstamp_us_delta(&tp->tcp_mstamp, - &rs->prior_mstamp); /* ack phase */ + ack_us = tcp_stamp_us_delta(tp->tcp_mstamp, + rs->prior_mstamp); /* ack phase */ rs->interval_us = max(snd_us, ack_us); /* Normally we expect interval_us >= min-rtt. diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index cd72b3d3879e..fe9a493d0208 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -17,12 +17,9 @@ static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb) } } -static bool tcp_rack_sent_after(const struct skb_mstamp *t1, - const struct skb_mstamp *t2, - u32 seq1, u32 seq2) +static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) { - return skb_mstamp_after(t1, t2) || - (t1->v64 == t2->v64 && after(seq1, seq2)); + return t1 > t2 || (t1 == t2 && after(seq1, seq2)); } /* RACK loss detection (IETF draft draft-ietf-tcpm-rack-01): @@ -72,14 +69,14 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) scb->sacked & TCPCB_SACKED_ACKED) continue; - if (tcp_rack_sent_after(&tp->rack.mstamp, &skb->skb_mstamp, + if (tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp, tp->rack.end_seq, scb->end_seq)) { /* Step 3 in draft-cheng-tcpm-rack-00.txt: * A packet is lost if its elapsed time is beyond * the recent RTT plus the reordering window. */ - u32 elapsed = skb_mstamp_us_delta(&tp->tcp_mstamp, - &skb->skb_mstamp); + u32 elapsed = tcp_stamp_us_delta(tp->tcp_mstamp, + skb->skb_mstamp); s32 remaining = tp->rack.rtt_us + reo_wnd - elapsed; if (remaining < 0) { @@ -127,16 +124,16 @@ void tcp_rack_mark_lost(struct sock *sk) * draft-cheng-tcpm-rack-00.txt */ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, - const struct skb_mstamp *xmit_time) + u64 xmit_time) { u32 rtt_us; - if (tp->rack.mstamp.v64 && - !tcp_rack_sent_after(xmit_time, &tp->rack.mstamp, + if (tp->rack.mstamp && + !tcp_rack_sent_after(xmit_time, tp->rack.mstamp, end_seq, tp->rack.end_seq)) return; - rtt_us = skb_mstamp_us_delta(&tp->tcp_mstamp, xmit_time); + rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, xmit_time); if (sacked & TCPCB_RETRANS) { /* If the sacked packet was retransmitted, it's ambiguous * whether the retransmission or the original (or the prior @@ -152,7 +149,7 @@ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, return; } tp->rack.rtt_us = rtt_us; - tp->rack.mstamp = *xmit_time; + tp->rack.mstamp = xmit_time; tp->rack.end_seq = end_seq; tp->rack.advanced = 1; } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 6629f47aa7f0..27a667bce806 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -153,8 +153,8 @@ static bool retransmits_timed_out(struct sock *sk, unsigned int timeout, bool syn_set) { - unsigned int linear_backoff_thresh, start_ts; unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN; + unsigned int linear_backoff_thresh, start_ts; if (!inet_csk(sk)->icsk_retransmits) return false; @@ -172,7 +172,7 @@ static bool retransmits_timed_out(struct sock *sk, timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + (boundary - linear_backoff_thresh) * TCP_RTO_MAX; } - return (tcp_time_stamp - start_ts) >= timeout; + return (tcp_time_stamp(tcp_sk(sk)) - start_ts) >= jiffies_to_msecs(timeout); } /* A write timeout has occurred. Process the after effects. */ @@ -341,7 +341,7 @@ static void tcp_probe_timer(struct sock *sk) if (!start_ts) tcp_send_head(sk)->skb_mstamp = tp->tcp_mstamp; else if (icsk->icsk_user_timeout && - (s32)(tcp_time_stamp - start_ts) > icsk->icsk_user_timeout) + (s32)(tcp_time_stamp(tp) - start_ts) > icsk->icsk_user_timeout) goto abort; max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2; @@ -561,7 +561,7 @@ void tcp_write_timer_handler(struct sock *sk) goto out; } - skb_mstamp_get(&tcp_sk(sk)->tcp_mstamp); + tcp_mstamp_refresh(tcp_sk(sk)); event = icsk->icsk_pending; switch (event) { diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 5abc3692b901..971823359f5b 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -211,7 +211,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok = tcp_opt.wscale_ok; ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - treq->snt_synack.v64 = 0; + treq->snt_synack = 0; treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; treq->ts_off = 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4f4310a36a04..233edfabe1db 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -949,7 +949,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcp_time_stamp + tcptw->tw_ts_offset, + tcp_time_stamp_raw() + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel)); @@ -971,7 +971,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, - tcp_time_stamp + tcp_rsk(req)->ts_off, + tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0, 0); diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index a504e87c6ddf..49bd8bb16b18 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -152,7 +152,7 @@ void synproxy_init_timestamp_cookie(const struct xt_synproxy_info *info, struct synproxy_options *opts) { opts->tsecr = opts->tsval; - opts->tsval = tcp_time_stamp & ~0x3f; + opts->tsval = tcp_time_stamp_raw() & ~0x3f; if (opts->options & XT_SYNPROXY_OPT_WSCALE) { opts->tsval |= opts->wscale; -- cgit v1.3-14-g43fede From 9756d33b852a17ee67539545c2acf8dc3bda4574 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Mon, 1 May 2017 23:54:17 -0700 Subject: Bluetooth: Enable LE Channel Selection Algorithm event If the Channel Selection Algorithm #2 feature is supported, then enable the new LE Channel Selection Algorithm event. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 1 + net/bluetooth/hci_core.c | 8 ++++++++ 2 files changed, 9 insertions(+) (limited to 'include/net') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 99aa5e5e3100..dd43cfdd443a 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -399,6 +399,7 @@ enum { #define HCI_LE_PING 0x10 #define HCI_LE_DATA_LEN_EXT 0x20 #define HCI_LE_EXT_SCAN_POLICY 0x80 +#define HCI_LE_CHAN_SEL_ALG2 0x40 /* Connection modes */ #define HCI_CM_ACTIVE 0x0000 diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 4a0cac774107..e58b9034afff 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -635,6 +635,14 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) * Report */ + /* If the controller supports Channel Selection Algorithm #2 + * feature, enable the corresponding event. + */ + if (hdev->le_features[1] & HCI_LE_CHAN_SEL_ALG2) + events[2] |= 0x08; /* LE Channel Selection + * Algorithm + */ + /* If the controller supports the LE Set Scan Enable command, * enable the corresponding advertising report event. */ -- cgit v1.3-14-g43fede From de2ba3039cfb61334b2523677cc032422873ff93 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Mon, 1 May 2017 23:54:19 -0700 Subject: Bluetooth: Set LE Default PHY preferences If the LE Set Default PHY command is supported, the indicate to the controller that the host has no preferences for transmitter PHY or receiver PHY selection. Issuing this command gives the controller a clear indication that other PHY can be selected if available. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 7 +++++++ net/bluetooth/hci_core.c | 12 ++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/net') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index dd43cfdd443a..fe98f0a5bef0 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1499,6 +1499,13 @@ struct hci_rp_le_read_max_data_len { __le16 rx_time; } __packed; +#define HCI_OP_LE_SET_DEFAULT_PHY 0x2031 +struct hci_cp_le_set_default_phy { + __u8 all_phys; + __u8 tx_phys; + __u8 rx_phys; +} __packed; + /* ---- HCI Events ---- */ #define HCI_EV_INQUIRY_COMPLETE 0x01 diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 88a616a2b959..43fecd59dfef 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -794,6 +794,18 @@ static int hci_init4_req(struct hci_request *req, unsigned long opt) hci_req_add(req, HCI_OP_LE_WRITE_DEF_DATA_LEN, sizeof(cp), &cp); } + /* Set Default PHY parameters if command is supported */ + if (hdev->commands[35] & 0x20) { + struct hci_cp_le_set_default_phy cp; + + /* No transmitter PHY or receiver PHY preferences */ + cp.all_phys = 0x03; + cp.tx_phys = 0; + cp.rx_phys = 0; + + hci_req_add(req, HCI_OP_LE_SET_DEFAULT_PHY, sizeof(cp), &cp); + } + return 0; } -- cgit v1.3-14-g43fede From 64df6d525fcff1630098db9238bfd2b3e092d5c1 Mon Sep 17 00:00:00 2001 From: linzhang Date: Wed, 17 May 2017 12:05:07 +0800 Subject: net: x25: fix one potential use-after-free issue The function x25_init is not properly unregister related resources on error handler.It is will result in kernel oops if x25_init init failed, so add properly unregister call on error handler. Also, i adjust the coding style and make x25_register_sysctl properly return failure. Signed-off-by: linzhang Signed-off-by: David S. Miller --- include/net/x25.h | 4 ++-- net/x25/af_x25.c | 24 ++++++++++++++++-------- net/x25/sysctl_net_x25.c | 5 ++++- 3 files changed, 22 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/net/x25.h b/include/net/x25.h index c383aa4edbf0..6d30a01d281d 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -298,10 +298,10 @@ void x25_check_rbuf(struct sock *); /* sysctl_net_x25.c */ #ifdef CONFIG_SYSCTL -void x25_register_sysctl(void); +int x25_register_sysctl(void); void x25_unregister_sysctl(void); #else -static inline void x25_register_sysctl(void) {}; +static inline int x25_register_sysctl(void) { return 0; }; static inline void x25_unregister_sysctl(void) {}; #endif /* CONFIG_SYSCTL */ diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 8b911c29860e..5a1a98df3499 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -1791,32 +1791,40 @@ void x25_kill_by_neigh(struct x25_neigh *nb) static int __init x25_init(void) { - int rc = proto_register(&x25_proto, 0); + int rc; - if (rc != 0) + rc = proto_register(&x25_proto, 0); + if (rc) goto out; rc = sock_register(&x25_family_ops); - if (rc != 0) + if (rc) goto out_proto; dev_add_pack(&x25_packet_type); rc = register_netdevice_notifier(&x25_dev_notifier); - if (rc != 0) + if (rc) goto out_sock; - pr_info("Linux Version 0.2\n"); + rc = x25_register_sysctl(); + if (rc) + goto out_dev; - x25_register_sysctl(); rc = x25_proc_init(); - if (rc != 0) - goto out_dev; + if (rc) + goto out_sysctl; + + pr_info("Linux Version 0.2\n"); + out: return rc; +out_sysctl: + x25_unregister_sysctl(); out_dev: unregister_netdevice_notifier(&x25_dev_notifier); out_sock: + dev_remove_pack(&x25_packet_type); sock_unregister(AF_X25); out_proto: proto_unregister(&x25_proto); diff --git a/net/x25/sysctl_net_x25.c b/net/x25/sysctl_net_x25.c index a06dfe143c67..ba078c85f0a1 100644 --- a/net/x25/sysctl_net_x25.c +++ b/net/x25/sysctl_net_x25.c @@ -73,9 +73,12 @@ static struct ctl_table x25_table[] = { { }, }; -void __init x25_register_sysctl(void) +int __init x25_register_sysctl(void) { x25_table_header = register_net_sysctl(&init_net, "net/x25", x25_table); + if (!x25_table_header) + return -ENOMEM; + return 0; } void x25_unregister_sysctl(void) -- cgit v1.3-14-g43fede From 667271455f883d23e6418ef3376eb1214da9d066 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 17 May 2017 19:31:39 +0300 Subject: net: make struct dst_entry::dev first member struct dst_entry::dev is used most often. Move it so it can be accessed without imm8 offset on x86_64. add/remove: 0/0 grow/shrink: 9/239 up/down: 52/-413 (-361) function old new delta dst_rcu_free 126 138 +12 fnhe_flush_routes 211 219 +8 rt_set_nexthop 747 754 +7 rt_cache_route 85 91 +6 rt6_release 209 215 +6 dst_release 107 111 +4 dst_destroy_rcu 29 33 +4 dn_dst_check_expire 329 333 +4 dn_insert_route 484 485 +1 xfrm_resolve_and_create_bundle 2991 2990 -1 ... ip_route_me_harder 1163 1157 -6 __ip_append_data.isra 2730 2724 -6 ip6_forward 3052 3045 -7 callforward_do_filter 659 651 -8 dst_gc_task 571 549 -22 Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/net/dst.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index 049af33da3b6..755a0eedffde 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -31,9 +31,9 @@ struct sk_buff; struct dst_entry { + struct net_device *dev; struct rcu_head rcu_head; struct dst_entry *child; - struct net_device *dev; struct dst_ops *ops; unsigned long _metrics; unsigned long expires; -- cgit v1.3-14-g43fede From f0c24ccf491b09de53cee32114c924551218f2bc Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Wed, 17 May 2017 15:46:04 -0400 Subject: net: dsa: include switchdev.h only once DSA drivers and core use switchdev. Include switchdev.h only once, in the dsa.h public header, so that inclusion in DSA drivers or forward declarations of switchdev structures in not necessary anymore. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/b53/b53_common.c | 1 - drivers/net/dsa/bcm_sf2.c | 1 - drivers/net/dsa/dsa_loop.c | 1 - drivers/net/dsa/mt7530.c | 1 - drivers/net/dsa/mv88e6xxx/chip.c | 1 - drivers/net/dsa/qca8k.c | 1 - include/net/dsa.h | 7 +------ net/dsa/slave.c | 1 - 8 files changed, 1 insertion(+), 13 deletions(-) (limited to 'include/net') diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 658a12c888a8..fbc3eb17c7a3 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -29,7 +29,6 @@ #include #include #include -#include #include "b53_regs.h" #include "b53_priv.h" diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 215d41c1e71f..687a8bae5d73 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include "bcm_sf2.h" diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index a19e1781e9bb..6afab16d13dd 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include "dsa_loop.h" diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index b070c167e70f..1bcbe15870ed 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -28,7 +28,6 @@ #include #include #include -#include #include "mt7530.h" diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index d034d8cd7d22..386d878569ed 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -32,7 +32,6 @@ #include #include #include -#include #include "mv88e6xxx.h" #include "global1.h" diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 942b9ac7f92a..149f109dbffb 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include diff --git a/include/net/dsa.h b/include/net/dsa.h index ed767beca9c6..bf6a2abb9b99 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -20,6 +20,7 @@ #include #include #include +#include struct tc_action; struct phy_device; @@ -284,12 +285,6 @@ static inline u8 dsa_upstream_port(struct dsa_switch *ds) return ds->rtable[dst->cpu_dp->ds->index]; } -struct switchdev_trans; -struct switchdev_obj; -struct switchdev_obj_port_fdb; -struct switchdev_obj_port_mdb; -struct switchdev_obj_port_vlan; - #define DSA_NOTIFIER_BRIDGE_JOIN 1 #define DSA_NOTIFIER_BRIDGE_LEAVE 2 diff --git a/net/dsa/slave.c b/net/dsa/slave.c index fb13c5d7d587..91236d602301 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include -- cgit v1.3-14-g43fede From 438ff53739ee523de3755a98ae3a290e69752620 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Wed, 17 May 2017 15:46:05 -0400 Subject: net: dsa: use switchdev_obj_dump_cb_t everywhere Now that the DSA public header includes switchdev.h, use the provided switchdev_obj_dump_cb_t typedef for the object dump callback. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/b53/b53_common.c | 6 +++--- drivers/net/dsa/b53/b53_priv.h | 4 ++-- drivers/net/dsa/dsa_loop.c | 2 +- drivers/net/dsa/mt7530.c | 2 +- drivers/net/dsa/mv88e6xxx/chip.c | 10 +++++----- drivers/net/dsa/qca8k.c | 2 +- include/net/dsa.h | 6 +++--- 7 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include/net') diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index fbc3eb17c7a3..fa099ed41652 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1055,7 +1055,7 @@ EXPORT_SYMBOL(b53_vlan_del); int b53_vlan_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_vlan *vlan, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct b53_device *dev = ds->priv; u16 vid, vid_start = 0, pvid; @@ -1284,7 +1284,7 @@ static void b53_arl_search_rd(struct b53_device *dev, u8 idx, static int b53_fdb_copy(struct net_device *dev, int port, const struct b53_arl_entry *ent, struct switchdev_obj_port_fdb *fdb, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { if (!ent->is_valid) return 0; @@ -1301,7 +1301,7 @@ static int b53_fdb_copy(struct net_device *dev, int port, int b53_fdb_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_fdb *fdb, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct b53_device *priv = ds->priv; struct net_device *dev = ds->ports[port].netdev; diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index a9dc90a01438..155a9c48c317 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -395,7 +395,7 @@ int b53_vlan_del(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); int b53_vlan_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_vlan *vlan, - int (*cb)(struct switchdev_obj *obj)); + switchdev_obj_dump_cb_t *cb); int b53_fdb_prepare(struct dsa_switch *ds, int port, const struct switchdev_obj_port_fdb *fdb, struct switchdev_trans *trans); @@ -406,7 +406,7 @@ int b53_fdb_del(struct dsa_switch *ds, int port, const struct switchdev_obj_port_fdb *fdb); int b53_fdb_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_fdb *fdb, - int (*cb)(struct switchdev_obj *obj)); + switchdev_obj_dump_cb_t *cb); int b53_mirror_add(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror, bool ingress); void b53_mirror_del(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index 6afab16d13dd..5edf07beb9d2 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -187,7 +187,7 @@ static int dsa_loop_port_vlan_del(struct dsa_switch *ds, int port, static int dsa_loop_port_vlan_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_vlan *vlan, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct dsa_loop_priv *ps = ds->priv; struct mii_bus *bus = ps->bus; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 1bcbe15870ed..4d2f45153ede 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -853,7 +853,7 @@ mt7530_port_fdb_del(struct dsa_switch *ds, int port, static int mt7530_port_fdb_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_fdb *fdb, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct mt7530_priv *priv = ds->priv; struct mt7530_fdb _fdb = { 0 }; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 386d878569ed..41de250dbcc3 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1268,7 +1268,7 @@ static int mv88e6xxx_vtu_loadpurge(struct mv88e6xxx_chip *chip, static int mv88e6xxx_port_vlan_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_vlan *vlan, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct mv88e6xxx_chip *chip = ds->priv; struct mv88e6xxx_vtu_entry next = { @@ -1699,7 +1699,7 @@ static int mv88e6xxx_port_fdb_del(struct dsa_switch *ds, int port, static int mv88e6xxx_port_db_dump_fid(struct mv88e6xxx_chip *chip, u16 fid, u16 vid, int port, struct switchdev_obj *obj, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct mv88e6xxx_atu_entry addr; int err; @@ -1754,7 +1754,7 @@ static int mv88e6xxx_port_db_dump_fid(struct mv88e6xxx_chip *chip, static int mv88e6xxx_port_db_dump(struct mv88e6xxx_chip *chip, int port, struct switchdev_obj *obj, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct mv88e6xxx_vtu_entry vlan = { .vid = chip->info->max_vid, @@ -1791,7 +1791,7 @@ static int mv88e6xxx_port_db_dump(struct mv88e6xxx_chip *chip, int port, static int mv88e6xxx_port_fdb_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_fdb *fdb, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct mv88e6xxx_chip *chip = ds->priv; int err; @@ -4037,7 +4037,7 @@ static int mv88e6xxx_port_mdb_del(struct dsa_switch *ds, int port, static int mv88e6xxx_port_mdb_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_mdb *mdb, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct mv88e6xxx_chip *chip = ds->priv; int err; diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 149f109dbffb..0f6a011d8ed1 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -872,7 +872,7 @@ qca8k_port_fdb_del(struct dsa_switch *ds, int port, static int qca8k_port_fdb_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_fdb *fdb, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; struct qca8k_fdb _fdb = { 0 }; diff --git a/include/net/dsa.h b/include/net/dsa.h index bf6a2abb9b99..791fed62fb16 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -404,7 +404,7 @@ struct dsa_switch_ops { const struct switchdev_obj_port_vlan *vlan); int (*port_vlan_dump)(struct dsa_switch *ds, int port, struct switchdev_obj_port_vlan *vlan, - int (*cb)(struct switchdev_obj *obj)); + switchdev_obj_dump_cb_t *cb); /* * Forwarding database @@ -419,7 +419,7 @@ struct dsa_switch_ops { const struct switchdev_obj_port_fdb *fdb); int (*port_fdb_dump)(struct dsa_switch *ds, int port, struct switchdev_obj_port_fdb *fdb, - int (*cb)(struct switchdev_obj *obj)); + switchdev_obj_dump_cb_t *cb); /* * Multicast database @@ -434,7 +434,7 @@ struct dsa_switch_ops { const struct switchdev_obj_port_mdb *mdb); int (*port_mdb_dump)(struct dsa_switch *ds, int port, struct switchdev_obj_port_mdb *mdb, - int (*cb)(struct switchdev_obj *obj)); + switchdev_obj_dump_cb_t *cb); /* * RXNFC -- cgit v1.3-14-g43fede From 6d8422a175ccf2846d9460ed2b6228fe0b12c243 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 21 May 2017 10:12:02 -0600 Subject: net: ipv4: Plumb extack through route add functions Plumb extack argument down to route add functions. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 3 ++- net/ipv4/fib_frontend.c | 16 +++++++++------- net/ipv4/fib_lookup.h | 3 ++- net/ipv4/fib_semantics.c | 22 +++++++++++++--------- net/ipv4/fib_trie.c | 4 ++-- 5 files changed, 28 insertions(+), 20 deletions(-) (limited to 'include/net') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 6692c5758b33..42e8b8f55f7c 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -263,7 +263,8 @@ struct fib_table { int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags); -int fib_table_insert(struct net *, struct fib_table *, struct fib_config *); +int fib_table_insert(struct net *, struct fib_table *, struct fib_config *, + struct netlink_ext_ack *extack); int fib_table_delete(struct net *, struct fib_table *, struct fib_config *); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 83e3ed258467..511edff76c01 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -594,7 +594,8 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg) } else { tb = fib_new_table(net, cfg.fc_table); if (tb) - err = fib_table_insert(net, tb, &cfg); + err = fib_table_insert(net, tb, + &cfg, NULL); else err = -ENOBUFS; } @@ -626,14 +627,15 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { }; static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, - struct nlmsghdr *nlh, struct fib_config *cfg) + struct nlmsghdr *nlh, struct fib_config *cfg, + struct netlink_ext_ack *extack) { struct nlattr *attr; int err, remaining; struct rtmsg *rtm; err = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy, - NULL); + extack); if (err < 0) goto errout; @@ -718,7 +720,7 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib_table *tb; int err; - err = rtm_to_fib_config(net, skb, nlh, &cfg); + err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; @@ -741,7 +743,7 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib_table *tb; int err; - err = rtm_to_fib_config(net, skb, nlh, &cfg); + err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; @@ -751,7 +753,7 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; } - err = fib_table_insert(net, tb, &cfg); + err = fib_table_insert(net, tb, &cfg, extack); errout: return err; } @@ -845,7 +847,7 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad cfg.fc_scope = RT_SCOPE_HOST; if (cmd == RTM_NEWROUTE) - fib_table_insert(net, tb, &cfg); + fib_table_insert(net, tb, &cfg, NULL); else fib_table_delete(net, tb, &cfg); } diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index 9c02920725db..2704e08545da 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -28,7 +28,8 @@ static inline void fib_alias_accessed(struct fib_alias *fa) /* Exported by fib_semantics.c */ void fib_release_info(struct fib_info *); -struct fib_info *fib_create_info(struct fib_config *cfg); +struct fib_info *fib_create_info(struct fib_config *cfg, + struct netlink_ext_ack *extack); int fib_nh_match(struct fib_config *cfg, struct fib_info *fi); int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi, diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index da449ddb8cc1..8587d1b55b53 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -454,7 +454,8 @@ static int fib_detect_death(struct fib_info *fi, int order, #ifdef CONFIG_IP_ROUTE_MULTIPATH -static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining) +static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining, + struct netlink_ext_ack *extack) { int nhs = 0; @@ -468,7 +469,8 @@ static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining) } static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, - int remaining, struct fib_config *cfg) + int remaining, struct fib_config *cfg, + struct netlink_ext_ack *extack) { int ret; @@ -714,7 +716,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) * |-> {local prefix} (terminal node) */ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, - struct fib_nh *nh) + struct fib_nh *nh, struct netlink_ext_ack *extack) { int err = 0; struct net *net; @@ -797,7 +799,6 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, if (nh->nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) return -EINVAL; - rcu_read_lock(); err = -ENODEV; in_dev = inetdev_by_index(net, nh->nh_oif); @@ -980,7 +981,8 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg) return 0; } -struct fib_info *fib_create_info(struct fib_config *cfg) +struct fib_info *fib_create_info(struct fib_config *cfg, + struct netlink_ext_ack *extack) { int err; struct fib_info *fi = NULL; @@ -1000,7 +1002,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) #ifdef CONFIG_IP_ROUTE_MULTIPATH if (cfg->fc_mp) { - nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len); + nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len, extack); if (nhs == 0) goto err_inval; } @@ -1062,7 +1064,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) if (cfg->fc_mp) { #ifdef CONFIG_IP_ROUTE_MULTIPATH - err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg); + err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg, extack); if (err != 0) goto failure; if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif) @@ -1129,7 +1131,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg) struct fib_nh *nh = fi->fib_nh; /* Local address is added. */ - if (nhs != 1 || nh->nh_gw) + if (nhs != 1) + goto err_inval; + if (nh->nh_gw) goto err_inval; nh->nh_scope = RT_SCOPE_NOWHERE; nh->nh_dev = dev_get_by_index(net, fi->fib_nh->nh_oif); @@ -1140,7 +1144,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) int linkdown = 0; change_nexthops(fi) { - err = fib_check_nh(cfg, fi, nexthop_nh); + err = fib_check_nh(cfg, fi, nexthop_nh, extack); if (err != 0) goto failure; if (nexthop_nh->nh_flags & RTNH_F_LINKDOWN) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 51182ff2b441..6d0f6c79d9aa 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1101,7 +1101,7 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp, /* Caller must hold RTNL. */ int fib_table_insert(struct net *net, struct fib_table *tb, - struct fib_config *cfg) + struct fib_config *cfg, struct netlink_ext_ack *extack) { enum fib_event_type event = FIB_EVENT_ENTRY_ADD; struct trie *t = (struct trie *)tb->tb_data; @@ -1125,7 +1125,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, if ((plen < KEYLENGTH) && (key << plen)) return -EINVAL; - fi = fib_create_info(cfg); + fi = fib_create_info(cfg, extack); if (IS_ERR(fi)) { err = PTR_ERR(fi); goto err; -- cgit v1.3-14-g43fede From 333c430167c21b96de81a674fa6cbe84b09475dc Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 21 May 2017 10:12:04 -0600 Subject: net: ipv6: Plumb extack through route add functions Plumb extack argument down to route add functions. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 3 ++- include/net/ip6_route.h | 2 +- net/ipv6/addrconf.c | 4 ++-- net/ipv6/ip6_fib.c | 14 +++++++----- net/ipv6/route.c | 57 +++++++++++++++++++++++++++---------------------- 5 files changed, 46 insertions(+), 34 deletions(-) (limited to 'include/net') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index c979c878df1c..aa50e2e6fa2a 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -277,7 +277,8 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg), void *arg); int fib6_add(struct fib6_node *root, struct rt6_info *rt, - struct nl_info *info, struct mx6_config *mxc); + struct nl_info *info, struct mx6_config *mxc, + struct netlink_ext_ack *extack); int fib6_del(struct rt6_info *rt, struct nl_info *info); void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info, diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index f5e625f53367..f3da9dd2a8db 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -90,7 +90,7 @@ void ip6_route_cleanup(void); int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg); -int ip6_route_add(struct fib6_config *cfg); +int ip6_route_add(struct fib6_config *cfg, struct netlink_ext_ack *extack); int ip6_ins_rt(struct rt6_info *); int ip6_del_rt(struct rt6_info *); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 6a4fb1e629fb..25443fd946a8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2280,7 +2280,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, cfg.fc_flags |= RTF_NONEXTHOP; #endif - ip6_route_add(&cfg); + ip6_route_add(&cfg, NULL); } @@ -2335,7 +2335,7 @@ static void addrconf_add_mroute(struct net_device *dev) ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); - ip6_route_add(&cfg); + ip6_route_add(&cfg, NULL); } static struct inet6_dev *addrconf_add_dev(struct net_device *dev) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index d4bf2c68a545..c1197e167d3e 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -473,7 +473,8 @@ out: static struct fib6_node *fib6_add_1(struct fib6_node *root, struct in6_addr *addr, int plen, int offset, int allow_create, - int replace_required, int sernum) + int replace_required, int sernum, + struct netlink_ext_ack *extack) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; @@ -964,7 +965,8 @@ void fib6_force_start_gc(struct net *net) */ int fib6_add(struct fib6_node *root, struct rt6_info *rt, - struct nl_info *info, struct mx6_config *mxc) + struct nl_info *info, struct mx6_config *mxc, + struct netlink_ext_ack *extack) { struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; @@ -987,7 +989,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), allow_create, - replace_required, sernum); + replace_required, sernum, extack); if (IS_ERR(fn)) { err = PTR_ERR(fn); fn = NULL; @@ -1028,7 +1030,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, sn = fib6_add_1(sfn, &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required, sernum); + allow_create, replace_required, sernum, + extack); if (IS_ERR(sn)) { /* If it is failed, discard just allocated @@ -1047,7 +1050,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required, sernum); + allow_create, replace_required, sernum, + extack); if (IS_ERR(sn)) { err = PTR_ERR(sn); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index dc61b0b5e64e..ca754ec4054a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -938,14 +938,15 @@ EXPORT_SYMBOL(rt6_lookup); */ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info, - struct mx6_config *mxc) + struct mx6_config *mxc, + struct netlink_ext_ack *extack) { int err; struct fib6_table *table; table = rt->rt6i_table; write_lock_bh(&table->tb6_lock); - err = fib6_add(&table->tb6_root, rt, info, mxc); + err = fib6_add(&table->tb6_root, rt, info, mxc, extack); write_unlock_bh(&table->tb6_lock); return err; @@ -956,7 +957,7 @@ int ip6_ins_rt(struct rt6_info *rt) struct nl_info info = { .nl_net = dev_net(rt->dst.dev), }; struct mx6_config mxc = { .mx = NULL, }; - return __ip6_ins_rt(rt, &info, &mxc); + return __ip6_ins_rt(rt, &info, &mxc, NULL); } static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort, @@ -1844,7 +1845,8 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net, return rt; } -static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) +static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct net *net = cfg->fc_nlinfo.nl_net; struct rt6_info *rt = NULL; @@ -2111,13 +2113,14 @@ out: return ERR_PTR(err); } -int ip6_route_add(struct fib6_config *cfg) +int ip6_route_add(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct mx6_config mxc = { .mx = NULL, }; struct rt6_info *rt; int err; - rt = ip6_route_info_create(cfg); + rt = ip6_route_info_create(cfg, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; @@ -2128,7 +2131,7 @@ int ip6_route_add(struct fib6_config *cfg) if (err) goto out; - err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc); + err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc, extack); kfree(mxc.mx); @@ -2222,7 +2225,8 @@ out_put: return err; } -static int ip6_route_del(struct fib6_config *cfg) +static int ip6_route_del(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct fib6_table *table; struct fib6_node *fn; @@ -2483,7 +2487,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net, if (!prefixlen) cfg.fc_flags |= RTF_DEFAULT; - ip6_route_add(&cfg); + ip6_route_add(&cfg, NULL); return rt6_get_route_info(net, prefix, prefixlen, gwaddr, dev); } @@ -2529,7 +2533,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, cfg.fc_gateway = *gwaddr; - if (!ip6_route_add(&cfg)) { + if (!ip6_route_add(&cfg, NULL)) { struct fib6_table *table; table = fib6_get_table(dev_net(dev), cfg.fc_table); @@ -2622,10 +2626,10 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) rtnl_lock(); switch (cmd) { case SIOCADDRT: - err = ip6_route_add(&cfg); + err = ip6_route_add(&cfg, NULL); break; case SIOCDELRT: - err = ip6_route_del(&cfg); + err = ip6_route_del(&cfg, NULL); break; default: err = -EINVAL; @@ -2903,7 +2907,8 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, - struct fib6_config *cfg) + struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; @@ -3097,7 +3102,8 @@ static void ip6_route_mpath_notify(struct rt6_info *rt, inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); } -static int ip6_route_multipath_add(struct fib6_config *cfg) +static int ip6_route_multipath_add(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct rt6_info *rt_notif = NULL, *rt_last = NULL; struct nl_info *info = &cfg->fc_nlinfo; @@ -3145,7 +3151,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg) r_cfg.fc_encap_type = nla_get_u16(nla); } - rt = ip6_route_info_create(&r_cfg); + rt = ip6_route_info_create(&r_cfg, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; @@ -3170,7 +3176,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg) err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, next) { rt_last = nh->rt6_info; - err = __ip6_ins_rt(nh->rt6_info, info, &nh->mxc); + err = __ip6_ins_rt(nh->rt6_info, info, &nh->mxc, extack); /* save reference to first route for notification */ if (!rt_notif && !err) rt_notif = nh->rt6_info; @@ -3212,7 +3218,7 @@ add_errout: list_for_each_entry(nh, &rt6_nh_list, next) { if (err_nh == nh) break; - ip6_route_del(&nh->r_cfg); + ip6_route_del(&nh->r_cfg, extack); } cleanup: @@ -3227,7 +3233,8 @@ cleanup: return err; } -static int ip6_route_multipath_del(struct fib6_config *cfg) +static int ip6_route_multipath_del(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct fib6_config r_cfg; struct rtnexthop *rtnh; @@ -3254,7 +3261,7 @@ static int ip6_route_multipath_del(struct fib6_config *cfg) r_cfg.fc_flags |= RTF_GATEWAY; } } - err = ip6_route_del(&r_cfg); + err = ip6_route_del(&r_cfg, extack); if (err) last_err = err; @@ -3270,15 +3277,15 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib6_config cfg; int err; - err = rtm_to_fib6_config(skb, nlh, &cfg); + err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_mp) - return ip6_route_multipath_del(&cfg); + return ip6_route_multipath_del(&cfg, extack); else { cfg.fc_delete_all_nh = 1; - return ip6_route_del(&cfg); + return ip6_route_del(&cfg, extack); } } @@ -3288,14 +3295,14 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib6_config cfg; int err; - err = rtm_to_fib6_config(skb, nlh, &cfg); + err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_mp) - return ip6_route_multipath_add(&cfg); + return ip6_route_multipath_add(&cfg, extack); else - return ip6_route_add(&cfg); + return ip6_route_add(&cfg, extack); } static size_t rt6_nlmsg_size(struct rt6_info *rt) -- cgit v1.3-14-g43fede From 52c96f9d7003c74c7fbec7438c0ed78df0cc1c79 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 19 May 2017 17:00:51 -0400 Subject: net: dsa: move notifier info to private header The DSA notifier events and info structure definitions are not meant for DSA drivers and users, but only used internally by the DSA core files. Move them from the public net/dsa.h file to the private dsa_priv.h file. Also use this opportunity to turn the events into an anonymous enum, because we don't care about the values, and this will prevent future conflicts when adding (and sorting) new events. Signed-off-by: Vivien Didelot Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 10 ---------- net/dsa/dsa_priv.h | 12 ++++++++++++ 2 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index 791fed62fb16..c0e567c0c824 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -285,16 +285,6 @@ static inline u8 dsa_upstream_port(struct dsa_switch *ds) return ds->rtable[dst->cpu_dp->ds->index]; } -#define DSA_NOTIFIER_BRIDGE_JOIN 1 -#define DSA_NOTIFIER_BRIDGE_LEAVE 2 - -/* DSA_NOTIFIER_BRIDGE_* */ -struct dsa_notifier_bridge_info { - struct net_device *br; - int sw_index; - int port; -}; - struct dsa_switch_ops { /* * Legacy probing. diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 16021a891095..c19241eb094b 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -16,6 +16,18 @@ #include #include +enum { + DSA_NOTIFIER_BRIDGE_JOIN, + DSA_NOTIFIER_BRIDGE_LEAVE, +}; + +/* DSA_NOTIFIER_BRIDGE_* */ +struct dsa_notifier_bridge_info { + struct net_device *br; + int sw_index; + int port; +}; + struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev, -- cgit v1.3-14-g43fede From 3aa4266405a6c2e03eb0ff12d7c573d3d903da4c Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Wed, 10 May 2017 13:48:41 +0300 Subject: net/sched: act_csum: Add accessors for offloading drivers Add the accessors for realizing if this is a csum action, and for which fields checksum is needed. Signed-off-by: Or Gerlitz Reviewed-by: Paul Blakey Signed-off-by: Saeed Mahameed --- include/net/tc_act/tc_csum.