![Vlad Buslov](/assets/img/avatar_default.png)
In function int tc_new_tfilter() q pointer can be NULL when adding filter
on a shared block. With recent change that resets TCQ_F_CAN_BYPASS after
filter creation, following NULL pointer dereference happens in case parent
block is shared:
[ 212.925060] BUG: kernel NULL pointer dereference, address: 0000000000000010
[ 212.925445] #PF: supervisor write access in kernel mode
[ 212.925709] #PF: error_code(0x0002) - not-present page
[ 212.925965] PGD 8000000827923067 P4D 8000000827923067 PUD 827924067 PMD 0
[ 212.926302] Oops: 0002 [#1] SMP KASAN PTI
[ 212.926539] CPU: 18 PID: 2617 Comm: tc Tainted: G B 5.2.0+ #512
[ 212.926938] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017
[ 212.927364] RIP: 0010:tc_new_tfilter+0x698/0xd40
[ 212.927633] Code: 74 0d 48 85 c0 74 08 48 89 ef e8 03 aa 62 00 48 8b 84 24 a0 00 00 00 48 8d 78 10 48 89 44 24 18 e8 4d 0c 6b ff 48 8b 44 24 18 <83> 60 10 f
b 48 85 ed 0f 85 3d fe ff ff e9 4f fe ff ff e8 81 26 f8
[ 212.928607] RSP: 0018:ffff88884fd5f5d8 EFLAGS: 00010296
[ 212.928905] RAX: 0000000000000000 RBX: 0000000000000000 RCX: dffffc0000000000
[ 212.929201] RDX: 0000000000000007 RSI: 0000000000000004 RDI: 0000000000000297
[ 212.929402] RBP: ffff88886bedd600 R08: ffffffffb91d4b51 R09: fffffbfff7616e4d
[ 212.929609] R10: fffffbfff7616e4c R11: ffffffffbb0b7263 R12: ffff88886bc61040
[ 212.929803] R13: ffff88884fd5f950 R14: ffffc900039c5000 R15: ffff88835e927680
[ 212.929999] FS: 00007fe7c50b6480(0000) GS:ffff88886f980000(0000) knlGS:0000000000000000
[ 212.930235] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 212.930394] CR2: 0000000000000010 CR3: 000000085bd04002 CR4: 00000000001606e0
[ 212.930588] Call Trace:
[ 212.930682] ? tc_del_tfilter+0xa40/0xa40
[ 212.930811] ? __lock_acquire+0x5b5/0x2460
[ 212.930948] ? find_held_lock+0x85/0xa0
[ 212.931081] ? tc_del_tfilter+0xa40/0xa40
[ 212.931201] rtnetlink_rcv_msg+0x4ab/0x5f0
[ 212.931332] ? rtnl_dellink+0x490/0x490
[ 212.931454] ? lockdep_hardirqs_on+0x260/0x260
[ 212.931589] ? netlink_deliver_tap+0xab/0x5a0
[ 212.931717] ? match_held_lock+0x1b/0x240
[ 212.931844] netlink_rcv_skb+0xd0/0x200
[ 212.931958] ? rtnl_dellink+0x490/0x490
[ 212.932079] ? netlink_ack+0x440/0x440
[ 212.932205] ? netlink_deliver_tap+0x161/0x5a0
[ 212.932335] ? lock_downgrade+0x360/0x360
[ 212.932457] ? lock_acquire+0xe5/0x210
[ 212.932579] netlink_unicast+0x296/0x350
[ 212.932705] ? netlink_attachskb+0x390/0x390
[ 212.932834] ? _copy_from_iter_full+0xe0/0x3a0
[ 212.932976] netlink_sendmsg+0x394/0x600
[ 212.937998] ? netlink_unicast+0x350/0x350
[ 212.943033] ? move_addr_to_kernel.part.0+0x90/0x90
[ 212.948115] ? netlink_unicast+0x350/0x350
[ 212.953185] sock_sendmsg+0x96/0xa0
[ 212.958099] ___sys_sendmsg+0x482/0x520
[ 212.962881] ? match_held_lock+0x1b/0x240
[ 212.967618] ? copy_msghdr_from_user+0x250/0x250
[ 212.972337] ? lock_downgrade+0x360/0x360
[ 212.976973] ? rwlock_bug.part.0+0x60/0x60
[ 212.981548] ? __mod_node_page_state+0x1f/0xa0
[ 212.986060] ? match_held_lock+0x1b/0x240
[ 212.990567] ? find_held_lock+0x85/0xa0
[ 212.994989] ? do_user_addr_fault+0x349/0x5b0
[ 212.999387] ? lock_downgrade+0x360/0x360
[ 213.003713] ? find_held_lock+0x85/0xa0
[ 213.007972] ? __fget_light+0xa1/0xf0
[ 213.012143] ? sockfd_lookup_light+0x91/0xb0
[ 213.016165] __sys_sendmsg+0xba/0x130
[ 213.020040] ? __sys_sendmsg_sock+0xb0/0xb0
[ 213.023870] ? handle_mm_fault+0x337/0x470
[ 213.027592] ? page_fault+0x8/0x30
[ 213.031316] ? lockdep_hardirqs_off+0xbe/0x100
[ 213.034999] ? mark_held_locks+0x24/0x90
[ 213.038671] ? do_syscall_64+0x1e/0xe0
[ 213.042297] do_syscall_64+0x74/0xe0
[ 213.045828] entry_SYSCALL_64_after_hwframe+0x49/0xbe
[ 213.049354] RIP: 0033:0x7fe7c527c7b8
[ 213.052792] Code: 89 02 48 c7 c0 ff ff ff ff eb bb 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 65 8f 0c 00 8b 00 85 c0 75 17 b8 2e 00 00 00 0f 05 <48> 3d 00 f
0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 48 83 ec 28 89 54
[ 213.060269] RSP: 002b:00007ffc3f7908a8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[ 213.064144] RAX: ffffffffffffffda RBX: 000000005d34716f RCX: 00007fe7c527c7b8
[ 213.068094] RDX: 0000000000000000 RSI: 00007ffc3f790910 RDI: 0000000000000003
[ 213.072109] RBP: 0000000000000000 R08: 0000000000000001 R09: 00007fe7c5340cc0
[ 213.076113] R10: 0000000000404ec2 R11: 0000000000000246 R12: 0000000000000080
[ 213.080146] R13: 0000000000480640 R14: 0000000000000080 R15: 0000000000000000
[ 213.084147] Modules linked in: act_gact cls_flower sch_ingress nfsv3 nfs_acl nfs lockd grace fscache bridge stp llc sunrpc intel_rapl_msr intel_rapl_common
[<1;69;32Msb_edac rdma_ucm rdma_cm x86_pkg_temp_thermal iw_cm intel_powerclamp ib_cm coretemp kvm_intel kvm irqbypass mlx5_ib ib_uverbs ib_core crct10dif_pclmul crc32_pc
lmul crc32c_intel ghash_clmulni_intel mlx5_core intel_cstate intel_uncore iTCO_wdt igb iTCO_vendor_support mlxfw mei_me ptp ses intel_rapl_perf mei pcspkr ipmi
_ssif i2c_i801 joydev enclosure pps_core lpc_ich ioatdma wmi dca ipmi_si ipmi_devintf ipmi_msghandler acpi_power_meter acpi_pad ast i2c_algo_bit drm_vram_helpe
r ttm drm_kms_helper drm mpt3sas raid_class scsi_transport_sas
[ 213.112326] CR2: 0000000000000010
[ 213.117429] ---[ end trace adb58eb0a4ee6283 ]---
Verify that q pointer is not NULL before setting the 'flags' field.
Fixes: 3f05e6886a
("net_sched: unset TCQ_F_CAN_BYPASS when adding filters")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
3362 lines
82 KiB
C
3362 lines
82 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
/*
|
|
* net/sched/cls_api.c Packet classifier API.
|
|
*
|
|
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
|
|
*
|
|
* Changes:
|
|
*
|
|
* Eduardo J. Blanco <ejbs@netlabs.com.uy> :990222: kmod support
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/types.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/string.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/err.h>
|
|
#include <linux/skbuff.h>
|
|
#include <linux/init.h>
|
|
#include <linux/kmod.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/idr.h>
|
|
#include <linux/rhashtable.h>
|
|
#include <net/net_namespace.h>
|
|
#include <net/sock.h>
|
|
#include <net/netlink.h>
|
|
#include <net/pkt_sched.h>
|
|
#include <net/pkt_cls.h>
|
|
#include <net/tc_act/tc_pedit.h>
|
|
#include <net/tc_act/tc_mirred.h>
|
|
#include <net/tc_act/tc_vlan.h>
|
|
#include <net/tc_act/tc_tunnel_key.h>
|
|
#include <net/tc_act/tc_csum.h>
|
|
#include <net/tc_act/tc_gact.h>
|
|
#include <net/tc_act/tc_police.h>
|
|
#include <net/tc_act/tc_sample.h>
|
|
#include <net/tc_act/tc_skbedit.h>
|
|
#include <net/tc_act/tc_ct.h>
|
|
|
|
extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1];
|
|
|
|
/* The list of all installed classifier types */
|
|
static LIST_HEAD(tcf_proto_base);
|
|
|
|
/* Protects list of registered TC modules. It is pure SMP lock. */
|
|
static DEFINE_RWLOCK(cls_mod_lock);
|
|
|
|
/* Find classifier type by string name */
|
|
|
|
static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind)
|
|
{
|
|
const struct tcf_proto_ops *t, *res = NULL;
|
|
|
|
if (kind) {
|
|
read_lock(&cls_mod_lock);
|
|
list_for_each_entry(t, &tcf_proto_base, head) {
|
|
if (strcmp(kind, t->kind) == 0) {
|
|
if (try_module_get(t->owner))
|
|
res = t;
|
|
break;
|
|
}
|
|
}
|
|
read_unlock(&cls_mod_lock);
|
|
}
|
|
return res;
|
|
}
|
|
|
|
static const struct tcf_proto_ops *
|
|
tcf_proto_lookup_ops(const char *kind, bool rtnl_held,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
const struct tcf_proto_ops *ops;
|
|
|
|
ops = __tcf_proto_lookup_ops(kind);
|
|
if (ops)
|
|
return ops;
|
|
#ifdef CONFIG_MODULES
|
|
if (rtnl_held)
|
|
rtnl_unlock();
|
|
request_module("cls_%s", kind);
|
|
if (rtnl_held)
|
|
rtnl_lock();
|
|
ops = __tcf_proto_lookup_ops(kind);
|
|
/* We dropped the RTNL semaphore in order to perform
|
|
* the module load. So, even if we succeeded in loading
|
|
* the module we have to replay the request. We indicate
|
|
* this using -EAGAIN.
|
|
*/
|
|
if (ops) {
|
|
module_put(ops->owner);
|
|
return ERR_PTR(-EAGAIN);
|
|
}
|
|
#endif
|
|
NL_SET_ERR_MSG(extack, "TC classifier not found");
|
|
return ERR_PTR(-ENOENT);
|
|
}
|
|
|
|
/* Register(unregister) new classifier type */
|
|
|
|
int register_tcf_proto_ops(struct tcf_proto_ops *ops)
|
|
{
|
|
struct tcf_proto_ops *t;
|
|
int rc = -EEXIST;
|
|
|
|
write_lock(&cls_mod_lock);
|
|
list_for_each_entry(t, &tcf_proto_base, head)
|
|
if (!strcmp(ops->kind, t->kind))
|
|
goto out;
|
|
|
|
list_add_tail(&ops->head, &tcf_proto_base);
|
|
rc = 0;
|
|
out:
|
|
write_unlock(&cls_mod_lock);
|
|
return rc;
|
|
}
|
|
EXPORT_SYMBOL(register_tcf_proto_ops);
|
|
|
|
static struct workqueue_struct *tc_filter_wq;
|
|
|
|
int unregister_tcf_proto_ops(struct tcf_proto_ops *ops)
|
|
{
|
|
struct tcf_proto_ops *t;
|
|
int rc = -ENOENT;
|
|
|
|
/* Wait for outstanding call_rcu()s, if any, from a
|
|
* tcf_proto_ops's destroy() handler.
|
|
*/
|
|
rcu_barrier();
|
|
flush_workqueue(tc_filter_wq);
|
|
|
|
write_lock(&cls_mod_lock);
|
|
list_for_each_entry(t, &tcf_proto_base, head) {
|
|
if (t == ops) {
|
|
list_del(&t->head);
|
|
rc = 0;
|
|
break;
|
|
}
|
|
}
|
|
write_unlock(&cls_mod_lock);
|
|
return rc;
|
|
}
|
|
EXPORT_SYMBOL(unregister_tcf_proto_ops);
|
|
|
|
bool tcf_queue_work(struct rcu_work *rwork, work_func_t func)
|
|
{
|
|
INIT_RCU_WORK(rwork, func);
|
|
return queue_rcu_work(tc_filter_wq, rwork);
|
|
}
|
|
EXPORT_SYMBOL(tcf_queue_work);
|
|
|
|
/* Select new prio value from the range, managed by kernel. */
|
|
|
|
static inline u32 tcf_auto_prio(struct tcf_proto *tp)
|
|
{
|
|
u32 first = TC_H_MAKE(0xC0000000U, 0U);
|
|
|
|
if (tp)
|
|
first = tp->prio - 1;
|
|
|
|
return TC_H_MAJ(first);
|
|
}
|
|
|
|
static bool tcf_proto_is_unlocked(const char *kind)
|
|
{
|
|
const struct tcf_proto_ops *ops;
|
|
bool ret;
|
|
|
|
ops = tcf_proto_lookup_ops(kind, false, NULL);
|
|
/* On error return false to take rtnl lock. Proto lookup/create
|
|
* functions will perform lookup again and properly handle errors.
