6.16.8-rc1 review

index 0faa3d97e06b9..08cbb31e6dbc1 100644
@@ -67,6 +67,8 @@ struct phylink {
 	struct timer_list link_poll;
 
 	struct mutex state_mutex;
+	/* Serialize updates to pl->phydev with phylink_resolve() */
+	struct mutex phydev_mutex;
 	struct phylink_link_state phy_state;
 	unsigned int phy_ib_mode;
 	struct work_struct resolve;

@@ -1568,8 +1570,11 @@ static void phylink_resolve(struct work_struct *w)
 	struct phylink_link_state link_state;
 	bool mac_config = false;
 	bool retrigger = false;
+	struct phy_device *phy;
 	bool cur_link_state;
 
+	mutex_lock(&pl->phydev_mutex);
+	phy = pl->phydev;
 	mutex_lock(&pl->state_mutex);
 	cur_link_state = phylink_link_is_up(pl);
 

@@ -1603,11 +1608,11 @@ static void phylink_resolve(struct work_struct *w)
 		/* If we have a phy, the "up" state is the union of both the
 		 * PHY and the MAC
 		 */
-		if (pl->phydev)
+		if (phy)
 			link_state.link &= pl->phy_state.link;
 
 		/* Only update if the PHY link is up */
-		if (pl->phydev && pl->phy_state.link) {
+		if (phy && pl->phy_state.link) {
 			/* If the interface has changed, force a link down
 			 * event if the link isn't already down, and re-resolve.
 			 */

@@ -1671,6 +1676,7 @@ static void phylink_resolve(struct work_struct *w)
 		queue_work(system_power_efficient_wq, &pl->resolve);
 	}
 	mutex_unlock(&pl->state_mutex);
+	mutex_unlock(&pl->phydev_mutex);
 }
 
 static void phylink_run_resolve(struct phylink *pl)

@@ -1806,6 +1812,7 @@ struct phylink *phylink_create(struct phylink_config *config,
 	if (!pl)
 		return ERR_PTR(-ENOMEM);
 
+	mutex_init(&pl->phydev_mutex);
 	mutex_init(&pl->state_mutex);
 	INIT_WORK(&pl->resolve, phylink_resolve);
 

@@ -2066,6 +2073,7 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
 		     dev_name(&phy->mdio.dev), phy->drv->name, irq_str);
 	kfree(irq_str);
 
+	mutex_lock(&pl->phydev_mutex);
 	mutex_lock(&phy->lock);
 	mutex_lock(&pl->state_mutex);
 	pl->phydev = phy;

@@ -2111,6 +2119,7 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
 
 	mutex_unlock(&pl->state_mutex);
 	mutex_unlock(&phy->lock);
+	mutex_unlock(&pl->phydev_mutex);
 
 	phylink_dbg(pl,
 		    "phy: %s setting supported %*pb advertising %*pb\n",

@@ -2289,6 +2298,7 @@ void phylink_disconnect_phy(struct phylink *pl)
 
 	ASSERT_RTNL();
 
+	mutex_lock(&pl->phydev_mutex);
 	phy = pl->phydev;
 	if (phy) {
 		mutex_lock(&phy->lock);

@@ -2298,8 +2308,11 @@ void phylink_disconnect_phy(struct phylink *pl)
 		pl->mac_tx_clk_stop = false;
 		mutex_unlock(&pl->state_mutex);
 		mutex_unlock(&phy->lock);
-		flush_work(&pl->resolve);
+	}
+	mutex_unlock(&pl->phydev_mutex);
 
+	if (phy) {
+		flush_work(&pl->resolve);
 		phy_disconnect(phy);
 	}
 }

index 13df28445f020..c02da57a4da5e 100644
@@ -1065,23 +1065,19 @@ EXPORT_SYMBOL_GPL(phy_inband_caps);
  */
 int phy_config_inband(struct phy_device *phydev, unsigned int modes)
 {
-	int err;
+	lockdep_assert_held(&phydev->lock);
 
 	if (!!(modes & LINK_INBAND_DISABLE) +
 	    !!(modes & LINK_INBAND_ENABLE) +
 	    !!(modes & LINK_INBAND_BYPASS) != 1)
 		return -EINVAL;
 
-	mutex_lock(&phydev->lock);
 	if (!phydev->drv)
-		err = -EIO;
+		return -EIO;
 	else if (!phydev->drv->config_inband)
-		err = -EOPNOTSUPP;
-	else
-		err = phydev->drv->config_inband(phydev, modes);
-	mutex_unlock(&phydev->lock);
+		return -EOPNOTSUPP;
 
-	return err;
+	return phydev->drv->config_inband(phydev, modes);
 }
 EXPORT_SYMBOL(phy_config_inband);
 

index 08cbb31e6dbc1..229a503d601ee 100644
@@ -1411,6 +1411,7 @@ static void phylink_get_fixed_state(struct phylink *pl,
 static void phylink_mac_initial_config(struct phylink *pl, bool force_restart)
 {
 	struct phylink_link_state link_state;
+	struct phy_device *phy = pl->phydev;
 
 	switch (pl->req_link_an_mode) {
 	case MLO_AN_PHY:

@@ -1434,7 +1435,11 @@ static void phylink_mac_initial_config(struct phylink *pl, bool force_restart)
 	link_state.link = false;
 
 	phylink_apply_manual_flow(pl, &link_state);
+	if (phy)
+		mutex_lock(&phy->lock);
 	phylink_major_config(pl, force_restart, &link_state);
+	if (phy)
+		mutex_unlock(&phy->lock);
 }
 
 static const char *phylink_pause_to_str(int pause)

@@ -1575,6 +1580,8 @@ static void phylink_resolve(struct work_struct *w)
 
 	mutex_lock(&pl->phydev_mutex);
 	phy = pl->phydev;
+	if (phy)
+		mutex_lock(&phy->lock);
 	mutex_lock(&pl->state_mutex);
 	cur_link_state = phylink_link_is_up(pl);
 

@@ -1676,6 +1683,8 @@ static void phylink_resolve(struct work_struct *w)
 		queue_work(system_power_efficient_wq, &pl->resolve);
 	}
 	mutex_unlock(&pl->state_mutex);
+	if (phy)
+		mutex_unlock(&phy->lock);
 	mutex_unlock(&pl->phydev_mutex);
 }
 

index a885dd168a372..87944e4467050 100644
@@ -3650,12 +3650,68 @@ static int ath12k_mac_fils_discovery(struct ath12k_link_vif *arvif,
 	return ret;
 }
 
+static void ath12k_mac_vif_setup_ps(struct ath12k_link_vif *arvif)
+{
+	struct ath12k *ar = arvif->ar;
+	struct ieee80211_vif *vif = arvif->ahvif->vif;
+	struct ieee80211_conf *conf = &ath12k_ar_to_hw(ar)->conf;
+	enum wmi_sta_powersave_param param;
+	struct ieee80211_bss_conf *info;
+	enum wmi_sta_ps_mode psmode;
+	int ret;
+	int timeout;
+	bool enable_ps;
+
+	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
+
+	if (vif->type != NL80211_IFTYPE_STATION)
+		return;
+
+	enable_ps = arvif->ahvif->ps;
+	if (enable_ps) {
+		psmode = WMI_STA_PS_MODE_ENABLED;
+		param = WMI_STA_PS_PARAM_INACTIVITY_TIME;
+
+		timeout = conf->dynamic_ps_timeout;
+		if (timeout == 0) {
+			info = ath12k_mac_get_link_bss_conf(arvif);
+			if (!info) {
+				ath12k_warn(ar->ab, "unable to access bss link conf in setup ps for vif %pM link %u\n",
+					    vif->addr, arvif->link_id);
+				return;
+			}
+
+			/* firmware doesn't like 0 */
+			timeout = ieee80211_tu_to_usec(info->beacon_int) / 1000;
+		}
+
+		ret = ath12k_wmi_set_sta_ps_param(ar, arvif->vdev_id, param,
+						  timeout);
+		if (ret) {
+			ath12k_warn(ar->ab, "failed to set inactivity time for vdev %d: %i\n",
+				    arvif->vdev_id, ret);
+			return;
+		}
+	} else {
+		psmode = WMI_STA_PS_MODE_DISABLED;
+	}
+
+	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac vdev %d psmode %s\n",
+		   arvif->vdev_id, psmode ? "enable" : "disable");
+
+	ret = ath12k_wmi_pdev_set_ps_mode(ar, arvif->vdev_id, psmode);
+	if (ret)
+		ath12k_warn(ar->ab, "failed to set sta power save mode %d for vdev %d: %d\n",
+			    psmode, arvif->vdev_id, ret);
+}
+
 static void ath12k_mac_op_vif_cfg_changed(struct ieee80211_hw *hw,
 					  struct ieee80211_vif *vif,
 					  u64 changed)
 {
 	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
 	unsigned long links = ahvif->links_map;
+	struct ieee80211_vif_cfg *vif_cfg;
 	struct ieee80211_bss_conf *info;
 	struct ath12k_link_vif *arvif;
 	struct ieee80211_sta *sta;

@@ -3719,61 +3775,24 @@ static void ath12k_mac_op_vif_cfg_changed(struct ieee80211_hw *hw,
 			}
 		}
 	}
-}
-
-static void ath12k_mac_vif_setup_ps(struct ath12k_link_vif *arvif)
-{
-	struct ath12k *ar = arvif->ar;
-	struct ieee80211_vif *vif = arvif->ahvif->vif;
-	struct ieee80211_conf *conf = &ath12k_ar_to_hw(ar)->conf;
-	enum wmi_sta_powersave_param param;
-	struct ieee80211_bss_conf *info;
-	enum wmi_sta_ps_mode psmode;
-	int ret;
-	int timeout;
-	bool enable_ps;
 
-	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
+	if (changed & BSS_CHANGED_PS) {
+		links = ahvif->links_map;
+		vif_cfg = &vif->cfg;
 
-	if (vif->type != NL80211_IFTYPE_STATION)
-		return;
+		for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) {
+			arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]);
+			if (!arvif || !arvif->ar)
+				continue;
 
-	enable_ps = arvif->ahvif->ps;
-	if (enable_ps) {
-		psmode = WMI_STA_PS_MODE_ENABLED;
-		param = WMI_STA_PS_PARAM_INACTIVITY_TIME;
+			ar = arvif->ar;
 
