From 8ac6c7a54ed1b98d142dce24b11c6de6a1e239a5 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 22 Oct 2024 10:36:11 +0000
Subject: [PATCH] 修改4g拨号为QMI,需要在系统里后台执行quectel-CM
---
kernel/net/sched/cls_flower.c | 1775 ++++++++++++++++++++++++++++++++++++++++++++++++++--------
1 files changed, 1,512 insertions(+), 263 deletions(-)
diff --git a/kernel/net/sched/cls_flower.c b/kernel/net/sched/cls_flower.c
index 208436e..dcf21d9 100644
--- a/kernel/net/sched/cls_flower.c
+++ b/kernel/net/sched/cls_flower.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* net/sched/cls_flower.c Flower classifier
*
* Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
- *
- * 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 <linux/kernel.h>
@@ -14,6 +10,7 @@
#include <linux/module.h>
#include <linux/rhashtable.h>
#include <linux/workqueue.h>
+#include <linux/refcount.h>
#include <linux/if_ether.h>
#include <linux/in6.h>
@@ -25,12 +22,21 @@
#include <net/ip.h>
#include <net/flow_dissector.h>
#include <net/geneve.h>
+#include <net/vxlan.h>
+#include <net/erspan.h>
#include <net/dst.h>
#include <net/dst_metadata.h>
+#include <uapi/linux/netfilter/nf_conntrack_common.h>
+
+#define TCA_FLOWER_KEY_CT_FLAGS_MAX \
+ ((__TCA_FLOWER_KEY_CT_FLAGS_MAX - 1) << 1)
+#define TCA_FLOWER_KEY_CT_FLAGS_MASK \
+ (TCA_FLOWER_KEY_CT_FLAGS_MAX - 1)
+
struct fl_flow_key {
- int indev_ifindex;
+ struct flow_dissector_key_meta meta;
struct flow_dissector_key_control control;
struct flow_dissector_key_control enc_control;
struct flow_dissector_key_basic basic;
@@ -55,6 +61,15 @@
struct flow_dissector_key_ip ip;
struct flow_dissector_key_ip enc_ip;
struct flow_dissector_key_enc_opts enc_opts;
+ union {
+ struct flow_dissector_key_ports tp;
+ struct {
+ struct flow_dissector_key_ports tp_min;
+ struct flow_dissector_key_ports tp_max;
+ };
+ } tp_range;
+ struct flow_dissector_key_ct ct;
+ struct flow_dissector_key_hash hash;
} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
struct fl_flow_mask_range {
@@ -65,6 +80,7 @@
struct fl_flow_mask {
struct fl_flow_key key;
struct fl_flow_mask_range range;
+ u32 flags;
struct rhash_head ht_node;
struct rhashtable ht;
struct rhashtable_params filter_ht_params;
@@ -72,6 +88,7 @@
struct list_head filters;
struct rcu_work rwork;
struct list_head list;
+ refcount_t refcnt;
};
struct fl_flow_tmplt {
@@ -83,7 +100,9 @@
struct cls_fl_head {
struct rhashtable ht;
+ spinlock_t masks_lock; /* Protect masks list */
struct list_head masks;
+ struct list_head hw_filters;
struct rcu_work rwork;
struct idr handle_idr;
};
@@ -96,11 +115,18 @@
struct tcf_result res;
struct fl_flow_key key;
struct list_head list;
+ struct list_head hw_list;
u32 handle;
u32 flags;
- unsigned int in_hw_count;
+ u32 in_hw_count;
struct rcu_work rwork;
struct net_device *hw_dev;
+ /* Flower classifier is unlocked, which means that its reference counter
+ * can be changed concurrently without any kind of external
+ * synchronization. Use atomic reference counter to be concurrency-safe.
+ */
+ refcount_t refcnt;
+ bool deleted;
};
static const struct rhashtable_params mask_ht_params = {
@@ -179,37 +205,129 @@
memset(fl_key_get_start(key, mask), 0, fl_mask_range(mask));
}
-static struct cls_fl_filter *fl_lookup(struct fl_flow_mask *mask,
- struct fl_flow_key *mkey)
+static bool fl_range_port_dst_cmp(struct cls_fl_filter *filter,
+ struct fl_flow_key *key,
+ struct fl_flow_key *mkey)
+{
+ u16 min_mask, max_mask, min_val, max_val;
+
+ min_mask = ntohs(filter->mask->key.tp_range.tp_min.dst);
+ max_mask = ntohs(filter->mask->key.tp_range.tp_max.dst);
+ min_val = ntohs(filter->key.tp_range.tp_min.dst);
+ max_val = ntohs(filter->key.tp_range.tp_max.dst);
+
+ if (min_mask && max_mask) {
+ if (ntohs(key->tp_range.tp.dst) < min_val ||
+ ntohs(key->tp_range.tp.dst) > max_val)
+ return false;
+
+ /* skb does not have min and max values */
+ mkey->tp_range.tp_min.dst = filter->mkey.tp_range.tp_min.dst;
+ mkey->tp_range.tp_max.dst = filter->mkey.tp_range.tp_max.dst;
+ }
+ return true;
+}
+
+static bool fl_range_port_src_cmp(struct cls_fl_filter *filter,
+ struct fl_flow_key *key,
+ struct fl_flow_key *mkey)
+{
+ u16 min_mask, max_mask, min_val, max_val;
+
+ min_mask = ntohs(filter->mask->key.tp_range.tp_min.src);
+ max_mask = ntohs(filter->mask->key.tp_range.tp_max.src);
+ min_val = ntohs(filter->key.tp_range.tp_min.src);
+ max_val = ntohs(filter->key.tp_range.tp_max.src);
+
+ if (min_mask && max_mask) {
+ if (ntohs(key->tp_range.tp.src) < min_val ||
+ ntohs(key->tp_range.tp.src) > max_val)
+ return false;
+
+ /* skb does not have min and max values */
+ mkey->tp_range.tp_min.src = filter->mkey.tp_range.tp_min.src;
+ mkey->tp_range.tp_max.src = filter->mkey.tp_range.tp_max.src;
+ }
+ return true;
+}
+
+static struct cls_fl_filter *__fl_lookup(struct fl_flow_mask *mask,
+ struct fl_flow_key *mkey)
{
return rhashtable_lookup_fast(&mask->ht, fl_key_get_start(mkey, mask),
mask->filter_ht_params);
}
+static struct cls_fl_filter *fl_lookup_range(struct fl_flow_mask *mask,
+ struct fl_flow_key *mkey,
+ struct fl_flow_key *key)
+{
+ struct cls_fl_filter *filter, *f;
+
+ list_for_each_entry_rcu(filter, &mask->filters, list) {
+ if (!fl_range_port_dst_cmp(filter, key, mkey))
+ continue;
+
+ if (!fl_range_port_src_cmp(filter, key, mkey))
+ continue;
+
+ f = __fl_lookup(mask, mkey);
+ if (f)
+ return f;
+ }
+ return NULL;
+}
+
+static noinline_for_stack
+struct cls_fl_filter *fl_mask_lookup(struct fl_flow_mask *mask, struct fl_flow_key *key)
+{
+ struct fl_flow_key mkey;
+
+ fl_set_masked_key(&mkey, key, mask);
+ if ((mask->flags & TCA_FLOWER_MASK_FLAGS_RANGE))
+ return fl_lookup_range(mask, &mkey, key);
+
+ return __fl_lookup(mask, &mkey);
+}
+
+static u16 fl_ct_info_to_flower_map[] = {
+ [IP_CT_ESTABLISHED] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+ TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED,
+ [IP_CT_RELATED] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+ TCA_FLOWER_KEY_CT_FLAGS_RELATED,
+ [IP_CT_ESTABLISHED_REPLY] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+ TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED,
+ [IP_CT_RELATED_REPLY] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+ TCA_FLOWER_KEY_CT_FLAGS_RELATED,
+ [IP_CT_NEW] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+ TCA_FLOWER_KEY_CT_FLAGS_NEW,
+};
+
static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
struct cls_fl_head *head = rcu_dereference_bh(tp->root);
- struct cls_fl_filter *f;
- struct fl_flow_mask *mask;
struct fl_flow_key skb_key;
- struct fl_flow_key skb_mkey;
+ struct fl_flow_mask *mask;
+ struct cls_fl_filter *f;
list_for_each_entry_rcu(mask, &head->masks, list) {
flow_dissector_init_keys(&skb_key.control, &skb_key.basic);
fl_clear_masked_range(&skb_key, mask);
- skb_key.indev_ifindex = skb->skb_iif;
+ skb_flow_dissect_meta(skb, &mask->dissector, &skb_key);
/* skb_flow_dissect() does not set n_proto in case an unknown
* protocol, so do it rather here.
*/
skb_key.basic.n_proto = skb_protocol(skb, false);
skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key);
+ skb_flow_dissect_ct(skb, &mask->dissector, &skb_key,
+ fl_ct_info_to_flower_map,
+ ARRAY_SIZE(fl_ct_info_to_flower_map));
+ skb_flow_dissect_hash(skb, &mask->dissector, &skb_key);
skb_flow_dissect(skb, &mask->dissector, &skb_key, 0);
- fl_set_masked_key(&skb_mkey, &skb_key, mask);
-
- f = fl_lookup(mask, &skb_mkey);
+ f = fl_mask_lookup(mask, &skb_key);
if (f && !tc_skip_sw(f->flags)) {
*res = f->res;
return tcf_exts_exec(skb, &f->exts, res);
@@ -226,16 +344,22 @@
if (!head)
return -ENOBUFS;
+ spin_lock_init(&head->masks_lock);
INIT_LIST_HEAD_RCU(&head->masks);
+ INIT_LIST_HEAD(&head->hw_filters);
rcu_assign_pointer(tp->root, head);
idr_init(&head->handle_idr);
return rhashtable_init(&head->ht, &mask_ht_params);
}
-static void fl_mask_free(struct fl_flow_mask *mask)
+static void fl_mask_free(struct fl_flow_mask *mask, bool mask_init_done)
{
- rhashtable_destroy(&mask->ht);
+ /* temporary masks don't have their filters list and ht initialized */
+ if (mask_init_done) {
+ WARN_ON(!list_empty(&mask->filters));
+ rhashtable_destroy(&mask->ht);
+ }
kfree(mask);
}
@@ -244,23 +368,41 @@
struct fl_flow_mask *mask = container_of(to_rcu_work(work),
struct fl_flow_mask, rwork);
- fl_mask_free(mask);
+ fl_mask_free(mask, true);
}
-static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask,
- bool async)
+static void fl_uninit_mask_free_work(struct work_struct *work)
{
- if (!list_empty(&mask->filters))
+ struct fl_flow_mask *mask = container_of(to_rcu_work(work),
+ struct fl_flow_mask, rwork);
+
+ fl_mask_free(mask, false);
+}
+
+static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask)
+{
+ if (!refcount_dec_and_test(&mask->refcnt))
return false;
rhashtable_remove_fast(&head->ht, &mask->ht_node, mask_ht_params);
+
+ spin_lock(&head->masks_lock);
list_del_rcu(&mask->list);
- if (async)
- tcf_queue_work(&mask->rwork, fl_mask_free_work);
- else
- fl_mask_free(mask);
+ spin_unlock(&head->masks_lock);
+
+ tcf_queue_work(&mask->rwork, fl_mask_free_work);
return true;
+}
+
+static struct cls_fl_head *fl_head_dereference(struct tcf_proto *tp)
+{
+ /* Flower classifier only changes root pointer during init and destroy.
