linux/net/core/flow_offload.c

557 lines
14 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/kernel.h>
#include <linux/slab.h>
#include <net/flow_offload.h>
#include <linux/rtnetlink.h>
#include <linux/mutex.h>
struct flow_rule *flow_rule_alloc(unsigned int num_actions)
{
struct flow_rule *rule;
int i;
rule = kzalloc(struct_size(rule, action.entries, num_actions),
GFP_KERNEL);
if (!rule)
return NULL;
rule->action.num_entries = num_actions;
/* Pre-fill each action hw_stats with DONT_CARE.
* Caller can override this if it wants stats for a given action.
*/
for (i = 0; i < num_actions; i++)
rule->action.entries[i].hw_stats = FLOW_ACTION_HW_STATS_DONT_CARE;
return rule;
}
EXPORT_SYMBOL(flow_rule_alloc);
#define FLOW_DISSECTOR_MATCH(__rule, __type, __out) \
const struct flow_match *__m = &(__rule)->match; \
struct flow_dissector *__d = (__m)->dissector; \
\
(__out)->key = skb_flow_dissector_target(__d, __type, (__m)->key); \
(__out)->mask = skb_flow_dissector_target(__d, __type, (__m)->mask); \
void flow_rule_match_meta(const struct flow_rule *rule,
struct flow_match_meta *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_META, out);
}
EXPORT_SYMBOL(flow_rule_match_meta);
void flow_rule_match_basic(const struct flow_rule *rule,
struct flow_match_basic *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_BASIC, out);
}
EXPORT_SYMBOL(flow_rule_match_basic);
void flow_rule_match_control(const struct flow_rule *rule,
struct flow_match_control *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_CONTROL, out);
}
EXPORT_SYMBOL(flow_rule_match_control);
void flow_rule_match_eth_addrs(const struct flow_rule *rule,
struct flow_match_eth_addrs *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS, out);
}
EXPORT_SYMBOL(flow_rule_match_eth_addrs);
void flow_rule_match_vlan(const struct flow_rule *rule,
struct flow_match_vlan *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_VLAN, out);
}
EXPORT_SYMBOL(flow_rule_match_vlan);
void flow_rule_match_cvlan(const struct flow_rule *rule,
struct flow_match_vlan *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_CVLAN, out);
}
EXPORT_SYMBOL(flow_rule_match_cvlan);
void flow_rule_match_ipv4_addrs(const struct flow_rule *rule,
struct flow_match_ipv4_addrs *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS, out);
}
EXPORT_SYMBOL(flow_rule_match_ipv4_addrs);
void flow_rule_match_ipv6_addrs(const struct flow_rule *rule,
struct flow_match_ipv6_addrs *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS, out);
}
EXPORT_SYMBOL(flow_rule_match_ipv6_addrs);
void flow_rule_match_ip(const struct flow_rule *rule,
struct flow_match_ip *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IP, out);
}
EXPORT_SYMBOL(flow_rule_match_ip);
void flow_rule_match_ports(const struct flow_rule *rule,
struct flow_match_ports *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_PORTS, out);
}
EXPORT_SYMBOL(flow_rule_match_ports);
void flow_rule_match_tcp(const struct flow_rule *rule,
struct flow_match_tcp *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_TCP, out);
}
EXPORT_SYMBOL(flow_rule_match_tcp);
void flow_rule_match_icmp(const struct flow_rule *rule,