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/net') diff --git a/include/net/tc_act/tc_csum.h b/include/net/tc_act/tc_csum.h index f31fb6331a53..3248beaf16b0 100644 --- a/include/net/tc_act/tc_csum.h +++ b/include/net/tc_act/tc_csum.h @@ -3,6 +3,7 @@ #include #include +#include struct tcf_csum { struct tc_action common; @@ -11,4 +12,18 @@ struct tcf_csum { }; #define to_tcf_csum(a) ((struct tcf_csum *)a) +static inline bool is_tcf_csum(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + if (a->ops && a->ops->type == TCA_ACT_CSUM) + return true; +#endif + return false; +} + +static inline u32 tcf_csum_update_flags(const struct tc_action *a) +{ + return to_tcf_csum(a)->update_flags; +} + #endif /* __NET_TC_CSUM_H */ -- cgit v1.3-14-g43fede From 4c0ebd6fed66388584abb27d7b0f188cc1ec01fe Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 23 May 2017 00:20:26 +0300 Subject: net: make struct inet_frags::qsize unsigned This field is sizeof of corresponding kmem_cache so it can't be negative. Prepare for 32-bit kmem_cache_create(). Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/net/inet_frag.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 5894730ec82a..975779d0e7b0 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -92,7 +92,7 @@ struct inet_frags { */ u32 rnd; seqlock_t rnd_seqlock; - int qsize; + unsigned int qsize; unsigned int (*hashfn)(const struct inet_frag_queue *); bool (*match)(const struct inet_frag_queue *q, -- cgit v1.3-14-g43fede From 417ccf6b5bc3f1a390505d5ef65ec17f10e8b29a Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 23 May 2017 00:21:39 +0300 Subject: net: make struct request_sock_ops::obj_size unsigned This field is sizeof of corresponding kmem_cache so it can't be negative. Space will be saved after 32-bit kmem_cache_create() patch. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/net/request_sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index a12a5d25b27e..53ced67c4ae9 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -29,7 +29,7 @@ struct proto; struct request_sock_ops { int family; - int obj_size; + unsigned int obj_size; struct kmem_cache *slab; char *slab_name; int (*rtx_syn_ack)(const struct sock *sk, -- cgit v1.3-14-g43fede From ac4bb5de27010e41f027c635dedca1393e7ebf55 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 23 May 2017 18:40:44 +0200 Subject: net: flow_dissector: add support for dissection of tcp flags Add support for dissection of tcp flags. Uses similar function call to tcp dissection function as arp, mpls and others. Signed-off-by: Jiri Pirko Acked-by: Or Gerlitz Signed-off-by: David S. Miller --- include/net/flow_dissector.h | 9 +++++++++ net/core/flow_dissector.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) (limited to 'include/net') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 8d21d448daa9..efe34eec61dc 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -157,6 +157,14 @@ struct flow_dissector_key_eth_addrs { unsigned char src[ETH_ALEN]; }; +/** + * struct flow_dissector_key_tcp: + * @flags: flags + */ +struct flow_dissector_key_tcp { + __be16 flags; +}; + enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */ @@ -177,6 +185,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_ENC_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_ENC_PORTS, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_MPLS, /* struct flow_dissector_key_mpls */ + FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */ FLOW_DISSECTOR_KEY_MAX, }; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 28d94bce4df8..5a45943081f5 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -342,6 +343,30 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, return FLOW_DISSECT_RET_OUT_PROTO_AGAIN; } +static void +__skb_flow_dissect_tcp(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, int thoff, int hlen) +{ + struct flow_dissector_key_tcp *key_tcp; + struct tcphdr *th, _th; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_TCP)) + return; + + th = __skb_header_pointer(skb, thoff, sizeof(_th), data, hlen, &_th); + if (!th) + return; + + if (unlikely(__tcp_hdrlen(th) < sizeof(_th))) + return; + + key_tcp = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_TCP, + target_container); + key_tcp->flags = (*(__be16 *) &tcp_flag_word(th) & htons(0x0FFF)); +} + /** * __skb_flow_dissect - extract the flow_keys struct and return it * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified @@ -683,6 +708,10 @@ ip_proto_again: case IPPROTO_MPLS: proto = htons(ETH_P_MPLS_UC); goto mpls; + case IPPROTO_TCP: + __skb_flow_dissect_tcp(skb, flow_dissector, target_container, + data, nhoff, hlen); + break; default: break; } -- cgit v1.3-14-g43fede From 367a8ce896f14018cc2c6cf2681aa440fff274f4 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Tue, 23 May 2017 09:42:37 -0700 Subject: net_sched: only create filter chains for new filters/actions tcf_chain_get() always creates a new filter chain if not found in existing ones. This is totally unnecessary when we get or delete filters, new chain should be only created for new filters (or new actions). Fixes: 5bc1701881e3 ("net: sched: introduce multichain support for filters") Cc: Jamal Hadi Salim Cc: Jiri Pirko Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 3 ++- net/sched/act_api.c | 2 +- net/sched/cls_api.c | 13 +++++++++---- 3 files changed, 12 insertions(+), 6 deletions(-) (limited to 'include/net') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 2c213a69c196..f7762295b7b8 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -18,7 +18,8 @@ int register_tcf_proto_ops(struct tcf_proto_ops *ops); int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); #ifdef CONFIG_NET_CLS -struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index); +struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, + bool create); void tcf_chain_put(struct tcf_chain *chain); int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 0ecf2a858767..aed6cf2e9fd8 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -34,7 +34,7 @@ static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp) if (!tp) return -EINVAL; - a->goto_chain = tcf_chain_get(tp->chain->block, chain_index); + a->goto_chain = tcf_chain_get(tp->chain->block, chain_index, true); if (!a->goto_chain) return -ENOMEM; return 0; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 89fbb35bc666..39da0c5801c9 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -220,7 +220,8 @@ static void tcf_chain_destroy(struct tcf_chain *chain) kfree(chain); } -struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index) +struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, + bool create) { struct tcf_chain *chain; @@ -230,7 +231,10 @@ struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index) return chain; } } - return tcf_chain_create(block, chain_index); + if (create) + return tcf_chain_create(block, chain_index); + else + return NULL; } EXPORT_SYMBOL(tcf_chain_get); @@ -511,9 +515,10 @@ replay: err = -EINVAL; goto errout; } - chain = tcf_chain_get(block, chain_index); + chain = tcf_chain_get(block, chain_index, + n->nlmsg_type == RTM_NEWTFILTER); if (!chain) { - err = -ENOMEM; + err = n->nlmsg_type == RTM_NEWTFILTER ? -ENOMEM : -EINVAL; goto errout; } -- cgit v1.3-14-g43fede From 3abd1ade6765e8edcccad6a9e1039cc709e65dde Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 25 May 2017 10:42:33 -0700 Subject: net: ipv4: refactor __ip_route_output_key_hash A later patch wants access to the fib result on an output route lookup with the rcu lock held. Refactor __ip_route_output_key_hash, pushing the logic between rcu_read_lock ... rcu_read_unlock into a new helper with the fib_result as an input arg. To keep the name length under control remove the leading underscores from the name and add _rcu to the name of the new helper indicating it is called with the rcu read lock held. Signed-off-by: David Ahern Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/net/route.h | 9 ++++++--- net/ipv4/icmp.c | 2 +- net/ipv4/route.c | 53 +++++++++++++++++++++++++++++++---------------------- 3 files changed, 38 insertions(+), 26 deletions(-) (limited to 'include/net') diff --git a/include/net/route.h b/include/net/route.h index 2cc0e14c6359..89e4028cd063 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -113,13 +113,16 @@ struct in_device; int ip_rt_init(void); void rt_cache_flush(struct net *net); void rt_flush_dev(struct net_device *dev); -struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *flp, - const struct sk_buff *skb); +struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *flp, + const struct sk_buff *skb); +struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp, + struct fib_result *res, + const struct sk_buff *skb); static inline struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp) { - return __ip_route_output_key_hash(net, flp, NULL); + return ip_route_output_key_hash(net, flp, NULL); } struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp, diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 43318b5f5647..5610971bf859 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -489,7 +489,7 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); - rt = __ip_route_output_key_hash(net, fl4, skb_in); + rt = ip_route_output_key_hash(net, fl4, skb_in); if (IS_ERR(rt)) return rt; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 655d9eebe43e..c9b55cb0e316 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2246,29 +2246,40 @@ add: * Major route resolver routine. */ -struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, - const struct sk_buff *skb) +struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, + const struct sk_buff *skb) { - struct net_device *dev_out = NULL; __u8 tos = RT_FL_TOS(fl4); - unsigned int flags = 0; struct fib_result res; struct rtable *rth; - int orig_oif; - int err = -ENETUNREACH; res.tclassid = 0; res.fi = NULL; res.table = NULL; - orig_oif = fl4->flowi4_oif; - fl4->flowi4_iif = LOOPBACK_IFINDEX; fl4->flowi4_tos = tos & IPTOS_RT_MASK; fl4->flowi4_scope = ((tos & RTO_ONLINK) ? RT_SCOPE_LINK : RT_SCOPE_UNIVERSE); rcu_read_lock(); + rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb); + rcu_read_unlock(); + + return rth; +} +EXPORT_SYMBOL_GPL(ip_route_output_key_hash); + +struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, + struct fib_result *res, + const struct sk_buff *skb) +{ + struct net_device *dev_out = NULL; + int orig_oif = fl4->flowi4_oif; + unsigned int flags = 0; + struct rtable *rth; + int err = -ENETUNREACH; + if (fl4->saddr) { rth = ERR_PTR(-EINVAL); if (ipv4_is_multicast(fl4->saddr) || @@ -2354,15 +2365,15 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK); dev_out = net->loopback_dev; fl4->flowi4_oif = LOOPBACK_IFINDEX; - res.type = RTN_LOCAL; + res->type = RTN_LOCAL; flags |= RTCF_LOCAL; goto make_route; } - err = fib_lookup(net, fl4, &res, 0); + err = fib_lookup(net, fl4, res, 0); if (err) { - res.fi = NULL; - res.table = NULL; + res->fi = NULL; + res->table = NULL; if (fl4->flowi4_oif && (ipv4_is_multicast(fl4->daddr) || !netif_index_is_l3_master(net, fl4->flowi4_oif))) { @@ -2387,43 +2398,41 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, if (fl4->saddr == 0) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); - res.type = RTN_UNICAST; + res->type = RTN_UNICAST; goto make_route; } rth = ERR_PTR(err); goto out; } - if (res.type == RTN_LOCAL) { + if (res->type == RTN_LOCAL) { if (!fl4->saddr) { - if (res.fi->fib_prefsrc) - fl4->saddr = res.fi->fib_prefsrc; + if (res->fi->fib_prefsrc) + fl4->saddr = res->fi->fib_prefsrc; else fl4->saddr = fl4->daddr; } /* L3 master device is the loopback for that domain */ - dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? : + dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) ? : net->loopback_dev; fl4->flowi4_oif = dev_out->ifindex; flags |= RTCF_LOCAL; goto make_route; } - fib_select_path(net, &res, fl4, skb); + fib_select_path(net, res, fl4, skb); - dev_out = FIB_RES_DEV(res); + dev_out = FIB_RES_DEV(*res); fl4->flowi4_oif = dev_out->ifindex; make_route: - rth = __mkroute_output(&res, fl4, orig_oif, dev_out, flags); + rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags); out: - rcu_read_unlock(); return rth; } -EXPORT_SYMBOL_GPL(__ip_route_output_key_hash); static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie) { -- cgit v1.3-14-g43fede From 5510cdf7be042a1943222e19912f13a396c0b914 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 25 May 2017 10:42:34 -0700 Subject: net: ipv4: refactor ip_route_input_noref A later patch wants access to the fib result on an input route lookup with the rcu lock held. Refactor ip_route_input_noref pushing the logic between rcu_read_lock ... rcu_read_unlock into a new helper that takes the fib_result as an input arg. Signed-off-by: David Ahern Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/net/route.h | 3 +++ net/ipv4/route.c | 66 ++++++++++++++++++++++++++++++----------------------- 2 files changed, 40 insertions(+), 29 deletions(-) (limited to 'include/net') diff --git a/include/net/route.h b/include/net/route.h index 89e4028cd063..08e689f23365 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -178,6 +178,9 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4 int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin); +int ip_route_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src, + u8 tos, struct net_device *devin, + struct fib_result *res); static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index c9b55cb0e316..1dc8fd1e60a9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1852,9 +1852,9 @@ static int ip_mkroute_input(struct sk_buff *skb, */ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev) + u8 tos, struct net_device *dev, + struct fib_result *res) { - struct fib_result res; struct in_device *in_dev = __in_dev_get_rcu(dev); struct ip_tunnel_info *tun_info; struct flowi4 fl4; @@ -1884,8 +1884,8 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; - res.fi = NULL; - res.table = NULL; + res->fi = NULL; + res->table = NULL; if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0)) goto brd_input; @@ -1921,17 +1921,17 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); - err = fib_lookup(net, &fl4, &res, 0); + err = fib_lookup(net, &fl4, res, 0); if (err != 0) { if (!IN_DEV_FORWARD(in_dev)) err = -EHOSTUNREACH; goto no_route; } - if (res.type == RTN_BROADCAST) + if (res->type == RTN_BROADCAST) goto brd_input; - if (res.type == RTN_LOCAL) { + if (res->type == RTN_LOCAL) { err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &itag); if (err < 0) @@ -1943,10 +1943,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, err = -EHOSTUNREACH; goto no_route; } - if (res.type != RTN_UNICAST) + if (res->type != RTN_UNICAST) goto martian_destination; - err = ip_mkroute_input(skb, &res, in_dev, daddr, saddr, tos); + err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos); out: return err; brd_input: @@ -1960,14 +1960,14 @@ brd_input: goto martian_source; } flags |= RTCF_BROADCAST; - res.type = RTN_BROADCAST; + res->type = RTN_BROADCAST; RT_CACHE_STAT_INC(in_brd); local_input: do_cache = false; - if (res.fi) { + if (res->fi) { if (!itag) { - rth = rcu_dereference(FIB_RES_NH(res).nh_rth_input); + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); err = 0; @@ -1978,7 +1978,7 @@ local_input: } rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev, - flags | RTCF_LOCAL, res.type, + flags | RTCF_LOCAL, res->type, IN_DEV_CONF_GET(in_dev, NOPOLICY), false, do_cache); if (!rth) goto e_nobufs; @@ -1988,18 +1988,18 @@ local_input: rth->dst.tclassid = itag; #endif rth->rt_is_input = 1; - if (res.table) - rth->rt_table_id = res.table->tb_id; + if (res->table) + rth->rt_table_id = res->table->tb_id; RT_CACHE_STAT_INC(in_slow_tot); - if (res.type == RTN_UNREACHABLE) { + if (res->type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL; } if (do_cache) { - struct fib_nh *nh = &FIB_RES_NH(res); + struct fib_nh *nh = &FIB_RES_NH(*res); rth->dst.lwtstate = lwtstate_get(nh->nh_lwtstate); if (lwtunnel_input_redirect(rth->dst.lwtstate)) { @@ -2019,9 +2019,9 @@ local_input: no_route: RT_CACHE_STAT_INC(in_no_route); - res.type = RTN_UNREACHABLE; - res.fi = NULL; - res.table = NULL; + res->type = RTN_UNREACHABLE; + res->fi = NULL; + res->table = NULL; goto local_input; /* @@ -2051,11 +2051,22 @@ martian_source: int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev) { - int res; + struct fib_result res; + int err; tos &= IPTOS_RT_MASK; rcu_read_lock(); + err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res); + rcu_read_unlock(); + return err; +} +EXPORT_SYMBOL(ip_route_input_noref); + +/* called with rcu_read_lock held */ +int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, struct fib_result *res) +{ /* Multicast recognition logic is moved from route cache to here. The problem was that too many Ethernet cards have broken/missing hardware multicast filters :-( As result the host on multicasting @@ -2070,6 +2081,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (ipv4_is_multicast(daddr)) { struct in_device *in_dev = __in_dev_get_rcu(dev); int our = 0; + int err = -EINVAL; if (in_dev) our = ip_check_mc_rcu(in_dev, daddr, saddr, @@ -2085,7 +2097,6 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, ip_hdr(skb)->protocol); } - res = -EINVAL; if (our #ifdef CONFIG_IP_MROUTE || @@ -2093,17 +2104,14 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, IN_DEV_MFORWARD(in_dev)) #endif ) { - res = ip_route_input_mc(skb, daddr, saddr, + err = ip_route_input_mc(skb, daddr, saddr, tos, dev, our); } - rcu_read_unlock(); - return res; + return err; } - res = ip_route_input_slow(skb, daddr, saddr, tos, dev); - rcu_read_unlock(); - return res; + + return ip_route_input_slow(skb, daddr, saddr, tos, dev, res); } -EXPORT_SYMBOL(ip_route_input_noref); /* called with rcu_read_lock() */ static struct rtable *__mkroute_output(const struct fib_result *res, -- cgit v1.3-14-g43fede From 6ffd903415320d68a528865296e4740da350785e Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 25 May 2017 10:42:37 -0700 Subject: net: ipv4: Save trie prefix to fib lookup result Prefix is needed for returning matching route spec on get route request. Signed-off-by: David Ahern Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/net/ip_fib.h | 1 + net/ipv4/fib_trie.c | 1 + 2 files changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 42e8b8f55f7c..25f5c516afd1 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -136,6 +136,7 @@ struct fib_rule; struct fib_table; struct fib_result { + __be32 prefix; unsigned char prefixlen; unsigned char nh_sel; unsigned char type; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 6d0f6c79d9aa..6e9df7d9bcc2 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1452,6 +1452,7 @@ found: if (!(fib_flags & FIB_LOOKUP_NOREF)) atomic_inc(&fi->fib_clntref); + res->prefix = htonl(n->key); res->prefixlen = KEYLENGTH - fa->fa_slen; res->nh_sel = nhsel; res->type = fa->fa_type; -- cgit v1.3-14-g43fede From 3fb07daff8e99243366a081e5129560734de4ada Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 25 May 2017 14:27:35 -0700 Subject: ipv4: add reference counting to metrics Andrey Konovalov reported crashes in ipv4_mtu() I could reproduce the issue with KASAN kernels, between 10.246.7.151 and 10.246.7.152 : 1) 20 concurrent netperf -t TCP_RR -H 10.246.7.152 -l 1000 & 2) At the same time run following loop : while : do ip ro add 10.246.7.152 dev eth0 src 10.246.7.151 mtu 1500 ip ro del 10.246.7.152 dev eth0 src 10.246.7.151 mtu 1500 done Cong Wang attempted to add back rt->fi in commit 82486aa6f1b9 ("ipv4: restore rt->fi for reference counting") but this proved to add some issues that were complex to solve. Instead, I suggested to add a refcount to the metrics themselves, being a standalone object (in particular, no reference to other objects) I tried to make this patch as small as possible to ease its backport, instead of being super clean. Note that we believe that only ipv4 dst need to take care of the metric refcount. But if this is wrong, this patch adds the basic infrastructure to extend this to other families. Many thanks to Julian Anastasov for reviewing this patch, and Cong Wang for his efforts on this problem. Fixes: 2860583fe840 ("ipv4: Kill rt->fi") Signed-off-by: Eric Dumazet Reported-by: Andrey Konovalov Reviewed-by: Julian Anastasov Acked-by: Cong Wang Signed-off-by: David S. Miller --- include/net/dst.h | 8 +++++++- include/net/ip_fib.h | 10 +++++----- net/core/dst.c | 23 ++++++++++++++--------- net/ipv4/fib_semantics.c | 17 ++++++++++------- net/ipv4/route.c | 10 +++++++++- 5 files changed, 45 insertions(+), 23 deletions(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index 049af33da3b6..cfc043784166 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -107,10 +107,16 @@ struct dst_entry { }; }; +struct dst_metrics { + u32 metrics[RTAX_MAX]; + atomic_t refcnt; +}; +extern const struct dst_metrics dst_default_metrics; + u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); -extern const u32 dst_default_metrics[]; #define DST_METRICS_READ_ONLY 0x1UL +#define DST_METRICS_REFCOUNTED 0x2UL #define DST_METRICS_FLAGS 0x3UL #define __DST_METRICS_PTR(Y) \ ((u32 *)((Y) & ~DST_METRICS_FLAGS)) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 6692c5758b33..f7f6aa789c61 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -114,11 +114,11 @@ struct fib_info { __be32 fib_prefsrc; u32 fib_tb_id; u32 fib_priority; - u32 *fib_metrics; -#define fib_mtu fib_metrics[RTAX_MTU-1] -#define fib_window fib_metrics[RTAX_WINDOW-1] -#define fib_rtt fib_metrics[RTAX_RTT-1] -#define fib_advmss fib_metrics[RTAX_ADVMSS-1] + struct dst_metrics *fib_metrics; +#define fib_mtu fib_metrics->metrics[RTAX_MTU-1] +#define fib_window fib_metrics->metrics[RTAX_WINDOW-1] +#define fib_rtt fib_metrics->metrics[RTAX_RTT-1] +#define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1] int fib_nhs; #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_weight; diff --git a/net/core/dst.c b/net/core/dst.c index 960e503b5a52..6192f11beec9 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -151,13 +151,13 @@ int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(dst_discard_out); -const u32 dst_default_metrics[RTAX_MAX + 1] = { +const struct dst_metrics dst_default_metrics = { /* This initializer is needed to force linker to place this variable * into const section. Otherwise it might end into bss section. * We really want to avoid false sharing on this variable, and catch * any writes on it. */ - [RTAX_MAX] = 0xdeadbeef, + .refcnt = ATOMIC_INIT(1), }; void dst_init(struct dst_entry *dst, struct dst_ops *ops, @@ -169,7 +169,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops, if (dev) dev_hold(dev); dst->ops = ops; - dst_init_metrics(dst, dst_default_metrics, true); + dst_init_metrics(dst, dst_default_metrics.metrics, true); dst->expires = 0UL; dst->path = dst; dst->from = NULL; @@ -314,25 +314,30 @@ EXPORT_SYMBOL(dst_release); u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old) { - u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC); + struct dst_metrics *p = kmalloc(sizeof(*p), GFP_ATOMIC); if (p) { - u32 *old_p = __DST_METRICS_PTR(old); + struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old); unsigned long prev, new; - memcpy(p, old_p, sizeof(u32) * RTAX_MAX); + atomic_set(&p->refcnt, 1); + memcpy(p->metrics, old_p->metrics, sizeof(p->metrics)); new = (unsigned long) p; prev = cmpxchg(&dst->_metrics, old, new); if (prev != old) { kfree(p); - p = __DST_METRICS_PTR(prev); + p = (struct dst_metrics *)__DST_METRICS_PTR(prev); if (prev & DST_METRICS_READ_ONLY) p = NULL; + } else if (prev & DST_METRICS_REFCOUNTED) { + if (atomic_dec_and_test(&old_p->refcnt)) + kfree(old_p); } } - return p; + BUILD_BUG_ON(offsetof(struct dst_metrics, metrics) != 0); + return (u32 *)p; } EXPORT_SYMBOL(dst_cow_metrics_generic); @@ -341,7 +346,7 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old) { unsigned long prev, new; - new = ((unsigned long) dst_default_metrics) | DST_METRICS_READ_ONLY; + new = ((unsigned long) &dst_default_metrics) | DST_METRICS_READ_ONLY; prev = cmpxchg(&dst->_metrics, old, new); if (prev == old) kfree(__DST_METRICS_PTR(old)); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index da449ddb8cc1..ad9ad4aab5da 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -203,6 +203,7 @@ static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp) static void free_fib_info_rcu(struct rcu_head *head) { struct fib_info *fi = container_of(head, struct fib_info, rcu); + struct dst_metrics *m; change_nexthops(fi) { if (nexthop_nh->nh_dev) @@ -213,8 +214,9 @@ static void free_fib_info_rcu(struct rcu_head *head) rt_fibinfo_free(&nexthop_nh->nh_rth_input); } endfor_nexthops(fi); - if (fi->fib_metrics != (u32 *) dst_default_metrics) - kfree(fi->fib_metrics); + m = fi->fib_metrics; + if (m != &dst_default_metrics && atomic_dec_and_test(&m->refcnt)) + kfree(m); kfree(fi); } @@ -971,11 +973,11 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg) val = 255; if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) return -EINVAL; - fi->fib_metrics[type - 1] = val; + fi->fib_metrics->metrics[type - 1] = val; } if (ecn_ca) - fi->fib_metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA; + fi->fib_metrics->metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA; return 0; } @@ -1033,11 +1035,12 @@ struct fib_info *fib_create_info(struct fib_config *cfg) goto failure; fib_info_cnt++; if (cfg->fc_mx) { - fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); + fi->fib_metrics = kzalloc(sizeof(*fi->fib_metrics), GFP_KERNEL); if (!fi->fib_metrics) goto failure; + atomic_set(&fi->fib_metrics->refcnt, 1); } else - fi->fib_metrics = (u32 *) dst_default_metrics; + fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics; fi->fib_net = net; fi->fib_protocol = cfg->fc_protocol; @@ -1238,7 +1241,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, if (fi->fib_priority && nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority)) goto nla_put_failure; - if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0) + if (rtnetlink_put_metrics(skb, fi->fib_metrics->metrics) < 0) goto nla_put_failure; if (fi->fib_prefsrc && diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 655d9eebe43e..6883b3d4ba8f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1385,8 +1385,12 @@ static void rt_add_uncached_list(struct rtable *rt) static void ipv4_dst_destroy(struct dst_entry *dst) { + struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); struct rtable *rt = (struct rtable *) dst; + if (p != &dst_default_metrics && atomic_dec_and_test(&p->refcnt)) + kfree(p); + if (!list_empty(&rt->rt_uncached)) { struct uncached_list *ul = rt->rt_uncached_list; @@ -1438,7 +1442,11 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, rt->rt_gateway = nh->nh_gw; rt->rt_uses_gateway = 1; } - dst_init_metrics(&rt->dst, fi->fib_metrics, true); + dst_init_metrics(&rt->dst, fi->fib_metrics->metrics, true); + if (fi->fib_metrics != &dst_default_metrics) { + rt->dst._metrics |= DST_METRICS_REFCOUNTED; + atomic_inc(&fi->fib_metrics->refcnt); + } #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; #endif -- cgit v1.3-14-g43fede From 7a7e96e09d463c7c3d51a51c539ae4352085ed18 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Sat, 27 May 2017 10:14:35 -0400 Subject: bonding: Prevent duplicate userspace notification Whenever a user changes bonding options, a NETDEV_CHANGEINFODATA notificatin is generated which results in a rtnelink message to be sent. While runnig 'ip monitor', we can actually see 2 messages, one a result of the event, and the other a result of state change that is generated bo netdev_state_change(). However, this is not always the case. If bonding changes were done via sysfs or ifenslave (old ioctl interface), then only 1 message is seen. This patch removes duplicate messages in the case of using netlink to configure bonding. It introduceds a separte function that triggers a netdev event and uses that function in the syfs and ioctl cases. This was discovered while auditing all the different envents and continues the effort of cleaning up duplicated netlink messages. CC: David Ahern CC: Jiri Pirko Signed-off-by: Vladislav Yasevich Acked-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 3 ++- drivers/net/bonding/bond_options.c | 27 +++++++++++++++++++++++++-- include/net/bond_options.h | 2 ++ 3 files changed, 29 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 2359478b977f..d4484d1a8164 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3488,7 +3488,8 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd case BOND_CHANGE_ACTIVE_OLD: case SIOCBONDCHANGEACTIVE: bond_opt_initstr(&newval, slave_dev->name); - res = __bond_opt_set(bond, BOND_OPT_ACTIVE_SLAVE, &newval); + res = __bond_opt_set_notify(bond, BOND_OPT_ACTIVE_SLAVE, + &newval); break; default: res = -EOPNOTSUPP; diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 1bcbb8913e17..8ca683396fcc 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -673,7 +673,30 @@ int __bond_opt_set(struct bonding *bond, out: if (ret) bond_opt_error_interpret(bond, opt, ret, val); - else if (bond->dev->reg_state == NETREG_REGISTERED) + + return ret; +} +/** + * __bond_opt_set_notify - set a bonding option + * @bond: target bond device + * @option: option to set + * @val: value to set it to + * + * This function is used to change the bond's option value and trigger + * a notification to user sapce. It can be used for both enabling/changing + * an option and for disabling it. RTNL lock must be obtained before calling + * this function. + */ +int __bond_opt_set_notify(struct bonding *bond, + unsigned int option, struct bond_opt_value *val) +{ + int ret = -ENOENT; + + ASSERT_RTNL(); + + ret = __bond_opt_set(bond, option, val); + + if (!ret && (bond->dev->reg_state == NETREG_REGISTERED)) call_netdevice_notifiers(NETDEV_CHANGEINFODATA, bond->dev); return ret; @@ -696,7 +719,7 @@ int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf) if (!rtnl_trylock()) return restart_syscall(); bond_opt_initstr(&optval, buf); - ret = __bond_opt_set(bond, option, &optval); + ret = __bond_opt_set_notify(bond, option, &optval); rtnl_unlock(); return ret; diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 1797235cd590..d79d28f5318c 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -104,6 +104,8 @@ struct bond_option { int __bond_opt_set(struct bonding *bond, unsigned int option, struct bond_opt_value *val); +int __bond_opt_set_notify(struct bonding *bond, unsigned int option, + struct bond_opt_value *val); int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf); const struct bond_opt_value *bond_opt_parse(const struct bond_option *opt, -- cgit v1.3-14-g43fede From 78055998954b7a3e6c31eb24d1d26f0b63a7ec0d Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sat, 27 May 2017 16:19:26 -0600 Subject: net: ipv4: Add extack message for invalid prefix or length Add extack error message for invalid prefix length and invalid prefix. Example of the latter is a route spec containing 172.16.100.1/24, where the /24 mask means the lower 8-bits should be 0. Amazing how easy that one is to overlook when an EINVAL is returned. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 3 ++- net/ipv4/fib_frontend.c | 7 ++++--- net/ipv4/fib_trie.c | 17 +++++++++++------ 3 files changed, 17 insertions(+), 10 deletions(-) (limited to 'include/net') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index dcbfd5dfd25e..3dbfd5e6a347 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -266,7 +266,8 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags); int fib_table_insert(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); -int fib_table_delete(struct net *, struct fib_table *, struct fib_config *); +int fib_table_delete(struct net *, struct fib_table *, struct fib_config *, + struct netlink_ext_ack *extack); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); int fib_table_flush(struct net *net, struct fib_table *table); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 14d2f7bd7c76..715b7967d8ea 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -588,7 +588,8 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (cmd == SIOCDELRT) { tb = fib_get_table(net, cfg.fc_table); if (tb) - err = fib_table_delete(net, tb, &cfg); + err = fib_table_delete(net, tb, &cfg, + NULL); else err = -ESRCH; } else { @@ -732,7 +733,7 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; } - err = fib_table_delete(net, tb, &cfg); + err = fib_table_delete(net, tb, &cfg, extack); errout: return err; } @@ -851,7 +852,7 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad if (cmd == RTM_NEWROUTE) fib_table_insert(net, tb, &cfg, NULL); else - fib_table_delete(net, tb, &cfg); + fib_table_delete(net, tb, &cfg, NULL); } void fib_add_ifaddr(struct in_ifaddr *ifa) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 9bd46e1e1037..a624d380c81d 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1099,13 +1099,18 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp, return 0; } -static bool fib_valid_key_len(u32 key, u8 plen) +static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack) { - if (plen > KEYLENGTH) + if (plen > KEYLENGTH) { + NL_SET_ERR_MSG(extack, "Invalid prefix length"); return false; + } - if ((plen < KEYLENGTH) && (key << plen)) + if ((plen < KEYLENGTH) && (key << plen)) { + NL_SET_ERR_MSG(extack, + "Invalid prefix for given prefix length"); return false; + } return true; } @@ -1128,7 +1133,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, key = ntohl(cfg->fc_dst); - if (!fib_valid_key_len(key, plen)) + if (!fib_valid_key_len(key, plen, extack)) return -EINVAL; pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); @@ -1516,7 +1521,7 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp, /* Caller must hold RTNL. */ int fib_table_delete(struct net *net, struct fib_table *tb, - struct fib_config *cfg) + struct fib_config *cfg, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *) tb->tb_data; struct fib_alias *fa, *fa_to_delete; @@ -1528,7 +1533,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, key = ntohl(cfg->fc_dst); - if (!fib_valid_key_len(key, plen)) + if (!fib_valid_key_len(key, plen, extack)) return -EINVAL; l = fib_find_node(t, &tp, key); -- cgit v1.3-14-g43fede From c255bd681d1a93fff2a2c249d91449cce830ac64 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sat, 27 May 2017 16:19:27 -0600 Subject: net: lwtunnel: Add extack to encap attr validation Pass extack down to lwtunnel_valid_encap_type and lwtunnel_valid_encap_type_attr. Add messages for unknown or unsupported encap types. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/lwtunnel.h | 13 +++++++++---- net/core/lwtunnel.c | 18 +++++++++++++----- net/ipv4/fib_frontend.c | 6 ++++-- net/ipv6/route.c | 4 ++-- 4 files changed, 28 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index ebfe237aad7e..ca6f002774ef 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -107,8 +107,10 @@ int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, unsigned int num); int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, unsigned int num); -int lwtunnel_valid_encap_type(u16 encap_type); -int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len); +int lwtunnel_valid_encap_type(u16 encap_type, + struct netlink_ext_ack *extack); +int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, + struct netlink_ext_ack *extack); int lwtunnel_build_state(u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, @@ -172,11 +174,14 @@ static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, return -EOPNOTSUPP; } -static inline int lwtunnel_valid_encap_type(u16 encap_type) +static inline int lwtunnel_valid_encap_type(u16 encap_type, + struct netlink_ext_ack *extack) { + NL_SET_ERR_MSG(extack, "CONFIG_LWTUNNEL is not enabled in this kernel"); return -EOPNOTSUPP; } -static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len) +static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, + struct netlink_ext_ack *extack) { /* return 0 since we are not walking attr looking for * RTA_ENCAP_TYPE attribute on nexthops. diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index cfae3d5fe11f..ab840386a74d 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -126,14 +126,16 @@ int lwtunnel_build_state(u16 encap_type, } EXPORT_SYMBOL(lwtunnel_build_state); -int lwtunnel_valid_encap_type(u16 encap_type) +int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack) { const struct lwtunnel_encap_ops *ops; int ret = -EINVAL; if (encap_type == LWTUNNEL_ENCAP_NONE || - encap_type > LWTUNNEL_ENCAP_MAX) + encap_type > LWTUNNEL_ENCAP_MAX) { + NL_SET_ERR_MSG(extack, "Unknown lwt encapsulation type"); return ret; + } rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); @@ -153,11 +155,16 @@ int lwtunnel_valid_encap_type(u16 encap_type) } } #endif - return ops ? 0 : -EOPNOTSUPP; + ret = ops ? 0 : -EOPNOTSUPP; + if (ret < 0) + NL_SET_ERR_MSG(extack, "lwt encapsulation type not supported"); + + return ret; } EXPORT_SYMBOL(lwtunnel_valid_encap_type); -int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining) +int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining, + struct netlink_ext_ack *extack) { struct rtnexthop *rtnh = (struct rtnexthop *)attr; struct nlattr *nla_entype; @@ -174,7 +181,8 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining) if (nla_entype) { encap_type = nla_get_u16(nla_entype); - if (lwtunnel_valid_encap_type(encap_type) != 0) + if (lwtunnel_valid_encap_type(encap_type, + extack) != 0) return -EOPNOTSUPP; } } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 715b7967d8ea..4e678fa892dd 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -685,7 +685,8 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, break; case RTA_MULTIPATH: err = lwtunnel_valid_encap_type_attr(nla_data(attr), - nla_len(attr)); + nla_len(attr), + extack); if (err < 0) goto errout; cfg->fc_mp = nla_data(attr); @@ -702,7 +703,8 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, break; case RTA_ENCAP_TYPE: cfg->fc_encap_type = nla_get_u16(attr); - err = lwtunnel_valid_encap_type(cfg->fc_encap_type); + err = lwtunnel_valid_encap_type(cfg->fc_encap_type, + extack); if (err < 0) goto errout; break; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2fe84bdc4e60..524a76b5206e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3016,7 +3016,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); err = lwtunnel_valid_encap_type_attr(cfg->fc_mp, - cfg->fc_mp_len); + cfg->fc_mp_len, extack); if (err < 0) goto errout; } @@ -3035,7 +3035,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[RTA_ENCAP_TYPE]) { cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); - err = lwtunnel_valid_encap_type(cfg->fc_encap_type); + err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack); if (err < 0) goto errout; } -- cgit v1.3-14-g43fede From 9ae287274817c032a4428fde84d1ab26d6b96761 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sat, 27 May 2017 16:19:28 -0600 Subject: net: add extack arg to lwtunnel build state Pass extack arg down to lwtunnel_build_state and the build_state callbacks. Add messages for failures in lwtunnel_build_state, and add the extarg to nla_parse where possible in the build_state callbacks. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netlink.h | 10 ++++++++++ include/net/lwtunnel.h | 9 ++++++--- net/core/lwt_bpf.c | 5 +++-- net/core/lwtunnel.c | 20 +++++++++++++++++--- net/ipv4/fib_lookup.h | 3 ++- net/ipv4/fib_semantics.c | 20 +++++++++++--------- net/ipv4/fib_trie.c | 2 +- net/ipv4/ip_tunnel_core.c | 11 +++++++---- net/ipv6/ila/ila_lwt.c | 5 +++-- net/ipv6/route.c | 2 +- net/ipv6/seg6_iptunnel.c | 5 +++-- net/mpls/mpls_iptunnel.c | 5 +++-- 12 files changed, 67 insertions(+), 30 deletions(-) (limited to 'include/net') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index a68aad484c69..8664fd26eb5d 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -102,6 +102,16 @@ struct netlink_ext_ack { (extack)->bad_attr = (attr); \ } while (0) +#define NL_SET_ERR_MSG_ATTR(extack, attr, msg) do { \ + static const char __msg[] = (msg); \ + struct netlink_ext_ack *__extack = (extack); \ + \ + if (__extack) { \ + __extack->_msg = __msg; \ + __extack->bad_attr = (attr); \ + } \ +} while (0) + extern void netlink_kernel_release(struct sock *sk); extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups); extern int netlink_change_ngroups(struct sock *sk, unsigned int groups); diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index ca6f002774ef..7c26863b8cf4 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -35,7 +35,8 @@ struct lwtunnel_state { struct lwtunnel_encap_ops { int (*build_state)(struct nlattr *encap, unsigned int family, const void *cfg, - struct lwtunnel_state **ts); + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack); void (*destroy_state)(struct lwtunnel_state *lws); int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*input)(struct sk_buff *skb); @@ -114,7 +115,8 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, int lwtunnel_build_state(u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, - struct lwtunnel_state **lws); + struct lwtunnel_state **lws, + struct netlink_ext_ack *extack); int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate); int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate); @@ -192,7 +194,8 @@ static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, static inline int lwtunnel_build_state(u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, - struct lwtunnel_state **lws) + struct lwtunnel_state **lws, + struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index b3bc0a31af9f..1307731ddfe4 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -240,7 +240,8 @@ static const struct nla_policy bpf_nl_policy[LWT_BPF_MAX + 1] = { static int bpf_build_state(struct nlattr *nla, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct nlattr *tb[LWT_BPF_MAX + 1]; struct lwtunnel_state *newts; @@ -250,7 +251,7 @@ static int bpf_build_state(struct nlattr *nla, if (family != AF_INET && family != AF_INET6) return -EAFNOSUPPORT; - ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy, NULL); + ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy, extack); if (ret < 0) return ret; diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index ab840386a74d..d9cb3532f1dd 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -103,25 +103,39 @@ EXPORT_SYMBOL(lwtunnel_encap_del_ops); int lwtunnel_build_state(u16 encap_type, struct nlattr *encap, unsigned int family, - const void *cfg, struct lwtunnel_state **lws) + const void *cfg, struct lwtunnel_state **lws, + struct netlink_ext_ack *extack) { const struct lwtunnel_encap_ops *ops; + bool found = false; int ret = -EINVAL; if (encap_type == LWTUNNEL_ENCAP_NONE || - encap_type > LWTUNNEL_ENCAP_MAX) + encap_type > LWTUNNEL_ENCAP_MAX) { + NL_SET_ERR_MSG_ATTR(extack, encap, + "Unknown LWT encapsulation type"); return ret; + } ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); if (likely(ops && ops->build_state && try_module_get(ops->owner))) { - ret = ops->build_state(encap, family, cfg, lws); + found = true; + ret = ops->build_state(encap, family, cfg, lws, extack); if (ret) module_put(ops->owner); } rcu_read_unlock(); + /* don't rely on -EOPNOTSUPP to detect match as build_state + * handlers could return it + */ + if (!found) { + NL_SET_ERR_MSG_ATTR(extack, encap, + "LWT encapsulation type not supported"); + } + return ret; } EXPORT_SYMBOL(lwtunnel_build_state); diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index 2704e08545da..769ab87ebc4b 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -30,7 +30,8 @@ static inline void fib_alias_accessed(struct fib_alias *fa) void fib_release_info(struct fib_info *); struct fib_info *fib_create_info(struct fib_config *cfg, struct netlink_ext_ack *extack); -int fib_nh_match(struct fib_config *cfg, struct fib_info *fi); +int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, + struct netlink_ext_ack *extack); int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi, unsigned int); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index de9484658232..2157dc08c407 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -532,7 +532,7 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, ret = lwtunnel_build_state(nla_get_u16( nla_entype), nla, AF_INET, cfg, - &lwtstate); + &lwtstate, extack); if (ret) goto errout; nexthop_nh->nh_lwtstate = @@ -614,7 +614,8 @@ static inline void fib_add_weight(struct fib_info *fi, static int fib_encap_match(u16 encap_type, struct nlattr *encap, const struct fib_nh *nh, - const struct fib_config *cfg) + const struct fib_config *cfg, + struct netlink_ext_ack *extack) { struct lwtunnel_state *lwtstate; int ret, result = 0; @@ -622,8 +623,8 @@ static int fib_encap_match(u16 encap_type, if (encap_type == LWTUNNEL_ENCAP_NONE) return 0; - ret = lwtunnel_build_state(encap_type, encap, - AF_INET, cfg, &lwtstate); + ret = lwtunnel_build_state(encap_type, encap, AF_INET, + cfg, &lwtstate, extack); if (!ret) { result = lwtunnel_cmp_encap(lwtstate, nh->nh_lwtstate); lwtstate_free(lwtstate); @@ -632,7 +633,8 @@ static int fib_encap_match(u16 encap_type, return result; } -int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) +int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, + struct netlink_ext_ack *extack) { #ifdef CONFIG_IP_ROUTE_MULTIPATH struct rtnexthop *rtnh; @@ -644,9 +646,9 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) if (cfg->fc_oif || cfg->fc_gw) { if (cfg->fc_encap) { - if (fib_encap_match(cfg->fc_encap_type, - cfg->fc_encap, fi->fib_nh, cfg)) - return 1; + if (fib_encap_match(cfg->fc_encap_type, cfg->fc_encap, + fi->fib_nh, cfg, extack)) + return 1; } if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) && (!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw)) @@ -1148,7 +1150,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, } err = lwtunnel_build_state(cfg->fc_encap_type, cfg->fc_encap, AF_INET, cfg, - &lwtstate); + &lwtstate, extack); if (err) goto failure; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index a624d380c81d..d56659e97a6e 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1562,7 +1562,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, fi->fib_prefsrc == cfg->fc_prefsrc) && (!cfg->fc_protocol || fi->fib_protocol == cfg->fc_protocol) && - fib_nh_match(cfg, fi) == 0) { + fib_nh_match(cfg, fi, extack) == 0) { fa_to_delete = fa; break; } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index baf196eaf1d8..90e11479c725 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -228,14 +228,16 @@ static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = { static int ip_tun_build_state(struct nlattr *attr, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct ip_tunnel_info *tun_info; struct lwtunnel_state *new_state; struct nlattr *tb[LWTUNNEL_IP_MAX + 1]; int err; - err = nla_parse_nested(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy, NULL); + err = nla_parse_nested(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy, + extack); if (err < 0) return err; @@ -325,7 +327,8 @@ static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = { static int ip6_tun_build_state(struct nlattr *attr, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct ip_tunnel_info *tun_info; struct lwtunnel_state *new_state; @@ -333,7 +336,7 @@ static int ip6_tun_build_state(struct nlattr *attr, int err; err = nla_parse_nested(tb, LWTUNNEL_IP6_MAX, attr, ip6_tun_policy, - NULL); + extack); if (err < 0) return err; diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index f4a413aba423..0c02a09bc351 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -117,7 +117,8 @@ static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { static int ila_build_state(struct nlattr *nla, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct ila_lwt *ilwt; struct ila_params *p; @@ -146,7 +147,7 @@ static int ila_build_state(struct nlattr *nla, return -EINVAL; } - ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, NULL); + ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, extack); if (ret < 0) return ret; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 524a76b5206e..9d9b5bbea153 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1939,7 +1939,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, err = lwtunnel_build_state(cfg->fc_encap_type, cfg->fc_encap, AF_INET6, cfg, - &lwtstate); + &lwtstate, extack); if (err) goto out; rt->dst.lwtstate = lwtstate_get(lwtstate); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 6a495490d43e..264d772d3c7d 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -326,7 +326,8 @@ drop: static int seg6_build_state(struct nlattr *nla, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct nlattr *tb[SEG6_IPTUNNEL_MAX + 1]; struct seg6_iptunnel_encap *tuninfo; @@ -336,7 +337,7 @@ static int seg6_build_state(struct nlattr *nla, int err; err = nla_parse_nested(tb, SEG6_IPTUNNEL_MAX, nla, - seg6_iptunnel_policy, NULL); + seg6_iptunnel_policy, extack); if (err < 0) return err; diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 369c7a23c86c..15e1aa708e50 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -159,7 +159,8 @@ drop: static int mpls_build_state(struct nlattr *nla, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct mpls_iptunnel_encap *tun_encap_info; struct nlattr *tb[MPLS_IPTUNNEL_MAX + 1]; @@ -168,7 +169,7 @@ static int mpls_build_state(struct nlattr *nla, int ret; ret = nla_parse_nested(tb, MPLS_IPTUNNEL_MAX, nla, - mpls_iptunnel_policy, NULL); + mpls_iptunnel_policy, extack); if (ret < 0) return ret; -- cgit v1.3-14-g43fede From 23c9ee4934e7a79b49151d0f05c24117d69c73fe Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 26 May 2017 18:12:51 -0400 Subject: net: dsa: remove dev arg of dsa_register_switch The current dsa_register_switch function takes a useless struct device pointer argument, which always equals ds->dev. Drivers either call it with ds->dev, or with the same device pointer passed to dsa_switch_alloc, which ends up being assigned to ds->dev. This patch removes the second argument of the dsa_register_switch and _dsa_register_switch functions. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/b53/b53_common.c | 2 +- drivers/net/dsa/dsa_loop.c | 2 +- drivers/net/dsa/lan9303-core.c | 2 +- drivers/net/dsa/mt7530.c | 2 +- drivers/net/dsa/mv88e6xxx/chip.c | 2 +- drivers/net/dsa/qca8k.c | 2 +- include/net/dsa.h | 2 +- net/dsa/dsa2.c | 10 +++++----- 8 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/net') diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 6a5648a9cb09..e68d368e20ac 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1989,7 +1989,7 @@ int b53_switch_register(struct b53_device *dev) pr_info("found switch: %s, rev %i\n", dev->name, dev->core_rev); - return dsa_register_switch(dev->ds, dev->ds->dev); + return dsa_register_switch(dev->ds); } EXPORT_SYMBOL(b53_switch_register); diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index 5edf07beb9d2..79e62593ff4e 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -271,7 +271,7 @@ static int dsa_loop_drv_probe(struct mdio_device *mdiodev) dev_set_drvdata(&mdiodev->dev, ds); - return dsa_register_switch(ds, ds->dev); + return dsa_register_switch(ds); } static void dsa_loop_drv_remove(struct mdio_device *mdiodev) diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index c8b2423c8ef7..cd76e61f1fca 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -802,7 +802,7 @@ static int lan9303_register_switch(struct lan9303 *chip) chip->ds->ops = &lan9303_switch_ops; chip->ds->phys_mii_mask = chip->phy_addr_sel_strap ? 