+ * Users must obtain reference to tcf_proto instance before calling its
+ * API, so tp->root pointer is protected from concurrent call to
+ * fl_destroy() by reference counting.
+ */
+ return rcu_dereference_raw(tp->root);
}
static void __fl_destroy_filter(struct cls_fl_filter *f)
@@ -275,52 +417,63 @@
struct cls_fl_filter *f = container_of(to_rcu_work(work),
struct cls_fl_filter, rwork);
- rtnl_lock();
__fl_destroy_filter(f);
- rtnl_unlock();
}
static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
- struct tc_cls_flower_offload cls_flower = {};
struct tcf_block *block = tp->chain->block;
+ struct flow_cls_offload cls_flower = {};
tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack);
- cls_flower.command = TC_CLSFLOWER_DESTROY;
+ cls_flower.command = FLOW_CLS_DESTROY;
cls_flower.cookie = (unsigned long) f;
- tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER,
- &cls_flower, false);
- tcf_block_offload_dec(block, &f->flags);
+ tc_setup_cb_destroy(block, tp, TC_SETUP_CLSFLOWER, &cls_flower, false,
+ &f->flags, &f->in_hw_count, rtnl_held);
+
}
static int fl_hw_replace_filter(struct tcf_proto *tp,
- struct cls_fl_filter *f,
+ struct cls_fl_filter *f, bool rtnl_held,
struct netlink_ext_ack *extack)
{
- struct tc_cls_flower_offload cls_flower = {};
struct tcf_block *block = tp->chain->block;
+ struct flow_cls_offload cls_flower = {};
bool skip_sw = tc_skip_sw(f->flags);
- int err;
+ int err = 0;
+
+ cls_flower.rule = flow_rule_alloc(tcf_exts_num_actions(&f->exts));
+ if (!cls_flower.rule)
+ return -ENOMEM;
tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack);
- cls_flower.command = TC_CLSFLOWER_REPLACE;
+ cls_flower.command = FLOW_CLS_REPLACE;
cls_flower.cookie = (unsigned long) f;
- cls_flower.dissector = &f->mask->dissector;
- cls_flower.mask = &f->mask->key;
- cls_flower.key = &f->mkey;
- cls_flower.exts = &f->exts;
+ cls_flower.rule->match.dissector = &f->mask->dissector;
+ cls_flower.rule->match.mask = &f->mask->key;
+ cls_flower.rule->match.key = &f->mkey;
cls_flower.classid = f->res.classid;
- err = tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER,
- &cls_flower, skip_sw);
- if (err < 0) {
- fl_hw_destroy_filter(tp, f, NULL);
+ err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts);
+ if (err) {
+ kfree(cls_flower.rule);
+ if (skip_sw) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action");
+ return err;
+ }
+ return 0;
+ }
+
+ err = tc_setup_cb_add(block, tp, TC_SETUP_CLSFLOWER, &cls_flower,
+ skip_sw, &f->flags, &f->in_hw_count, rtnl_held);
+ tc_cleanup_flow_action(&cls_flower.rule->action);
+ kfree(cls_flower.rule);
+
+ if (err) {
+ fl_hw_destroy_filter(tp, f, rtnl_held, NULL);
return err;
- } else if (err > 0) {
- f->in_hw_count = err;
- tcf_block_offload_inc(block, &f->flags);
}
if (skip_sw && !(f->flags & TCA_CLS_FLAGS_IN_HW))
@@ -329,40 +482,80 @@
return 0;
}
-static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
+static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f,
+ bool rtnl_held)
{
- struct tc_cls_flower_offload cls_flower = {};
struct tcf_block *block = tp->chain->block;
+ struct flow_cls_offload cls_flower = {};
tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, NULL);
- cls_flower.command = TC_CLSFLOWER_STATS;
+ cls_flower.command = FLOW_CLS_STATS;
cls_flower.cookie = (unsigned long) f;
- cls_flower.exts = &f->exts;
cls_flower.classid = f->res.classid;
- tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER,
- &cls_flower, false);
+ tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false,
+ rtnl_held);
+
+ tcf_exts_stats_update(&f->exts, cls_flower.stats.bytes,
+ cls_flower.stats.pkts,
+ cls_flower.stats.drops,
+ cls_flower.stats.lastused,
+ cls_flower.stats.used_hw_stats,
+ cls_flower.stats.used_hw_stats_valid);
}
-static bool __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f,
- struct netlink_ext_ack *extack)
+static void __fl_put(struct cls_fl_filter *f)
{
- struct cls_fl_head *head = rtnl_dereference(tp->root);
- bool async = tcf_exts_get_net(&f->exts);
- bool last;
+ if (!refcount_dec_and_test(&f->refcnt))
+ return;
- idr_remove(&head->handle_idr, f->handle);
- list_del_rcu(&f->list);
- last = fl_mask_put(head, f->mask, async);
- if (!tc_skip_hw(f->flags))
- fl_hw_destroy_filter(tp, f, extack);
- tcf_unbind_filter(tp, &f->res);
- if (async)
+ if (tcf_exts_get_net(&f->exts))
tcf_queue_work(&f->rwork, fl_destroy_filter_work);
else
__fl_destroy_filter(f);
+}
- return last;
+static struct cls_fl_filter *__fl_get(struct cls_fl_head *head, u32 handle)
+{
+ struct cls_fl_filter *f;
+
+ rcu_read_lock();
+ f = idr_find(&head->handle_idr, handle);
+ if (f && !refcount_inc_not_zero(&f->refcnt))
+ f = NULL;
+ rcu_read_unlock();
+
+ return f;
+}
+
+static int __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f,
+ bool *last, bool rtnl_held,
+ struct netlink_ext_ack *extack)
+{
+ struct cls_fl_head *head = fl_head_dereference(tp);
+
+ *last = false;
+
+ spin_lock(&tp->lock);
+ if (f->deleted) {
+ spin_unlock(&tp->lock);
+ return -ENOENT;
+ }
+
+ f->deleted = true;
+ rhashtable_remove_fast(&f->mask->ht, &f->ht_node,
+ f->mask->filter_ht_params);
+ idr_remove(&head->handle_idr, f->handle);
+ list_del_rcu(&f->list);
+ spin_unlock(&tp->lock);
+
+ *last = fl_mask_put(head, f->mask);
+ if (!tc_skip_hw(f->flags))
+ fl_hw_destroy_filter(tp, f, rtnl_held, extack);
+ tcf_unbind_filter(tp, &f->res);
+ __fl_put(f);
+
+ return 0;
}
static void fl_destroy_sleepable(struct work_struct *work)
@@ -376,15 +569,18 @@
module_put(THIS_MODULE);
}
-static void fl_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
+static void fl_destroy(struct tcf_proto *tp, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
- struct cls_fl_head *head = rtnl_dereference(tp->root);
+ struct cls_fl_head *head = fl_head_dereference(tp);
struct fl_flow_mask *mask, *next_mask;
struct cls_fl_filter *f, *next;
+ bool last;
list_for_each_entry_safe(mask, next_mask, &head->masks, list) {
list_for_each_entry_safe(f, next, &mask->filters, list) {
- if (__fl_delete(tp, f, extack))
+ __fl_delete(tp, f, &last, rtnl_held, extack);
+ if (last)
break;
}
}
@@ -394,11 +590,18 @@
tcf_queue_work(&head->rwork, fl_destroy_sleepable);
}
+static void fl_put(struct tcf_proto *tp, void *arg)
+{
+ struct cls_fl_filter *f = arg;
+
+ __fl_put(f);
+}
+
static void *fl_get(struct tcf_proto *tp, u32 handle)
{
- struct cls_fl_head *head = rtnl_dereference(tp->root);
+ struct cls_fl_head *head = fl_head_dereference(tp);
- return idr_find(&head->handle_idr, handle);
+ return __fl_get(head, handle);
}
static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
@@ -472,6 +675,7 @@
[TCA_FLOWER_KEY_MPLS_BOS] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_MPLS_TC] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_MPLS_LABEL] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_MPLS_OPTS] = { .type = NLA_NESTED },
[TCA_FLOWER_KEY_TCP_FLAGS] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_TCP_FLAGS_MASK] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_IP_TOS] = { .type = NLA_U8 },
@@ -487,12 +691,31 @@
[TCA_FLOWER_KEY_ENC_IP_TTL_MASK] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_ENC_OPTS] = { .type = NLA_NESTED },
[TCA_FLOWER_KEY_ENC_OPTS_MASK] = { .type = NLA_NESTED },
+ [TCA_FLOWER_KEY_CT_STATE] =
+ NLA_POLICY_MASK(NLA_U16, TCA_FLOWER_KEY_CT_FLAGS_MASK),
+ [TCA_FLOWER_KEY_CT_STATE_MASK] =
+ NLA_POLICY_MASK(NLA_U16, TCA_FLOWER_KEY_CT_FLAGS_MASK),
+ [TCA_FLOWER_KEY_CT_ZONE] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_CT_ZONE_MASK] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_CT_MARK] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_CT_MARK_MASK] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_CT_LABELS] = { .type = NLA_BINARY,
+ .len = 128 / BITS_PER_BYTE },
+ [TCA_FLOWER_KEY_CT_LABELS_MASK] = { .type = NLA_BINARY,
+ .len = 128 / BITS_PER_BYTE },
[TCA_FLOWER_FLAGS] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_HASH] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_HASH_MASK] = { .type = NLA_U32 },
+
};
static const struct nla_policy
enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = {
+ [TCA_FLOWER_KEY_ENC_OPTS_UNSPEC] = {
+ .strict_start_type = TCA_FLOWER_KEY_ENC_OPTS_VXLAN },
[TCA_FLOWER_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED },
+ [TCA_FLOWER_KEY_ENC_OPTS_VXLAN] = { .type = NLA_NESTED },
+ [TCA_FLOWER_KEY_ENC_OPTS_ERSPAN] = { .type = NLA_NESTED },
};
static const struct nla_policy
@@ -503,50 +726,281 @@
.len = 128 },
};
+static const struct nla_policy