-		timeout = conf->dynamic_ps_timeout;
-		if (timeout == 0) {
-			info = ath12k_mac_get_link_bss_conf(arvif);
-			if (!info) {
-				ath12k_warn(ar->ab, "unable to access bss link conf in setup ps for vif %pM link %u\n",
-					    vif->addr, arvif->link_id);
-				return;
+			if (ar->ab->hw_params->supports_sta_ps) {
+				ahvif->ps = vif_cfg->ps;
+				ath12k_mac_vif_setup_ps(arvif);
 			}
-
-			/* firmware doesn't like 0 */
-			timeout = ieee80211_tu_to_usec(info->beacon_int) / 1000;
 		}
-
-		ret = ath12k_wmi_set_sta_ps_param(ar, arvif->vdev_id, param,
-						  timeout);
-		if (ret) {
-			ath12k_warn(ar->ab, "failed to set inactivity time for vdev %d: %i\n",
-				    arvif->vdev_id, ret);
-			return;
-		}
-	} else {
-		psmode = WMI_STA_PS_MODE_DISABLED;
 	}
-
-	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac vdev %d psmode %s\n",
-		   arvif->vdev_id, psmode ? "enable" : "disable");
-
-	ret = ath12k_wmi_pdev_set_ps_mode(ar, arvif->vdev_id, psmode);
-	if (ret)
-		ath12k_warn(ar->ab, "failed to set sta power save mode %d for vdev %d: %d\n",
-			    psmode, arvif->vdev_id, ret);
 }
 
 static bool ath12k_mac_supports_station_tpc(struct ath12k *ar,

@@ -3795,7 +3814,6 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar,
 {
 	struct ath12k_vif *ahvif = arvif->ahvif;
 	struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif);
-	struct ieee80211_vif_cfg *vif_cfg = &vif->cfg;
 	struct cfg80211_chan_def def;
 	u32 param_id, param_value;
 	enum nl80211_band band;

@@ -4069,12 +4087,6 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar,
 	}
 
 	ath12k_mac_fils_discovery(arvif, info);
-
-	if (changed & BSS_CHANGED_PS &&
-	    ar->ab->hw_params->supports_sta_ps) {
-		ahvif->ps = vif_cfg->ps;
-		ath12k_mac_vif_setup_ps(arvif);
-	}
 }
 
 static struct ath12k_vif_cache *ath12k_ahvif_get_link_cache(struct ath12k_vif *ahvif,

index 91f4e3aff74c3..6a0915a0c7aae 100644
@@ -3610,7 +3610,6 @@ ath12k_dp_mon_rx_update_user_stats(struct ath12k *ar,
 				   struct hal_rx_mon_ppdu_info *ppdu_info,
 				   u32 uid)
 {
-	struct ath12k_sta *ahsta;
 	struct ath12k_link_sta *arsta;
 	struct ath12k_rx_peer_stats *rx_stats = NULL;
 	struct hal_rx_user_status *user_stats = &ppdu_info->userstats[uid];

@@ -3628,8 +3627,13 @@ ath12k_dp_mon_rx_update_user_stats(struct ath12k *ar,
 		return;
 	}
 
-	ahsta = ath12k_sta_to_ahsta(peer->sta);
-	arsta = &ahsta->deflink;
+	arsta = ath12k_peer_get_link_sta(ar->ab, peer);
+	if (!arsta) {
+		ath12k_warn(ar->ab, "link sta not found on peer %pM id %d\n",
+			    peer->addr, peer->peer_id);
+		return;
+	}
+
 	arsta->rssi_comb = ppdu_info->rssi_comb;
 	ewma_avg_rssi_add(&arsta->avg_rssi, ppdu_info->rssi_comb);
 	rx_stats = arsta->rx_stats;

@@ -3742,7 +3746,6 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
 	struct dp_srng *mon_dst_ring;
 	struct hal_srng *srng;
 	struct dp_rxdma_mon_ring *buf_ring;
-	struct ath12k_sta *ahsta = NULL;
 	struct ath12k_link_sta *arsta;
 	struct ath12k_peer *peer;
 	struct sk_buff_head skb_list;

@@ -3868,8 +3871,15 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
 		}
 
 		if (ppdu_info->reception_type == HAL_RX_RECEPTION_TYPE_SU) {
-			ahsta = ath12k_sta_to_ahsta(peer->sta);
-			arsta = &ahsta->deflink;
+			arsta = ath12k_peer_get_link_sta(ar->ab, peer);
+			if (!arsta) {
+				ath12k_warn(ar->ab, "link sta not found on peer %pM id %d\n",
+					    peer->addr, peer->peer_id);
+				spin_unlock_bh(&ab->base_lock);
+				rcu_read_unlock();
+				dev_kfree_skb_any(skb);
+				continue;
+			}
 			ath12k_dp_mon_rx_update_peer_su_stats(ar, arsta,
 							      ppdu_info);
 		} else if ((ppdu_info->fc_valid) &&

index bd95dc88f9b21..e9137ffeb5ab4 100644
@@ -1418,8 +1418,6 @@ ath12k_update_per_peer_tx_stats(struct ath12k *ar,
 {
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_peer *peer;
-	struct ieee80211_sta *sta;
-	struct ath12k_sta *ahsta;
 	struct ath12k_link_sta *arsta;
 	struct htt_ppdu_stats_user_rate *user_rate;
 	struct ath12k_per_peer_tx_stats *peer_stats = &ar->peer_tx_stats;

@@ -1500,9 +1498,12 @@ ath12k_update_per_peer_tx_stats(struct ath12k *ar,
 		return;
 	}
 
-	sta = peer->sta;
-	ahsta = ath12k_sta_to_ahsta(sta);
-	arsta = &ahsta->deflink;
+	arsta = ath12k_peer_get_link_sta(ab, peer);
+	if (!arsta) {
+		spin_unlock_bh(&ab->base_lock);
+		rcu_read_unlock();
+		return;
+	}
 
 	memset(&arsta->txrate, 0, sizeof(arsta->txrate));
 

index f3a5e054d2b55..92c4988df2f16 100644
@@ -91,5 +91,31 @@ struct ath12k_peer *ath12k_peer_find_by_ast(struct ath12k_base *ab, int ast_hash
 int ath12k_peer_ml_create(struct ath12k_hw *ah, struct ieee80211_sta *sta);
 int ath12k_peer_ml_delete(struct ath12k_hw *ah, struct ieee80211_sta *sta);
 int ath12k_peer_mlo_link_peers_delete(struct ath12k_vif *ahvif, struct ath12k_sta *ahsta);
+static inline
+struct ath12k_link_sta *ath12k_peer_get_link_sta(struct ath12k_base *ab,
+						 struct ath12k_peer *peer)
+{
+	struct ath12k_sta *ahsta;
+	struct ath12k_link_sta *arsta;
+
+	if (!peer->sta)
+		return NULL;
+
+	ahsta = ath12k_sta_to_ahsta(peer->sta);
+	if (peer->ml_id & ATH12K_PEER_ML_ID_VALID) {
+		if (!(ahsta->links_map & BIT(peer->link_id))) {
+			ath12k_warn(ab, "peer %pM id %d link_id %d can't found in STA link_map 0x%x\n",
+				    peer->addr, peer->peer_id, peer->link_id,
+				    ahsta->links_map);
+			return NULL;
+		}
+		arsta = rcu_dereference(ahsta->link[peer->link_id]);
+		if (!arsta)
+			return NULL;
+	} else {
+		arsta =  &ahsta->deflink;
+	}
+	return arsta;
+}
 
 #endif /* _PEER_H_ */

index 4bd286296da79..cebdf62ce3db9 100644
@@ -116,6 +116,7 @@ static inline u64 ath12k_le32hilo_to_u64(__le32 hi, __le32 lo)
 enum ath12k_skb_flags {
 	ATH12K_SKB_HW_80211_ENCAP = BIT(0),
 	ATH12K_SKB_CIPHER_SET = BIT(1),
+	ATH12K_SKB_MLO_STA = BIT(2),
 };
 
 struct ath12k_skb_cb {

85 lines not on this page · raw message

index 0a75bc5abfa24..9c69dd5a22afa 100644
@@ -246,6 +246,8 @@ struct ath12k_hw_ops {
 	int (*rxdma_ring_sel_config)(struct ath12k_base *ab);
 	u8 (*get_ring_selector)(struct sk_buff *skb);
 	bool (*dp_srng_is_tx_comp_ring)(int ring_num);
+	bool (*is_frame_link_agnostic)(struct ath12k_link_vif *arvif,
+				       struct ieee80211_mgmt *mgmt);
 };
 
 static inline

index 87944e4467050..708dc3dd4347a 100644
@@ -7685,7 +7685,7 @@ static int ath12k_mac_mgmt_tx_wmi(struct ath12k *ar, struct ath12k_link_vif *arv
 
 	skb_cb->paddr = paddr;
 
-	ret = ath12k_wmi_mgmt_send(ar, arvif->vdev_id, buf_id, skb);
+	ret = ath12k_wmi_mgmt_send(arvif, buf_id, skb);
 	if (ret) {
 		ath12k_warn(ar->ab, "failed to send mgmt frame: %d\n", ret);
 		goto err_unmap_buf;

@@ -7997,6 +7997,9 @@ static void ath12k_mac_op_tx(struct ieee80211_hw *hw,
 
 		skb_cb->flags |= ATH12K_SKB_HW_80211_ENCAP;
 	} else if (ieee80211_is_mgmt(hdr->frame_control)) {
+		if (sta && sta->mlo)
+			skb_cb->flags |= ATH12K_SKB_MLO_STA;
+
 		ret = ath12k_mac_mgmt_tx(ar, skb, is_prb_rsp);
 		if (ret) {
 			ath12k_warn(ar->ab, "failed to queue management frame %d\n",

index ec7236bbccc0f..eb7aeff014903 100644
@@ -8,7 +8,7 @@
 #include "peer.h"
 #include "debug.h"
 
-static struct ath12k_ml_peer *ath12k_peer_ml_find(struct ath12k_hw *ah, const u8 *addr)
+struct ath12k_ml_peer *ath12k_peer_ml_find(struct ath12k_hw *ah, const u8 *addr)
 {
 	struct ath12k_ml_peer *ml_peer;
 

index 92c4988df2f16..44afc0b7dd53e 100644
@@ -91,6 +91,8 @@ struct ath12k_peer *ath12k_peer_find_by_ast(struct ath12k_base *ab, int ast_hash
 int ath12k_peer_ml_create(struct ath12k_hw *ah, struct ieee80211_sta *sta);
 int ath12k_peer_ml_delete(struct ath12k_hw *ah, struct ieee80211_sta *sta);
 int ath12k_peer_mlo_link_peers_delete(struct ath12k_vif *ahvif, struct ath12k_sta *ahsta);
+struct ath12k_ml_peer *ath12k_peer_ml_find(struct ath12k_hw *ah,
+					   const u8 *addr);
 static inline
 struct ath12k_link_sta *ath12k_peer_get_link_sta(struct ath12k_base *ab,
 						 struct ath12k_peer *peer)

78 lines not on this page · raw message

index 8627154f1680f..6dbcedcf08175 100644
@@ -3963,6 +3963,7 @@ struct wmi_scan_chan_list_cmd {
 } __packed;
 