|
|
*/
|
|
if (IS_ERR(ops))
|
|
return false;
|
|
|
|
ret = !!(ops->flags & TCF_PROTO_OPS_DOIT_UNLOCKED);
|
|
module_put(ops->owner);
|
|
return ret;
|
|
}
|
|
|
|
static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol,
|
|
u32 prio, struct tcf_chain *chain,
|
|
bool rtnl_held,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tcf_proto *tp;
|
|
int err;
|
|
|
|
tp = kzalloc(sizeof(*tp), GFP_KERNEL);
|
|
if (!tp)
|
|
return ERR_PTR(-ENOBUFS);
|
|
|
|
tp->ops = tcf_proto_lookup_ops(kind, rtnl_held, extack);
|
|
if (IS_ERR(tp->ops)) {
|
|
err = PTR_ERR(tp->ops);
|
|
goto errout;
|
|
}
|
|
tp->classify = tp->ops->classify;
|
|
tp->protocol = protocol;
|
|
tp->prio = prio;
|
|
tp->chain = chain;
|
|
spin_lock_init(&tp->lock);
|
|
refcount_set(&tp->refcnt, 1);
|
|
|
|
err = tp->ops->init(tp);
|
|
if (err) {
|
|
module_put(tp->ops->owner);
|
|
goto errout;
|
|
}
|
|
return tp;
|
|
|
|
errout:
|
|
kfree(tp);
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
static void tcf_proto_get(struct tcf_proto *tp)
|
|
{
|
|
refcount_inc(&tp->refcnt);
|
|
}
|
|
|
|
static void tcf_chain_put(struct tcf_chain *chain);
|
|
|
|
static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
tp->ops->destroy(tp, rtnl_held, extack);
|
|
tcf_chain_put(tp->chain);
|
|
module_put(tp->ops->owner);
|
|
kfree_rcu(tp, rcu);
|
|
}
|
|
|
|
static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
if (refcount_dec_and_test(&tp->refcnt))
|
|
tcf_proto_destroy(tp, rtnl_held, extack);
|
|
}
|
|
|
|
static int walker_check_empty(struct tcf_proto *tp, void *fh,
|
|
struct tcf_walker *arg)
|
|
{
|
|
if (fh) {
|
|
arg->nonempty = true;
|
|
return -1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static bool tcf_proto_is_empty(struct tcf_proto *tp, bool rtnl_held)
|
|
{
|
|
struct tcf_walker walker = { .fn = walker_check_empty, };
|
|
|
|
if (tp->ops->walk) {
|
|
tp->ops->walk(tp, &walker, rtnl_held);
|
|
return !walker.nonempty;
|
|
}
|
|
return true;
|
|
}
|
|
|
|
static bool tcf_proto_check_delete(struct tcf_proto *tp, bool rtnl_held)
|
|
{
|
|
spin_lock(&tp->lock);
|
|
if (tcf_proto_is_empty(tp, rtnl_held))
|
|
tp->deleting = true;
|
|
spin_unlock(&tp->lock);
|
|
return tp->deleting;
|
|
}
|
|
|
|
static void tcf_proto_mark_delete(struct tcf_proto *tp)
|
|
{
|
|
spin_lock(&tp->lock);
|
|
tp->deleting = true;
|
|
spin_unlock(&tp->lock);
|
|
}
|
|
|
|
static bool tcf_proto_is_deleting(struct tcf_proto *tp)
|
|
{
|
|
bool deleting;
|
|
|
|
spin_lock(&tp->lock);
|
|
deleting = tp->deleting;
|
|
spin_unlock(&tp->lock);
|
|
|
|
return deleting;
|
|
}
|
|
|
|
#define ASSERT_BLOCK_LOCKED(block) \
|
|
lockdep_assert_held(&(block)->lock)
|
|
|
|
struct tcf_filter_chain_list_item {
|
|
struct list_head list;
|
|
tcf_chain_head_change_t *chain_head_change;
|
|
void *chain_head_change_priv;
|
|
};
|
|
|
|
static struct tcf_chain *tcf_chain_create(struct tcf_block *block,
|
|
u32 chain_index)
|
|
{
|
|
struct tcf_chain *chain;
|
|
|
|
ASSERT_BLOCK_LOCKED(block);
|
|
|
|
chain = kzalloc(sizeof(*chain), GFP_KERNEL);
|
|
if (!chain)
|
|
return NULL;
|
|
list_add_tail(&chain->list, &block->chain_list);
|
|
mutex_init(&chain->filter_chain_lock);
|
|
chain->block = block;
|
|
chain->index = chain_index;
|
|
chain->refcnt = 1;
|
|
if (!chain->index)
|
|
block->chain0.chain = chain;
|
|
return chain;
|
|
}
|
|
|
|
static void tcf_chain_head_change_item(struct tcf_filter_chain_list_item *item,
|
|
struct tcf_proto *tp_head)
|
|
{
|
|
if (item->chain_head_change)
|
|
item->chain_head_change(tp_head, item->chain_head_change_priv);
|
|
}
|
|
|
|
static void tcf_chain0_head_change(struct tcf_chain *chain,
|
|
struct tcf_proto *tp_head)
|
|
{
|
|
struct tcf_filter_chain_list_item *item;
|
|
struct tcf_block *block = chain->block;
|
|
|
|
if (chain->index)
|
|
return;
|
|
|
|
mutex_lock(&block->lock);
|
|
list_for_each_entry(item, &block->chain0.filter_chain_list, list)
|
|
tcf_chain_head_change_item(item, tp_head);
|
|
mutex_unlock(&block->lock);
|
|
}
|
|
|
|
/* Returns true if block can be safely freed. */
|
|
|
|
static bool tcf_chain_detach(struct tcf_chain *chain)
|
|
{
|
|
struct tcf_block *block = chain->block;
|
|
|
|
ASSERT_BLOCK_LOCKED(block);
|
|
|
|
list_del(&chain->list);
|
|
if (!chain->index)
|
|
block->chain0.chain = NULL;
|
|
|
|
if (list_empty(&block->chain_list) &&
|
|
refcount_read(&block->refcnt) == 0)
|
|
return true;
|
|
|
|
return false;
|
|
}
|
|
|
|
static void tcf_block_destroy(struct tcf_block *block)
|
|
{
|
|
mutex_destroy(&block->lock);
|
|
kfree_rcu(block, rcu);
|
|
}
|
|
|
|
static void tcf_chain_destroy(struct tcf_chain *chain, bool free_block)
|
|
{
|
|
struct tcf_block *block = chain->block;
|
|
|
|
mutex_destroy(&chain->filter_chain_lock);
|
|
kfree_rcu(chain, rcu);
|
|
if (free_block)
|
|
tcf_block_destroy(block);
|
|
}
|
|
|
|
static void tcf_chain_hold(struct tcf_chain *chain)
|
|
{
|
|
ASSERT_BLOCK_LOCKED(chain->block);
|
|
|
|
++chain->refcnt;
|
|
}
|
|
|
|
static bool tcf_chain_held_by_acts_only(struct tcf_chain *chain)
|
|
{
|
|
ASSERT_BLOCK_LOCKED(chain->block);
|
|
|
|
/* In case all the references are action references, this
|
|
* chain should not be shown to the user.
|
|
*/
|
|
return chain->refcnt == chain->action_refcnt;
|
|
}
|
|
|
|
static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block,
|
|
u32 chain_index)
|
|
{
|
|
struct tcf_chain *chain;
|
|
|
|
ASSERT_BLOCK_LOCKED(block);
|
|
|
|
list_for_each_entry(chain, &block->chain_list, list) {
|
|
if (chain->index == chain_index)
|
|
return chain;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb,
|
|
u32 seq, u16 flags, int event, bool unicast);
|
|
|
|
static struct tcf_chain *__tcf_chain_get(struct tcf_block *block,
|
|
u32 chain_index, bool create,
|
|
bool by_act)
|
|
{
|
|
struct tcf_chain *chain = NULL;
|
|
bool is_first_reference;
|
|
|
|
mutex_lock(&block->lock);
|
|
chain = tcf_chain_lookup(block, chain_index);
|
|
if (chain) {
|
|
tcf_chain_hold(chain);
|
|
} else {
|
|
if (!create)
|
|
goto errout;
|
|
chain = tcf_chain_create(block, chain_index);
|
|
if (!chain)
|
|
goto errout;
|
|
}
|
|
|
|
if (by_act)
|
|
++chain->action_refcnt;
|
|
is_first_reference = chain->refcnt - chain->action_refcnt == 1;
|
|
mutex_unlock(&block->lock);
|
|
|
|
/* Send notification only in case we got the first
|
|
* non-action reference. Until then, the chain acts only as
|
|
* a placeholder for actions pointing to it and user ought
|
|
* not know about them.
|
|
*/
|
|
if (is_first_reference && !by_act)
|
|
tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL,
|
|
RTM_NEWCHAIN, false);
|
|
|
|
return chain;
|
|
|
|
errout:
|
|
mutex_unlock(&block->lock);
|
|
return chain;
|
|
}
|
|
|
|
static struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
|
|
bool create)
|
|
{
|
|
return __tcf_chain_get(block, chain_index, create, false);
|
|
}
|
|
|
|
struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index)
|
|
{
|
|
return __tcf_chain_get(block, chain_index, true, true);
|
|
}
|
|
EXPORT_SYMBOL(tcf_chain_get_by_act);
|
|
|
|
static void tc_chain_tmplt_del(const struct tcf_proto_ops *tmplt_ops,
|
|
void *tmplt_priv);
|
|
static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops,
|
|
void *tmplt_priv, u32 chain_index,
|
|
struct tcf_block *block, struct sk_buff *oskb,
|
|
u32 seq, u16 flags, bool unicast);
|
|
|
|
static void __tcf_chain_put(struct tcf_chain *chain, bool by_act,
|
|
bool explicitly_created)
|
|
{
|
|
struct tcf_block *block = chain->block;
|
|
const struct tcf_proto_ops *tmplt_ops;
|
|
bool free_block = false;
|
|
unsigned int refcnt;
|
|
void *tmplt_priv;
|
|
|
|
mutex_lock(&block->lock);
|
|
if (explicitly_created) {
|
|
if (!chain->explicitly_created) {
|
|
mutex_unlock(&block->lock);
|
|
return;
|
|
}
|
|
chain->explicitly_created = false;
|
|
}
|
|
|
|
if (by_act)
|
|
chain->action_refcnt--;
|
|
|
|
/* tc_chain_notify_delete can't be called while holding block lock.
|
|
* However, when block is unlocked chain can be changed concurrently, so
|
|
* save these to temporary variables.
|
|
*/
|
|
refcnt = --chain->refcnt;
|
|
tmplt_ops = chain->tmplt_ops;
|
|
tmplt_priv = chain->tmplt_priv;
|
|
|
|
/* The last dropped non-action reference will trigger notification. */
|
|
if (refcnt - chain->action_refcnt == 0 && !by_act) {
|
|
tc_chain_notify_delete(tmplt_ops, tmplt_priv, chain->index,
|
|
block, NULL, 0, 0, false);
|
|
/* Last reference to chain, no need to lock. */
|
|
chain->flushing = false;
|
|
}
|
|
|
|
if (refcnt == 0)
|
|
free_block = tcf_chain_detach(chain);
|
|
mutex_unlock(&block->lock);
|
|
|
|
if (refcnt == 0) {
|
|
tc_chain_tmplt_del(tmplt_ops, tmplt_priv);
|
|
tcf_chain_destroy(chain, free_block);
|
|
}
|
|
}
|
|
|
|
static void tcf_chain_put(struct tcf_chain *chain)
|
|
{
|
|
__tcf_chain_put(chain, false, false);
|
|
}
|
|
|
|
void tcf_chain_put_by_act(struct tcf_chain *chain)
|
|
{
|
|
__tcf_chain_put(chain, true, false);
|
|
}
|
|
EXPORT_SYMBOL(tcf_chain_put_by_act);
|
|
|
|
static void tcf_chain_put_explicitly_created(struct tcf_chain *chain)
|
|
{
|
|
__tcf_chain_put(chain, false, true);
|
|
}
|
|
|
|
static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held)
|
|
{
|
|
struct tcf_proto *tp, *tp_next;
|
|
|
|
mutex_lock(&chain->filter_chain_lock);
|
|
tp = tcf_chain_dereference(chain->filter_chain, chain);
|
|
RCU_INIT_POINTER(chain->filter_chain, NULL);
|
|
tcf_chain0_head_change(chain, NULL);
|
|
chain->flushing = true;
|
|
mutex_unlock(&chain->filter_chain_lock);
|
|
|
|
while (tp) {
|
|
tp_next = rcu_dereference_protected(tp->next, 1);
|
|
tcf_proto_put(tp, rtnl_held, NULL);
|
|
tp = tp_next;
|
|
}
|
|
}
|
|
|
|
static struct tcf_block *tc_dev_ingress_block(struct net_device *dev)
|
|
{
|
|
const struct Qdisc_class_ops *cops;
|
|
struct Qdisc *qdisc;
|
|
|
|
if (!dev_ingress_queue(dev))
|
|
return NULL;
|
|
|
|
qdisc = dev_ingress_queue(dev)->qdisc_sleeping;
|
|
if (!qdisc)
|
|
return NULL;
|
|
|
|
cops = qdisc->ops->cl_ops;
|
|
if (!cops)
|
|
return NULL;
|
|
|
|
if (!cops->tcf_block)
|
|
return NULL;
|
|
|
|
return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL);
|
|
}
|
|
|
|
static struct rhashtable indr_setup_block_ht;
|
|
|
|
struct tc_indr_block_dev {
|
|
struct rhash_head ht_node;
|
|
struct net_device *dev;
|
|
unsigned int refcnt;
|
|
struct list_head cb_list;
|
|
struct tcf_block *block;
|
|
};
|
|
|
|
struct tc_indr_block_cb {
|
|
struct list_head list;
|
|
void *cb_priv;
|
|
tc_indr_block_bind_cb_t *cb;
|
|
void *cb_ident;
|
|
};
|
|
|
|
static const struct rhashtable_params tc_indr_setup_block_ht_params = {
|
|
.key_offset = offsetof(struct tc_indr_block_dev, dev),
|
|
.head_offset = offsetof(struct tc_indr_block_dev, ht_node),
|
|
.key_len = sizeof(struct net_device *),
|
|
};
|
|
|
|
static struct tc_indr_block_dev *
|
|
tc_indr_block_dev_lookup(struct net_device *dev)
|
|
{
|
|
return rhashtable_lookup_fast(&indr_setup_block_ht, &dev,
|
|
tc_indr_setup_block_ht_params);
|
|
}
|
|
|
|
static struct tc_indr_block_dev *tc_indr_block_dev_get(struct net_device *dev)
|
|
{
|
|
struct tc_indr_block_dev *indr_dev;
|
|
|
|
indr_dev = tc_indr_block_dev_lookup(dev);
|
|
if (indr_dev)
|
|
goto inc_ref;
|
|
|
|
indr_dev = kzalloc(sizeof(*indr_dev), GFP_KERNEL);
|
|
if (!indr_dev)
|
|
return NULL;
|
|
|
|
INIT_LIST_HEAD(&indr_dev->cb_list);
|
|
indr_dev->dev = dev;
|
|
indr_dev->block = tc_dev_ingress_block(dev);
|
|
if (rhashtable_insert_fast(&indr_setup_block_ht, &indr_dev->ht_node,
|
|
tc_indr_setup_block_ht_params)) {
|
|
kfree(indr_dev);
|
|
return NULL;
|
|
}
|
|
|
|
inc_ref:
|
|
indr_dev->refcnt++;
|
|
return indr_dev;
|
|
}
|
|
|
|
static void tc_indr_block_dev_put(struct tc_indr_block_dev *indr_dev)
|
|
{
|
|
if (--indr_dev->refcnt)
|
|
return;
|
|
|
|
rhashtable_remove_fast(&indr_setup_block_ht, &indr_dev->ht_node,
|
|
tc_indr_setup_block_ht_params);
|
|
kfree(indr_dev);
|
|
}
|
|
|
|
static struct tc_indr_block_cb *
|
|
tc_indr_block_cb_lookup(struct tc_indr_block_dev *indr_dev,
|
|
tc_indr_block_bind_cb_t *cb, void *cb_ident)
|
|
{
|
|
struct tc_indr_block_cb *indr_block_cb;
|
|
|
|
list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list)
|
|
if (indr_block_cb->cb == cb &&
|
|
indr_block_cb->cb_ident == cb_ident)
|
|
return indr_block_cb;
|
|
return NULL;
|
|
}
|
|
|
|
static struct tc_indr_block_cb *
|
|
tc_indr_block_cb_add(struct tc_indr_block_dev *indr_dev, void *cb_priv,
|
|
tc_indr_block_bind_cb_t *cb, void *cb_ident)
|
|
{
|
|
struct tc_indr_block_cb *indr_block_cb;
|
|
|
|
indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident);
|
|
if (indr_block_cb)
|
|
return ERR_PTR(-EEXIST);
|
|
|
|
indr_block_cb = kzalloc(sizeof(*indr_block_cb), GFP_KERNEL);
|
|
if (!indr_block_cb)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
indr_block_cb->cb_priv = cb_priv;
|
|
indr_block_cb->cb = cb;
|
|
indr_block_cb->cb_ident = cb_ident;
|
|
list_add(&indr_block_cb->list, &indr_dev->cb_list);