+vxlan_opt_policy[TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX + 1] = {
+ [TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP] = { .type = NLA_U32 },
+};
+
+static const struct nla_policy
+erspan_opt_policy[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX + 1] = {
+ [TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID] = { .type = NLA_U8 },
+};
+
+static const struct nla_policy
+mpls_stack_entry_policy[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1] = {
+ [TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_MPLS_OPT_LSE_TC] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL] = { .type = NLA_U32 },
+};
+
static void fl_set_key_val(struct nlattr **tb,
void *val, int val_type,
void *mask, int mask_type, int len)
{
if (!tb[val_type])
return;
- memcpy(val, nla_data(tb[val_type]), len);
+ nla_memcpy(val, tb[val_type], len);
if (mask_type == TCA_FLOWER_UNSPEC || !tb[mask_type])
memset(mask, 0xff, len);
else
- memcpy(mask, nla_data(tb[mask_type]), len);
+ nla_memcpy(mask, tb[mask_type], len);
+}
+
+static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key,
+ struct fl_flow_key *mask,
+ struct netlink_ext_ack *extack)
+{
+ fl_set_key_val(tb, &key->tp_range.tp_min.dst,
+ TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_range.tp_min.dst,
+ TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_min.dst));
+ fl_set_key_val(tb, &key->tp_range.tp_max.dst,
+ TCA_FLOWER_KEY_PORT_DST_MAX, &mask->tp_range.tp_max.dst,
+ TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.dst));
+ fl_set_key_val(tb, &key->tp_range.tp_min.src,
+ TCA_FLOWER_KEY_PORT_SRC_MIN, &mask->tp_range.tp_min.src,
+ TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_min.src));
+ fl_set_key_val(tb, &key->tp_range.tp_max.src,
+ TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_range.tp_max.src,
+ TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.src));
+
+ if (mask->tp_range.tp_min.dst != mask->tp_range.tp_max.dst) {
+ NL_SET_ERR_MSG(extack,
+ "Both min and max destination ports must be specified");
+ return -EINVAL;
+ }
+ if (mask->tp_range.tp_min.src != mask->tp_range.tp_max.src) {
+ NL_SET_ERR_MSG(extack,
+ "Both min and max source ports must be specified");
+ return -EINVAL;
+ }
+ if (mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst &&
+ ntohs(key->tp_range.tp_max.dst) <=
+ ntohs(key->tp_range.tp_min.dst)) {
+ NL_SET_ERR_MSG_ATTR(extack,
+ tb[TCA_FLOWER_KEY_PORT_DST_MIN],
+ "Invalid destination port range (min must be strictly smaller than max)");
+ return -EINVAL;
+ }
+ if (mask->tp_range.tp_min.src && mask->tp_range.tp_max.src &&
+ ntohs(key->tp_range.tp_max.src) <=
+ ntohs(key->tp_range.tp_min.src)) {
+ NL_SET_ERR_MSG_ATTR(extack,
+ tb[TCA_FLOWER_KEY_PORT_SRC_MIN],
+ "Invalid source port range (min must be strictly smaller than max)");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int fl_set_key_mpls_lse(const struct nlattr *nla_lse,
+ struct flow_dissector_key_mpls *key_val,
+ struct flow_dissector_key_mpls *key_mask,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1];
+ struct flow_dissector_mpls_lse *lse_mask;
+ struct flow_dissector_mpls_lse *lse_val;
+ u8 lse_index;
+ u8 depth;
+ int err;
+
+ err = nla_parse_nested(tb, TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX, nla_lse,
+ mpls_stack_entry_policy, extack);
+ if (err < 0)
+ return err;
+
+ if (!tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH]) {
+ NL_SET_ERR_MSG(extack, "Missing MPLS option \"depth\"");
+ return -EINVAL;
+ }
+
+ depth = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH]);
+
+ /* LSE depth starts at 1, for consistency with terminology used by
+ * RFC 3031 (section 3.9), where depth 0 refers to unlabeled packets.
+ */
+ if (depth < 1 || depth > FLOW_DIS_MPLS_MAX) {
+ NL_SET_ERR_MSG_ATTR(extack,
+ tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH],
+ "Invalid MPLS depth");
+ return -EINVAL;
+ }
+ lse_index = depth - 1;
+
+ dissector_set_mpls_lse(key_val, lse_index);
+ dissector_set_mpls_lse(key_mask, lse_index);
+
+ lse_val = &key_val->ls[lse_index];
+ lse_mask = &key_mask->ls[lse_index];
+
+ if (tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL]) {
+ lse_val->mpls_ttl = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL]);
+ lse_mask->mpls_ttl = MPLS_TTL_MASK;
+ }
+ if (tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS]) {
+ u8 bos = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS]);
+
+ if (bos & ~MPLS_BOS_MASK) {
+ NL_SET_ERR_MSG_ATTR(extack,
+ tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS],
+ "Bottom Of Stack (BOS) must be 0 or 1");
+ return -EINVAL;
+ }
+ lse_val->mpls_bos = bos;
+ lse_mask->mpls_bos = MPLS_BOS_MASK;
+ }
+ if (tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TC]) {
+ u8 tc = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TC]);
+
+ if (tc & ~MPLS_TC_MASK) {
+ NL_SET_ERR_MSG_ATTR(extack,
+ tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TC],
+ "Traffic Class (TC) must be between 0 and 7");
+ return -EINVAL;
+ }
+ lse_val->mpls_tc = tc;
+ lse_mask->mpls_tc = MPLS_TC_MASK;
+ }
+ if (tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL]) {
+ u32 label = nla_get_u32(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL]);
+
+ if (label & ~MPLS_LABEL_MASK) {
+ NL_SET_ERR_MSG_ATTR(extack,
+ tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL],
+ "Label must be between 0 and 1048575");
+ return -EINVAL;
+ }
+ lse_val->mpls_label = label;
+ lse_mask->mpls_label = MPLS_LABEL_MASK;
+ }
+
+ return 0;
+}
+
+static int fl_set_key_mpls_opts(const struct nlattr *nla_mpls_opts,
+ struct flow_dissector_key_mpls *key_val,
+ struct flow_dissector_key_mpls *key_mask,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *nla_lse;
+ int rem;
+ int err;
+
+ if (!(nla_mpls_opts->nla_type & NLA_F_NESTED)) {
+ NL_SET_ERR_MSG_ATTR(extack, nla_mpls_opts,
+ "NLA_F_NESTED is missing");
+ return -EINVAL;
+ }
+
+ nla_for_each_nested(nla_lse, nla_mpls_opts, rem) {
+ if (nla_type(nla_lse) != TCA_FLOWER_KEY_MPLS_OPTS_LSE) {
+ NL_SET_ERR_MSG_ATTR(extack, nla_lse,
+ "Invalid MPLS option type");
+ return -EINVAL;
+ }
+
+ err = fl_set_key_mpls_lse(nla_lse, key_val, key_mask, extack);
+ if (err < 0)
+ return err;
+ }
+ if (rem) {
+ NL_SET_ERR_MSG(extack,
+ "Bytes leftover after parsing MPLS options");
+ return -EINVAL;
+ }
+
+ return 0;
}
static int fl_set_key_mpls(struct nlattr **tb,
struct flow_dissector_key_mpls *key_val,
- struct flow_dissector_key_mpls *key_mask)
+ struct flow_dissector_key_mpls *key_mask,
+ struct netlink_ext_ack *extack)
{
+ struct flow_dissector_mpls_lse *lse_mask;
+ struct flow_dissector_mpls_lse *lse_val;
+
+ if (tb[TCA_FLOWER_KEY_MPLS_OPTS]) {
+ if (tb[TCA_FLOWER_KEY_MPLS_TTL] ||
+ tb[TCA_FLOWER_KEY_MPLS_BOS] ||
+ tb[TCA_FLOWER_KEY_MPLS_TC] ||
+ tb[TCA_FLOWER_KEY_MPLS_LABEL]) {
+ NL_SET_ERR_MSG_ATTR(extack,
+ tb[TCA_FLOWER_KEY_MPLS_OPTS],
+ "MPLS label, Traffic Class, Bottom Of Stack and Time To Live must be encapsulated in the MPLS options attribute");
+ return -EBADMSG;
+ }
+
+ return fl_set_key_mpls_opts(tb[TCA_FLOWER_KEY_MPLS_OPTS],
+ key_val, key_mask, extack);
+ }
+
+ lse_val = &key_val->ls[0];
+ lse_mask = &key_mask->ls[0];
+
if (tb[TCA_FLOWER_KEY_MPLS_TTL]) {
- key_val->mpls_ttl = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TTL]);
- key_mask->mpls_ttl = MPLS_TTL_MASK;
+ lse_val->mpls_ttl = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TTL]);
+ lse_mask->mpls_ttl = MPLS_TTL_MASK;
+ dissector_set_mpls_lse(key_val, 0);
+ dissector_set_mpls_lse(key_mask, 0);
}
if (tb[TCA_FLOWER_KEY_MPLS_BOS]) {
u8 bos = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_BOS]);
- if (bos & ~MPLS_BOS_MASK)
+ if (bos & ~MPLS_BOS_MASK) {
+ NL_SET_ERR_MSG_ATTR(extack,
+ tb[TCA_FLOWER_KEY_MPLS_BOS],
+ "Bottom Of Stack (BOS) must be 0 or 1");
return -EINVAL;
- key_val->mpls_bos = bos;
- key_mask->mpls_bos = MPLS_BOS_MASK;
+ }
+ lse_val->mpls_bos = bos;
+ lse_mask->mpls_bos = MPLS_BOS_MASK;
+ dissector_set_mpls_lse(key_val, 0);
+ dissector_set_mpls_lse(key_mask, 0);
}
if (tb[TCA_FLOWER_KEY_MPLS_TC]) {
u8 tc = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TC]);
- if (tc & ~MPLS_TC_MASK)
+ if (tc & ~MPLS_TC_MASK) {
+ NL_SET_ERR_MSG_ATTR(extack,
+ tb[TCA_FLOWER_KEY_MPLS_TC],
+ "Traffic Class (TC) must be between 0 and 7");
return -EINVAL;
- key_val->mpls_tc = tc;
- key_mask->mpls_tc = MPLS_TC_MASK;
+ }
+ lse_val->mpls_tc = tc;
+ lse_mask->mpls_tc = MPLS_TC_MASK;
+ dissector_set_mpls_lse(key_val, 0);
+ dissector_set_mpls_lse(key_mask, 0);
}