struct flow_match_icmp *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ICMP, out);
}
EXPORT_SYMBOL(flow_rule_match_icmp);
void flow_rule_match_mpls(const struct flow_rule *rule,
struct flow_match_mpls *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_MPLS, out);
}
EXPORT_SYMBOL(flow_rule_match_mpls);
void flow_rule_match_enc_control(const struct flow_rule *rule,
struct flow_match_control *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL, out);
}
EXPORT_SYMBOL(flow_rule_match_enc_control);
void flow_rule_match_enc_ipv4_addrs(const struct flow_rule *rule,
struct flow_match_ipv4_addrs *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, out);
}
EXPORT_SYMBOL(flow_rule_match_enc_ipv4_addrs);
void flow_rule_match_enc_ipv6_addrs(const struct flow_rule *rule,
struct flow_match_ipv6_addrs *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, out);
}
EXPORT_SYMBOL(flow_rule_match_enc_ipv6_addrs);
void flow_rule_match_enc_ip(const struct flow_rule *rule,
struct flow_match_ip *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IP, out);
}
EXPORT_SYMBOL(flow_rule_match_enc_ip);
void flow_rule_match_enc_ports(const struct flow_rule *rule,
struct flow_match_ports *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_PORTS, out);
}
EXPORT_SYMBOL(flow_rule_match_enc_ports);
void flow_rule_match_enc_keyid(const struct flow_rule *rule,
struct flow_match_enc_keyid *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_KEYID, out);
}
EXPORT_SYMBOL(flow_rule_match_enc_keyid);
void flow_rule_match_enc_opts(const struct flow_rule *rule,
struct flow_match_enc_opts *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_OPTS, out);
}
EXPORT_SYMBOL(flow_rule_match_enc_opts);
struct flow_action_cookie *flow_action_cookie_create(void *data,
unsigned int len,
gfp_t gfp)
{
struct flow_action_cookie *cookie;
cookie = kmalloc(sizeof(*cookie) + len, gfp);
if (!cookie)
return NULL;
cookie->cookie_len = len;
memcpy(cookie->cookie, data, len);
return cookie;
}
EXPORT_SYMBOL(flow_action_cookie_create);
void flow_action_cookie_destroy(struct flow_action_cookie *cookie)
{
kfree(cookie);
}
EXPORT_SYMBOL(flow_action_cookie_destroy);
void flow_rule_match_ct(const struct flow_rule *rule,
struct flow_match_ct *out)
{
FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_CT, out);
}
EXPORT_SYMBOL(flow_rule_match_ct);
struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb,
void *cb_ident, void *cb_priv,
void (*release)(void *cb_priv))
{
struct flow_block_cb *block_cb;
block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL);
if (!block_cb)
return ERR_PTR(-ENOMEM);
block_cb->cb = cb;
block_cb->cb_ident = cb_ident;
block_cb->cb_priv = cb_priv;
block_cb->release = release;
return block_cb;
}
EXPORT_SYMBOL(flow_block_cb_alloc);
void flow_block_cb_free(struct flow_block_cb *block_cb)
{
if (block_cb->release)
block_cb->release(block_cb->cb_priv);
kfree(block_cb);
}
EXPORT_SYMBOL(flow_block_cb_free);
struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block,
flow_setup_cb_t *cb, void *cb_ident)
{
struct flow_block_cb *block_cb;
list_for_each_entry(block_cb, &block->cb_list, list) {
