forked from Minki/linux
653cd284a8
Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes:4e232818bd
("net: sched: act_mirred: remove dependency on rtnl lock") Fixes:764e9a2448
("net: sched: act_vlan: remove dependency on rtnl lock") Fixes:729e012609
("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes:d772849566
("net: sched: act_sample: remove dependency on rtnl lock") Fixes:e8917f4370
("net: sched: act_gact: remove dependency on rtnl lock") Fixes:b6a2b971c0
("net: sched: act_csum: remove dependency on rtnl lock") Fixes:2142236b45
("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
454 lines
10 KiB
C
454 lines
10 KiB
C
/*
|
|
* Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/init.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/skbuff.h>
|
|
#include <linux/rtnetlink.h>
|
|
#include <linux/filter.h>
|
|
#include <linux/bpf.h>
|
|
|
|
#include <net/netlink.h>
|
|
#include <net/pkt_sched.h>
|
|
|
|
#include <linux/tc_act/tc_bpf.h>
|
|
#include <net/tc_act/tc_bpf.h>
|
|
|
|
#define ACT_BPF_NAME_LEN 256
|
|
|
|
struct tcf_bpf_cfg {
|
|
struct bpf_prog *filter;
|
|
struct sock_filter *bpf_ops;
|
|
const char *bpf_name;
|
|
u16 bpf_num_ops;
|
|
bool is_ebpf;
|
|
};
|
|
|
|
static unsigned int bpf_net_id;
|
|
static struct tc_action_ops act_bpf_ops;
|
|
|
|
static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act,
|
|
struct tcf_result *res)
|
|
{
|
|
bool at_ingress = skb_at_tc_ingress(skb);
|
|
struct tcf_bpf *prog = to_bpf(act);
|
|
struct bpf_prog *filter;
|
|
int action, filter_res;
|
|
|
|
tcf_lastuse_update(&prog->tcf_tm);
|
|
bstats_cpu_update(this_cpu_ptr(prog->common.cpu_bstats), skb);
|
|
|
|
rcu_read_lock();
|
|
filter = rcu_dereference(prog->filter);
|
|
if (at_ingress) {
|
|
__skb_push(skb, skb->mac_len);
|
|
bpf_compute_data_pointers(skb);
|
|
filter_res = BPF_PROG_RUN(filter, skb);
|
|
__skb_pull(skb, skb->mac_len);
|
|
} else {
|
|
bpf_compute_data_pointers(skb);
|
|
filter_res = BPF_PROG_RUN(filter, skb);
|
|
}
|
|
rcu_read_unlock();
|
|
|
|
/* A BPF program may overwrite the default action opcode.
|
|
* Similarly as in cls_bpf, if filter_res == -1 we use the
|
|
* default action specified from tc.
|
|
*
|
|
* In case a different well-known TC_ACT opcode has been
|
|
* returned, it will overwrite the default one.
|
|
*
|
|
* For everything else that is unkown, TC_ACT_UNSPEC is
|
|
* returned.
|
|
*/
|
|
switch (filter_res) {
|
|
case TC_ACT_PIPE:
|
|
case TC_ACT_RECLASSIFY:
|
|
case TC_ACT_OK:
|
|
case TC_ACT_REDIRECT:
|
|
action = filter_res;
|
|
break;
|
|
case TC_ACT_SHOT:
|
|
action = filter_res;
|
|
qstats_drop_inc(this_cpu_ptr(prog->common.cpu_qstats));
|
|
break;
|
|
case TC_ACT_UNSPEC:
|
|
action = prog->tcf_action;
|
|
break;
|
|
default:
|
|
action = TC_ACT_UNSPEC;
|
|
break;
|
|
}
|
|
|
|
return action;
|
|
}
|
|
|
|
static bool tcf_bpf_is_ebpf(const struct tcf_bpf *prog)
|
|
{
|
|
return !prog->bpf_ops;
|
|
}
|
|
|
|
static int tcf_bpf_dump_bpf_info(const struct tcf_bpf *prog,