if (tb[TCA_FLOWER_KEY_MPLS_LABEL]) {
u32 label = nla_get_u32(tb[TCA_FLOWER_KEY_MPLS_LABEL]);
- if (label & ~MPLS_LABEL_MASK)
+ if (label & ~MPLS_LABEL_MASK) {
+ NL_SET_ERR_MSG_ATTR(extack,
+ tb[TCA_FLOWER_KEY_MPLS_LABEL],
+ "Label must be between 0 and 1048575");
return -EINVAL;
- key_val->mpls_label = label;
- key_mask->mpls_label = MPLS_LABEL_MASK;
+ }
+ lse_val->mpls_label = label;
+ lse_mask->mpls_label = MPLS_LABEL_MASK;
+ dissector_set_mpls_lse(key_val, 0);
+ dissector_set_mpls_lse(key_mask, 0);
}
return 0;
}
@@ -554,6 +1008,7 @@
static void fl_set_key_vlan(struct nlattr **tb,
__be16 ethertype,
int vlan_id_key, int vlan_prio_key,
+ int vlan_next_eth_type_key,
struct flow_dissector_key_vlan *key_val,
struct flow_dissector_key_vlan *key_mask)
{
@@ -572,6 +1027,11 @@
}
key_val->vlan_tpid = ethertype;
key_mask->vlan_tpid = cpu_to_be16(~0);
+ if (tb[vlan_next_eth_type_key]) {
+ key_val->vlan_eth_type =
+ nla_get_be16(tb[vlan_next_eth_type_key]);
+ key_mask->vlan_eth_type = cpu_to_be16(~0);
+ }
}
static void fl_set_key_flag(u32 flower_key, u32 flower_mask,
@@ -585,14 +1045,16 @@
}
}
-static int fl_set_key_flags(struct nlattr **tb,
- u32 *flags_key, u32 *flags_mask)
+static int fl_set_key_flags(struct nlattr **tb, u32 *flags_key,
+ u32 *flags_mask, struct netlink_ext_ack *extack)
{
u32 key, mask;
/* mask is mandatory for flags */
- if (!tb[TCA_FLOWER_KEY_FLAGS_MASK])
+ if (!tb[TCA_FLOWER_KEY_FLAGS_MASK]) {
+ NL_SET_ERR_MSG(extack, "Missing flags mask");
return -EINVAL;
+ }
key = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS]));
mask = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS_MASK]));
@@ -634,6 +1096,9 @@
if (option_len > sizeof(struct geneve_opt))
data_len = option_len - sizeof(struct geneve_opt);
+ if (key->enc_opts.len > FLOW_DIS_TUN_OPTS_MAX - 4)
+ return -ERANGE;
+
opt = (struct geneve_opt *)&key->enc_opts.data[key->enc_opts.len];
memset(opt, 0xff, option_len);
opt->length = data_len / 4;
@@ -650,8 +1115,9 @@
return -EINVAL;
}
- err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX,
- nla, geneve_opt_policy, extack);
+ err = nla_parse_nested_deprecated(tb,
+ TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX,
+ nla, geneve_opt_policy, extack);
if (err < 0)
return err;
@@ -706,6 +1172,108 @@
return sizeof(struct geneve_opt) + data_len;
}
+static int fl_set_vxlan_opt(const struct nlattr *nla, struct fl_flow_key *key,
+ int depth, int option_len,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX + 1];
+ struct vxlan_metadata *md;
+ int err;
+
+ md = (struct vxlan_metadata *)&key->enc_opts.data[key->enc_opts.len];
+ memset(md, 0xff, sizeof(*md));
+
+ if (!depth)
+ return sizeof(*md);
+
+ if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_VXLAN) {
+ NL_SET_ERR_MSG(extack, "Non-vxlan option type for mask");
+ return -EINVAL;
+ }
+
+ err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX, nla,
+ vxlan_opt_policy, extack);
+ if (err < 0)
+ return err;
+
+ if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) {
+ NL_SET_ERR_MSG(extack, "Missing tunnel key vxlan option gbp");
+ return -EINVAL;
+ }
+
+ if (tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) {
+ md->gbp = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]);
+ md->gbp &= VXLAN_GBP_MASK;
+ }
+
+ return sizeof(*md);
+}
+
+static int fl_set_erspan_opt(const struct nlattr *nla, struct fl_flow_key *key,
+ int depth, int option_len,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX + 1];
+ struct erspan_metadata *md;
+ int err;
+
+ md = (struct erspan_metadata *)&key->enc_opts.data[key->enc_opts.len];
+ memset(md, 0xff, sizeof(*md));
+ md->version = 1;
+
+ if (!depth)
+ return sizeof(*md);
+
+ if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_ERSPAN) {
+ NL_SET_ERR_MSG(extack, "Non-erspan option type for mask");
+ return -EINVAL;
+ }
+
+ err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX, nla,
+ erspan_opt_policy, extack);
+ if (err < 0)
+ return err;
+
+ if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER]) {
+ NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option ver");
+ return -EINVAL;
+ }
+
+ if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER])
+ md->version = nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER]);
+
+ if (md->version == 1) {
+ if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]) {
+ NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option index");
+ return -EINVAL;
+ }
+ if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]) {
+ nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX];
+ memset(&md->u, 0x00, sizeof(md->u));
+ md->u.index = nla_get_be32(nla);
+ }
+ } else if (md->version == 2) {
+ if (!option_len && (!tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR] ||
+ !tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID])) {
+ NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option dir or hwid");
+ return -EINVAL;
+ }
+ if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR]) {
+ nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR];
+ md->u.md2.dir = nla_get_u8(nla);
+ }
+ if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID]) {
+ nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID];
+ set_hwid(&md->u.md2, nla_get_u8(nla));
+ }
+ } else {
+ NL_SET_ERR_MSG(extack, "Tunnel key erspan option ver is incorrect");
+ return -EINVAL;
+ }
+
+ return sizeof(*md);
+}
+
static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
struct fl_flow_key *mask,
struct netlink_ext_ack *extack)
@@ -713,29 +1281,38 @@
const struct nlattr *nla_enc_key, *nla_opt_key, *nla_opt_msk = NULL;
int err, option_len, key_depth, msk_depth = 0;
- err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS],
- TCA_FLOWER_KEY_ENC_OPTS_MAX,
- enc_opts_policy, extack);
+ err = nla_validate_nested_deprecated(tb[TCA_FLOWER_KEY_ENC_OPTS],
+ TCA_FLOWER_KEY_ENC_OPTS_MAX,
+ enc_opts_policy, extack);
if (err)
return err;
nla_enc_key = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS]);
if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) {
- err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK],
- TCA_FLOWER_KEY_ENC_OPTS_MAX,
- enc_opts_policy, extack);
+ err = nla_validate_nested_deprecated(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK],
+ TCA_FLOWER_KEY_ENC_OPTS_MAX,
+ enc_opts_policy, extack);
if (err)
return err;
nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
+ if (!nla_ok(nla_opt_msk, msk_depth)) {
+ NL_SET_ERR_MSG(extack, "Invalid nested attribute for masks");
+ return -EINVAL;
+ }
}
nla_for_each_attr(nla_opt_key, nla_enc_key,
nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS]), key_depth) {
switch (nla_type(nla_opt_key)) {
case TCA_FLOWER_KEY_ENC_OPTS_GENEVE:
+ if (key->enc_opts.dst_opt_type &&
+ key->enc_opts.dst_opt_type != TUNNEL_GENEVE_OPT) {
+ NL_SET_ERR_MSG(extack, "Duplicate type for geneve options");
+ return -EINVAL;
+ }
option_len = 0;
key->enc_opts.dst_opt_type = TUNNEL_GENEVE_OPT;
option_len = fl_set_geneve_opt(nla_opt_key, key,
@@ -760,14 +1337,153 @@
NL_SET_ERR_MSG(extack, "Key and mask miss aligned");
return -EINVAL;
}
+ break;
+ case TCA_FLOWER_KEY_ENC_OPTS_VXLAN:
+ if (key->enc_opts.dst_opt_type) {
+ NL_SET_ERR_MSG(extack, "Duplicate type for vxlan options");
+ return -EINVAL;
+ }
+ option_len = 0;
+ key->enc_opts.dst_opt_type = TUNNEL_VXLAN_OPT;
+ option_len = fl_set_vxlan_opt(nla_opt_key, key,
+ key_depth, option_len,
+ extack);
+ if (option_len < 0)
+ return option_len;
- if (msk_depth)
- nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
+ key->enc_opts.len += option_len;
+ /* At the same time we need to parse through the mask
+ * in order to verify exact and mask attribute lengths.
+ */
+ mask->enc_opts.dst_opt_type = TUNNEL_VXLAN_OPT;
+ option_len = fl_set_vxlan_opt(nla_opt_msk, mask,
+ msk_depth, option_len,
+ extack);
+ if (option_len < 0)
+ return option_len;
+
+ mask->enc_opts.len += option_len;
+ if (key->enc_opts.len != mask->enc_opts.len) {
+ NL_SET_ERR_MSG(extack, "Key and mask miss aligned");
+ return -EINVAL;
+ }
+ break;
+ case TCA_FLOWER_KEY_ENC_OPTS_ERSPAN:
+ if (key->enc_opts.dst_opt_type) {
+ NL_SET_ERR_MSG(extack, "Duplicate type for erspan options");
+ return -EINVAL;
+ }
+ option_len = 0;
+ key->enc_opts.dst_opt_type = TUNNEL_ERSPAN_OPT;
+ option_len = fl_set_erspan_opt(nla_opt_key, key,
+ key_depth, option_len,
+ extack);
+ if (option_len < 0)
+ return option_len;
+
+ key->enc_opts.len += option_len;
+ /* At the same time we need to parse through the mask
+ * in order to verify exact and mask attribute lengths.