 #define WMI_MGMT_SEND_DOWNLD_LEN	64
+#define WMI_MGMT_LINK_AGNOSTIC_ID	0xFFFFFFFF
 
 #define WMI_TX_PARAMS_DWORD0_POWER		GENMASK(7, 0)
 #define WMI_TX_PARAMS_DWORD0_MCS_MASK		GENMASK(19, 8)

@@ -3988,7 +3989,18 @@ struct wmi_mgmt_send_cmd {
 
 	/* This TLV is followed by struct wmi_mgmt_frame */
 
-	/* Followed by struct wmi_mgmt_send_params */
+	/* Followed by struct ath12k_wmi_mlo_mgmt_send_params */
+} __packed;
+
+struct ath12k_wmi_mlo_mgmt_send_params {
+	__le32 tlv_header;
+	__le32 hw_link_id;
+} __packed;
+
+struct ath12k_wmi_mgmt_send_tx_params {
+	__le32 tlv_header;
+	__le32 tx_param_dword0;
+	__le32 tx_param_dword1;
 } __packed;
 
 struct wmi_sta_powersave_mode_cmd {

@@ -6183,7 +6195,7 @@ void ath12k_wmi_init_wcn7850(struct ath12k_base *ab,
 int ath12k_wmi_cmd_send(struct ath12k_wmi_pdev *wmi, struct sk_buff *skb,
 			u32 cmd_id);
 struct sk_buff *ath12k_wmi_alloc_skb(struct ath12k_wmi_base *wmi_sc, u32 len);
-int ath12k_wmi_mgmt_send(struct ath12k *ar, u32 vdev_id, u32 buf_id,
+int ath12k_wmi_mgmt_send(struct ath12k_link_vif *arvif, u32 buf_id,
 			 struct sk_buff *frame);
 int ath12k_wmi_p2p_go_bcn_ie(struct ath12k *ar, u32 vdev_id,
 			     const u8 *p2p_ie);

index d333f40408feb..d740326079e1d 100644
@@ -840,7 +840,7 @@ int ath12k_wmi_mgmt_send(struct ath12k_link_vif *arvif, u32 buf_id,
 	cmd->tx_params_valid = 0;
 
 	frame_tlv = (struct wmi_tlv *)(skb->data + sizeof(*cmd));
-	frame_tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_BYTE, buf_len);
+	frame_tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_BYTE, buf_len_aligned);
 
 	memcpy(frame_tlv->value, frame->data, buf_len);
 

index a4a2bac4f4b27..2f8d0223c1a6d 100644
@@ -1168,12 +1168,6 @@ static void __iomem *mvebu_pcie_map_registers(struct platform_device *pdev,
 	return devm_ioremap_resource(&pdev->dev, &port->regs);
 }
 
-#define DT_FLAGS_TO_TYPE(flags)       (((flags) >> 24) & 0x03)
-#define    DT_TYPE_IO                 0x1
-#define    DT_TYPE_MEM32              0x2
-#define DT_CPUADDR_TO_TARGET(cpuaddr) (((cpuaddr) >> 56) & 0xFF)
-#define DT_CPUADDR_TO_ATTR(cpuaddr)   (((cpuaddr) >> 48) & 0xFF)
-
 static int mvebu_get_tgt_attr(struct device_node *np, int devfn,
 			      unsigned long type,
 			      unsigned int *tgt,

@@ -1189,19 +1183,12 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn,
 		return -EINVAL;
 
 	for_each_of_range(&parser, &range) {
-		unsigned long rtype;
 		u32 slot = upper_32_bits(range.bus_addr);
 
-		if (DT_FLAGS_TO_TYPE(range.flags) == DT_TYPE_IO)
-			rtype = IORESOURCE_IO;
-		else if (DT_FLAGS_TO_TYPE(range.flags) == DT_TYPE_MEM32)
-			rtype = IORESOURCE_MEM;
-		else
-			continue;
-
-		if (slot == PCI_SLOT(devfn) && type == rtype) {
-			*tgt = DT_CPUADDR_TO_TARGET(range.cpu_addr);
-			*attr = DT_CPUADDR_TO_ATTR(range.cpu_addr);
+		if (slot == PCI_SLOT(devfn) &&
+		    type == (range.flags & IORESOURCE_TYPE_BITS)) {
+			*tgt = (range.parent_bus_addr >> 56) & 0xFF;
+			*attr = (range.parent_bus_addr >> 48) & 0xFF;
 			return 0;
 		}
 	}

index 104732d345434..978c129c60950 100644
@@ -1836,6 +1836,9 @@ static int genl_bind(struct net *net, int group)
 		    !ns_capable(net->user_ns, CAP_SYS_ADMIN))
 			ret = -EPERM;
 
+		if (ret)
+			break;
+
 		if (family->bind)
 			family->bind(i);
 

index d15d912690c40..073d20241a4c9 100644
@@ -1229,9 +1229,15 @@ static int b53_setup(struct dsa_switch *ds)
 	 */
 	ds->untag_vlan_aware_bridge_pvid = true;
 
-	/* Ageing time is set in seconds */
-	ds->ageing_time_min = 1 * 1000;
-	ds->ageing_time_max = AGE_TIME_MAX * 1000;
+	if (dev->chip_id == BCM53101_DEVICE_ID) {
+		/* BCM53101 uses 0.5 second increments */
+		ds->ageing_time_min = 1 * 500;
+		ds->ageing_time_max = AGE_TIME_MAX * 500;
+	} else {
+		/* Everything else uses 1 second increments */
+		ds->ageing_time_min = 1 * 1000;
+		ds->ageing_time_max = AGE_TIME_MAX * 1000;
+	}
 
 	ret = b53_reset_switch(dev);
 	if (ret) {

@@ -2448,7 +2454,10 @@ int b53_set_ageing_time(struct dsa_switch *ds, unsigned int msecs)
 	else
 		reg = B53_AGING_TIME_CONTROL;
 
-	atc = DIV_ROUND_CLOSEST(msecs, 1000);
+	if (dev->chip_id == BCM53101_DEVICE_ID)
+		atc = DIV_ROUND_CLOSEST(msecs, 500);
+	else
+		atc = DIV_ROUND_CLOSEST(msecs, 1000);
 
 	if (!is5325(dev) && !is5365(dev))
 		atc |= AGE_CHANGE;

index 0adeafe11a365..ad2d8f59fc7bc 100644
@@ -324,6 +324,13 @@ int br_boolopt_multi_toggle(struct net_bridge *br,
 	int err = 0;
 	int opt_id;
 
+	opt_id = find_next_bit(&bitmap, BITS_PER_LONG, BR_BOOLOPT_MAX);
+	if (opt_id != BITS_PER_LONG) {
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Unknown boolean option %d",
+				       opt_id);
+		return -EINVAL;
+	}
+
 	for_each_set_bit(opt_id, &bitmap, BR_BOOLOPT_MAX) {
 		bool on = !!(bm->optval & BIT(opt_id));
 

index f65d2f7273813..8392d304a72eb 100644
@@ -204,6 +204,9 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu)
 	if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr)))
 		return -EINVAL;
 
+	if (skb_is_gso(skb))
+		skb_gso_reset(skb);
+
 	skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN);
 	pskb_pull(skb, ETH_HLEN);
 	skb_reset_network_header(skb);

@@ -298,6 +301,9 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu)
 	if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr)))
 		return -EINVAL;
 
+	if (skb_is_gso(skb))
+		skb_gso_reset(skb);
+
 	skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN);
 	pskb_pull(skb, ETH_HLEN);
 	skb_reset_network_header(skb);

index b76a154e635e0..d87438bef6fba 100644
@@ -4451,8 +4451,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring)
 	if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
 		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
 	res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
-			       rx_ring->queue_index,
-			       rx_ring->q_vector->napi.napi_id);
+			       rx_ring->queue_index, 0);
 	if (res < 0) {
 		dev_err(dev, "Failed to register xdp_rxq index %u\n",
 			rx_ring->queue_index);

index ca6ccbc139548..6412c84e2d17d 100644
@@ -2081,11 +2081,8 @@ static void igb_diag_test(struct net_device *netdev,
 	} else {
 		dev_info(&adapter->pdev->dev, "online testing starting\n");
 
-		/* PHY is powered down when interface is down */
-		if (if_running && igb_link_test(adapter, &data[TEST_LINK]))
+		if (igb_link_test(adapter, &data[TEST_LINK]))
 			eth_test->flags |= ETH_TEST_FL_FAILED;
-		else
-			data[TEST_LINK] = 0;
 
 		/* Online tests aren't run; pass by default */
 		data[TEST_REG] = 0;

index f1c9e575703ea..26dcdceae741e 100644
@@ -4182,7 +4182,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename)
 		irq_num = pf->msix_entries[base + vector].vector;
 		irq_set_affinity_notifier(irq_num, NULL);
 		irq_update_affinity_hint(irq_num, NULL);
-		free_irq(irq_num, &vsi->q_vectors[vector]);
+		free_irq(irq_num, vsi->q_vectors[vector]);
 	}
 	return err;
 }

index 1f710b3fc599b..5ae3d70e45167 100644
@@ -40,6 +40,8 @@
  *
  *	# echo 1 > /sys/kernel/config/xe/0000:03:00.0/survivability_mode
  *
+ * It is the responsibility of the user to clear the mode once firmware flash is complete.
+ *
  * Refer :ref:`xe_configfs` for more details on how to use configfs
  *
  * Survivability mode is indicated by the below admin-only readable sysfs which provides additional

@@ -146,7 +148,6 @@ static void xe_survivability_mode_fini(void *arg)
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
 	struct device *dev = &pdev->dev;
 
-	xe_configfs_clear_survivability_mode(pdev);
 	sysfs_remove_file(&dev->kobj, &dev_attr_survivability_mode.attr);
 }
 

index cdb8685ae7d71..454e362ff096a 100644
@@ -955,7 +955,7 @@ enum dc_status dcn20_enable_stream_timing(
 		return DC_ERROR_UNEXPECTED;
 	}
 
-	fsleep(stream->timing.v_total * (stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz));
+	udelay(stream->timing.v_total * (stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz));
 
 	params.vertical_total_min = stream->adjust.v_total_min;
 	params.vertical_total_max = stream->adjust.v_total_max;

index 616479e714663..9447065d01afb 100644
@@ -464,8 +464,15 @@ int generic_hwtstamp_get_lower(struct net_device *dev,
 	if (!netif_device_present(dev))
 		return -ENODEV;
 
-	if (ops->ndo_hwtstamp_get)
-		return dev_get_hwtstamp_phylib(dev, kernel_cfg);
+	if (ops->ndo_hwtstamp_get) {
+		int err;
+
+		netdev_lock_ops(dev);
+		err = dev_get_hwtstamp_phylib(dev, kernel_cfg);
+		netdev_unlock_ops(dev);
+
+		return err;
+	}
 
