| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20250905090505.104882-3-marco.crivellari@suse.com>
Date: Fri, 5 Sep 2025 11:05:04 +0200
From: Marco Crivellari <marco.crivellari@...e.com>
To: linux-kernel@...r.kernel.org,
netdev@...r.kernel.org
Cc: Tejun Heo <tj@...nel.org>,
Lai Jiangshan <jiangshanlai@...il.com>,
Frederic Weisbecker <frederic@...nel.org>,
Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
Marco Crivellari <marco.crivellari@...e.com>,
Michal Hocko <mhocko@...e.com>,
"David S . Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>
Subject: [PATCH net-next 2/3] net: replace use of system_wq with system_percpu_wq
Currently if a user enqueue a work item using schedule_delayed_work() the
used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use
WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to
schedule_work() that is using system_wq and queue_work(), that makes use
again of WORK_CPU_UNBOUND.
This lack of consistentcy cannot be addressed without refactoring the API.
system_unbound_wq should be the default workqueue so as not to enforce
locality constraints for random work whenever it's not required.
Adding system_dfl_wq to encourage its use when unbound work should be used.
queue_work() / queue_delayed_work() / mod_delayed_work() will now use the
new unbound wq: whether the user still use the old wq a warn will be
printed along with a wq redirect to the new one.
The old system_unbound_wq will be kept for a few release cycles.
Suggested-by: Tejun Heo <tj@...nel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@...e.com>
---
drivers/net/ethernet/sfc/efx_channels.c | 2 +-
drivers/net/ethernet/sfc/siena/efx_channels.c | 2 +-
drivers/net/phy/sfp.c | 12 ++++++------
drivers/net/wireless/intel/ipw2x00/ipw2100.c | 6 +++---
drivers/net/wireless/intel/ipw2x00/ipw2200.c | 2 +-
drivers/net/wireless/intel/iwlwifi/mvm/tdls.c | 6 +++---
drivers/net/wireless/mediatek/mt76/mt7921/init.c | 2 +-
drivers/net/wireless/mediatek/mt76/mt7925/init.c | 2 +-
net/bridge/br_cfm.c | 6 +++---
net/bridge/br_mrp.c | 8 ++++----
net/ceph/mon_client.c | 2 +-
net/core/skmsg.c | 2 +-
net/devlink/core.c | 2 +-
net/ipv4/inet_fragment.c | 2 +-
net/netfilter/nf_conntrack_ecache.c | 2 +-
net/openvswitch/dp_notify.c | 2 +-
net/rfkill/input.c | 2 +-
net/smc/smc_core.c | 2 +-
net/vmw_vsock/af_vsock.c | 2 +-
19 files changed, 33 insertions(+), 33 deletions(-)
diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c
index 06b4f52713ef..4fba49d4f36c 100644
--- a/drivers/net/ethernet/sfc/efx_channels.c
+++ b/drivers/net/ethernet/sfc/efx_channels.c
@@ -1281,7 +1281,7 @@ static int efx_poll(struct napi_struct *napi, int budget)
time = jiffies - channel->rfs_last_expiry;
/* Would our quota be >= 20? */
if (channel->rfs_filter_count * time >= 600 * HZ)
- mod_delayed_work(system_wq, &channel->filter_work, 0);
+ mod_delayed_work(system_percpu_wq, &channel->filter_work, 0);
#endif
/* There is no race here; although napi_disable() will
diff --git a/drivers/net/ethernet/sfc/siena/efx_channels.c b/drivers/net/ethernet/sfc/siena/efx_channels.c
index d120b3c83ac0..2039083205bb 100644
--- a/drivers/net/ethernet/sfc/siena/efx_channels.c
+++ b/drivers/net/ethernet/sfc/siena/efx_channels.c
@@ -1300,7 +1300,7 @@ static int efx_poll(struct napi_struct *napi, int budget)
time = jiffies - channel->rfs_last_expiry;
/* Would our quota be >= 20? */