+ */
+ mask->enc_opts.dst_opt_type = TUNNEL_ERSPAN_OPT;
+ option_len = fl_set_erspan_opt(nla_opt_msk, mask,
+ msk_depth, option_len,
+ extack);
+ if (option_len < 0)
+ return option_len;
+
+ mask->enc_opts.len += option_len;
+ if (key->enc_opts.len != mask->enc_opts.len) {
+ NL_SET_ERR_MSG(extack, "Key and mask miss aligned");
+ return -EINVAL;
+ }
break;
default:
NL_SET_ERR_MSG(extack, "Unknown tunnel option type");
return -EINVAL;
}
+
+ if (!msk_depth)
+ continue;
+
+ if (!nla_ok(nla_opt_msk, msk_depth)) {
+ NL_SET_ERR_MSG(extack, "A mask attribute is invalid");
+ return -EINVAL;
+ }
+ nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
+ }
+
+ return 0;
+}
+
+static int fl_validate_ct_state(u16 state, struct nlattr *tb,
+ struct netlink_ext_ack *extack)
+{
+ if (state && !(state & TCA_FLOWER_KEY_CT_FLAGS_TRACKED)) {
+ NL_SET_ERR_MSG_ATTR(extack, tb,
+ "no trk, so no other flag can be set");
+ return -EINVAL;
+ }
+
+ if (state & TCA_FLOWER_KEY_CT_FLAGS_NEW &&
+ state & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED) {
+ NL_SET_ERR_MSG_ATTR(extack, tb,
+ "new and est are mutually exclusive");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int fl_set_key_ct(struct nlattr **tb,
+ struct flow_dissector_key_ct *key,
+ struct flow_dissector_key_ct *mask,
+ struct netlink_ext_ack *extack)
+{
+ if (tb[TCA_FLOWER_KEY_CT_STATE]) {
+ int err;
+
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK)) {
+ NL_SET_ERR_MSG(extack, "Conntrack isn't enabled");
+ return -EOPNOTSUPP;
+ }
+ fl_set_key_val(tb, &key->ct_state, TCA_FLOWER_KEY_CT_STATE,
+ &mask->ct_state, TCA_FLOWER_KEY_CT_STATE_MASK,
+ sizeof(key->ct_state));
+
+ err = fl_validate_ct_state(key->ct_state & mask->ct_state,
+ tb[TCA_FLOWER_KEY_CT_STATE_MASK],
+ extack);
+ if (err)
+ return err;
+
+ }
+ if (tb[TCA_FLOWER_KEY_CT_ZONE]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)) {
+ NL_SET_ERR_MSG(extack, "Conntrack zones isn't enabled");
+ return -EOPNOTSUPP;
+ }
+ fl_set_key_val(tb, &key->ct_zone, TCA_FLOWER_KEY_CT_ZONE,
+ &mask->ct_zone, TCA_FLOWER_KEY_CT_ZONE_MASK,
+ sizeof(key->ct_zone));
+ }
+ if (tb[TCA_FLOWER_KEY_CT_MARK]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)) {
+ NL_SET_ERR_MSG(extack, "Conntrack mark isn't enabled");
+ return -EOPNOTSUPP;
+ }
+ fl_set_key_val(tb, &key->ct_mark, TCA_FLOWER_KEY_CT_MARK,
+ &mask->ct_mark, TCA_FLOWER_KEY_CT_MARK_MASK,
+ sizeof(key->ct_mark));
+ }
+ if (tb[TCA_FLOWER_KEY_CT_LABELS]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) {
+ NL_SET_ERR_MSG(extack, "Conntrack labels aren't enabled");
+ return -EOPNOTSUPP;
+ }
+ fl_set_key_val(tb, key->ct_labels, TCA_FLOWER_KEY_CT_LABELS,
+ mask->ct_labels, TCA_FLOWER_KEY_CT_LABELS_MASK,
+ sizeof(key->ct_labels));
}
return 0;
@@ -779,15 +1495,14 @@
{
__be16 ethertype;
int ret = 0;
-#ifdef CONFIG_NET_CLS_IND
+
if (tb[TCA_FLOWER_INDEV]) {
int err = tcf_change_indev(net, tb[TCA_FLOWER_INDEV], extack);
if (err < 0)
return err;
- key->indev_ifindex = err;
- mask->indev_ifindex = 0xffffffff;
+ key->meta.ingress_ifindex = err;
+ mask->meta.ingress_ifindex = 0xffffffff;
}
-#endif
fl_set_key_val(tb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST,
mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK,
@@ -801,8 +1516,9 @@
if (eth_type_vlan(ethertype)) {
fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_VLAN_ID,
- TCA_FLOWER_KEY_VLAN_PRIO, &key->vlan,
- &mask->vlan);
+ TCA_FLOWER_KEY_VLAN_PRIO,
+ TCA_FLOWER_KEY_VLAN_ETH_TYPE,
+ &key->vlan, &mask->vlan);
if (tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]) {
ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]);
@@ -810,6 +1526,7 @@
fl_set_key_vlan(tb, ethertype,
TCA_FLOWER_KEY_CVLAN_ID,
TCA_FLOWER_KEY_CVLAN_PRIO,
+ TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
&key->cvlan, &mask->cvlan);
fl_set_key_val(tb, &key->basic.n_proto,
TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
@@ -901,7 +1618,7 @@
sizeof(key->icmp.code));
} else if (key->basic.n_proto == htons(ETH_P_MPLS_UC) ||
key->basic.n_proto == htons(ETH_P_MPLS_MC)) {
- ret = fl_set_key_mpls(tb, &key->mpls, &mask->mpls);
+ ret = fl_set_key_mpls(tb, &key->mpls, &mask->mpls, extack);
if (ret)
return ret;
} else if (key->basic.n_proto == htons(ETH_P_ARP) ||
@@ -921,6 +1638,14 @@
fl_set_key_val(tb, key->arp.tha, TCA_FLOWER_KEY_ARP_THA,
mask->arp.tha, TCA_FLOWER_KEY_ARP_THA_MASK,
sizeof(key->arp.tha));
+ }
+
+ if (key->basic.ip_proto == IPPROTO_TCP ||
+ key->basic.ip_proto == IPPROTO_UDP ||
+ key->basic.ip_proto == IPPROTO_SCTP) {
+ ret = fl_set_key_port_range(tb, key, mask, extack);
+ if (ret)
+ return ret;
}
if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] ||
@@ -969,14 +1694,23 @@
fl_set_key_ip(tb, true, &key->enc_ip, &mask->enc_ip);
+ fl_set_key_val(tb, &key->hash.hash, TCA_FLOWER_KEY_HASH,
+ &mask->hash.hash, TCA_FLOWER_KEY_HASH_MASK,
+ sizeof(key->hash.hash));
+
if (tb[TCA_FLOWER_KEY_ENC_OPTS]) {
ret = fl_set_enc_opt(tb, key, mask, extack);
if (ret)
return ret;
}
+ ret = fl_set_key_ct(tb, &key->ct, &mask->ct, extack);
+ if (ret)
+ return ret;
+
if (tb[TCA_FLOWER_KEY_FLAGS])
- ret = fl_set_key_flags(tb, &key->control.flags, &mask->control.flags);
+ ret = fl_set_key_flags(tb, &key->control.flags,
+ &mask->control.flags, extack);
return ret;
}
@@ -1007,7 +1741,7 @@
}
#define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member)
-#define FL_KEY_MEMBER_SIZE(member) (sizeof(((struct fl_flow_key *) 0)->member))
+#define FL_KEY_MEMBER_SIZE(member) sizeof_field(struct fl_flow_key, member)
#define FL_KEY_IS_MASKED(mask, member) \
memchr_inv(((char *)mask) + FL_KEY_MEMBER_OFFSET(member), \
@@ -1032,6 +1766,8 @@
struct flow_dissector_key keys[FLOW_DISSECTOR_KEY_MAX];
size_t cnt = 0;
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+ FLOW_DISSECTOR_KEY_META, meta);
FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_CONTROL, control);
FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_BASIC, basic);
FL_KEY_SET_IF_MASKED(mask, keys, cnt,
@@ -1042,6 +1778,8 @@
FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6);
FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_PORTS, tp);
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+ FLOW_DISSECTOR_KEY_PORTS_RANGE, tp_range);
FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_IP, ip);
FL_KEY_SET_IF_MASKED(mask, keys, cnt,
@@ -1072,6 +1810,10 @@
FLOW_DISSECTOR_KEY_ENC_IP, enc_ip);
FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_OPTS, enc_opts);
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+ FLOW_DISSECTOR_KEY_CT, ct);
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+ FLOW_DISSECTOR_KEY_HASH, hash);
skb_flow_dissector_init(dissector, keys, cnt);
}
@@ -1088,6 +1830,12 @@
fl_mask_copy(newmask, mask);
+ if ((newmask->key.tp_range.tp_min.dst &&
+ newmask->key.tp_range.tp_max.dst) ||
+ (newmask->key.tp_range.tp_min.src &&
+ newmask->key.tp_range.tp_max.src))
+ newmask->flags |= TCA_FLOWER_MASK_FLAGS_RANGE;
+
err = fl_init_mask_hashtable(newmask);
if (err)
goto errout_free;
@@ -1096,12 +1844,15 @@
INIT_LIST_HEAD_RCU(&newmask->filters);
- err = rhashtable_insert_fast(&head->ht, &newmask->ht_node,
- mask_ht_params);
+ refcount_set(&newmask->refcnt, 1);
+ err = rhashtable_replace_fast(&head->ht, &mask->ht_node,
+ &newmask->ht_node, mask_ht_params);
if (err)
goto errout_destroy;
+ spin_lock(&head->masks_lock);
list_add_tail_rcu(&newmask->list, &head->masks);
+ spin_unlock(&head->masks_lock);
return newmask;
@@ -1119,40 +1870,71 @@
struct fl_flow_mask *mask)
{
struct fl_flow_mask *newmask;
+ int ret = 0;
- fnew->mask = rhashtable_lookup_fast(&head->ht, mask, mask_ht_params);
+ rcu_read_lock();
+
+ /* Insert mask as temporary node to prevent concurrent creation of mask
+ * with same key. Any concurrent lookups with same key will return
+ * -EAGAIN because mask's refcnt is zero.
+ */
+ fnew->mask = rhashtable_lookup_get_insert_fast(&head->ht,
+ &mask->ht_node,
+ mask_ht_params);
if (!fnew->mask) {
- if (fold)
- return -EINVAL;
+ rcu_read_unlock();
+
+ if (fold) {
+ ret = -EINVAL;
+ goto errout_cleanup;
+ }
newmask = fl_create_new_mask(head, mask);
- if (IS_ERR(newmask))
- return PTR_ERR(newmask);
+ if (IS_ERR(newmask)) {
+ ret = PTR_ERR(newmask);
+ goto errout_cleanup;
+ }
fnew->mask = newmask;
+ return 0;
+ } else if (IS_ERR(fnew->mask)) {
+ ret = PTR_ERR(fnew->mask);
} else if (fold && fold->mask != fnew->mask) {
- return -EINVAL;
+ ret = -EINVAL;
+ } else if (!refcount_inc_not_zero(&fnew->mask->refcnt)) {
+ /* Mask was deleted concurrently, try again */
+ ret = -EAGAIN;
}
+ rcu_read_unlock();
+ return ret;
- return 0;
+errout_cleanup:
+ rhashtable_remove_fast(&head->ht, &mask->ht_node,
+ mask_ht_params);
+ return ret;
}
static int fl_set_parms(struct net *net, struct tcf_proto *tp,
struct cls_fl_filter *f, struct fl_flow_mask *mask,
unsigned long base, struct nlattr **tb,
struct nlattr *est, bool ovr,
- struct fl_flow_tmplt *tmplt,
+ struct fl_flow_tmplt *tmplt, bool rtnl_held,
struct netlink_ext_ack *extack)
{
int err;
- err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, extack);
+ err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, rtnl_held,
+ extack);
if (err < 0)
return err;
if (tb[TCA_FLOWER_CLASSID]) {
f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]);
+ if (!rtnl_held)
+ rtnl_lock();
tcf_bind_filter(tp, &f->res, base);
+ if (!rtnl_held)
+ rtnl_unlock();
}
err = fl_set_key(net, tb, &f->key, &mask->key, extack);
@@ -1170,24 +1952,52 @@
return 0;
}
+static int fl_ht_insert_unique(struct cls_fl_filter *fnew,
+ struct cls_fl_filter *fold,
+ bool *in_ht)
+{
+ struct fl_flow_mask *mask = fnew->mask;
+ int err;
+
+ err = rhashtable_lookup_insert_fast(&mask->ht,
+ &fnew->ht_node,
+ mask->filter_ht_params);
+ if (err) {
+ *in_ht = false;
+ /* It is okay if filter with same key exists when
+ * overwriting.