|
|
|
|
return indr_block_cb;
|
|
}
|
|
|
|
static void tc_indr_block_cb_del(struct tc_indr_block_cb *indr_block_cb)
|
|
{
|
|
list_del(&indr_block_cb->list);
|
|
kfree(indr_block_cb);
|
|
}
|
|
|
|
static int tcf_block_setup(struct tcf_block *block,
|
|
struct flow_block_offload *bo);
|
|
|
|
static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev,
|
|
struct tc_indr_block_cb *indr_block_cb,
|
|
enum flow_block_command command)
|
|
{
|
|
struct flow_block_offload bo = {
|
|
.command = command,
|
|
.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS,
|
|
.net = dev_net(indr_dev->dev),
|
|
.block_shared = tcf_block_non_null_shared(indr_dev->block),
|
|
};
|
|
INIT_LIST_HEAD(&bo.cb_list);
|
|
|
|
if (!indr_dev->block)
|
|
return;
|
|
|
|
bo.block = &indr_dev->block->flow_block;
|
|
|
|
indr_block_cb->cb(indr_dev->dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK,
|
|
&bo);
|
|
tcf_block_setup(indr_dev->block, &bo);
|
|
}
|
|
|
|
int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
|
|
tc_indr_block_bind_cb_t *cb, void *cb_ident)
|
|
{
|
|
struct tc_indr_block_cb *indr_block_cb;
|
|
struct tc_indr_block_dev *indr_dev;
|
|
int err;
|
|
|
|
indr_dev = tc_indr_block_dev_get(dev);
|
|
if (!indr_dev)
|
|
return -ENOMEM;
|
|
|
|
indr_block_cb = tc_indr_block_cb_add(indr_dev, cb_priv, cb, cb_ident);
|
|
err = PTR_ERR_OR_ZERO(indr_block_cb);
|
|
if (err)
|
|
goto err_dev_put;
|
|
|
|
tc_indr_block_ing_cmd(indr_dev, indr_block_cb, FLOW_BLOCK_BIND);
|
|
return 0;
|
|
|
|
err_dev_put:
|
|
tc_indr_block_dev_put(indr_dev);
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__tc_indr_block_cb_register);
|
|
|
|
int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
|
|
tc_indr_block_bind_cb_t *cb, void *cb_ident)
|
|
{
|
|
int err;
|
|
|
|
rtnl_lock();
|
|
err = __tc_indr_block_cb_register(dev, cb_priv, cb, cb_ident);
|
|
rtnl_unlock();
|
|
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL_GPL(tc_indr_block_cb_register);
|
|
|
|
void __tc_indr_block_cb_unregister(struct net_device *dev,
|
|
tc_indr_block_bind_cb_t *cb, void *cb_ident)
|
|
{
|
|
struct tc_indr_block_cb *indr_block_cb;
|
|
struct tc_indr_block_dev *indr_dev;
|
|
|
|
indr_dev = tc_indr_block_dev_lookup(dev);
|
|
if (!indr_dev)
|
|
return;
|
|
|
|
indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident);
|
|
if (!indr_block_cb)
|
|
return;
|
|
|
|
/* Send unbind message if required to free any block cbs. */
|
|
tc_indr_block_ing_cmd(indr_dev, indr_block_cb, FLOW_BLOCK_UNBIND);
|
|
tc_indr_block_cb_del(indr_block_cb);
|
|
tc_indr_block_dev_put(indr_dev);
|
|
}
|
|
EXPORT_SYMBOL_GPL(__tc_indr_block_cb_unregister);
|
|
|
|
void tc_indr_block_cb_unregister(struct net_device *dev,
|
|
tc_indr_block_bind_cb_t *cb, void *cb_ident)
|
|
{
|
|
rtnl_lock();
|
|
__tc_indr_block_cb_unregister(dev, cb, cb_ident);
|
|
rtnl_unlock();
|
|
}
|
|
EXPORT_SYMBOL_GPL(tc_indr_block_cb_unregister);
|
|
|
|
static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev,
|
|
struct tcf_block_ext_info *ei,
|
|
enum flow_block_command command,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tc_indr_block_cb *indr_block_cb;
|
|
struct tc_indr_block_dev *indr_dev;
|
|
struct flow_block_offload bo = {
|
|
.command = command,
|
|
.binder_type = ei->binder_type,
|
|
.net = dev_net(dev),
|
|
.block = &block->flow_block,
|
|
.block_shared = tcf_block_shared(block),
|
|
.extack = extack,
|
|
};
|
|
INIT_LIST_HEAD(&bo.cb_list);
|
|
|
|
indr_dev = tc_indr_block_dev_lookup(dev);
|
|
if (!indr_dev)
|
|
return;
|
|
|
|
indr_dev->block = command == FLOW_BLOCK_BIND ? block : NULL;
|
|
|
|
list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list)
|
|
indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK,
|
|
&bo);
|
|
|
|
tcf_block_setup(block, &bo);
|
|
}
|
|
|
|
static bool tcf_block_offload_in_use(struct tcf_block *block)
|
|
{
|
|
return block->offloadcnt;
|
|
}
|
|
|
|
static int tcf_block_offload_cmd(struct tcf_block *block,
|
|
struct net_device *dev,
|
|
struct tcf_block_ext_info *ei,
|
|
enum flow_block_command command,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct flow_block_offload bo = {};
|
|
int err;
|
|
|
|
bo.net = dev_net(dev);
|
|
bo.command = command;
|
|
bo.binder_type = ei->binder_type;
|
|
bo.block = &block->flow_block;
|
|
bo.block_shared = tcf_block_shared(block);
|
|
bo.extack = extack;
|
|
INIT_LIST_HEAD(&bo.cb_list);
|
|
|
|
err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
|
|
if (err < 0)
|
|
return err;
|
|
|
|
return tcf_block_setup(block, &bo);
|
|
}
|
|
|
|
static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
|
|
struct tcf_block_ext_info *ei,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct net_device *dev = q->dev_queue->dev;
|
|
int err;
|
|
|
|
if (!dev->netdev_ops->ndo_setup_tc)
|
|
goto no_offload_dev_inc;
|
|
|
|
/* If tc offload feature is disabled and the block we try to bind
|
|
* to already has some offloaded filters, forbid to bind.
|
|
*/
|
|
if (!tc_can_offload(dev) && tcf_block_offload_in_use(block)) {
|
|
NL_SET_ERR_MSG(extack, "Bind to offloaded block failed as dev has offload disabled");
|
|
return -EOPNOTSUPP;
|
|
}
|
|
|
|
err = tcf_block_offload_cmd(block, dev, ei, FLOW_BLOCK_BIND, extack);
|
|
if (err == -EOPNOTSUPP)
|
|
goto no_offload_dev_inc;
|
|
if (err)
|
|
return err;
|
|
|
|
tc_indr_block_call(block, dev, ei, FLOW_BLOCK_BIND, extack);
|
|
return 0;
|
|
|
|
no_offload_dev_inc:
|
|
if (tcf_block_offload_in_use(block))
|
|
return -EOPNOTSUPP;
|
|
block->nooffloaddevcnt++;
|
|
tc_indr_block_call(block, dev, ei, FLOW_BLOCK_BIND, extack);
|
|
return 0;
|
|
}
|
|
|
|
static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q,
|
|
struct tcf_block_ext_info *ei)
|
|
{
|
|
struct net_device *dev = q->dev_queue->dev;
|
|
int err;
|
|
|
|
tc_indr_block_call(block, dev, ei, FLOW_BLOCK_UNBIND, NULL);
|
|
|
|
if (!dev->netdev_ops->ndo_setup_tc)
|
|
goto no_offload_dev_dec;
|
|
err = tcf_block_offload_cmd(block, dev, ei, FLOW_BLOCK_UNBIND, NULL);
|
|
if (err == -EOPNOTSUPP)
|
|
goto no_offload_dev_dec;
|
|
return;
|
|
|
|
no_offload_dev_dec:
|
|
WARN_ON(block->nooffloaddevcnt-- == 0);
|
|
}
|
|
|
|
static int
|
|
tcf_chain0_head_change_cb_add(struct tcf_block *block,
|
|
struct tcf_block_ext_info *ei,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tcf_filter_chain_list_item *item;
|
|
struct tcf_chain *chain0;
|
|
|
|
item = kmalloc(sizeof(*item), GFP_KERNEL);
|
|
if (!item) {
|
|
NL_SET_ERR_MSG(extack, "Memory allocation for head change callback item failed");
|
|
return -ENOMEM;
|
|
}
|
|
item->chain_head_change = ei->chain_head_change;
|
|
item->chain_head_change_priv = ei->chain_head_change_priv;
|
|
|
|
mutex_lock(&block->lock);
|
|
chain0 = block->chain0.chain;
|
|
if (chain0)
|
|
tcf_chain_hold(chain0);
|
|
else
|
|
list_add(&item->list, &block->chain0.filter_chain_list);
|
|
mutex_unlock(&block->lock);
|
|
|
|
if (chain0) {
|
|
struct tcf_proto *tp_head;
|
|
|
|
mutex_lock(&chain0->filter_chain_lock);
|
|
|
|
tp_head = tcf_chain_dereference(chain0->filter_chain, chain0);
|
|
if (tp_head)
|
|
tcf_chain_head_change_item(item, tp_head);
|
|
|
|
mutex_lock(&block->lock);
|
|
list_add(&item->list, &block->chain0.filter_chain_list);
|
|
mutex_unlock(&block->lock);
|
|
|
|
mutex_unlock(&chain0->filter_chain_lock);
|
|
tcf_chain_put(chain0);
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void
|
|
tcf_chain0_head_change_cb_del(struct tcf_block *block,
|
|
struct tcf_block_ext_info *ei)
|
|
{
|
|
struct tcf_filter_chain_list_item *item;
|
|
|
|
mutex_lock(&block->lock);
|
|
list_for_each_entry(item, &block->chain0.filter_chain_list, list) {
|
|
if ((!ei->chain_head_change && !ei->chain_head_change_priv) ||
|
|
(item->chain_head_change == ei->chain_head_change &&
|
|
item->chain_head_change_priv == ei->chain_head_change_priv)) {
|
|
if (block->chain0.chain)
|
|
tcf_chain_head_change_item(item, NULL);
|
|
list_del(&item->list);
|
|
mutex_unlock(&block->lock);
|
|
|
|
kfree(item);
|
|
return;
|
|
}
|
|
}
|
|
mutex_unlock(&block->lock);
|
|
WARN_ON(1);
|
|
}
|
|
|
|
struct tcf_net {
|
|
spinlock_t idr_lock; /* Protects idr */
|
|
struct idr idr;
|
|
};
|
|
|
|
static unsigned int tcf_net_id;
|
|
|
|
static int tcf_block_insert(struct tcf_block *block, struct net *net,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tcf_net *tn = net_generic(net, tcf_net_id);
|
|
int err;
|
|
|
|
idr_preload(GFP_KERNEL);
|
|
spin_lock(&tn->idr_lock);
|
|
err = idr_alloc_u32(&tn->idr, block, &block->index, block->index,
|
|
GFP_NOWAIT);
|
|
spin_unlock(&tn->idr_lock);
|
|
idr_preload_end();
|
|
|
|
return err;
|
|
}
|
|
|
|
static void tcf_block_remove(struct tcf_block *block, struct net *net)
|
|
{
|
|
struct tcf_net *tn = net_generic(net, tcf_net_id);
|
|
|
|
spin_lock(&tn->idr_lock);
|
|
idr_remove(&tn->idr, block->index);
|
|
spin_unlock(&tn->idr_lock);
|
|
}
|
|
|
|
static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
|
|
u32 block_index,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tcf_block *block;
|
|
|
|
block = kzalloc(sizeof(*block), GFP_KERNEL);
|
|
if (!block) {
|
|
NL_SET_ERR_MSG(extack, "Memory allocation for block failed");
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
mutex_init(&block->lock);
|
|
flow_block_init(&block->flow_block);
|
|
INIT_LIST_HEAD(&block->chain_list);
|
|
INIT_LIST_HEAD(&block->owner_list);
|
|
INIT_LIST_HEAD(&block->chain0.filter_chain_list);
|
|
|
|
refcount_set(&block->refcnt, 1);
|
|
block->net = net;
|
|
block->index = block_index;
|
|
|
|
/* Don't store q pointer for blocks which are shared */
|
|
if (!tcf_block_shared(block))
|
|
block->q = q;
|
|
return block;
|
|
}
|
|
|
|
static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index)
|
|
{
|
|
struct tcf_net *tn = net_generic(net, tcf_net_id);
|
|
|
|
return idr_find(&tn->idr, block_index);
|
|
}
|
|
|
|
static struct tcf_block *tcf_block_refcnt_get(struct net *net, u32 block_index)
|
|
{
|
|
struct tcf_block *block;
|
|
|
|
rcu_read_lock();
|
|
block = tcf_block_lookup(net, block_index);
|
|
if (block && !refcount_inc_not_zero(&block->refcnt))
|
|
block = NULL;
|
|
rcu_read_unlock();
|
|
|
|
return block;
|
|
}
|
|
|
|
static struct tcf_chain *
|
|
__tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain)
|
|
{
|
|
mutex_lock(&block->lock);
|
|
if (chain)
|
|
chain = list_is_last(&chain->list, &block->chain_list) ?
|
|
NULL : list_next_entry(chain, list);
|
|
else
|
|
chain = list_first_entry_or_null(&block->chain_list,
|
|
struct tcf_chain, list);
|
|
|
|
/* skip all action-only chains */
|
|
while (chain && tcf_chain_held_by_acts_only(chain))
|
|
chain = list_is_last(&chain->list, &block->chain_list) ?
|
|
NULL : list_next_entry(chain, list);
|
|
|
|
if (chain)
|
|
tcf_chain_hold(chain);
|
|
mutex_unlock(&block->lock);
|
|
|
|
return chain;
|
|
}
|
|
|
|
/* Function to be used by all clients that want to iterate over all chains on
|
|
* block. It properly obtains block->lock and takes reference to chain before
|
|
* returning it. Users of this function must be tolerant to concurrent chain
|
|
* insertion/deletion or ensure that no concurrent chain modification is
|
|
* possible. Note that all netlink dump callbacks cannot guarantee to provide
|
|
* consistent dump because rtnl lock is released each time skb is filled with
|
|
* data and sent to user-space.
|
|
*/
|
|
|
|
struct tcf_chain *
|
|
tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain)
|
|
{
|
|
struct tcf_chain *chain_next = __tcf_get_next_chain(block, chain);
|
|
|
|
if (chain)
|
|
tcf_chain_put(chain);
|
|
|
|
return chain_next;
|
|
}
|
|
EXPORT_SYMBOL(tcf_get_next_chain);
|
|
|
|
static struct tcf_proto *
|
|
__tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp)
|
|
{
|
|
u32 prio = 0;
|
|
|
|
ASSERT_RTNL();
|
|
mutex_lock(&chain->filter_chain_lock);
|
|
|
|
if (!tp) {
|
|
tp = tcf_chain_dereference(chain->filter_chain, chain);
|
|
} else if (tcf_proto_is_deleting(tp)) {
|
|
/* 'deleting' flag is set and chain->filter_chain_lock was
|
|
* unlocked, which means next pointer could be invalid. Restart
|
|
* search.
|
|
*/
|
|
prio = tp->prio + 1;
|
|
tp = tcf_chain_dereference(chain->filter_chain, chain);
|
|
|
|
for (; tp; tp = tcf_chain_dereference(tp->next, chain))
|
|
if (!tp->deleting && tp->prio >= prio)
|
|
break;
|
|
} else {
|
|
tp = tcf_chain_dereference(tp->next, chain);
|
|
}
|
|
|
|
if (tp)
|
|
tcf_proto_get(tp);
|
|
|
|
mutex_unlock(&chain->filter_chain_lock);
|
|
|
|
return tp;
|
|
}
|
|
|
|
/* Function to be used by all clients that want to iterate over all tp's on
|
|
* chain. Users of this function must be tolerant to concurrent tp
|
|
* insertion/deletion or ensure that no concurrent chain modification is
|
|
* possible. Note that all netlink dump callbacks cannot guarantee to provide
|
|
* consistent dump because rtnl lock is released each time skb is filled with
|
|
* data and sent to user-space.