if (channel->rfs_filter_count * time >= 600 * HZ)
- mod_delayed_work(system_wq, &channel->filter_work, 0);
+ mod_delayed_work(system_percpu_wq, &channel->filter_work, 0);
#endif
/* There is no race here; although napi_disable() will
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 347c1e0e94d9..19fcff02db51 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -890,7 +890,7 @@ static void sfp_soft_start_poll(struct sfp *sfp)
if (sfp->state_soft_mask & (SFP_F_LOS | SFP_F_TX_FAULT) &&
!sfp->need_poll)
- mod_delayed_work(system_wq, &sfp->poll, poll_jiffies);
+ mod_delayed_work(system_percpu_wq, &sfp->poll, poll_jiffies);
mutex_unlock(&sfp->st_mutex);
}
@@ -1661,7 +1661,7 @@ static void sfp_hwmon_probe(struct work_struct *work)
err = sfp_read(sfp, true, 0, &sfp->diag, sizeof(sfp->diag));
if (err < 0) {
if (sfp->hwmon_tries--) {
- mod_delayed_work(system_wq, &sfp->hwmon_probe,
+ mod_delayed_work(system_percpu_wq, &sfp->hwmon_probe,
T_PROBE_RETRY_SLOW);
} else {
dev_warn(sfp->dev, "hwmon probe failed: %pe\n",
@@ -1688,7 +1688,7 @@ static void sfp_hwmon_probe(struct work_struct *work)
static int sfp_hwmon_insert(struct sfp *sfp)
{
if (sfp->have_a2 && sfp->id.ext.diagmon & SFP_DIAGMON_DDM) {
- mod_delayed_work(system_wq, &sfp->hwmon_probe, 1);
+ mod_delayed_work(system_percpu_wq, &sfp->hwmon_probe, 1);
sfp->hwmon_tries = R_PROBE_RETRY_SLOW;
}
@@ -2542,7 +2542,7 @@ static void sfp_sm_module(struct sfp *sfp, unsigned int event)
/* Force a poll to re-read the hardware signal state after
* sfp_sm_mod_probe() changed state_hw_mask.
*/
- mod_delayed_work(system_wq, &sfp->poll, 1);
+ mod_delayed_work(system_percpu_wq, &sfp->poll, 1);
err = sfp_hwmon_insert(sfp);
if (err)
@@ -2987,7 +2987,7 @@ static void sfp_poll(struct work_struct *work)
// it's unimportant if we race while reading this.
if (sfp->state_soft_mask & (SFP_F_LOS | SFP_F_TX_FAULT) ||
sfp->need_poll)
- mod_delayed_work(system_wq, &sfp->poll, poll_jiffies);
+ mod_delayed_work(system_percpu_wq, &sfp->poll, poll_jiffies);
}
static struct sfp *sfp_alloc(struct device *dev)
@@ -3157,7 +3157,7 @@ static int sfp_probe(struct platform_device *pdev)
}
if (sfp->need_poll)
- mod_delayed_work(system_wq, &sfp->poll, poll_jiffies);
+ mod_delayed_work(system_percpu_wq, &sfp->poll, poll_jiffies);
/* We could have an issue in cases no Tx disable pin is available or
* wired as modules using a laser as their light source will continue to
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.c b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
index 215814861cbd..c7c5bc0f1650 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
@@ -2143,7 +2143,7 @@ static void isr_indicate_rf_kill(struct ipw2100_priv *priv, u32 status)
/* Make sure the RF Kill check timer is running */
priv->stop_rf_kill = 0;
- mod_delayed_work(system_wq, &priv->rf_kill, round_jiffies_relative(HZ));
+ mod_delayed_work(system_percpu_wq, &priv->rf_kill, round_jiffies_relative(HZ));
}
static void ipw2100_scan_event(struct work_struct *work)
@@ -2170,7 +2170,7 @@ static void isr_scan_complete(struct ipw2100_priv *priv, u32 status)
round_jiffies_relative(msecs_to_jiffies(4000)));
} else {
priv->user_requested_scan = 0;
- mod_delayed_work(system_wq, &priv->scan_event, 0);
+ mod_delayed_work(system_percpu_wq, &priv->scan_event, 0);
}
}
@@ -4252,7 +4252,7 @@ static int ipw_radio_kill_sw(struct ipw2100_priv *priv, int disable_radio)