+ */
+ return fold && err == -EEXIST ? 0 : err;
+ }
+
+ *in_ht = true;
+ return 0;
+}
+
static int fl_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
- void **arg, bool ovr, struct netlink_ext_ack *extack)
+ void **arg, bool ovr, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
- struct cls_fl_head *head = rtnl_dereference(tp->root);
+ struct cls_fl_head *head = fl_head_dereference(tp);
struct cls_fl_filter *fold = *arg;
struct cls_fl_filter *fnew;
struct fl_flow_mask *mask;
struct nlattr **tb;
+ bool in_ht;
int err;
- if (!tca[TCA_OPTIONS])
- return -EINVAL;
+ if (!tca[TCA_OPTIONS]) {
+ err = -EINVAL;
+ goto errout_fold;
+ }
mask = kzalloc(sizeof(struct fl_flow_mask), GFP_KERNEL);
- if (!mask)
- return -ENOBUFS;
+ if (!mask) {
+ err = -ENOBUFS;
+ goto errout_fold;
+ }
tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL);
if (!tb) {
@@ -1195,8 +2005,8 @@
goto errout_mask_alloc;
}
- err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS],
- fl_policy, NULL);
+ err = nla_parse_nested_deprecated(tb, TCA_FLOWER_MAX,
+ tca[TCA_OPTIONS], fl_policy, NULL);
if (err < 0)
goto errout_tb;
@@ -1210,8 +2020,10 @@
err = -ENOBUFS;
goto errout_tb;
}
+ INIT_LIST_HEAD(&fnew->hw_list);
+ refcount_set(&fnew->refcnt, 1);
- err = tcf_exts_init(&fnew->exts, TCA_FLOWER_ACT, 0);
+ err = tcf_exts_init(&fnew->exts, net, TCA_FLOWER_ACT, 0);
if (err < 0)
goto errout;
@@ -1225,7 +2037,7 @@
}
err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], ovr,
- tp->chain->tmplt_priv, extack);
+ tp->chain->tmplt_priv, rtnl_held, extack);
if (err)
goto errout;
@@ -1233,189 +2045,320 @@
if (err)
goto errout;
- if (!handle) {
- handle = 1;
- err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
- INT_MAX, GFP_KERNEL);
- } else if (!fold) {
- /* user specifies a handle and it doesn't exist */
- err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
- handle, GFP_KERNEL);
- }
+ err = fl_ht_insert_unique(fnew, fold, &in_ht);
if (err)
goto errout_mask;
- fnew->handle = handle;
-
- if (!tc_skip_sw(fnew->flags)) {
- if (!fold && fl_lookup(fnew->mask, &fnew->mkey)) {
- err = -EEXIST;
- goto errout_idr;
- }
-
- err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node,
- fnew->mask->filter_ht_params);
- if (err)
- goto errout_idr;
- }
if (!tc_skip_hw(fnew->flags)) {
- err = fl_hw_replace_filter(tp, fnew, extack);
+ err = fl_hw_replace_filter(tp, fnew, rtnl_held, extack);
if (err)
- goto errout_mask;
+ goto errout_ht;
}
if (!tc_in_hw(fnew->flags))
fnew->flags |= TCA_CLS_FLAGS_NOT_IN_HW;
+ spin_lock(&tp->lock);
+
+ /* tp was deleted concurrently. -EAGAIN will cause caller to lookup
+ * proto again or create new one, if necessary.
+ */
+ if (tp->deleting) {
+ err = -EAGAIN;
+ goto errout_hw;
+ }
+
if (fold) {
- if (!tc_skip_sw(fold->flags))
- rhashtable_remove_fast(&fold->mask->ht,
- &fold->ht_node,
- fold->mask->filter_ht_params);
+ /* Fold filter was deleted concurrently. Retry lookup. */
+ if (fold->deleted) {
+ err = -EAGAIN;
+ goto errout_hw;
+ }
+
+ fnew->handle = handle;
+
+ if (!in_ht) {
+ struct rhashtable_params params =
+ fnew->mask->filter_ht_params;
+
+ err = rhashtable_insert_fast(&fnew->mask->ht,
+ &fnew->ht_node,
+ params);
+ if (err)
+ goto errout_hw;
+ in_ht = true;
+ }
+
+ refcount_inc(&fnew->refcnt);
+ rhashtable_remove_fast(&fold->mask->ht,
+ &fold->ht_node,
+ fold->mask->filter_ht_params);
+ idr_replace(&head->handle_idr, fnew, fnew->handle);
+ list_replace_rcu(&fold->list, &fnew->list);
+ fold->deleted = true;
+
+ spin_unlock(&tp->lock);
+
+ fl_mask_put(head, fold->mask);
if (!tc_skip_hw(fold->flags))
- fl_hw_destroy_filter(tp, fold, NULL);
+ fl_hw_destroy_filter(tp, fold, rtnl_held, NULL);
+ tcf_unbind_filter(tp, &fold->res);
+ /* Caller holds reference to fold, so refcnt is always > 0
+ * after this.
+ */
+ refcount_dec(&fold->refcnt);
+ __fl_put(fold);
+ } else {
+ if (handle) {
+ /* user specifies a handle and it doesn't exist */
+ err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
+ handle, GFP_ATOMIC);
+
+ /* Filter with specified handle was concurrently
+ * inserted after initial check in cls_api. This is not
+ * necessarily an error if NLM_F_EXCL is not set in
+ * message flags. Returning EAGAIN will cause cls_api to
+ * try to update concurrently inserted rule.
+ */
+ if (err == -ENOSPC)
+ err = -EAGAIN;
+ } else {
+ handle = 1;
+ err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
+ INT_MAX, GFP_ATOMIC);
+ }
+ if (err)
+ goto errout_hw;
+
+ refcount_inc(&fnew->refcnt);
+ fnew->handle = handle;
+ list_add_tail_rcu(&fnew->list, &fnew->mask->filters);
+ spin_unlock(&tp->lock);
}
*arg = fnew;
- if (fold) {
- idr_replace(&head->handle_idr, fnew, fnew->handle);
- list_replace_rcu(&fold->list, &fnew->list);
- tcf_unbind_filter(tp, &fold->res);
- tcf_exts_get_net(&fold->exts);
- tcf_queue_work(&fold->rwork, fl_destroy_filter_work);
- } else {
- list_add_tail_rcu(&fnew->list, &fnew->mask->filters);
- }
-
kfree(tb);
- kfree(mask);
+ tcf_queue_work(&mask->rwork, fl_uninit_mask_free_work);
return 0;
-errout_idr:
- if (!fold)
- idr_remove(&head->handle_idr, fnew->handle);
-
+errout_ht:
+ spin_lock(&tp->lock);
+errout_hw:
+ fnew->deleted = true;
+ spin_unlock(&tp->lock);
+ if (!tc_skip_hw(fnew->flags))
+ fl_hw_destroy_filter(tp, fnew, rtnl_held, NULL);
+ if (in_ht)
+ rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node,
+ fnew->mask->filter_ht_params);
errout_mask:
- fl_mask_put(head, fnew->mask, false);
-
+ fl_mask_put(head, fnew->mask);
errout:
- tcf_exts_destroy(&fnew->exts);
- kfree(fnew);
+ __fl_put(fnew);
errout_tb:
kfree(tb);
errout_mask_alloc:
- kfree(mask);
+ tcf_queue_work(&mask->rwork, fl_uninit_mask_free_work);
+errout_fold:
+ if (fold)
+ __fl_put(fold);
return err;
}
static int fl_delete(struct tcf_proto *tp, void *arg, bool *last,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
- struct cls_fl_head *head = rtnl_dereference(tp->root);
+ struct cls_fl_head *head = fl_head_dereference(tp);
struct cls_fl_filter *f = arg;
+ bool last_on_mask;
+ int err = 0;
- if (!tc_skip_sw(f->flags))
- rhashtable_remove_fast(&f->mask->ht, &f->ht_node,
- f->mask->filter_ht_params);
- __fl_delete(tp, f, extack);
+ err = __fl_delete(tp, f, &last_on_mask, rtnl_held, extack);
*last = list_empty(&head->masks);
- return 0;
+ __fl_put(f);
+
+ return err;
}
-static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg)
+static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg,
+ bool rtnl_held)
{
- struct cls_fl_head *head = rtnl_dereference(tp->root);
+ struct cls_fl_head *head = fl_head_dereference(tp);
+ unsigned long id = arg->cookie, tmp;
struct cls_fl_filter *f;
arg->count = arg->skip;
- while ((f = idr_get_next_ul(&head->handle_idr,
- &arg->cookie)) != NULL) {
+ rcu_read_lock();
+ idr_for_each_entry_continue_ul(&head->handle_idr, f, tmp, id) {
+ /* don't return filters that are being deleted */
+ if (!refcount_inc_not_zero(&f->refcnt))
+ continue;
+ rcu_read_unlock();
+
if (arg->fn(tp, f, arg) < 0) {
+ __fl_put(f);
arg->stop = 1;
+ rcu_read_lock();
break;
}
- arg->cookie = f->handle + 1;
+ __fl_put(f);
arg->count++;
+ rcu_read_lock();
}
+ rcu_read_unlock();
+ arg->cookie = id;
}
-static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+static struct cls_fl_filter *
+fl_get_next_hw_filter(struct tcf_proto *tp, struct cls_fl_filter *f, bool add)
+{
+ struct cls_fl_head *head = fl_head_dereference(tp);
+
+ spin_lock(&tp->lock);
+ if (list_empty(&head->hw_filters)) {
+ spin_unlock(&tp->lock);
+ return NULL;
+ }
+
+ if (!f)
+ f = list_entry(&head->hw_filters, struct cls_fl_filter,
+ hw_list);
+ list_for_each_entry_continue(f, &head->hw_filters, hw_list) {
+ if (!(add && f->deleted) && refcount_inc_not_zero(&f->refcnt)) {
+ spin_unlock(&tp->lock);
+ return f;
+ }
+ }
+
+ spin_unlock(&tp->lock);
+ return NULL;
+}
+
+static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
void *cb_priv, struct netlink_ext_ack *extack)
{
- struct cls_fl_head *head = rtnl_dereference(tp->root);
- struct tc_cls_flower_offload cls_flower = {};
struct tcf_block *block = tp->chain->block;
- struct fl_flow_mask *mask;
- struct cls_fl_filter *f;
+ struct flow_cls_offload cls_flower = {};
+ struct cls_fl_filter *f = NULL;
int err;
- list_for_each_entry(mask, &head->masks, list) {
- list_for_each_entry(f, &mask->filters, list) {
- if (tc_skip_hw(f->flags))
- continue;
+ /* hw_filters list can only be changed by hw offload functions after
+ * obtaining rtnl lock. Make sure it is not changed while reoffload is
+ * iterating it.
+ */
+ ASSERT_RTNL();
- tc_cls_common_offload_init(&cls_flower.common, tp,
- f->flags, extack);
- cls_flower.command = add ?
- TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY;
- cls_flower.cookie = (unsigned long)f;
- cls_flower.dissector = &mask->dissector;
- cls_flower.mask = &mask->key;
- cls_flower.key = &f->mkey;
- cls_flower.exts = &f->exts;
- cls_flower.classid = f->res.classid;
-
- err = cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv);
- if (err) {
- if (add && tc_skip_sw(f->flags))
- return err;
- continue;
- }
-
- tc_cls_offload_cnt_update(block, &f->in_hw_count,
- &f->flags, add);
+ while ((f = fl_get_next_hw_filter(tp, f, add))) {
+ cls_flower.rule =
+ flow_rule_alloc(tcf_exts_num_actions(&f->exts));
+ if (!cls_flower.rule) {
+ __fl_put(f);
+ return -ENOMEM;
}
+
+ tc_cls_common_offload_init(&cls_flower.common, tp, f->flags,
+ extack);
+ cls_flower.command = add ?
+ FLOW_CLS_REPLACE : FLOW_CLS_DESTROY;
+ cls_flower.cookie = (unsigned long)f;
+ cls_flower.rule->match.dissector = &f->mask->dissector;
+ cls_flower.rule->match.mask = &f->mask->key;
+ cls_flower.rule->match.key = &f->mkey;
+
+ err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts);
+ if (err) {
+ kfree(cls_flower.rule);
+ if (tc_skip_sw(f->flags)) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action");
+ __fl_put(f);
+ return err;
+ }
+ goto next_flow;
+ }
+
+ cls_flower.classid = f->res.classid;
+
+ err = tc_setup_cb_reoffload(block, tp, add, cb,
+ TC_SETUP_CLSFLOWER, &cls_flower,
+ cb_priv, &f->flags,
+ &f->in_hw_count);
+ tc_cleanup_flow_action(&cls_flower.rule->action);
+ kfree(cls_flower.rule);
+
+ if (err) {
+ __fl_put(f);
+ return err;
+ }
+next_flow:
+ __fl_put(f);
}
return 0;
}
-static void fl_hw_create_tmplt(struct tcf_chain *chain,
- struct fl_flow_tmplt *tmplt)
+static void fl_hw_add(struct tcf_proto *tp, void *type_data)
{
- struct tc_cls_flower_offload cls_flower = {};
+ struct flow_cls_offload *cls_flower = type_data;
+ struct cls_fl_filter *f =
+ (struct cls_fl_filter *) cls_flower->cookie;
+ struct cls_fl_head *head = fl_head_dereference(tp);
+
+ spin_lock(&tp->lock);
+ list_add(&f->hw_list, &head->hw_filters);
+ spin_unlock(&tp->lock);
+}
+
+static void fl_hw_del(struct tcf_proto *tp, void *type_data)
+{
+ struct flow_cls_offload *cls_flower = type_data;
+ struct cls_fl_filter *f =
+ (struct cls_fl_filter *) cls_flower->cookie;
+
+ spin_lock(&tp->lock);
+ if (!list_empty(&f->hw_list))
+ list_del_init(&f->hw_list);
+ spin_unlock(&tp->lock);
+}
+
+static int fl_hw_create_tmplt(struct tcf_chain *chain,
+ struct fl_flow_tmplt *tmplt)
+{
+ struct flow_cls_offload cls_flower = {};
struct tcf_block *block = chain->block;
- struct tcf_exts dummy_exts = { 0, };
+
+ cls_flower.rule = flow_rule_alloc(0);
+ if (!cls_flower.rule)
+ return -ENOMEM;
cls_flower.common.chain_index = chain->index;
- cls_flower.command = TC_CLSFLOWER_TMPLT_CREATE;
+ cls_flower.command = FLOW_CLS_TMPLT_CREATE;
cls_flower.cookie = (unsigned long) tmplt;
- cls_flower.dissector = &tmplt->dissector;
- cls_flower.mask = &tmplt->mask;
- cls_flower.key = &tmplt->dummy_key;
- cls_flower.exts = &dummy_exts;
+ cls_flower.rule->match.dissector = &tmplt->dissector;
+ cls_flower.rule->match.mask = &tmplt->mask;
+ cls_flower.rule->match.key = &tmplt->dummy_key;
/* We don't care if driver (any of them) fails to handle this
* call. It serves just as a hint for it.
*/
- tc_setup_cb_call(block, NULL, TC_SETUP_CLSFLOWER,
- &cls_flower, false);
+ tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false, true);
+ kfree(cls_flower.rule);
+
+ return 0;
}
static void fl_hw_destroy_tmplt(struct tcf_chain *chain,
struct fl_flow_tmplt *tmplt)
{
- struct tc_cls_flower_offload cls_flower = {};
+ struct flow_cls_offload cls_flower = {};
struct tcf_block *block = chain->block;
cls_flower.common.chain_index = chain->index;
- cls_flower.command = TC_CLSFLOWER_TMPLT_DESTROY;
+ cls_flower.command = FLOW_CLS_TMPLT_DESTROY;
cls_flower.cookie = (unsigned long) tmplt;
- tc_setup_cb_call(block, NULL, TC_SETUP_CLSFLOWER,
- &cls_flower, false);
+ tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false, true);
}
static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain,
@@ -1432,8 +2375,8 @@
tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL);
if (!tb)
return ERR_PTR(-ENOBUFS);
- err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS],
- fl_policy, NULL);
+ err = nla_parse_nested_deprecated(tb, TCA_FLOWER_MAX,
+ tca[TCA_OPTIONS], fl_policy, NULL);
if (err)
goto errout_tb;
@@ -1446,12 +2389,14 @@
err = fl_set_key(net, tb, &tmplt->dummy_key, &tmplt->mask, extack);
if (err)
goto errout_tmplt;
- kfree(tb);
fl_init_dissector(&tmplt->dissector, &tmplt->mask);
- fl_hw_create_tmplt(chain, tmplt);
+ err = fl_hw_create_tmplt(chain, tmplt);
+ if (err)
+ goto errout_tmplt;
+ kfree(tb);
return tmplt;
errout_tmplt:
@@ -1488,35 +2433,156 @@
return 0;
}
+static int fl_dump_key_port_range(struct sk_buff *skb, struct fl_flow_key *key,
+ struct fl_flow_key *mask)
+{
+ if (fl_dump_key_val(skb, &key->tp_range.tp_min.dst,
+ TCA_FLOWER_KEY_PORT_DST_MIN,
+ &mask->tp_range.tp_min.dst, TCA_FLOWER_UNSPEC,
+ sizeof(key->tp_range.tp_min.dst)) ||
+ fl_dump_key_val(skb, &key->tp_range.tp_max.dst,
+ TCA_FLOWER_KEY_PORT_DST_MAX,
+ &mask->tp_range.tp_max.dst, TCA_FLOWER_UNSPEC,
+ sizeof(key->tp_range.tp_max.dst)) ||
+ fl_dump_key_val(skb, &key->tp_range.tp_min.src,
+ TCA_FLOWER_KEY_PORT_SRC_MIN,
+ &mask->tp_range.tp_min.src, TCA_FLOWER_UNSPEC,
+ sizeof(key->tp_range.tp_min.src)) ||
+ fl_dump_key_val(skb, &key->tp_range.tp_max.src,
+ TCA_FLOWER_KEY_PORT_SRC_MAX,
+ &mask->tp_range.tp_max.src, TCA_FLOWER_UNSPEC,
+ sizeof(key->tp_range.tp_max.src)))
+ return -1;
+
+ return 0;
+}
+
+static int fl_dump_key_mpls_opt_lse(struct sk_buff *skb,
+ struct flow_dissector_key_mpls *mpls_key,
+ struct flow_dissector_key_mpls *mpls_mask,
+ u8 lse_index)
+{
+ struct flow_dissector_mpls_lse *lse_mask = &mpls_mask->ls[lse_index];
+ struct flow_dissector_mpls_lse *lse_key = &mpls_key->ls[lse_index];
+ int err;
+
+ err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH,
+ lse_index + 1);
+ if (err)
+ return err;
+
+ if (lse_mask->mpls_ttl) {
+ err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL,
+ lse_key->mpls_ttl);
+ if (err)
+ return err;
+ }
+ if (lse_mask->mpls_bos) {
+ err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS,
+ lse_key->mpls_bos);
+ if (err)
+ return err;
+ }
+ if (lse_mask->mpls_tc) {
+ err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_TC,
+ lse_key->mpls_tc);
+ if (err)
+ return err;
+ }
+ if (lse_mask->mpls_label) {
+ err = nla_put_u32(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL,
+ lse_key->mpls_label);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int fl_dump_key_mpls_opts(struct sk_buff *skb,
+ struct flow_dissector_key_mpls *mpls_key,
+ struct flow_dissector_key_mpls *mpls_mask)
+{
+ struct nlattr *opts;
+ struct nlattr *lse;
+ u8 lse_index;
+ int err;
+
+ opts = nla_nest_start(skb, TCA_FLOWER_KEY_MPLS_OPTS);
+ if (!opts)
+ return -EMSGSIZE;
+
+ for (lse_index = 0; lse_index < FLOW_DIS_MPLS_MAX; lse_index++) {
+ if (!(mpls_mask->used_lses & 1 << lse_index))
+ continue;
+
+ lse = nla_nest_start(skb, TCA_FLOWER_KEY_MPLS_OPTS_LSE);
+ if (!lse) {
+ err = -EMSGSIZE;
+ goto err_opts;
+ }
+
+ err = fl_dump_key_mpls_opt_lse(skb, mpls_key, mpls_mask,
+ lse_index);
+ if (err)
+ goto err_opts_lse;
+ nla_nest_end(skb, lse);
+ }
+ nla_nest_end(skb, opts);
+
+ return 0;
+
+err_opts_lse:
+ nla_nest_cancel(skb, lse);
+err_opts:
+ nla_nest_cancel(skb, opts);
+
+ return err;
+}
+
static int fl_dump_key_mpls(struct sk_buff *skb,
struct flow_dissector_key_mpls *mpls_key,
struct flow_dissector_key_mpls *mpls_mask)
{
+ struct flow_dissector_mpls_lse *lse_mask;
+ struct flow_dissector_mpls_lse *lse_key;
int err;
- if (!memchr_inv(mpls_mask, 0, sizeof(*mpls_mask)))
+ if (!mpls_mask->used_lses)
return 0;
- if (mpls_mask->mpls_ttl) {
+
+ lse_mask = &mpls_mask->ls[0];
+ lse_key = &mpls_key->ls[0];
+
+ /* For backward compatibility, don't use the MPLS nested attributes if
+ * the rule can be expressed using the old attributes.