 	/* Legacy path: unconverted lower driver */
 	return generic_hwtstamp_ioctl_lower(dev, SIOCGHWTSTAMP, kernel_cfg);

@@ -481,8 +488,15 @@ int generic_hwtstamp_set_lower(struct net_device *dev,
 	if (!netif_device_present(dev))
 		return -ENODEV;
 
-	if (ops->ndo_hwtstamp_set)
-		return dev_set_hwtstamp_phylib(dev, kernel_cfg, extack);
+	if (ops->ndo_hwtstamp_set) {
+		int err;
+
+		netdev_lock_ops(dev);
+		err = dev_set_hwtstamp_phylib(dev, kernel_cfg, extack);
+		netdev_unlock_ops(dev);
+
+		return err;
+	}
 
 	/* Legacy path: unconverted lower driver */
 	return generic_hwtstamp_ioctl_lower(dev, SIOCSHWTSTAMP, kernel_cfg);

index 01329fe7451a1..0eca96eeed58a 100644
@@ -4286,6 +4286,7 @@ static int macsec_newlink(struct net_device *dev,
 	if (err < 0)
 		goto del_dev;
 
+	netdev_update_features(dev);
 	netif_stacked_transfer_operstate(real_dev, dev);
 	linkwatch_fire_event(dev);
 

index 31a93cae5111b..81f58924b4acd 100644
@@ -212,6 +212,7 @@ void j1939_priv_get(struct j1939_priv *priv);
 
 /* notify/alert all j1939 sockets bound to ifindex */
 void j1939_sk_netdev_event_netdown(struct j1939_priv *priv);
+void j1939_sk_netdev_event_unregister(struct j1939_priv *priv);
 int j1939_cancel_active_session(struct j1939_priv *priv, struct sock *sk);
 void j1939_tp_init(struct j1939_priv *priv);
 

index 7e8a20f2fc42b..3706a872ecafd 100644
@@ -377,6 +377,9 @@ static int j1939_netdev_notify(struct notifier_block *nb,
 		j1939_sk_netdev_event_netdown(priv);
 		j1939_ecu_unmap_all(priv);
 		break;
+	case NETDEV_UNREGISTER:
+		j1939_sk_netdev_event_unregister(priv);
+		break;
 	}
 
 	j1939_priv_put(priv);

55 lines not on this page · raw message

index b3a45aa70cf2f..785b883a1319d 100644
@@ -520,6 +520,9 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 	ret = j1939_local_ecu_get(priv, jsk->addr.src_name, jsk->addr.sa);
 	if (ret) {
 		j1939_netdev_stop(priv);
+		jsk->priv = NULL;
+		synchronize_rcu();
+		j1939_priv_put(priv);
 		goto out_release_sock;
 	}
 

index 39844f14eed86..797719cb227ec 100644
@@ -290,8 +290,11 @@ int j1939_local_ecu_get(struct j1939_priv *priv, name_t name, u8 sa)
 	if (!ecu)
 		ecu = j1939_ecu_create_locked(priv, name);
 	err = PTR_ERR_OR_ZERO(ecu);
-	if (err)
+	if (err) {
+		if (j1939_address_is_unicast(sa))
+			priv->ents[sa].nusers--;
 		goto done;
+	}
 
 	ecu->nusers++;
 	/* TODO: do we care if ecu->addr != sa? */

index 3f2e378199abb..5abe4af61655c 100644
@@ -690,14 +690,6 @@ static void xcan_write_frame(struct net_device *ndev, struct sk_buff *skb,
 		dlc |= XCAN_DLCR_EDL_MASK;
 	}
 
-	if (!(priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES) &&
-	    (priv->devtype.flags & XCAN_FLAG_TXFEMP))
-		can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max, 0);
-	else
-		can_put_echo_skb(skb, ndev, 0, 0);
-
-	priv->tx_head++;
-
 	priv->write_reg(priv, XCAN_FRAME_ID_OFFSET(frame_offset), id);
 	/* If the CAN frame is RTR frame this write triggers transmission
 	 * (not on CAN FD)

@@ -730,6 +722,14 @@ static void xcan_write_frame(struct net_device *ndev, struct sk_buff *skb,
 					data[1]);
 		}
 	}
+
+	if (!(priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES) &&
+	    (priv->devtype.flags & XCAN_FLAG_TXFEMP))
+		can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max, 0);
+	else
+		can_put_echo_skb(skb, ndev, 0, 0);
+
+	priv->tx_head++;
 }
 
 /**

index 12390d2e994fc..8a435cc0e98c4 100644
@@ -221,7 +221,8 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx,
 	const struct nft_bitmap *priv = nft_set_priv(set);
 	struct nft_bitmap_elem *be;
 
-	list_for_each_entry_rcu(be, &priv->list, head) {
+	list_for_each_entry_rcu(be, &priv->list, head,
+				lockdep_is_held(&nft_pernet(ctx->net)->commit_mutex)) {
 		if (iter->count < iter->skip)
 			goto cont;
 

index 9e4e25f2458f9..9ac48e6b4332c 100644
@@ -502,8 +502,6 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 
 /**
  * pipapo_get() - Get matching element reference given key data
- * @net:	Network namespace
- * @set:	nftables API set representation
  * @m:		storage containing active/existing elements
  * @data:	Key data to be matched against existing elements
  * @genmask:	If set, check that element is active in given genmask

@@ -516,9 +514,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
  *
  * Return: pointer to &struct nft_pipapo_elem on match, error pointer otherwise.
  */
-static struct nft_pipapo_elem *pipapo_get(const struct net *net,
-					  const struct nft_set *set,
-					  const struct nft_pipapo_match *m,
+static struct nft_pipapo_elem *pipapo_get(const struct nft_pipapo_match *m,
 					  const u8 *data, u8 genmask,
 					  u64 tstamp, gfp_t gfp)
 {

@@ -615,7 +611,7 @@ nft_pipapo_get(const struct net *net, const struct nft_set *set,
 	struct nft_pipapo_match *m = rcu_dereference(priv->match);
 	struct nft_pipapo_elem *e;
 
-	e = pipapo_get(net, set, m, (const u8 *)elem->key.val.data,
+	e = pipapo_get(m, (const u8 *)elem->key.val.data,
 		       nft_genmask_cur(net), get_jiffies_64(),
 		       GFP_ATOMIC);
 	if (IS_ERR(e))

@@ -1344,7 +1340,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 	else
 		end = start;
 
-	dup = pipapo_get(net, set, m, start, genmask, tstamp, GFP_KERNEL);
+	dup = pipapo_get(m, start, genmask, tstamp, GFP_KERNEL);
 	if (!IS_ERR(dup)) {
 		/* Check if we already have the same exact entry */
 		const struct nft_data *dup_key, *dup_end;

@@ -1366,7 +1362,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 
 	if (PTR_ERR(dup) == -ENOENT) {
 		/* Look for partially overlapping entries */
-		dup = pipapo_get(net, set, m, end, nft_genmask_next(net), tstamp,
+		dup = pipapo_get(m, end, nft_genmask_next(net), tstamp,
 				 GFP_KERNEL);
 	}
 

@@ -1913,7 +1909,7 @@ nft_pipapo_deactivate(const struct net *net, const struct nft_set *set,
 	if (!m)
 		return NULL;
 
-	e = pipapo_get(net, set, m, (const u8 *)elem->key.val.data,
+	e = pipapo_get(m, (const u8 *)elem->key.val.data,
 		       nft_genmask_next(net), nft_net_tstamp(net), GFP_KERNEL);
 	if (IS_ERR(e))
 		return NULL;

index 5e49619ae49c6..cf65703e221fa 100644
@@ -459,19 +459,17 @@ struct nft_set_ext;
  *	control plane functions.
  */
 struct nft_set_ops {
-	bool				(*lookup)(const struct net *net,
+	const struct nft_set_ext *	(*lookup)(const struct net *net,
 						  const struct nft_set *set,
-						  const u32 *key,
-						  const struct nft_set_ext **ext);
-	bool				(*update)(struct nft_set *set,
+						  const u32 *key);
+	const struct nft_set_ext *	(*update)(struct nft_set *set,
 						  const u32 *key,
 						  struct nft_elem_priv *
 							(*new)(struct nft_set *,
 							       const struct nft_expr *,
 							       struct nft_regs *),
 						  const struct nft_expr *expr,
-						  struct nft_regs *regs,
-						  const struct nft_set_ext **ext);
+						  struct nft_regs *regs);
 	bool				(*delete)(const struct nft_set *set,
 						  const u32 *key);
 

61 lines not on this page · raw message

index 88922e0e8e837..e24493d9e7761 100644
@@ -91,8 +91,9 @@ void nft_dynset_eval(const struct nft_expr *expr,
 		return;
 	}
 
-	if (set->ops->update(set, &regs->data[priv->sreg_key], nft_dynset_new,
-			     expr, regs, &ext)) {
+	ext = set->ops->update(set, &regs->data[priv->sreg_key], nft_dynset_new,
+			     expr, regs);
+	if (ext) {
 		if (priv->op == NFT_DYNSET_OP_UPDATE &&
 		    nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) &&
 		    READ_ONCE(nft_set_ext_timeout(ext)->timeout) != 0) {

index 63ef832b8aa71..40c602ffbcba7 100644
@@ -25,32 +25,33 @@ struct nft_lookup {
 };
 
 #ifdef CONFIG_MITIGATION_RETPOLINE
-bool nft_set_do_lookup(const struct net *net, const struct nft_set *set,
-		       const u32 *key, const struct nft_set_ext **ext)
+const struct nft_set_ext *
+nft_set_do_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key)
 {
 	if (set->ops == &nft_set_hash_fast_type.ops)
-		return nft_hash_lookup_fast(net, set, key, ext);
+		return nft_hash_lookup_fast(net, set, key);
 	if (set->ops == &nft_set_hash_type.ops)
-		return nft_hash_lookup(net, set, key, ext);
+		return nft_hash_lookup(net, set, key);
 
 	if (set->ops == &nft_set_rhash_type.ops)
-		return nft_rhash_lookup(net, set, key, ext);
+		return nft_rhash_lookup(net, set, key);
 
 	if (set->ops == &nft_set_bitmap_type.ops)
-		return nft_bitmap_lookup(net, set, key, ext);
+		return nft_bitmap_lookup(net, set, key);
 
 	if (set->ops == &nft_set_pipapo_type.ops)
-		return nft_pipapo_lookup(net, set, key, ext);
+		return nft_pipapo_lookup(net, set, key);
 #if defined(CONFIG_X86_64) && !defined(CONFIG_UML)
 	if (set->ops == &nft_set_pipapo_avx2_type.ops)
-		return nft_pipapo_avx2_lookup(net, set, key, ext);
+		return nft_pipapo_avx2_lookup(net, set, key);
 #endif
 
 	if (set->ops == &nft_set_rbtree_type.ops)
-		return nft_rbtree_lookup(net, set, key, ext);
+		return nft_rbtree_lookup(net, set, key);
 