"disabled by HW switch\n");
/* Make sure the RF_KILL check timer is running */
priv->stop_rf_kill = 0;
- mod_delayed_work(system_wq, &priv->rf_kill,
+ mod_delayed_work(system_percpu_wq, &priv->rf_kill,
round_jiffies_relative(HZ));
} else
schedule_reset(priv);
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.c b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
index 24a5624ef207..09035a77e775 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2200.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
@@ -4415,7 +4415,7 @@ static void handle_scan_event(struct ipw_priv *priv)
round_jiffies_relative(msecs_to_jiffies(4000)));
} else {
priv->user_requested_scan = 0;
- mod_delayed_work(system_wq, &priv->scan_event, 0);
+ mod_delayed_work(system_percpu_wq, &priv->scan_event, 0);
}
}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c b/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c
index 36379b738de1..0df31639fa5e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c
@@ -234,7 +234,7 @@ void iwl_mvm_rx_tdls_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
* Also convert TU to msec.
*/
delay = TU_TO_MS(vif->bss_conf.dtim_period * vif->bss_conf.beacon_int);
- mod_delayed_work(system_wq, &mvm->tdls_cs.dwork,
+ mod_delayed_work(system_percpu_wq, &mvm->tdls_cs.dwork,
msecs_to_jiffies(delay));
iwl_mvm_tdls_update_cs_state(mvm, IWL_MVM_TDLS_SW_ACTIVE);
@@ -548,7 +548,7 @@ iwl_mvm_tdls_channel_switch(struct ieee80211_hw *hw,
*/
delay = 2 * TU_TO_MS(vif->bss_conf.dtim_period *
vif->bss_conf.beacon_int);
- mod_delayed_work(system_wq, &mvm->tdls_cs.dwork,
+ mod_delayed_work(system_percpu_wq, &mvm->tdls_cs.dwork,
msecs_to_jiffies(delay));
return 0;
}
@@ -659,6 +659,6 @@ iwl_mvm_tdls_recv_channel_switch(struct ieee80211_hw *hw,
/* register a timeout in case we don't succeed in switching */
delay = vif->bss_conf.dtim_period * vif->bss_conf.beacon_int *
1024 / 1000;
- mod_delayed_work(system_wq, &mvm->tdls_cs.dwork,
+ mod_delayed_work(system_percpu_wq, &mvm->tdls_cs.dwork,
msecs_to_jiffies(delay));
}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index 14e17dc90256..cb97f69a9149 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -341,7 +341,7 @@ int mt7921_register_device(struct mt792x_dev *dev)
dev->mphy.hw->wiphy->available_antennas_rx = dev->mphy.chainmask;
dev->mphy.hw->wiphy->available_antennas_tx = dev->mphy.chainmask;
- queue_work(system_wq, &dev->init_work);
+ queue_work(system_percpu_wq, &dev->init_work);
return 0;
}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/init.c b/drivers/net/wireless/mediatek/mt76/mt7925/init.c
index 63cb08f4d87c..090ecd1f2a0a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/init.c
@@ -410,7 +410,7 @@ int mt7925_register_device(struct mt792x_dev *dev)
dev->mphy.hw->wiphy->available_antennas_rx = dev->mphy.chainmask;
dev->mphy.hw->wiphy->available_antennas_tx = dev->mphy.chainmask;
- queue_work(system_wq, &dev->init_work);
+ queue_work(system_percpu_wq, &dev->init_work);
return 0;
}
diff --git a/net/bridge/br_cfm.c b/net/bridge/br_cfm.c
index a3c755d0a09d..c2c1c7d44c61 100644
--- a/net/bridge/br_cfm.c
+++ b/net/bridge/br_cfm.c
@@ -134,7 +134,7 @@ static void ccm_rx_timer_start(struct br_cfm_peer_mep *peer_mep)
* of the configured CC 'expected_interval'
* in order to detect CCM defect after 3.25 interval.