|
|
*/
|
|
|
|
struct tcf_proto *
|
|
tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp,
|
|
bool rtnl_held)
|
|
{
|
|
struct tcf_proto *tp_next = __tcf_get_next_proto(chain, tp);
|
|
|
|
if (tp)
|
|
tcf_proto_put(tp, rtnl_held, NULL);
|
|
|
|
return tp_next;
|
|
}
|
|
EXPORT_SYMBOL(tcf_get_next_proto);
|
|
|
|
static void tcf_block_flush_all_chains(struct tcf_block *block, bool rtnl_held)
|
|
{
|
|
struct tcf_chain *chain;
|
|
|
|
/* Last reference to block. At this point chains cannot be added or
|
|
* removed concurrently.
|
|
*/
|
|
for (chain = tcf_get_next_chain(block, NULL);
|
|
chain;
|
|
chain = tcf_get_next_chain(block, chain)) {
|
|
tcf_chain_put_explicitly_created(chain);
|
|
tcf_chain_flush(chain, rtnl_held);
|
|
}
|
|
}
|
|
|
|
/* Lookup Qdisc and increments its reference counter.
|
|
* Set parent, if necessary.
|
|
*/
|
|
|
|
static int __tcf_qdisc_find(struct net *net, struct Qdisc **q,
|
|
u32 *parent, int ifindex, bool rtnl_held,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
const struct Qdisc_class_ops *cops;
|
|
struct net_device *dev;
|
|
int err = 0;
|
|
|
|
if (ifindex == TCM_IFINDEX_MAGIC_BLOCK)
|
|
return 0;
|
|
|
|
rcu_read_lock();
|
|
|
|
/* Find link */
|
|
dev = dev_get_by_index_rcu(net, ifindex);
|
|
if (!dev) {
|
|
rcu_read_unlock();
|
|
return -ENODEV;
|
|
}
|
|
|
|
/* Find qdisc */
|
|
if (!*parent) {
|
|
*q = dev->qdisc;
|
|
*parent = (*q)->handle;
|
|
} else {
|
|
*q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent));
|
|
if (!*q) {
|
|
NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
|
|
err = -EINVAL;
|
|
goto errout_rcu;
|
|
}
|
|
}
|
|
|
|
*q = qdisc_refcount_inc_nz(*q);
|
|
if (!*q) {
|
|
NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
|
|
err = -EINVAL;
|
|
goto errout_rcu;
|
|
}
|
|
|
|
/* Is it classful? */
|
|
cops = (*q)->ops->cl_ops;
|
|
if (!cops) {
|
|
NL_SET_ERR_MSG(extack, "Qdisc not classful");
|
|
err = -EINVAL;
|
|
goto errout_qdisc;
|
|
}
|
|
|
|
if (!cops->tcf_block) {
|
|
NL_SET_ERR_MSG(extack, "Class doesn't support blocks");
|
|
err = -EOPNOTSUPP;
|
|
goto errout_qdisc;
|
|
}
|
|
|
|
errout_rcu:
|
|
/* At this point we know that qdisc is not noop_qdisc,
|
|
* which means that qdisc holds a reference to net_device
|
|
* and we hold a reference to qdisc, so it is safe to release
|
|
* rcu read lock.
|
|
*/
|
|
rcu_read_unlock();
|
|
return err;
|
|
|
|
errout_qdisc:
|
|
rcu_read_unlock();
|
|
|
|
if (rtnl_held)
|
|
qdisc_put(*q);
|
|
else
|
|
qdisc_put_unlocked(*q);
|
|
*q = NULL;
|
|
|
|
return err;
|
|
}
|
|
|
|
static int __tcf_qdisc_cl_find(struct Qdisc *q, u32 parent, unsigned long *cl,
|
|
int ifindex, struct netlink_ext_ack *extack)
|
|
{
|
|
if (ifindex == TCM_IFINDEX_MAGIC_BLOCK)
|
|
return 0;
|
|
|
|
/* Do we search for filter, attached to class? */
|
|
if (TC_H_MIN(parent)) {
|
|
const struct Qdisc_class_ops *cops = q->ops->cl_ops;
|
|
|
|
*cl = cops->find(q, parent);
|
|
if (*cl == 0) {
|
|
NL_SET_ERR_MSG(extack, "Specified class doesn't exist");
|
|
return -ENOENT;
|
|
}
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static struct tcf_block *__tcf_block_find(struct net *net, struct Qdisc *q,
|
|
unsigned long cl, int ifindex,
|
|
u32 block_index,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tcf_block *block;
|
|
|
|
if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
|
|
block = tcf_block_refcnt_get(net, block_index);
|
|
if (!block) {
|
|
NL_SET_ERR_MSG(extack, "Block of given index was not found");
|
|
return ERR_PTR(-EINVAL);
|
|
}
|
|
} else {
|
|
const struct Qdisc_class_ops *cops = q->ops->cl_ops;
|
|
|
|
block = cops->tcf_block(q, cl, extack);
|
|
if (!block)
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
if (tcf_block_shared(block)) {
|
|
NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters");
|
|
return ERR_PTR(-EOPNOTSUPP);
|
|
}
|
|
|
|
/* Always take reference to block in order to support execution
|
|
* of rules update path of cls API without rtnl lock. Caller
|
|
* must release block when it is finished using it. 'if' block
|
|
* of this conditional obtain reference to block by calling
|
|
* tcf_block_refcnt_get().
|
|
*/
|
|
refcount_inc(&block->refcnt);
|
|
}
|
|
|
|
return block;
|
|
}
|
|
|
|
static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q,
|
|
struct tcf_block_ext_info *ei, bool rtnl_held)
|
|
{
|
|
if (refcount_dec_and_mutex_lock(&block->refcnt, &block->lock)) {
|
|
/* Flushing/putting all chains will cause the block to be
|
|
* deallocated when last chain is freed. However, if chain_list
|
|
* is empty, block has to be manually deallocated. After block
|
|
* reference counter reached 0, it is no longer possible to
|
|
* increment it or add new chains to block.
|
|
*/
|
|
bool free_block = list_empty(&block->chain_list);
|
|
|
|
mutex_unlock(&block->lock);
|
|
if (tcf_block_shared(block))
|
|
tcf_block_remove(block, block->net);
|
|
|
|
if (q)
|
|
tcf_block_offload_unbind(block, q, ei);
|
|
|
|
if (free_block)
|
|
tcf_block_destroy(block);
|
|
else
|
|
tcf_block_flush_all_chains(block, rtnl_held);
|
|
} else if (q) {
|
|
tcf_block_offload_unbind(block, q, ei);
|
|
}
|
|
}
|
|
|
|
static void tcf_block_refcnt_put(struct tcf_block *block, bool rtnl_held)
|
|
{
|
|
__tcf_block_put(block, NULL, NULL, rtnl_held);
|
|
}
|
|
|
|
/* Find tcf block.
|
|
* Set q, parent, cl when appropriate.
|
|
*/
|
|
|
|
static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
|
|
u32 *parent, unsigned long *cl,
|
|
int ifindex, u32 block_index,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tcf_block *block;
|
|
int err = 0;
|
|
|
|
ASSERT_RTNL();
|
|
|
|
err = __tcf_qdisc_find(net, q, parent, ifindex, true, extack);
|
|
if (err)
|
|
goto errout;
|
|
|
|
err = __tcf_qdisc_cl_find(*q, *parent, cl, ifindex, extack);
|
|
if (err)
|
|
goto errout_qdisc;
|
|
|
|
block = __tcf_block_find(net, *q, *cl, ifindex, block_index, extack);
|
|
if (IS_ERR(block)) {
|
|
err = PTR_ERR(block);
|
|
goto errout_qdisc;
|
|
}
|
|
|
|
return block;
|
|
|
|
errout_qdisc:
|
|
if (*q)
|
|
qdisc_put(*q);
|
|
errout:
|
|
*q = NULL;
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
static void tcf_block_release(struct Qdisc *q, struct tcf_block *block,
|
|
bool rtnl_held)
|
|
{
|
|
if (!IS_ERR_OR_NULL(block))
|
|
tcf_block_refcnt_put(block, rtnl_held);
|
|
|
|
if (q) {
|
|
if (rtnl_held)
|
|
qdisc_put(q);
|
|
else
|
|
qdisc_put_unlocked(q);
|
|
}
|
|
}
|
|
|
|
struct tcf_block_owner_item {
|
|
struct list_head list;
|
|
struct Qdisc *q;
|
|
enum flow_block_binder_type binder_type;
|
|
};
|
|
|
|
static void
|
|
tcf_block_owner_netif_keep_dst(struct tcf_block *block,
|
|
struct Qdisc *q,
|
|
enum flow_block_binder_type binder_type)
|
|
{
|
|
if (block->keep_dst &&
|
|
binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS &&
|
|
binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
|
|
netif_keep_dst(qdisc_dev(q));
|
|
}
|
|
|
|
void tcf_block_netif_keep_dst(struct tcf_block *block)
|
|
{
|
|
struct tcf_block_owner_item *item;
|
|
|
|
block->keep_dst = true;
|
|
list_for_each_entry(item, &block->owner_list, list)
|
|
tcf_block_owner_netif_keep_dst(block, item->q,
|
|
item->binder_type);
|
|
}
|
|
EXPORT_SYMBOL(tcf_block_netif_keep_dst);
|
|
|
|
static int tcf_block_owner_add(struct tcf_block *block,
|
|
struct Qdisc *q,
|
|
enum flow_block_binder_type binder_type)
|
|
{
|
|
struct tcf_block_owner_item *item;
|
|
|
|
item = kmalloc(sizeof(*item), GFP_KERNEL);
|
|
if (!item)
|
|
return -ENOMEM;
|
|
item->q = q;
|
|
item->binder_type = binder_type;
|
|
list_add(&item->list, &block->owner_list);
|
|
return 0;
|
|
}
|
|
|
|
static void tcf_block_owner_del(struct tcf_block *block,
|
|
struct Qdisc *q,
|
|
enum flow_block_binder_type binder_type)
|
|
{
|
|
struct tcf_block_owner_item *item;
|
|
|
|
list_for_each_entry(item, &block->owner_list, list) {
|
|
if (item->q == q && item->binder_type == binder_type) {
|
|
list_del(&item->list);
|
|
kfree(item);
|
|
return;
|
|
}
|
|
}
|
|
WARN_ON(1);
|
|
}
|
|
|
|
int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
|
|
struct tcf_block_ext_info *ei,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct net *net = qdisc_net(q);
|
|
struct tcf_block *block = NULL;
|
|
int err;
|
|
|
|
if (ei->block_index)
|
|
/* block_index not 0 means the shared block is requested */
|
|
block = tcf_block_refcnt_get(net, ei->block_index);
|
|
|
|
if (!block) {
|
|
block = tcf_block_create(net, q, ei->block_index, extack);
|
|
if (IS_ERR(block))
|
|
return PTR_ERR(block);
|
|
if (tcf_block_shared(block)) {
|
|
err = tcf_block_insert(block, net, extack);
|
|
if (err)
|
|
goto err_block_insert;
|
|
}
|
|
}
|
|
|
|
err = tcf_block_owner_add(block, q, ei->binder_type);
|
|
if (err)
|
|
goto err_block_owner_add;
|
|
|
|
tcf_block_owner_netif_keep_dst(block, q, ei->binder_type);
|
|
|
|
err = tcf_chain0_head_change_cb_add(block, ei, extack);
|
|
if (err)
|
|
goto err_chain0_head_change_cb_add;
|
|
|
|
err = tcf_block_offload_bind(block, q, ei, extack);
|
|
if (err)
|
|
goto err_block_offload_bind;
|
|
|
|
*p_block = block;
|
|
return 0;
|
|
|
|
err_block_offload_bind:
|
|
tcf_chain0_head_change_cb_del(block, ei);
|
|
err_chain0_head_change_cb_add:
|
|
tcf_block_owner_del(block, q, ei->binder_type);
|
|
err_block_owner_add:
|
|
err_block_insert:
|
|
tcf_block_refcnt_put(block, true);
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL(tcf_block_get_ext);
|
|
|
|
static void tcf_chain_head_change_dflt(struct tcf_proto *tp_head, void *priv)
|
|
{
|
|
struct tcf_proto __rcu **p_filter_chain = priv;
|
|
|
|
rcu_assign_pointer(*p_filter_chain, tp_head);
|
|
}
|
|
|
|
int tcf_block_get(struct tcf_block **p_block,
|
|
struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tcf_block_ext_info ei = {
|
|
.chain_head_change = tcf_chain_head_change_dflt,
|
|
.chain_head_change_priv = p_filter_chain,
|
|
};
|
|
|
|
WARN_ON(!p_filter_chain);
|
|
return tcf_block_get_ext(p_block, q, &ei, extack);
|
|
}
|
|
EXPORT_SYMBOL(tcf_block_get);
|
|
|
|
/* XXX: Standalone actions are not allowed to jump to any chain, and bound
|
|
* actions should be all removed after flushing.