if (block_cb->cb == cb &&
block_cb->cb_ident == cb_ident)
return block_cb;
}
return NULL;
}
EXPORT_SYMBOL(flow_block_cb_lookup);
void *flow_block_cb_priv(struct flow_block_cb *block_cb)
{
return block_cb->cb_priv;
}
EXPORT_SYMBOL(flow_block_cb_priv);
void flow_block_cb_incref(struct flow_block_cb *block_cb)
{
block_cb->refcnt++;
}
EXPORT_SYMBOL(flow_block_cb_incref);
unsigned int flow_block_cb_decref(struct flow_block_cb *block_cb)
{
return --block_cb->refcnt;
}
EXPORT_SYMBOL(flow_block_cb_decref);
bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident,
struct list_head *driver_block_list)
{
struct flow_block_cb *block_cb;
list_for_each_entry(block_cb, driver_block_list, driver_list) {
if (block_cb->cb == cb &&
block_cb->cb_ident == cb_ident)
return true;
}
return false;
}
EXPORT_SYMBOL(flow_block_cb_is_busy);
int flow_block_cb_setup_simple(struct flow_block_offload *f,
struct list_head *driver_block_list,
flow_setup_cb_t *cb,
void *cb_ident, void *cb_priv,
bool ingress_only)
{
struct flow_block_cb *block_cb;
if (ingress_only &&
f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
return -EOPNOTSUPP;
f->driver_block_list = driver_block_list;
switch (f->command) {
case FLOW_BLOCK_BIND:
if (flow_block_cb_is_busy(cb, cb_ident, driver_block_list))
return -EBUSY;
block_cb = flow_block_cb_alloc(cb, cb_ident, cb_priv, NULL);
if (IS_ERR(block_cb))
return PTR_ERR(block_cb);
flow_block_cb_add(block_cb, f);
list_add_tail(&block_cb->driver_list, driver_block_list);
return 0;
case FLOW_BLOCK_UNBIND:
block_cb = flow_block_cb_lookup(f->block, cb, cb_ident);
if (!block_cb)
return -ENOENT;
flow_block_cb_remove(block_cb, f);
list_del(&block_cb->driver_list);
return 0;
default:
return -EOPNOTSUPP;
}
}
EXPORT_SYMBOL(flow_block_cb_setup_simple);
static LIST_HEAD(block_cb_list);
static struct rhashtable indr_setup_block_ht;
struct flow_indr_block_cb {
struct list_head list;
void *cb_priv;
flow_indr_block_bind_cb_t *cb;
void *cb_ident;
};
struct flow_indr_block_dev {
struct rhash_head ht_node;
struct net_device *dev;
unsigned int refcnt;
struct list_head cb_list;
};
static const struct rhashtable_params flow_indr_setup_block_ht_params = {
.key_offset = offsetof(struct flow_indr_block_dev, dev),
.head_offset = offsetof(struct flow_indr_block_dev, ht_node),
.key_len = sizeof(struct net_device *),
};
static struct flow_indr_block_dev *
flow_indr_block_dev_lookup(struct net_device *dev)
{
return rhashtable_lookup_fast(&indr_setup_block_ht, &dev,
flow_indr_setup_block_ht_params);
}
static struct flow_indr_block_dev *
flow_indr_block_dev_get(struct net_device *dev)
{
struct flow_indr_block_dev *indr_dev;
indr_dev = flow_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;
if (rhashtable_insert_fast(&indr_setup_block_ht, &indr_dev->ht_node,
flow_indr_setup_block_ht_params)) {
kfree(indr_dev);
return NULL;
}
inc_ref:
indr_dev->refcnt++;
return indr_dev;
}
static void flow_indr_block_dev_put(struct flow_indr_block_dev *indr_dev)
{
if (--indr_dev->refcnt)
return;
rhashtable_remove_fast(&indr_setup_block_ht, &indr_dev->ht_node,
flow_indr_setup_block_ht_params);
kfree(indr_dev);
}
static struct flow_indr_block_cb *