+ */
+ if (mpls_mask->used_lses & ~1 ||
+ (!lse_mask->mpls_ttl && !lse_mask->mpls_bos &&
+ !lse_mask->mpls_tc && !lse_mask->mpls_label))
+ return fl_dump_key_mpls_opts(skb, mpls_key, mpls_mask);
+
+ if (lse_mask->mpls_ttl) {
err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_TTL,
- mpls_key->mpls_ttl);
+ lse_key->mpls_ttl);
if (err)
return err;
}
- if (mpls_mask->mpls_tc) {
+ if (lse_mask->mpls_tc) {
err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_TC,
- mpls_key->mpls_tc);
+ lse_key->mpls_tc);
if (err)
return err;
}
- if (mpls_mask->mpls_label) {
+ if (lse_mask->mpls_label) {
err = nla_put_u32(skb, TCA_FLOWER_KEY_MPLS_LABEL,
- mpls_key->mpls_label);
+ lse_key->mpls_label);
if (err)
return err;
}
- if (mpls_mask->mpls_bos) {
+ if (lse_mask->mpls_bos) {
err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_BOS,
- mpls_key->mpls_bos);
+ lse_key->mpls_bos);
if (err)
return err;
}
@@ -1609,7 +2675,7 @@
struct nlattr *nest;
int opt_off = 0;
- nest = nla_nest_start(skb, TCA_FLOWER_KEY_ENC_OPTS_GENEVE);
+ nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_GENEVE);
if (!nest)
goto nla_put_failure;
@@ -1636,6 +2702,95 @@
return -EMSGSIZE;
}
+static int fl_dump_key_vxlan_opt(struct sk_buff *skb,
+ struct flow_dissector_key_enc_opts *enc_opts)
+{
+ struct vxlan_metadata *md;
+ struct nlattr *nest;
+
+ nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_VXLAN);
+ if (!nest)
+ goto nla_put_failure;
+
+ md = (struct vxlan_metadata *)&enc_opts->data[0];
+ if (nla_put_u32(skb, TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP, md->gbp))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, nest);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, nest);
+ return -EMSGSIZE;
+}
+
+static int fl_dump_key_erspan_opt(struct sk_buff *skb,
+ struct flow_dissector_key_enc_opts *enc_opts)
+{
+ struct erspan_metadata *md;
+ struct nlattr *nest;
+
+ nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_ERSPAN);
+ if (!nest)
+ goto nla_put_failure;
+
+ md = (struct erspan_metadata *)&enc_opts->data[0];
+ if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER, md->version))
+ goto nla_put_failure;
+
+ if (md->version == 1 &&
+ nla_put_be32(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX, md->u.index))
+ goto nla_put_failure;
+
+ if (md->version == 2 &&
+ (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR,
+ md->u.md2.dir) ||
+ nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID,
+ get_hwid(&md->u.md2))))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, nest);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, nest);
+ return -EMSGSIZE;
+}
+
+static int fl_dump_key_ct(struct sk_buff *skb,
+ struct flow_dissector_key_ct *key,
+ struct flow_dissector_key_ct *mask)
+{
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK) &&
+ fl_dump_key_val(skb, &key->ct_state, TCA_FLOWER_KEY_CT_STATE,
+ &mask->ct_state, TCA_FLOWER_KEY_CT_STATE_MASK,
+ sizeof(key->ct_state)))
+ goto nla_put_failure;
+
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
+ fl_dump_key_val(skb, &key->ct_zone, TCA_FLOWER_KEY_CT_ZONE,
+ &mask->ct_zone, TCA_FLOWER_KEY_CT_ZONE_MASK,
+ sizeof(key->ct_zone)))
+ goto nla_put_failure;
+
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) &&
+ fl_dump_key_val(skb, &key->ct_mark, TCA_FLOWER_KEY_CT_MARK,
+ &mask->ct_mark, TCA_FLOWER_KEY_CT_MARK_MASK,
+ sizeof(key->ct_mark)))
+ goto nla_put_failure;
+
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
+ fl_dump_key_val(skb, &key->ct_labels, TCA_FLOWER_KEY_CT_LABELS,
+ &mask->ct_labels, TCA_FLOWER_KEY_CT_LABELS_MASK,
+ sizeof(key->ct_labels)))
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type,
struct flow_dissector_key_enc_opts *enc_opts)
{
@@ -1645,13 +2800,23 @@
if (!enc_opts->len)
return 0;
- nest = nla_nest_start(skb, enc_opt_type);
+ nest = nla_nest_start_noflag(skb, enc_opt_type);
if (!nest)
goto nla_put_failure;
switch (enc_opts->dst_opt_type) {
case TUNNEL_GENEVE_OPT:
err = fl_dump_key_geneve_opt(skb, enc_opts);
+ if (err)
+ goto nla_put_failure;
+ break;
+ case TUNNEL_VXLAN_OPT:
+ err = fl_dump_key_vxlan_opt(skb, enc_opts);
+ if (err)
+ goto nla_put_failure;
+ break;
+ case TUNNEL_ERSPAN_OPT:
+ err = fl_dump_key_erspan_opt(skb, enc_opts);
if (err)
goto nla_put_failure;
break;
@@ -1682,10 +2847,10 @@
static int fl_dump_key(struct sk_buff *skb, struct net *net,
struct fl_flow_key *key, struct fl_flow_key *mask)
{
- if (mask->indev_ifindex) {
+ if (mask->meta.ingress_ifindex) {
struct net_device *dev;
- dev = __dev_get_by_index(net, key->indev_ifindex);
+ dev = __dev_get_by_index(net, key->meta.ingress_ifindex);
if (dev && nla_put_string(skb, TCA_FLOWER_INDEV, dev->name))
goto nla_put_failure;
}
@@ -1717,13 +2882,13 @@
goto nla_put_failure;
if (mask->basic.n_proto) {
- if (mask->cvlan.vlan_tpid) {
+ if (mask->cvlan.vlan_eth_type) {
if (nla_put_be16(skb, TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
key->basic.n_proto))
goto nla_put_failure;
- } else if (mask->vlan.vlan_tpid) {
+ } else if (mask->vlan.vlan_eth_type) {
if (nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE,
- key->basic.n_proto))
+ key->vlan.vlan_eth_type))
goto nla_put_failure;
}
}
@@ -1824,6 +2989,12 @@
sizeof(key->arp.tha))))
goto nla_put_failure;
+ if ((key->basic.ip_proto == IPPROTO_TCP ||
+ key->basic.ip_proto == IPPROTO_UDP ||
+ key->basic.ip_proto == IPPROTO_SCTP) &&
+ fl_dump_key_port_range(skb, key, mask))
+ goto nla_put_failure;
+
if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
(fl_dump_key_val(skb, &key->enc_ipv4.src,
TCA_FLOWER_KEY_ENC_IPV4_SRC, &mask->enc_ipv4.src,
@@ -1863,7 +3034,15 @@
fl_dump_key_enc_opt(skb, &key->enc_opts, &mask->enc_opts))
goto nla_put_failure;
+ if (fl_dump_key_ct(skb, &key->ct, &mask->ct))
+ goto nla_put_failure;
+
if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags))
+ goto nla_put_failure;
+
+ if (fl_dump_key_val(skb, &key->hash.hash, TCA_FLOWER_KEY_HASH,
+ &mask->hash.hash, TCA_FLOWER_KEY_HASH_MASK,
+ sizeof(key->hash.hash)))
goto nla_put_failure;
return 0;
@@ -1873,35 +3052,44 @@
}
static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
- struct sk_buff *skb, struct tcmsg *t)
+ struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
{
struct cls_fl_filter *f = fh;
struct nlattr *nest;
struct fl_flow_key *key, *mask;
+ bool skip_hw;
if (!f)
return skb->len;
t->tcm_handle = f->handle;
- nest = nla_nest_start(skb, TCA_OPTIONS);
+ nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
if (!nest)
goto nla_put_failure;
+ spin_lock(&tp->lock);
+
if (f->res.classid &&
nla_put_u32(skb, TCA_FLOWER_CLASSID, f->res.classid))
- goto nla_put_failure;
+ goto nla_put_failure_locked;
key = &f->key;
mask = &f->mask->key;
+ skip_hw = tc_skip_hw(f->flags);
if (fl_dump_key(skb, net, key, mask))
- goto nla_put_failure;
-
- if (!tc_skip_hw(f->flags))
- fl_hw_update_stats(tp, f);
+ goto nla_put_failure_locked;
if (f->flags && nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags))
+ goto nla_put_failure_locked;
+
+ spin_unlock(&tp->lock);
+
+ if (!skip_hw)
+ fl_hw_update_stats(tp, f, rtnl_held);
+
+ if (nla_put_u32(skb, TCA_FLOWER_IN_HW_COUNT, f->in_hw_count))
goto nla_put_failure;
if (tcf_exts_dump(skb, &f->exts))
@@ -1914,6 +3102,50 @@
return skb->len;
+nla_put_failure_locked:
+ spin_unlock(&tp->lock);
+nla_put_failure:
+ nla_nest_cancel(skb, nest);
+ return -1;
+}
+
+static int fl_terse_dump(struct net *net, struct tcf_proto *tp, void *fh,
+ struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
+{
+ struct cls_fl_filter *f = fh;
+ struct nlattr *nest;
+ bool skip_hw;
+
+ if (!f)
+ return skb->len;
+
+ t->tcm_handle = f->handle;
+
+ nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
+ if (!nest)
+ goto nla_put_failure;
+
+ spin_lock(&tp->lock);
+
+ skip_hw = tc_skip_hw(f->flags);
+
+ if (f->flags && nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags))
+ goto nla_put_failure_locked;
+
+ spin_unlock(&tp->lock);
+
+ if (!skip_hw)
+ fl_hw_update_stats(tp, f, rtnl_held);
+
+ if (tcf_exts_terse_dump(skb, &f->exts))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, nest);
+
+ return skb->len;
+
+nla_put_failure_locked:
+ spin_unlock(&tp->lock);
nla_put_failure:
nla_nest_cancel(skb, nest);
return -1;
@@ -1925,7 +3157,7 @@
struct fl_flow_key *key, *mask;
struct nlattr *nest;
- nest = nla_nest_start(skb, TCA_OPTIONS);
+ nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
if (!nest)
goto nla_put_failure;
@@ -1957,22 +3189,39 @@
}
}
+static bool fl_delete_empty(struct tcf_proto *tp)
+{
+ struct cls_fl_head *head = fl_head_dereference(tp);
+
+ spin_lock(&tp->lock);
+ tp->deleting = idr_is_empty(&head->handle_idr);
+ spin_unlock(&tp->lock);
+
+ return tp->deleting;
+}
+
static struct tcf_proto_ops cls_fl_ops __read_mostly = {
.kind = "flower",
.classify = fl_classify,
.init = fl_init,
.destroy = fl_destroy,
.get = fl_get,
+ .put = fl_put,
.change = fl_change,
.delete = fl_delete,
+ .delete_empty = fl_delete_empty,
.walk = fl_walk,
.reoffload = fl_reoffload,
+ .hw_add = fl_hw_add,
+ .hw_del = fl_hw_del,
.dump = fl_dump,
+ .terse_dump = fl_terse_dump,
.bind_class = fl_bind_class,
.tmplt_create = fl_tmplt_create,
.tmplt_destroy = fl_tmplt_destroy,
.tmplt_dump = fl_tmplt_dump,
.owner = THIS_MODULE,
+ .flags = TCF_PROTO_OPS_DOIT_UNLOCKED,
};
static int __init cls_fl_init(void)
--
Gitblit v1.6.2