|
|
*/
|
|
void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
|
|
struct tcf_block_ext_info *ei)
|
|
{
|
|
if (!block)
|
|
return;
|
|
tcf_chain0_head_change_cb_del(block, ei);
|
|
tcf_block_owner_del(block, q, ei->binder_type);
|
|
|
|
__tcf_block_put(block, q, ei, true);
|
|
}
|
|
EXPORT_SYMBOL(tcf_block_put_ext);
|
|
|
|
void tcf_block_put(struct tcf_block *block)
|
|
{
|
|
struct tcf_block_ext_info ei = {0, };
|
|
|
|
if (!block)
|
|
return;
|
|
tcf_block_put_ext(block, block->q, &ei);
|
|
}
|
|
|
|
EXPORT_SYMBOL(tcf_block_put);
|
|
|
|
static int
|
|
tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb,
|
|
void *cb_priv, bool add, bool offload_in_use,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tcf_chain *chain, *chain_prev;
|
|
struct tcf_proto *tp, *tp_prev;
|
|
int err;
|
|
|
|
for (chain = __tcf_get_next_chain(block, NULL);
|
|
chain;
|
|
chain_prev = chain,
|
|
chain = __tcf_get_next_chain(block, chain),
|
|
tcf_chain_put(chain_prev)) {
|
|
for (tp = __tcf_get_next_proto(chain, NULL); tp;
|
|
tp_prev = tp,
|
|
tp = __tcf_get_next_proto(chain, tp),
|
|
tcf_proto_put(tp_prev, true, NULL)) {
|
|
if (tp->ops->reoffload) {
|
|
err = tp->ops->reoffload(tp, add, cb, cb_priv,
|
|
extack);
|
|
if (err && add)
|
|
goto err_playback_remove;
|
|
} else if (add && offload_in_use) {
|
|
err = -EOPNOTSUPP;
|
|
NL_SET_ERR_MSG(extack, "Filter HW offload failed - classifier without re-offloading support");
|
|
goto err_playback_remove;
|
|
}
|
|
}
|
|
}
|
|
|
|
return 0;
|
|
|
|
err_playback_remove:
|
|
tcf_proto_put(tp, true, NULL);
|
|
tcf_chain_put(chain);
|
|
tcf_block_playback_offloads(block, cb, cb_priv, false, offload_in_use,
|
|
extack);
|
|
return err;
|
|
}
|
|
|
|
static int tcf_block_bind(struct tcf_block *block,
|
|
struct flow_block_offload *bo)
|
|
{
|
|
struct flow_block_cb *block_cb, *next;
|
|
int err, i = 0;
|
|
|
|
list_for_each_entry(block_cb, &bo->cb_list, list) {
|
|
err = tcf_block_playback_offloads(block, block_cb->cb,
|
|
block_cb->cb_priv, true,
|
|
tcf_block_offload_in_use(block),
|
|
bo->extack);
|
|
if (err)
|
|
goto err_unroll;
|
|
|
|
i++;
|
|
}
|
|
list_splice(&bo->cb_list, &block->flow_block.cb_list);
|
|
|
|
return 0;
|
|
|
|
err_unroll:
|
|
list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) {
|
|
if (i-- > 0) {
|
|
list_del(&block_cb->list);
|
|
tcf_block_playback_offloads(block, block_cb->cb,
|
|
block_cb->cb_priv, false,
|
|
tcf_block_offload_in_use(block),
|
|
NULL);
|
|
}
|
|
flow_block_cb_free(block_cb);
|
|
}
|
|
|
|
return err;
|
|
}
|
|
|
|
static void tcf_block_unbind(struct tcf_block *block,
|
|
struct flow_block_offload *bo)
|
|
{
|
|
struct flow_block_cb *block_cb, *next;
|
|
|
|
list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) {
|
|
tcf_block_playback_offloads(block, block_cb->cb,
|
|
block_cb->cb_priv, false,
|
|
tcf_block_offload_in_use(block),
|
|
NULL);
|
|
list_del(&block_cb->list);
|
|
flow_block_cb_free(block_cb);
|
|
}
|
|
}
|
|
|
|
static int tcf_block_setup(struct tcf_block *block,
|
|
struct flow_block_offload *bo)
|
|
{
|
|
int err;
|
|
|
|
switch (bo->command) {
|
|
case FLOW_BLOCK_BIND:
|
|
err = tcf_block_bind(block, bo);
|
|
break;
|
|
case FLOW_BLOCK_UNBIND:
|
|
err = 0;
|
|
tcf_block_unbind(block, bo);
|
|
break;
|
|
default:
|
|
WARN_ON_ONCE(1);
|
|
err = -EOPNOTSUPP;
|
|
}
|
|
|
|
return err;
|
|
}
|
|
|
|
/* 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)
|
|
{
|
|
#ifdef CONFIG_NET_CLS_ACT
|
|
const int max_reclassify_loop = 4;
|
|
const struct tcf_proto *orig_tp = tp;
|
|
const struct tcf_proto *first_tp;
|
|
int limit = 0;
|
|
|
|
reclassify:
|
|
#endif
|
|
for (; tp; tp = rcu_dereference_bh(tp->next)) {
|
|
__be16 protocol = tc_skb_protocol(skb);
|
|
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)) {
|
|
first_tp = orig_tp;
|
|
goto reset;
|
|
} else if (unlikely(TC_ACT_EXT_CMP(err, TC_ACT_GOTO_CHAIN))) {
|
|
first_tp = res->goto_tp;
|
|
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("%u: reclassify loop, rule prio %u, protocol %02x\n",
|
|
tp->chain->block->index,
|
|
tp->prio & 0xffff,
|
|
ntohs(tp->protocol));
|
|
return TC_ACT_SHOT;
|
|
}
|
|
|
|
tp = first_tp;
|
|
goto reclassify;
|
|
#endif
|
|
}
|
|
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 *chain,
|
|
struct tcf_chain_info *chain_info)
|
|
{
|
|
return tcf_chain_dereference(*chain_info->pprev, chain);
|
|
}
|
|
|
|
static int tcf_chain_tp_insert(struct tcf_chain *chain,
|
|
struct tcf_chain_info *chain_info,
|
|
struct tcf_proto *tp)
|
|
{
|
|
if (chain->flushing)
|
|
return -EAGAIN;
|
|
|
|
if (*chain_info->pprev == chain->filter_chain)
|
|
tcf_chain0_head_change(chain, tp);
|
|
tcf_proto_get(tp);
|
|
RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info));
|
|
rcu_assign_pointer(*chain_info->pprev, tp);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void tcf_chain_tp_remove(struct tcf_chain *chain,
|
|
struct tcf_chain_info *chain_info,
|
|
struct tcf_proto *tp)
|
|
{
|
|
struct tcf_proto *next = tcf_chain_dereference(chain_info->next, chain);
|
|
|
|
tcf_proto_mark_delete(tp);
|
|
if (tp == chain->filter_chain)
|
|
tcf_chain0_head_change(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);
|
|
|
|
/* Try to insert new proto.
|
|
* If proto with specified priority already exists, free new proto
|
|
* and return existing one.
|
|
*/
|
|
|
|
static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain,
|
|
struct tcf_proto *tp_new,
|
|
u32 protocol, u32 prio,
|
|
bool rtnl_held)
|
|
{
|
|
struct tcf_chain_info chain_info;
|
|
struct tcf_proto *tp;
|
|
int err = 0;
|
|
|
|
mutex_lock(&chain->filter_chain_lock);
|
|
|
|
tp = tcf_chain_tp_find(chain, &chain_info,
|
|
protocol, prio, false);
|
|
if (!tp)
|
|
err = tcf_chain_tp_insert(chain, &chain_info, tp_new);
|
|
mutex_unlock(&chain->filter_chain_lock);
|
|
|
|
if (tp) {
|
|
tcf_proto_destroy(tp_new, rtnl_held, NULL);
|
|
tp_new = tp;
|
|
} else if (err) {
|
|
tcf_proto_destroy(tp_new, rtnl_held, NULL);
|
|
tp_new = ERR_PTR(err);
|
|
}
|
|
|
|
return tp_new;
|
|
}
|
|
|
|
static void tcf_chain_tp_delete_empty(struct tcf_chain *chain,
|
|
struct tcf_proto *tp, bool rtnl_held,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tcf_chain_info chain_info;
|
|
struct tcf_proto *tp_iter;
|
|
struct tcf_proto **pprev;
|
|
struct tcf_proto *next;
|
|
|
|
mutex_lock(&chain->filter_chain_lock);
|
|
|
|
/* Atomically find and remove tp from chain. */
|
|
for (pprev = &chain->filter_chain;
|
|
(tp_iter = tcf_chain_dereference(*pprev, chain));
|
|
pprev = &tp_iter->next) {
|
|
if (tp_iter == tp) {
|
|
chain_info.pprev = pprev;
|
|
chain_info.next = tp_iter->next;
|
|
WARN_ON(tp_iter->deleting);
|
|
break;
|
|
}
|
|
}
|
|
/* Verify that tp still exists and no new filters were inserted
|
|
* concurrently.
|
|
* Mark tp for deletion if it is empty.
|
|
*/
|
|
if (!tp_iter || !tcf_proto_check_delete(tp, rtnl_held)) {
|
|
mutex_unlock(&chain->filter_chain_lock);
|
|
return;
|
|
}
|
|
|
|
next = tcf_chain_dereference(chain_info.next, chain);
|
|
if (tp == chain->filter_chain)
|
|
tcf_chain0_head_change(chain, next);
|
|
RCU_INIT_POINTER(*chain_info.pprev, next);
|
|
mutex_unlock(&chain->filter_chain_lock);
|
|
|
|
tcf_proto_put(tp, rtnl_held, extack);
|
|
}
|
|
|
|
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 = tcf_chain_dereference(*pprev, chain));
|
|
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;
|
|
if (tp) {
|
|
chain_info->next = tp->next;
|
|
tcf_proto_get(tp);
|
|
} else {
|
|
chain_info->next = NULL;
|
|
}
|
|
return tp;
|
|
}
|
|
|
|
static int tcf_fill_node(struct net *net, struct sk_buff *skb,
|
|
struct tcf_proto *tp, struct tcf_block *block,
|
|
struct Qdisc *q, u32 parent, void *fh,
|
|
u32 portid, u32 seq, u16 flags, int event,
|
|
bool rtnl_held)
|
|
{
|
|
struct tcmsg *tcm;
|
|
struct nlmsghdr *nlh;
|
|
unsigned char *b = skb_tail_pointer(skb);
|
|
|
|
nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
|
|
if (!nlh)
|
|
goto out_nlmsg_trim;
|
|
tcm = nlmsg_data(nlh);
|
|
tcm->tcm_family = AF_UNSPEC;
|
|
tcm->tcm__pad1 = 0;
|
|
tcm->tcm__pad2 = 0;
|
|
if (q) {
|
|
tcm->tcm_ifindex = qdisc_dev(q)->ifindex;
|
|
tcm->tcm_parent = parent;
|
|
} else {
|
|
tcm->tcm_ifindex = TCM_IFINDEX_MAGIC_BLOCK;
|
|
tcm->tcm_block_index = block->index;
|
|
}
|
|
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;
|
|
if (!fh) {
|
|
tcm->tcm_handle = 0;
|
|
} else {
|
|
if (tp->ops->dump &&
|
|
tp->ops->dump(net, tp, fh, skb, tcm, rtnl_held) < 0)
|
|
goto nla_put_failure;
|
|
}
|
|
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
|
|
return skb->len;
|
|
|
|
out_nlmsg_trim:
|
|
nla_put_failure:
|
|
nlmsg_trim(skb, b);
|
|
return -1;
|
|
}
|
|
|
|
static int tfilter_notify(struct net *net, struct sk_buff *oskb,
|
|
struct nlmsghdr *n, struct tcf_proto *tp,
|
|
struct tcf_block *block, struct Qdisc *q,
|
|
u32 parent, void *fh, int event, bool unicast,
|
|
bool rtnl_held)
|
|
{
|
|
struct sk_buff *skb;
|
|
u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
|
|
int err = 0;
|
|
|
|
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
|
|
if (!skb)
|
|
return -ENOBUFS;
|
|
|
|
if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
|
|
n->nlmsg_seq, n->nlmsg_flags, event,
|
|
rtnl_held) <= 0) {
|
|
kfree_skb(skb);
|
|
return -EINVAL;
|
|
}
|
|
|
|
if (unicast)
|
|
err = netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT);
|
|
else
|
|
err = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
|
|
n->nlmsg_flags & NLM_F_ECHO);
|
|
|
|
if (err > 0)
|
|
err = 0;
|
|
return err;
|
|
}
|
|
|
|
static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
|
|
struct nlmsghdr *n, struct tcf_proto *tp,
|
|
struct tcf_block *block, struct Qdisc *q,
|
|
u32 parent, void *fh, bool unicast, bool *last,
|
|
bool rtnl_held, struct netlink_ext_ack *extack)
|
|
{
|
|
struct sk_buff *skb;
|
|
u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
|
|
int err;
|
|
|
|
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
|
|
if (!skb)
|
|
return -ENOBUFS;
|
|
|
|
if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
|
|
n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER,
|
|
rtnl_held) <= 0) {
|
|
NL_SET_ERR_MSG(extack, "Failed to build del event notification");
|
|
kfree_skb(skb);
|
|
return -EINVAL;
|
|
}
|
|
|
|
err = tp->ops->delete(tp, fh, last, rtnl_held, extack);
|
|
if (err) {
|
|
kfree_skb(skb);
|
|
return err;
|
|
}
|
|
|
|
if (unicast)
|
|
err = netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT);
|
|
else
|
|
err = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
|
|
n->nlmsg_flags & NLM_F_ECHO);
|
|
if (err < 0)
|
|
NL_SET_ERR_MSG(extack, "Failed to send filter delete notification");
|
|
|
|
if (err > 0)
|
|
err = 0;
|
|
return err;
|
|
}
|
|
|
|
static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
|
|
struct tcf_block *block, struct Qdisc *q,
|
|
u32 parent, struct nlmsghdr *n,
|
|
struct tcf_chain *chain, int event,
|
|
bool rtnl_held)
|
|
{
|
|
struct tcf_proto *tp;
|
|
|
|
for (tp = tcf_get_next_proto(chain, NULL, rtnl_held);
|
|
tp; tp = tcf_get_next_proto(chain, tp, rtnl_held))
|
|
tfilter_notify(net, oskb, n, tp, block,
|
|
q, parent, NULL, event, false, rtnl_held);
|
|
}
|
|
|
|
static void tfilter_put(struct tcf_proto *tp, void *fh)
|
|
{
|
|
if (tp->ops->put && fh)
|
|
tp->ops->put(tp, fh);
|
|
}
|
|
|
|
static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct net *net = sock_net(skb->sk);
|
|
struct nlattr *tca[TCA_MAX + 1];
|
|
struct tcmsg *t;
|
|
u32 protocol;
|
|
u32 prio;
|
|
bool prio_allocate;
|
|
u32 parent;
|
|
u32 chain_index;
|
|
struct Qdisc *q = NULL;
|
|
struct tcf_chain_info chain_info;
|
|
struct tcf_chain *chain = NULL;
|
|
struct tcf_block *block;
|
|
struct tcf_proto *tp;
|
|
unsigned long cl;
|
|
void *fh;
|
|
int err;
|
|
int tp_created;
|
|
bool rtnl_held = false;
|
|
|
|
if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
|
|
return -EPERM;
|
|
|
|
replay:
|
|
tp_created = 0;
|
|
|
|
err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX,
|
|
rtm_tca_policy, extack);
|
|
if (err < 0)
|
|
return err;
|
|
|
|
t = nlmsg_data(n);
|
|
protocol = TC_H_MIN(t->tcm_info);
|
|
prio = TC_H_MAJ(t->tcm_info);
|
|
prio_allocate = false;
|
|
parent = t->tcm_parent;
|
|
tp = NULL;
|
|
cl = 0;
|
|
block = NULL;
|
|
|
|
if (prio == 0) {
|
|
/* If no priority is provided by the user,
|
|
* we allocate one.
|
|
*/
|
|
if (n->nlmsg_flags & NLM_F_CREATE) {
|
|
prio = TC_H_MAKE(0x80000000U, 0U);
|
|
prio_allocate = true;
|
|
} else {
|
|
NL_SET_ERR_MSG(extack, "Invalid filter command with priority of zero");
|
|
return -ENOENT;
|
|
}
|
|
}
|
|
|
|
/* Find head of filter chain. */
|
|
|
|
err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack);
|
|
if (err)
|
|
return err;
|
|
|
|
/* Take rtnl mutex if rtnl_held was set to true on previous iteration,
|
|
* block is shared (no qdisc found), qdisc is not unlocked, classifier
|
|
* type is not specified, classifier is not unlocked.