flow_indr_block_cb_lookup(struct flow_indr_block_dev *indr_dev,
flow_indr_block_bind_cb_t *cb, void *cb_ident)
{
struct flow_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 flow_indr_block_cb *
flow_indr_block_cb_add(struct flow_indr_block_dev *indr_dev, void *cb_priv,
flow_indr_block_bind_cb_t *cb, void *cb_ident)
{
struct flow_indr_block_cb *indr_block_cb;
indr_block_cb = flow_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 flow_indr_block_cb_del(struct flow_indr_block_cb *indr_block_cb)
{
list_del(&indr_block_cb->list);
kfree(indr_block_cb);
}
static DEFINE_MUTEX(flow_indr_block_cb_lock);
net: flow_offload: convert block_ing_cb_list to regular list type RCU list block_ing_cb_list is protected by rcu read lock in flow_block_ing_cmd() and with flow_indr_block_ing_cb_lock mutex in all functions that use it. However, flow_block_ing_cmd() needs to call blocking functions while iterating block_ing_cb_list which leads to following suspicious RCU usage warning: [ 401.510948] ============================= [ 401.510952] WARNING: suspicious RCU usage [ 401.510993] 5.3.0-rc3+ #589 Not tainted [ 401.510996] ----------------------------- [ 401.511001] include/linux/rcupdate.h:265 Illegal context switch in RCU read-side critical section! [ 401.511004] other info that might help us debug this: [ 401.511008] rcu_scheduler_active = 2, debug_locks = 1 [ 401.511012] 7 locks held by test-ecmp-add-v/7576: [ 401.511015] #0: 00000000081d71a5 (sb_writers#4){.+.+}, at: vfs_write+0x166/0x1d0 [ 401.511037] #1: 000000002bd338c3 (&of->mutex){+.+.}, at: kernfs_fop_write+0xef/0x1b0 [ 401.511051] #2: 00000000c921c634 (kn->count#317){.+.+}, at: kernfs_fop_write+0xf7/0x1b0 [ 401.511062] #3: 00000000a19cdd56 (&dev->mutex){....}, at: sriov_numvfs_store+0x6b/0x130 [ 401.511079] #4: 000000005425fa52 (pernet_ops_rwsem){++++}, at: unregister_netdevice_notifier+0x30/0x140 [ 401.511092] #5: 00000000c5822793 (rtnl_mutex){+.+.}, at: unregister_netdevice_notifier+0x35/0x140 [ 401.511101] #6: 00000000c2f3507e (rcu_read_lock){....}, at: flow_block_ing_cmd+0x5/0x130 [ 401.511115] stack backtrace: [ 401.511121] CPU: 21 PID: 7576 Comm: test-ecmp-add-v Not tainted 5.3.0-rc3+ #589 [ 401.511124] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 401.511127] Call Trace: [ 401.511138] dump_stack+0x85/0xc0 [ 401.511146] ___might_sleep+0x100/0x180 [ 401.511154] __mutex_lock+0x5b/0x960 [ 401.511162] ? find_held_lock+0x2b/0x80 [ 401.511173] ? __tcf_get_next_chain+0x1d/0xb0 [ 401.511179] ? mark_held_locks+0x49/0x70 [ 401.511194] ? __tcf_get_next_chain+0x1d/0xb0 [ 401.511198] __tcf_get_next_chain+0x1d/0xb0 [ 401.511251] ? uplink_rep_async_event+0x70/0x70 [mlx5_core] [ 401.511261] tcf_block_playback_offloads+0x39/0x160 [ 401.511276] tcf_block_setup+0x1b0/0x240 [ 401.511312] ? mlx5e_rep_indr_setup_tc_cb+0xca/0x290 [mlx5_core] [ 401.511347] ? mlx5e_rep_indr_tc_block_unbind+0x50/0x50 [mlx5_core] [ 401.511359] tc_indr_block_get_and_ing_cmd+0x11b/0x1e0 [ 401.511404] ? mlx5e_rep_indr_tc_block_unbind+0x50/0x50 [mlx5_core] [ 401.511414] flow_block_ing_cmd+0x7e/0x130 [ 401.511453] ? mlx5e_rep_indr_tc_block_unbind+0x50/0x50 [mlx5_core] [ 401.511462] __flow_indr_block_cb_unregister+0x7f/0xf0 [ 401.511502] mlx5e_nic_rep_netdevice_event+0x75/0xb0 [mlx5_core] [ 401.511513] unregister_netdevice_notifier+0xe9/0x140 [ 401.511554] mlx5e_cleanup_rep_tx+0x6f/0xe0 [mlx5_core] [ 401.511597] mlx5e_detach_netdev+0x4b/0x60 [mlx5_core] [ 401.511637] mlx5e_vport_rep_unload+0x71/0xc0 [mlx5_core] [ 401.511679] esw_offloads_disable+0x5b/0x90 [mlx5_core] [ 401.511724] mlx5_eswitch_disable.cold+0xdf/0x176 [mlx5_core] [ 401.511759] mlx5_device_disable_sriov+0xab/0xb0 [mlx5_core] [ 401.511794] mlx5_core_sriov_configure+0xaf/0xd0 [mlx5_core] [ 401.511805] sriov_numvfs_store+0xf8/0x130 [ 401.511817] kernfs_fop_write+0x122/0x1b0 [ 401.511826] vfs_write+0xdb/0x1d0 [ 401.511835] ksys_write+0x65/0xe0 [ 401.511847] do_syscall_64+0x5c/0xb0 [ 401.511857] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 401.511862] RIP: 0033:0x7fad892d30f8 [ 401.511868] 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 25 96 0d 00 8b 00 85 c0 75 17 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 60 c3 0f 1f 80 00 00 00 00 48 83 ec 28 48 89 [ 401.511871] RSP: 002b:00007ffca2a9fad8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 401.511875] RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007fad892d30f8 [ 401.511878] RDX: 0000000000000002 RSI: 000055afeb072a90 RDI: 0000000000000001 [ 401.511881] RBP: 000055afeb072a90 R08: 00000000ffffffff R09: 000000000000000a [ 401.511884] R10: 000055afeb058710 R11: 0000000000000246 R12: 0000000000000002 [ 401.511887] R13: 00007fad893a8780 R14: 0000000000000002 R15: 00007fad893a3740 To fix the described incorrect RCU usage, convert block_ing_cb_list from RCU list to regular list and protect it with flow_indr_block_ing_cb_lock mutex in flow_block_ing_cmd(). Fixes: 1150ab0f1b33 ("flow_offload: support get multi-subsystem block") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-16 18:06:54 +03:00
static void flow_block_cmd(struct net_device *dev,
flow_indr_block_bind_cb_t *cb, void *cb_priv,
enum flow_block_command command)
{
struct flow_indr_block_entry *entry;
mutex_lock(&flow_indr_block_cb_lock);
list_for_each_entry(entry, &block_cb_list, list) {
entry->cb(dev, cb, cb_priv, command);
}
mutex_unlock(&flow_indr_block_cb_lock);
}
int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv,
flow_indr_block_bind_cb_t *cb,
void *cb_ident)
{
struct flow_indr_block_cb *indr_block_cb;
struct flow_indr_block_dev *indr_dev;
int err;
indr_dev = flow_indr_block_dev_get(dev);
if (!indr_dev)
return -ENOMEM;
indr_block_cb = flow_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;
flow_block_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv,
FLOW_BLOCK_BIND);
return 0;
err_dev_put:
flow_indr_block_dev_put(indr_dev);
return err;
}
EXPORT_SYMBOL_GPL(__flow_indr_block_cb_register);
int flow_indr_block_cb_register(struct net_device *dev, void *cb_priv,
flow_indr_block_bind_cb_t *cb,
void *cb_ident)
{
int err;
rtnl_lock();
err = __flow_indr_block_cb_register(dev, cb_priv, cb, cb_ident);
rtnl_unlock();
return err;
}
EXPORT_SYMBOL_GPL(flow_indr_block_cb_register);
void __flow_indr_block_cb_unregister(struct net_device *dev,