 	WARN_ON_ONCE(1);
-	return set->ops->lookup(net, set, key, ext);
+	return set->ops->lookup(net, set, key);
 }
 EXPORT_SYMBOL_GPL(nft_set_do_lookup);
 #endif

@@ -61,12 +62,12 @@ void nft_lookup_eval(const struct nft_expr *expr,
 {
 	const struct nft_lookup *priv = nft_expr_priv(expr);
 	const struct nft_set *set = priv->set;
-	const struct nft_set_ext *ext = NULL;
 	const struct net *net = nft_net(pkt);
+	const struct nft_set_ext *ext;
 	bool found;
 
-	found =	nft_set_do_lookup(net, set, &regs->data[priv->sreg], &ext) ^
-				  priv->invert;
+	ext = nft_set_do_lookup(net, set, &regs->data[priv->sreg]);
+	found = !!ext ^ priv->invert;
 	if (!found) {
 		ext = nft_set_catchall_lookup(net, set);
 		if (!ext) {

index 09da7a3f9f967..8ee66a86c3bc7 100644
@@ -111,10 +111,9 @@ void nft_objref_map_eval(const struct nft_expr *expr,
 	struct net *net = nft_net(pkt);
 	const struct nft_set_ext *ext;
 	struct nft_object *obj;
-	bool found;
 
-	found = nft_set_do_lookup(net, set, &regs->data[priv->sreg], &ext);
-	if (!found) {
+	ext = nft_set_do_lookup(net, set, &regs->data[priv->sreg]);
+	if (!ext) {
 		ext = nft_set_catchall_lookup(net, set);
 		if (!ext) {
 			regs->verdict.code = NFT_BREAK;

index 8a435cc0e98c4..8d3f040a904a2 100644
@@ -75,16 +75,21 @@ nft_bitmap_active(const u8 *bitmap, u32 idx, u32 off, u8 genmask)
 }
 
 INDIRECT_CALLABLE_SCOPE
-bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set,
-		       const u32 *key, const struct nft_set_ext **ext)
+const struct nft_set_ext *
+nft_bitmap_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key)
 {
 	const struct nft_bitmap *priv = nft_set_priv(set);
+	static const struct nft_set_ext found;
 	u8 genmask = nft_genmask_cur(net);
 	u32 idx, off;
 
 	nft_bitmap_location(set, key, &idx, &off);
 
-	return nft_bitmap_active(priv->bitmap, idx, off, genmask);
+	if (nft_bitmap_active(priv->bitmap, idx, off, genmask))
+		return &found;
+
+	return NULL;
 }
 
 static struct nft_bitmap_elem *

110 lines not on this page · raw message

index 9ac48e6b4332c..a844b33fa6002 100644
@@ -407,8 +407,9 @@ int pipapo_refill(unsigned long *map, unsigned int len, unsigned int rules,
  *
  * Return: true on match, false otherwise.
  */
-bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
-		       const u32 *key, const struct nft_set_ext **ext)
+const struct nft_set_ext *
+nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
 	struct nft_pipapo_scratch *scratch;

@@ -465,13 +466,15 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 			scratch->map_index = map_index;
 			local_bh_enable();
 
-			return false;
+			return NULL;
 		}
 
 		if (last) {
-			*ext = &f->mt[b].e->ext;
-			if (unlikely(nft_set_elem_expired(*ext) ||
-				     !nft_set_elem_active(*ext, genmask)))
+			const struct nft_set_ext *ext;
+
+			ext = &f->mt[b].e->ext;
+			if (unlikely(nft_set_elem_expired(ext) ||
+				     !nft_set_elem_active(ext, genmask)))
 				goto next_match;
 
 			/* Last field: we're just returning the key without

@@ -482,7 +485,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 			scratch->map_index = map_index;
 			local_bh_enable();
 
-			return true;
+			return ext;
 		}
 
 		/* Swap bitmap indices: res_map is the initial bitmap for the

@@ -497,7 +500,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 
 out:
 	local_bh_enable();
-	return false;
+	return NULL;
 }
 
 /**

index be7c16c79f711..6c441e2dc8af3 100644
@@ -1146,8 +1146,9 @@ static inline void pipapo_resmap_init_avx2(const struct nft_pipapo_match *m, uns
  *
  * Return: true on match, false otherwise.
  */
-bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
-			    const u32 *key, const struct nft_set_ext **ext)
+const struct nft_set_ext *
+nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
+		       const u32 *key)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
 	struct nft_pipapo_scratch *scratch;

@@ -1155,17 +1156,18 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 	const struct nft_pipapo_match *m;
 	const struct nft_pipapo_field *f;
 	const u8 *rp = (const u8 *)key;
+	const struct nft_set_ext *ext;
 	unsigned long *res, *fill;
 	bool map_index;
-	int i, ret = 0;
+	int i;
 
 	local_bh_disable();
 
 	if (unlikely(!irq_fpu_usable())) {
-		bool fallback_res = nft_pipapo_lookup(net, set, key, ext);
+		ext = nft_pipapo_lookup(net, set, key);
 
 		local_bh_enable();
-		return fallback_res;
+		return ext;
 	}
 
 	m = rcu_dereference(priv->match);

@@ -1182,7 +1184,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 	if (unlikely(!scratch)) {
 		kernel_fpu_end();
 		local_bh_enable();
-		return false;
+		return NULL;
 	}
 
 	map_index = scratch->map_index;

@@ -1197,6 +1199,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 next_match:
 	nft_pipapo_for_each_field(f, i, m) {
 		bool last = i == m->field_count - 1, first = !i;
+		int ret = 0;
 
 #define NFT_SET_PIPAPO_AVX2_LOOKUP(b, n)				\
 		(ret = nft_pipapo_avx2_lookup_##b##b_##n(res, fill, f,	\

@@ -1244,10 +1247,10 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 			goto out;
 
 		if (last) {
-			*ext = &f->mt[ret].e->ext;
-			if (unlikely(nft_set_elem_expired(*ext) ||
-				     !nft_set_elem_active(*ext, genmask))) {
-				ret = 0;
+			ext = &f->mt[ret].e->ext;
+			if (unlikely(nft_set_elem_expired(ext) ||
+				     !nft_set_elem_active(ext, genmask))) {
+				ext = NULL;
 				goto next_match;
 			}
 

@@ -1264,5 +1267,5 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 	kernel_fpu_end();
 	local_bh_enable();
 
-	return ret >= 0;
+	return ext;
 }

index 2e8ef16ff191d..938a257c069e2 100644
@@ -52,9 +52,9 @@ static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe)
 	return nft_set_elem_expired(&rbe->ext);
 }
 
-static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
-				const u32 *key, const struct nft_set_ext **ext,
-				unsigned int seq)
+static const struct nft_set_ext *
+__nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
+		    const u32 *key, unsigned int seq)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	const struct nft_rbtree_elem *rbe, *interval = NULL;

@@ -65,7 +65,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 	parent = rcu_dereference_raw(priv->root.rb_node);
 	while (parent != NULL) {
 		if (read_seqcount_retry(&priv->count, seq))
-			return false;
+			return NULL;
 
 		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
 

@@ -87,50 +87,48 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 			}
 
 			if (nft_rbtree_elem_expired(rbe))
-				return false;
+				return NULL;
 
 			if (nft_rbtree_interval_end(rbe)) {
 				if (nft_set_is_anonymous(set))
-					return false;
+					return NULL;
 				parent = rcu_dereference_raw(parent->rb_left);
 				interval = NULL;
 				continue;
 			}
 
-			*ext = &rbe->ext;
-			return true;
+			return &rbe->ext;
 		}
 	}
 
 	if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
 	    nft_set_elem_active(&interval->ext, genmask) &&
 	    !nft_rbtree_elem_expired(interval) &&
-	    nft_rbtree_interval_start(interval)) {
-		*ext = &interval->ext;
-		return true;
-	}
+	    nft_rbtree_interval_start(interval))
+		return &interval->ext;
 
-	return false;
+	return NULL;
 }
 
 INDIRECT_CALLABLE_SCOPE
-bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
-		       const u32 *key, const struct nft_set_ext **ext)
+const struct nft_set_ext *
+nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	unsigned int seq = read_seqcount_begin(&priv->count);
-	bool ret;
+	const struct nft_set_ext *ext;
 
-	ret = __nft_rbtree_lookup(net, set, key, ext, seq);
-	if (ret || !read_seqcount_retry(&priv->count, seq))
-		return ret;
+	ext = __nft_rbtree_lookup(net, set, key, seq);
+	if (ext || !read_seqcount_retry(&priv->count, seq))
+		return ext;
 
 	read_lock_bh(&priv->lock);
 	seq = read_seqcount_begin(&priv->count);
-	ret = __nft_rbtree_lookup(net, set, key, ext, seq);
+	ext = __nft_rbtree_lookup(net, set, key, seq);
 	read_unlock_bh(&priv->lock);
 
-	return ret;
+	return ext;
 }
 
 static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set,

index a844b33fa6002..1a19649c28511 100644
@@ -397,35 +397,36 @@ int pipapo_refill(unsigned long *map, unsigned int len, unsigned int rules,
 }
 
 /**
- * nft_pipapo_lookup() - Lookup function
- * @net:	Network namespace
- * @set:	nftables API set representation
- * @key:	nftables API element representation containing key data
- * @ext:	nftables API extension pointer, filled with matching reference
+ * pipapo_get() - Get matching element reference given key data
+ * @m:		storage containing the set elements
+ * @data:	Key data to be matched against existing elements
+ * @genmask:	If set, check that element is active in given genmask
+ * @tstamp:	timestamp to check for expired elements
  *
  * For more details, see DOC: Theory of Operation.
  *
- * Return: true on match, false otherwise.
+ * This is the main lookup function.  It matches key data against either
+ * the working match set or the uncommitted copy, depending on what the
+ * caller passed to us.
+ * nft_pipapo_get (lookup from userspace/control plane) and nft_pipapo_lookup
+ * (datapath lookup) pass the active copy.
+ * The insertion path will pass the uncommitted working copy.
+ *
+ * Return: pointer to &struct nft_pipapo_elem on match, NULL otherwise.
  */
-const struct nft_set_ext *
-nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
-		  const u32 *key)
+static struct nft_pipapo_elem *pipapo_get(const struct nft_pipapo_match *m,
+					  const u8 *data, u8 genmask,
+					  u64 tstamp)
 {
-	struct nft_pipapo *priv = nft_set_priv(set);
 	struct nft_pipapo_scratch *scratch;
 	unsigned long *res_map, *fill_map;
-	u8 genmask = nft_genmask_cur(net);
-	const struct nft_pipapo_match *m;
 	const struct nft_pipapo_field *f;
-	const u8 *rp = (const u8 *)key;
 	bool map_index;
 	int i;
 
 	local_bh_disable();
 