*/
- queue_delayed_work(system_wq, &peer_mep->ccm_rx_dwork,
+ queue_delayed_work(system_percpu_wq, &peer_mep->ccm_rx_dwork,
usecs_to_jiffies(interval_us / 4));
}
@@ -285,7 +285,7 @@ static void ccm_tx_work_expired(struct work_struct *work)
ccm_frame_tx(skb);
interval_us = interval_to_us(mep->cc_config.exp_interval);
- queue_delayed_work(system_wq, &mep->ccm_tx_dwork,
+ queue_delayed_work(system_percpu_wq, &mep->ccm_tx_dwork,
usecs_to_jiffies(interval_us));
}
@@ -809,7 +809,7 @@ int br_cfm_cc_ccm_tx(struct net_bridge *br, const u32 instance,
* to send first frame immediately
*/
mep->ccm_tx_end = jiffies + usecs_to_jiffies(tx_info->period * 1000000);
- queue_delayed_work(system_wq, &mep->ccm_tx_dwork, 0);
+ queue_delayed_work(system_percpu_wq, &mep->ccm_tx_dwork, 0);
save:
mep->cc_ccm_tx_info = *tx_info;
diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c
index fd2de35ffb3c..3c36fa24bc05 100644
--- a/net/bridge/br_mrp.c
+++ b/net/bridge/br_mrp.c
@@ -341,7 +341,7 @@ static void br_mrp_test_work_expired(struct work_struct *work)
out:
rcu_read_unlock();
- queue_delayed_work(system_wq, &mrp->test_work,
+ queue_delayed_work(system_percpu_wq, &mrp->test_work,
usecs_to_jiffies(mrp->test_interval));
}
@@ -418,7 +418,7 @@ static void br_mrp_in_test_work_expired(struct work_struct *work)
out:
rcu_read_unlock();
- queue_delayed_work(system_wq, &mrp->in_test_work,
+ queue_delayed_work(system_percpu_wq, &mrp->in_test_work,
usecs_to_jiffies(mrp->in_test_interval));
}
@@ -725,7 +725,7 @@ int br_mrp_start_test(struct net_bridge *br,
mrp->test_max_miss = test->max_miss;
mrp->test_monitor = test->monitor;
mrp->test_count_miss = 0;
- queue_delayed_work(system_wq, &mrp->test_work,
+ queue_delayed_work(system_percpu_wq, &mrp->test_work,
usecs_to_jiffies(test->interval));
return 0;
@@ -865,7 +865,7 @@ int br_mrp_start_in_test(struct net_bridge *br,
mrp->in_test_end = jiffies + usecs_to_jiffies(in_test->period);
mrp->in_test_max_miss = in_test->max_miss;
mrp->in_test_count_miss = 0;
- queue_delayed_work(system_wq, &mrp->in_test_work,
+ queue_delayed_work(system_percpu_wq, &mrp->in_test_work,
usecs_to_jiffies(in_test->interval));
return 0;
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index ab66b599ac47..c227ececa925 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -314,7 +314,7 @@ static void __schedule_delayed(struct ceph_mon_client *monc)
delay = CEPH_MONC_PING_INTERVAL;
dout("__schedule_delayed after %lu\n", delay);
- mod_delayed_work(system_wq, &monc->delayed_work,
+ mod_delayed_work(system_percpu_wq, &monc->delayed_work,
round_jiffies_relative(delay));
}
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 0ddc4c718833..83fc433f5461 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -855,7 +855,7 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
sk_psock_stop(psock);
INIT_RCU_WORK(&psock->rwork, sk_psock_destroy);
- queue_rcu_work(system_wq, &psock->rwork);
+ queue_rcu_work(system_percpu_wq, &psock->rwork);
}
EXPORT_SYMBOL_GPL(sk_psock_drop);
diff --git a/net/devlink/core.c b/net/devlink/core.c
index 7203c39532fc..58093f49c090 100644
--- a/net/devlink/core.c
+++ b/net/devlink/core.c
@@ -320,7 +320,7 @@ static void devlink_release(struct work_struct *work)
void devlink_put(struct devlink *devlink)
{