0xe : 0x7; - return dsa_register_switch(chip->ds, chip->dev); + return dsa_register_switch(chip->ds); } static void lan9303_probe_reset_gpio(struct lan9303 *chip, diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 4d2f45153ede..25e00d5e0eec 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1080,7 +1080,7 @@ mt7530_probe(struct mdio_device *mdiodev) mutex_init(&priv->reg_mutex); dev_set_drvdata(&mdiodev->dev, priv); - return dsa_register_switch(priv->ds, &mdiodev->dev); + return dsa_register_switch(priv->ds); } static void diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 070e82ac6132..7cf470c3e662 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3884,7 +3884,7 @@ static int mv88e6xxx_register_switch(struct mv88e6xxx_chip *chip) dev_set_drvdata(dev, ds); - return dsa_register_switch(ds, dev); + return dsa_register_switch(ds); } static void mv88e6xxx_unregister_switch(struct mv88e6xxx_chip *chip) diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 0f6a011d8ed1..b3bee7eab45f 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -958,7 +958,7 @@ qca8k_sw_probe(struct mdio_device *mdiodev) mutex_init(&priv->reg_mutex); dev_set_drvdata(&mdiodev->dev, priv); - return dsa_register_switch(priv->ds, &mdiodev->dev); + return dsa_register_switch(priv->ds); } static void diff --git a/include/net/dsa.h b/include/net/dsa.h index c0e567c0c824..d9bd6939229a 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -480,7 +480,7 @@ static inline bool netdev_uses_dsa(struct net_device *dev) struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n); void dsa_unregister_switch(struct dsa_switch *ds); -int dsa_register_switch(struct dsa_switch *ds, struct device *dev); +int dsa_register_switch(struct dsa_switch *ds); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); int dsa_switch_resume(struct dsa_switch *ds); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 4301f52e4f5a..c0a4576db4a2 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -686,10 +686,10 @@ static struct device_node *dsa_get_ports(struct dsa_switch *ds, return ports; } -static int _dsa_register_switch(struct dsa_switch *ds, struct device *dev) +static int _dsa_register_switch(struct dsa_switch *ds) { - struct dsa_chip_data *pdata = dev->platform_data; - struct device_node *np = dev->of_node; + struct dsa_chip_data *pdata = ds->dev->platform_data; + struct device_node *np = ds->dev->of_node; struct dsa_switch_tree *dst; struct device_node *ports; u32 tree, index; @@ -803,12 +803,12 @@ struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n) } EXPORT_SYMBOL_GPL(dsa_switch_alloc); -int dsa_register_switch(struct dsa_switch *ds, struct device *dev) +int dsa_register_switch(struct dsa_switch *ds) { int err; mutex_lock(&dsa2_mutex); - err = _dsa_register_switch(ds, dev); + err = _dsa_register_switch(ds); mutex_unlock(&dsa2_mutex); return err; -- cgit v1.3-14-g43fede From d897a638e98c476c56118d0dcc1bc55450504866 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 31 May 2017 08:06:43 -0700 Subject: sched: add helper for updating statistics on all actions Forgetting to disable preemption around tcf_action_stats_update() seems to be a common mistake. Add a helper function for updating stats on all actions of a filter. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 10 +--------- drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c | 10 +--------- drivers/net/ethernet/netronome/nfp/nfp_net_offload.c | 11 ++--------- include/net/pkt_cls.h | 19 +++++++++++++++++++ 4 files changed, 23 insertions(+), 27 deletions(-) (limited to 'include/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index d2f90ba2dbc4..7914a32a3036 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1863,9 +1863,7 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv, { struct mlx5e_tc_table *tc = &priv->fs.tc; struct mlx5e_tc_flow *flow; - struct tc_action *a; struct mlx5_fc *counter; - LIST_HEAD(actions); u64 bytes; u64 packets; u64 lastuse; @@ -1884,13 +1882,7 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv, mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse); - preempt_disable(); - - tcf_exts_to_list(f->exts, &actions); - list_for_each_entry(a, &actions, list) - tcf_action_stats_update(a, bytes, packets, lastuse); - - preempt_enable(); + tcf_exts_stats_update(f->exts, bytes, packets, lastuse); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index ed75c6a85bc3..13af8e358847 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -397,8 +397,6 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_acl_ruleset *ruleset; struct mlxsw_sp_acl_rule *rule; - struct tc_action *a; - LIST_HEAD(actions); u64 packets; u64 lastuse; u64 bytes; @@ -419,13 +417,7 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, if (err) goto err_rule_get_stats; - preempt_disable(); - - tcf_exts_to_list(f->exts, &actions); - list_for_each_entry(a, &actions, list) - tcf_action_stats_update(a, bytes, packets, lastuse); - - preempt_enable(); + tcf_exts_stats_update(f->exts, bytes, packets, lastuse); mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset); return 0; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c index cc823df12c8a..2fa7b67d0c6f 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c @@ -84,8 +84,6 @@ static void nfp_net_bpf_stats_reset(struct nfp_net *nn) static int nfp_net_bpf_stats_update(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf) { - struct tc_action *a; - LIST_HEAD(actions); u64 bytes, pkts; pkts = nn->rx_filter.pkts - nn->rx_filter_prev.pkts; @@ -94,13 +92,8 @@ nfp_net_bpf_stats_update(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf) nn->rx_filter_prev = nn->rx_filter; - preempt_disable(); - - tcf_exts_to_list(cls_bpf->exts, &actions); - list_for_each_entry(a, &actions, list) - tcf_action_stats_update(a, bytes, pkts, nn->rx_filter_change); - - preempt_enable(); + tcf_exts_stats_update(cls_bpf->exts, + bytes, pkts, nn->rx_filter_change); return 0; } diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index f7762295b7b8..537d0a0ad4c4 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -157,6 +157,25 @@ static inline void tcf_exts_to_list(const struct tcf_exts *exts, #endif } +static inline void +tcf_exts_stats_update(const struct tcf_exts *exts, + u64 bytes, u64 packets, u64 lastuse) +{ +#ifdef CONFIG_NET_CLS_ACT + int i; + + preempt_disable(); + + for (i = 0; i < exts->nr_actions; i++) { + struct tc_action *a = exts->actions[i]; + + tcf_action_stats_update(a, bytes, packets, lastuse); + } + + preempt_enable(); +#endif +} + /** * tcf_exts_exec - execute tc filter extensions * @skb: socket buffer -- cgit v1.3-14-g43fede From 8b8010fb7876e816300ddd60fa089e9ceb209f3e Mon Sep 17 00:00:00 2001 From: Woojung Huh Date: Wed, 31 May 2017 20:19:06 +0000 Subject: dsa: add support for Microchip KSZ tail tagging Adding support for the Microchip KSZ switch family tail tagging. Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: Woojung Huh Signed-off-by: David S. Miller --- include/net/dsa.h | 1 + net/dsa/Kconfig | 3 ++ net/dsa/Makefile | 1 + net/dsa/dsa.c | 3 ++ net/dsa/dsa_priv.h | 3 ++ net/dsa/tag_ksz.c | 101 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 112 insertions(+) create mode 100644 net/dsa/tag_ksz.c (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index d9bd6939229a..7de1234ba136 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -31,6 +31,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_BRCM, DSA_TAG_PROTO_DSA, DSA_TAG_PROTO_EDSA, + DSA_TAG_PROTO_KSZ, DSA_TAG_PROTO_LAN9303, DSA_TAG_PROTO_MTK, DSA_TAG_PROTO_QCA, diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 297389b2ab35..cc5f8f971689 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -25,6 +25,9 @@ config NET_DSA_TAG_DSA config NET_DSA_TAG_EDSA bool +config NET_DSA_TAG_KSZ + bool + config NET_DSA_TAG_LAN9303 bool diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 90e5aa6f7d0f..fcce25da937c 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -6,6 +6,7 @@ dsa_core-y += dsa.o dsa2.o legacy.o port.o slave.o switch.o dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o +dsa_core-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o dsa_core-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o dsa_core-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o dsa_core-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 3288a80d4d6c..402459e73f33 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -49,6 +49,9 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = { #ifdef CONFIG_NET_DSA_TAG_EDSA [DSA_TAG_PROTO_EDSA] = &edsa_netdev_ops, #endif +#ifdef CONFIG_NET_DSA_TAG_KSZ + [DSA_TAG_PROTO_KSZ] = &ksz_netdev_ops, +#endif #ifdef CONFIG_NET_DSA_TAG_LAN9303 [DSA_TAG_PROTO_LAN9303] = &lan9303_netdev_ops, #endif diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index c1d4180651af..7459d5735d8b 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -167,6 +167,9 @@ extern const struct dsa_device_ops dsa_netdev_ops; /* tag_edsa.c */ extern const struct dsa_device_ops edsa_netdev_ops; +/* tag_ksz.c */ +extern const struct dsa_device_ops ksz_netdev_ops; + /* tag_lan9303.c */ extern const struct dsa_device_ops lan9303_netdev_ops; diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c new file mode 100644 index 000000000000..0b08a40b493a --- /dev/null +++ b/net/dsa/tag_ksz.c @@ -0,0 +1,101 @@ +/* + * net/dsa/tag_ksz.c - Microchip KSZ Switch tag format handling + * Copyright (c) 2017 Microchip Technology + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include +#include +#include +#include +#include "dsa_priv.h" + +/* For Ingress (Host -> KSZ), 2 bytes are added before FCS. + * --------------------------------------------------------------------------- + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|tag1(1byte)|FCS(4bytes) + * --------------------------------------------------------------------------- + * tag0 : Prioritization (not used now) + * tag1 : each bit represents port (eg, 0x01=port1, 0x02=port2, 0x10=port5) + * + * For Egress (KSZ -> Host), 1 byte is added before FCS. + * --------------------------------------------------------------------------- + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes) + * --------------------------------------------------------------------------- + * tag0 : zero-based value represents port + * (eg, 0x00=port1, 0x02=port3, 0x06=port7) + */ + +#define KSZ_INGRESS_TAG_LEN 2 +#define KSZ_EGRESS_TAG_LEN 1 + +static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct sk_buff *nskb; + int padlen; + u8 *tag; + + padlen = (skb->len >= ETH_ZLEN) ? 0 : ETH_ZLEN - skb->len; + + if (skb_tailroom(skb) >= padlen + KSZ_INGRESS_TAG_LEN) { + nskb = skb; + } else { + nskb = alloc_skb(NET_IP_ALIGN + skb->len + + padlen + KSZ_INGRESS_TAG_LEN, GFP_ATOMIC); + if (!nskb) { + kfree_skb(skb); + return NULL; + } + skb_reserve(nskb, NET_IP_ALIGN); + + skb_reset_mac_header(nskb); + skb_set_network_header(nskb, + skb_network_header(skb) - skb->head); + skb_set_transport_header(nskb, + skb_transport_header(skb) - skb->head); + skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len)); + kfree_skb(skb); + } + + /* skb is freed when it fails */ + if (skb_put_padto(nskb, nskb->len + padlen)) + return NULL; + + tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); + tag[0] = 0; + tag[1] = 1 << p->dp->index; /* destination port */ + + return nskb; +} + +struct sk_buff *ksz_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + struct dsa_switch_tree *dst = dev->dsa_ptr; + struct dsa_switch *ds; + u8 *tag; + int source_port; + + ds = dst->cpu_dp->ds; + + tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; + + source_port = tag[0] & 7; + if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) + return NULL; + + pskb_trim_rcsum(skb, skb->len - KSZ_EGRESS_TAG_LEN); + + skb->dev = ds->ports[source_port].netdev; + + return skb; +} + +const struct dsa_device_ops ksz_netdev_ops = { + .xmit = ksz_xmit, + .rcv = ksz_rcv, +}; -- cgit v1.3-14-g43fede From 73a7ece8f70c955464080e434b5324bcdfdcb1b1 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Thu, 1 Jun 2017 16:07:11 -0400 Subject: net: dsa: comment hot path requirements The DSA layer uses inline helpers and copy of the tagging functions for faster access in hot path. Add comments to detail that. Reviewed-by: Florian Fainelli Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 3 +++ net/dsa/dsa_priv.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index 7de1234ba136..18ca0a935c96 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -127,6 +127,8 @@ struct dsa_switch_tree { * protocol to use. */ struct net_device *master_netdev; + + /* Copy of tag_ops->rcv for faster access in hot path */ struct sk_buff * (*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, @@ -465,6 +467,7 @@ struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev); struct net_device *dsa_dev_to_net_device(struct device *dev); +/* Keep inline for faster access in hot path */ static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst) { return dst->rcv != NULL; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 7459d5735d8b..db2a7b9edfb8 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -73,6 +73,7 @@ struct dsa_device_ops { }; struct dsa_slave_priv { + /* Copy of dp->ds->dst->tag_ops->xmit for faster access in hot path */ struct sk_buff * (*xmit)(struct sk_buff *skb, struct net_device *dev); -- cgit v1.3-14-g43fede From 717ffbfb28ac2b53d3140b2a7dfd345e1569b3a5 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Thu, 1 Jun 2017 16:07:13 -0400 Subject: net: dsa: remove dsa_uses_tagged_protocol Since dev->dsa_ptr is a pointer to a dsa_switch_tree, there is no need to have another inline helper just to check rcv. Remove dsa_uses_tagged_protocol and check dsa_ptr && dsa_ptr->rcv together at the same time. Reviewed-by: Florian Fainelli Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index 18ca0a935c96..448d8bc77707 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -468,16 +468,10 @@ struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev); struct net_device *dsa_dev_to_net_device(struct device *dev); /* Keep inline for faster access in hot path */ -static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst) -{ - return dst->rcv != NULL; -} - static inline bool netdev_uses_dsa(struct net_device *dev) { #if IS_ENABLED(CONFIG_NET_DSA) - if (dev->dsa_ptr != NULL) - return dsa_uses_tagged_protocol(dev->dsa_ptr); + return dev->dsa_ptr && dev->dsa_ptr->rcv; #endif return false; } -- cgit v1.3-14-g43fede From cee360ab4dd66fc1de33a5fa1cb418fa21c27ce3 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 31 May 2017 16:36:31 +0800 Subject: sctp: define the member stream as an object instead of pointer in asoc As Marcelo's suggestion, stream is a fixed size member of asoc and would not grow with more streams. To avoid an allocation for it, this patch is to define it as an object instead of pointer and update the places using it, also create sctp_stream_update() called in sctp_assoc_update() to migrate the stream info from one stream to another. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 3 +- net/sctp/associola.c | 13 ++++----- net/sctp/chunk.c | 4 +-- net/sctp/outqueue.c | 10 +++---- net/sctp/proc.c | 4 +-- net/sctp/sm_make_chunk.c | 2 +- net/sctp/sm_statefuns.c | 8 +++--- net/sctp/socket.c | 14 +++++----- net/sctp/stream.c | 68 ++++++++++++++++++++++------------------------ net/sctp/ulpqueue.c | 8 +++--- 10 files changed, 65 insertions(+), 69 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index a8b38e123f97..c8dbf410c4f5 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -381,6 +381,7 @@ int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp); int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp); void sctp_stream_free(struct sctp_stream *stream); void sctp_stream_clear(struct sctp_stream *stream); +void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new); /* What is the current SSN number for this stream? */ #define sctp_ssn_peek(stream, type, sid) \ @@ -1750,7 +1751,7 @@ struct sctp_association { __u32 default_rcv_context; /* Stream arrays */ - struct sctp_stream *stream; + struct sctp_stream stream; /* All outbound chunks go through this structure. */ struct sctp_outq outqueue; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 95238284c422..6625b15ab81a 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -291,7 +291,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a return asoc; stream_free: - sctp_stream_free(asoc->stream); + sctp_stream_free(&asoc->stream); fail_init: sock_put(asoc->base.sk); sctp_endpoint_put(asoc->ep); @@ -365,7 +365,7 @@ void sctp_association_free(struct sctp_association *asoc) sctp_tsnmap_free(&asoc->peer.tsn_map); /* Free stream information. */ - sctp_stream_free(asoc->stream); + sctp_stream_free(&asoc->stream); if (asoc->strreset_chunk) sctp_chunk_free(asoc->strreset_chunk); @@ -1151,7 +1151,7 @@ void sctp_assoc_update(struct sctp_association *asoc, /* Reinitialize SSN for both local streams * and peer's streams. */ - sctp_stream_clear(asoc->stream); + sctp_stream_clear(&asoc->stream); /* Flush the ULP reassembly and ordered queue. * Any data there will now be stale and will @@ -1177,11 +1177,8 @@ void sctp_assoc_update(struct sctp_association *asoc, asoc->ctsn_ack_point = asoc->next_tsn - 1; asoc->adv_peer_ack_point = asoc->ctsn_ack_point; - if (sctp_state(asoc, COOKIE_WAIT)) { - sctp_stream_free(asoc->stream); - asoc->stream = new->stream; - new->stream = NULL; - } + if (sctp_state(asoc, COOKIE_WAIT)) + sctp_stream_update(&asoc->stream, &new->stream); if (!asoc->assoc_id) { /* get a new association id since we don't have one diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 697721a7a3f1..81466f6442e8 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -307,7 +307,7 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) && time_after(jiffies, chunk->msg->expires_at)) { struct sctp_stream_out *streamout = - &chunk->asoc->stream->out[chunk->sinfo.sinfo_stream]; + &chunk->asoc->stream.out[chunk->sinfo.sinfo_stream]; if (chunk->sent_count) { chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++; @@ -320,7 +320,7 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) } else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) && chunk->sent_count > chunk->sinfo.sinfo_timetolive) { struct sctp_stream_out *streamout = - &chunk->asoc->stream->out[chunk->sinfo.sinfo_stream]; + &chunk->asoc->stream.out[chunk->sinfo.sinfo_stream]; chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++; streamout->abandoned_sent[SCTP_PR_INDEX(RTX)]++; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index fe4c3d462f6e..20299df163b9 