flow_indr_block_bind_cb_t *cb,
void *cb_ident)
{
struct flow_indr_block_cb *indr_block_cb;
struct flow_indr_block_dev *indr_dev;
indr_dev = flow_indr_block_dev_lookup(dev);
if (!indr_dev)
return;
indr_block_cb = flow_indr_block_cb_lookup(indr_dev, cb, cb_ident);
if (!indr_block_cb)
return;
flow_block_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv,
FLOW_BLOCK_UNBIND);
flow_indr_block_cb_del(indr_block_cb);
flow_indr_block_dev_put(indr_dev);
}
EXPORT_SYMBOL_GPL(__flow_indr_block_cb_unregister);
void flow_indr_block_cb_unregister(struct net_device *dev,
flow_indr_block_bind_cb_t *cb,
void *cb_ident)
{
rtnl_lock();
__flow_indr_block_cb_unregister(dev, cb, cb_ident);
rtnl_unlock();
}
EXPORT_SYMBOL_GPL(flow_indr_block_cb_unregister);
void flow_indr_block_call(struct net_device *dev,
struct flow_block_offload *bo,
enum flow_block_command command,
enum tc_setup_type type)
{
struct flow_indr_block_cb *indr_block_cb;
struct flow_indr_block_dev *indr_dev;
indr_dev = flow_indr_block_dev_lookup(dev);
if (!indr_dev)
return;
list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list)
indr_block_cb->cb(dev, indr_block_cb->cb_priv, type, bo);
}
EXPORT_SYMBOL_GPL(flow_indr_block_call);
void flow_indr_add_block_cb(struct flow_indr_block_entry *entry)
{
mutex_lock(&flow_indr_block_cb_lock);
list_add_tail(&entry->list, &block_cb_list);
mutex_unlock(&flow_indr_block_cb_lock);
}
EXPORT_SYMBOL_GPL(flow_indr_add_block_cb);
void flow_indr_del_block_cb(struct flow_indr_block_entry *entry)
{
mutex_lock(&flow_indr_block_cb_lock);
net: flow_offload: convert block_ing_cb_list to regular list type RCU list block_ing_cb_list is protected by rcu read lock in flow_block_ing_cmd() and with flow_indr_block_ing_cb_lock mutex in all functions that use it. However, flow_block_ing_cmd() needs to call blocking functions while iterating block_ing_cb_list which leads to following suspicious RCU usage warning: [ 401.510948] ============================= [ 401.510952] WARNING: suspicious RCU usage [ 401.510993] 5.3.0-rc3+ #589 Not tainted [ 401.510996] ----------------------------- [ 401.511001] include/linux/rcupdate.h:265 Illegal context switch in RCU read-side critical section! [ 401.511004] other info that might help us debug this: [ 401.511008] rcu_scheduler_active = 2, debug_locks = 1 [ 401.511012] 7 locks held by test-ecmp-add-v/7576: [ 401.511015] #0: 00000000081d71a5 (sb_writers#4){.+.+}, at: vfs_write+0x166/0x1d0 [ 401.511037] #1: 000000002bd338c3 (&of->mutex){+.+.}, at: kernfs_fop_write+0xef/0x1b0 [ 401.511051] #2: 00000000c921c634 (kn->count#317){.+.+}, at: kernfs_fop_write+0xf7/0x1b0 [ 401.511062] #3: 00000000a19cdd56 (&dev->mutex){....}, at: sriov_numvfs_store+0x6b/0x130 [ 401.511079] #4: 000000005425fa52 (pernet_ops_rwsem){++++}, at: unregister_netdevice_notifier+0x30/0x140 [ 401.511092] #5: 00000000c5822793 (rtnl_mutex){+.+.}, at: unregister_netdevice_notifier+0x35/0x140 [ 401.511101] #6: 00000000c2f3507e (rcu_read_lock){....