|
|
struct sk_buff *skb)
|
|
{
|
|
struct nlattr *nla;
|
|
|
|
if (nla_put_u16(skb, TCA_ACT_BPF_OPS_LEN, prog->bpf_num_ops))
|
|
return -EMSGSIZE;
|
|
|
|
nla = nla_reserve(skb, TCA_ACT_BPF_OPS, prog->bpf_num_ops *
|
|
sizeof(struct sock_filter));
|
|
if (nla == NULL)
|
|
return -EMSGSIZE;
|
|
|
|
memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog,
|
|
struct sk_buff *skb)
|
|
{
|
|
struct nlattr *nla;
|
|
|
|
if (prog->bpf_name &&
|
|
nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name))
|
|
return -EMSGSIZE;
|
|
|
|
if (nla_put_u32(skb, TCA_ACT_BPF_ID, prog->filter->aux->id))
|
|
return -EMSGSIZE;
|
|
|
|
nla = nla_reserve(skb, TCA_ACT_BPF_TAG, sizeof(prog->filter->tag));
|
|
if (nla == NULL)
|
|
return -EMSGSIZE;
|
|
|
|
memcpy(nla_data(nla), prog->filter->tag, nla_len(nla));
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act,
|
|
int bind, int ref)
|
|
{
|
|
unsigned char *tp = skb_tail_pointer(skb);
|
|
struct tcf_bpf *prog = to_bpf(act);
|
|
struct tc_act_bpf opt = {
|
|
.index = prog->tcf_index,
|
|
.refcnt = refcount_read(&prog->tcf_refcnt) - ref,
|
|
.bindcnt = atomic_read(&prog->tcf_bindcnt) - bind,
|
|
};
|
|
struct tcf_t tm;
|
|
int ret;
|
|
|
|
spin_lock_bh(&prog->tcf_lock);
|
|
opt.action = prog->tcf_action;
|
|
if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt))
|
|
goto nla_put_failure;
|
|
|
|
if (tcf_bpf_is_ebpf(prog))
|
|
ret = tcf_bpf_dump_ebpf_info(prog, skb);
|
|
else
|
|
ret = tcf_bpf_dump_bpf_info(prog, skb);
|
|
if (ret)
|
|
goto nla_put_failure;
|
|
|
|
tcf_tm_dump(&tm, &prog->tcf_tm);
|
|
if (nla_put_64bit(skb, TCA_ACT_BPF_TM, sizeof(tm), &tm,
|
|
TCA_ACT_BPF_PAD))
|
|
goto nla_put_failure;
|
|
|
|
spin_unlock_bh(&prog->tcf_lock);
|
|
return skb->len;
|
|
|
|
nla_put_failure:
|
|
spin_unlock_bh(&prog->tcf_lock);
|
|
nlmsg_trim(skb, tp);
|
|
return -1;
|
|
}
|
|
|
|
static const struct nla_policy act_bpf_policy[TCA_ACT_BPF_MAX + 1] = {
|
|
[TCA_ACT_BPF_PARMS] = { .len = sizeof(struct tc_act_bpf) },
|
|
[TCA_ACT_BPF_FD] = { .type = NLA_U32 },
|
|
[TCA_ACT_BPF_NAME] = { .type = NLA_NUL_STRING,
|
|
.len = ACT_BPF_NAME_LEN },
|
|
[TCA_ACT_BPF_OPS_LEN] = { .type = NLA_U16 },
|
|
[TCA_ACT_BPF_OPS] = { .type = NLA_BINARY,
|
|
.len = sizeof(struct sock_filter) * BPF_MAXINSNS },
|
|
};
|
|
|
|
static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
|
|
{
|
|
struct sock_filter *bpf_ops;
|
|
struct sock_fprog_kern fprog_tmp;
|
|
struct bpf_prog *fp;
|
|
u16 bpf_size, bpf_num_ops;
|
|
int ret;
|
|
|
|
bpf_num_ops = nla_get_u16(tb[TCA_ACT_BPF_OPS_LEN]);
|
|
if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0)
|
|
return -EINVAL;
|
|
|
|
bpf_size = bpf_num_ops * sizeof(*bpf_ops);
|
|
if (bpf_size != nla_len(tb[TCA_ACT_BPF_OPS]))
|
|
return -EINVAL;
|
|
|
|
bpf_ops = kmemdup(nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size, GFP_KERNEL);
|
|
if (bpf_ops == NULL)
|
|
return -ENOMEM;
|
|
|
|
fprog_tmp.len = bpf_num_ops;
|
|
fprog_tmp.filter = bpf_ops;
|
|
|
|