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -363,7 +363,7 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc, sctp_insert_list(&asoc->outqueue.abandoned, &chk->transmitted_list); - streamout = &asoc->stream->out[chk->sinfo.sinfo_stream]; + streamout = &asoc->stream.out[chk->sinfo.sinfo_stream]; asoc->sent_cnt_removable--; asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; streamout->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; @@ -400,9 +400,9 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, q->out_qlen -= chk->skb->len; asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; - if (chk->sinfo.sinfo_stream < asoc->stream->outcnt) { + if (chk->sinfo.sinfo_stream < asoc->stream.outcnt) { struct sctp_stream_out *streamout = - &asoc->stream->out[chk->sinfo.sinfo_stream]; + &asoc->stream.out[chk->sinfo.sinfo_stream]; streamout->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; } @@ -1036,7 +1036,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) /* RFC 2960 6.5 Every DATA chunk MUST carry a valid * stream identifier. */ - if (chunk->sinfo.sinfo_stream >= asoc->stream->outcnt) { + if (chunk->sinfo.sinfo_stream >= asoc->stream.outcnt) { /* Mark as failed send. */ sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM); @@ -1054,7 +1054,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) continue; } - if (asoc->stream->out[sid].state == SCTP_STREAM_CLOSED) { + if (asoc->stream.out[sid].state == SCTP_STREAM_CLOSED) { sctp_outq_head_data(q, chunk); goto sctp_flush_out; } diff --git a/net/sctp/proc.c b/net/sctp/proc.c index a0b29d43627f..5a27d0f03df5 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -361,8 +361,8 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) sctp_seq_dump_remote_addrs(seq, assoc); seq_printf(seq, "\t%8lu %5d %5d %4d %4d %4d %8d " "%8d %8d %8d %8d", - assoc->hbinterval, assoc->stream->incnt, - assoc->stream->outcnt, assoc->max_retrans, + assoc->hbinterval, assoc->stream.incnt, + assoc->stream.outcnt, assoc->max_retrans, assoc->init_retries, assoc->shutdown_retries, assoc->rtx_data_chunks, atomic_read(&sk->sk_wmem_alloc), diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 92e332e17391..244181413bca 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1544,7 +1544,7 @@ void sctp_chunk_assign_ssn(struct sctp_chunk *chunk) /* All fragments will be on the same stream */ sid = ntohs(chunk->subh.data_hdr->stream); - stream = chunk->asoc->stream; + stream = &chunk->asoc->stream; /* Now assign the sequence number to the entire message. * All fragments must have the same stream sequence number. diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index f863b5573e42..df73190da761 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3958,7 +3958,7 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn(struct net *net, /* Silently discard the chunk if stream-id is not valid */ sctp_walk_fwdtsn(skip, chunk) { - if (ntohs(skip->stream) >= asoc->stream->incnt) + if (ntohs(skip->stream) >= asoc->stream.incnt) goto discard_noforce; } @@ -4029,7 +4029,7 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn_fast( /* Silently discard the chunk if stream-id is not valid */ sctp_walk_fwdtsn(skip, chunk) { - if (ntohs(skip->stream) >= asoc->stream->incnt) + if (ntohs(skip->stream) >= asoc->stream.incnt) goto gen_shutdown; } @@ -6365,7 +6365,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * and discard the DATA chunk. */ sid = ntohs(data_hdr->stream); - if (sid >= asoc->stream->incnt) { + if (sid >= asoc->stream.incnt) { /* Mark tsn as received even though we drop it */ sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_TSN, SCTP_U32(tsn)); @@ -6387,7 +6387,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * and is invalid. */ ssn = ntohs(data_hdr->ssn); - if (ordered && SSN_lt(ssn, sctp_ssn_peek(asoc->stream, in, sid))) + if (ordered && SSN_lt(ssn, sctp_ssn_peek(&asoc->stream, in, sid))) return SCTP_IERROR_PROTO_VIOLATION; /* Send the data up to the user. Note: Schedule the diff --git a/net/sctp/socket.c b/net/sctp/socket.c index f16c8d97b7f3..0822046e4f3f 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1920,7 +1920,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) } /* Check for invalid stream. */ - if (sinfo->sinfo_stream >= asoc->stream->outcnt) { + if (sinfo->sinfo_stream >= asoc->stream.outcnt) { err = -EINVAL; goto out_free; } @@ -4497,8 +4497,8 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, info->sctpi_rwnd = asoc->a_rwnd; info->sctpi_unackdata = asoc->unack_data; info->sctpi_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map); - info->sctpi_instrms = asoc->stream->incnt; - info->sctpi_outstrms = asoc->stream->outcnt; + info->sctpi_instrms = asoc->stream.incnt; + info->sctpi_outstrms = asoc->stream.outcnt; list_for_each(pos, &asoc->base.inqueue.in_chunk_list) info->sctpi_inqueue++; list_for_each(pos, &asoc->outqueue.out_chunk_list) @@ -4727,8 +4727,8 @@ static int sctp_getsockopt_sctp_status(struct sock *sk, int len, status.sstat_unackdata = asoc->unack_data; status.sstat_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map); - status.sstat_instrms = asoc->stream->incnt; - status.sstat_outstrms = asoc->stream->outcnt; + status.sstat_instrms = asoc->stream.incnt; + status.sstat_outstrms = asoc->stream.outcnt; status.sstat_fragmentation_point = asoc->frag_point; status.sstat_primary.spinfo_assoc_id = sctp_assoc2id(transport->asoc); memcpy(&status.sstat_primary.spinfo_address, &transport->ipaddr, @@ -6600,10 +6600,10 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len, goto out; asoc = sctp_id2assoc(sk, params.sprstat_assoc_id); - if (!asoc || params.sprstat_sid >= asoc->stream->outcnt) + if (!asoc || params.sprstat_sid >= asoc->stream.outcnt) goto out; - streamout = &asoc->stream->out[params.sprstat_sid]; + streamout = &asoc->stream.out[params.sprstat_sid]; if (policy == SCTP_PR_SCTP_NONE) { params.sprstat_abandoned_unsent = 0; params.sprstat_abandoned_sent = 0; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index dda53a293986..af6b49850344 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -37,30 +37,23 @@ int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp) { - struct sctp_stream *stream; + struct sctp_stream *stream = &asoc->stream; int i; - stream = kzalloc(sizeof(*stream), gfp); - if (!stream) - return -ENOMEM; - stream->outcnt = asoc->c.sinit_num_ostreams; stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp); - if (!stream->out) { - kfree(stream); + if (!stream->out) return -ENOMEM; - } + for (i = 0; i < stream->outcnt; i++) stream->out[i].state = SCTP_STREAM_OPEN; - asoc->stream = stream; - return 0; } int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp) { - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; int i; /* Initial stream->out size may be very big, so free it and alloc @@ -70,7 +63,7 @@ int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp) stream->outcnt = asoc->c.sinit_num_ostreams; stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp); if (!stream->out) - goto nomem; + return -ENOMEM; for (i = 0; i < stream->outcnt; i++) stream->out[i].state = SCTP_STREAM_OPEN; @@ -79,26 +72,17 @@ int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp) stream->in = kcalloc(stream->incnt, sizeof(*stream->in), gfp); if (!stream->in) { kfree(stream->out); - goto nomem; + stream->out = NULL; + return -ENOMEM; } return 0; - -nomem: - asoc->stream = NULL; - kfree(stream); - - return -ENOMEM; } void sctp_stream_free(struct sctp_stream *stream) { - if (unlikely(!stream)) - return; - kfree(stream->out); kfree(stream->in); - kfree(stream); } void sctp_stream_clear(struct sctp_stream *stream) @@ -112,6 +96,19 @@ void sctp_stream_clear(struct sctp_stream *stream) stream->in[i].ssn = 0; } +void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) +{ + sctp_stream_free(stream); + + stream->out = new->out; + stream->in = new->in; + stream->outcnt = new->outcnt; + stream->incnt = new->incnt; + + new->out = NULL; + new->in = NULL; +} + static int sctp_send_reconf(struct sctp_association *asoc, struct sctp_chunk *chunk) { @@ -128,7 +125,7 @@ static int sctp_send_reconf(struct sctp_association *asoc, int sctp_send_reset_streams(struct sctp_association *asoc, struct sctp_reset_streams *params) { - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u16 i, str_nums, *str_list; struct sctp_chunk *chunk; int retval = -EINVAL; @@ -214,6 +211,7 @@ out: int sctp_send_reset_assoc(struct sctp_association *asoc) { + struct sctp_stream *stream = &asoc->stream; struct sctp_chunk *chunk = NULL; int retval; __u16 i; @@ -230,8 +228,8 @@ int sctp_send_reset_assoc(struct sctp_association *asoc) return -ENOMEM; /* Block further xmit of data until this request is completed */ - for (i = 0; i < asoc->stream->outcnt; i++) - asoc->stream->out[i].state = SCTP_STREAM_CLOSED; + for (i = 0; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_CLOSED; asoc->strreset_chunk = chunk; sctp_chunk_hold(asoc->strreset_chunk); @@ -241,8 +239,8 @@ int sctp_send_reset_assoc(struct sctp_association *asoc) sctp_chunk_put(asoc->strreset_chunk); asoc->strreset_chunk = NULL; - for (i = 0; i < asoc->stream->outcnt; i++) - asoc->stream->out[i].state = SCTP_STREAM_OPEN; + for (i = 0; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_OPEN; return retval; } @@ -255,7 +253,7 @@ int sctp_send_reset_assoc(struct sctp_association *asoc) int sctp_send_add_streams(struct sctp_association *asoc, struct sctp_add_streams *params) { - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; struct sctp_chunk *chunk = NULL; int retval = -ENOMEM; __u32 outcnt, incnt; @@ -357,7 +355,7 @@ struct sctp_chunk *sctp_process_strreset_outreq( struct sctp_ulpevent **evp) { struct sctp_strreset_outreq *outreq = param.v; - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u16 i, nums, flags = 0, *str_p = NULL; __u32 result = SCTP_STRRESET_DENIED; __u32 request_seq; @@ -449,7 +447,7 @@ struct sctp_chunk *sctp_process_strreset_inreq( struct sctp_ulpevent **evp) { struct sctp_strreset_inreq *inreq = param.v; - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; struct sctp_chunk *chunk = NULL; __u16 i, nums, *str_p; @@ -523,7 +521,7 @@ struct sctp_chunk *sctp_process_strreset_tsnreq( { __u32 init_tsn = 0, next_tsn = 0, max_tsn_seen; struct sctp_strreset_tsnreq *tsnreq = param.v; - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; __u32 request_seq; __u16 i; @@ -612,7 +610,7 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out( struct sctp_ulpevent **evp) { struct sctp_strreset_addstrm *addstrm = param.v; - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; struct sctp_stream_in *streamin; __u32 request_seq, incnt; @@ -687,7 +685,7 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in( struct sctp_ulpevent **evp) { struct sctp_strreset_addstrm *addstrm = param.v; - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; struct sctp_stream_out *streamout; struct sctp_chunk *chunk = NULL; @@ -758,8 +756,8 @@ struct sctp_chunk *sctp_process_strreset_resp( union sctp_params param, struct sctp_ulpevent **evp) { + struct sctp_stream *stream = &asoc->stream; struct sctp_strreset_resp *resp = param.v; - struct sctp_stream *stream = asoc->stream; struct sctp_transport *t; __u16 i, nums, flags = 0; sctp_paramhdr_t *req; diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index aa3624d50278..25f7e4140566 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -764,7 +764,7 @@ static void sctp_ulpq_retrieve_ordered(struct sctp_ulpq *ulpq, __u16 sid, csid, cssn; sid = event->stream; - stream = ulpq->asoc->stream; + stream = &ulpq->asoc->stream; event_list = (struct sk_buff_head *) sctp_event2skb(event)->prev; @@ -858,7 +858,7 @@ static struct sctp_ulpevent *sctp_ulpq_order(struct sctp_ulpq *ulpq, /* Note: The stream ID must be verified before this routine. */ sid = event->stream; ssn = event->ssn; - stream = ulpq->asoc->stream; + stream = &ulpq->asoc->stream; /* Is this the expected SSN for this stream ID? */ if (ssn != sctp_ssn_peek(stream, in, sid)) { @@ -893,7 +893,7 @@ static void sctp_ulpq_reap_ordered(struct sctp_ulpq *ulpq, __u16 sid) struct sk_buff_head *lobby = &ulpq->lobby; __u16 csid, cssn; - stream = ulpq->asoc->stream; + stream = &ulpq->asoc->stream; /* We are holding the chunks by stream, by SSN. */ skb_queue_head_init(&temp); @@ -958,7 +958,7 @@ void sctp_ulpq_skip(struct sctp_ulpq *ulpq, __u16 sid, __u16 ssn) struct sctp_stream *stream; /* Note: The stream ID must be verified before this routine. */ - stream = ulpq->asoc->stream; + stream = &ulpq->asoc->stream; /* Is this an old SSN? If so ignore. */ if (SSN_lt(ssn, sctp_ssn_peek(stream, in, sid))) -- cgit v1.3-14-g43fede From ff356414dc006170153c79434eb81d130c03beec Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 31 May 2017 16:36:32 +0800 Subject: sctp: merge sctp_stream_new and sctp_stream_init Since last patch, sctp doesn't need to alloc memory for asoc->stream any more. sctp_stream_new and sctp_stream_init both are used to alloc memory for stream.in or stream.out, and their names are also confusing. This patch is to merge them into sctp_stream_init, and only pass stream and streamcnt parameters into it, instead of the whole asoc. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 4 ++-- net/sctp/associola.c | 3 ++- net/sctp/sm_make_chunk.c | 3 ++- net/sctp/stream.c | 33 +++++++++++---------------------- 4 files changed, 17 insertions(+), 26 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index c8dbf410c4f5..5051317162df 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -377,8 +377,8 @@ typedef struct sctp_sender_hb_info { __u64 hb_nonce; } sctp_sender_hb_info_t; -int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp); -int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp); +int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, + gfp_t gfp); void sctp_stream_free(struct sctp_stream *stream); void sctp_stream_clear(struct sctp_stream *stream); void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 6625b15ab81a..288c5e0cda5d 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -246,7 +246,8 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a if (!sctp_ulpq_init(&asoc->ulpq, asoc)) goto fail_init; - if (sctp_stream_new(asoc, gfp)) + if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, + 0, gfp)) goto fail_init; /* Assume that peer would support both address types unless we are diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 244181413bca..bd439edf2d8a 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2454,7 +2454,8 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, * stream sequence number shall be set to 0. */ - if (sctp_stream_init(asoc, gfp)) + if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, + asoc->c.sinit_max_instreams, gfp)) goto clean_up; if (!asoc->temp && sctp_assoc_set_id(asoc, gfp)) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index af6b49850344..82e6d40052a8 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -35,47 +35,36 @@ #include #include -int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp) +int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, + gfp_t gfp) { - struct sctp_stream *stream = &asoc->stream; - int i; - - stream->outcnt = asoc->c.sinit_num_ostreams; - stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp); - if (!stream->out) - return -ENOMEM; - - for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_OPEN; - - return 0; -} - -int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp) -{ - struct sctp_stream *stream = &asoc->stream; int i; /* Initial stream->out size may be very big, so free it and alloc * a new one with new outcnt to save memory. */ kfree(stream->out); - stream->outcnt = asoc->c.sinit_num_ostreams; - stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp); + + stream->out = kcalloc(outcnt, sizeof(*stream->out), gfp); if (!stream->out) return -ENOMEM; + stream->outcnt = outcnt; for (i = 0; i < stream->outcnt; i++) stream->out[i].state = SCTP_STREAM_OPEN; - stream->incnt = asoc->c.sinit_max_instreams; - stream->in = kcalloc(stream->incnt, sizeof(*stream->in), gfp); + if (!incnt) + return 0; + + stream->in = kcalloc(incnt, sizeof(*stream->in), gfp); if (!stream->in) { kfree(stream->out); stream->out = NULL; return -ENOMEM; } + stream->incnt = incnt; + return 0; } -- cgit v1.3-14-g43fede From 518d8a2e9bad83c6040eccebc3d1f7388fc034e7 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 1 Jun 2017 21:37:37 +0300 Subject: net/flow_dissector: add support for dissection of misc ip header fields Add support for dissection of ip tos and ttl and ipv6 traffic-class and hoplimit. Both are dissected into the same struct. Uses similar call to ip dissection function as with tcp, arp and others. Signed-off-by: Or Gerlitz Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/flow_dissector.h | 11 +++++++++++ net/core/flow_dissector.c | 40 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+) (limited to 'include/net') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index efe34eec61dc..e2663e900b0a 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -165,6 +165,16 @@ struct flow_dissector_key_tcp { __be16 flags; }; +/** + * struct flow_dissector_key_ip: + * @tos: tos + * @ttl: ttl + */ +struct flow_dissector_key_ip { + __u8 tos; + __u8 ttl; +}; + enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */ @@ -186,6 +196,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_ENC_PORTS, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_MPLS, /* struct flow_dissector_key_mpls */ FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */ + FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */ FLOW_DISSECTOR_KEY_MAX, }; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 5a45943081f5..fc5fc4594c90 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -367,6 +367,40 @@ __skb_flow_dissect_tcp(const struct sk_buff *skb, key_tcp->flags = (*(__be16 *) &tcp_flag_word(th) & htons(0x0FFF)); } +static void +__skb_flow_dissect_ipv4(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, const struct iphdr *iph) +{ + struct flow_dissector_key_ip *key_ip; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP)) + return; + + key_ip = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IP, + target_container); + key_ip->tos = iph->tos; + key_ip->ttl = iph->ttl; +} + +static void +__skb_flow_dissect_ipv6(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, const struct ipv6hdr *iph) +{ + struct flow_dissector_key_ip *key_ip; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP)) + return; + + key_ip = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IP, + target_container); + key_ip->tos = ipv6_get_dsfield(iph); + key_ip->ttl = iph->hop_limit; +} + /** * __skb_flow_dissect - extract the flow_keys struct and return it * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified @@ -469,6 +503,9 @@ ip: } } + __skb_flow_dissect_ipv4(skb, flow_dissector, + target_container, data, iph); + if (flags & FLOW_DISSECTOR_F_STOP_AT_L3) goto out_good; @@ -514,6 +551,9 @@ ipv6: goto out_good; } + __skb_flow_dissect_ipv6(skb, flow_dissector, + target_container, data, iph); + if (flags & FLOW_DISSECTOR_F_STOP_AT_L3) goto out_good; -- cgit v1.3-14-g43fede From 14be36c2c96cd18cfa036f230b57ea78d82a303f Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 2 Jun 2017 12:31:23 -0700 Subject: net: dsa: Initialize all CPU and enabled ports masks in dsa_ds_parse() There was no reason for duplicating the code that initializes ds->enabled_port_mask in both dsa_parse_ports_dn() and dsa_parse_ports(), instead move this to dsa_ds_parse() which is early enough before ops->setup() has run. While at it, we can now make dsa_is_cpu_port() check ds->cpu_port_mask which is a step towards being multi-CPU port capable. Signed-off-by: Florian Fainelli Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 2 +- net/dsa/dsa2.c | 33 +++++++++++++++------------------ 2 files changed, 16 insertions(+), 19 deletions(-) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index 448d8bc77707..2effb0af9d7c 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -254,7 +254,7 @@ struct dsa_switch { static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) { - return ds->dst->cpu_dp == &ds->ports[p]; + return !!