}, at: flow_block_ing_cmd+0x5/0x130 [ 401.511115] stack backtrace: [ 401.511121] CPU: 21 PID: 7576 Comm: test-ecmp-add-v Not tainted 5.3.0-rc3+ #589 [ 401.511124] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 401.511127] Call Trace: [ 401.511138] dump_stack+0x85/0xc0 [ 401.511146] ___might_sleep+0x100/0x180 [ 401.511154] __mutex_lock+0x5b/0x960 [ 401.511162] ? find_held_lock+0x2b/0x80 [ 401.511173] ? __tcf_get_next_chain+0x1d/0xb0 [ 401.511179] ? mark_held_locks+0x49/0x70 [ 401.511194] ? __tcf_get_next_chain+0x1d/0xb0 [ 401.511198] __tcf_get_next_chain+0x1d/0xb0 [ 401.511251] ? uplink_rep_async_event+0x70/0x70 [mlx5_core] [ 401.511261] tcf_block_playback_offloads+0x39/0x160 [ 401.511276] tcf_block_setup+0x1b0/0x240 [ 401.511312] ? mlx5e_rep_indr_setup_tc_cb+0xca/0x290 [mlx5_core] [ 401.511347] ? mlx5e_rep_indr_tc_block_unbind+0x50/0x50 [mlx5_core] [ 401.511359] tc_indr_block_get_and_ing_cmd+0x11b/0x1e0 [ 401.511404] ? mlx5e_rep_indr_tc_block_unbind+0x50/0x50 [mlx5_core] [ 401.511414] flow_block_ing_cmd+0x7e/0x130 [ 401.511453] ? mlx5e_rep_indr_tc_block_unbind+0x50/0x50 [mlx5_core] [ 401.511462] __flow_indr_block_cb_unregister+0x7f/0xf0 [ 401.511502] mlx5e_nic_rep_netdevice_event+0x75/0xb0 [mlx5_core] [ 401.511513] unregister_netdevice_notifier+0xe9/0x140 [ 401.511554] mlx5e_cleanup_rep_tx+0x6f/0xe0 [mlx5_core] [ 401.511597] mlx5e_detach_netdev+0x4b/0x60 [mlx5_core] [ 401.511637] mlx5e_vport_rep_unload+0x71/0xc0 [mlx5_core] [ 401.511679] esw_offloads_disable+0x5b/0x90 [mlx5_core] [ 401.511724] mlx5_eswitch_disable.cold+0xdf/0x176 [mlx5_core] [ 401.511759] mlx5_device_disable_sriov+0xab/0xb0 [mlx5_core] [ 401.511794] mlx5_core_sriov_configure+0xaf/0xd0 [mlx5_core] [ 401.511805] sriov_numvfs_store+0xf8/0x130 [ 401.511817] kernfs_fop_write+0x122/0x1b0 [ 401.511826] vfs_write+0xdb/0x1d0 [ 401.511835] ksys_write+0x65/0xe0 [ 401.511847] do_syscall_64+0x5c/0xb0 [ 401.511857] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 401.511862] RIP: 0033:0x7fad892d30f8 [ 401.511868] 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 25 96 0d 00 8b 00 85 c0 75 17 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 60 c3 0f 1f 80 00 00 00 00 48 83 ec 28 48 89 [ 401.511871] RSP: 002b:00007ffca2a9fad8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 401.511875] RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007fad892d30f8 [ 401.511878] RDX: 0000000000000002 RSI: 000055afeb072a90 RDI: 0000000000000001 [ 401.511881] RBP: 000055afeb072a90 R08: 00000000ffffffff R09: 000000000000000a [ 401.511884] R10: 000055afeb058710 R11: 0000000000000246 R12: 0000000000000002 [ 401.511887] R13: 00007fad893a8780 R14: 0000000000000002 R15: 00007fad893a3740 To fix the described incorrect RCU usage, convert block_ing_cb_list from RCU list to regular list and protect it with flow_indr_block_ing_cb_lock mutex in flow_block_ing_cmd(). Fixes: 1150ab0f1b33 ("flow_offload: support get multi-subsystem block") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-16 18:06:54 +03:00
list_del(&entry->list);
mutex_unlock(&flow_indr_block_cb_lock);
}
EXPORT_SYMBOL_GPL(flow_indr_del_block_cb);
static int __init init_flow_indr_rhashtable(void)
{
return rhashtable_init(&indr_setup_block_ht,
&flow_indr_setup_block_ht_params);
}
subsys_initcall(init_flow_indr_rhashtable);