|
|
*/
|
|
if (rtnl_held ||
|
|
(q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) ||
|
|
!tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) {
|
|
rtnl_held = true;
|
|
rtnl_lock();
|
|
}
|
|
|
|
err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack);
|
|
if (err)
|
|
goto errout;
|
|
|
|
block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index,
|
|
extack);
|
|
if (IS_ERR(block)) {
|
|
err = PTR_ERR(block);
|
|
goto errout;
|
|
}
|
|
|
|
chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
|
|
if (chain_index > TC_ACT_EXT_VAL_MASK) {
|
|
NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
|
|
err = -EINVAL;
|
|
goto errout;
|
|
}
|
|
chain = tcf_chain_get(block, chain_index, true);
|
|
if (!chain) {
|
|
NL_SET_ERR_MSG(extack, "Cannot create specified filter chain");
|
|
err = -ENOMEM;
|
|
goto errout;
|
|
}
|
|
|
|
mutex_lock(&chain->filter_chain_lock);
|
|
tp = tcf_chain_tp_find(chain, &chain_info, protocol,
|
|
prio, prio_allocate);
|
|
if (IS_ERR(tp)) {
|
|
NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
|
|
err = PTR_ERR(tp);
|
|
goto errout_locked;
|
|
}
|
|
|
|
if (tp == NULL) {
|
|
struct tcf_proto *tp_new = NULL;
|
|
|
|
if (chain->flushing) {
|
|
err = -EAGAIN;
|
|
goto errout_locked;
|
|
}
|
|
|
|
/* Proto-tcf does not exist, create new one */
|
|
|
|
if (tca[TCA_KIND] == NULL || !protocol) {
|
|
NL_SET_ERR_MSG(extack, "Filter kind and protocol must be specified");
|
|
err = -EINVAL;
|
|
goto errout_locked;
|
|
}
|
|
|
|
if (!(n->nlmsg_flags & NLM_F_CREATE)) {
|
|
NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter");
|
|
err = -ENOENT;
|
|
goto errout_locked;
|
|
}
|
|
|
|
if (prio_allocate)
|
|
prio = tcf_auto_prio(tcf_chain_tp_prev(chain,
|
|
&chain_info));
|
|
|
|
mutex_unlock(&chain->filter_chain_lock);
|
|
tp_new = tcf_proto_create(nla_data(tca[TCA_KIND]),
|
|
protocol, prio, chain, rtnl_held,
|
|
extack);
|
|
if (IS_ERR(tp_new)) {
|
|
err = PTR_ERR(tp_new);
|
|
goto errout_tp;
|
|
}
|
|
|
|
tp_created = 1;
|
|
tp = tcf_chain_tp_insert_unique(chain, tp_new, protocol, prio,
|
|
rtnl_held);
|
|
if (IS_ERR(tp)) {
|
|
err = PTR_ERR(tp);
|
|
goto errout_tp;
|
|
}
|
|
} else {
|
|
mutex_unlock(&chain->filter_chain_lock);
|
|
}
|
|
|
|
if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
|
|
NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
|
|
err = -EINVAL;
|
|
goto errout;
|
|
}
|
|
|
|
fh = tp->ops->get(tp, t->tcm_handle);
|
|
|
|
if (!fh) {
|
|
if (!(n->nlmsg_flags & NLM_F_CREATE)) {
|
|
NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter");
|
|
err = -ENOENT;
|
|
goto errout;
|
|
}
|
|
} else if (n->nlmsg_flags & NLM_F_EXCL) {
|
|
tfilter_put(tp, fh);
|
|
NL_SET_ERR_MSG(extack, "Filter already exists");
|
|
err = -EEXIST;
|
|
goto errout;
|
|
}
|
|
|
|
if (chain->tmplt_ops && chain->tmplt_ops != tp->ops) {
|
|
NL_SET_ERR_MSG(extack, "Chain template is set to a different filter kind");
|
|
err = -EINVAL;
|
|
goto errout;
|
|
}
|
|
|
|
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,
|
|
rtnl_held, extack);
|
|
if (err == 0) {
|
|
tfilter_notify(net, skb, n, tp, block, q, parent, fh,
|
|
RTM_NEWTFILTER, false, rtnl_held);
|
|
tfilter_put(tp, fh);
|
|
/* q pointer is NULL for shared blocks */
|
|
if (q)
|
|
q->flags &= ~TCQ_F_CAN_BYPASS;
|
|
}
|
|
|
|
errout:
|
|
if (err && tp_created)
|
|
tcf_chain_tp_delete_empty(chain, tp, rtnl_held, NULL);
|
|
errout_tp:
|
|
if (chain) {
|
|
if (tp && !IS_ERR(tp))
|
|
tcf_proto_put(tp, rtnl_held, NULL);
|
|
if (!tp_created)
|
|
tcf_chain_put(chain);
|
|
}
|
|
tcf_block_release(q, block, rtnl_held);
|
|
|
|
if (rtnl_held)
|
|
rtnl_unlock();
|
|
|
|
if (err == -EAGAIN) {
|
|
/* Take rtnl lock in case EAGAIN is caused by concurrent flush
|
|
* of target chain.
|
|
*/
|
|
rtnl_held = true;
|
|
/* Replay the request. */
|
|
goto replay;
|
|
}
|
|
return err;
|
|
|
|
errout_locked:
|
|
mutex_unlock(&chain->filter_chain_lock);
|
|
goto errout;
|
|
}
|
|
|
|
static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct net *net = sock_net(skb->sk);
|
|
struct nlattr *tca[TCA_MAX + 1];
|
|
struct tcmsg *t;
|
|
u32 protocol;
|
|
u32 prio;
|
|
u32 parent;
|
|
u32 chain_index;
|
|
struct Qdisc *q = NULL;
|
|
struct tcf_chain_info chain_info;
|
|
struct tcf_chain *chain = NULL;
|
|
struct tcf_block *block = NULL;
|
|
struct tcf_proto *tp = NULL;
|
|
unsigned long cl = 0;
|
|
void *fh = NULL;
|
|
int err;
|
|
bool rtnl_held = false;
|
|
|
|
if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
|
|
return -EPERM;
|
|
|
|
err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX,
|
|
rtm_tca_policy, extack);
|
|
if (err < 0)
|
|
return err;
|
|
|
|
t = nlmsg_data(n);
|
|
protocol = TC_H_MIN(t->tcm_info);
|
|
prio = TC_H_MAJ(t->tcm_info);
|
|
parent = t->tcm_parent;
|
|
|
|
if (prio == 0 && (protocol || t->tcm_handle || tca[TCA_KIND])) {
|
|
NL_SET_ERR_MSG(extack, "Cannot flush filters with protocol, handle or kind set");
|
|
return -ENOENT;
|
|
}
|
|
|
|
/* Find head of filter chain. */
|
|
|
|
err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack);
|
|
if (err)
|
|
return err;
|
|
|
|
/* Take rtnl mutex if flushing whole chain, block is shared (no qdisc
|
|
* found), qdisc is not unlocked, classifier type is not specified,
|
|
* classifier is not unlocked.
|
|
*/
|
|
if (!prio ||
|
|
(q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) ||
|
|
!tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) {
|
|
rtnl_held = true;
|
|
rtnl_lock();
|
|
}
|
|
|
|
err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack);
|
|
if (err)
|
|
goto errout;
|
|
|
|
block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index,
|
|
extack);
|
|
if (IS_ERR(block)) {
|
|
err = PTR_ERR(block);
|
|
goto errout;
|
|
}
|
|
|
|
chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
|
|
if (chain_index > TC_ACT_EXT_VAL_MASK) {
|
|
NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
|
|
err = -EINVAL;
|
|
goto errout;
|
|
}
|
|
chain = tcf_chain_get(block, chain_index, false);
|
|
if (!chain) {
|
|
/* User requested flush on non-existent chain. Nothing to do,
|
|
* so just return success.
|
|
*/
|
|
if (prio == 0) {
|
|
err = 0;
|
|
goto errout;
|
|
}
|
|
NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
|
|
err = -ENOENT;
|
|
goto errout;
|
|
}
|
|
|
|
if (prio == 0) {
|
|
tfilter_notify_chain(net, skb, block, q, parent, n,
|
|
chain, RTM_DELTFILTER, rtnl_held);
|
|
tcf_chain_flush(chain, rtnl_held);
|
|
err = 0;
|
|
goto errout;
|
|
}
|
|
|
|
mutex_lock(&chain->filter_chain_lock);
|
|
tp = tcf_chain_tp_find(chain, &chain_info, protocol,
|
|
prio, false);
|
|
if (!tp || IS_ERR(tp)) {
|
|
NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
|
|
err = tp ? PTR_ERR(tp) : -ENOENT;
|
|
goto errout_locked;
|
|
} else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
|
|
NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
|
|
err = -EINVAL;
|
|
goto errout_locked;
|
|
} else if (t->tcm_handle == 0) {
|
|
tcf_chain_tp_remove(chain, &chain_info, tp);
|
|
mutex_unlock(&chain->filter_chain_lock);
|
|
|
|
tcf_proto_put(tp, rtnl_held, NULL);
|
|
tfilter_notify(net, skb, n, tp, block, q, parent, fh,
|
|
RTM_DELTFILTER, false, rtnl_held);
|
|
err = 0;
|
|
goto errout;
|
|
}
|
|
mutex_unlock(&chain->filter_chain_lock);
|
|
|
|
fh = tp->ops->get(tp, t->tcm_handle);
|
|
|
|
if (!fh) {
|
|
NL_SET_ERR_MSG(extack, "Specified filter handle not found");
|
|
err = -ENOENT;
|
|
} else {
|
|
bool last;
|
|
|
|
err = tfilter_del_notify(net, skb, n, tp, block,
|
|
q, parent, fh, false, &last,
|
|
rtnl_held, extack);
|
|
|
|
if (err)
|
|
goto errout;
|
|
if (last)
|
|
tcf_chain_tp_delete_empty(chain, tp, rtnl_held, extack);
|
|
}
|
|
|
|
errout:
|
|
if (chain) {
|
|
if (tp && !IS_ERR(tp))
|
|
tcf_proto_put(tp, rtnl_held, NULL);
|
|
tcf_chain_put(chain);
|
|
}
|
|
tcf_block_release(q, block, rtnl_held);
|
|
|
|
if (rtnl_held)
|
|
rtnl_unlock();
|
|
|
|
return err;
|
|
|
|
errout_locked:
|
|
mutex_unlock(&chain->filter_chain_lock);
|
|
goto errout;
|
|
}
|
|
|
|
static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct net *net = sock_net(skb->sk);
|
|
struct nlattr *tca[TCA_MAX + 1];
|
|
struct tcmsg *t;
|
|
u32 protocol;
|
|
u32 prio;
|
|
u32 parent;
|
|
u32 chain_index;
|
|
struct Qdisc *q = NULL;
|
|
struct tcf_chain_info chain_info;
|
|
struct tcf_chain *chain = NULL;
|
|
struct tcf_block *block = NULL;
|
|
struct tcf_proto *tp = NULL;
|
|
unsigned long cl = 0;
|
|
void *fh = NULL;
|
|
int err;
|
|
bool rtnl_held = false;
|
|
|
|
err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX,
|
|
rtm_tca_policy, extack);
|
|
if (err < 0)
|
|
return err;
|
|
|
|
t = nlmsg_data(n);
|
|
protocol = TC_H_MIN(t->tcm_info);
|
|
prio = TC_H_MAJ(t->tcm_info);
|
|
parent = t->tcm_parent;
|
|
|
|
if (prio == 0) {
|
|
NL_SET_ERR_MSG(extack, "Invalid filter command with priority of zero");
|
|
return -ENOENT;
|
|
}
|
|
|
|
/* Find head of filter chain. */
|
|
|
|
err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack);
|
|
if (err)
|
|
return err;
|
|
|
|
/* Take rtnl mutex if block is shared (no qdisc found), qdisc is not
|
|
* unlocked, classifier type is not specified, classifier is not
|
|
* unlocked.
|
|
*/
|
|
if ((q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) ||
|
|
!tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) {
|
|
rtnl_held = true;
|
|
rtnl_lock();
|
|
}
|
|
|
|
err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack);
|
|
if (err)
|
|
goto errout;
|
|
|
|
block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index,
|
|
extack);
|
|
if (IS_ERR(block)) {
|
|
err = PTR_ERR(block);
|
|
goto errout;
|
|
}
|
|
|
|
chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
|
|
if (chain_index > TC_ACT_EXT_VAL_MASK) {
|
|
NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
|
|
err = -EINVAL;
|
|
goto errout;
|
|
}
|
|
chain = tcf_chain_get(block, chain_index, false);
|
|
if (!chain) {
|
|
NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
|
|
err = -EINVAL;
|
|
goto errout;
|
|
}
|
|
|
|
mutex_lock(&chain->filter_chain_lock);
|
|
tp = tcf_chain_tp_find(chain, &chain_info, protocol,
|
|
prio, false);
|
|
mutex_unlock(&chain->filter_chain_lock);
|
|
if (!tp || IS_ERR(tp)) {
|
|
NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
|
|
err = tp ? PTR_ERR(tp) : -ENOENT;
|
|
goto errout;
|
|
} else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
|
|
NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
|
|
err = -EINVAL;
|
|
goto errout;
|
|
}
|
|
|
|
fh = tp->ops->get(tp, t->tcm_handle);
|
|
|
|
if (!fh) {
|
|
NL_SET_ERR_MSG(extack, "Specified filter handle not found");
|
|
err = -ENOENT;
|
|
} else {
|
|
err = tfilter_notify(net, skb, n, tp, block, q, parent,
|
|
fh, RTM_NEWTFILTER, true, rtnl_held);
|
|
if (err < 0)
|
|
NL_SET_ERR_MSG(extack, "Failed to send filter notify message");
|
|
}
|
|
|
|
tfilter_put(tp, fh);
|
|
errout:
|
|
if (chain) {
|
|
if (tp && !IS_ERR(tp))
|
|
tcf_proto_put(tp, rtnl_held, NULL);
|
|
tcf_chain_put(chain);
|
|
}
|
|
tcf_block_release(q, block, rtnl_held);
|
|
|
|
if (rtnl_held)
|
|
rtnl_unlock();
|
|
|
|
return err;
|
|
}
|
|
|
|
struct tcf_dump_args {
|
|
struct tcf_walker w;
|
|
struct sk_buff *skb;
|
|
struct netlink_callback *cb;
|
|
struct tcf_block *block;
|
|
struct Qdisc *q;
|
|
u32 parent;
|
|
};
|
|
|
|
static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
|
|
{
|
|
struct tcf_dump_args *a = (void *)arg;
|
|
struct net *net = sock_net(a->skb->sk);
|
|
|
|
return tcf_fill_node(net, a->skb, tp, a->block, a->q, a->parent,
|
|
n, NETLINK_CB(a->cb->skb).portid,
|
|
a->cb->nlh->nlmsg_seq, NLM_F_MULTI,
|
|
RTM_NEWTFILTER, true);
|
|
}
|
|
|
|
static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
|
|
struct sk_buff *skb, struct netlink_callback *cb,
|
|
long index_start, long *p_index)
|
|
{
|
|
struct net *net = sock_net(skb->sk);
|
|
struct tcf_block *block = chain->block;
|
|
struct tcmsg *tcm = nlmsg_data(cb->nlh);
|
|
struct tcf_proto *tp, *tp_prev;
|
|
struct tcf_dump_args arg;
|
|
|
|
for (tp = __tcf_get_next_proto(chain, NULL);
|
|
tp;
|
|
tp_prev = tp,
|
|
tp = __tcf_get_next_proto(chain, tp),
|
|
tcf_proto_put(tp_prev, true, NULL),
|
|
(*p_index)++) {
|
|
if (*p_index < index_start)
|
|
continue;
|
|
if (TC_H_MAJ(tcm->tcm_info) &&
|
|
TC_H_MAJ(tcm->tcm_info) != tp->prio)
|
|
continue;
|
|
if (TC_H_MIN(tcm->tcm_info) &&
|
|
TC_H_MIN(tcm->tcm_info) != tp->protocol)
|
|
continue;
|
|
if (*p_index > index_start)
|
|
memset(&cb->args[1], 0,
|
|
sizeof(cb->args) - sizeof(cb->args[0]));
|
|
if (cb->args[1] == 0) {
|
|
if (tcf_fill_node(net, skb, tp, block, q, parent, NULL,
|
|
NETLINK_CB(cb->skb).portid,
|
|
cb->nlh->nlmsg_seq, NLM_F_MULTI,
|
|
RTM_NEWTFILTER, true) <= 0)
|
|
goto errout;
|
|
cb->args[1] = 1;
|
|
}
|
|
if (!tp->ops->walk)
|
|
continue;
|
|
arg.w.fn = tcf_node_dump;
|
|
arg.skb = skb;
|
|
arg.cb = cb;
|
|
arg.block = block;
|
|
arg.q = q;
|
|
arg.parent = parent;
|
|
arg.w.stop = 0;
|
|
arg.w.skip = cb->args[1] - 1;
|
|
arg.w.count = 0;
|
|
arg.w.cookie = cb->args[2];
|
|
tp->ops->walk(tp, &arg.w, true);
|
|
cb->args[2] = arg.w.cookie;
|
|
cb->args[1] = arg.w.count + 1;
|
|
if (arg.w.stop)
|
|
goto errout;
|
|
}
|
|
return true;
|
|
|
|
errout:
|
|
tcf_proto_put(tp, true, NULL);
|
|
return false;
|
|
}
|
|
|
|
/* called with RTNL */
|
|
static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
|
|
{
|
|
struct tcf_chain *chain, *chain_prev;
|
|
struct net *net = sock_net(skb->sk);
|
|
struct nlattr *tca[TCA_MAX + 1];
|
|
struct Qdisc *q = NULL;
|
|
struct tcf_block *block;
|
|
struct tcmsg *tcm = nlmsg_data(cb->nlh);
|
|
long index_start;
|
|
long index;
|
|
u32 parent;
|
|
int err;
|
|
|
|
if (nlmsg_len(cb->nlh) < sizeof(*tcm))
|
|
return skb->len;
|
|
|
|
err = nlmsg_parse_deprecated(cb->nlh, sizeof(*tcm), tca, TCA_MAX,
|
|
NULL, cb->extack);
|
|
if (err)
|
|
return err;
|
|
|
|
if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
|
|
block = tcf_block_refcnt_get(net, tcm->tcm_block_index);
|
|
if (!block)
|
|
goto out;
|
|
/* If we work with block index, q is NULL and parent value
|
|
* will never be used in the following code. The check
|
|
* in tcf_fill_node prevents it. However, compiler does not
|
|
* see that far, so set parent to zero to silence the warning
|
|
* about parent being uninitialized.