(ds->cpu_port_mask & (1 << p)); } static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 067daec644c1..cd13bb54a30c 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -250,8 +250,6 @@ static int dsa_cpu_port_apply(struct dsa_port *port) return err; } - ds->cpu_port_mask |= BIT(port->index); - memset(&port->devlink_port, 0, sizeof(port->devlink_port)); err = devlink_port_register(ds->devlink, &port->devlink_port, port->index); @@ -522,6 +520,12 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, dst->rcv = dst->tag_ops->rcv; + /* Initialize cpu_port_mask now for drv->setup() + * to have access to a correct value, just like what + * net/dsa/dsa.c::dsa_switch_setup_one does. + */ + ds->cpu_port_mask |= BIT(index); + return 0; } @@ -533,14 +537,22 @@ static int dsa_ds_parse(struct dsa_switch_tree *dst, struct dsa_switch *ds) for (index = 0; index < ds->num_ports; index++) { port = &ds->ports[index]; - if (!dsa_port_is_valid(port)) + if (!dsa_port_is_valid(port) || + dsa_port_is_dsa(port)) continue; if (dsa_port_is_cpu(port)) { err = dsa_cpu_parse(port, index, dst, ds); if (err) return err; + } else { + /* Initialize enabled_port_mask now for drv->setup() + * to have access to a correct value, just like what + * net/dsa/dsa.c::dsa_switch_setup_one does. + */ + ds->enabled_port_mask |= BIT(index); } + } pr_info("DSA: switch %d %d parsed\n", dst->tree, ds->index); @@ -589,13 +601,6 @@ static int dsa_parse_ports_dn(struct device_node *ports, struct dsa_switch *ds) return -EINVAL; ds->ports[reg].dn = port; - - /* Initialize enabled_port_mask now for ops->setup() - * to have access to a correct value, just like what - * net/dsa/dsa.c::dsa_switch_setup_one does. - */ - if (!dsa_port_is_cpu(&ds->ports[reg])) - ds->enabled_port_mask |= 1 << reg; } return 0; @@ -611,14 +616,6 @@ static int dsa_parse_ports(struct dsa_chip_data *cd, struct dsa_switch *ds) continue; ds->ports[i].name = cd->port_names[i]; - - /* Initialize enabled_port_mask now for drv->setup() - * to have access to a correct value, just like what - * net/dsa/dsa.c::dsa_switch_setup_one does. - */ - if (!dsa_port_is_cpu(&ds->ports[i])) - ds->enabled_port_mask |= 1 << i; - valid_name_found = true; } -- cgit v1.3-14-g43fede From 5071034e4af709d6783b7d105dc296a5cc84739b Mon Sep 17 00:00:00 2001 From: Sowmini Varadhan Date: Fri, 2 Jun 2017 09:01:49 -0700 Subject: neigh: Really delete an arp/neigh entry on "ip neigh delete" or "arp -d" The command # arp -s 62.2.0.1 a:b:c:d:e:f dev eth2 adds an entry like the following (listed by "arp -an") ? (62.2.0.1) at 0a:0b:0c:0d:0e:0f [ether] PERM on eth2 but the symmetric deletion command # arp -i eth2 -d 62.2.0.1 does not remove the PERM entry from the table, and instead leaves behind ? (62.2.0.1) at on eth2 The reason is that there is a refcnt of 1 for the arp_tbl itself (neigh_alloc starts off the entry with a refcnt of 1), thus the neigh_release() call from arp_invalidate() will (at best) just decrement the ref to 1, but will never actually free it from the table. To fix this, we need to do something like neigh_forced_gc: if the refcnt is 1 (i.e., on the table's ref), remove the entry from the table and free it. This patch refactors and shares common code between neigh_forced_gc and the newly added neigh_remove_one. A similar issue exists for IPv6 Neighbor Cache entries, and is fixed in a similar manner by this patch. Signed-off-by: Sowmini Varadhan Reviewed-by: Julian Anastasov Signed-off-by: David S. Miller --- include/net/neighbour.h | 1 + net/core/neighbour.c | 60 ++++++++++++++++++++++++++++++++++++++++--------- net/ipv4/arp.c | 4 ++++ 3 files changed, 54 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index e4dd3a214034..639b67564a7d 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -317,6 +317,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb); int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid); void __neigh_set_probe_once(struct neighbour *neigh); +bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl); void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev); int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index d274f81fcc2c..dadb5eef91c3 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -118,6 +118,50 @@ unsigned long neigh_rand_reach_time(unsigned long base) EXPORT_SYMBOL(neigh_rand_reach_time); +static bool neigh_del(struct neighbour *n, __u8 state, + struct neighbour __rcu **np, struct neigh_table *tbl) +{ + bool retval = false; + + write_lock(&n->lock); + if (atomic_read(&n->refcnt) == 1 && !(n->nud_state & state)) { + struct neighbour *neigh; + + neigh = rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock)); + rcu_assign_pointer(*np, neigh); + n->dead = 1; + retval = true; + } + write_unlock(&n->lock); + if (retval) + neigh_cleanup_and_release(n); + return retval; +} + +bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl) +{ + struct neigh_hash_table *nht; + void *pkey = ndel->primary_key; + u32 hash_val; + struct neighbour *n; + struct neighbour __rcu **np; + + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); + hash_val = tbl->hash(pkey, ndel->dev, nht->hash_rnd); + hash_val = hash_val >> (32 - nht->hash_shift); + + np = &nht->hash_buckets[hash_val]; + while ((n = rcu_dereference_protected(*np, + lockdep_is_held(&tbl->lock)))) { + if (n == ndel) + return neigh_del(n, 0, np, tbl); + np = &n->next; + } + return false; +} + static int neigh_forced_gc(struct neigh_table *tbl) { int shrunk = 0; @@ -140,19 +184,10 @@ static int neigh_forced_gc(struct neigh_table *tbl) * - nobody refers to it. * - it is not permanent */ - write_lock(&n->lock); - if (atomic_read(&n->refcnt) == 1 && - !(n->nud_state & NUD_PERMANENT)) { - rcu_assign_pointer(*np, - rcu_dereference_protected(n->next, - lockdep_is_held(&tbl->lock))); - n->dead = 1; - shrunk = 1; - write_unlock(&n->lock); - neigh_cleanup_and_release(n); + if (neigh_del(n, NUD_PERMANENT, np, tbl)) { + shrunk = 1; continue; } - write_unlock(&n->lock); np = &n->next; } } @@ -1649,7 +1684,10 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN, NETLINK_CB(skb).portid); + write_lock_bh(&tbl->lock); neigh_release(neigh); + neigh_remove_one(neigh, tbl); + write_unlock_bh(&tbl->lock); out: return err; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index e9f3386a528b..a651c53260ec 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1113,13 +1113,17 @@ static int arp_invalidate(struct net_device *dev, __be32 ip) { struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev); int err = -ENXIO; + struct neigh_table *tbl = &arp_tbl; if (neigh) { if (neigh->nud_state & ~NUD_NOARP) err = neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_ADMIN, 0); + write_lock_bh(&tbl->lock); neigh_release(neigh); + neigh_remove_one(neigh, tbl); + write_unlock_bh(&tbl->lock); } return err; -- cgit v1.3-14-g43fede From 77d4b1d36926a9b8387c6b53eeba42bcaaffcea3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 3 Jun 2017 09:29:25 -0700 Subject: net: ping: do not abuse udp_poll() Alexander reported various KASAN messages triggered in recent kernels The problem is that ping sockets should not use udp_poll() in the first place, and recent changes in UDP stack finally exposed this old bug. Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind") Fixes: 6d0bfe226116 ("net: ipv6: Add IPv6 support to the ping socket.") Signed-off-by: Eric Dumazet Reported-by: Sasha Levin Cc: Solar Designer Cc: Vasiliy Kulikov Cc: Lorenzo Colitti Acked-By: Lorenzo Colitti Tested-By: Lorenzo Colitti Signed-off-by: David S. Miller --- include/net/ipv6.h | 1 + net/ipv4/af_inet.c | 2 +- net/ipv6/ping.c | 2 +- net/ipv6/raw.c | 2 +- 4 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index dbf0abba33b8..3e505bbff8ca 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1007,6 +1007,7 @@ int inet6_hash_connect(struct inet_timewait_death_row *death_row, */ extern const struct proto_ops inet6_stream_ops; extern const struct proto_ops inet6_dgram_ops; +extern const struct proto_ops inet6_sockraw_ops; struct group_source_req; struct group_filter; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f3dad1661343..58925b6597de 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1043,7 +1043,7 @@ static struct inet_protosw inetsw_array[] = .type = SOCK_DGRAM, .protocol = IPPROTO_ICMP, .prot = &ping_prot, - .ops = &inet_dgram_ops, + .ops = &inet_sockraw_ops, .flags = INET_PROTOSW_REUSE, }, diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 9b522fa90e6d..ac826dd338ff 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -192,7 +192,7 @@ static struct inet_protosw pingv6_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_ICMPV6, .prot = &pingv6_prot, - .ops = &inet6_dgram_ops, + .ops = &inet6_sockraw_ops, .flags = INET_PROTOSW_REUSE, }; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 1f992d9e261d..60be012fe708 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1338,7 +1338,7 @@ void raw6_proc_exit(void) #endif /* CONFIG_PROC_FS */ /* Same as inet6_dgram_ops, sans udp_poll. */ -static const struct proto_ops inet6_sockraw_ops = { +const struct proto_ops inet6_sockraw_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, -- cgit v1.3-14-g43fede From 1e0ce2a1ee0d5fb334e82e80600f1e8e77df525c Mon Sep 17 00:00:00 2001 From: Anmol Sarma Date: Sat, 3 Jun 2017 17:40:54 +0530 Subject: net: Update TCP congestion control documentation Update tcp.txt to fix mandatory congestion control ops and default CCA selection. Also, fix comment in tcp.h for undo_cwnd. Signed-off-by: Anmol Sarma Signed-off-by: David S. Miller --- Documentation/networking/tcp.txt | 31 +++++++++++++------------------ include/net/tcp.h | 2 +- 2 files changed, 14 insertions(+), 19 deletions(-) (limited to 'include/net') diff --git a/Documentation/networking/tcp.txt b/Documentation/networking/tcp.txt index bdc4c0db51e1..9c7139d57e57 100644 --- a/Documentation/networking/tcp.txt +++ b/Documentation/networking/tcp.txt @@ -1,7 +1,7 @@ TCP protocol ============ -Last updated: 9 February 2008 +Last updated: 3 June 2017 Contents ======== @@ -29,18 +29,19 @@ As of 2.6.13, Linux supports pluggable congestion control algorithms. A congestion control mechanism can be registered through functions in tcp_cong.c. The functions used by the congestion control mechanism are registered via passing a tcp_congestion_ops struct to -tcp_register_congestion_control. As a minimum name, ssthresh, -cong_avoid must be valid. +tcp_register_congestion_control. As a minimum, the congestion control +mechanism must provide a valid name and must implement either ssthresh, +cong_avoid and undo_cwnd hooks or the "omnipotent" cong_control hook. Private data for a congestion control mechanism is stored in tp->ca_priv. tcp_ca(tp) returns a pointer to this space. This is preallocated space - it is important to check the size of your private data will fit this space, or -alternatively space could be allocated elsewhere and a pointer to it could +alternatively, space could be allocated elsewhere and a pointer to it could be stored here. There are three kinds of congestion control algorithms currently: The simplest ones are derived from TCP reno (highspeed, scalable) and just -provide an alternative the congestion window calculation. More complex +provide an alternative congestion window calculation. More complex ones like BIC try to look at other events to provide better heuristics. There are also round trip time based algorithms like Vegas and Westwood+. @@ -49,21 +50,15 @@ Good TCP congestion control is a complex problem because the algorithm needs to maintain fairness and performance. Please review current research and RFC's before developing new modules. -The method that is used to determine which congestion control mechanism is -determined by the setting of the sysctl net.ipv4.tcp_congestion_control. -The default congestion control will be the last one registered (LIFO); -so if you built everything as modules, the default will be reno. If you -build with the defaults from Kconfig, then CUBIC will be builtin (not a -module) and it will end up the default. +The default congestion control mechanism is chosen based on the +DEFAULT_TCP_CONG Kconfig parameter. If you really want a particular default +value then you can set it using sysctl net.ipv4.tcp_congestion_control. The +module will be autoloaded if needed and you will get the expected protocol. If +you ask for an unknown congestion method, then the sysctl attempt will fail. -If you really want a particular default value then you will need -to set it with the sysctl. If you use a sysctl, the module will be autoloaded -if needed and you will get the expected protocol. If you ask for an -unknown congestion method, then the sysctl attempt will fail. - -If you remove a tcp congestion control module, then you will get the next +If you remove a TCP congestion control module, then you will get the next available one. Since reno cannot be built as a module, and cannot be -deleted, it will always be available. +removed, it will always be available. How the new TCP output machine [nyi] works. =========================================== diff --git a/include/net/tcp.h b/include/net/tcp.h index 38a7427ae902..be6223c586fa 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -924,7 +924,7 @@ struct tcp_congestion_ops { void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev); /* call when ack arrives (optional) */ void (*in_ack_event)(struct sock *sk, u32 flags); - /* new value of cwnd after loss (optional) */ + /* new value of cwnd after loss (required) */ u32 (*undo_cwnd)(struct sock *sk); /* hook for packet ack accounting (optional) */ void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample); -- cgit v1.3-14-g43fede From 4e2ec43654f240a3731612764850140f669d1b4b Mon Sep 17 00:00:00 2001 From: "Rosen, Rami" Date: Sun, 4 Jun 2017 15:20:01 +0300 Subject: genetlink: remove ops_list from genetlink header. commit d91824c08fbc ("genetlink: register family ops as array") removed the ops_list member from both genl_family and genl_ops; while the documentation of genl_family was updated accordingly by this patch, ops_list remained in the documentation of the genl_ops object. This patch fixes it by removing ops_list from genl_ops documentation. Signed-off-by: Rami Rosen Signed-off-by: David S. Miller --- include/net/genetlink.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/net') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 68b88192b00c..c59a098221db 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -128,7 +128,6 @@ static inline int genl_err_attr(struct genl_info *info, int err, * @start: start callback for dumps * @dumpit: callback for dumpers * @done: completion callback for dumps - * @ops_list: operations list */ struct genl_ops { const struct nla_policy *policy; -- cgit v1.3-14-g43fede From 5a4d1fee2f844813cb2092b7a06b0e20ed9e2fa4 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 6 Jun 2017 14:12:03 +0200 Subject: net: sched: introduce helper to identify gact trap action Introduce a helper called is_tcf_gact_trap which could be used to tell if the action is gact trap or not. Signed-off-by: Jiri Pirko Reviewed-by: Yotam Gigi Signed-off-by: David S. Miller --- include/net/tc_act/tc_gact.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h index b6f173910226..d576374c4d6f 100644 --- a/include/net/tc_act/tc_gact.h +++ b/include/net/tc_act/tc_gact.h @@ -15,7 +15,7 @@ struct tcf_gact { }; #define to_gact(a) ((struct tcf_gact *)a) -static inline bool is_tcf_gact_shot(const struct tc_action *a) +static inline bool __is_tcf_gact_act(const struct tc_action *a, int act) { #ifdef CONFIG_NET_CLS_ACT struct tcf_gact *gact; @@ -24,10 +24,21 @@ static inline bool is_tcf_gact_shot(const struct tc_action *a) return false; gact = to_gact(a); - if (gact->tcf_action == TC_ACT_SHOT) + if (gact->tcf_action == act) return true; #endif return false; } + +static inline bool is_tcf_gact_shot(const struct tc_action *a) +{ + return __is_tcf_gact_act(a, TC_ACT_SHOT); +} + +static inline bool is_tcf_gact_trap(const struct tc_action *a) +{ + return __is_tcf_gact_act(a, TC_ACT_TRAP); +} + #endif /* __NET_TC_GACT_H */ -- cgit v1.3-14-g43fede