-	m = rcu_dereference(priv->match);
-
-	if (unlikely(!m || !*raw_cpu_ptr(m->scratch)))
+	if (unlikely(!raw_cpu_ptr(m->scratch)))
 		goto out;
 
 	scratch = *raw_cpu_ptr(m->scratch);

@@ -445,12 +446,12 @@ nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 		 * packet bytes value, then AND bucket value
 		 */
 		if (likely(f->bb == 8))
-			pipapo_and_field_buckets_8bit(f, res_map, rp);
+			pipapo_and_field_buckets_8bit(f, res_map, data);
 		else
-			pipapo_and_field_buckets_4bit(f, res_map, rp);
+			pipapo_and_field_buckets_4bit(f, res_map, data);
 		NFT_PIPAPO_GROUP_BITS_ARE_8_OR_4;
 
-		rp += f->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f);
+		data += f->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f);
 
 		/* Now populate the bitmap for the next field, unless this is
 		 * the last field, in which case return the matched 'ext'

@@ -470,11 +471,11 @@ nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 		}
 
 		if (last) {
-			const struct nft_set_ext *ext;
+			struct nft_pipapo_elem *e;
 
-			ext = &f->mt[b].e->ext;
-			if (unlikely(nft_set_elem_expired(ext) ||
-				     !nft_set_elem_active(ext, genmask)))
+			e = f->mt[b].e;
+			if (unlikely(__nft_set_elem_expired(&e->ext, tstamp) ||
+				     !nft_set_elem_active(&e->ext, genmask)))
 				goto next_match;
 
 			/* Last field: we're just returning the key without

@@ -484,8 +485,7 @@ nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 			 */
 			scratch->map_index = map_index;
 			local_bh_enable();
-
-			return ext;
+			return e;
 		}
 
 		/* Swap bitmap indices: res_map is the initial bitmap for the

@@ -495,7 +495,7 @@ nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 		map_index = !map_index;
 		swap(res_map, fill_map);
 
-		rp += NFT_PIPAPO_GROUPS_PADDING(f);
+		data += NFT_PIPAPO_GROUPS_PADDING(f);
 	}
 
 out:

@@ -504,99 +504,29 @@ nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 }
 
 /**
- * pipapo_get() - Get matching element reference given key data
- * @m:		storage containing active/existing elements
- * @data:	Key data to be matched against existing elements
- * @genmask:	If set, check that element is active in given genmask
- * @tstamp:	timestamp to check for expired elements
- * @gfp:	the type of memory to allocate (see kmalloc).
+ * nft_pipapo_lookup() - Dataplane fronted for main lookup function
+ * @net:	Network namespace
+ * @set:	nftables API set representation
+ * @key:	pointer to nft registers containing key data
  *
- * This is essentially the same as the lookup function, except that it matches
- * key data against the uncommitted copy and doesn't use preallocated maps for
- * bitmap results.
+ * This function is called from the data path.  It will search for
+ * an element matching the given key in the current active copy.
  *
- * Return: pointer to &struct nft_pipapo_elem on match, error pointer otherwise.
+ * Return: ntables API extension pointer or NULL if no match.
  */
-static struct nft_pipapo_elem *pipapo_get(const struct nft_pipapo_match *m,
-					  const u8 *data, u8 genmask,
-					  u64 tstamp, gfp_t gfp)
+const struct nft_set_ext *
+nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key)
 {
-	struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT);
-	unsigned long *res_map, *fill_map = NULL;
-	const struct nft_pipapo_field *f;
-	int i;
-
-	if (m->bsize_max == 0)
-		return ret;
-
-	res_map = kmalloc_array(m->bsize_max, sizeof(*res_map), gfp);
-	if (!res_map) {
-		ret = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	fill_map = kcalloc(m->bsize_max, sizeof(*res_map), gfp);
-	if (!fill_map) {
-		ret = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	pipapo_resmap_init(m, res_map);
-
-	nft_pipapo_for_each_field(f, i, m) {
-		bool last = i == m->field_count - 1;
-		int b;
-
-		/* For each bit group: select lookup table bucket depending on
-		 * packet bytes value, then AND bucket value
-		 */
-		if (f->bb == 8)
-			pipapo_and_field_buckets_8bit(f, res_map, data);
-		else if (f->bb == 4)
-			pipapo_and_field_buckets_4bit(f, res_map, data);
-		else
-			BUG();
-
-		data += f->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f);
-
-		/* Now populate the bitmap for the next field, unless this is
-		 * the last field, in which case return the matched 'ext'
-		 * pointer if any.
-		 *
-		 * Now res_map contains the matching bitmap, and fill_map is the
-		 * bitmap for the next field.
-		 */
-next_match:
-		b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt,
-				  last);
-		if (b < 0)
-			goto out;
-
-		if (last) {
-			if (__nft_set_elem_expired(&f->mt[b].e->ext, tstamp))
-				goto next_match;
-			if ((genmask &&
-			     !nft_set_elem_active(&f->mt[b].e->ext, genmask)))
-				goto next_match;
-
-			ret = f->mt[b].e;
-			goto out;
-		}
-
-		data += NFT_PIPAPO_GROUPS_PADDING(f);
+	struct nft_pipapo *priv = nft_set_priv(set);
+	u8 genmask = nft_genmask_cur(net);
+	const struct nft_pipapo_match *m;
+	const struct nft_pipapo_elem *e;
 
-		/* Swap bitmap indices: fill_map will be the initial bitmap for
-		 * the next field (i.e. the new res_map), and res_map is
-		 * guaranteed to be all-zeroes at this point, ready to be filled
-		 * according to the next mapping table.
-		 */
-		swap(res_map, fill_map);
-	}
+	m = rcu_dereference(priv->match);
+	e = pipapo_get(m, (const u8 *)key, genmask, get_jiffies_64());
 
-out:
-	kfree(fill_map);
-	kfree(res_map);
-	return ret;
+	return e ? &e->ext : NULL;
 }
 
 /**

@@ -605,6 +535,11 @@ static struct nft_pipapo_elem *pipapo_get(const struct nft_pipapo_match *m,
  * @set:	nftables API set representation
  * @elem:	nftables API element representation containing key data
  * @flags:	Unused
+ *
+ * This function is called from the control plane path under
+ * RCU read lock.
+ *
+ * Return: set element private pointer or ERR_PTR(-ENOENT).
  */
 static struct nft_elem_priv *
 nft_pipapo_get(const struct net *net, const struct nft_set *set,

@@ -615,10 +550,9 @@ nft_pipapo_get(const struct net *net, const struct nft_set *set,
 	struct nft_pipapo_elem *e;
 
 	e = pipapo_get(m, (const u8 *)elem->key.val.data,
-		       nft_genmask_cur(net), get_jiffies_64(),
-		       GFP_ATOMIC);
-	if (IS_ERR(e))
-		return ERR_CAST(e);
+		       nft_genmask_cur(net), get_jiffies_64());
+	if (!e)
+		return ERR_PTR(-ENOENT);
 
 	return &e->priv;
 }

@@ -1343,8 +1277,8 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 	else
 		end = start;
 
-	dup = pipapo_get(m, start, genmask, tstamp, GFP_KERNEL);
-	if (!IS_ERR(dup)) {
+	dup = pipapo_get(m, start, genmask, tstamp);
+	if (dup) {
 		/* Check if we already have the same exact entry */
 		const struct nft_data *dup_key, *dup_end;
 

@@ -1363,15 +1297,9 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 		return -ENOTEMPTY;
 	}
 
-	if (PTR_ERR(dup) == -ENOENT) {
-		/* Look for partially overlapping entries */
-		dup = pipapo_get(m, end, nft_genmask_next(net), tstamp,
-				 GFP_KERNEL);
-	}
-
-	if (PTR_ERR(dup) != -ENOENT) {
-		if (IS_ERR(dup))
-			return PTR_ERR(dup);
+	/* Look for partially overlapping entries */
+	dup = pipapo_get(m, end, nft_genmask_next(net), tstamp);
+	if (dup) {
 		*elem_priv = &dup->priv;
 		return -ENOTEMPTY;
 	}

@@ -1913,8 +1841,8 @@ nft_pipapo_deactivate(const struct net *net, const struct nft_set *set,
 		return NULL;
 
 	e = pipapo_get(m, (const u8 *)elem->key.val.data,
-		       nft_genmask_next(net), nft_net_tstamp(net), GFP_KERNEL);
-	if (IS_ERR(e))
+		       nft_genmask_next(net), nft_net_tstamp(net));
+	if (!e)
 		return NULL;
 
 	nft_set_elem_change_active(net, set, &e->ext);

index 6c441e2dc8af3..2155c7f345c21 100644
@@ -1151,12 +1151,12 @@ nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 		       const u32 *key)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
+	const struct nft_set_ext *ext = NULL;
 	struct nft_pipapo_scratch *scratch;
 	u8 genmask = nft_genmask_cur(net);
 	const struct nft_pipapo_match *m;
 	const struct nft_pipapo_field *f;
 	const u8 *rp = (const u8 *)key;
-	const struct nft_set_ext *ext;
 	unsigned long *res, *fill;
 	bool map_index;
 	int i;

@@ -1247,13 +1247,13 @@ nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 			goto out;
 
 		if (last) {
-			ext = &f->mt[ret].e->ext;
-			if (unlikely(nft_set_elem_expired(ext) ||
-				     !nft_set_elem_active(ext, genmask))) {
-				ext = NULL;
+			const struct nft_set_ext *e = &f->mt[ret].e->ext;
+
+			if (unlikely(nft_set_elem_expired(e) ||
+				     !nft_set_elem_active(e, genmask)))
 				goto next_match;
-			}
 
+			ext = e;
 			goto out;
 		}
 

index 1a19649c28511..fa6741b3205a6 100644
@@ -511,6 +511,23 @@ static struct nft_pipapo_elem *pipapo_get(const struct nft_pipapo_match *m,
  *
  * This function is called from the data path.  It will search for
  * an element matching the given key in the current active copy.
+ * Unlike other set types, this uses NFT_GENMASK_ANY instead of
+ * nft_genmask_cur().
+ *
+ * This is because new (future) elements are not reachable from
+ * priv->match, they get added to priv->clone instead.
+ * When the commit phase flips the generation bitmask, the
+ * 'now old' entries are skipped but without the 'now current'
+ * elements becoming visible. Using nft_genmask_cur() thus creates
+ * inconsistent state: matching old entries get skipped but thew
+ * newly matching entries are unreachable.
+ *
+ * GENMASK will still find the 'now old' entries which ensures consistent
+ * priv->match view.
+ *
+ * nft_pipapo_commit swaps ->clone and ->match shortly after the
+ * genbit flip.  As ->clone doesn't contain the old entries in the first
+ * place, lookup will only find the now-current ones.
  *
  * Return: ntables API extension pointer or NULL if no match.
  */