|
|
*/
|
|
parent = 0;
|
|
} else {
|
|
const struct Qdisc_class_ops *cops;
|
|
struct net_device *dev;
|
|
unsigned long cl = 0;
|
|
|
|
dev = __dev_get_by_index(net, tcm->tcm_ifindex);
|
|
if (!dev)
|
|
return skb->len;
|
|
|
|
parent = tcm->tcm_parent;
|
|
if (!parent) {
|
|
q = dev->qdisc;
|
|
parent = q->handle;
|
|
} else {
|
|
q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
|
|
}
|
|
if (!q)
|
|
goto out;
|
|
cops = q->ops->cl_ops;
|
|
if (!cops)
|
|
goto out;
|
|
if (!cops->tcf_block)
|
|
goto out;
|
|
if (TC_H_MIN(tcm->tcm_parent)) {
|
|
cl = cops->find(q, tcm->tcm_parent);
|
|
if (cl == 0)
|
|
goto out;
|
|
}
|
|
block = cops->tcf_block(q, cl, NULL);
|
|
if (!block)
|
|
goto out;
|
|
if (tcf_block_shared(block))
|
|
q = NULL;
|
|
}
|
|
|
|
index_start = cb->args[0];
|
|
index = 0;
|
|
|
|
for (chain = __tcf_get_next_chain(block, NULL);
|
|
chain;
|
|
chain_prev = chain,
|
|
chain = __tcf_get_next_chain(block, chain),
|
|
tcf_chain_put(chain_prev)) {
|
|
if (tca[TCA_CHAIN] &&
|
|
nla_get_u32(tca[TCA_CHAIN]) != chain->index)
|
|
continue;
|
|
if (!tcf_chain_dump(chain, q, parent, skb, cb,
|
|
index_start, &index)) {
|
|
tcf_chain_put(chain);
|
|
err = -EMSGSIZE;
|
|
break;
|
|
}
|
|
}
|
|
|
|
if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK)
|
|
tcf_block_refcnt_put(block, true);
|
|
cb->args[0] = index;
|
|
|
|
out:
|
|
/* If we did no progress, the error (EMSGSIZE) is real */
|
|
if (skb->len == 0 && err)
|
|
return err;
|
|
return skb->len;
|
|
}
|
|
|
|
static int tc_chain_fill_node(const struct tcf_proto_ops *tmplt_ops,
|
|
void *tmplt_priv, u32 chain_index,
|
|
struct net *net, struct sk_buff *skb,
|
|
struct tcf_block *block,
|
|
u32 portid, u32 seq, u16 flags, int event)
|
|
{
|
|
unsigned char *b = skb_tail_pointer(skb);
|
|
const struct tcf_proto_ops *ops;
|
|
struct nlmsghdr *nlh;
|
|
struct tcmsg *tcm;
|
|
void *priv;
|
|
|
|
ops = tmplt_ops;
|
|
priv = tmplt_priv;
|
|
|
|
nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
|
|
if (!nlh)
|
|
goto out_nlmsg_trim;
|
|
tcm = nlmsg_data(nlh);
|
|
tcm->tcm_family = AF_UNSPEC;
|
|
tcm->tcm__pad1 = 0;
|
|
tcm->tcm__pad2 = 0;
|
|
tcm->tcm_handle = 0;
|
|
if (block->q) {
|
|
tcm->tcm_ifindex = qdisc_dev(block->q)->ifindex;
|
|
tcm->tcm_parent = block->q->handle;
|
|
} else {
|
|
tcm->tcm_ifindex = TCM_IFINDEX_MAGIC_BLOCK;
|
|
tcm->tcm_block_index = block->index;
|
|
}
|
|
|
|
if (nla_put_u32(skb, TCA_CHAIN, chain_index))
|
|
goto nla_put_failure;
|
|
|
|
if (ops) {
|
|
if (nla_put_string(skb, TCA_KIND, ops->kind))
|
|
goto nla_put_failure;
|
|
if (ops->tmplt_dump(skb, net, priv) < 0)
|
|
goto nla_put_failure;
|
|
}
|
|
|
|
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
|
|
return skb->len;
|
|
|
|
out_nlmsg_trim:
|
|
nla_put_failure:
|
|
nlmsg_trim(skb, b);
|
|
return -EMSGSIZE;
|
|
}
|
|
|
|
static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb,
|
|
u32 seq, u16 flags, int event, bool unicast)
|
|
{
|
|
u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
|
|
struct tcf_block *block = chain->block;
|
|
struct net *net = block->net;
|
|
struct sk_buff *skb;
|
|
int err = 0;
|
|
|
|
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
|
|
if (!skb)
|
|
return -ENOBUFS;
|
|
|
|
if (tc_chain_fill_node(chain->tmplt_ops, chain->tmplt_priv,
|
|
chain->index, net, skb, block, portid,
|
|
seq, flags, event) <= 0) {
|
|
kfree_skb(skb);
|
|
return -EINVAL;
|
|
}
|
|
|
|
if (unicast)
|
|
err = netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT);
|
|
else
|
|
err = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
|
|
flags & NLM_F_ECHO);
|
|
|
|
if (err > 0)
|
|
err = 0;
|
|
return err;
|
|
}
|
|
|
|
static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops,
|
|
void *tmplt_priv, u32 chain_index,
|
|
struct tcf_block *block, struct sk_buff *oskb,
|
|
u32 seq, u16 flags, bool unicast)
|
|
{
|
|
u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
|
|
struct net *net = block->net;
|
|
struct sk_buff *skb;
|
|
|
|
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
|
|
if (!skb)
|
|
return -ENOBUFS;
|
|
|
|
if (tc_chain_fill_node(tmplt_ops, tmplt_priv, chain_index, net, skb,
|
|
block, portid, seq, flags, RTM_DELCHAIN) <= 0) {
|
|
kfree_skb(skb);
|
|
return -EINVAL;
|
|
}
|
|
|
|
if (unicast)
|
|
return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT);
|
|
|
|
return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO);
|
|
}
|
|
|
|
static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net,
|
|
struct nlattr **tca,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
const struct tcf_proto_ops *ops;
|
|
void *tmplt_priv;
|
|
|
|
/* If kind is not set, user did not specify template. */
|
|
if (!tca[TCA_KIND])
|
|
return 0;
|
|
|
|
ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), true, extack);
|
|
if (IS_ERR(ops))
|
|
return PTR_ERR(ops);
|
|
if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) {
|
|
NL_SET_ERR_MSG(extack, "Chain templates are not supported with specified classifier");
|
|
return -EOPNOTSUPP;
|
|
}
|
|
|
|
tmplt_priv = ops->tmplt_create(net, chain, tca, extack);
|
|
if (IS_ERR(tmplt_priv)) {
|
|
module_put(ops->owner);
|
|
return PTR_ERR(tmplt_priv);
|
|
}
|
|
chain->tmplt_ops = ops;
|
|
chain->tmplt_priv = tmplt_priv;
|
|
return 0;
|
|
}
|
|
|
|
static void tc_chain_tmplt_del(const struct tcf_proto_ops *tmplt_ops,
|
|
void *tmplt_priv)
|
|
{
|
|
/* If template ops are set, no work to do for us. */
|
|
if (!tmplt_ops)
|
|
return;
|
|
|
|
tmplt_ops->tmplt_destroy(tmplt_priv);
|
|
module_put(tmplt_ops->owner);
|
|
}
|
|
|
|
/* Add/delete/get a chain */
|
|
|
|
static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct net *net = sock_net(skb->sk);
|
|
struct nlattr *tca[TCA_MAX + 1];
|
|
struct tcmsg *t;
|
|
u32 parent;
|
|
u32 chain_index;
|
|
struct Qdisc *q = NULL;
|
|
struct tcf_chain *chain = NULL;
|
|
struct tcf_block *block;
|
|
unsigned long cl;
|
|
int err;
|
|
|
|
if (n->nlmsg_type != RTM_GETCHAIN &&
|
|
!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
|
|
return -EPERM;
|
|
|
|
replay:
|
|
err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX,
|
|
rtm_tca_policy, extack);
|
|
if (err < 0)
|
|
return err;
|
|
|
|
t = nlmsg_data(n);
|
|
parent = t->tcm_parent;
|
|
cl = 0;
|
|
|
|
block = tcf_block_find(net, &q, &parent, &cl,
|
|
t->tcm_ifindex, t->tcm_block_index, extack);
|
|
if (IS_ERR(block))
|
|
return PTR_ERR(block);
|
|
|
|
chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
|
|
if (chain_index > TC_ACT_EXT_VAL_MASK) {
|
|
NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
|
|
err = -EINVAL;
|
|
goto errout_block;
|
|
}
|
|
|
|
mutex_lock(&block->lock);
|
|
chain = tcf_chain_lookup(block, chain_index);
|
|
if (n->nlmsg_type == RTM_NEWCHAIN) {
|
|
if (chain) {
|
|
if (tcf_chain_held_by_acts_only(chain)) {
|
|
/* The chain exists only because there is
|
|
* some action referencing it.
|
|
*/
|
|
tcf_chain_hold(chain);
|
|
} else {
|
|
NL_SET_ERR_MSG(extack, "Filter chain already exists");
|
|
err = -EEXIST;
|
|
goto errout_block_locked;
|
|
}
|
|
} else {
|
|
if (!(n->nlmsg_flags & NLM_F_CREATE)) {
|
|
NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain");
|
|
err = -ENOENT;
|
|
goto errout_block_locked;
|
|
}
|
|
chain = tcf_chain_create(block, chain_index);
|
|
if (!chain) {
|
|
NL_SET_ERR_MSG(extack, "Failed to create filter chain");
|
|
err = -ENOMEM;
|
|
goto errout_block_locked;
|
|
}
|
|
}
|
|
} else {
|
|
if (!chain || tcf_chain_held_by_acts_only(chain)) {
|
|
NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
|
|
err = -EINVAL;
|
|
goto errout_block_locked;
|
|
}
|
|
tcf_chain_hold(chain);
|
|
}
|
|
|
|
if (n->nlmsg_type == RTM_NEWCHAIN) {
|
|
/* Modifying chain requires holding parent block lock. In case
|
|
* the chain was successfully added, take a reference to the
|
|
* chain. This ensures that an empty chain does not disappear at
|
|
* the end of this function.
|
|
*/
|
|
tcf_chain_hold(chain);
|
|
chain->explicitly_created = true;
|
|
}
|
|
mutex_unlock(&block->lock);
|
|
|
|
switch (n->nlmsg_type) {
|
|
case RTM_NEWCHAIN:
|
|
err = tc_chain_tmplt_add(chain, net, tca, extack);
|
|
if (err) {
|
|
tcf_chain_put_explicitly_created(chain);
|
|
goto errout;
|
|
}
|
|
|
|
tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL,
|
|
RTM_NEWCHAIN, false);
|
|
break;
|
|
case RTM_DELCHAIN:
|
|
tfilter_notify_chain(net, skb, block, q, parent, n,
|
|
chain, RTM_DELTFILTER, true);
|
|
/* Flush the chain first as the user requested chain removal. */
|
|
tcf_chain_flush(chain, true);
|
|
/* In case the chain was successfully deleted, put a reference
|
|
* to the chain previously taken during addition.
|
|
*/
|
|
tcf_chain_put_explicitly_created(chain);
|
|
break;
|
|
case RTM_GETCHAIN:
|
|
err = tc_chain_notify(chain, skb, n->nlmsg_seq,
|
|
n->nlmsg_seq, n->nlmsg_type, true);
|
|
if (err < 0)
|
|
NL_SET_ERR_MSG(extack, "Failed to send chain notify message");
|
|
break;
|
|
default:
|
|
err = -EOPNOTSUPP;
|
|
NL_SET_ERR_MSG(extack, "Unsupported message type");
|
|
goto errout;
|
|
}
|
|
|
|
errout:
|
|
tcf_chain_put(chain);
|
|
errout_block:
|
|
tcf_block_release(q, block, true);
|
|
if (err == -EAGAIN)
|
|
/* Replay the request. */
|
|
goto replay;
|
|
return err;
|
|
|
|
errout_block_locked:
|
|
mutex_unlock(&block->lock);
|
|
goto errout_block;
|
|
}
|
|
|
|
/* called with RTNL */
|
|
static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
|
|
{
|
|
struct net *net = sock_net(skb->sk);
|
|
struct nlattr *tca[TCA_MAX + 1];
|
|
struct Qdisc *q = NULL;
|
|
struct tcf_block *block;
|
|
struct tcmsg *tcm = nlmsg_data(cb->nlh);
|
|
struct tcf_chain *chain;
|
|
long index_start;
|
|
long index;
|
|
u32 parent;
|
|
int err;
|
|
|
|
if (nlmsg_len(cb->nlh) < sizeof(*tcm))
|
|
return skb->len;
|
|
|
|
err = nlmsg_parse_deprecated(cb->nlh, sizeof(*tcm), tca, TCA_MAX,
|
|
rtm_tca_policy, cb->extack);
|
|
if (err)
|
|
return err;
|
|
|
|
if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
|
|
block = tcf_block_refcnt_get(net, tcm->tcm_block_index);
|
|
if (!block)
|
|
goto out;
|
|
/* If we work with block index, q is NULL and parent value
|
|
* will never be used in the following code. The check
|
|
* in tcf_fill_node prevents it. However, compiler does not
|
|
* see that far, so set parent to zero to silence the warning
|
|
* about parent being uninitialized.