ret = bpf_prog_create(&fp, &fprog_tmp);
|
|
if (ret < 0) {
|
|
kfree(bpf_ops);
|
|
return ret;
|
|
}
|
|
|
|
cfg->bpf_ops = bpf_ops;
|
|
cfg->bpf_num_ops = bpf_num_ops;
|
|
cfg->filter = fp;
|
|
cfg->is_ebpf = false;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
|
|
{
|
|
struct bpf_prog *fp;
|
|
char *name = NULL;
|
|
u32 bpf_fd;
|
|
|
|
bpf_fd = nla_get_u32(tb[TCA_ACT_BPF_FD]);
|
|
|
|
fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_ACT);
|
|
if (IS_ERR(fp))
|
|
return PTR_ERR(fp);
|
|
|
|
if (tb[TCA_ACT_BPF_NAME]) {
|
|
name = nla_memdup(tb[TCA_ACT_BPF_NAME], GFP_KERNEL);
|
|
if (!name) {
|
|
bpf_prog_put(fp);
|
|
return -ENOMEM;
|
|
}
|
|
}
|
|
|
|
cfg->bpf_name = name;
|
|
cfg->filter = fp;
|
|
cfg->is_ebpf = true;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg)
|
|
{
|
|
struct bpf_prog *filter = cfg->filter;
|
|
|
|
if (filter) {
|
|
if (cfg->is_ebpf)
|
|
bpf_prog_put(filter);
|
|
else
|
|
bpf_prog_destroy(filter);
|
|
}
|
|
|
|
kfree(cfg->bpf_ops);
|
|
kfree(cfg->bpf_name);
|
|
}
|
|
|
|
static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog,
|
|
struct tcf_bpf_cfg *cfg)
|
|
{
|
|
cfg->is_ebpf = tcf_bpf_is_ebpf(prog);
|
|
/* updates to prog->filter are prevented, since it's called either
|
|
* with tcf lock or during final cleanup in rcu callback
|
|
*/
|
|
cfg->filter = rcu_dereference_protected(prog->filter, 1);
|
|
|
|
cfg->bpf_ops = prog->bpf_ops;
|
|
cfg->bpf_name = prog->bpf_name;
|
|
}
|
|
|
|
static int tcf_bpf_init(struct net *net, struct nlattr *nla,
|
|
struct nlattr *est, struct tc_action **act,
|
|
int replace, int bind, bool rtnl_held,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tc_action_net *tn = net_generic(net, bpf_net_id);
|
|
struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
|
|
struct tcf_bpf_cfg cfg, old;
|
|
struct tc_act_bpf *parm;
|
|
struct tcf_bpf *prog;
|
|
bool is_bpf, is_ebpf;
|
|
int ret, res = 0;
|
|
|
|
if (!nla)
|
|
return -EINVAL;
|
|
|
|
ret = nla_parse_nested(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy, NULL);
|
|
if (ret < 0)
|
|
return ret;
|
|
|
|
if (!tb[TCA_ACT_BPF_PARMS])
|
|
return -EINVAL;
|
|
|
|
parm = nla_data(tb[TCA_ACT_BPF_PARMS]);
|
|
|
|
ret = tcf_idr_check_alloc(tn, &parm->index, act, bind);
|
|
if (!ret) {
|
|
ret = tcf_idr_create(tn, parm->index, est, act,
|
|
&act_bpf_ops, bind, true);
|
|
if (ret < 0) {
|
|
tcf_idr_cleanup(tn, parm->index);
|
|
return ret;
|
|
}
|
|
|
|
res = ACT_P_CREATED;
|
|
} else if (ret > 0) {
|
|
/* Don't override defaults. */
|
|
if (bind)
|
|
return 0;
|
|
|
|
if (!replace) {
|
|
tcf_idr_release(*act, bind);
|
|
return -EEXIST;
|
|
}
|
|
} else {
|
|
return ret;
|
|
}
|
|
|
|
is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS];
|
|
is_ebpf = tb[TCA_ACT_BPF_FD];
|
|
|
|
if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) {
|
|
ret = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
memset(&cfg, 0, sizeof(cfg));
|
|
|
|
ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) :