@@ -519,12 +536,11 @@ nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 		  const u32 *key)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
-	u8 genmask = nft_genmask_cur(net);
 	const struct nft_pipapo_match *m;
 	const struct nft_pipapo_elem *e;
 
 	m = rcu_dereference(priv->match);
-	e = pipapo_get(m, (const u8 *)key, genmask, get_jiffies_64());
+	e = pipapo_get(m, (const u8 *)key, NFT_GENMASK_ANY, get_jiffies_64());
 
 	return e ? &e->ext : NULL;
 }

index 2155c7f345c21..39e356c9687a9 100644
@@ -1153,7 +1153,6 @@ nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 	struct nft_pipapo *priv = nft_set_priv(set);
 	const struct nft_set_ext *ext = NULL;
 	struct nft_pipapo_scratch *scratch;
-	u8 genmask = nft_genmask_cur(net);
 	const struct nft_pipapo_match *m;
 	const struct nft_pipapo_field *f;
 	const u8 *rp = (const u8 *)key;

@@ -1249,8 +1248,7 @@ nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 		if (last) {
 			const struct nft_set_ext *e = &f->mt[ret].e->ext;
 
-			if (unlikely(nft_set_elem_expired(e) ||
-				     !nft_set_elem_active(e, genmask)))
+			if (unlikely(nft_set_elem_expired(e)))
 				goto next_match;
 
 			ext = e;

index 938a257c069e2..b1f04168ec937 100644
@@ -77,7 +77,9 @@ __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
 			    nft_rbtree_interval_end(rbe) &&
 			    nft_rbtree_interval_start(interval))
 				continue;
-			interval = rbe;
+			if (nft_set_elem_active(&rbe->ext, genmask) &&
+			    !nft_rbtree_elem_expired(rbe))
+				interval = rbe;
 		} else if (d > 0)
 			parent = rcu_dereference_raw(parent->rb_right);
 		else {

@@ -102,8 +104,6 @@ __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
 	}
 
 	if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
-	    nft_set_elem_active(&interval->ext, genmask) &&
-	    !nft_rbtree_elem_expired(interval) &&
 	    nft_rbtree_interval_start(interval))
 		return &interval->ext;
 

index 0e86434ca13b0..3a443765d7e90 100644
@@ -1153,9 +1153,9 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
 {
 	struct nlmsghdr *nlh;
 
-	event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
-	nlh = nfnl_msg_put(skb, portid, seq, event, flags, family,
-			   NFNETLINK_V0, nft_base_seq(net));
+	nlh = nfnl_msg_put(skb, portid, seq,
+			   nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
+			   flags, family, NFNETLINK_V0, nft_base_seq(net));
 	if (!nlh)
 		goto nla_put_failure;
 

@@ -1165,6 +1165,12 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
 			 NFTA_TABLE_PAD))
 		goto nla_put_failure;
 
+	if (event == NFT_MSG_DELTABLE ||
+	    event == NFT_MSG_DESTROYTABLE) {
+		nlmsg_end(skb, nlh);
+		return 0;
+	}
+
 	if (nla_put_be32(skb, NFTA_TABLE_FLAGS,
 			 htonl(table->flags & NFT_TABLE_F_MASK)))
 		goto nla_put_failure;

@@ -2022,9 +2028,9 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
 {
 	struct nlmsghdr *nlh;
 
-	event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
-	nlh = nfnl_msg_put(skb, portid, seq, event, flags, family,
-			   NFNETLINK_V0, nft_base_seq(net));
+	nlh = nfnl_msg_put(skb, portid, seq,
+			   nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
+			   flags, family, NFNETLINK_V0, nft_base_seq(net));
 	if (!nlh)
 		goto nla_put_failure;
 

@@ -2034,6 +2040,13 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
 			 NFTA_CHAIN_PAD))
 		goto nla_put_failure;
 
+	if (!hook_list &&
+	    (event == NFT_MSG_DELCHAIN ||
+	     event == NFT_MSG_DESTROYCHAIN)) {
+		nlmsg_end(skb, nlh);
+		return 0;
+	}
+
 	if (nft_is_base_chain(chain)) {
 		const struct nft_base_chain *basechain = nft_base_chain(chain);
 		struct nft_stats __percpu *stats;

@@ -4871,9 +4884,10 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 	u32 seq = ctx->seq;
 	int i;
 
-	event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
-	nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family,
-			   NFNETLINK_V0, nft_base_seq(ctx->net));
+	nlh = nfnl_msg_put(skb, portid, seq,
+			   nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
+			   flags, ctx->family, NFNETLINK_V0,
+			   nft_base_seq(ctx->net));
 	if (!nlh)
 		goto nla_put_failure;
 

@@ -4885,6 +4899,12 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 			 NFTA_SET_PAD))
 		goto nla_put_failure;
 
+	if (event == NFT_MSG_DELSET ||
+	    event == NFT_MSG_DESTROYSET) {
+		nlmsg_end(skb, nlh);
+		return 0;
+	}
+
 	if (set->flags != 0)
 		if (nla_put_be32(skb, NFTA_SET_FLAGS, htonl(set->flags)))
 			goto nla_put_failure;

@@ -8359,20 +8379,26 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net,
 {
 	struct nlmsghdr *nlh;
 
-	event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
-	nlh = nfnl_msg_put(skb, portid, seq, event, flags, family,
-			   NFNETLINK_V0, nft_base_seq(net));
+	nlh = nfnl_msg_put(skb, portid, seq,
+			   nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
+			   flags, family, NFNETLINK_V0, nft_base_seq(net));
 	if (!nlh)
 		goto nla_put_failure;
 
 	if (nla_put_string(skb, NFTA_OBJ_TABLE, table->name) ||
 	    nla_put_string(skb, NFTA_OBJ_NAME, obj->key.name) ||
+	    nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->ops->type->type)) ||
 	    nla_put_be64(skb, NFTA_OBJ_HANDLE, cpu_to_be64(obj->handle),
 			 NFTA_OBJ_PAD))
 		goto nla_put_failure;
 
-	if (nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->ops->type->type)) ||
-	    nla_put_be32(skb, NFTA_OBJ_USE, htonl(obj->use)) ||
+	if (event == NFT_MSG_DELOBJ ||
+	    event == NFT_MSG_DESTROYOBJ) {
+		nlmsg_end(skb, nlh);
+		return 0;
+	}
+
+	if (nla_put_be32(skb, NFTA_OBJ_USE, htonl(obj->use)) ||
 	    nft_object_dump(skb, NFTA_OBJ_DATA, obj, reset))
 		goto nla_put_failure;
 

@@ -9413,9 +9439,9 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
 	struct nft_hook *hook;
 	struct nlmsghdr *nlh;
 
-	event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
-	nlh = nfnl_msg_put(skb, portid, seq, event, flags, family,
-			   NFNETLINK_V0, nft_base_seq(net));
+	nlh = nfnl_msg_put(skb, portid, seq,
+			   nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
+			   flags, family, NFNETLINK_V0, nft_base_seq(net));
 	if (!nlh)
 		goto nla_put_failure;
 

@@ -9425,6 +9451,13 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
 			 NFTA_FLOWTABLE_PAD))
 		goto nla_put_failure;
 
+	if (!hook_list &&
+	    (event == NFT_MSG_DELFLOWTABLE ||
+	     event == NFT_MSG_DESTROYFLOWTABLE)) {
+		nlmsg_end(skb, nlh);
+		return 0;
+	}
+
 	if (nla_put_be32(skb, NFTA_FLOWTABLE_USE, htonl(flowtable->use)) ||
 	    nla_put_be32(skb, NFTA_FLOWTABLE_FLAGS, htonl(flowtable->data.flags)))
 		goto nla_put_failure;

index cf65703e221fa..16daeac2ac555 100644
@@ -1916,7 +1916,6 @@ struct nftables_pernet {
 	struct mutex		commit_mutex;
 	u64			table_handle;
 	u64			tstamp;
-	unsigned int		base_seq;
 	unsigned int		gc_seq;
 	u8			validate_state;
 	struct work_struct	destroy_work;

index cc8060c017d5f..99dd166c5d07c 100644
@@ -3,6 +3,7 @@
 #define _NETNS_NFTABLES_H_
 
 struct netns_nftables {
+	unsigned int		base_seq;
 	u8			gencursor;
 };
 

235 lines not on this page · raw message

index 6a52fb97b8443..04699eac5b524 100644
@@ -109,17 +109,11 @@ nft_hash_lookup_fast(const struct net *net, const struct nft_set *set,
 const struct nft_set_ext *
 nft_hash_lookup(const struct net *net, const struct nft_set *set,
 		const u32 *key);
+#endif
+
 const struct nft_set_ext *
 nft_set_do_lookup(const struct net *net, const struct nft_set *set,
 		  const u32 *key);
-#else
-static inline const struct nft_set_ext *
-nft_set_do_lookup(const struct net *net, const struct nft_set *set,
-		  const u32 *key)
-{
-	return set->ops->lookup(net, set, key);
-}
-#endif
 
 /* called from nft_pipapo_avx2.c */
 const struct nft_set_ext *

index 40c602ffbcba7..2c6909bf1b407 100644
@@ -24,11 +24,11 @@ struct nft_lookup {
 	struct nft_set_binding		binding;
 };
 
-#ifdef CONFIG_MITIGATION_RETPOLINE
-const struct nft_set_ext *
-nft_set_do_lookup(const struct net *net, const struct nft_set *set,
-		  const u32 *key)
+static const struct nft_set_ext *
+__nft_set_do_lookup(const struct net *net, const struct nft_set *set,
+		    const u32 *key)
 {
+#ifdef CONFIG_MITIGATION_RETPOLINE
 	if (set->ops == &nft_set_hash_fast_type.ops)
 		return nft_hash_lookup_fast(net, set, key);
 	if (set->ops == &nft_set_hash_type.ops)

@@ -51,10 +51,17 @@ nft_set_do_lookup(const struct net *net, const struct nft_set *set,
 		return nft_rbtree_lookup(net, set, key);
 
 	WARN_ON_ONCE(1);
+#endif
 	return set->ops->lookup(net, set, key);
 }
+
+const struct nft_set_ext *
+nft_set_do_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key)
+{
+	return __nft_set_do_lookup(net, set, key);
+}
 EXPORT_SYMBOL_GPL(nft_set_do_lookup);
-#endif
 
 void nft_lookup_eval(const struct nft_expr *expr,
 		     struct nft_regs *regs,

index 5ea7a015504bb..cde63e5f18d8f 100644
@@ -10971,7 +10971,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 	while (++base_seq == 0)
 		;
 