|
|
*/
|
|
parent = 0;
|
|
} else {
|
|
const struct Qdisc_class_ops *cops;
|
|
struct net_device *dev;
|
|
unsigned long cl = 0;
|
|
|
|
dev = __dev_get_by_index(net, tcm->tcm_ifindex);
|
|
if (!dev)
|
|
return skb->len;
|
|
|
|
parent = tcm->tcm_parent;
|
|
if (!parent) {
|
|
q = dev->qdisc;
|
|
parent = q->handle;
|
|
} else {
|
|
q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
|
|
}
|
|
if (!q)
|
|
goto out;
|
|
cops = q->ops->cl_ops;
|
|
if (!cops)
|
|
goto out;
|
|
if (!cops->tcf_block)
|
|
goto out;
|
|
if (TC_H_MIN(tcm->tcm_parent)) {
|
|
cl = cops->find(q, tcm->tcm_parent);
|
|
if (cl == 0)
|
|
goto out;
|
|
}
|
|
block = cops->tcf_block(q, cl, NULL);
|
|
if (!block)
|
|
goto out;
|
|
if (tcf_block_shared(block))
|
|
q = NULL;
|
|
}
|
|
|
|
index_start = cb->args[0];
|
|
index = 0;
|
|
|
|
mutex_lock(&block->lock);
|
|
list_for_each_entry(chain, &block->chain_list, list) {
|
|
if ((tca[TCA_CHAIN] &&
|
|
nla_get_u32(tca[TCA_CHAIN]) != chain->index))
|
|
continue;
|
|
if (index < index_start) {
|
|
index++;
|
|
continue;
|
|
}
|
|
if (tcf_chain_held_by_acts_only(chain))
|
|
continue;
|
|
err = tc_chain_fill_node(chain->tmplt_ops, chain->tmplt_priv,
|
|
chain->index, net, skb, block,
|
|
NETLINK_CB(cb->skb).portid,
|
|
cb->nlh->nlmsg_seq, NLM_F_MULTI,
|
|
RTM_NEWCHAIN);
|
|
if (err <= 0)
|
|
break;
|
|
index++;
|
|
}
|
|
mutex_unlock(&block->lock);
|
|
|
|
if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK)
|
|
tcf_block_refcnt_put(block, true);
|
|
cb->args[0] = index;
|
|
|
|
out:
|
|
/* If we did no progress, the error (EMSGSIZE) is real */
|
|
if (skb->len == 0 && err)
|
|
return err;
|
|
return skb->len;
|
|
}
|
|
|
|
void tcf_exts_destroy(struct tcf_exts *exts)
|
|
{
|
|
#ifdef CONFIG_NET_CLS_ACT
|
|
tcf_action_destroy(exts->actions, TCA_ACT_UNBIND);
|
|
kfree(exts->actions);
|
|
exts->nr_actions = 0;
|
|
#endif
|
|
}
|
|
EXPORT_SYMBOL(tcf_exts_destroy);
|
|
|
|
int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
|
|
struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr,
|
|
bool rtnl_held, struct netlink_ext_ack *extack)
|
|
{
|
|
#ifdef CONFIG_NET_CLS_ACT
|
|
{
|
|
struct tc_action *act;
|
|
size_t attr_size = 0;
|
|
|
|
if (exts->police && tb[exts->police]) {
|
|
act = tcf_action_init_1(net, tp, tb[exts->police],
|
|
rate_tlv, "police", ovr,
|
|
TCA_ACT_BIND, rtnl_held,
|
|
extack);
|
|
if (IS_ERR(act))
|
|
return PTR_ERR(act);
|
|
|
|
act->type = exts->type = TCA_OLD_COMPAT;
|
|
exts->actions[0] = act;
|
|
exts->nr_actions = 1;
|
|
} else if (exts->action && tb[exts->action]) {
|
|
int err;
|
|
|
|
err = tcf_action_init(net, tp, tb[exts->action],
|
|
rate_tlv, NULL, ovr, TCA_ACT_BIND,
|
|
exts->actions, &attr_size,
|
|
rtnl_held, extack);
|
|
if (err < 0)
|
|
return err;
|
|
exts->nr_actions = err;
|
|
}
|
|
}
|
|
#else
|
|
if ((exts->action && tb[exts->action]) ||
|
|
(exts->police && tb[exts->police])) {
|
|
NL_SET_ERR_MSG(extack, "Classifier actions are not supported per compile options (CONFIG_NET_CLS_ACT)");
|
|
return -EOPNOTSUPP;
|
|
}
|
|
#endif
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(tcf_exts_validate);
|
|
|
|
void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src)
|
|
{
|
|
#ifdef CONFIG_NET_CLS_ACT
|
|
struct tcf_exts old = *dst;
|
|
|
|
*dst = *src;
|
|
tcf_exts_destroy(&old);
|
|
#endif
|
|
}
|
|
EXPORT_SYMBOL(tcf_exts_change);
|
|
|
|
#ifdef CONFIG_NET_CLS_ACT
|
|
static struct tc_action *tcf_exts_first_act(struct tcf_exts *exts)
|
|
{
|
|
if (exts->nr_actions == 0)
|
|
return NULL;
|
|
else
|
|
return exts->actions[0];
|
|
}
|
|
#endif
|
|
|
|
int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts)
|
|
{
|
|
#ifdef CONFIG_NET_CLS_ACT
|
|
struct nlattr *nest;
|
|
|
|
if (exts->action && tcf_exts_has_actions(exts)) {
|
|
/*
|
|
* again for backward compatible mode - we want
|
|
* to work with both old and new modes of entering
|
|
* tc data even if iproute2 was newer - jhs
|
|
*/
|
|
if (exts->type != TCA_OLD_COMPAT) {
|
|
nest = nla_nest_start_noflag(skb, exts->action);
|
|
if (nest == NULL)
|
|
goto nla_put_failure;
|
|
|
|
if (tcf_action_dump(skb, exts->actions, 0, 0) < 0)
|
|
goto nla_put_failure;
|
|
nla_nest_end(skb, nest);
|
|
} else if (exts->police) {
|
|
struct tc_action *act = tcf_exts_first_act(exts);
|
|
nest = nla_nest_start_noflag(skb, exts->police);
|
|
if (nest == NULL || !act)
|
|
goto nla_put_failure;
|
|
if (tcf_action_dump_old(skb, act, 0, 0) < 0)
|
|
goto nla_put_failure;
|
|
nla_nest_end(skb, nest);
|
|
}
|
|
}
|
|
return 0;
|
|
|
|
nla_put_failure:
|
|
nla_nest_cancel(skb, nest);
|
|
return -1;
|
|
#else
|
|
return 0;
|
|
#endif
|
|
}
|
|
EXPORT_SYMBOL(tcf_exts_dump);
|
|
|
|
|
|
int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts)
|
|
{
|
|
#ifdef CONFIG_NET_CLS_ACT
|
|
struct tc_action *a = tcf_exts_first_act(exts);
|
|
if (a != NULL && tcf_action_copy_stats(skb, a, 1) < 0)
|
|
return -1;
|
|
#endif
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(tcf_exts_dump_stats);
|
|
|
|
int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
|
|
void *type_data, bool err_stop)
|
|
{
|
|
struct flow_block_cb *block_cb;
|
|
int ok_count = 0;
|
|
int err;
|
|
|
|
/* Make sure all netdevs sharing this block are offload-capable. */
|
|
if (block->nooffloaddevcnt && err_stop)
|
|
return -EOPNOTSUPP;
|
|
|
|
list_for_each_entry(block_cb, &block->flow_block.cb_list, list) {
|
|
err = block_cb->cb(type, type_data, block_cb->cb_priv);
|
|
if (err) {
|
|
if (err_stop)
|
|
return err;
|
|
} else {
|
|
ok_count++;
|
|
}
|
|
}
|
|
return ok_count;
|
|
}
|
|
EXPORT_SYMBOL(tc_setup_cb_call);
|
|
|
|
int tc_setup_flow_action(struct flow_action *flow_action,
|
|
const struct tcf_exts *exts)
|
|
{
|
|
const struct tc_action *act;
|
|
int i, j, k;
|
|
|
|
if (!exts)
|
|
return 0;
|
|
|
|
j = 0;
|
|
tcf_exts_for_each_action(i, act, exts) {
|
|
struct flow_action_entry *entry;
|
|
|
|
entry = &flow_action->entries[j];
|
|
if (is_tcf_gact_ok(act)) {
|
|
entry->id = FLOW_ACTION_ACCEPT;
|
|
} else if (is_tcf_gact_shot(act)) {
|
|
entry->id = FLOW_ACTION_DROP;
|
|
} else if (is_tcf_gact_trap(act)) {
|
|
entry->id = FLOW_ACTION_TRAP;
|
|
} else if (is_tcf_gact_goto_chain(act)) {
|
|
entry->id = FLOW_ACTION_GOTO;
|
|
entry->chain_index = tcf_gact_goto_chain_index(act);
|
|
} else if (is_tcf_mirred_egress_redirect(act)) {
|
|
entry->id = FLOW_ACTION_REDIRECT;
|
|
entry->dev = tcf_mirred_dev(act);
|
|
} else if (is_tcf_mirred_egress_mirror(act)) {
|
|
entry->id = FLOW_ACTION_MIRRED;
|
|
entry->dev = tcf_mirred_dev(act);
|
|
} else if (is_tcf_vlan(act)) {
|
|
switch (tcf_vlan_action(act)) {
|
|
case TCA_VLAN_ACT_PUSH:
|
|
entry->id = FLOW_ACTION_VLAN_PUSH;
|
|
entry->vlan.vid = tcf_vlan_push_vid(act);
|
|
entry->vlan.proto = tcf_vlan_push_proto(act);
|
|
entry->vlan.prio = tcf_vlan_push_prio(act);
|
|
break;
|
|
case TCA_VLAN_ACT_POP:
|
|
entry->id = FLOW_ACTION_VLAN_POP;
|
|
break;
|
|
case TCA_VLAN_ACT_MODIFY:
|
|
entry->id = FLOW_ACTION_VLAN_MANGLE;
|
|
entry->vlan.vid = tcf_vlan_push_vid(act);
|
|
entry->vlan.proto = tcf_vlan_push_proto(act);
|
|
entry->vlan.prio = tcf_vlan_push_prio(act);
|
|
break;
|
|
default:
|
|
goto err_out;
|
|
}
|
|
} else if (is_tcf_tunnel_set(act)) {
|
|
entry->id = FLOW_ACTION_TUNNEL_ENCAP;
|
|
entry->tunnel = tcf_tunnel_info(act);
|
|
} else if (is_tcf_tunnel_release(act)) {
|
|
entry->id = FLOW_ACTION_TUNNEL_DECAP;
|
|
} else if (is_tcf_pedit(act)) {
|
|
for (k = 0; k < tcf_pedit_nkeys(act); k++) {
|
|
switch (tcf_pedit_cmd(act, k)) {
|
|
case TCA_PEDIT_KEY_EX_CMD_SET:
|
|
entry->id = FLOW_ACTION_MANGLE;
|
|
break;
|
|
case TCA_PEDIT_KEY_EX_CMD_ADD:
|
|
entry->id = FLOW_ACTION_ADD;
|
|
break;
|
|
default:
|
|
goto err_out;
|
|
}
|
|
entry->mangle.htype = tcf_pedit_htype(act, k);
|
|
entry->mangle.mask = tcf_pedit_mask(act, k);
|
|
entry->mangle.val = tcf_pedit_val(act, k);
|
|
entry->mangle.offset = tcf_pedit_offset(act, k);
|
|
entry = &flow_action->entries[++j];
|
|
}
|
|
} else if (is_tcf_csum(act)) {
|
|
entry->id = FLOW_ACTION_CSUM;
|
|
entry->csum_flags = tcf_csum_update_flags(act);
|
|
} else if (is_tcf_skbedit_mark(act)) {
|
|
entry->id = FLOW_ACTION_MARK;
|
|
entry->mark = tcf_skbedit_mark(act);
|
|
} else if (is_tcf_sample(act)) {
|
|
entry->id = FLOW_ACTION_SAMPLE;
|
|
entry->sample.psample_group =
|
|
tcf_sample_psample_group(act);
|
|
entry->sample.trunc_size = tcf_sample_trunc_size(act);
|
|
entry->sample.truncate = tcf_sample_truncate(act);
|
|
entry->sample.rate = tcf_sample_rate(act);
|
|
} else if (is_tcf_police(act)) {
|
|
entry->id = FLOW_ACTION_POLICE;
|
|
entry->police.burst = tcf_police_tcfp_burst(act);
|
|
entry->police.rate_bytes_ps =
|
|
tcf_police_rate_bytes_ps(act);
|
|
} else if (is_tcf_ct(act)) {
|
|
entry->id = FLOW_ACTION_CT;
|
|
entry->ct.action = tcf_ct_action(act);
|
|
entry->ct.zone = tcf_ct_zone(act);
|
|
} else {
|
|
goto err_out;
|
|
}
|
|
|
|
if (!is_tcf_pedit(act))
|
|
j++;
|
|
}
|
|
return 0;
|
|
err_out:
|
|
return -EOPNOTSUPP;
|
|
}
|
|
EXPORT_SYMBOL(tc_setup_flow_action);
|
|
|
|
unsigned int tcf_exts_num_actions(struct tcf_exts *exts)
|
|
{
|
|
unsigned int num_acts = 0;
|
|
struct tc_action *act;
|
|
int i;
|
|
|
|
tcf_exts_for_each_action(i, act, exts) {
|
|
if (is_tcf_pedit(act))
|
|
num_acts += tcf_pedit_nkeys(act);
|
|
else
|
|
num_acts++;
|
|
}
|
|
return num_acts;
|
|
}
|
|
EXPORT_SYMBOL(tcf_exts_num_actions);
|
|
|
|
static __net_init int tcf_net_init(struct net *net)
|
|
{
|
|
struct tcf_net *tn = net_generic(net, tcf_net_id);
|
|
|
|
spin_lock_init(&tn->idr_lock);
|
|
idr_init(&tn->idr);
|
|
return 0;
|
|
}
|
|
|
|
static void __net_exit tcf_net_exit(struct net *net)
|
|
{
|
|
struct tcf_net *tn = net_generic(net, tcf_net_id);
|
|
|
|
idr_destroy(&tn->idr);
|
|
}
|
|
|
|
static struct pernet_operations tcf_net_ops = {
|
|
.init = tcf_net_init,
|
|
.exit = tcf_net_exit,
|
|
.id = &tcf_net_id,
|
|
.size = sizeof(struct tcf_net),
|
|
};
|
|
|
|
static int __init tc_filter_init(void)
|
|
{
|
|
int err;
|
|
|
|
tc_filter_wq = alloc_ordered_workqueue("tc_filter_workqueue", 0);
|
|
if (!tc_filter_wq)
|
|
return -ENOMEM;
|
|
|
|
err = register_pernet_subsys(&tcf_net_ops);
|
|
if (err)
|
|
goto err_register_pernet_subsys;
|
|
|
|
err = rhashtable_init(&indr_setup_block_ht,
|
|
&tc_indr_setup_block_ht_params);
|
|
if (err)
|
|
goto err_rhash_setup_block_ht;
|
|
|
|
rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL,
|
|
RTNL_FLAG_DOIT_UNLOCKED);
|
|
rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL,
|
|
RTNL_FLAG_DOIT_UNLOCKED);
|
|
rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_get_tfilter,
|
|
tc_dump_tfilter, RTNL_FLAG_DOIT_UNLOCKED);
|
|
rtnl_register(PF_UNSPEC, RTM_NEWCHAIN, tc_ctl_chain, NULL, 0);
|
|
rtnl_register(PF_UNSPEC, RTM_DELCHAIN, tc_ctl_chain, NULL, 0);
|
|
rtnl_register(PF_UNSPEC, RTM_GETCHAIN, tc_ctl_chain,
|
|
tc_dump_chain, 0);
|
|
|
|
return 0;
|
|
|
|
err_rhash_setup_block_ht:
|
|
unregister_pernet_subsys(&tcf_net_ops);
|
|
err_register_pernet_subsys:
|
|
destroy_workqueue(tc_filter_wq);
|
|
return err;
|
|
}
|
|
|
|
subsys_initcall(tc_filter_init);
|