|
|
tcf_bpf_init_from_efd(tb, &cfg);
|
|
if (ret < 0)
|
|
goto out;
|
|
|
|
prog = to_bpf(*act);
|
|
|
|
spin_lock_bh(&prog->tcf_lock);
|
|
if (res != ACT_P_CREATED)
|
|
tcf_bpf_prog_fill_cfg(prog, &old);
|
|
|
|
prog->bpf_ops = cfg.bpf_ops;
|
|
prog->bpf_name = cfg.bpf_name;
|
|
|
|
if (cfg.bpf_num_ops)
|
|
prog->bpf_num_ops = cfg.bpf_num_ops;
|
|
|
|
prog->tcf_action = parm->action;
|
|
rcu_assign_pointer(prog->filter, cfg.filter);
|
|
spin_unlock_bh(&prog->tcf_lock);
|
|
|
|
if (res == ACT_P_CREATED) {
|
|
tcf_idr_insert(tn, *act);
|
|
} else {
|
|
/* make sure the program being replaced is no longer executing */
|
|
synchronize_rcu();
|
|
tcf_bpf_cfg_cleanup(&old);
|
|
}
|
|
|
|
return res;
|
|
out:
|
|
tcf_idr_release(*act, bind);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static void tcf_bpf_cleanup(struct tc_action *act)
|
|
{
|
|
struct tcf_bpf_cfg tmp;
|
|
|
|
tcf_bpf_prog_fill_cfg(to_bpf(act), &tmp);
|
|
tcf_bpf_cfg_cleanup(&tmp);
|
|
}
|
|
|
|
static int tcf_bpf_walker(struct net *net, struct sk_buff *skb,
|
|
struct netlink_callback *cb, int type,
|
|
const struct tc_action_ops *ops,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tc_action_net *tn = net_generic(net, bpf_net_id);
|
|
|
|
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
|
|
}
|
|
|
|
static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tc_action_net *tn = net_generic(net, bpf_net_id);
|
|
|
|
return tcf_idr_search(tn, a, index);
|
|
}
|
|
|
|
static int tcf_bpf_delete(struct net *net, u32 index)
|
|
{
|
|
struct tc_action_net *tn = net_generic(net, bpf_net_id);
|
|
|
|
return tcf_idr_delete_index(tn, index);
|
|
}
|
|
|
|
static struct tc_action_ops act_bpf_ops __read_mostly = {
|
|
.kind = "bpf",
|
|
.type = TCA_ACT_BPF,
|
|
.owner = THIS_MODULE,
|
|
.act = tcf_bpf_act,
|
|
.dump = tcf_bpf_dump,
|
|
.cleanup = tcf_bpf_cleanup,
|
|
.init = tcf_bpf_init,
|
|
.walk = tcf_bpf_walker,
|
|
.lookup = tcf_bpf_search,
|
|
.delete = tcf_bpf_delete,
|
|
.size = sizeof(struct tcf_bpf),
|
|
};
|
|
|
|
static __net_init int bpf_init_net(struct net *net)
|
|
{
|
|
struct tc_action_net *tn = net_generic(net, bpf_net_id);
|
|
|
|
return tc_action_net_init(tn, &act_bpf_ops);
|
|
}
|
|
|
|
static void __net_exit bpf_exit_net(struct list_head *net_list)
|
|
{
|
|
tc_action_net_exit(net_list, bpf_net_id);
|
|
}
|
|
|
|
static struct pernet_operations bpf_net_ops = {
|
|
.init = bpf_init_net,
|
|
.exit_batch = bpf_exit_net,
|
|
.id = &bpf_net_id,
|
|
.size = sizeof(struct tc_action_net),
|
|
};
|
|
|
|
static int __init bpf_init_module(void)
|
|
{
|
|
return tcf_register_action(&act_bpf_ops, &bpf_net_ops);
|
|
}
|
|
|
|
static void __exit bpf_cleanup_module(void)
|
|
{
|
|
tcf_unregister_action(&act_bpf_ops, &bpf_net_ops);
|
|
}
|
|
|
|
module_init(bpf_init_module);
|
|
module_exit(bpf_cleanup_module);
|
|
|
|
MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>");
|
|
MODULE_DESCRIPTION("TC BPF based action");
|
|
MODULE_LICENSE("GPL v2");
|