-	WRITE_ONCE(net->nft.base_seq, base_seq);
+	/* pairs with smp_load_acquire in nft_lookup_eval */
+	smp_store_release(&net->nft.base_seq, base_seq);
 
 	gc_seq = nft_gc_seq_begin(nft_net);
 

index 2c6909bf1b407..58c5b14889c47 100644
@@ -55,11 +55,40 @@ __nft_set_do_lookup(const struct net *net, const struct nft_set *set,
 	return set->ops->lookup(net, set, key);
 }
 
+static unsigned int nft_base_seq(const struct net *net)
+{
+	/* pairs with smp_store_release() in nf_tables_commit() */
+	return smp_load_acquire(&net->nft.base_seq);
+}
+
+static bool nft_lookup_should_retry(const struct net *net, unsigned int seq)
+{
+	return unlikely(seq != nft_base_seq(net));
+}
+
 const struct nft_set_ext *
 nft_set_do_lookup(const struct net *net, const struct nft_set *set,
 		  const u32 *key)
 {
-	return __nft_set_do_lookup(net, set, key);
+	const struct nft_set_ext *ext;
+	unsigned int base_seq;
+
+	do {
+		base_seq = nft_base_seq(net);
+
+		ext = __nft_set_do_lookup(net, set, key);
+		if (ext)
+			break;
+		/* No match?  There is a small chance that lookup was
+		 * performed in the old generation, but nf_tables_commit()
+		 * already unlinked a (matching) element.
+		 *
+		 * We need to repeat the lookup to make sure that we didn't
+		 * miss a matching element in the new generation.
+		 */
+	} while (nft_lookup_should_retry(net, base_seq));
+
+	return ext;
 }
 EXPORT_SYMBOL_GPL(nft_set_do_lookup);
 

index 88657255fec12..bce7b4061ce08 100644
@@ -49,7 +49,7 @@ static bool hsr_check_carrier(struct hsr_port *master)
 
 	ASSERT_RTNL();
 
-	hsr_for_each_port(master->hsr, port) {
+	hsr_for_each_port_rtnl(master->hsr, port) {
 		if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) {
 			netif_carrier_on(master->dev);
 			return true;

@@ -105,7 +105,7 @@ int hsr_get_max_mtu(struct hsr_priv *hsr)
 	struct hsr_port *port;
 
 	mtu_max = ETH_DATA_LEN;
-	hsr_for_each_port(hsr, port)
+	hsr_for_each_port_rtnl(hsr, port)
 		if (port->type != HSR_PT_MASTER)
 			mtu_max = min(port->dev->mtu, mtu_max);
 

@@ -139,7 +139,7 @@ static int hsr_dev_open(struct net_device *dev)
 
 	hsr = netdev_priv(dev);
 
-	hsr_for_each_port(hsr, port) {
+	hsr_for_each_port_rtnl(hsr, port) {
 		if (port->type == HSR_PT_MASTER)
 			continue;
 		switch (port->type) {

@@ -172,7 +172,7 @@ static int hsr_dev_close(struct net_device *dev)
 	struct hsr_priv *hsr;
 
 	hsr = netdev_priv(dev);
-	hsr_for_each_port(hsr, port) {
+	hsr_for_each_port_rtnl(hsr, port) {
 		if (port->type == HSR_PT_MASTER)
 			continue;
 		switch (port->type) {

@@ -205,7 +205,7 @@ static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr,
 	 * may become enabled.
 	 */
 	features &= ~NETIF_F_ONE_FOR_ALL;
-	hsr_for_each_port(hsr, port)
+	hsr_for_each_port_rtnl(hsr, port)
 		features = netdev_increment_features(features,
 						     port->dev->features,
 						     mask);

@@ -484,7 +484,7 @@ static void hsr_set_rx_mode(struct net_device *dev)
 
 	hsr = netdev_priv(dev);
 
-	hsr_for_each_port(hsr, port) {
+	hsr_for_each_port_rtnl(hsr, port) {
 		if (port->type == HSR_PT_MASTER)
 			continue;
 		switch (port->type) {

@@ -506,7 +506,7 @@ static void hsr_change_rx_flags(struct net_device *dev, int change)
 
 	hsr = netdev_priv(dev);
 
-	hsr_for_each_port(hsr, port) {
+	hsr_for_each_port_rtnl(hsr, port) {
 		if (port->type == HSR_PT_MASTER)
 			continue;
 		switch (port->type) {

@@ -534,7 +534,7 @@ static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev,
 
 	hsr = netdev_priv(dev);
 
-	hsr_for_each_port(hsr, port) {
+	hsr_for_each_port_rtnl(hsr, port) {
 		if (port->type == HSR_PT_MASTER ||
 		    port->type == HSR_PT_INTERLINK)
 			continue;

@@ -580,7 +580,7 @@ static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev,
 
 	hsr = netdev_priv(dev);
 
-	hsr_for_each_port(hsr, port) {
+	hsr_for_each_port_rtnl(hsr, port) {
 		switch (port->type) {
 		case HSR_PT_SLAVE_A:
 		case HSR_PT_SLAVE_B:

index 192893c3f2ec7..ac1eb1db1a52b 100644
@@ -22,7 +22,7 @@ static bool hsr_slave_empty(struct hsr_priv *hsr)
 {
 	struct hsr_port *port;
 
-	hsr_for_each_port(hsr, port)
+	hsr_for_each_port_rtnl(hsr, port)
 		if (port->type != HSR_PT_MASTER)
 			return false;
 	return true;

index 135ec5fce0196..33b0d2460c9bc 100644
@@ -224,6 +224,9 @@ struct hsr_priv {
 #define hsr_for_each_port(hsr, port) \
 	list_for_each_entry_rcu((port), &(hsr)->ports, port_list)
 
+#define hsr_for_each_port_rtnl(hsr, port) \
+	list_for_each_entry_rcu((port), &(hsr)->ports, port_list, lockdep_rtnl_is_held())
+
 struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt);
 
 /* Caller must ensure skb is a valid HSR frame */

index bce7b4061ce08..702da1f9aaa90 100644
@@ -226,6 +226,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct hsr_priv *hsr = netdev_priv(dev);
 	struct hsr_port *master;
 
+	rcu_read_lock();
 	master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
 	if (master) {
 		skb->dev = master->dev;

@@ -238,6 +239,8 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 		dev_core_stats_tx_dropped_inc(dev);
 		dev_kfree_skb_any(skb);
 	}
+	rcu_read_unlock();
+
 	return NETDEV_TX_OK;
 }
 

index ac1eb1db1a52b..bc94b07101d80 100644
@@ -134,7 +134,7 @@ struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt)
 {
 	struct hsr_port *port;
 
-	hsr_for_each_port(hsr, port)
+	hsr_for_each_port_rtnl(hsr, port)
 		if (port->type == pt)
 			return port;
 	return NULL;

index f436d7cf565a1..1a9cc8206430b 100644
@@ -691,7 +691,7 @@ static void icssg_prueth_hsr_fdb_add_del(struct prueth_emac *emac,
 
 static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr)
 {
-	struct net_device *real_dev;
+	struct net_device *real_dev, *port_dev;
 	struct prueth_emac *emac;
 	u8 vlan_id, i;
 

@@ -700,11 +700,15 @@ static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr)
 
 	if (is_hsr_master(real_dev)) {
 		for (i = HSR_PT_SLAVE_A; i < HSR_PT_INTERLINK; i++) {
-			emac = netdev_priv(hsr_get_port_ndev(real_dev, i));
-			if (!emac)
+			port_dev = hsr_get_port_ndev(real_dev, i);
+			emac = netdev_priv(port_dev);
+			if (!emac) {
+				dev_put(port_dev);
 				return -EINVAL;
+			}
 			icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id,
 						     true);
+			dev_put(port_dev);
 		}
 	} else {
 		emac = netdev_priv(real_dev);

@@ -716,7 +720,7 @@ static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr)
 
 static int icssg_prueth_hsr_del_mcast(struct net_device *ndev, const u8 *addr)
 {
-	struct net_device *real_dev;
+	struct net_device *real_dev, *port_dev;
 	struct prueth_emac *emac;
 	u8 vlan_id, i;
 

@@ -725,11 +729,15 @@ static int icssg_prueth_hsr_del_mcast(struct net_device *ndev, const u8 *addr)
 
 	if (is_hsr_master(real_dev)) {
 		for (i = HSR_PT_SLAVE_A; i < HSR_PT_INTERLINK; i++) {
-			emac = netdev_priv(hsr_get_port_ndev(real_dev, i));
-			if (!emac)
+			port_dev = hsr_get_port_ndev(real_dev, i);
+			emac = netdev_priv(port_dev);
+			if (!emac) {
+				dev_put(port_dev);
 				return -EINVAL;
+			}
 			icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id,
 						     false);
+			dev_put(port_dev);
 		}
 	} else {
 		emac = netdev_priv(real_dev);

index 702da1f9aaa90..fbbc3ccf9df64 100644
@@ -675,9 +675,14 @@ struct net_device *hsr_get_port_ndev(struct net_device *ndev,
 	struct hsr_priv *hsr = netdev_priv(ndev);
 	struct hsr_port *port;
 
+	rcu_read_lock();
 	hsr_for_each_port(hsr, port)
-		if (port->type == pt)
+		if (port->type == pt) {
+			dev_hold(port->dev);
+			rcu_read_unlock();
 			return port->dev;
+		}
+	rcu_read_unlock();
 	return NULL;
 }
 EXPORT_SYMBOL(hsr_get_port_ndev);

index d7493c2294ef2..3709fba42ebd8 100644
@@ -127,13 +127,13 @@ static int eusb2_repeater_init(struct phy *phy)
 			     rptr->cfg->init_tbl[i].value);
 
 	/* Override registers from devicetree values */
-	if (!of_property_read_u8(np, "qcom,tune-usb2-amplitude", &val))
+	if (!of_property_read_u8(np, "qcom,tune-usb2-preem", &val))
 		regmap_write(regmap, base + EUSB2_TUNE_USB2_PREEM, val);
 
 	if (!of_property_read_u8(np, "qcom,tune-usb2-disc-thres", &val))
 		regmap_write(regmap, base + EUSB2_TUNE_HSDISC, val);
 
-	if (!of_property_read_u8(np, "qcom,tune-usb2-preem", &val))
+	if (!of_property_read_u8(np, "qcom,tune-usb2-amplitude", &val))
 		regmap_write(regmap, base + EUSB2_TUNE_IUSB2, val);
 
 	/* Wait for status OK */