if (refcount_dec_and_test(&devlink->refcount))
- queue_rcu_work(system_wq, &devlink->rwork);
+ queue_rcu_work(system_percpu_wq, &devlink->rwork);
}
struct devlink *devlinks_xa_find_get(struct net *net, unsigned long *indexp)
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 470ab17ceb51..025895eb6ec5 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -183,7 +183,7 @@ static void fqdir_work_fn(struct work_struct *work)
rhashtable_free_and_destroy(&fqdir->rhashtable, inet_frags_free_cb, NULL);
if (llist_add(&fqdir->free_list, &fqdir_free_list))
- queue_delayed_work(system_wq, &fqdir_free_work, HZ);
+ queue_delayed_work(system_percpu_wq, &fqdir_free_work, HZ);
}
int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net)
diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c
index af68c64acaab..81baf2082604 100644
--- a/net/netfilter/nf_conntrack_ecache.c
+++ b/net/netfilter/nf_conntrack_ecache.c
@@ -301,7 +301,7 @@ void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state)
net->ct.ecache_dwork_pending = true;
} else if (state == NFCT_ECACHE_DESTROY_SENT) {
if (!hlist_nulls_empty(&cnet->ecache.dying_list))
- mod_delayed_work(system_wq, &cnet->ecache.dwork, 0);
+ mod_delayed_work(system_percpu_wq, &cnet->ecache.dwork, 0);
else
net->ct.ecache_dwork_pending = false;
}
diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c
index 7af0cde8b293..a2af90ee99af 100644
--- a/net/openvswitch/dp_notify.c
+++ b/net/openvswitch/dp_notify.c
@@ -75,7 +75,7 @@ static int dp_device_event(struct notifier_block *unused, unsigned long event,
/* schedule vport destroy, dev_put and genl notification */
ovs_net = net_generic(dev_net(dev), ovs_net_id);
- queue_work(system_wq, &ovs_net->dp_notify_work);
+ queue_work(system_percpu_wq, &ovs_net->dp_notify_work);
}
return NOTIFY_DONE;
diff --git a/net/rfkill/input.c b/net/rfkill/input.c
index 598d0a61bda7..53d286b10843 100644
--- a/net/rfkill/input.c
+++ b/net/rfkill/input.c
@@ -159,7 +159,7 @@ static void rfkill_schedule_global_op(enum rfkill_sched_op op)
rfkill_op_pending = true;
if (op == RFKILL_GLOBAL_OP_EPO && !rfkill_is_epo_lock_active()) {
/* bypass the limiter for EPO */
- mod_delayed_work(system_wq, &rfkill_op_work, 0);
+ mod_delayed_work(system_percpu_wq, &rfkill_op_work, 0);
rfkill_last_scheduled = jiffies;
} else
rfkill_schedule_ratelimited();
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index ac07b963aede..ab870109f916 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -85,7 +85,7 @@ static void smc_lgr_schedule_free_work(struct smc_link_group *lgr)
* otherwise there is a risk of out-of-sync link groups.
*/
if (!lgr->freeing) {
- mod_delayed_work(system_wq, &lgr->free_work,
+ mod_delayed_work(system_percpu_wq, &lgr->free_work,
(!lgr->is_smcd && lgr->role == SMC_CLNT) ?
SMC_LGR_FREE_DELAY_CLNT :
SMC_LGR_FREE_DELAY_SERV);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index fc6afbc8d680..f8798d7b5de7 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1569,7 +1569,7 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr,
* reschedule it, then ungrab the socket refcount to
* keep it balanced.
*/
- if (mod_delayed_work(system_wq, &vsk->connect_work,
+ if (mod_delayed_work(system_percpu_wq, &vsk->connect_work,
timeout))
sock_put(sk);
--
2.51.0
Powered by blists - more mailing lists